build-appliance-image: Update to fido head revision

(From OE-Core rev: f0873b83d693af4a103999160d67fcf25c7eedc1)

Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

.gitignore

@@ -8,7 +8,7 @@ scripts/oe-git-proxy-socks
 sources/
 meta-*/
 !meta-skeleton
-!meta-hob
+!meta-selftest
 hob-image-*.bb
 *.swp
 *.orig

README

@@ -30,20 +30,29 @@ For information about OpenEmbedded, see the OpenEmbedded website:
 Where to Send Patches
 =====================
 
-As Poky is an integration repository, patches against the various components
-should be sent to their respective upstreams.
+As Poky is an integration repository (built using a tool called combo-layer),
+patches against the various components should be sent to their respective
+upstreams:
 
 bitbake:
-    bitbake-devel@lists.openembedded.org
+    Git repository: http://git.openembedded.org/bitbake/
+    Mailing list: bitbake-devel@lists.openembedded.org
 
-meta-yocto:
-    poky@yoctoproject.org
+documentation:
+    Git repository: http://git.yoctoproject.org/cgit/cgit.cgi/yocto-docs/
+    Mailing list: yocto@yoctoproject.org
 
-Most everything else should be sent to the OpenEmbedded Core mailing list.  If
-in doubt, check the oe-core git repository for the content you intend to modify.
+meta-yocto(-bsp):
+    Git repository: http://git.yoctoproject.org/cgit/cgit.cgi/meta-yocto(-bsp)
+    Mailing list: poky@yoctoproject.org
+
+Everything else should be sent to the OpenEmbedded Core mailing list.  If in
+doubt, check the oe-core git repository for the content you intend to modify.
 Before sending, be sure the patches apply cleanly to the current oe-core git
 repository.
-    openembedded-core@lists.openembedded.org
 
-Note: The scripts directory should be treated with extra care as it is a mix
-      of oe-core and poky-specific files.
+    Git repository: http://git.openembedded.org/openembedded-core/
+    Mailing list: openembedded-core@lists.openembedded.org
+
+Note: The scripts directory should be treated with extra care as it is a mix of
+oe-core and poky-specific files.

README.hardware

@@ -52,6 +52,13 @@ The following boards are supported by the meta-yocto-bsp layer:
 For more information see the board's section below. The appropriate MACHINE
 variable value corresponding to the board is given in brackets.
 
+Reference Board Maintenance
+===========================
+
+Send pull requests, patches, comments or questions about meta-yocto-bsps to poky@yoctoproject.org
+
+Maintainers: Kevin Hao <kexin.hao@windriver.com>
+             Bruce Ashfield <bruce.ashfield@windriver.com>
 
 Consumer Devices
 ================
@@ -244,14 +251,14 @@ if used via a usb card reader):
   5. If using core-image-minimal rootfs, install the modules
      # tar x -C /media/root -f modules-beaglebone.tgz
 
-  6. If using core-image-minimal rootfs, install the kernel uImage into /boot
+  6. If using core-image-minimal rootfs, install the kernel zImage into /boot
      directory of rootfs
-     # cp uImage-beaglebone.bin /media/root/boot/uImage
+     # cp zImage-beaglebone.bin /media/root/boot/zImage
 
   7. If using core-image-minimal rootfs, also install device tree (DTB) files
      into /boot directory of rootfs
-     # cp uImage-am335x-bone.dtb /media/root/boot/am335x-bone.dtb
-     # cp uImage-am335x-boneblack.dtb /media/root/boot/am335x-boneblack.dtb
+     # cp zImage-am335x-bone.dtb /media/root/boot/am335x-bone.dtb
+     # cp zImage-am335x-boneblack.dtb /media/root/boot/am335x-boneblack.dtb
 
   8. Unmount the SD partitions, insert the SD card into the Beaglebone, and
      boot the Beaglebone
@@ -317,6 +324,22 @@ Load the kernel and dtb (device tree blob), and boot the system as follows:
  => tftp 2000000 uImage-mpc8315e-rdb.dtb
  => bootm 1000000 - 2000000
 
+--- Booting from JFFS2 root ---
+
+ 1. First boot the board with NFS root.
+
+ 2. Erase the MTD partition which will be used as root:
+
+    $ flash_eraseall  /dev/mtd3
+
+ 3. Copy the JFFS2 image to the MTD partition:
+
+    $ flashcp core-image-minimal-mpc8315e-rdb.jffs2 /dev/mtd3
+
+ 4. Then reboot the board and set up the environment in U-Boot:
+
+    => setenv bootargs root=/dev/mtdblock3 rootfstype=jffs2 console=ttyS0,115200
+
 
 Ubiquiti Networks EdgeRouter Lite (edgerouter)
 ==============================================
@@ -329,19 +352,22 @@ Setup instructions
 ------------------
 
 You will need the following:
-* NFS root setup on your workstation
-* TFTP server installed on your workstation
 * RJ45 -> serial ("rollover") cable connected from your PC to the CONSOLE
-  port on the board
+  port on the device
 * Ethernet connected to the first ethernet port on the board
 
+If using NFS as part of the setup process, you will also need:
+* NFS root setup on your workstation
+* TFTP server installed on your workstation (if fetching the kernel from
+  TFTP, see below).
+
 --- Preparation ---
 
 Build an image (e.g. core-image-minimal) using "edgerouter" as the MACHINE.
 In the following instruction it is based on core-image-minimal. Another target
 may be similiar with it.
 
---- Booting from NFS root ---
+--- Booting from NFS root / kernel via TFTP ---
 
 Load the kernel, and boot the system as follows:
 

bitbake/bin/bitbake

@@ -23,335 +23,22 @@
 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 
 import os
-import sys, logging
+import sys
+
 sys.path.insert(0, os.path.join(os.path.dirname(os.path.dirname(__file__)),
                                 'lib'))
-
-import optparse
-import warnings
-from traceback import format_exception
 try:
     import bb
 except RuntimeError as exc:
     sys.exit(str(exc))
-from bb import event
-import bb.msg
-from bb import cooker
-from bb import ui
-from bb import server
+
 from bb import cookerdata
-
-__version__ = "1.22.0"
-logger = logging.getLogger("BitBake")
-
-# Python multiprocessing requires /dev/shm
-if not os.access('/dev/shm', os.W_OK | os.X_OK):
-    sys.exit("FATAL: /dev/shm does not exist or is not writable")
-
-# Unbuffer stdout to avoid log truncation in the event
-# of an unorderly exit as well as to provide timely
-# updates to log files for use with tail
-try:
-    if sys.stdout.name == '<stdout>':
-        sys.stdout = os.fdopen(sys.stdout.fileno(), 'w', 0)
-except:
-    pass
-
-
-def get_ui(config):
-    if not config.ui:
-        # modify 'ui' attribute because it is also read by cooker
-        config.ui = os.environ.get('BITBAKE_UI', 'knotty')
-
-    interface = config.ui
-
-    try:
-        # Dynamically load the UI based on the ui name. Although we
-        # suggest a fixed set this allows you to have flexibility in which
-        # ones are available.
-        module = __import__("bb.ui", fromlist = [interface])
-        return getattr(module, interface)
-    except AttributeError:
-        sys.exit("FATAL: Invalid user interface '%s' specified.\n"
-                 "Valid interfaces: depexp, goggle, ncurses, hob, knotty [default]." % interface)
-
-
-# Display bitbake/OE warnings via the BitBake.Warnings logger, ignoring others"""
-warnlog = logging.getLogger("BitBake.Warnings")
-_warnings_showwarning = warnings.showwarning
-def _showwarning(message, category, filename, lineno, file=None, line=None):
-    if file is not None:
-        if _warnings_showwarning is not None:
-            _warnings_showwarning(message, category, filename, lineno, file, line)
-    else:
-        s = warnings.formatwarning(message, category, filename, lineno)
-        warnlog.warn(s)
-
-warnings.showwarning = _showwarning
-warnings.filterwarnings("ignore")
-warnings.filterwarnings("default", module="(<string>$|(oe|bb)\.)")
-warnings.filterwarnings("ignore", category=PendingDeprecationWarning)
-warnings.filterwarnings("ignore", category=ImportWarning)
-warnings.filterwarnings("ignore", category=DeprecationWarning, module="<string>$")
-warnings.filterwarnings("ignore", message="With-statements now directly support multiple context managers")
-
-class BitBakeConfigParameters(cookerdata.ConfigParameters):
-
-    def parseCommandLine(self):
-        parser = optparse.OptionParser(
-            version = "BitBake Build Tool Core version %s, %%prog version %s" % (bb.__version__, __version__),
-            usage = """%prog [options] [recipename/target ...]
-
-    Executes the specified task (default is 'build') for a given set of target recipes (.bb files).
-    It is assumed there is a conf/bblayers.conf available in cwd or in BBPATH which
-    will provide the layer, BBFILES and other configuration information.""")
-
-        parser.add_option("-b", "--buildfile", help = "Execute tasks from a specific .bb recipe directly. WARNING: Does not handle any dependencies from other recipes.",
-                   action = "store", dest = "buildfile", default = None)
-
-        parser.add_option("-k", "--continue", help = "Continue as much as possible after an error. While the target that failed and anything depending on it cannot be built, as much as possible will be built before stopping.",
-                   action = "store_false", dest = "abort", default = True)
-
-        parser.add_option("-a", "--tryaltconfigs", help = "Continue with builds by trying to use alternative providers where possible.",
-                   action = "store_true", dest = "tryaltconfigs", default = False)
-
-        parser.add_option("-f", "--force", help = "Force the specified targets/task to run (invalidating any existing stamp file).",
-                   action = "store_true", dest = "force", default = False)
-
-        parser.add_option("-c", "--cmd", help = "Specify the task to execute. The exact options available depend on the metadata. Some examples might be 'compile' or 'populate_sysroot' or 'listtasks' may give a list of the tasks available.",
-                   action = "store", dest = "cmd")
-
-        parser.add_option("-C", "--clear-stamp", help = "Invalidate the stamp for the specified task such as 'compile' and then run the default task for the specified target(s).",
-                    action = "store", dest = "invalidate_stamp")
-
-        parser.add_option("-r", "--read", help = "Read the specified file before bitbake.conf.",
-                   action = "append", dest = "prefile", default = [])
-
-        parser.add_option("-R", "--postread", help = "Read the specified file after bitbake.conf.",
-                          action = "append", dest = "postfile", default = [])
-
-        parser.add_option("-v", "--verbose", help = "Output more log message data to the terminal.",
-                   action = "store_true", dest = "verbose", default = False)
-
-        parser.add_option("-D", "--debug", help = "Increase the debug level. You can specify this more than once.",
-                   action = "count", dest="debug", default = 0)
-
-        parser.add_option("-n", "--dry-run", help = "Don't execute, just go through the motions.",
-                   action = "store_true", dest = "dry_run", default = False)
-
-        parser.add_option("-S", "--dump-signatures", help = "Dump out the signature construction information, with no task execution. Parameters are passed to the signature handling code, use 'none' if no specific handler is required.",
-                   action = "append", dest = "dump_signatures", default = [])
-
-        parser.add_option("-p", "--parse-only", help = "Quit after parsing the BB recipes.",
-                   action = "store_true", dest = "parse_only", default = False)
-
-        parser.add_option("-s", "--show-versions", help = "Show current and preferred versions of all recipes.",
-                   action = "store_true", dest = "show_versions", default = False)
-
-        parser.add_option("-e", "--environment", help = "Show the global or per-package environment complete with information about where variables were set/changed.",
-                   action = "store_true", dest = "show_environment", default = False)
-
-        parser.add_option("-g", "--graphviz", help = "Save dependency tree information for the specified targets in the dot syntax.",
-                    action = "store_true", dest = "dot_graph", default = False)
-
-        parser.add_option("-I", "--ignore-deps", help = """Assume these dependencies don't exist and are already provided (equivalent to ASSUME_PROVIDED). Useful to make dependency graphs more appealing""",
-                    action = "append", dest = "extra_assume_provided", default = [])
-
-        parser.add_option("-l", "--log-domains", help = """Show debug logging for the specified logging domains""",
-                    action = "append", dest = "debug_domains", default = [])
-
-        parser.add_option("-P", "--profile", help = "Profile the command and save reports.",
-                   action = "store_true", dest = "profile", default = False)
-
-        parser.add_option("-u", "--ui", help = "The user interface to use (e.g. knotty, hob, depexp).",
-                   action = "store", dest = "ui")
-
-        parser.add_option("-t", "--servertype", help = "Choose which server to use, process or xmlrpc.",
-                   action = "store", dest = "servertype")
-
-        parser.add_option("", "--revisions-changed", help = "Set the exit code depending on whether upstream floating revisions have changed or not.",
-                   action = "store_true", dest = "revisions_changed", default = False)
-
-        parser.add_option("", "--server-only", help = "Run bitbake without a UI, only starting a server (cooker) process.",
-                   action = "store_true", dest = "server_only", default = False)
-
-        parser.add_option("-B", "--bind", help = "The name/address for the bitbake server to bind to.",
-                   action = "store", dest = "bind", default = False)
-
-        parser.add_option("", "--no-setscene", help = "Do not run any setscene tasks. sstate will be ignored and everything needed, built.",
-                   action = "store_true", dest = "nosetscene", default = False)
-
-        parser.add_option("", "--remote-server", help = "Connect to the specified server.",
-                   action = "store", dest = "remote_server", default = False)
-
-        parser.add_option("-m", "--kill-server", help = "Terminate the remote server.",
-                    action = "store_true", dest = "kill_server", default = False)
-
-        parser.add_option("", "--observe-only", help = "Connect to a server as an observing-only client.",
-                   action = "store_true", dest = "observe_only", default = False)
-
-        parser.add_option("", "--status-only", help = "Check the status of the remote bitbake server.",
-                   action = "store_true", dest = "status_only", default = False)
-
-        options, targets = parser.parse_args(sys.argv)
-
-        # some environmental variables set also configuration options
-        if "BBSERVER" in os.environ:
-            options.servertype = "xmlrpc"
-            options.remote_server = os.environ["BBSERVER"]
-
-        return options, targets[1:]
-
-
-def start_server(servermodule, configParams, configuration, features):
-    server = servermodule.BitBakeServer()
-    if configParams.bind:
-        (host, port) = configParams.bind.split(':')
-        server.initServer((host, int(port)))
-        configuration.interface = [ server.serverImpl.host, server.serverImpl.port ]
-    else:
-        server.initServer()
-        configuration.interface = []
-
-    try:
-        configuration.setServerRegIdleCallback(server.getServerIdleCB())
-
-        cooker = bb.cooker.BBCooker(configuration, features)
-
-        server.addcooker(cooker)
-        server.saveConnectionDetails()
-    except Exception as e:
-        exc_info = sys.exc_info()
-        while hasattr(server, "event_queue"):
-            try:
-                import queue
-            except ImportError:
-                import Queue as queue
-            try:
-                event = server.event_queue.get(block=False)
-            except (queue.Empty, IOError):
-                break
-            if isinstance(event, logging.LogRecord):
-                logger.handle(event)
-        raise exc_info[1], None, exc_info[2]
-    server.detach()
-    return server
-
-
-
-def main():
-
-    configParams = BitBakeConfigParameters()
-    configuration = cookerdata.CookerConfiguration()
-    configuration.setConfigParameters(configParams)
-
-    ui_module = get_ui(configParams)
-
-    # Server type can be xmlrpc or process currently, if nothing is specified,
-    # the default server is process
-    if configParams.servertype:
-        server_type = configParams.servertype
-    else:
-        server_type = 'process'
-
-    try:
-        module = __import__("bb.server", fromlist = [server_type])
-        servermodule = getattr(module, server_type)
-    except AttributeError:
-        sys.exit("FATAL: Invalid server type '%s' specified.\n"
-                 "Valid interfaces: xmlrpc, process [default]." % server_type)
-
-    if configParams.server_only:
-        if configParams.servertype != "xmlrpc":
-            sys.exit("FATAL: If '--server-only' is defined, we must set the servertype as 'xmlrpc'.\n")
-        if not configParams.bind:
-            sys.exit("FATAL: The '--server-only' option requires a name/address to bind to with the -B option.\n")
-        if configParams.remote_server:
-            sys.exit("FATAL: The '--server-only' option conflicts with %s.\n" % 
-                ("the BBSERVER environment variable" if "BBSERVER" in os.environ else "the '--remote-server' option" ))
-
-    if configParams.bind and configParams.servertype != "xmlrpc":
-        sys.exit("FATAL: If '-B' or '--bind' is defined, we must set the servertype as 'xmlrpc'.\n")
-
-    if configParams.remote_server and configParams.servertype != "xmlrpc":
-        sys.exit("FATAL: If '--remote-server' is defined, we must set the servertype as 'xmlrpc'.\n")
-
-    if configParams.observe_only and (not configParams.remote_server or configParams.bind):
-        sys.exit("FATAL: '--observe-only' can only be used by UI clients connecting to a server.\n")
-
-    if "BBDEBUG" in os.environ:
-        level = int(os.environ["BBDEBUG"])
-        if level > configuration.debug:
-            configuration.debug = level
-
-    bb.msg.init_msgconfig(configParams.verbose, configuration.debug,
-                         configuration.debug_domains)
-
-    # Ensure logging messages get sent to the UI as events
-    handler = bb.event.LogHandler()
-    if not configParams.status_only:
-        # In status only mode there are no logs and no UI
-        logger.addHandler(handler)
-
-    # Clear away any spurious environment variables while we stoke up the cooker
-    cleanedvars = bb.utils.clean_environment()
-
-    featureset = []
-    if not configParams.server_only:
-        # Collect the feature set for the UI
-        featureset = getattr(ui_module, "featureSet", [])
-
-    if not configParams.remote_server:
-        # we start a server with a given configuration
-        server = start_server(servermodule, configParams, configuration, featureset)
-        bb.event.ui_queue = []
-    else:
-        # we start a stub server that is actually a XMLRPClient that connects to a real server
-        server = servermodule.BitBakeXMLRPCClient(configParams.observe_only)
-        server.saveConnectionDetails(configParams.remote_server)
-        server.saveConnectionConfigParams(configParams)
-
-    if not configParams.server_only:
-        if configParams.status_only:
-            try:
-                server_connection = server.establishConnection(featureset)
-            except:
-                sys.exit(1)
-            if not server_connection:
-                sys.exit(1)
-            server_connection.terminate()
-            sys.exit(0)
-
-        # Setup a connection to the server (cooker)
-        server_connection = server.establishConnection(featureset)
-        if not server_connection:
-            if configParams.kill_server:
-                bb.fatal("Server already killed")
-            configParams.bind = configParams.remote_server
-            start_server(servermodule, configParams, configuration, featureset)
-            bb.event.ui_queue = []
-            server_connection = server.establishConnection(featureset)
-
-        # Restore the environment in case the UI needs it
-        for k in cleanedvars:
-            os.environ[k] = cleanedvars[k]
-
-        logger.removeHandler(handler)
-
-        try:
-            return ui_module.main(server_connection.connection, server_connection.events, configParams)
-        finally:
-            bb.event.ui_queue = []
-            server_connection.terminate()
-    else:
-        print("server address: %s, server port: %s" % (server.serverImpl.host, server.serverImpl.port))
-        return 0
-
-    return 1
+from bb.main import bitbake_main, BitBakeConfigParameters
 
 if __name__ == "__main__":
     try:
-        ret = main()
+        ret = bitbake_main(BitBakeConfigParameters(sys.argv),
+                           cookerdata.CookerConfiguration())
     except bb.BBHandledException:
         ret = 1
     except Exception:

bitbake/bin/bitbake-diffsigs

@@ -46,6 +46,12 @@ logger = logger_create('bitbake-diffsigs')
 def find_compare_task(bbhandler, pn, taskname):
     """ Find the most recent signature files for the specified PN/task and compare them """
 
+    def get_hashval(siginfo):
+        if siginfo.endswith('.siginfo'):
+            return siginfo.rpartition(':')[2].partition('_')[0]
+        else:
+            return siginfo.rpartition('.')[2]
+
     if not hasattr(bb.siggen, 'find_siginfo'):
         logger.error('Metadata does not support finding signature data files')
         sys.exit(1)
@@ -54,7 +60,7 @@ def find_compare_task(bbhandler, pn, taskname):
         taskname = 'do_%s' % taskname
 
     filedates = bb.siggen.find_siginfo(pn, taskname, None, bbhandler.config_data)
-    latestfiles = sorted(filedates.keys(), key=lambda f: filedates[f])[-2:]
+    latestfiles = sorted(filedates.keys(), key=lambda f: filedates[f])[-3:]
     if not latestfiles:
         logger.error('No sigdata files found matching %s %s' % (pn, taskname))
         sys.exit(1)
@@ -62,6 +68,16 @@ def find_compare_task(bbhandler, pn, taskname):
         logger.error('Only one matching sigdata file found for the specified task (%s %s)' % (pn, taskname))
         sys.exit(1)
     else:
+        # It's possible that latestfiles contain 3 elements and the first two have the same hash value.
+        # In this case, we delete the second element.
+        # The above case is actually the most common one. Because we may have sigdata file and siginfo
+        # file having the same hash value. Comparing such two files makes no sense.
+        if len(latestfiles) == 3:
+            hash0 = get_hashval(latestfiles[0])
+            hash1 = get_hashval(latestfiles[1])
+            if hash0 == hash1:
+                latestfiles.pop(1)
+
         # Define recursion callback
         def recursecb(key, hash1, hash2):
             hashes = [hash1, hash2]
@@ -118,5 +134,5 @@ else:
             logger.error('Invalid signature data - ensure you are specifying sigdata/siginfo files')
             sys.exit(1)
 
-    if output:
-        print '\n'.join(output)
+        if output:
+            print '\n'.join(output)

bitbake/bin/bitbake-layers

@@ -5,7 +5,7 @@
 # See the help output for details on available commands.
 
 # Copyright (C) 2011 Mentor Graphics Corporation
-# Copyright (C) 2012 Intel Corporation
+# Copyright (C) 2011-2015 Intel Corporation
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License version 2 as
@@ -20,13 +20,15 @@
 # with this program; if not, write to the Free Software Foundation, Inc.,
 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 
-import cmd
 import logging
 import os
 import sys
 import fnmatch
 from collections import defaultdict
+import argparse
 import re
+import httplib, urlparse, json
+import subprocess
 
 bindir = os.path.dirname(__file__)
 topdir = os.path.dirname(bindir)
@@ -39,26 +41,24 @@ import bb.utils
 import bb.tinfoil
 
 
-logger = logging.getLogger('BitBake')
+def logger_create(name, output=sys.stderr):
+    logger = logging.getLogger(name)
+    console = logging.StreamHandler(output)
+    format = bb.msg.BBLogFormatter("%(levelname)s: %(message)s")
+    if output.isatty():
+        format.enable_color()
+    console.setFormatter(format)
+    logger.addHandler(console)
+    logger.setLevel(logging.INFO)
+    return logger
+
+logger = logger_create('bitbake-layers', sys.stdout)
 
 
-def main(args):
-    cmds = Commands()
-    if args:
-        # Allow user to specify e.g. show-layers instead of show_layers
-        args = [args[0].replace('-', '_')] + args[1:]
-        cmds.onecmd(' '.join(args))
-    else:
-        cmds.do_help('')
-    return cmds.returncode
-
-
-class Commands(cmd.Cmd):
+class Commands():
     def __init__(self):
         self.bbhandler = None
-        self.returncode = 0
         self.bblayers = []
-        cmd.Cmd.__init__(self)
 
     def init_bbhandler(self, config_only = False):
         if not self.bbhandler:
@@ -66,27 +66,6 @@ class Commands(cmd.Cmd):
             self.bblayers = (self.bbhandler.config_data.getVar('BBLAYERS', True) or "").split()
             self.bbhandler.prepare(config_only)
 
-    def default(self, line):
-        """Handle unrecognised commands"""
-        sys.stderr.write("Unrecognised command or option\n")
-        self.do_help('')
-
-    def do_help(self, topic):
-        """display general help or help on a specified command"""
-        if topic:
-            sys.stdout.write('%s: ' % topic)
-            cmd.Cmd.do_help(self, topic.replace('-', '_'))
-        else:
-            sys.stdout.write("usage: bitbake-layers <command> [arguments]\n\n")
-            sys.stdout.write("Available commands:\n")
-            procnames = list(set(self.get_names()))
-            for procname in procnames:
-                if procname[:3] == 'do_':
-                    sys.stdout.write("  %s\n" % procname[3:].replace('_', '-'))
-                    doc = getattr(self, procname).__doc__
-                    if doc:
-                        sys.stdout.write("    %s\n" % doc.splitlines()[0])
-
     def do_show_layers(self, args):
         """show current configured layers"""
         self.init_bbhandler(config_only = True)
@@ -103,6 +82,293 @@ class Commands(cmd.Cmd):
             logger.plain("%s  %s  %d" % (layername.ljust(20), layerdir.ljust(40), layerpri))
 
 
+    def do_add_layer(self, args):
+        """Add a layer to bblayers.conf
+
+Adds the specified layer to bblayers.conf
+"""
+        layerdir = os.path.abspath(args.layerdir)
+        if not os.path.exists(layerdir):
+            sys.stderr.write("Specified layer directory doesn't exist\n")
+            return 1
+
+        layer_conf = os.path.join(layerdir, 'conf', 'layer.conf')
+        if not os.path.exists(layer_conf):
+            sys.stderr.write("Specified layer directory doesn't contain a conf/layer.conf file\n")
+            return 1
+
+        bblayers_conf = os.path.join('conf', 'bblayers.conf')
+        if not os.path.exists(bblayers_conf):
+            sys.stderr.write("Unable to find bblayers.conf\n")
+            return 1
+
+        (notadded, _) = bb.utils.edit_bblayers_conf(bblayers_conf, layerdir, None)
+        if notadded:
+            for item in notadded:
+                sys.stderr.write("Specified layer %s is already in BBLAYERS\n" % item)
+
+
+    def do_remove_layer(self, args):
+        """Remove a layer from bblayers.conf
+
+Removes the specified layer from bblayers.conf
+"""
+        bblayers_conf = os.path.join('conf', 'bblayers.conf')
+        if not os.path.exists(bblayers_conf):
+            sys.stderr.write("Unable to find bblayers.conf\n")
+            return 1
+
+        if args.layerdir.startswith('*'):
+            layerdir = args.layerdir
+        else:
+            layerdir = os.path.abspath(args.layerdir)
+        (_, notremoved) = bb.utils.edit_bblayers_conf(bblayers_conf, None, layerdir)
+        if notremoved:
+            for item in notremoved:
+                sys.stderr.write("No layers matching %s found in BBLAYERS\n" % item)
+            return 1
+
+
+    def get_json_data(self, apiurl):
+        proxy_settings = os.environ.get("http_proxy", None)
+        conn = None
+        _parsedurl = urlparse.urlparse(apiurl)
+        path = _parsedurl.path
+        query = _parsedurl.query
+        def parse_url(url):
+            parsedurl = urlparse.urlparse(url)
+            if parsedurl.netloc[0] == '[':
+                host, port = parsedurl.netloc[1:].split(']', 1)
+                if ':' in port:
+                    port = port.rsplit(':', 1)[1]
+                else:
+                    port = None
+            else:
+                if parsedurl.netloc.count(':') == 1:
+                    (host, port) = parsedurl.netloc.split(":")
+                else:
+                    host = parsedurl.netloc
+                    port = None
+            return (host, 80 if port is None else int(port))
+
+        if proxy_settings is None:
+            host, port = parse_url(apiurl)
+            conn = httplib.HTTPConnection(host, port)
+            conn.request("GET", path + "?" + query)
+        else:
+            host, port = parse_url(proxy_settings)
+            conn = httplib.HTTPConnection(host, port)
+            conn.request("GET", apiurl)
+
+        r = conn.getresponse()
+        if r.status != 200:
+            raise Exception("Failed to read " + path + ": %d %s" % (r.status, r.reason))
+        return json.loads(r.read())
+
+
+    def get_layer_deps(self, layername, layeritems, layerbranches, layerdependencies, branchnum, selfname=False):
+        def layeritems_info_id(items_name, layeritems):
+            litems_id = None
+            for li in layeritems:
+                if li['name'] == items_name:
+                    litems_id = li['id']
+                    break
+            return litems_id
+
+        def layerbranches_info(items_id, layerbranches):
+            lbranch = {}
+            for lb in layerbranches:
+                if lb['layer'] == items_id and lb['branch'] == branchnum:
+                    lbranch['id'] = lb['id']
+                    lbranch['vcs_subdir'] = lb['vcs_subdir']
+                    break
+            return lbranch
+
+        def layerdependencies_info(lb_id, layerdependencies):
+            ld_deps = []
+            for ld in layerdependencies:
+                if ld['layerbranch'] == lb_id and not ld['dependency'] in ld_deps:
+                    ld_deps.append(ld['dependency'])
+            if not ld_deps:
+                logger.error("The dependency of layerDependencies is not found.")
+            return ld_deps
+
+        def layeritems_info_name_subdir(items_id, layeritems):
+            litems = {}
+            for li in layeritems:
+                if li['id'] == items_id:
+                    litems['vcs_url'] = li['vcs_url']
+                    litems['name'] = li['name']
+                    break
+            return litems
+
+        if selfname:
+            selfid = layeritems_info_id(layername, layeritems)
+            lbinfo = layerbranches_info(selfid, layerbranches)
+            if lbinfo:
+                selfsubdir = lbinfo['vcs_subdir']
+            else:
+                logger.error("%s is not found in the specified branch" % layername)
+                return
+            selfurl = layeritems_info_name_subdir(selfid, layeritems)['vcs_url']
+            if selfurl:
+                return selfurl, selfsubdir
+            else:
+                logger.error("Cannot get layer %s git repo and subdir" % layername)
+                return
+        ldict = {}
+        itemsid = layeritems_info_id(layername, layeritems)
+        if not itemsid:
+            return layername, None
+        lbid = layerbranches_info(itemsid, layerbranches)
+        if lbid:
+            lbid = layerbranches_info(itemsid, layerbranches)['id']
+        else:
+            logger.error("%s is not found in the specified branch" % layername)
+            return None, None
+        for dependency in layerdependencies_info(lbid, layerdependencies):
+            lname = layeritems_info_name_subdir(dependency, layeritems)['name']
+            lurl = layeritems_info_name_subdir(dependency, layeritems)['vcs_url']
+            lsubdir = layerbranches_info(dependency, layerbranches)['vcs_subdir']
+            ldict[lname] = lurl, lsubdir
+        return None, ldict
+
+
+    def get_fetch_layer(self, fetchdir, url, subdir, fetch_layer):
+        layername = self.get_layer_name(url)
+        if os.path.splitext(layername)[1] == '.git':
+            layername = os.path.splitext(layername)[0]
+        repodir = os.path.join(fetchdir, layername)
+        layerdir = os.path.join(repodir, subdir)
+        if not os.path.exists(repodir):
+            if fetch_layer:
+                result = subprocess.call('git clone %s %s' % (url, repodir), shell = True)
+                if result:
+                    logger.error("Failed to download %s" % url)
+                    return None, None
+                else:
+                    return layername, layerdir
+            else:
+                logger.plain("Repository %s needs to be fetched" % url)
+                return layername, layerdir
+        elif os.path.exists(layerdir):
+            return layername, layerdir
+        else:
+            logger.error("%s is not in %s" % (url, subdir))
+        return None, None
+
+
+    def do_layerindex_fetch(self, args):
+        """Fetches a layer from a layer index along with its dependent layers, and adds them to conf/bblayers.conf.
+"""
+        self.init_bbhandler(config_only = True)
+        apiurl = self.bbhandler.config_data.getVar('BBLAYERS_LAYERINDEX_URL', True)
+        if not apiurl:
+            logger.error("Cannot get BBLAYERS_LAYERINDEX_URL")
+        else:
+            if apiurl[-1] != '/':
+                apiurl += '/'
+            apiurl += "api/"
+        apilinks = self.get_json_data(apiurl)
+        branches = self.get_json_data(apilinks['branches'])
+
+        branchnum = 0
+        for branch in branches:
+            if branch['name'] == args.branch:
+                branchnum = branch['id']
+                break
+        if branchnum == 0:
+            validbranches = ', '.join([branch['name'] for branch in branches])
+            logger.error('Invalid layer branch name "%s". Valid branches: %s' % (args.branch, validbranches))
+            return 1
+
+        ignore_layers = []
+        for collection in self.bbhandler.config_data.getVar('BBFILE_COLLECTIONS', True).split():
+            lname = self.bbhandler.config_data.getVar('BBLAYERS_LAYERINDEX_NAME_%s' % collection, True)
+            if lname:
+                ignore_layers.append(lname)
+
+        if args.ignore:
+            ignore_layers.extend(args.ignore.split(','))
+
+        layeritems = self.get_json_data(apilinks['layerItems'])
+        layerbranches = self.get_json_data(apilinks['layerBranches'])
+        layerdependencies = self.get_json_data(apilinks['layerDependencies'])
+        invaluenames = []
+        repourls = {}
+        printlayers = []
+        def query_dependencies(layers, layeritems, layerbranches, layerdependencies, branchnum):
+            depslayer = []
+            for layername in layers:
+                invaluename, layerdict = self.get_layer_deps(layername, layeritems, layerbranches, layerdependencies, branchnum)
+                if layerdict:
+                    repourls[layername] = self.get_layer_deps(layername, layeritems, layerbranches, layerdependencies, branchnum, selfname=True)
+                    for layer in layerdict:
+                        if not layer in ignore_layers:
+                            depslayer.append(layer)
+                        printlayers.append((layername, layer, layerdict[layer][0], layerdict[layer][1]))
+                        if not layer in ignore_layers and not layer in repourls:
+                            repourls[layer] = (layerdict[layer][0], layerdict[layer][1])
+                if invaluename and not invaluename in invaluenames:
+                    invaluenames.append(invaluename)
+            return depslayer
+
+        depslayers = query_dependencies(args.layername, layeritems, layerbranches, layerdependencies, branchnum)
+        while depslayers:
+            depslayer = query_dependencies(depslayers, layeritems, layerbranches, layerdependencies, branchnum)
+            depslayers = depslayer
+        if invaluenames:
+            for invaluename in invaluenames:
+                logger.error('Layer "%s" not found in layer index' % invaluename)
+            return 1
+        logger.plain("%s  %s  %s  %s" % ("Layer".ljust(19), "Required by".ljust(19), "Git repository".ljust(54), "Subdirectory"))
+        logger.plain('=' * 115)
+        for layername in args.layername:
+            layerurl = repourls[layername]
+            logger.plain("%s %s %s %s" % (layername.ljust(20), '-'.ljust(20), layerurl[0].ljust(55), layerurl[1]))
+        printedlayers = []
+        for layer, dependency, gitrepo, subdirectory in printlayers:
+            if dependency in printedlayers:
+                continue
+            logger.plain("%s %s %s %s" % (dependency.ljust(20), layer.ljust(20), gitrepo.ljust(55), subdirectory))
+            printedlayers.append(dependency)
+
+        if repourls:
+            fetchdir = self.bbhandler.config_data.getVar('BBLAYERS_FETCH_DIR', True)
+            if not fetchdir:
+                logger.error("Cannot get BBLAYERS_FETCH_DIR")
+                return 1
+            if not os.path.exists(fetchdir):
+                os.makedirs(fetchdir)
+            addlayers = []
+            for repourl, subdir in repourls.values():
+                name, layerdir = self.get_fetch_layer(fetchdir, repourl, subdir, not args.show_only)
+                if not name:
+                    # Error already shown
+                    return 1
+                addlayers.append((subdir, name, layerdir))
+        if not args.show_only:
+            for subdir, name, layerdir in set(addlayers):
+                if os.path.exists(layerdir):
+                    if subdir:
+                        logger.plain("Adding layer \"%s\" to conf/bblayers.conf" % subdir)
+                    else:
+                        logger.plain("Adding layer \"%s\" to conf/bblayers.conf" % name)
+                    localargs = argparse.Namespace()
+                    localargs.layerdir = layerdir
+                    self.do_add_layer(localargs)
+                else:
+                    break
+
+
+    def do_layerindex_show_depends(self, args):
+        """Find layer dependencies from layer index.
+"""
+        args.show_only = True
+        args.ignore = []
+        self.do_layerindex_fetch(args)
+
+
     def version_str(self, pe, pv, pr = None):
         verstr = "%s" % pv
         if pr:
@@ -115,32 +381,13 @@ class Commands(cmd.Cmd):
     def do_show_overlayed(self, args):
         """list overlayed recipes (where the same recipe exists in another layer)
 
-usage: show-overlayed [-f] [-s]
-
 Lists the names of overlayed recipes and the available versions in each
 layer, with the preferred version first. Note that skipped recipes that
 are overlayed will also be listed, with a " (skipped)" suffix.
-
-Options:
-  -f   instead of the default formatting, list filenames of higher priority
-       recipes with the ones they overlay indented underneath
-  -s   only list overlayed recipes where the version is the same
 """
         self.init_bbhandler()
 
-        show_filenames = False
-        show_same_ver_only = False
-        for arg in args.split():
-            if arg == '-f':
-                show_filenames = True
-            elif arg == '-s':
-                show_same_ver_only = True
-            else:
-                sys.stderr.write("show-overlayed: invalid option %s\n" % arg)
-                self.do_help('')
-                return
-
-        items_listed = self.list_recipes('Overlayed recipes', None, True, show_same_ver_only, show_filenames, True)
+        items_listed = self.list_recipes('Overlayed recipes', None, True, args.same_version, args.filenames, True)
 
         # Check for overlayed .bbclass files
         classes = defaultdict(list)
@@ -167,7 +414,7 @@ Options:
                     overlayed_class_found = True
 
                 mainfile = bb.utils.which(bbpath, os.path.join('classes', classfile))
-                if show_filenames:
+                if args.filenames:
                     logger.plain('%s' % mainfile)
                 else:
                     # We effectively have to guess the layer here
@@ -181,7 +428,7 @@ Options:
                 for classdir in classdirs:
                     fullpath = os.path.join(classdir, classfile)
                     if fullpath != mainfile:
-                        if show_filenames:
+                        if args.filenames:
                             print('  %s' % fullpath)
                         else:
                             print('  %s' % self.get_layer_name(os.path.dirname(classdir)))
@@ -196,38 +443,15 @@ Options:
     def do_show_recipes(self, args):
         """list available recipes, showing the layer they are provided by
 
-usage: show-recipes [-f] [-m] [pnspec]
-
-Lists the names of overlayed recipes and the available versions in each
+Lists the names of recipes and the available versions in each
 layer, with the preferred version first. Optionally you may specify
 pnspec to match a specified recipe name (supports wildcards). Note that
 skipped recipes will also be listed, with a " (skipped)" suffix.
-
-Options:
-  -f   instead of the default formatting, list filenames of higher priority
-       recipes with other available recipes indented underneath
-  -m   only list where multiple recipes (in the same layer or different
-       layers) exist for the same recipe name
 """
         self.init_bbhandler()
 
-        show_filenames = False
-        show_multi_provider_only = False
-        pnspec = None
         title = 'Available recipes:'
-        for arg in args.split():
-            if arg == '-f':
-                show_filenames = True
-            elif arg == '-m':
-                show_multi_provider_only = True
-            elif not arg.startswith('-'):
-                pnspec = arg
-                title = 'Available recipes matching %s:' % pnspec
-            else:
-                sys.stderr.write("show-recipes: invalid option %s\n" % arg)
-                self.do_help('')
-                return
-        self.list_recipes(title, pnspec, False, False, show_filenames, show_multi_provider_only)
+        self.list_recipes(title, args.pnspec, False, False, args.filenames, args.multiple)
 
 
     def list_recipes(self, title, pnspec, show_overlayed_only, show_same_ver_only, show_filenames, show_multi_provider_only):
@@ -277,7 +501,13 @@ Options:
 
             if len(allproviders[p]) > 1 or not show_multi_provider_only:
                 pref = preferred_versions[p]
-                preffile = bb.cache.Cache.virtualfn2realfn(pref[1])[0]
+                realfn = bb.cache.Cache.virtualfn2realfn(pref[1])
+                preffile = realfn[0]
+                # We only display once per recipe, we should prefer non extended versions of the
+                # recipe if present (so e.g. in OpenEmbedded, openssl rather than nativesdk-openssl
+                # which would otherwise sort first).
+                if realfn[1] and realfn[0] in self.bbhandler.cooker.recipecache.pkg_fn:
+                    continue
                 if preffile not in preffiles:
                     preflayer = self.get_file_layer(preffile)
                     multilayer = False
@@ -307,9 +537,7 @@ Options:
 
 
     def do_flatten(self, args):
-        """flattens layer configuration into a separate output directory.
-
-usage: flatten [layer1 layer2 [layer3]...] <outputdir>
+        """flatten layer configuration into a separate output directory.
 
 Takes the specified layers (or all layers in the current layer
 configuration if none are specified) and builds a "flattened" directory
@@ -331,26 +559,19 @@ bbappends in the layers interact, and then attempt to use the new output
 layer together with that other layer, you may no longer get the same
 build results (as the layer priority order has effectively changed).
 """
-        arglist = args.split()
-        if len(arglist) < 1:
-            logger.error('Please specify an output directory')
-            self.do_help('flatten')
-            return
-
-        if len(arglist) == 2:
+        if len(args.layer) == 1:
             logger.error('If you specify layers to flatten you must specify at least two')
-            self.do_help('flatten')
-            return
+            return 1
 
-        outputdir = arglist[-1]
+        outputdir = args.outputdir
         if os.path.exists(outputdir) and os.listdir(outputdir):
             logger.error('Directory %s exists and is non-empty, please clear it out first' % outputdir)
-            return
+            return 1
 
         self.init_bbhandler()
         layers = self.bblayers
-        if len(arglist) > 2:
-            layernames = arglist[:-1]
+        if len(args.layer) > 2:
+            layernames = args.layer
             found_layernames = []
             found_layerdirs = []
             for layerdir in layers:
@@ -499,14 +720,12 @@ build results (as the layer priority order has effectively changed).
     def do_show_appends(self, args):
         """list bbappend files and recipe files they apply to
 
-usage: show-appends
-
-Recipes are listed with the bbappends that apply to them as subitems.
+Lists recipes with the bbappends that apply to them as subitems.
 """
         self.init_bbhandler()
         if not self.bbhandler.cooker.collection.appendlist:
             logger.plain('No append files found')
-            return
+            return 0
 
         logger.plain('=== Appended recipes ===')
 
@@ -545,7 +764,6 @@ Recipes are listed with the bbappends that apply to them as subitems.
                 if best_filename in missing:
                     logger.warn('%s: missing append for preferred version',
                                 best_filename)
-                    self.returncode |= 1
 
 
     def get_appends_for_files(self, filenames):
@@ -556,7 +774,7 @@ Recipes are listed with the bbappends that apply to them as subitems.
                 continue
 
             basename = os.path.basename(filename)
-            appends = self.bbhandler.cooker.collection.appendlist.get(basename)
+            appends = self.bbhandler.cooker.collection.get_file_appends(basename)
             if appends:
                 appended.append((basename, list(appends)))
             else:
@@ -564,28 +782,15 @@ Recipes are listed with the bbappends that apply to them as subitems.
         return appended, notappended
 
     def do_show_cross_depends(self, args):
-        """figure out the dependency between recipes that crosses a layer boundary.
+        """Show dependencies between recipes that cross layer boundaries.
 
-usage: show-cross-depends [-f]
+Figure out the dependencies between recipes that cross layer boundaries.
 
-Figure out the dependency between recipes that crosses a layer boundary.
-
-Options:
-  -f   show full file path
-
-NOTE:
-The .bbappend file can impact the dependency.
+NOTE: .bbappend files can impact the dependencies.
 """
-        self.init_bbhandler()
+        ignore_layers = (args.ignore or '').split(',')
 
-        show_filenames = False
-        for arg in args.split():
-            if arg == '-f':
-                show_filenames = True
-            else:
-                sys.stderr.write("show-cross-depends: invalid option %s\n" % arg)
-                self.do_help('')
-                return
+        self.init_bbhandler()
 
         pkg_fn = self.bbhandler.cooker_data.pkg_fn
         bbpath = str(self.bbhandler.config_data.getVar('BBPATH', True))
@@ -593,6 +798,8 @@ The .bbappend file can impact the dependency.
         self.include_re = re.compile(r"include\s+(.+)")
         self.inherit_re = re.compile(r"inherit\s+(.+)")
 
+        global_inherit = (self.bbhandler.config_data.getVar('INHERIT', True) or "").split()
+
         # The bb's DEPENDS and RDEPENDS
         for f in pkg_fn:
             f = bb.cache.Cache.virtualfn2realfn(f)[0]
@@ -607,7 +814,7 @@ The .bbappend file can impact the dependency.
                             self.bbhandler.config_data,
                             self.bbhandler.cooker_data,
                             self.bbhandler.cooker_data.pkg_pn)
-                    self.check_cross_depends("DEPENDS", layername, f, best[3], show_filenames)
+                    self.check_cross_depends("DEPENDS", layername, f, best[3], args.filenames, ignore_layers)
 
             # The RDPENDS
             all_rdeps = self.bbhandler.cooker_data.rundeps[f].values()
@@ -621,10 +828,33 @@ The .bbappend file can impact the dependency.
             for rdep in all_rdeps:
                 all_p = bb.providers.getRuntimeProviders(self.bbhandler.cooker_data, rdep)
                 if all_p:
+                    if f in all_p:
+                        # The recipe provides this one itself, ignore
+                        continue
                     best = bb.providers.filterProvidersRunTime(all_p, rdep,
                                     self.bbhandler.config_data,
                                     self.bbhandler.cooker_data)[0][0]
-                    self.check_cross_depends("RDEPENDS", layername, f, best, show_filenames)
+                    self.check_cross_depends("RDEPENDS", layername, f, best, args.filenames, ignore_layers)
+
+            # The RRECOMMENDS
+            all_rrecs = self.bbhandler.cooker_data.runrecs[f].values()
+            # Remove the duplicated or null one.
+            sorted_rrecs = {}
+            # The all_rrecs is the list in list, so we need two for loops
+            for k1 in all_rrecs:
+                for k2 in k1:
+                    sorted_rrecs[k2] = 1
+            all_rrecs = sorted_rrecs.keys()
+            for rrec in all_rrecs:
+                all_p = bb.providers.getRuntimeProviders(self.bbhandler.cooker_data, rrec)
+                if all_p:
+                    if f in all_p:
+                        # The recipe provides this one itself, ignore
+                        continue
+                    best = bb.providers.filterProvidersRunTime(all_p, rrec,
+                                    self.bbhandler.config_data,
+                                    self.bbhandler.cooker_data)[0][0]
+                    self.check_cross_depends("RRECOMMENDS", layername, f, best, args.filenames, ignore_layers)
 
             # The inherit class
             cls_re = re.compile('classes/')
@@ -634,9 +864,12 @@ The .bbappend file can impact the dependency.
                     # The inherits' format is [classes/cls, /path/to/classes/cls]
                     # ignore the classes/cls.
                     if not cls_re.match(cls):
+                        classname = os.path.splitext(os.path.basename(cls))[0]
+                        if classname in global_inherit:
+                            continue
                         inherit_layername = self.get_file_layer(cls)
-                        if inherit_layername != layername:
-                            if not show_filenames:
+                        if inherit_layername != layername and not inherit_layername in ignore_layers:
+                            if not args.filenames:
                                 f_short = self.remove_layer_prefix(f)
                                 cls = self.remove_layer_prefix(cls)
                             else:
@@ -656,7 +889,7 @@ The .bbappend file can impact the dependency.
                     if pv_re.search(needed_file) and f in self.bbhandler.cooker_data.pkg_pepvpr:
                         pv = self.bbhandler.cooker_data.pkg_pepvpr[f][1]
                         needed_file = re.sub(r"\${PV}", pv, needed_file)
-                    self.print_cross_files(bbpath, keyword, layername, f, needed_file, show_filenames)
+                    self.print_cross_files(bbpath, keyword, layername, f, needed_file, args.filenames, ignore_layers)
                 line = fnfile.readline()
             fnfile.close()
 
@@ -683,21 +916,22 @@ The .bbappend file can impact the dependency.
                                 bbclass=".bbclass"
                             # Find a 'require/include xxxx'
                             if m:
-                                self.print_cross_files(bbpath, keyword, layername, f, m.group(1) + bbclass, show_filenames)
+                                self.print_cross_files(bbpath, keyword, layername, f, m.group(1) + bbclass, args.filenames, ignore_layers)
                             line = ffile.readline()
                         ffile.close()
 
-    def print_cross_files(self, bbpath, keyword, layername, f, needed_filename, show_filenames):
+    def print_cross_files(self, bbpath, keyword, layername, f, needed_filename, show_filenames, ignore_layers):
         """Print the depends that crosses a layer boundary"""
         needed_file = bb.utils.which(bbpath, needed_filename)
         if needed_file:
             # Which layer is this file from
             needed_layername = self.get_file_layer(needed_file)
-            if needed_layername != layername:
+            if needed_layername != layername and not needed_layername in ignore_layers:
                 if not show_filenames:
                     f = self.remove_layer_prefix(f)
                     needed_file = self.remove_layer_prefix(needed_file)
                 logger.plain("%s %s %s" %(f, keyword, needed_file))
+
     def match_inherit(self, line):
         """Match the inherit xxx line"""
         return (self.inherit_re.match(line), "inherits")
@@ -711,16 +945,95 @@ The .bbappend file can impact the dependency.
             keyword = "includes"
         return (m, keyword)
 
-    def check_cross_depends(self, keyword, layername, f, needed_file, show_filenames):
+    def check_cross_depends(self, keyword, layername, f, needed_file, show_filenames, ignore_layers):
         """Print the DEPENDS/RDEPENDS file that crosses a layer boundary"""
         best_realfn = bb.cache.Cache.virtualfn2realfn(needed_file)[0]
         needed_layername = self.get_file_layer(best_realfn)
-        if needed_layername != layername:
+        if needed_layername != layername and not needed_layername in ignore_layers:
             if not show_filenames:
                 f = self.remove_layer_prefix(f)
                 best_realfn = self.remove_layer_prefix(best_realfn)
 
             logger.plain("%s %s %s" % (f, keyword, best_realfn))
 
-if __name__ == '__main__':
-    sys.exit(main(sys.argv[1:]) or 0)
+
+def main():
+
+    cmds = Commands()
+
+    def add_command(cmdname, function, *args, **kwargs):
+        # Convert docstring for function to help (one-liner shown in main --help) and description (shown in subcommand --help)
+        docsplit = function.__doc__.splitlines()
+        help = docsplit[0]
+        if len(docsplit) > 1:
+            desc = '\n'.join(docsplit[1:])
+        else:
+            desc = help
+        subparser = subparsers.add_parser(cmdname, *args, help=help, description=desc, formatter_class=argparse.RawTextHelpFormatter, **kwargs)
+        subparser.set_defaults(func=function)
+        return subparser
+
+    parser = argparse.ArgumentParser(description="BitBake layers utility",
+                                     epilog="Use %(prog)s <subcommand> --help to get help on a specific command")
+    parser.add_argument('-d', '--debug', help='Enable debug output', action='store_true')
+    parser.add_argument('-q', '--quiet', help='Print only errors', action='store_true')
+    subparsers = parser.add_subparsers(title='subcommands', metavar='<subcommand>')
+
+    parser_show_layers = add_command('show-layers', cmds.do_show_layers)
+
+    parser_add_layer = add_command('add-layer', cmds.do_add_layer)
+    parser_add_layer.add_argument('layerdir', help='Layer directory to add')
+
+    parser_remove_layer = add_command('remove-layer', cmds.do_remove_layer)
+    parser_remove_layer.add_argument('layerdir', help='Layer directory to remove (wildcards allowed, enclose in quotes to avoid shell expansion)')
+    parser_remove_layer.set_defaults(func=cmds.do_remove_layer)
+
+    parser_show_overlayed = add_command('show-overlayed', cmds.do_show_overlayed)
+    parser_show_overlayed.add_argument('-f', '--filenames', help='instead of the default formatting, list filenames of higher priority recipes with the ones they overlay indented underneath', action='store_true')
+    parser_show_overlayed.add_argument('-s', '--same-version', help='only list overlayed recipes where the version is the same', action='store_true')
+
+    parser_show_recipes = add_command('show-recipes', cmds.do_show_recipes)
+    parser_show_recipes.add_argument('-f', '--filenames', help='instead of the default formatting, list filenames of higher priority recipes with the ones they overlay indented underneath', action='store_true')
+    parser_show_recipes.add_argument('-m', '--multiple', help='only list where multiple recipes (in the same layer or different layers) exist for the same recipe name', action='store_true')
+    parser_show_recipes.add_argument('pnspec', nargs='?', help='optional recipe name specification (wildcards allowed, enclose in quotes to avoid shell expansion)')
+
+    parser_show_appends = add_command('show-appends', cmds.do_show_appends)
+
+    parser_flatten = add_command('flatten', cmds.do_flatten)
+    parser_flatten.add_argument('layer', nargs='*', help='Optional layer(s) to flatten (otherwise all are flattened)')
+    parser_flatten.add_argument('outputdir', help='Output directory')
+
+    parser_show_cross_depends = add_command('show-cross-depends', cmds.do_show_cross_depends)
+    parser_show_cross_depends.add_argument('-f', '--filenames', help='show full file path', action='store_true')
+    parser_show_cross_depends.add_argument('-i', '--ignore', help='ignore dependencies on items in the specified layer(s) (split multiple layer names with commas, no spaces)', metavar='LAYERNAME')
+
+    parser_layerindex_fetch = add_command('layerindex-fetch', cmds.do_layerindex_fetch)
+    parser_layerindex_fetch.add_argument('-n', '--show-only', help='show dependencies and do nothing else', action='store_true')
+    parser_layerindex_fetch.add_argument('-b', '--branch', help='branch name to fetch (default %(default)s)', default='master')
+    parser_layerindex_fetch.add_argument('-i', '--ignore', help='assume the specified layers do not need to be fetched/added (separate multiple layers with commas, no spaces)', metavar='LAYER')
+    parser_layerindex_fetch.add_argument('layername', nargs='+', help='layer to fetch')
+
+    parser_layerindex_show_depends = add_command('layerindex-show-depends', cmds.do_layerindex_show_depends)
+    parser_layerindex_show_depends.add_argument('-b', '--branch', help='branch name to fetch (default %(default)s)', default='master')
+    parser_layerindex_show_depends.add_argument('layername', nargs='+', help='layer to query')
+
+    args = parser.parse_args()
+
+    if args.debug:
+        logger.setLevel(logging.DEBUG)
+    elif args.quiet:
+        logger.setLevel(logging.ERROR)
+
+    ret = args.func(args)
+
+    return ret
+
+
+if __name__ == "__main__":
+    try:
+        ret = main()
+    except Exception:
+        ret = 1
+        import traceback
+        traceback.print_exc(5)
+    sys.exit(ret)

bitbake/bin/bitbake-worker

@@ -12,10 +12,18 @@ import errno
 import signal
 
 # Users shouldn't be running this code directly
-if len(sys.argv) != 2 or sys.argv[1] != "decafbad":
+if len(sys.argv) != 2 or not sys.argv[1].startswith("decafbad"):
     print("bitbake-worker is meant for internal execution by bitbake itself, please don't use it standalone.")
     sys.exit(1)
 
+profiling = False
+if sys.argv[1] == "decafbadbad":
+    profiling = True
+    try:
+        import cProfile as profile
+    except:
+        import profile
+
 logger = logging.getLogger("BitBake")
 
 try:
@@ -81,6 +89,11 @@ def workerlog_write(msg):
         lf.write(msg)
         lf.flush()
 
+def sigterm_handler(signum, frame):
+    signal.signal(signal.SIGTERM, signal.SIG_DFL)
+    os.killpg(0, signal.SIGTERM)
+    sys.exit()
+
 def fork_off_task(cfg, data, workerdata, fn, task, taskname, appends, taskdepdata, quieterrors=False):
     # We need to setup the environment BEFORE the fork, since
     # a fork() or exec*() activates PSEUDO...
@@ -129,10 +142,13 @@ def fork_off_task(cfg, data, workerdata, fn, task, taskname, appends, taskdepdat
         bb.msg.fatal("RunQueue", "fork failed: %d (%s)" % (e.errno, e.strerror))
 
     if pid == 0:
+        def child():
             global worker_pipe
             pipein.close()
 
-            signal.signal(signal.SIGTERM, signal.SIG_DFL)
+            signal.signal(signal.SIGTERM, sigterm_handler)
+            # Let SIGHUP exit as SIGTERM
+            signal.signal(signal.SIGHUP, sigterm_handler)
 
             # Save out the PID so that the event can include it the
             # events
@@ -140,8 +156,11 @@ def fork_off_task(cfg, data, workerdata, fn, task, taskname, appends, taskdepdat
             bb.event.worker_fire = worker_child_fire
             worker_pipe = pipeout
 
-            # Make the child the process group leader
-            os.setpgid(0, 0)
+            # Make the child the process group leader and ensure no
+            # child process will be controlled by the current terminal
+            # This ensures signals sent to the controlling terminal like Ctrl+C
+            # don't stop the child processes.
+            os.setsid()
             # No stdin
             newsi = os.open(os.devnull, os.O_RDWR)
             os.dup2(newsi, sys.stdin.fileno())
@@ -154,15 +173,11 @@ def fork_off_task(cfg, data, workerdata, fn, task, taskname, appends, taskdepdat
             data.setVar("BUILDNAME", workerdata["buildname"])
             data.setVar("DATE", workerdata["date"])
             data.setVar("TIME", workerdata["time"])
-            bb.parse.siggen.set_taskdata(workerdata["hashes"], workerdata["hash_deps"], workerdata["sigchecksums"])
+            bb.parse.siggen.set_taskdata(workerdata["sigdata"])
             ret = 0
             try:
                 the_data = bb.cache.Cache.loadDataFull(fn, appends, data)
                 the_data.setVar('BB_TASKHASH', workerdata["runq_hash"][task])
-                for h in workerdata["hashes"]:
-                    the_data.setVar("BBHASH_%s" % h, workerdata["hashes"][h])
-                for h in workerdata["hash_deps"]:
-                    the_data.setVar("BBHASHDEPS_%s" % h, workerdata["hash_deps"][h])
 
                 # exported_vars() returns a generator which *cannot* be passed to os.environ.update() 
                 # successfully. We also need to unset anything from the environment which shouldn't be there 
@@ -183,11 +198,22 @@ def fork_off_task(cfg, data, workerdata, fn, task, taskname, appends, taskdepdat
                     logger.critical(str(exc))
                 os._exit(1)
             try:
-                if not cfg.dry_run:
-                    ret = bb.build.exec_task(fn, taskname, the_data, cfg.profile)
-                os._exit(ret)
+                if cfg.dry_run:
+                    return 0
+                return bb.build.exec_task(fn, taskname, the_data, cfg.profile)
             except:
                 os._exit(1)
+        if not profiling:
+            os._exit(child())
+        else:
+            profname = "profile-%s.log" % (fn.replace("/", "-") + "-" + taskname)
+            prof = profile.Profile()
+            try: 
+                ret = profile.Profile.runcall(prof, child)
+            finally:
+                prof.dump_stats(profname)
+                bb.utils.process_profilelog(profname)
+                os._exit(ret)
     else:
         for key, value in envbackup.iteritems():
             if value is None:
@@ -245,9 +271,14 @@ class BitbakeWorker(object):
         self.build_pipes = {}
     
         signal.signal(signal.SIGTERM, self.sigterm_exception)
+        # Let SIGHUP exit as SIGTERM
+        signal.signal(signal.SIGHUP, self.sigterm_exception)
 
     def sigterm_exception(self, signum, stackframe):
-        bb.warn("Worker recieved SIGTERM, shutting down...")
+        if signum == signal.SIGTERM:
+            bb.warn("Worker recieved SIGTERM, shutting down...")
+        elif signum == signal.SIGHUP:
+            bb.warn("Worker recieved SIGHUP, shutting down...")
         self.handle_finishnow(None)
         signal.signal(signal.SIGTERM, signal.SIG_DFL)
         os.kill(os.getpid(), signal.SIGTERM)
@@ -362,7 +393,16 @@ class BitbakeWorker(object):
 
 try:
     worker = BitbakeWorker(sys.stdin)
-    worker.serve()
+    if not profiling:
+        worker.serve()
+    else:
+        profname = "profile-worker.log"
+        prof = profile.Profile()
+        try:
+            profile.Profile.runcall(prof, worker.serve)
+        finally:
+            prof.dump_stats(profname)
+            bb.utils.process_profilelog(profname)
 except BaseException as e:
     if not normalexit:
         import traceback

bitbake/bin/image-writer

@@ -34,7 +34,7 @@ from bb.ui.crumbs.hig.deployimagedialog import DeployImageDialog
 from bb.ui.crumbs.hig.imageselectiondialog import ImageSelectionDialog
 
 # I put all the fs bitbake supported here. Need more test.
-DEPLOYABLE_IMAGE_TYPES = ["jffs2", "cramfs", "ext2", "ext3", "btrfs", "squashfs", "ubi", "vmdk"]
+DEPLOYABLE_IMAGE_TYPES = ["jffs2", "cramfs", "ext2", "ext3", "ext4", "btrfs", "squashfs", "ubi", "vmdk"]
 Title = "USB Image Writer"
 
 class DeployWindow(gtk.Window):

bitbake/bin/toaster

@@ -16,9 +16,15 @@
 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 
-# This script enables toaster event logging and
-# starts bitbake resident server
-# use as:  source toaster [start|stop]
+# This script can be run in two modes.
+
+# When used with "source", from a build directory,
+# it enables toaster event logging and starts the bitbake resident server.
+# use as:  source toaster [start|stop] [noweb] [noui]
+
+# When it is called as a stand-alone script, it starts just the
+# web server, and the building shall be done through the web interface.
+# As script, it will not return to the command prompt. Stop with Ctrl-C.
 
 # Helper function to kill a background toaster development server
 
@@ -30,6 +36,8 @@ function webserverKillAll()
 		while kill -0 $(< ${pidfile}) 2>/dev/null; do
 			kill -SIGTERM -$(< ${pidfile}) 2>/dev/null
 			sleep 1;
+			# Kill processes if they are still running - may happen in interactive shells
+			ps fux | grep "python.*manage.py runserver" | awk '{print $2}' | xargs kill
 		done;
 		rm  ${pidfile}
 		fi
@@ -38,6 +46,12 @@ function webserverKillAll()
 
 function webserverStartAll()
 {
+	# do not start if toastermain points to a valid process
+	if ! cat "${BUILDDIR}/.toastermain.pid" 2>/dev/null | xargs -I{} kill -0 {} ; then
+            retval=1
+            rm "${BUILDDIR}/.toastermain.pid"
+        fi
+
         retval=0
         python $BBBASEDIR/lib/toaster/manage.py syncdb || retval=1
         python $BBBASEDIR/lib/toaster/manage.py migrate orm || retval=2
@@ -49,12 +63,19 @@ function webserverStartAll()
             retval=0
             python $BBBASEDIR/lib/toaster/manage.py migrate orm || retval=1
         fi
+	if [ "x$TOASTER_MANAGED" == "x1" ]; then
+	        python $BBBASEDIR/lib/toaster/manage.py migrate bldcontrol || retval=1
+		python $BBBASEDIR/lib/toaster/manage.py checksettings  --traceback || retval=1
+	fi
         if [ $retval -eq 0 ]; then
-            python $BBBASEDIR/lib/toaster/manage.py runserver 0.0.0.0:8000 </dev/null >${BUILDDIR}/toaster_web.log 2>&1 & echo $! >${BUILDDIR}/.toastermain.pid
+	    echo "Starting webserver..."
+            python $BBBASEDIR/lib/toaster/manage.py runserver "0.0.0.0:$WEB_PORT" </dev/null >>${BUILDDIR}/toaster_web.log 2>&1 & echo $! >${BUILDDIR}/.toastermain.pid
             sleep 1
             if ! cat "${BUILDDIR}/.toastermain.pid" | xargs -I{} kill -0 {} ; then
                 retval=1
                 rm "${BUILDDIR}/.toastermain.pid"
+	    else
+		echo "Webserver address:  http://0.0.0.0:$WEB_PORT/"
             fi
         fi
         return $retval
@@ -64,8 +85,10 @@ function webserverStartAll()
 
 function addtoConfiguration()
 {
-        echo "#Created by toaster start script" > ${BUILDDIR}/conf/$2
-        echo $1 >> ${BUILDDIR}/conf/$2
+        file=$1
+        shift
+        echo "#Created by toaster start script" > ${BUILDDIR}/conf/$file
+        for var in "$@"; do echo $var >> ${BUILDDIR}/conf/$file; done
 }
 
 INSTOPSYSTEM=0
@@ -80,7 +103,7 @@ function stop_system()
         kill $(< ${BUILDDIR}/.toasterui.pid ) 2>/dev/null
         rm ${BUILDDIR}/.toasterui.pid
     fi
-    BBSERVER=localhost:8200 bitbake -m
+    BBSERVER=0.0.0.0:-1 bitbake -m
     unset BBSERVER
     webserverKillAll
     # force stop any misbehaving bitbake server
@@ -103,36 +126,136 @@ function notify_chldexit() {
 }
 
 
-# We make sure we're running in the current shell and in a good environment
+function verify_prereq() {
+	# Verify prerequisites
+
+    if ! echo "import django; print (1,) == django.VERSION[0:1] and django.VERSION[1:2][0] in (6,)" | python 2>/dev/null | grep True >/dev/null; then
+        echo -e "This program needs Django 1.6. Please install with\n\npip install django==1.6\n"
+        return 2
+    fi
+
+    if ! echo "import south; print reduce(lambda x, y: 2 if x==2 else 0 if x == 0 else y, map(lambda x: 1+cmp(x[1]-x[0],0), zip([0,8,4], map(int,south.__version__.split(\".\"))))) > 0" | python 2>/dev/null | grep True >/dev/null; then
+        echo -e "This program needs South 0.8.4. Please install with\n\npip install south==0.8.4\n"
+        return 2
+    fi
+    return 0
+}
+
+
+# read command line parameters
+
+BBBASEDIR=`dirname ${BASH_SOURCE}`/..
+RUNNING=0
+
+NOTOASTERUI=0
+WEBSERVER=1
+TOASTER_BRBE=""
+WEB_PORT="8000"
+
+for param in $*; do
+    case $param in
+    noui )
+            NOTOASTERUI=1
+    ;;
+    noweb )
+            WEBSERVER=0
+    ;;
+    brbe=* )
+            TOASTER_BRBE=$'\n'"TOASTER_BRBE=\""${param#*=}"\""
+    ;;
+    webport=*)
+            WEB_PORT="${param#*=}"
+    esac
+done
+
 
 if [ -z "$ZSH_NAME" ] && [ `basename \"$0\"` = `basename \"$BASH_SOURCE\"` ]; then
-    echo "Error: This script needs to be sourced. Please run as 'source toaster [start|stop]'" 1>&2;
-    exit 1
+    # We are called as standalone. We refuse to run in a build environment - we need the interactive mode for that.
+    # Start just the web server, point the web browser to the interface, and start any Django services.
+
+    if ! verify_prereq; then
+        echo -e "Error: Could not verify that the needed dependencies are installed. Please use virtualenv and pip to install dependencies listed in toaster-requirements.txt" 1>&2;
+        exit 1;
+    fi
+
+    if [ -n "$BUILDDIR" ]; then
+	echo -e "Error: It looks like you sourced oe-init-build-env. Toaster cannot start in build mode from an oe-core build environment.\n You should be starting Toaster from a new terminal window." 1>&2;
+        exit 1;
+    fi
+
+    if [ "x`which daemon`" == "x" ]; then
+        echo -e "Failed dependency; toaster needs the 'daemon' program in order to be able to start builds'. Please install the 'daemon' program from your distribution repositories or http://www.libslack.org/daemon/" 1>&2;
+	exit 1;
+    fi
+
+    # Define a fake builddir where only the pid files are actually created. No real builds will take place here.
+    BUILDDIR=/tmp/toaster_$$
+    if [ -d "$BUILDDIR" ]; then
+        echo -e "Previous toaster run directory $BUILDDIR found, cowardly refusing to start. Please remove the directory when that toaster instance is over" 2>&1
+        exit 1;
+    fi
+
+    mkdir -p "$BUILDDIR"
+
+    RUNNING=1
+    function trap_ctrlc() {
+        echo "** Stopping system"
+        webserverKillAll
+        RUNNING=0
+    }
+
+    function do_cleanup() {
+        find "$BUILDDIR" -type f | xargs rm
+        rmdir "$BUILDDIR"
+    }
+    function cleanup() {
+        if grep -ir error "$BUILDDIR" >/dev/null; then
+            if grep -irn "That port is already in use" "$BUILDDIR"; then
+                echo "You can use the \"webport=PORTNUMBER\" parameter to start Toaster on a different port (port $WEB_PORT is already in use)"
+                do_cleanup
+            else
+                echo -e "\nErrors found in the Toaster log files present in '$BUILDDIR'. Directory will not be cleaned.\n Please review the errors and notify toaster@yoctoproject.org or submit a bug https://bugzilla.yoctoproject.org/enter_bug.cgi?product=Toaster"
+            fi
+        else
+            echo "No errors found, removing the run directory '$BUILDDIR'"
+            do_cleanup
+        fi;
+    }
+    TOASTER_MANAGED=1
+    export TOASTER_MANAGED=1
+    if [ $WEBSERVER -gt 0 ] && ! webserverStartAll; then
+        echo "Failed to start the web server, stopping" 1>&2;
+        cleanup
+        exit 1;
+    fi
+    if [ $WEBSERVER -gt 0 ]; then
+        echo "Starting browser..."
+        xdg-open http://127.0.0.1:$WEB_PORT/ >/dev/null 2>&1 &
+    fi
+    trap trap_ctrlc SIGINT
+    echo "Toaster is now running. You can stop it with Ctrl-C"
+    while [ $RUNNING -gt 0 ]; do
+        python $BBBASEDIR/lib/toaster/manage.py runbuilds 2>&1 | tee -a "$BUILDDIR/toaster.log"
+        sleep 1
+    done
+    cleanup
+    echo "**** Exit"
+    exit 0
 fi
 
+
+if ! verify_prereq; then
+	echo -e "Error: Could not verify that the needed dependencies are installed. Please use virtualenv and pip to install dependencies listed in toaster-requirements.txt" 1>&2;
+	return 1;
+fi
+
+
+# We make sure we're running in the current shell and in a good environment
 if [ -z "$BUILDDIR" ] || [ -z `which bitbake` ]; then
     echo "Error: Build environment is not setup or bitbake is not in path." 1>&2;
     return 2
 fi
 
-BBBASEDIR=`dirname ${BASH_SOURCE}`/..
-
-
-# Verify prerequisites
-
-if ! echo "import django; print (1,5) == django.VERSION[0:2]" | python 2>/dev/null | grep True >/dev/null; then
-    echo -e "This program needs Django 1.5. Please install with\n\nsudo pip install django==1.5"
-    return 2
-fi
-
-if ! echo "import south; print [0,8,4] ==  map(int,south.__version__.split(\".\"))" | python 2>/dev/null | grep True >/dev/null; then
-    echo -e "This program needs South 0.8.4. Please install with\n\nsudo pip install south==0.8.4"
-    return 2
-fi
-
-
-
-
 
 # Determine the action. If specified by arguments, fine, if not, toggle it
 if [ "x$1" == "xstart" ] || [ "x$1" == "xstop" ]; then
@@ -145,15 +268,6 @@ else
     fi;
 fi
 
-NOTOASTERUI=0
-for param in $*; do
-    case $param in
-    noui )
-            NOTOASTERUI=1
-    ;;
-    esac
-done
-
 echo "The system will $CMD."
 
 # Make sure it's safe to run by checking bitbake lock
@@ -163,42 +277,54 @@ if [ -e $BUILDDIR/bitbake.lock ]; then
     (flock -n 200 ) 200<$BUILDDIR/bitbake.lock || lock=0
 fi
 
-if [ ${CMD} == "start" ] && ( [ $lock -eq 0 ] || [ -e $BUILDDIR/.toastermain.pid ] ); then
-    echo "Error: bitbake lock state error. File locks show that the system is on." 2>&1
-    echo "If you see problems, stop and then start the system again." 2>&1
+if [ ${CMD} == "start" ] && [ $lock -eq 0 ]; then
+    echo "Error: bitbake lock state error. File locks show that the system is on." 1>&2
+    echo "Please wait for the current build to finish, stop and then start the system again." 1>&2
     return 3
 fi
 
+if [ ${CMD} == "start" ] && [ -e $BUILDDIR/.toastermain.pid ] && kill -0 `cat $BUILDDIR/.toastermain.pid`; then
+    echo "Warning: bitbake appears to be dead, but the Toaster web server is running. Something fishy is going on." 1>&2
+    echo "Cleaning up the web server to start from a clean slate."
+    webserverKillAll
+fi
+
 
 # Execute the commands
 
 case $CMD in
     start )
         start_success=1
-        addtoConfiguration "INHERIT+=\"toaster buildhistory\"" toaster.conf
-        if ! webserverStartAll; then
+        addtoConfiguration toaster.conf "INHERIT+=\"toaster buildhistory\"" $TOASTER_BRBE
+        if [ $WEBSERVER -gt 0 ] && ! webserverStartAll; then
             echo "Failed ${CMD}."
             return 4
         fi
         unset BBSERVER
-        bitbake --postread conf/toaster.conf --server-only -t xmlrpc -B localhost:8200
+        PREREAD=""
+        if [ -e ${BUILDDIR}/conf/toaster-pre.conf ]; then
+		rm ${BUILDDIR}/conf/toaster-pre.conf
+        fi
+        bitbake $PREREAD --postread conf/toaster.conf --server-only -t xmlrpc -B 0.0.0.0:0
         if [ $? -ne 0 ]; then
             start_success=0
             echo "Bitbake server start failed"
         else
-            export BBSERVER=localhost:8200
+            export BBSERVER=0.0.0.0:-1
             if [ $NOTOASTERUI == 0 ]; then        # we start the TOASTERUI only if not inhibited
-                bitbake --observe-only -u toasterui >${BUILDDIR}/toaster_ui.log 2>&1 & echo $! >${BUILDDIR}/.toasterui.pid
+                bitbake --observe-only -u toasterui >>${BUILDDIR}/toaster_ui.log 2>&1 & echo $! >${BUILDDIR}/.toasterui.pid
             fi
         fi
         if [ $start_success -eq 1 ]; then
             # set fail safe stop system on terminal exit
             trap stop_system SIGHUP
             echo "Successful ${CMD}."
+            return 0
         else
             # failed start, do stop
             stop_system
             echo "Failed ${CMD}."
+            return 1
         fi
         # stop system on terminal exit
         set -o monitor

bitbake/bin/toaster-eventreplay

@@ -0,0 +1,179 @@
+#!/usr/bin/env python
+# ex:ts=4:sw=4:sts=4:et
+# -*- tab-width: 4; c-basic-offset: 4; indent-tabs-mode: nil -*-
+#
+# Copyright (C) 2014        Alex Damian
+#
+# This file re-uses code spread throughout other Bitbake source files.
+# As such, all other copyrights belong to their own right holders.
+#
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along
+# with this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+
+# This command takes a filename as a single parameter. The filename is read
+# as a build eventlog, and the ToasterUI is used to process events in the file
+# and log data in the database
+
+import os
+import sys, logging
+
+# mangle syspath to allow easy import of modules
+sys.path.insert(0, os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))),
+                                'lib'))
+
+
+import bb.cooker
+from bb.ui import toasterui
+import sys
+import logging
+
+logger = logging.getLogger(__name__)
+console = logging.StreamHandler(sys.stdout)
+format_str = "%(levelname)s: %(message)s"
+logging.basicConfig(format=format_str)
+
+
+import json, pickle
+
+
+class FileReadEventsServerConnection():
+    """  Emulates a connection to a bitbake server that feeds
+        events coming actually read from a saved log file.
+    """
+
+    class MockConnection():
+        """ fill-in for the proxy to the server. we just return generic data
+        """
+        def __init__(self, sc):
+            self._sc = sc
+
+        def runCommand(self, commandArray):
+            """ emulates running a command on the server; only read-only commands are accepted """
+            command_name = commandArray[0]
+
+            if command_name == "getVariable":
+                if commandArray[1] in self._sc._variables:
+                    return (self._sc._variables[commandArray[1]]['v'], None)
+                return (None, "Missing variable")
+
+            elif command_name == "getAllKeysWithFlags":
+                dump = {}
+                flaglist = commandArray[1]
+                for k in self._sc._variables.keys():
+                    try:
+                        if not k.startswith("__"):
+                            v = self._sc._variables[k]['v']
+                            dump[k] = {
+                                'v' : v ,
+                                'history' : self._sc._variables[k]['history'],
+                            }
+                            for d in flaglist:
+                                dump[k][d] = self._sc._variables[k][d]
+                    except Exception as e:
+                        print(e)
+                return (dump, None)
+            else:
+                raise Exception("Command %s not implemented" % commandArray[0])
+
+        def terminateServer(self):
+            """ do not do anything """
+            pass
+
+
+
+    class EventReader():
+        def __init__(self, sc):
+            self._sc = sc
+            self.firstraise = 0
+
+        def _create_event(self, line):
+            def _import_class(name):
+                assert len(name) > 0
+                assert "." in name, name
+
+                components = name.strip().split(".")
+                modulename = ".".join(components[:-1])
+                moduleklass = components[-1]
+
+                module = __import__(modulename, fromlist=[str(moduleklass)])
+                return getattr(module, moduleklass)
+
+            # we build a toaster event out of current event log line
+            try:
+                event_data = json.loads(line.strip())
+                event_class = _import_class(event_data['class'])
+                event_object = pickle.loads(json.loads(event_data['vars']))
+            except ValueError as e:
+                print("Failed loading ", line)
+                raise e
+
+            if not isinstance(event_object, event_class):
+                raise Exception("Error loading objects %s class %s ", event_object, event_class)
+
+            return event_object
+
+        def waitEvent(self, timeout):
+
+            nextline = self._sc._eventfile.readline()
+            if len(nextline) == 0:
+                # the build data ended, while toasterui still waits for events.
+                # this happens when the server was abruptly stopped, so we simulate this
+                self.firstraise += 1
+                if self.firstraise == 1:
+                    raise KeyboardInterrupt()
+                else:
+                    return None
+            else:
+                self._sc.lineno += 1
+            return self._create_event(nextline)
+
+
+    def _readVariables(self, variableline):
+        self._variables = json.loads(variableline.strip())['allvariables']
+
+
+    def __init__(self, file_name):
+        self.connection = FileReadEventsServerConnection.MockConnection(self)
+        self._eventfile = open(file_name, "r")
+
+        # we expect to have the variable dump at the start of the file
+        self.lineno = 1
+        self._readVariables(self._eventfile.readline())
+
+        self.events = FileReadEventsServerConnection.EventReader(self)
+
+
+
+
+
+class MockConfigParameters():
+    """ stand-in for cookerdata.ConfigParameters; as we don't really config a cooker, this
+        serves just to supply needed interfaces for the toaster ui to work """
+    def __init__(self):
+        self.observe_only = True            # we can only read files
+
+
+# run toaster ui on our mock bitbake class
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        logger.error("Usage: %s event.log " % sys.argv[0])
+        sys.exit(1)
+
+    file_name = sys.argv[-1]
+    mock_connection = FileReadEventsServerConnection(file_name)
+    configParams = MockConfigParameters()
+
+    # run the main program
+    toasterui.main(mock_connection.connection, mock_connection.events, configParams)

bitbake/contrib/vim/plugin/newbb.vim

@@ -53,7 +53,6 @@ fun! NewBBTemplate()
     put ='LICENSE = \"\"' 
     put ='SECTION = \"\"'
     put ='DEPENDS = \"\"'
-    put ='PR = \"r0\"'
     put =''
     put ='SRC_URI = \"\"'
 

bitbake/doc/Makefile

@@ -11,7 +11,7 @@
 #    validate: validates
 #    clean:    removes files
 #
-# The Makefile generates an HTML and PDF version of every document.  The
+# The Makefile generates an HTML version of every document.  The
 # variable DOC indicates the folder name for a given manual.
 #
 # To build a manual, you must invoke 'make' with the DOC argument.
@@ -21,8 +21,8 @@
 #     make DOC=bitbake-user-manual
 #     make pdf DOC=bitbake-user-manual
 #
-# The first example generates the HTML and PDF versions of the User Manual.
-# The second example generates the HTML version only of the User Manual.
+# The first example generates the HTML version of the User Manual.
+# The second example generates the PDF version of the User Manual.
 #
 
 ifeq ($(DOC),bitbake-user-manual)
@@ -31,9 +31,9 @@ XSLTOPTS = --stringparam html.stylesheet bitbake-user-manual-style.css \
            --stringparam  section.autolabel 1 \
            --stringparam  section.label.includes.component.label 1 \
            --xinclude
-ALLPREQ = html pdf tarball
-TARFILES = bitbake-user-manual-style.css bitbake-user-manual.html bitbake-user-manual.pdf figures/bitbake-title.png
-MANUALS = $(DOC)/$(DOC).html $(DOC)/$(DOC).pdf
+ALLPREQ = html tarball
+TARFILES = bitbake-user-manual-style.css bitbake-user-manual.html figures/bitbake-title.png
+MANUALS = $(DOC)/$(DOC).html
 FIGURES = figures
 STYLESHEET = $(DOC)/*.css
 

bitbake/doc/bitbake-user-manual/bitbake-user-manual-customization.xsl

@@ -3,9 +3,15 @@
 
   <xsl:import href="http://docbook.sourceforge.net/release/xsl/current/xhtml/docbook.xsl" />
 
+  <xsl:include href="../template/permalinks.xsl"/>
+  <xsl:include href="../template/section.title.xsl"/>
+  <xsl:include href="../template/component.title.xsl"/>
+  <xsl:include href="../template/division.title.xsl"/>
+  <xsl:include href="../template/formal.object.heading.xsl"/>
+  <xsl:include href="../template/gloss-permalinks.xsl"/>
+
   <xsl:param name="html.stylesheet" select="'user-manual-style.css'" />
   <xsl:param name="chapter.autolabel" select="1" />
-<!--  <xsl:param name="appendix.autolabel" select="A" /> -->
   <xsl:param name="section.autolabel" select="1" />
   <xsl:param name="section.label.includes.component.label" select="1" />
   <xsl:param name="appendix.autolabel">A</xsl:param>

bitbake/doc/bitbake-user-manual/bitbake-user-manual-execution.xml

@@ -6,8 +6,9 @@
 
     <para>
         The primary purpose for running BitBake is to produce some kind
-        of output such as an image, a kernel, or a software development
-        kit.
+        of output such as a single installable package, a kernel, a software
+        development kit, or even a full, board-specific bootable Linux image,
+        complete with bootloader, kernel, and root filesystem.
         Of course, you can execute the <filename>bitbake</filename>
         command with options that cause it to execute single tasks,
         compile single recipe files, capture or clear data, or simply
@@ -26,15 +27,32 @@
         see
         "<link linkend='bitbake-user-manual-command'>The BitBake Command</link>"
         section.
-    </para>
+        <note>
+            <para>
+                Prior to executing BitBake, you should take advantage of available
+                parallel thread execution on your build host by setting the
+                <link linkend='var-BB_NUMBER_THREADS'><filename>BB_NUMBER_THREADS</filename></link>
+                variable in your project's <filename>local.conf</filename>
+                configuration file.
+            </para>
 
-    <note>
-        Prior to executing BitBake, you should take advantage of parallel
-        thread execution by setting the
-        <link linkend='var-BB_NUMBER_THREADS'><filename>BB_NUMBER_THREADS</filename></link>
-        variable in your <filename>local.conf</filename>
-        configuration file.
-    </note>
+            <para>
+                A common way to determine this value for your build host is to run:
+                <literallayout class='monospaced'>
+     $ grep processor /proc/cpuinfo
+                </literallayout>
+                and count the number of processors displayed. Note that the number of
+                processors will take into account hyper-threading, so that a quad-core
+                build host with hyper-threading will most likely show eight processors,
+                which is the value you would then assign to that variable.
+            </para>
+
+            <para>
+                A possibly simpler solution is that some Linux distributions
+                (e.g. Debian and Ubuntu) provide the <filename>ncpus</filename> command.
+            </para>
+        </note>
+    </para>
 
     <section id='parsing-the-base-configuration-metadata'>
         <title>Parsing the Base Configuration Metadata</title>
@@ -42,7 +60,7 @@
         <para>
             The first thing BitBake does is parse base configuration
             metadata.
-            Base configuration metadata consists of the
+            Base configuration metadata consists of your project's
             <filename>bblayers.conf</filename> file to determine what
             layers BitBake needs to recognize, all necessary
             <filename>layer.conf</filename> files (one from each layer),
@@ -71,10 +89,11 @@
             and
             <link linkend='var-BBFILES'><filename>BBFILES</filename></link>.
             <filename>BBPATH</filename> is used to search for
-            configuration and class files under
-            <filename>conf/</filename> and <filename>class/</filename>
+            configuration and class files under the
+            <filename>conf</filename> and <filename>classes</filename>
             directories, respectively.
-            <filename>BBFILES</filename> is used to find recipe files
+            <filename>BBFILES</filename> is used to locate both recipe
+            and recipe append files
             (<filename>.bb</filename> and <filename>.bbappend</filename>).
             If there is no <filename>bblayers.conf</filename> file,
             it is assumed the user has set the <filename>BBPATH</filename>
@@ -82,7 +101,7 @@
         </para>
 
         <para>
-            Next, the <filename>bitbake.conf</filename> file is searched
+            Next, the <filename>bitbake.conf</filename> file is located
             using the <filename>BBPATH</filename> variable that was
             just constructed.
             The <filename>bitbake.conf</filename> file may also include other
@@ -117,18 +136,18 @@
             optional <filename>conf/bblayers.conf</filename> configuration file.
             This file is expected to contain a
             <link linkend='var-BBLAYERS'><filename>BBLAYERS</filename></link>
-            variable that is a space delimited list of 'layer' directories.
+            variable that is a space-delimited list of 'layer' directories.
             Recall that if BitBake cannot find a <filename>bblayers.conf</filename>
-            file then it is assumed the user has set the <filename>BBPATH</filename>
-            and <filename>BBFILES</filename> directly in the environment.
+            file, then it is assumed the user has set the <filename>BBPATH</filename>
+            and <filename>BBFILES</filename> variables directly in the environment.
         </para>
 
         <para>
             For each directory (layer) in this list, a <filename>conf/layer.conf</filename>
-            file is searched for and parsed with the
+            file is located and parsed with the
             <link linkend='var-LAYERDIR'><filename>LAYERDIR</filename></link>
             variable being set to the directory where the layer was found.
-            The idea is these files automatically setup
+            The idea is these files automatically set up
             <link linkend='var-BBPATH'><filename>BBPATH</filename></link>
             and other variables correctly for a given build directory.
         </para>
@@ -143,7 +162,7 @@
 
         <para>
             Only variable definitions and include directives are allowed
-            in <filename>.conf</filename> files.
+            in BitBake <filename>.conf</filename> files.
             Some variables directly influence BitBake's behavior.
             These variables might have been set from the environment
             depending on the environment variables previously
@@ -166,7 +185,8 @@
             Other classes that are specified in the configuration using the
             <link linkend='var-INHERIT'><filename>INHERIT</filename></link>
             variable are also included.
-            BitBake searches for class files in a "classes" subdirectory under
+            BitBake searches for class files in a
+            <filename>classes</filename> subdirectory under
             the paths in <filename>BBPATH</filename> in the same way as
             configuration files.
         </para>
@@ -189,7 +209,7 @@
                 If a recipe uses a closing curly brace within the function and
                 the character has no leading spaces, BitBake produces a parsing
                 error.
-                If you use a pair of curly brace in a shell function, the
+                If you use a pair of curly braces in a shell function, the
                 closing curly brace must not be located at the start of the line
                 without leading spaces.
             </para>
@@ -261,14 +281,14 @@
             One common convention is to use the recipe filename to define
             pieces of metadata.
             For example, in <filename>bitbake.conf</filename> the recipe
-            name and version set
+            name and version are used to set the variables
             <link linkend='var-PN'><filename>PN</filename></link> and
             <link linkend='var-PV'><filename>PV</filename></link>:
             <literallayout class='monospaced'>
-     PV = "${@bb.parse.BBHandler.vars_from_file(d.getVar('FILE'),d)[1] or '1.0'}"
      PN = "${@bb.parse.BBHandler.vars_from_file(d.getVar('FILE'),d)[0] or 'defaultpkgname'}"
+     PV = "${@bb.parse.BBHandler.vars_from_file(d.getVar('FILE'),d)[1] or '1.0'}"
             </literallayout>
-            In this example, a recipe called "something_1.2.3.bb" sets
+            In this example, a recipe called "something_1.2.3.bb" would set
             <filename>PN</filename> to "something" and
             <filename>PV</filename> to "1.2.3".
         </para>
@@ -331,38 +351,55 @@
     </section>
 
     <section id='bb-bitbake-providers'>
-        <title>Preferences and Providers</title>
+        <title>Providers</title>
 
         <para>
             Assuming BitBake has been instructed to execute a target
             and that all the recipe files have been parsed, BitBake
             starts to figure out how to build the target.
-            BitBake starts by looking through the
+            BitBake looks through the <filename>PROVIDES</filename> list
+            for each of the recipes.
+            A <filename>PROVIDES</filename> list is the list of names by which
+            the recipe can be known.
+            Each recipe's <filename>PROVIDES</filename> list is created
+            implicitly through the recipe's
+            <link linkend='var-PN'><filename>PN</filename></link> variable
+            and explicitly through the recipe's
             <link linkend='var-PROVIDES'><filename>PROVIDES</filename></link>
-            set in recipe files.
-            The default <filename>PROVIDES</filename> for a recipe is its name
-            (<link linkend='var-PN'><filename>PN</filename></link>),
-            however, a recipe can provide multiple things.
+            variable, which is optional.
         </para>
 
         <para>
-            As an example of adding an extra provider, suppose a recipe named
-            <filename>foo_1.0.bb</filename> contained the following:
+            When a recipe uses <filename>PROVIDES</filename>, that recipe's
+            functionality can be found under an alternative name or names other
+            than the implicit <filename>PN</filename> name.
+            As an example, suppose a recipe named <filename>keyboard_1.0.bb</filename>
+            contained the following:
             <literallayout class='monospaced'>
-     PROVIDES += "virtual/bar_1.0"
+     PROVIDES += "fullkeyboard"
             </literallayout>
-            The recipe now provides both "foo_1.0" and "virtual/bar_1.0".
-            The "virtual/" namespace is often used to denote cases where
-            multiple providers are expected with the user choosing between
-            them.
-            Kernels and toolchain components are common cases of this in
-            OpenEmbedded.
+            The <filename>PROVIDES</filename> list for this recipe becomes
+            "keyboard", which is implicit, and "fullkeyboard", which is explicit.
+            Consequently, the functionality found in
+            <filename>keyboard_1.0.bb</filename> can be found under two
+            different names.
+        </para>
+    </section>
+
+    <section id='bb-bitbake-preferences'>
+        <title>Preferences</title>
+
+        <para>
+            The <filename>PROVIDES</filename> list is only part of the solution
+            for figuring out a target's recipes.
+            Because targets might have multiple providers, BitBake needs
+            to prioritize providers by determining provider preferences.
         </para>
 
         <para>
-            Sometimes a target might have multiple providers.
-            A common example is "virtual/kernel", which is provided by each
-            kernel recipe.
+            A common example in which a target has multiple providers
+            is "virtual/kernel", which is on the
+            <filename>PROVIDES</filename> list for each kernel recipe.
             Each machine often selects the best kernel provider by using a
             line similar to the following in the machine configuration file:
             <literallayout class='monospaced'>
@@ -377,7 +414,7 @@
 
         <para>
             Understanding how providers are chosen is made complicated by the fact
-            that multiple versions might exist.
+            that multiple versions might exist for a given provider.
             BitBake defaults to the highest version of a provider.
             Version comparisons are made using the same method as Debian.
             You can use the
@@ -386,13 +423,19 @@
             You can influence the order by using the
             <link linkend='var-DEFAULT_PREFERENCE'><filename>DEFAULT_PREFERENCE</filename></link>
             variable.
+        </para>
+
+        <para>
             By default, files have a preference of "0".
-            Setting the <filename>DEFAULT_PREFERENCE</filename> to "-1" makes the
+            Setting <filename>DEFAULT_PREFERENCE</filename> to "-1" makes the
             recipe unlikely to be used unless it is explicitly referenced.
-            Setting the <filename>DEFAULT_PREFERENCE</filename> to "1" makes it likely the recipe is used.
-            <filename>PREFERRED_VERSION</filename> overrides any <filename>DEFAULT_PREFERENCE</filename> setting.
-            <filename>DEFAULT_PREFERENCE</filename> is often used to mark newer and more experimental recipe
-            versions until they have undergone sufficient testing to be considered stable.
+            Setting <filename>DEFAULT_PREFERENCE</filename> to "1" makes it
+            likely the recipe is used.
+            <filename>PREFERRED_VERSION</filename> overrides any
+            <filename>DEFAULT_PREFERENCE</filename> setting.
+            <filename>DEFAULT_PREFERENCE</filename> is often used to mark newer
+            and more experimental recipe versions until they have undergone
+            sufficient testing to be considered stable.
         </para>
 
         <para>
@@ -401,18 +444,16 @@
             version, unless otherwise specified.
             If the recipe in question has a
             <link linkend='var-DEFAULT_PREFERENCE'><filename>DEFAULT_PREFERENCE</filename></link>
-            set lower than
-            the other recipes (default is 0), then it will not be
-            selected.
+            set lower than the other recipes (default is 0), then
+            it will not be selected.
             This allows the person or persons maintaining
             the repository of recipe files to specify
             their preference for the default selected version.
-            In addition, the user can specify their preferred version.
+            Additionally, the user can specify their preferred version.
         </para>
 
         <para>
-            If the first recipe is named <filename>a_1.1.bb</filename>,
-            then the
+            If the first recipe is named <filename>a_1.1.bb</filename>, then the
             <link linkend='var-PN'><filename>PN</filename></link> variable
             will be set to “a”, and the
             <link linkend='var-PV'><filename>PV</filename></link>
@@ -420,19 +461,38 @@
         </para>
 
         <para>
-            If we then have a recipe named <filename>a_1.2.bb</filename>, BitBake
+            Thus, if a recipe named <filename>a_1.2.bb</filename> exists, BitBake
             will choose 1.2 by default.
-            However, if we define the following variable in a
-            <filename>.conf</filename> file that BitBake parses, we
-            can change that.
+            However, if you define the following variable in a
+            <filename>.conf</filename> file that BitBake parses, you
+            can change that preference:
             <literallayout class='monospaced'>
      PREFERRED_VERSION_a = "1.1"
             </literallayout>
         </para>
 
-        <para>
-            In summary, BitBake has created a list of providers, which is prioritized, for each target.
-        </para>
+        <note>
+            <para>
+                It is common for a recipe to provide two versions -- a stable,
+                numbered (and preferred) version, and a version that is
+                automatically checked out from a source code repository that
+                is considered more "bleeding edge" but can be selected only
+                explicitly.
+            </para>
+
+            <para>
+                For example, in the OpenEmbedded codebase, there is a standard,
+                versioned recipe file for BusyBox,
+                <filename>busybox_1.22.1.bb</filename>,
+                but there is also a Git-based version,
+                <filename>busybox_git.bb</filename>, which explicitly contains the line
+                <literallayout class='monospaced'>
+    DEFAULT_PREFERENCE = "-1"
+                </literallayout>
+                to ensure that the numbered, stable version is always preferred
+                unless the developer selects otherwise.
+            </para>
+        </note>
     </section>
 
     <section id='bb-bitbake-dependencies'>
@@ -495,7 +555,7 @@
             As each task completes, a timestamp is written to the directory specified by the
             <link linkend='var-STAMP'><filename>STAMP</filename></link> variable.
             On subsequent runs, BitBake looks in the build directory within
-            <filename>tmp/stamps</filename>and does not rerun
+            <filename>tmp/stamps</filename> and does not rerun
             tasks that are already completed unless a timestamp is found to be invalid.
             Currently, invalid timestamps are only considered on a per
             recipe file basis.
@@ -535,7 +595,7 @@
         <title>Executing Tasks</title>
 
         <para>
-            Tasks can either be a shell task or a Python task.
+            Tasks can be either a shell task or a Python task.
             For shell tasks, BitBake writes a shell script to
             <filename>${</filename><link linkend='var-T'><filename>T</filename></link><filename>}/run.do_taskname.pid</filename>
             and then executes the script.
@@ -755,9 +815,9 @@
             to determine the stamps and delta where these two
             stamp trees diverge.
             <note>
-                It is likely that future versions of BitBake with
+                It is likely that future versions of BitBake will
                 provide other signature handlers triggered through
-                additional "-S" paramters.
+                additional "-S" parameters.
             </note>
         </para>
 

bitbake/doc/bitbake-user-manual/bitbake-user-manual-fetching.xml

@@ -8,14 +8,14 @@
         BitBake's fetch module is a standalone piece of library code
         that deals with the intricacies of downloading source code
         and files from remote systems.
-        Fetching source code is one of the corner stones of building software.
+        Fetching source code is one of the cornerstones of building software.
         As such, this module forms an important part of BitBake.
     </para>
 
     <para>
         The current fetch module is called "fetch2" and refers to the
         fact that it is the second major version of the API.
-        The original version is obsolete and removed from the codebase.
+        The original version is obsolete and has been removed from the codebase.
         Thus, in all cases, "fetch" refers to "fetch2" in this
         manual.
     </para>
@@ -60,17 +60,19 @@
             <note>
                 For convenience, the naming in these examples matches
                 the variables used by OpenEmbedded.
+                If you want to see the above code in action, examine
+                the OpenEmbedded class file <filename>base.bbclass</filename>.
             </note>
             The <filename>SRC_URI</filename> and <filename>WORKDIR</filename>
-            variables are not coded into the fetcher.
-            They variables can (and are) called with different variable names.
+            variables are not hardcoded into the fetcher, since those fetcher
+            methods can be (and are) called with different variable names.
             In OpenEmbedded for example, the shared state (sstate) code uses
             the fetch module to fetch the sstate files.
         </para>
 
         <para>
             When the <filename>download()</filename> method is called,
-            BitBake tries to fulfill the URLs by looking for source files
+            BitBake tries to resolve the URLs by looking for source files
             in a specific search order:
             <itemizedlist>
                 <listitem><para><emphasis>Pre-mirror Sites:</emphasis>
@@ -84,7 +86,7 @@
                     <filename>SRC_URI</filename>).
                     </para></listitem>
                 <listitem><para><emphasis>Mirror Sites:</emphasis>
-                    If fetch failures occur, BitBake next uses mirror location as
+                    If fetch failures occur, BitBake next uses mirror locations as
                     defined by the
                     <link linkend='var-MIRRORS'><filename>MIRRORS</filename></link>
                     variable.
@@ -149,7 +151,7 @@
         <para>
             File integrity is of key importance for reproducing builds.
             For non-local archive downloads, the fetcher code can verify
-            sha256 and md5 checksums to ensure the archives have been
+            SHA-256 and MD5 checksums to ensure the archives have been
             downloaded correctly.
             You can specify these checksums by using the
             <filename>SRC_URI</filename> variable with the appropriate
@@ -260,8 +262,8 @@
             <para>
                 This submodule handles URLs that begin with
                 <filename>file://</filename>.
-                The filename you specify with in the URL can
-                either be an absolute or relative path to a file.
+                The filename you specify within the URL can be
+                either an absolute or relative path to a file.
                 If the filename is relative, the contents of the
                 <link linkend='var-FILESPATH'><filename>FILESPATH</filename></link>
                 variable is used in the same way
@@ -286,15 +288,45 @@
             </para>
 
             <para>
-                Here are some example URLs:
+                Here are a couple of example URLs, the first relative and
+                the second absolute:
                 <literallayout class='monospaced'>
      SRC_URI = "file://relativefile.patch"
-     SRC_URI = "file://relativefile.patch;this=ignored"
      SRC_URI = "file:///Users/ich/very_important_software"
                 </literallayout>
             </para>
         </section>
 
+        <section id='http-ftp-fetcher'>
+            <title>HTTP/FTP wget fetcher (<filename>http://</filename>, <filename>ftp://</filename>, <filename>https://</filename>)</title>
+
+            <para>
+                This fetcher obtains files from web and FTP servers.
+                Internally, the fetcher uses the wget utility.
+            </para>
+
+            <para>
+                The executable and parameters used are specified by the
+                <filename>FETCHCMD_wget</filename> variable, which defaults
+                to sensible values.
+                The fetcher supports a parameter "downloadfilename" that
+                allows the name of the downloaded file to be specified.
+                Specifying the name of the downloaded file is useful
+                for avoiding collisions in
+                <link linkend='var-DL_DIR'><filename>DL_DIR</filename></link>
+                when dealing with multiple files that have the same name.
+            </para>
+
+            <para>
+                Some example URLs are as follows:
+                <literallayout class='monospaced'>
+     SRC_URI = "http://oe.handhelds.org/not_there.aac"
+     SRC_URI = "ftp://oe.handhelds.org/not_there_as_well.aac"
+     SRC_URI = "ftp://you@oe.handhelds.org/home/you/secret.plan"
+                </literallayout>
+            </para>
+        </section>
+
         <section id='cvs-fetcher'>
             <title>CVS fetcher (<filename>(cvs://</filename>)</title>
 
@@ -313,7 +345,7 @@
                         A special value of "now" causes the checkout to
                         be updated on every build.
                         </para></listitem>
-                    <listitem><para><emphasis><filename>CVSDIR</filename>:</emphasis>
+                    <listitem><para><emphasis><link linkend='var-CVSDIR'><filename>CVSDIR</filename></link>:</emphasis>
                         Specifies where a temporary checkout is saved.
                         The location is often <filename>DL_DIR/cvs</filename>.
                         </para></listitem>
@@ -334,7 +366,7 @@
                 The supported parameters are as follows:
                 <itemizedlist>
                     <listitem><para><emphasis>"method":</emphasis>
-                        The protocol over which to communicate with the cvs server.
+                        The protocol over which to communicate with the CVS server.
                         By default, this protocol is "pserver".
                         If "method" is set to "ext", BitBake examines the
                         "rsh" parameter and sets <filename>CVS_RSH</filename>.
@@ -362,7 +394,8 @@
                         Effectively, you are renaming the output directory
                         to which the module is unpacked.
                         You are forcing the module into a special
-                        directory relative to <filename>CVSDIR</filename>.
+                        directory relative to
+                        <link linkend='var-CVSDIR'><filename>CVSDIR</filename></link>.
                         </para></listitem>
                     <listitem><para><emphasis>"rsh"</emphasis>
                         Used in conjunction with the "method" parameter.
@@ -394,36 +427,6 @@
             </para>
         </section>
 
-        <section id='http-ftp-fetcher'>
-            <title>HTTP/FTP wget fetcher (<filename>http://</filename>, <filename>ftp://</filename>, <filename>https://</filename>)</title>
-
-            <para>
-                This fetcher obtains files from web and FTP servers.
-                Internally, the fetcher uses the wget utility.
-            </para>
-
-            <para>
-                The executable and parameters used are specified by the
-                <filename>FETCHCMD_wget</filename> variable, which defaults
-                to a sensible values.
-                The fetcher supports a parameter "downloadfilename" that
-                allows the name of the downloaded file to be specified.
-                Specifying the name of the downloaded file is useful
-                for avoiding collisions in
-                <link linkend='var-DL_DIR'><filename>DL_DIR</filename></link>
-                when dealing with multiple files that have the same name.
-            </para>
-
-            <para>
-                Some example URLs are as follows:
-                <literallayout class='monospaced'>
-     SRC_URI = "http://oe.handhelds.org/not_there.aac"
-     SRC_URI = "ftp://oe.handhelds.org/not_there_as_well.aac"
-     SRC_URI = "ftp://you@oe.handheld.sorg/home/you/secret.plan"
-                </literallayout>
-            </para>
-        </section>
-
         <section id='svn-fetcher'>
             <title>Subversion (SVN) Fetcher (<filename>svn://</filename>)</title>
 
@@ -433,9 +436,9 @@
                 The executable used is specified by
                 <filename>FETCHCMD_svn</filename>, which defaults
                 to "svn".
-                The fetcher's temporary working directory is set
-                by <filename>SVNDIR</filename>, which is usually
-                <filename>DL_DIR/svn</filename>.
+                The fetcher's temporary working directory is set by
+                <link linkend='var-SVNDIR'><filename>SVNDIR</filename></link>,
+                which is usually <filename>DL_DIR/svn</filename>.
             </para>
 
             <para>
@@ -466,6 +469,13 @@
                         compile-time when set to "keep".
                         By default, these directories are removed.
                         </para></listitem>
+                    <listitem><para><emphasis>"transportuser":</emphasis>
+                        When required, sets the username for the transport.
+                        By default, this parameter is empty.
+                        The transport username is different than the username
+                        used in the main URL, which is passed to the subversion
+                        command.
+                        </para></listitem>
                 </itemizedlist>
                 Following are two examples using svn:
                 <literallayout class='monospaced'>
@@ -476,14 +486,15 @@
         </section>
 
         <section id='git-fetcher'>
-            <title>GIT Fetcher (<filename>git://</filename>)</title>
+            <title>Git Fetcher (<filename>git://</filename>)</title>
 
             <para>
                 This fetcher submodule fetches code from the Git
                 source control system.
                 The fetcher works by creating a bare clone of the
-                remote into <filename>GITDIR</filename>, which is
-                usually <filename>DL_DIR/git</filename>.
+                remote into
+                <link linkend='var-GITDIR'><filename>GITDIR</filename></link>,
+                which is usually <filename>DL_DIR/git2</filename>.
                 This bare clone is then cloned into the work directory during the
                 unpack stage when a specific tree is checked out.
                 This is done using alternates and by reference to
@@ -551,7 +562,7 @@
                         network.
                         For that reason, tags are often not used.
                         As far as Git is concerned, the "tag" parameter behaves
-                        effectively the same as the "revision" parameter.
+                        effectively the same as the "rev" parameter.
                         </para></listitem>
                     <listitem><para><emphasis>"subpath":</emphasis>
                         Limits the checkout to a specific subpath of the tree.
@@ -570,6 +581,116 @@
             </para>
         </section>
 
+        <section id='gitsm-fetcher'>
+            <title>Git Submodule Fetcher (<filename>gitsm://</filename>)</title>
+
+            <para>
+                This fetcher submodule inherits from the
+                <link linkend='git-fetcher'>Git fetcher</link> and extends
+                that fetcher's behavior by fetching a repository's submodules.
+                <link linkend='var-SRC_URI'><filename>SRC_URI</filename></link>
+                is passed to the Git fetcher as described in the
+                "<link linkend='git-fetcher'>Git Fetcher (<filename>git://</filename>)</link>"
+                section.
+                <note>
+                    <title>Notes and Warnings</title>
+                    <para>
+                        You must clean a recipe when switching between
+                        '<filename>git://</filename>' and
+                        '<filename>gitsm://</filename>' URLs.
+                    </para>
+
+                    <para>
+                        The Git Submodules fetcher is not a complete fetcher
+                        implementation.
+                        The fetcher has known issues where it does not use the
+                        normal source mirroring infrastructure properly.
+                    </para>
+                </note>
+            </para>
+        </section>
+
+        <section id='clearcase-fetcher'>
+            <title>ClearCase Fetcher (<filename>ccrc://</filename>)</title>
+
+            <para>
+                This fetcher submodule fetches code from a
+                <ulink url='http://en.wikipedia.org/wiki/Rational_ClearCase'>ClearCase</ulink>
+                repository.
+            </para>
+
+            <para>
+                To use this fetcher, make sure your recipe has proper
+                <link linkend='var-SRC_URI'><filename>SRC_URI</filename></link>,
+                <link linkend='var-SRCREV'><filename>SRCREV</filename></link>, and
+                <link linkend='var-PV'><filename>PV</filename></link> settings.
+                Here is an example:
+                <literallayout class='monospaced'>
+     SRC_URI = "ccrc://cc.example.org/ccrc;vob=/example_vob;module=/example_module"
+     SRCREV = "EXAMPLE_CLEARCASE_TAG"
+     PV = "${@d.getVar("SRCREV").replace("/", "+")}"
+                </literallayout>
+                The fetcher uses the <filename>rcleartool</filename> or
+                <filename>cleartool</filename> remote client, depending on
+                which one is available.
+            </para>
+
+            <para>
+                Following are options for the <filename>SRC_URI</filename>
+                statement:
+                <itemizedlist>
+                    <listitem><para><emphasis><filename>vob</filename></emphasis>:
+                        The name, which must include the
+                        prepending "/" character, of the ClearCase VOB.
+                        This option is required.
+                        </para></listitem>
+                    <listitem><para><emphasis><filename>module</filename></emphasis>:
+                        The module, which must include the
+                        prepending "/" character, in the selected VOB
+                        The <filename>module</filename> and <filename>vob</filename>
+                        options are combined to create the following load rule in
+                        the view config spec:
+                        <literallayout class='monospaced'>
+     load &lt;vob&gt;&lt;module&gt;
+                        </literallayout>
+                        </para></listitem>
+                    <listitem><para><emphasis><filename>proto</filename></emphasis>:
+                        The protocol, which can be either <filename>http</filename> or
+                        <filename>https</filename>.
+                        </para></listitem>
+                </itemizedlist>
+            </para>
+
+            <para>
+                By default, the fetcher creates a configuration specification.
+                If you want this specification written to an area other than the default,
+                use the <filename>CCASE_CUSTOM_CONFIG_SPEC</filename> variable
+                in your recipe to define where the specification is written.
+                <note>
+                    the <filename>SRCREV</filename> loses its functionality if you
+                    specify this variable.
+                    However, <filename>SRCREV</filename> is still used to label the
+                    archive after a fetch even though it does not define what is
+                    fetched.
+                </note>
+            </para>
+
+            <para>
+                Here are a couple of other behaviors worth mentioning:
+                <itemizedlist>
+                    <listitem><para>
+                        When using <filename>cleartool</filename>, the login of
+                        <filename>cleartool</filename> is handled by the system.
+                        The login require no special steps.
+                        </para></listitem>
+                    <listitem><para>
+                        In order to use <filename>rcleartool</filename> with authenticated
+                        users, an "rcleartool login" is necessary before using the fetcher.
+                        </para></listitem>
+                </itemizedlist>
+            </para>
+        </section>
+
         <section id='other-fetchers'>
             <title>Other Fetchers</title>
 
@@ -582,9 +703,6 @@
                     <listitem><para>
                         Perforce (<filename>p4://</filename>)
                         </para></listitem>
-                    <listitem><para>
-                        Git Submodules (<filename>gitsm://</filename>)
-                        </para></listitem>
                     <listitem><para>
                         Trees using Git Annex (<filename>gitannex://</filename>)
                         </para></listitem>

bitbake/doc/bitbake-user-manual/bitbake-user-manual-hello.xml

@@ -471,7 +471,7 @@ ERROR: Unable to parse base: ParseError in configuration INHERITs: Could not inh
      Time: 00:00:00
      Parsing of 1 .bb files complete (0 cached, 1 parsed). 1 targets, 0 skipped, 0 masked, 0 errors.
      NOTE: Resolving any missing task queue dependencies
-     NOTE: Preparing runqueue
+     NOTE: Preparing RunQueue
      NOTE: Executing RunQueue Tasks
      ********************
      *                  *

bitbake/doc/bitbake-user-manual/bitbake-user-manual-intro.xml

@@ -8,9 +8,9 @@
         Welcome to the BitBake User Manual.
         This manual provides information on the BitBake tool.
         The information attempts to be as independent as possible regarding
-        systems that use BitBake, such as the Yocto Project and
-        OpenEmbedded.
-        In some cases, scenarios or examples that within the context of
+        systems that use BitBake, such as OpenEmbedded and the
+        Yocto Project.
+        In some cases, scenarios or examples within the context of
         a build system are used in the manual to help with understanding.
         For these cases, the manual clearly states the context.
     </para>
@@ -35,28 +35,31 @@
                 <listitem><para>
                     BitBake executes tasks according to provided
                     metadata that builds up the tasks.
-                    Metadata is stored in recipe (<filename>.bb</filename>),
-                    configuration (<filename>.conf</filename>), and class
-                    (<filename>.bbclass</filename>) files and provides
+                    Metadata is stored in recipe (<filename>.bb</filename>)
+                    and related recipe "append" (<filename>.bbappend</filename>)
+                    files, configuration (<filename>.conf</filename>) and
+                    underlying include (<filename>.inc</filename>) files, and
+                    in class (<filename>.bbclass</filename>) files.
+                    The metadata provides
                     BitBake with instructions on what tasks to run and
                     the dependencies between those tasks.
                     </para></listitem>
                 <listitem><para>
                     BitBake includes a fetcher library for obtaining source
-                    code from various places such as source control
-                    systems or websites.
+                    code from various places such as local files, source control
+                    systems, or websites.
                     </para></listitem>
                 <listitem><para>
                     The instructions for each unit to be built (e.g. a piece
-                    of software) are known as recipe files and
+                    of software) are known as "recipe" files and
                     contain all the information about the unit
                     (dependencies, source file locations, checksums, description
                     and so on).
                     </para></listitem>
                 <listitem><para>
                     BitBake includes a client/server abstraction and can
-                    be used from a command line or used as a service over XMLRPC and
-                    has several different user interfaces.
+                    be used from a command line or used as a service over
+                    XML-RPC and has several different user interfaces.
                     </para></listitem>
             </itemizedlist>
         </para>
@@ -69,7 +72,7 @@
             BitBake was originally a part of the OpenEmbedded project.
             It was inspired by the Portage package management system
             used by the Gentoo Linux distribution.
-            On December 7, 2004, OpenEmbedded project team member,
+            On December 7, 2004, OpenEmbedded project team member
             Chris Larson split the project into two distinct pieces:
             <itemizedlist>
                 <listitem><para>BitBake, a generic task executor</para></listitem>
@@ -79,8 +82,11 @@
             Today, BitBake is the primary basis of the
             <ulink url="http://www.openembedded.org/">OpenEmbedded</ulink>
             project, which is being used to build and maintain Linux
-            distributions such as the Angstrom Distribution and which is used
-            as the build tool for Linux projects such as the Yocto Project.
+            distributions such as the
+            <ulink url='http://www.angstrom-distribution.org/'>Angstrom Distribution</ulink>,
+            and which is also being used as the build tool for Linux projects
+            such as the
+            <ulink url='http://www.yoctoproject.org'>Yocto Project</ulink>.
         </para>
 
         <para>
@@ -88,7 +94,7 @@
             an aspiring embedded Linux distribution.
             All of the build systems used by traditional desktop Linux
             distributions lacked important functionality, and none of the
-            ad-hoc Buildroot-based systems, prevalent in the
+            ad hoc Buildroot-based systems, prevalent in the
             embedded space, were scalable or maintainable.
         </para>
 
@@ -138,7 +144,7 @@
                     projects for their builds.
                     </para></listitem>
                 <listitem><para>
-                    Provide an inheritance mechanism that share
+                    Provide an inheritance mechanism to share
                     common metadata between many packages.
                     </para></listitem>
             </itemizedlist>
@@ -151,7 +157,7 @@
                     </para></listitem>
                 <listitem><para>
                     Split metadata into layers and allow layers
-                    to override each other.
+                    to enhance or override other layers.
                     </para></listitem>
                 <listitem><para>
                     Allow representation of a given set of input variables
@@ -178,14 +184,14 @@
             what tasks are required to run, and executes those tasks.
             Similar to GNU Make, BitBake controls how software is
             built.
-            GNU Make achieves its control through "makefiles".
+            GNU Make achieves its control through "makefiles", while
             BitBake uses "recipes".
         </para>
 
         <para>
             BitBake extends the capabilities of a simple
-            tool like GNU Make by allowing for much more complex tasks
-            to be completed, such as assembling entire embedded Linux
+            tool like GNU Make by allowing for the definition of much more
+            complex tasks, such as assembling entire embedded Linux
             distributions.
         </para>
 
@@ -203,14 +209,20 @@
                 <filename>.bb</filename>, are the most basic metadata files.
                 These recipe files provide BitBake with the following:
                 <itemizedlist>
-                    <listitem><para>Descriptive information about the package</para></listitem>
+                    <listitem><para>Descriptive information about the
+                        package (author, homepage, license, and so on)</para></listitem>
                     <listitem><para>The version of the recipe</para></listitem>
-                    <listitem><para>Existing Dependencies</para></listitem>
-                    <listitem><para>Where the source code resides</para></listitem>
-                    <listitem><para>Whether the source code requires any patches</para></listitem>
-                    <listitem><para>How to compile the source code</para></listitem>
+                    <listitem><para>Existing dependencies (both build
+                        and runtime dependencies)</para></listitem>
+                    <listitem><para>Where the source code resides and
+                        how to fetch it</para></listitem>
+                    <listitem><para>Whether the source code requires
+                        any patches, where to find them, and how to apply
+                        them</para></listitem>
+                    <listitem><para>How to configure and compile the
+                        source code</para></listitem>
                     <listitem><para>Where on the target machine to install the
-                        package being compiled</para></listitem>
+                        package or packages created</para></listitem>
                 </itemizedlist>
             </para>
 
@@ -222,7 +234,11 @@
                     The term "package" is also commonly used to describe recipes.
                     However, since the same word is used to describe packaged
                     output from a project, it is best to maintain a single
-                    descriptive term, "recipes".
+                    descriptive term - "recipes".
+                    Put another way, a single "recipe" file is quite capable
+                    of generating a number of related but separately installable
+                    "packages".
+                    In fact, that ability is fairly common.
                 </note>
             </para>
         </section>
@@ -257,7 +273,7 @@
                 called <filename>base.bbclass</filename>.
                 You can find this file in the
                 <filename>classes</filename> directory.
-                The <filename>base.bbclass</filename> is special since it
+                The <filename>base.bbclass</filename> class files is special since it
                 is always included automatically for all recipes
                 and classes.
                 This class contains definitions for standard basic tasks such
@@ -284,7 +300,8 @@
                 To illustrate how you can use layers to keep things modular,
                 consider customizations you might make to support a specific target machine.
                 These types of customizations typically reside in a special layer,
-                rather than a general layer, called a Board Specific Package (BSP) Layer.
+                rather than a general layer, called a Board Support Package (BSP)
+                Layer.
                 Furthermore, the machine customizations should be isolated from
                 recipes and metadata that support a new GUI environment, for
                 example.
@@ -304,9 +321,8 @@
 
             <para>
                 Append files, which are files that have the
-                <filename>.bbappend</filename> file extension, add or
-                extend build information to an existing
-                recipe file.
+                <filename>.bbappend</filename> file extension, extend or
+                override information in an existing recipe file.
             </para>
 
             <para>
@@ -319,8 +335,9 @@
             </para>
 
             <para>
-                Information in append files overrides the information in the
-                similarly-named recipe file.
+                Information in append files extends or
+                overrides the information in the underlying,
+                similarly-named recipe files.
             </para>
 
             <para>
@@ -345,6 +362,12 @@
                 However, if you named the append file
                 <filename>busybox_1.%.bbappend</filename>, then you would have a match.
             </para>
+
+            <para>
+                In the most general case, you could name the append file something as
+                simple as <filename>busybox_%.bbappend</filename> to be entirely
+                version independent.
+            </para>
         </section>
     </section>
 
@@ -413,6 +436,20 @@
                     you have a directory entitled
                     <filename>bitbake-1.17.0</filename>.
                     </para></listitem>
+                <listitem><para><emphasis>Using the BitBake that Comes With Your
+                    Build Checkout:</emphasis>
+                    A final possibility for getting a copy of BitBake is that it
+                    already comes with your checkout of a larger Bitbake-based build
+                    system, such as Poky or Yocto Project.
+                    Rather than manually checking out individual layers and
+                    gluing them together yourself, you can check
+                    out an entire build system.
+                    The checkout will already include a version of BitBake that
+                    has been thoroughly tested for compatibility with the other
+                    components.
+                    For information on how to check out a particular BitBake-based
+                    build system, consult that build system's supporting documentation.
+                    </para></listitem>
             </itemizedlist>
         </para>
     </section>
@@ -471,14 +508,16 @@
        -D, --debug           Increase the debug level. You can specify this more
                              than once.
        -n, --dry-run         Don't execute, just go through the motions.
-       -S DUMP_SIGNATURES, --dump-signatures=DUMP_SIGNATURES
+       -S SIGNATURE_HANDLER, --dump-signatures=SIGNATURE_HANDLER
                              Dump out the signature construction information, with
-                             no task execution. Parameters are passed to the
-                             signature handling code, use 'none' if no specific
-                             handler is required.
+                             no task execution. The SIGNATURE_HANDLER parameter is
+                             passed to the handler. Two common values are none and
+                             printdiff but the handler may define more/less. none
+                             means only dump the signature, printdiff means compare
+                             the dumped signature with the cached one.
        -p, --parse-only      Quit after parsing the BB recipes.
        -s, --show-versions   Show current and preferred versions of all recipes.
-       -e, --environment     Show the global or per-package environment complete
+       -e, --environment     Show the global or per-recipe environment complete
                              with information about where variables were
                              set/changed.
        -g, --graphviz        Save dependency tree information for the specified
@@ -493,6 +532,8 @@
        -u UI, --ui=UI        The user interface to use (e.g. knotty, hob, depexp).
        -t SERVERTYPE, --servertype=SERVERTYPE
                              Choose which server to use, process or xmlrpc.
+       --token=XMLRPCTOKEN   Specify the connection token to be used when
+                             connecting to a remote server.
        --revisions-changed   Set the exit code depending on whether upstream
                              floating revisions have changed or not.
        --server-only         Run bitbake without a UI, only starting a server
@@ -559,14 +600,14 @@
                     when one wants to manage multiple <filename>.bb</filename>
                     files.
                     Clearly there needs to be a way to tell BitBake what
-                    files are available, and of those, which you
+                    files are available and, of those, which you
                     want to execute.
                     There also needs to be a way for each recipe
                     to express its dependencies, both for build-time and
                     runtime.
                     There must be a way for you to express recipe preferences
                     when multiple recipes provide the same functionality, or when
-                    there are multiple versions of a  recipe.
+                    there are multiple versions of a recipe.
                 </para>
 
                 <para>

bitbake/doc/bitbake-user-manual/bitbake-user-manual-metadata.xml

@@ -159,6 +159,10 @@
                 using the "+=" and "=+" operators.
                 These operators insert a space between the current
                 value and prepended or appended value.
+            </para>
+
+            <para>
+                These operators take immediate effect during parsing.
                 Here are some examples:
                 <literallayout class='monospaced'>
      B = "bval"
@@ -178,6 +182,10 @@
             <para>
                 If you want to append or prepend values without an
                 inserted space, use the ".=" and "=." operators.
+            </para>
+
+            <para>
+                These operators take immediate effect during parsing.
                 Here are some examples:
                 <literallayout class='monospaced'>
      B = "bval"
@@ -198,6 +206,13 @@
                 You can also append and prepend a variable's value
                 using an override style syntax.
                 When you use this syntax, no spaces are inserted.
+            </para>
+
+            <para>
+                These operators differ from the ":=", ".=", "=.", "+=", and "=+"
+                operators in that their effects are deferred
+                until after parsing completes rather than being immediately
+                applied.
                 Here are some examples:
                 <literallayout class='monospaced'>
      B = "bval"
@@ -217,13 +232,6 @@
                     override syntax.
                 </note>
             </para>
-
-            <para>
-                The operators "_append" and "_prepend" differ from
-                the operators ".=" and "=." in that they are deferred
-                until after parsing completes rather than being immediately
-                applied.
-            </para>
         </section>
 
         <section id='removing-override-style-syntax'>
@@ -283,7 +291,18 @@
                 The variable <filename>FOO</filename> has two flags:
                 <filename>a</filename> and <filename>b</filename>.
                 The flags are immediately set to "abc" and "123", respectively.
-                The <filename>a</filename> flag becomes "abc456".
+                The <filename>a</filename> flag becomes "abc 456".
+            </para>
+
+            <para>
+                No need exists to pre-define variable flags.
+                You can simply start using them.
+                One extremely common application
+                is to attach some brief documentation to a BitBake variable as
+                follows:
+                <literallayout class='monospaced'>
+     CACHE[doc] = "The directory holding the cache of the metadata."
+                </literallayout>
             </para>
         </section>
 
@@ -298,7 +317,19 @@
      DATE = "${@time.strftime('%Y%m%d',time.gmtime())}"
                 </literallayout>
                 This example results in the <filename>DATE</filename>
-                variable becoming the current date.
+                variable being set to the current date.
+            </para>
+
+            <para>
+                Probably the most common use of this feature is to extract
+                the value of variables from BitBake's internal data dictionary,
+                <filename>d</filename>.
+                The following lines select the values of a package name
+                and its version number, respectively:
+                <literallayout class='monospaced'>
+     PN = "${@bb.parse.BBHandler.vars_from_file(d.getVar('FILE'),d)[0] or 'defaultpkgname'}"
+     PV = "${@bb.parse.BBHandler.vars_from_file(d.getVar('FILE'),d)[1] or '1.0'}"
+                </literallayout>
             </para>
         </section>
 
@@ -372,6 +403,25 @@
                         You select the os-specific version of the <filename>TEST</filename>
                         variable by appending the "os" override to the variable
                         (i.e.<filename>TEST_os</filename>).
+                        </para>
+
+                        <para>
+                            To better understand this, consider a practical example
+                            that assumes an OpenEmbedded metadata-based Linux
+                            kernel recipe file.
+                            The following lines from the recipe file first set
+                            the kernel branch variable <filename>KBRANCH</filename>
+                            to a default value, then conditionally override that
+                            value based on the architecture of the build:
+                        <literallayout class='monospaced'>
+     KBRANCH = "standard/base"
+     KBRANCH_qemuarm  = "standard/arm-versatile-926ejs"
+     KBRANCH_qemumips = "standard/mti-malta32"
+     KBRANCH_qemuppc  = "standard/qemuppc"
+     KBRANCH_qemux86  = "standard/common-pc/base"
+     KBRANCH_qemux86-64  = "standard/common-pc-64/base"
+     KBRANCH_qemumips64 = "standard/mti-malta64"
+                        </literallayout>
                         </para></listitem>
                     <listitem><para><emphasis>Appending and Prepending:</emphasis>
                         BitBake also supports append and prepend operations to
@@ -385,6 +435,19 @@
                         </literallayout>
                         In this example, <filename>DEPENDS</filename> becomes
                         "glibc ncurses libmad".
+                        </para>
+
+                        <para>
+                            Again, using an OpenEmbedded metadata-based
+                            kernel recipe file as an example, the
+                            following lines will conditionally append to the
+                            <filename>KERNEL_FEATURES</filename> variable based
+                            on the architecture:
+                        <literallayout class='monospaced'>
+     KERNEL_FEATURES_append = " ${KERNEL_EXTRA_FEATURES}"
+     KERNEL_FEATURES_append_qemux86=" cfg/sound.scc cfg/paravirt_kvm.scc"
+     KERNEL_FEATURES_append_qemux86-64=" cfg/sound.scc cfg/paravirt_kvm.scc"
+                        </literallayout>
                         </para></listitem>
                 </itemizedlist>
             </para>
@@ -1077,8 +1140,6 @@
                 <filename>DISPLAY</filename> variable.
                 Here is an example:
                 <literallayout class='monospaced'>
-     BB_ORIGENV - add example?
-
      origenv = d.getVar("BB_ORIGENV", False)
      bar = origenv.getVar("BAR", False)
                 </literallayout>
@@ -1140,12 +1201,6 @@
                     Tells BitBake to not generate a stamp file for a task,
                     which implies the task should always be executed.
                     </para></listitem>
-                <listitem><para><emphasis>fakeroot:</emphasis>
-                    Causes a task to be run in a fakeroot environment,
-                    obtained by adding the variables in
-                    <link linkend='var-FAKEROOTENV'><filename>FAKEROOTENV</filename></link>
-                    to the environment.
-                    </para></listitem>
                 <listitem><para><emphasis>umask:</emphasis>
                     The umask to run the task under.
                     </para></listitem>
@@ -1251,8 +1306,8 @@
             BitBake allows installation of event handlers within
             recipe and class files.
             Events are triggered at certain points during operation,
-            such as the beginning of operation against a given
-            <filename>.bb</filename>, the start of a given task,
+            such as the beginning of an operation against a given recipe
+            (<filename>*.bb</filename> file), the start of a given task,
             task failure, task success, and so forth.
             The intent is to make it easy to do things like email
             notification on build failure.
@@ -1280,6 +1335,27 @@
             the name of the triggered event.
         </para>
 
+        <para>
+            Because you probably are only interested in a subset of events,
+            you would likely use the <filename>[eventmask]</filename> flag
+            for your event handler to be sure that only certain events
+            trigger the handler.
+            Given the previous example, suppose you only wanted the
+            <filename>bb.build.TaskFailed</filename> event to trigger that
+            event handler.
+            Use the flag as follows:
+            <literallayout class='monospaced'>
+     addhandler myclass_eventhandler
+     myclass_eventhandler[eventmask] = "bb.build.TaskFailed"
+     python myclass_eventhandler() {
+         from bb.event import getName
+         from bb import data
+         print("The name of the Event is %s" % getName(e))
+         print("The file we run for is %s" % data.getVar('FILE', e.data, True))
+     }
+            </literallayout>
+        </para>
+
         <para>
             During a standard build, the following common events might occur:
             <itemizedlist>
@@ -1466,9 +1542,9 @@
                 complete before that task can be executed.
                 Here is an example:
                 <literallayout class='monospaced'>
-     do_configure[deptask] = "do_populate_staging"
+     do_configure[deptask] = "do_populate_sysroot"
                 </literallayout>
-                In this example, the <filename>do_populate_staging</filename>
+                In this example, the <filename>do_populate_sysroot</filename>
                 task of each item in <filename>DEPENDS</filename> must complete before
                 <filename>do_configure</filename> can execute.
             </para>
@@ -1494,11 +1570,11 @@
                 item runtime dependency which must have completed before that
                 task can be executed.
                 <literallayout class='monospaced'>
-     do_package_write[rdeptask] = "do_package"
+     do_package_qa[rdeptask] = "do_packagedata"
                 </literallayout>
-                In the previous example, the <filename>do_package</filename>
+                In the previous example, the <filename>do_packagedata</filename>
                 task of each item in <filename>RDEPENDS</filename> must have
-                completed before <filename>do_package_write</filename> can execute.
+                completed before <filename>do_package_qa</filename> can execute.
             </para>
         </section>
 
@@ -1543,9 +1619,9 @@
                 the data in <filename>DEPENDS</filename>.
                 Here is an example:
                 <literallayout class='monospaced'>
-     do_patch[depends] = "quilt-native:do_populate_staging"
+     do_patch[depends] = "quilt-native:do_populate_sysroot"
                 </literallayout>
-                In this example, the <filename>do_populate_staging</filename>
+                In this example, the <filename>do_populate_sysroot</filename>
                 task of the target <filename>quilt-native</filename>
                 must have completed before the
                 <filename>do_patch</filename> task can execute.

bitbake/doc/bitbake-user-manual/bitbake-user-manual-ref-variables.xml

@@ -43,8 +43,8 @@
        <link linkend='var-DEFAULT_PREFERENCE'>D</link>
        <link linkend='var-EXCLUDE_FROM_WORLD'>E</link>
        <link linkend='var-FAKEROOT'>F</link>
-<!--       <link linkend='var-GROUPADD_PARAM'>G</link> -->
-       <link linkend='var-HOMEPAGE'>H</link>
+       <link linkend='var-GITDIR'>G</link>
+       <link linkend='var-HGDIR'>H</link>
 <!--       <link linkend='var-ICECC_DISABLED'>I</link> -->
 <!--               <link linkend='var-glossary-j'>J</link> -->
 <!--       <link linkend='var-KARCH'>K</link> -->
@@ -1154,6 +1154,15 @@
             </glossdef>
         </glossentry>
 
+        <glossentry id='var-BZRDIR'><glossterm>BZRDIR</glossterm>
+            <glossdef>
+                <para>
+                    The directory in which files checked out of a Bazaar
+                    system are stored.
+                </para>
+            </glossdef>
+        </glossentry>
+
     </glossdiv>
 
     <glossdiv id='var-glossary-c'><title>C</title>
@@ -1168,6 +1177,15 @@
             </glossdef>
         </glossentry>
 
+        <glossentry id='var-CVSDIR'><glossterm>CVSDIR</glossterm>
+            <glossdef>
+                <para>
+                    The directory in which files checked out under the
+                    CVS system are stored.
+                </para>
+            </glossdef>
+        </glossentry>
+
     </glossdiv>
 
     <glossdiv id='var-glossary-d'><title>D</title>
@@ -1412,13 +1430,32 @@
 
     </glossdiv>
 
-<!--
+
     <glossdiv id='var-glossary-g'><title>G</title>
+
+        <glossentry id='var-GITDIR'><glossterm>GITDIR</glossterm>
+            <glossdef>
+                <para>
+                    The directory in which a local copy of a Git repository
+                    is stored when it is cloned.
+                </para>
+            </glossdef>
+        </glossentry>
+
     </glossdiv>
--->
+
 
     <glossdiv id='var-glossary-h'><title>H</title>
 
+        <glossentry id='var-HGDIR'><glossterm>HGDIR</glossterm>
+            <glossdef>
+                <para>
+                    The directory in which files checked out of a Mercurial
+                    system are stored.
+                </para>
+            </glossdef>
+        </glossentry>
+
         <glossentry id='var-HOMEPAGE'><glossterm>HOMEPAGE</glossterm>
             <glossdef>
                 <para>Website where more information about the software the recipe is building
@@ -1560,8 +1597,16 @@
                     BitBake uses <filename>OVERRIDES</filename> to control
                     what variables are overridden after BitBake parses
                     recipes and configuration files.
-                    You can find more information on how overrides are handled
-                    in the
+                </para>
+
+                <para>
+                    Following is a simple example that uses an overrides
+                    list based on machine architectures:
+                    <literallayout class='monospaced'>
+     OVERRIDES = "arm:x86:mips:powerpc"
+                    </literallayout>
+                    You can find information on how to use
+                    <filename>OVERRIDES</filename> in the
                     "<link linkend='conditional-syntax-overrides'>Conditional Syntax (Overrides)</link>"
                     section.
                 </para>
@@ -1744,16 +1789,28 @@
         <glossentry id='var-PROVIDES'><glossterm>PROVIDES</glossterm>
             <glossdef>
                 <para>
-                    A list of aliases that a recipe also provides.
-                    These aliases are useful for satisfying dependencies of
-                    other recipes during the build (as specified by
-                    <filename><link linkend='var-DEPENDS'>DEPENDS</link></filename>).
-                    <note>
-                        A recipe's own
-                        <filename><link linkend='var-PN'>PN</link></filename>
-                        is implicitly already in its
-                        <filename>PROVIDES</filename> list.
-                    </note>
+                    A list of aliases by which a particular recipe can be
+                    known.
+                    By default, a recipe's own
+                    <filename><link linkend='var-PN'>PN</link></filename>
+                    is implicitly already in its <filename>PROVIDES</filename>
+                    list.
+                    If a recipe uses <filename>PROVIDES</filename>, the
+                    additional aliases are synonyms for the recipe and can
+                    be useful satisfying dependencies of other recipes during
+                    the build as specified by
+                    <filename><link linkend='var-DEPENDS'>DEPENDS</link></filename>.
+                </para>
+
+                <para>
+                    Consider the following example
+                    <filename>PROVIDES</filename> statement from a recipe
+                    file <filename>libav_0.8.11.bb</filename>:
+                    <literallayout class='monospaced'>
+     PROVIDES += "libpostproc"
+                    </literallayout>
+                    The <filename>PROVIDES</filename> statement results in
+                    the "libav" recipe also being known as "libpostproc".
                 </para>
             </glossdef>
         </glossentry>
@@ -2080,6 +2137,15 @@
             </glossdef>
         </glossentry>
 
+        <glossentry id='var-SVNDIR'><glossterm>SVNDIR</glossterm>
+            <glossdef>
+                <para>
+                    The directory in which files checked out of a Subversion
+                    system are stored.
+                </para>
+            </glossdef>
+        </glossentry>
+
     </glossdiv>
 
     <glossdiv id='var-glossary-t'><title>T</title>

bitbake/doc/bitbake-user-manual/bitbake-user-manual-style.css

@@ -313,6 +313,13 @@ a:hover {
   /*font-weight: bold;*/
 }
 
+/* This style defines how the permalink character
+   appears by itself and when hovered over with
+   the mouse. */
+
+[alt='Permalink'] { color: #eee; }
+[alt='Permalink']:hover { color: black; }
+
 
 div.informalfigure,
 div.informalexample,
@@ -793,7 +800,6 @@ div.sect2 .titlepage .title {
 
 h1.title {
   background-color: transparent;
-  background-image: url("figures/yocto-project-bw.png");
   background-repeat: no-repeat;
   height: 256px;
   text-indent: -9000px;

bitbake/doc/bitbake-user-manual/bitbake-user-manual.xml

@@ -56,7 +56,7 @@
 -->
 
         <copyright>
-            <year>2004-2014</year>
+            <year>2004-2015</year>
             <holder>Richard Purdie</holder>
             <holder>Chris Larson</holder>
             <holder>and Phil Blundell</holder>

bitbake/doc/bitbake.1

@@ -89,7 +89,7 @@ quit after parsing the BB files (developers only)
 show current and preferred versions of all packages
 .TP
 .B \-e, \-\-environment
-show the global or per-package environment (this is what used to be bbread)
+show the global or per-recipe environment (this is what used to be bbread)
 .TP
 .B \-g, \-\-graphviz
 emit the dependency trees of the specified packages in the dot syntax

bitbake/doc/template/component.title.xsl

@@ -0,0 +1,39 @@
+<xsl:stylesheet version="1.0"
+  xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+  xmlns:d="http://docbook.org/ns/docbook"
+  xmlns="http://www.w3.org/1999/xhtml"
+  exclude-result-prefixes="d">
+  
+  <xsl:template name="component.title">
+    <xsl:param name="node" select="."/>
+    
+    <xsl:variable name="level">
+      <xsl:choose>
+        <xsl:when test="ancestor::d:section">
+          <xsl:value-of select="count(ancestor::d:section)+1"/>
+        </xsl:when>
+        <xsl:when test="ancestor::d:sect5">6</xsl:when>
+        <xsl:when test="ancestor::d:sect4">5</xsl:when>
+        <xsl:when test="ancestor::d:sect3">4</xsl:when>
+        <xsl:when test="ancestor::d:sect2">3</xsl:when>
+        <xsl:when test="ancestor::d:sect1">2</xsl:when>
+        <xsl:otherwise>1</xsl:otherwise>
+      </xsl:choose>
+    </xsl:variable>
+    <xsl:element name="h{$level+1}" namespace="http://www.w3.org/1999/xhtml">
+      <xsl:attribute name="class">title</xsl:attribute>
+      <xsl:if test="$generate.id.attributes = 0">
+        <xsl:call-template name="anchor">
+          <xsl:with-param name="node" select="$node"/>
+          <xsl:with-param name="conditional" select="0"/>
+        </xsl:call-template>
+      </xsl:if>
+      <xsl:apply-templates select="$node" mode="object.title.markup">
+        <xsl:with-param name="allow-anchors" select="1"/>
+      </xsl:apply-templates>
+      <xsl:call-template name="permalink">
+        <xsl:with-param name="node" select="$node"/>
+      </xsl:call-template>
+    </xsl:element>
+  </xsl:template>
+</xsl:stylesheet>

bitbake/doc/template/division.title.xsl

@@ -0,0 +1,25 @@
+<xsl:stylesheet version="1.0"
+  xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+  xmlns:d="http://docbook.org/ns/docbook"
+  xmlns="http://www.w3.org/1999/xhtml"
+  exclude-result-prefixes="d">
+  
+  <xsl:template name="division.title">
+    <xsl:param name="node" select="."/>
+    
+    <h1>
+      <xsl:attribute name="class">title</xsl:attribute>
+      <xsl:call-template name="anchor">
+        <xsl:with-param name="node" select="$node"/>
+        <xsl:with-param name="conditional" select="0"/>
+      </xsl:call-template>
+      <xsl:apply-templates select="$node" mode="object.title.markup">
+        <xsl:with-param name="allow-anchors" select="1"/>
+      </xsl:apply-templates>
+      <xsl:call-template name="permalink">
+        <xsl:with-param name="node" select="$node"/>
+      </xsl:call-template>
+    </h1>
+  </xsl:template>
+</xsl:stylesheet>
+

bitbake/doc/template/formal.object.heading.xsl

@@ -0,0 +1,21 @@
+<xsl:stylesheet version="1.0"
+  xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+  xmlns:d="http://docbook.org/ns/docbook"
+  xmlns="http://www.w3.org/1999/xhtml"
+  exclude-result-prefixes="d">
+  
+  <xsl:template name="formal.object.heading">
+    <xsl:param name="object" select="."/>
+    <xsl:param name="title">
+      <xsl:apply-templates select="$object" mode="object.title.markup">
+        <xsl:with-param name="allow-anchors" select="1"/>
+      </xsl:apply-templates>
+    </xsl:param>
+    <p class="title">
+      <b><xsl:copy-of select="$title"/></b>
+      <xsl:call-template name="permalink">
+        <xsl:with-param name="node" select="$object"/>
+      </xsl:call-template>
+    </p>
+  </xsl:template>
+</xsl:stylesheet>

bitbake/doc/template/gloss-permalinks.xsl

@@ -0,0 +1,14 @@
+<xsl:stylesheet version="1.0"
+  xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+  xmlns:d="http://docbook.org/ns/docbook"
+  xmlns="http://www.w3.org/1999/xhtml">
+
+  <xsl:template match="glossentry/glossterm">
+    <xsl:apply-imports/>
+    <xsl:if test="$generate.permalink != 0">
+      <xsl:call-template name="permalink">
+        <xsl:with-param name="node" select=".."/>
+      </xsl:call-template>
+    </xsl:if>
+  </xsl:template>
+</xsl:stylesheet>

bitbake/doc/template/permalinks.xsl

@@ -0,0 +1,25 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xsl:stylesheet version="1.0"
+  xmlns="http://www.w3.org/1999/xhtml"
+  xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
+
+  <xsl:param name="generate.permalink" select="1"/>
+  <xsl:param name="permalink.text">¶</xsl:param>
+
+  <xsl:template name="permalink">
+    <xsl:param name="node"/>
+
+    <xsl:if test="$generate.permalink != '0'">
+      <span class="permalink">
+        <a alt="Permalink" title="Permalink">
+          <xsl:attribute name="href">
+            <xsl:call-template name="href.target">
+              <xsl:with-param name="object"  select="$node"/>
+            </xsl:call-template>
+          </xsl:attribute>
+          <xsl:copy-of select="$permalink.text"/>
+        </a>
+      </span>
+    </xsl:if>
+  </xsl:template>
+</xsl:stylesheet>

bitbake/doc/template/section.title.xsl

@@ -0,0 +1,55 @@
+<xsl:stylesheet version="1.0"
+  xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+  xmlns:d="http://docbook.org/ns/docbook"
+  xmlns="http://www.w3.org/1999/xhtml" exclude-result-prefixes="d">
+
+  <xsl:template name="section.title">
+    <xsl:variable name="section"
+      select="(ancestor::section |
+               ancestor::simplesect|
+               ancestor::sect1|
+               ancestor::sect2|
+               ancestor::sect3|
+               ancestor::sect4|
+               ancestor::sect5)[last()]"/>
+
+    <xsl:variable name="renderas">
+      <xsl:choose>
+        <xsl:when test="$section/@renderas = 'sect1'">1</xsl:when>
+        <xsl:when test="$section/@renderas = 'sect2'">2</xsl:when>
+        <xsl:when test="$section/@renderas = 'sect3'">3</xsl:when>
+        <xsl:when test="$section/@renderas = 'sect4'">4</xsl:when>
+        <xsl:when test="$section/@renderas = 'sect5'">5</xsl:when>
+        <xsl:otherwise><xsl:value-of select="''"/></xsl:otherwise>
+      </xsl:choose>
+    </xsl:variable>
+
+    <xsl:variable name="level">
+      <xsl:choose>
+        <xsl:when test="$renderas != ''">
+          <xsl:value-of select="$renderas"/>
+        </xsl:when>
+        <xsl:otherwise>
+          <xsl:call-template name="section.level">
+            <xsl:with-param name="node" select="$section"/>
+          </xsl:call-template>
+        </xsl:otherwise>
+      </xsl:choose>
+    </xsl:variable>
+
+    <xsl:call-template name="section.heading">
+      <xsl:with-param name="section" select="$section"/>
+      <xsl:with-param name="level" select="$level"/>
+      <xsl:with-param name="title">
+        <xsl:apply-templates select="$section" mode="object.title.markup">
+          <xsl:with-param name="allow-anchors" select="1"/>
+        </xsl:apply-templates>
+        <xsl:if test="$level &gt; 0">
+          <xsl:call-template name="permalink">
+            <xsl:with-param name="node" select="$section"/>
+          </xsl:call-template>
+        </xsl:if>
+      </xsl:with-param>
+    </xsl:call-template>
+  </xsl:template>
+</xsl:stylesheet>

bitbake/lib/bb/__init__.py

@@ -21,7 +21,7 @@
 # with this program; if not, write to the Free Software Foundation, Inc.,
 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 
-__version__ = "1.22.0"
+__version__ = "1.26.0"
 
 import sys
 if sys.version_info < (2, 7, 3):
@@ -99,12 +99,11 @@ def error(*args):
 
 def fatal(*args):
     logger.critical(''.join(args))
-    sys.exit(1)
-
+    raise BBHandledException()
 
 def deprecated(func, name=None, advice=""):
     """This is a decorator which can be used to mark functions
-    as deprecated. It will result in a warning being emmitted
+    as deprecated. It will result in a warning being emitted
     when the function is used."""
     import warnings
 

bitbake/lib/bb/build.py

@@ -23,7 +23,7 @@
 # with this program; if not, write to the Free Software Foundation, Inc.,
 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 #
-#Based on functions from the base bb module, Copyright 2003 Holger Schurig
+# Based on functions from the base bb module, Copyright 2003 Holger Schurig
 
 import os
 import sys
@@ -42,9 +42,8 @@ logger = logging.getLogger('BitBake.Build')
 
 NULL = open(os.devnull, 'r+')
 
-
-# When we execute a python function we'd like certain things
-# in all namespaces, hence we add them to __builtins__
+# When we execute a Python function, we'd like certain things
+# in all namespaces, hence we add them to __builtins__.
 # If we do not do this and use the exec globals, they will
 # not be available to subfunctions.
 __builtins__['bb'] = bb
@@ -143,7 +142,7 @@ class LogTee(object):
         self.outfile.flush()
 
 def exec_func(func, d, dirs = None):
-    """Execute an BB 'function'"""
+    """Execute a BB 'function'"""
 
     body = d.getVar(func)
     if not body:
@@ -228,7 +227,7 @@ def exec_func_python(func, d, runfile, cwd=None):
     code = _functionfmt.format(function=func, body=d.getVar(func, True))
     bb.utils.mkdirhier(os.path.dirname(runfile))
     with open(runfile, 'w') as script:
-        script.write(code)
+        bb.data.emit_func_python(func, script, d)
 
     if cwd:
         try:
@@ -242,10 +241,9 @@ def exec_func_python(func, d, runfile, cwd=None):
     try:
         comp = utils.better_compile(code, func, bbfile)
         utils.better_exec(comp, {"d": d}, code, bbfile)
+    except (bb.parse.SkipRecipe, bb.build.FuncFailed):
+        raise
     except:
-        if sys.exc_info()[0] in (bb.parse.SkipPackage, bb.build.FuncFailed):
-            raise
-
         raise FuncFailed(func, None)
     finally:
         bb.debug(2, "Python function %s finished" % func)
@@ -418,7 +416,7 @@ def _exec_task(fn, task, d, quieterr):
     os.dup2(logfile.fileno(), oso[1])
     os.dup2(logfile.fileno(), ose[1])
 
-    # Ensure python logging goes to the logfile
+    # Ensure Python logging goes to the logfile
     handler = logging.StreamHandler(logfile)
     handler.setFormatter(logformatter)
     # Always enable full debug output into task logfiles
@@ -507,7 +505,7 @@ def exec_task(fn, task, d, profile = False):
             event.fire(failedevent, d)
         return 1
 
-def stamp_internal(taskname, d, file_name):
+def stamp_internal(taskname, d, file_name, baseonly=False):
     """
     Internal stamp helper function
     Makes sure the stamp directory exists
@@ -528,6 +526,9 @@ def stamp_internal(taskname, d, file_name):
         file_name = d.getVar('BB_FILENAME', True)
         extrainfo = d.getVarFlag(taskflagname, 'stamp-extra-info', True) or ""
 
+    if baseonly:
+        return stamp
+
     if not stamp:
         return
 
@@ -592,8 +593,9 @@ def make_stamp(task, d, file_name = None):
     # If we're in task context, write out a signature file for each task
     # as it completes
     if not task.endswith("_setscene") and task != "do_setscene" and not file_name:
+        stampbase = stamp_internal(task, d, None, True)
         file_name = d.getVar('BB_FILENAME', True)
-        bb.parse.siggen.dump_sigtask(file_name, task, d.getVar('STAMP', True), True)
+        bb.parse.siggen.dump_sigtask(file_name, task, stampbase, True)
 
 def del_stamp(task, d, file_name = None):
     """

bitbake/lib/bb/cache.py

@@ -43,7 +43,7 @@ except ImportError:
     logger.info("Importing cPickle failed. "
                 "Falling back to a very slow implementation.")
 
-__cache_version__ = "147"
+__cache_version__ = "148"
 
 def getCacheFile(path, filename, data_hash):
     return os.path.join(path, filename + "." + data_hash)
@@ -225,14 +225,16 @@ class CoreRecipeInfo(RecipeInfoCommon):
         for package in self.packages_dynamic:
             cachedata.packages_dynamic[package].append(fn)
 
-        # Build hash of runtime depends and rececommends
+        # Build hash of runtime depends and recommends
         for package in self.packages + [self.pn]:
             cachedata.rundeps[fn][package] = list(self.rdepends) + self.rdepends_pkg[package]
             cachedata.runrecs[fn][package] = list(self.rrecommends) + self.rrecommends_pkg[package]
 
         # Collect files we may need for possible world-dep
         # calculations
-        if not self.not_world:
+        if self.not_world:
+            logger.debug(1, "EXCLUDE FROM WORLD: %s", fn)
+        else:
             cachedata.possible_world.append(fn)
 
         # create a collection of all targets for sanity checking
@@ -259,7 +261,7 @@ class Cache(object):
 
     def __init__(self, data, data_hash, caches_array):
         # Pass caches_array information into Cache Constructor
-        # It will be used in later for deciding whether we 
+        # It will be used later for deciding whether we 
         # need extra cache file dump/load support 
         self.caches_array = caches_array
         self.cachedir = data.getVar("CACHE", True)
@@ -527,8 +529,11 @@ class Cache(object):
         if hasattr(info_array[0], 'file_checksums'):
             for _, fl in info_array[0].file_checksums.items():
                 for f in fl.split():
-                    if not ('*' in f or os.path.exists(f)):
-                        logger.debug(2, "Cache: %s's file checksum list file %s was removed",
+                    if "*" in f:
+                        continue
+                    f, exist = f.split(":")
+                    if (exist == "True" and not os.path.exists(f)) or (exist == "False" and os.path.exists(f)):
+                        logger.debug(2, "Cache: %s's file checksum list file %s changed",
                                         fn, f)
                         self.remove(fn)
                         return False
@@ -618,10 +623,13 @@ class Cache(object):
     def mtime(cachefile):
         return bb.parse.cached_mtime_noerror(cachefile)
 
-    def add_info(self, filename, info_array, cacheData, parsed=None):
+    def add_info(self, filename, info_array, cacheData, parsed=None, watcher=None):
         if isinstance(info_array[0], CoreRecipeInfo) and (not info_array[0].skipped):
             cacheData.add_from_recipeinfo(filename, info_array)
 
+            if watcher:
+                watcher(info_array[0].file_depends)
+
         if not self.has_cache:
             return
 
@@ -692,7 +700,7 @@ def init(cooker):
 
     * Its mtime
     * The mtimes of all its dependencies
-    * Whether it caused a parse.SkipPackage exception
+    * Whether it caused a parse.SkipRecipe exception
 
     Files causing parsing errors are evicted from the cache.
 
@@ -762,16 +770,6 @@ class MultiProcessCache(object):
 
         self.cachedata = data
 
-    def internSet(self, items):
-        new = set()
-        for i in items:
-            new.add(intern(i))
-        return new
-
-    def compress_keys(self, data):
-        # Override in subclasses if desired
-        return
-
     def create_cachedata(self):
         data = [{}]
         return data
@@ -812,15 +810,7 @@ class MultiProcessCache(object):
 
         glf = bb.utils.lockfile(self.cachefile + ".lock")
 
-        try:
-            with open(self.cachefile, "rb") as f:
-                p = pickle.Unpickler(f)
-                data, version = p.load()
-        except (IOError, EOFError):
-            data, version = None, None
-
-        if version != self.__class__.CACHE_VERSION:
-            data = self.create_cachedata()
+        data = self.cachedata
 
         for f in [y for y in os.listdir(os.path.dirname(self.cachefile)) if y.startswith(os.path.basename(self.cachefile) + '-')]:
             f = os.path.join(os.path.dirname(self.cachefile), f)
@@ -829,16 +819,16 @@ class MultiProcessCache(object):
                     p = pickle.Unpickler(fd)
                     extradata, version = p.load()
             except (IOError, EOFError):
-                extradata, version = self.create_cachedata(), None
+                os.unlink(f)
+                continue
 
             if version != self.__class__.CACHE_VERSION:
+                os.unlink(f)
                 continue
 
             self.merge_data(extradata, data)
             os.unlink(f)
 
-        self.compress_keys(data)
-
         with open(self.cachefile, "wb") as f:
             p = pickle.Pickler(f, -1)
             p.dump([data, self.__class__.CACHE_VERSION])

bitbake/lib/bb/codeparser.py

@@ -33,9 +33,82 @@ def check_indent(codestr):
     return codestr
 
 
+# Basically pickle, in python 2.7.3 at least, does badly with data duplication 
+# upon pickling and unpickling. Combine this with duplicate objects and things
+# are a mess.
+#
+# When the sets are originally created, python calls intern() on the set keys
+# which significantly improves memory usage. Sadly the pickle/unpickle process
+# doesn't call intern() on the keys and results in the same strings being duplicated
+# in memory. This also means pickle will save the same string multiple times in
+# the cache file.
+#
+# By having shell and python cacheline objects with setstate/getstate, we force
+# the object creation through our own routine where we can call intern (via internSet).
+#
+# We also use hashable frozensets and ensure we use references to these so that
+# duplicates can be removed, both in memory and in the resulting pickled data.
+#
+# By playing these games, the size of the cache file shrinks dramatically
+# meaning faster load times and the reloaded cache files also consume much less
+# memory. Smaller cache files, faster load times and lower memory usage is good.
+#
+# A custom getstate/setstate using tuples is actually worth 15% cachesize by
+# avoiding duplication of the attribute names!
+
+class SetCache(object):
+    def __init__(self):
+        self.setcache = {}
+
+    def internSet(self, items):
+        
+        new = []
+        for i in items:
+            new.append(intern(i))
+        s = frozenset(new)
+        if hash(s) in self.setcache:
+            return self.setcache[hash(s)]
+        self.setcache[hash(s)] = s
+        return s
+
+codecache = SetCache()
+
+class pythonCacheLine(object):
+    def __init__(self, refs, execs, contains):
+        self.refs = codecache.internSet(refs)
+        self.execs = codecache.internSet(execs)
+        self.contains = {}
+        for c in contains:
+            self.contains[c] = codecache.internSet(contains[c])
+
+    def __getstate__(self):
+        return (self.refs, self.execs, self.contains)
+
+    def __setstate__(self, state):
+        (refs, execs, contains) = state
+        self.__init__(refs, execs, contains)
+    def __hash__(self):
+        l = (hash(self.refs), hash(self.execs))
+        for c in sorted(self.contains.keys()):
+            l = l + (c, hash(self.contains[c]))
+        return hash(l)
+
+class shellCacheLine(object):
+    def __init__(self, execs):
+        self.execs = codecache.internSet(execs)
+
+    def __getstate__(self):
+        return (self.execs)
+
+    def __setstate__(self, state):
+        (execs) = state
+        self.__init__(execs)
+    def __hash__(self):
+        return hash(self.execs)
+
 class CodeParserCache(MultiProcessCache):
     cache_file_name = "bb_codeparser.dat"
-    CACHE_VERSION = 4
+    CACHE_VERSION = 7
 
     def __init__(self):
         MultiProcessCache.__init__(self)
@@ -44,6 +117,27 @@ class CodeParserCache(MultiProcessCache):
         self.pythoncacheextras = self.cachedata_extras[0]
         self.shellcacheextras = self.cachedata_extras[1]
 
+        # To avoid duplication in the codeparser cache, keep
+        # a lookup of hashes of objects we already have
+        self.pythoncachelines = {}
+        self.shellcachelines = {}
+
+    def newPythonCacheLine(self, refs, execs, contains):
+        cacheline = pythonCacheLine(refs, execs, contains)
+        h = hash(cacheline)
+        if h in self.pythoncachelines:
+            return self.pythoncachelines[h]
+        self.pythoncachelines[h] = cacheline
+        return cacheline
+
+    def newShellCacheLine(self, execs):
+        cacheline = shellCacheLine(execs)
+        h = hash(cacheline)
+        if h in self.shellcachelines:
+            return self.shellcachelines[h]
+        self.shellcachelines[h] = cacheline
+        return cacheline
+
     def init_cache(self, d):
         MultiProcessCache.init_cache(self, d)
 
@@ -51,25 +145,6 @@ class CodeParserCache(MultiProcessCache):
         self.pythoncache = self.cachedata[0]
         self.shellcache = self.cachedata[1]
 
-    def compress_keys(self, data):
-        # When the dicts are originally created, python calls intern() on the set keys
-        # which significantly improves memory usage. Sadly the pickle/unpickle process
-        # doesn't call intern() on the keys and results in the same strings being duplicated
-        # in memory. This also means pickle will save the same string multiple times in
-        # the cache file. By interning the data here, the cache file shrinks dramatically
-        # meaning faster load times and the reloaded cache files also consume much less
-        # memory. This is worth any performance hit from this loops and the use of the
-        # intern() data storage.
-        # Python 3.x may behave better in this area
-        for h in data[0]:
-            data[0][h]["refs"] = self.internSet(data[0][h]["refs"])
-            data[0][h]["execs"] = self.internSet(data[0][h]["execs"])
-            for k in data[0][h]["contains"]:
-                data[0][h]["contains"][k] = self.internSet(data[0][h]["contains"][k])
-        for h in data[1]:
-            data[1][h]["execs"] = self.internSet(data[1][h]["execs"])
-        return
-
     def create_cachedata(self):
         data = [{}, {}]
         return data
@@ -102,8 +177,8 @@ class BufferedLogger(Logger):
         self.buffer = []
 
 class PythonParser():
-    getvars = ("d.getVar", "bb.data.getVar", "data.getVar", "d.appendVar", "d.prependVar")
-    containsfuncs = ("bb.utils.contains", "base_contains", "oe.utils.contains")
+    getvars = (".getVar", ".appendVar", ".prependVar")
+    containsfuncs = ("bb.utils.contains", "base_contains", "bb.utils.contains_any")
     execfuncs = ("bb.build.exec_func", "bb.build.exec_task")
 
     def warn(self, func, arg):
@@ -122,7 +197,7 @@ class PythonParser():
 
     def visit_Call(self, node):
         name = self.called_node_name(node.func)
-        if name in self.getvars or name in self.containsfuncs:
+        if name and name.endswith(self.getvars) or name in self.containsfuncs:
             if isinstance(node.args[0], ast.Str):
                 varname = node.args[0].s
                 if name in self.containsfuncs and isinstance(node.args[1], ast.Str):
@@ -168,15 +243,19 @@ class PythonParser():
         h = hash(str(node))
 
         if h in codeparsercache.pythoncache:
-            self.references = codeparsercache.pythoncache[h]["refs"]
-            self.execs = codeparsercache.pythoncache[h]["execs"]
-            self.contains = codeparsercache.pythoncache[h]["contains"]
+            self.references = set(codeparsercache.pythoncache[h].refs)
+            self.execs = set(codeparsercache.pythoncache[h].execs)
+            self.contains = {}
+            for i in codeparsercache.pythoncache[h].contains:
+                self.contains[i] = set(codeparsercache.pythoncache[h].contains[i])
             return
 
         if h in codeparsercache.pythoncacheextras:
-            self.references = codeparsercache.pythoncacheextras[h]["refs"]
-            self.execs = codeparsercache.pythoncacheextras[h]["execs"]
-            self.contains = codeparsercache.pythoncacheextras[h]["contains"]
+            self.references = set(codeparsercache.pythoncacheextras[h].refs)
+            self.execs = set(codeparsercache.pythoncacheextras[h].execs)
+            self.contains = {}
+            for i in codeparsercache.pythoncacheextras[h].contains:
+                self.contains[i] = set(codeparsercache.pythoncacheextras[h].contains[i])
             return
 
         code = compile(check_indent(str(node)), "<string>", "exec",
@@ -188,10 +267,7 @@ class PythonParser():
 
         self.execs.update(self.var_execs)
 
-        codeparsercache.pythoncacheextras[h] = {}
-        codeparsercache.pythoncacheextras[h]["refs"] = self.references
-        codeparsercache.pythoncacheextras[h]["execs"] = self.execs
-        codeparsercache.pythoncacheextras[h]["contains"] = self.contains
+        codeparsercache.pythoncacheextras[h] = codeparsercache.newPythonCacheLine(self.references, self.execs, self.contains)
 
 class ShellParser():
     def __init__(self, name, log):
@@ -210,13 +286,21 @@ class ShellParser():
         h = hash(str(value))
 
         if h in codeparsercache.shellcache:
-            self.execs = codeparsercache.shellcache[h]["execs"]
+            self.execs = set(codeparsercache.shellcache[h].execs)
             return self.execs
 
         if h in codeparsercache.shellcacheextras:
-            self.execs = codeparsercache.shellcacheextras[h]["execs"]
+            self.execs = set(codeparsercache.shellcacheextras[h].execs)
             return self.execs
 
+        self._parse_shell(value)
+        self.execs = set(cmd for cmd in self.allexecs if cmd not in self.funcdefs)
+
+        codeparsercache.shellcacheextras[h] = codeparsercache.newShellCacheLine(self.execs)
+
+        return self.execs
+
+    def _parse_shell(self, value):
         try:
             tokens, _ = pyshyacc.parse(value, eof=True, debug=False)
         except pyshlex.NeedMore:
@@ -224,12 +308,6 @@ class ShellParser():
 
         for token in tokens:
             self.process_tokens(token)
-        self.execs = set(cmd for cmd in self.allexecs if cmd not in self.funcdefs)
-
-        codeparsercache.shellcacheextras[h] = {}
-        codeparsercache.shellcacheextras[h]["execs"] = self.execs
-
-        return self.execs
 
     def process_tokens(self, tokens):
         """Process a supplied portion of the syntax tree as returned by
@@ -303,7 +381,7 @@ class ShellParser():
 
                 if part[0] in ('`', '$('):
                     command = pyshlex.wordtree_as_string(part[1:-1])
-                    self.parse_shell(command)
+                    self._parse_shell(command)
 
                     if word[0] in ("cmd_name", "cmd_word"):
                         if word in words:
@@ -322,7 +400,7 @@ class ShellParser():
                     self.log.debug(1, self.unhandled_template % cmd)
                 elif cmd == "eval":
                     command = " ".join(word for _, word in words[1:])
-                    self.parse_shell(command)
+                    self._parse_shell(command)
                 else:
                     self.allexecs.add(cmd)
                 break

bitbake/lib/bb/command.py

@@ -86,7 +86,10 @@ class Command:
 
     def runAsyncCommand(self):
         try:
-            if self.cooker.state == bb.cooker.state.error:
+            if self.cooker.state in (bb.cooker.state.error, bb.cooker.state.shutdown, bb.cooker.state.forceshutdown):
+                # updateCache will trigger a shutdown of the parser
+                # and then raise BBHandledException triggering an exit
+                self.cooker.updateCache()
                 return False
             if self.currentAsyncCommand is not None:
                 (command, options) = self.currentAsyncCommand
@@ -120,11 +123,11 @@ class Command:
 
     def finishAsyncCommand(self, msg=None, code=None):
         if msg or msg == "":
-            bb.event.fire(CommandFailed(msg), self.cooker.event_data)
+            bb.event.fire(CommandFailed(msg), self.cooker.expanded_data)
         elif code:
-            bb.event.fire(CommandExit(code), self.cooker.event_data)
+            bb.event.fire(CommandExit(code), self.cooker.expanded_data)
         else:
-            bb.event.fire(CommandCompleted(), self.cooker.event_data)
+            bb.event.fire(CommandCompleted(), self.cooker.expanded_data)
         self.currentAsyncCommand = None
         self.cooker.finishcommand()
 
@@ -268,6 +271,11 @@ class CommandsSync:
     # we always take and leave the cooker in state.initial
     setFeatures.readonly = True
 
+    def updateConfig(self, command, params):
+        options = params[0]
+        environment = params[1]
+        command.cooker.updateConfigOpts(options, environment)
+
 class CommandsAsync:
     """
     A class of asynchronous commands

bitbake/lib/bb/cooker.py

@@ -38,7 +38,10 @@ import bb, bb.exceptions, bb.command
 from bb import utils, data, parse, event, cache, providers, taskdata, runqueue
 import Queue
 import signal
+import subprocess
+import errno
 import prserv.serv
+import pyinotify
 
 logger      = logging.getLogger("BitBake")
 collectlog  = logging.getLogger("BitBake.Collection")
@@ -120,8 +123,34 @@ class BBCooker:
 
         self.configuration = configuration
 
+        self.configwatcher = pyinotify.WatchManager()
+        self.configwatcher.bbseen = []
+        self.confignotifier = pyinotify.Notifier(self.configwatcher, self.config_notifications)
+        self.watchmask = pyinotify.IN_CLOSE_WRITE | pyinotify.IN_CREATE | pyinotify.IN_DELETE | \
+                         pyinotify.IN_DELETE_SELF | pyinotify.IN_MODIFY | pyinotify.IN_MOVE_SELF | \
+                         pyinotify.IN_MOVED_FROM | pyinotify.IN_MOVED_TO 
+        self.watcher = pyinotify.WatchManager()
+        self.watcher.bbseen = []
+        self.notifier = pyinotify.Notifier(self.watcher, self.notifications)
+
+
         self.initConfigurationData()
 
+        self.inotify_modified_files = []
+
+        def _process_inotify_updates(server, notifier_list, abort):
+            for n in notifier_list:
+                if n.check_events(timeout=0):
+                    # read notified events and enqeue them
+                    n.read_events()
+                    n.process_events()
+            return 1.0
+
+        self.configuration.server_register_idlecallback(_process_inotify_updates, [self.confignotifier, self.notifier])
+
+        self.baseconfig_valid = True
+        self.parsecache_valid = False
+
         # Take a lock so only one copy of bitbake can run against a given build
         # directory at a time
         lockfile = self.data.expand("${TOPDIR}/bitbake.lock")
@@ -153,20 +182,62 @@ class BBCooker:
         self.parser = None
 
         signal.signal(signal.SIGTERM, self.sigterm_exception)
+        # Let SIGHUP exit as SIGTERM
+        signal.signal(signal.SIGHUP, self.sigterm_exception)
+
+    def config_notifications(self, event):
+        if not event.path in self.inotify_modified_files:
+            self.inotify_modified_files.append(event.path)
+        self.baseconfig_valid = False
+
+    def notifications(self, event):
+        if not event.path in self.inotify_modified_files:
+            self.inotify_modified_files.append(event.path)
+        self.parsecache_valid = False
+
+    def add_filewatch(self, deps, watcher=None):
+        if not watcher:
+            watcher = self.watcher
+        for i in deps:
+            f = os.path.dirname(i[0])
+            if f in watcher.bbseen:
+                continue
+            watcher.bbseen.append(f)
+            while True:
+                # We try and add watches for files that don't exist but if they did, would influence
+                # the parser. The parent directory of these files may not exist, in which case we need 
+                # to watch any parent that does exist for changes.
+                try:
+                    watcher.add_watch(f, self.watchmask, quiet=False)
+                    break
+                except pyinotify.WatchManagerError as e:
+                    if 'ENOENT' in str(e):
+                        f = os.path.dirname(f)
+                        watcher.bbseen.append(f)
+                        continue
+                    if 'ENOSPC' in str(e):
+                        providerlog.error("No space left on device or exceeds fs.inotify.max_user_watches?")
+                        providerlog.error("To check max_user_watches: sysctl -n fs.inotify.max_user_watches.")
+                        providerlog.error("To modify max_user_watches: sysctl -n -w fs.inotify.max_user_watches=<value>.")
+                        providerlog.error("Root privilege is required to modify max_user_watches.")
+                    raise
 
     def sigterm_exception(self, signum, stackframe):
-        bb.warn("Cooker recieved SIGTERM, shutting down...")
+        if signum == signal.SIGTERM:
+            bb.warn("Cooker recieved SIGTERM, shutting down...")
+        elif signum == signal.SIGHUP:
+            bb.warn("Cooker recieved SIGHUP, shutting down...")
         self.state = state.forceshutdown
 
     def setFeatures(self, features):
         # we only accept a new feature set if we're in state initial, so we can reset without problems
-        if self.state != state.initial:
+        if not self.state in [state.initial, state.shutdown, state.forceshutdown, state.stopped, state.error]:
             raise Exception("Illegal state for feature set change")
         original_featureset = list(self.featureset)
         for feature in features:
             self.featureset.setFeature(feature)
         bb.debug(1, "Features set %s (was %s)" % (original_featureset, list(self.featureset)))
-        if (original_featureset != list(self.featureset)):
+        if (original_featureset != list(self.featureset)) and self.state != state.error:
             self.reset()
 
     def initConfigurationData(self):
@@ -200,12 +271,82 @@ class BBCooker:
         self.data = self.databuilder.data
         self.data_hash = self.databuilder.data_hash
 
+
+        # we log all events to a file if so directed
+        if self.configuration.writeeventlog:
+            import json, pickle
+            DEFAULT_EVENTFILE = self.configuration.writeeventlog
+            class EventLogWriteHandler():
+
+                class EventWriter():
+                    def __init__(self, cooker):
+                        self.file_inited = None
+                        self.cooker = cooker
+                        self.event_queue = []
+
+                    def init_file(self):
+                        try:
+                            # delete the old log
+                            os.remove(DEFAULT_EVENTFILE)
+                        except:
+                            pass
+
+                        # write current configuration data
+                        with open(DEFAULT_EVENTFILE, "w") as f:
+                            f.write("%s\n" % json.dumps({ "allvariables" : self.cooker.getAllKeysWithFlags(["doc", "func"])}))
+
+                    def write_event(self, event):
+                        with open(DEFAULT_EVENTFILE, "a") as f:
+                            try:
+                                f.write("%s\n" % json.dumps({"class":event.__module__ + "." + event.__class__.__name__, "vars":json.dumps(pickle.dumps(event)) }))
+                            except Exception as e:
+                                import traceback
+                                print(e, traceback.format_exc(e))
+
+
+                    def send(self, event):
+                        event_class = event.__module__ + "." + event.__class__.__name__
+
+                        # init on bb.event.BuildStarted
+                        if self.file_inited is None:
+                            if  event_class == "bb.event.BuildStarted":
+                                self.init_file()
+                                self.file_inited = True
+
+                                # write pending events
+                                for e in self.event_queue:
+                                    self.write_event(e)
+
+                                # also write the current event
+                                self.write_event(event)
+
+                            else:
+                                # queue all events until the file is inited
+                                self.event_queue.append(event)
+
+                        else:
+                            # we have the file, just write the event
+                            self.write_event(event)
+
+                # set our handler's event processor
+                event = EventWriter(self)       # self is the cooker here
+
+
+            # set up cooker features for this mock UI handler
+
+            # we need to write the dependency tree in the log
+            self.featureset.setFeature(CookerFeatures.SEND_DEPENDS_TREE)
+            # register the log file writer as UI Handler
+            bb.event.register_UIHhandler(EventLogWriteHandler())
+
+
         #
-        # Special updated configuration we use for firing events
+        # Copy of the data store which has been expanded.
+        # Used for firing events and accessing variables where expansion needs to be accounted for
         #
-        self.event_data = bb.data.createCopy(self.data)
-        bb.data.update_data(self.event_data)
-        bb.parse.init_parser(self.event_data)
+        self.expanded_data = bb.data.createCopy(self.data)
+        bb.data.update_data(self.expanded_data)
+        bb.parse.init_parser(self.expanded_data)
 
         if CookerFeatures.BASEDATASTORE_TRACKING in self.featureset:
             self.disableDataTracking()
@@ -240,7 +381,7 @@ class BBCooker:
             f.write(total)
 
         #add to history
-        loginfo = {"op":append, "file":default_file, "line":total.count("\n")}
+        loginfo = {"op":"append", "file":default_file, "line":total.count("\n")}
         self.data.appendVar(var, val, **loginfo)
 
     def saveConfigurationVar(self, var, val, default_file, op):
@@ -309,7 +450,7 @@ class BBCooker:
                 f.write(total)
 
             #add to history
-            loginfo = {"op":set, "file":default_file, "line":total.count("\n")}
+            loginfo = {"op":"set", "file":default_file, "line":total.count("\n")}
             self.data.setVar(var, val, **loginfo)
 
     def removeConfigurationVar(self, var):
@@ -371,6 +512,30 @@ class BBCooker:
 
         self.handleCollections( self.data.getVar("BBFILE_COLLECTIONS", True) )
 
+    def updateConfigOpts(self, options, environment):
+        for o in options:
+            setattr(self.configuration, o, options[o])
+        clean = True
+        for k in bb.utils.approved_variables():
+            if k in environment and k not in self.configuration.env:
+                logger.debug(1, "Updating environment variable %s to %s" % (k, environment[k]))
+                self.configuration.env[k] = environment[k]
+                clean = False
+            if k in self.configuration.env and k not in environment:
+                logger.debug(1, "Updating environment variable %s (deleted)" % (k))
+                del self.configuration.env[k]
+                clean = False
+            if k not in self.configuration.env and k not in environment:
+                 continue
+            if environment[k] != self.configuration.env[k]:
+                logger.debug(1, "Updating environment variable %s to %s" % (k, environment[k]))
+                self.configuration.env[k] = environment[k]
+                clean = False
+        if not clean:
+            logger.debug(1, "Base environment change, triggering reparse")
+            self.baseconfig_valid = False        
+            self.reset()
+
     def runCommands(self, server, data, abort):
         """
         Run any queued asynchronous command
@@ -402,7 +567,7 @@ class BBCooker:
 
     def showEnvironment(self, buildfile = None, pkgs_to_build = []):
         """
-        Show the outer or per-package environment
+        Show the outer or per-recipe environment
         """
         fn = None
         envdata = None
@@ -416,7 +581,7 @@ class BBCooker:
             fn = self.matchFile(fn)
             fn = bb.cache.Cache.realfn2virtual(fn, cls)
         elif len(pkgs_to_build) == 1:
-            ignore = self.data.getVar("ASSUME_PROVIDED", True) or ""
+            ignore = self.expanded_data.getVar("ASSUME_PROVIDED", True) or ""
             if pkgs_to_build[0] in set(ignore.split()):
                 bb.fatal("%s is in ASSUME_PROVIDED" % pkgs_to_build[0])
 
@@ -496,7 +661,7 @@ class BBCooker:
         taskdata, runlist, pkgs_to_build = self.buildTaskData(pkgs_to_build, task, False)
 
         return runlist, taskdata
-    
+
     ######## WARNING : this function requires cache_extra to be enabled ########
 
     def generateTaskDepTreeData(self, pkgs_to_build, task):
@@ -818,7 +983,6 @@ class BBCooker:
         or to find all machine configuration files one could call:
         findFilesMatchingInDir(self, 'conf/machines', 'conf')
         """
-        import re
 
         matches = []
         p = re.compile(re.escape(filepattern))
@@ -949,42 +1113,30 @@ class BBCooker:
                 # Check dependencies and store information for priority calculation
                 deps = self.data.getVar("LAYERDEPENDS_%s" % c, True)
                 if deps:
-                    depnamelist = []
-                    deplist = deps.split()
-                    for dep in deplist:
-                        depsplit = dep.split(':')
-                        if len(depsplit) > 1:
-                            try:
-                                depver = int(depsplit[1])
-                            except ValueError:
-                                parselog.error("invalid version value in LAYERDEPENDS_%s: \"%s\"", c, dep)
-                                errors = True
-                                continue
-                        else:
-                            depver = None
-                        dep = depsplit[0]
-                        depnamelist.append(dep)
-
+                    try:
+                        deplist = bb.utils.explode_dep_versions2(deps)
+                    except bb.utils.VersionStringException as vse:
+                        bb.fatal('Error parsing LAYERDEPENDS_%s: %s' % (c, str(vse)))
+                    for dep, oplist in deplist.iteritems():
                         if dep in collection_list:
-                            if depver:
+                            for opstr in oplist:
                                 layerver = self.data.getVar("LAYERVERSION_%s" % dep, True)
+                                (op, depver) = opstr.split()
                                 if layerver:
                                     try:
-                                        lver = int(layerver)
-                                    except ValueError:
-                                        parselog.error("invalid value for LAYERVERSION_%s: \"%s\"", c, layerver)
-                                        errors = True
-                                        continue
-                                    if lver != depver:
-                                        parselog.error("Layer '%s' depends on version %d of layer '%s', but version %d is enabled in your configuration", c, depver, dep, lver)
+                                        res = bb.utils.vercmp_string_op(layerver, depver, op)
+                                    except bb.utils.VersionStringException as vse:
+                                        bb.fatal('Error parsing LAYERDEPENDS_%s: %s' % (c, str(vse)))
+                                    if not res:
+                                        parselog.error("Layer '%s' depends on version %s of layer '%s', but version %s is currently enabled in your configuration. Check that you are using the correct matching versions/branches of these two layers.", c, opstr, dep, layerver)
                                         errors = True
                                 else:
-                                    parselog.error("Layer '%s' depends on version %d of layer '%s', which exists in your configuration but does not specify a version", c, depver, dep)
+                                    parselog.error("Layer '%s' depends on version %s of layer '%s', which exists in your configuration but does not specify a version. Check that you are using the correct matching versions/branches of these two layers.", c, opstr, dep)
                                     errors = True
                         else:
                             parselog.error("Layer '%s' depends on layer '%s', but this layer is not enabled in your configuration", c, dep)
                             errors = True
-                    collection_depends[c] = depnamelist
+                    collection_depends[c] = deplist.keys()
                 else:
                     collection_depends[c] = []
 
@@ -1036,7 +1188,7 @@ class BBCooker:
             bf = os.path.abspath(bf)
 
         self.collection = CookerCollectFiles(self.recipecache.bbfile_config_priorities)
-        filelist, masked = self.collection.collect_bbfiles(self.data, self.event_data)
+        filelist, masked = self.collection.collect_bbfiles(self.data, self.expanded_data)
         try:
             os.stat(bf)
             bf = os.path.abspath(bf)
@@ -1126,7 +1278,7 @@ class BBCooker:
         taskdata.add_provider(self.data, self.recipecache, item)
 
         buildname = self.data.getVar("BUILDNAME")
-        bb.event.fire(bb.event.BuildStarted(buildname, [item]), self.event_data)
+        bb.event.fire(bb.event.BuildStarted(buildname, [item]), self.expanded_data)
 
         # Execute the runqueue
         runlist = [[item, "do_%s" % task]]
@@ -1153,7 +1305,7 @@ class BBCooker:
                 return False
 
             if not retval:
-                bb.event.fire(bb.event.BuildCompleted(len(rq.rqdata.runq_fnid), buildname, item, failures), self.event_data)
+                bb.event.fire(bb.event.BuildCompleted(len(rq.rqdata.runq_fnid), buildname, item, failures), self.expanded_data)
                 self.command.finishAsyncCommand(msg)
                 return False
             if retval is True:
@@ -1228,7 +1380,6 @@ class BBCooker:
         '''
         Create a new image with a "require"/"inherit" base_image statement
         '''
-        import re
         if timestamp:
             image_name = os.path.splitext(image)[0]
             timestr = time.strftime("-%Y%m%d-%H%M%S")
@@ -1279,29 +1430,45 @@ class BBCooker:
         if self.state == state.running:
             return
 
-        if self.state in (state.shutdown, state.forceshutdown):
+        if self.state in (state.shutdown, state.forceshutdown, state.error):
             if hasattr(self.parser, 'shutdown'):
                 self.parser.shutdown(clean=False, force = True)
             raise bb.BBHandledException()
 
         if self.state != state.parsing:
+
+            # reload files for which we got notifications
+            for p in self.inotify_modified_files:
+                bb.parse.update_cache(p)
+            self.inotify_modified_files = []
+
+            if not self.baseconfig_valid:
+                logger.debug(1, "Reloading base configuration data")
+                self.initConfigurationData()
+                self.baseconfig_valid = True
+                self.parsecache_valid = False
+
+        if self.state != state.parsing and not self.parsecache_valid:
             self.parseConfiguration ()
             if CookerFeatures.SEND_SANITYEVENTS in self.featureset:
                 bb.event.fire(bb.event.SanityCheck(False), self.data)
 
-            ignore = self.data.getVar("ASSUME_PROVIDED", True) or ""
+            ignore = self.expanded_data.getVar("ASSUME_PROVIDED", True) or ""
             self.recipecache.ignored_dependencies = set(ignore.split())
 
             for dep in self.configuration.extra_assume_provided:
                 self.recipecache.ignored_dependencies.add(dep)
 
             self.collection = CookerCollectFiles(self.recipecache.bbfile_config_priorities)
-            (filelist, masked) = self.collection.collect_bbfiles(self.data, self.event_data)
+            (filelist, masked) = self.collection.collect_bbfiles(self.data, self.expanded_data)
 
             self.data.renameVar("__depends", "__base_depends")
+            self.add_filewatch(self.data.getVar("__base_depends"), self.configwatcher)
 
             self.parser = CookerParser(self, filelist, masked)
-            self.state = state.parsing
+            self.parsecache_valid = True
+
+        self.state = state.parsing
 
         if not self.parser.parse_next():
             collectlog.debug(1, "parsing complete")
@@ -1309,7 +1476,7 @@ class BBCooker:
                 raise bb.BBHandledException()
             self.show_appends_with_no_recipes()
             self.handlePrefProviders()
-            self.recipecache.bbfile_priority = self.collection.collection_priorities(self.recipecache.pkg_fn)
+            self.recipecache.bbfile_priority = self.collection.collection_priorities(self.recipecache.pkg_fn, self.data)
             self.state = state.running
             return None
 
@@ -1323,7 +1490,7 @@ class BBCooker:
         if len(pkgs_to_build) == 0:
             raise NothingToBuild
 
-        ignore = (self.data.getVar("ASSUME_PROVIDED", True) or "").split()
+        ignore = (self.expanded_data.getVar("ASSUME_PROVIDED", True) or "").split()
         for pkg in pkgs_to_build:
             if pkg in ignore:
                 parselog.warn("Explicit target \"%s\" is in ASSUME_PROVIDED, ignoring" % pkg)
@@ -1353,13 +1520,41 @@ class BBCooker:
         try:
             self.prhost = prserv.serv.auto_start(self.data)
         except prserv.serv.PRServiceConfigError:
-            bb.event.fire(CookerExit(), self.event_data)
+            bb.event.fire(CookerExit(), self.expanded_data)
             self.state = state.error
         return
 
     def post_serve(self):
         prserv.serv.auto_shutdown(self.data)
-        bb.event.fire(CookerExit(), self.event_data)
+        bb.event.fire(CookerExit(), self.expanded_data)
+        lockfile = self.lock.name
+        self.lock.close()
+        self.lock = None
+
+        while not self.lock:
+            with bb.utils.timeout(3):
+                self.lock = bb.utils.lockfile(lockfile, shared=False, retry=False, block=True)
+                if not self.lock:
+                    # Some systems may not have lsof available
+                    procs = None
+                    try:
+                        procs = subprocess.check_output(["lsof", '-w', lockfile], stderr=subprocess.STDOUT)
+                    except OSError as e:
+                        if e.errno != errno.ENOENT:
+                            raise
+                    if procs is None:
+                        # Fall back to fuser if lsof is unavailable
+                        try:
+                            procs = subprocess.check_output(["fuser", '-v', lockfile], stderr=subprocess.STDOUT)
+                        except OSError as e:
+                            if e.errno != errno.ENOENT:
+                                raise
+
+                    msg = "Delaying shutdown due to active processes which appear to be holding bitbake.lock"
+                    if procs:
+                        msg += ":\n%s" % str(procs)
+                    print(msg)
+
 
     def shutdown(self, force = False):
         if force:
@@ -1408,6 +1603,7 @@ class CookerExit(bb.event.Event):
 class CookerCollectFiles(object):
     def __init__(self, priorities):
         self.appendlist = {}
+        self.bbappends = []
         self.appliedappendlist = []
         self.bbfile_config_priorities = priorities
 
@@ -1437,7 +1633,7 @@ class CookerCollectFiles(object):
             for ignored in ('SCCS', 'CVS', '.svn'):
                 if ignored in dirs:
                     dirs.remove(ignored)
-            found += [os.path.join(dir, f) for f in files if (f.endswith('.bb') or f.endswith('.bbappend'))]
+            found += [os.path.join(dir, f) for f in files if (f.endswith(['.bb', '.bbappend']))]
 
         return found
 
@@ -1502,6 +1698,7 @@ class CookerCollectFiles(object):
         # Build a list of .bbappend files for each .bb file
         for f in bbappend:
             base = os.path.basename(f).replace('.bbappend', '.bb')
+            self.bbappends.append((base, f))
             if not base in self.appendlist:
                self.appendlist[base] = []
             if f not in self.appendlist[base]:
@@ -1527,14 +1724,14 @@ class CookerCollectFiles(object):
         """
         filelist = []
         f = os.path.basename(fn)
-        for bbappend in self.appendlist:
+        for b in self.bbappends:
+            (bbappend, filename) = b
             if (bbappend == f) or ('%' in bbappend and bbappend.startswith(f[:bbappend.index('%')])):
                 self.appliedappendlist.append(bbappend)
-                for filename in self.appendlist[bbappend]:
-                    filelist.append(filename)
+                filelist.append(filename)
         return filelist
 
-    def collection_priorities(self, pkgfns):
+    def collection_priorities(self, pkgfns, d):
 
         priorities = {}
 
@@ -1543,18 +1740,18 @@ class CookerCollectFiles(object):
         for p in pkgfns:
             realfn, cls = bb.cache.Cache.virtualfn2realfn(p)
             priorities[p] = self.calc_bbfile_priority(realfn, matched)
- 
+
         # Don't show the warning if the BBFILE_PATTERN did match .bbappend files
         unmatched = set()
-        for _, _, regex, pri in self.bbfile_config_priorities:        
+        for _, _, regex, pri in self.bbfile_config_priorities:
             if not regex in matched:
                 unmatched.add(regex)
 
         def findmatch(regex):
-            for bbfile in self.appendlist:
-                for append in self.appendlist[bbfile]:
-                    if regex.match(append):
-                        return True
+            for b in self.bbappends:
+                (bbfile, append) = b
+                if regex.match(append):
+                    return True
             return False
 
         for unmatch in unmatched.copy():
@@ -1563,7 +1760,8 @@ class CookerCollectFiles(object):
 
         for collection, pattern, regex, _ in self.bbfile_config_priorities:
             if regex in unmatched:
-                collectlog.warn("No bb files matched BBFILE_PATTERN_%s '%s'" % (collection, pattern))
+                if d.getVar('BBFILE_PATTERN_IGNORE_EMPTY_%s' % collection, True) != '1':
+                    collectlog.warn("No bb files matched BBFILE_PATTERN_%s '%s'" % (collection, pattern))
 
         return priorities
 
@@ -1863,7 +2061,7 @@ class CookerParser(object):
                 self.skipped += 1
                 self.cooker.skiplist[virtualfn] = SkippedPackage(info_array[0])
             self.bb_cache.add_info(virtualfn, info_array, self.cooker.recipecache,
-                                        parsed=parsed)
+                                        parsed=parsed, watcher = self.cooker.add_filewatch)
         return True
 
     def reparse(self, filename):

bitbake/lib/bb/cookerdata.py

@@ -33,8 +33,8 @@ logger      = logging.getLogger("BitBake")
 parselog    = logging.getLogger("BitBake.Parsing")
 
 class ConfigParameters(object):
-    def __init__(self):
-        self.options, targets = self.parseCommandLine()
+    def __init__(self, argv=sys.argv):
+        self.options, targets = self.parseCommandLine(argv)
         self.environment = self.parseEnvironment()
 
         self.options.pkgs_to_build = targets or []
@@ -46,7 +46,7 @@ class ConfigParameters(object):
         for key, val in self.options.__dict__.items():
             setattr(self, key, val)
 
-    def parseCommandLine(self):
+    def parseCommandLine(self, argv=sys.argv):
         raise Exception("Caller must implement commandline option parsing")
 
     def parseEnvironment(self):
@@ -69,6 +69,17 @@ class ConfigParameters(object):
             if bbpkgs:
                 self.options.pkgs_to_build.extend(bbpkgs.split())
 
+    def updateToServer(self, server, environment):
+        options = {}
+        for o in ["abort", "tryaltconfigs", "force", "invalidate_stamp", 
+                  "verbose", "debug", "dry_run", "dump_signatures", 
+                  "debug_domains", "extra_assume_provided", "profile"]:
+            options[o] = getattr(self.options, o)
+
+        ret, error = server.runCommand(["updateConfig", options, environment])
+        if error:
+                raise Exception("Unable to update the server configuration with local parameters: %s" % error)
+
     def parseActions(self):
         # Parse any commandline into actions
         action = {'action':None, 'msg':None}
@@ -128,6 +139,7 @@ class CookerConfiguration(object):
         self.dry_run = False
         self.tracking = False
         self.interface = []
+        self.writeeventlog = False
 
         self.env = {}
 
@@ -227,10 +239,13 @@ class CookerDataBuilder(object):
         try:
             self.parseConfigurationFiles(self.prefiles, self.postfiles)
         except SyntaxError:
-            sys.exit(1)
+            raise bb.BBHandledException
+        except bb.data_smart.ExpansionError as e:
+            logger.error(str(e))
+            raise bb.BBHandledException
         except Exception:
             logger.exception("Error parsing configuration files")
-            sys.exit(1)
+            raise bb.BBHandledException
 
     def _findLayerConf(self, data):
         return findConfigFile("bblayers.conf", data)

bitbake/lib/bb/daemonize.py

@@ -1,5 +1,5 @@
 """
-Python Deamonizing helper
+Python Daemonizing helper
 
 Configurable daemon behaviors:
 
@@ -12,8 +12,11 @@ A failed call to fork() now raises an exception.
 
 References:
     1) Advanced Programming in the Unix Environment: W. Richard Stevens
-    2) Unix Programming Frequently Asked Questions:
-            http://www.erlenstar.demon.co.uk/unix/faq_toc.html
+	http://www.apuebook.com/apue3e.html
+    2) The Linux Programming Interface: Michael Kerrisk
+	http://man7.org/tlpi/index.html
+    3) Unix Programming Frequently Asked Questions:
+	http://www.faqs.org/faqs/unix-faq/programmer/faq/
 
 Modified to allow a function to be daemonized and return for 
 bitbake use by Richard Purdie
@@ -25,7 +28,7 @@ __version__ = "0.2"
 
 # Standard Python modules.
 import os                    # Miscellaneous OS interfaces.
-import sys                  # System-specific parameters and functions.
+import sys                   # System-specific parameters and functions.
 
 # Default daemon parameters.
 # File mode creation mask of the daemon.
@@ -128,7 +131,7 @@ def createDaemon(function, logfile):
     # of methods to accomplish this task.  Three are listed below.
     #
     # Try the system configuration variable, SC_OPEN_MAX, to obtain the maximum
-    # number of open file descriptors to close.  If it doesn't exists, use
+    # number of open file descriptors to close.  If it doesn't exist, use
     # the default value (configurable).
     #
     # try:
@@ -146,7 +149,7 @@ def createDaemon(function, logfile):
     # OR
     #
     # Use the getrlimit method to retrieve the maximum file descriptor number
-    # that can be opened by this process.  If there is not limit on the
+    # that can be opened by this process.  If there is no limit on the
     # resource, use the default value.
     #
     import resource             # Resource usage information.

bitbake/lib/bb/data.py

@@ -6,7 +6,7 @@ BitBake 'Data' implementations
 Functions for interacting with the data structure used by the
 BitBake build tools.
 
-The expandData and update_data are the most expensive
+The expandKeys and update_data are the most expensive
 operations. At night the cookie monster came by and
 suggested 'give me cookies on setting the variables and
 things will work out'. Taking this suggestion into account
@@ -15,7 +15,7 @@ Analyse von Algorithmen' lecture and the cookie
 monster seems to be right. We will track setVar more carefully
 to have faster update_data and expandKeys operations.
 
-This is a treade-off between speed and memory again but
+This is a trade-off between speed and memory again but
 the speed is more critical here.
 """
 
@@ -35,7 +35,7 @@ the speed is more critical here.
 # with this program; if not, write to the Free Software Foundation, Inc.,
 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 #
-#Based on functions from the base bb module, Copyright 2003 Holger Schurig
+# Based on functions from the base bb module, Copyright 2003 Holger Schurig
 
 import sys, os, re
 if sys.argv[0][-5:] == "pydoc":
@@ -219,6 +219,13 @@ def emit_var(var, o=sys.__stdout__, d = init(), all=False):
 
     val = str(val)
 
+    if varExpanded.startswith("BASH_FUNC_"):
+        varExpanded = varExpanded[10:-2]
+        val = val[3:] # Strip off "() "
+        o.write("%s() %s\n" % (varExpanded, val))
+        o.write("export -f %s\n" % (varExpanded))
+        return 1
+
     if func:
         # NOTE: should probably check for unbalanced {} within the var
         o.write("%s() {\n%s\n}\n" % (varExpanded, val))
@@ -231,6 +238,7 @@ def emit_var(var, o=sys.__stdout__, d = init(), all=False):
     # to a shell, we need to escape the quotes in the var
     alter = re.sub('"', '\\"', val)
     alter = re.sub('\n', ' \\\n', alter)
+    alter = re.sub('\\$', '\\\\$', alter)
     o.write('%s="%s"\n' % (varExpanded, alter))
     return 0
 
@@ -281,6 +289,41 @@ def emit_func(func, o=sys.__stdout__, d = init()):
                newdeps |= set((d.getVarFlag(dep, "vardeps", True) or "").split())
         newdeps -= seen
 
+_functionfmt = """
+def {function}(d):
+{body}"""
+
+def emit_func_python(func, o=sys.__stdout__, d = init()):
+    """Emits all items in the data store in a format such that it can be sourced by a shell."""
+
+    def write_func(func, o, call = False):
+        body = d.getVar(func, True)
+        if not body.startswith("def"):
+            body = _functionfmt.format(function=func, body=body)
+
+        o.write(body.strip() + "\n\n")
+        if call:
+            o.write(func + "(d)" + "\n\n")
+
+    write_func(func, o, True)
+    pp = bb.codeparser.PythonParser(func, logger)
+    pp.parse_python(d.getVar(func, True))
+    newdeps = pp.execs
+    newdeps |= set((d.getVarFlag(func, "vardeps", True) or "").split())
+    seen = set()
+    while newdeps:
+        deps = newdeps
+        seen |= deps
+        newdeps = set()
+        for dep in deps:
+            if d.getVarFlag(dep, "func") and d.getVarFlag(dep, "python"):
+               write_func(dep, o)
+               pp = bb.codeparser.PythonParser(dep, logger)
+               pp.parse_python(d.getVar(dep, True))
+               newdeps |= pp.execs
+               newdeps |= set((d.getVarFlag(dep, "vardeps", True) or "").split())
+        newdeps -= seen
+
 def update_data(d):
     """Performs final steps upon the datastore, including application of overrides"""
     d.finalize(parent = True)

bitbake/lib/bb/data_smart.py

@@ -263,7 +263,7 @@ class VariableHistory(object):
                     flag = ''
                 o.write("#   %s %s:%s%s\n#     %s\"%s\"\n" % (event['op'], event['file'], event['line'], display_func, flag, re.sub('\n', '\n#     ', event['detail'])))
             if len(history) > 1:
-                o.write("# computed:\n")
+                o.write("# pre-expansion value:\n")
                 o.write('#   "%s"\n' % (commentVal))
         else:
             o.write("#\n# $%s\n#   [no history recorded]\n#\n" % var)
@@ -296,9 +296,14 @@ class VariableHistory(object):
                 self.variables[var] = []
 
 class DataSmart(MutableMapping):
-    def __init__(self, special = COWDictBase.copy(), seen = COWDictBase.copy() ):
+    def __init__(self, special = None, seen = None ):
         self.dict = {}
 
+        if special is None:
+            special = COWDictBase.copy()
+        if seen is None:
+            seen = COWDictBase.copy()
+
         self.inchistory = IncludeHistory()
         self.varhistory = VariableHistory(self)
         self._tracking = False
@@ -334,7 +339,7 @@ class DataSmart(MutableMapping):
                     break
             except ExpansionError:
                 raise
-            except bb.parse.SkipPackage:
+            except bb.parse.SkipRecipe:
                 raise
             except Exception as exc:
                 raise ExpansionError(varname, s, exc)
@@ -513,10 +518,15 @@ class DataSmart(MutableMapping):
     def _setvar_update_overrides(self, var):
         # aka pay the cookie monster
         override = var[var.rfind('_')+1:]
-        if len(override) > 0:
+        shortvar = var[:var.rfind('_')]
+        while override:
             if override not in self._seen_overrides:
                 self._seen_overrides[override] = set()
             self._seen_overrides[override].add( var )
+            override = None
+            if "_" in shortvar:
+                override = var[shortvar.rfind('_')+1:]
+                shortvar = var[:shortvar.rfind('_')]
 
     def getVar(self, var, expand=False, noweakdefault=False):
         return self.getVarFlag(var, "_content", expand, noweakdefault)
@@ -584,7 +594,7 @@ class DataSmart(MutableMapping):
             self._makeShadowCopy(var)
         self.dict[var][flag] = value
 
-        if flag == "defaultval" and '_' in var:
+        if flag == "_defaultval" and '_' in var:
             self._setvar_update_overrides(var)
 
         if flag == "unexport" or flag == "export":
@@ -600,8 +610,8 @@ class DataSmart(MutableMapping):
         if local_var is not None:
             if flag in local_var:
                 value = copy.copy(local_var[flag])
-            elif flag == "_content" and "defaultval" in local_var and not noweakdefault:
-                value = copy.copy(local_var["defaultval"])
+            elif flag == "_content" and "_defaultval" in local_var and not noweakdefault:
+                value = copy.copy(local_var["_defaultval"])
         if expand and value:
             # Only getvar (flag == _content) hits the expand cache
             cachename = None
@@ -610,9 +620,11 @@ class DataSmart(MutableMapping):
             else:
                 cachename = var + "[" + flag + "]"
             value = self.expand(value, cachename)
-        if value is not None and flag == "_content" and local_var is not None and "_removeactive" in local_var:
-            filtered = filter(lambda v: v not in local_var["_removeactive"],
-                              value.split(" "))
+        if value and flag == "_content" and local_var is not None and "_removeactive" in local_var:
+            removes = [self.expand(r).split()  for r in local_var["_removeactive"]]
+            removes = reduce(lambda a, b: a+b, removes, [])
+            filtered = filter(lambda v: v not in removes,
+                              value.split())
             value = " ".join(filtered)
             if expand:
                  # We need to ensure the expand cache has the correct value
@@ -734,12 +746,16 @@ class DataSmart(MutableMapping):
                 yield key
 
     def __iter__(self):
+        deleted = set()
         def keylist(d):        
             klist = set()
             for key in d:
                 if key == "_data":
                     continue
+                if key in deleted:
+                    continue
                 if not d[key]:
+                    deleted.add(key)
                     continue
                 klist.add(key)
 

bitbake/lib/bb/event.py

@@ -55,6 +55,7 @@ def get_class_handlers():
     return _handlers
 
 def set_class_handlers(h):
+    global _handlers
     _handlers = h
 
 def clean_class_handlers():
@@ -67,12 +68,13 @@ _ui_logfilters = {}
 _ui_handler_seq = 0
 _event_handler_map = {}
 _catchall_handlers = {}
+_eventfilter = None
 
 def execute_handler(name, handler, event, d):
     event.data = d
     try:
         ret = handler(event)
-    except bb.parse.SkipPackage:
+    except (bb.parse.SkipRecipe, bb.BBHandledException):
         raise
     except Exception:
         etype, value, tb = sys.exc_info()
@@ -94,10 +96,10 @@ def fire_class_handlers(event, d):
     evt_hmap = _event_handler_map.get(eid, {})
     for name, handler in _handlers.iteritems():
         if name in _catchall_handlers or name in evt_hmap:
-            try:
-                execute_handler(name, handler, event, d)
-            except Exception:
-                continue
+            if _eventfilter:
+                if not _eventfilter(name, handler, event, d):
+                    continue
+            execute_handler(name, handler, event, d)
 
 ui_queue = []
 @atexit.register
@@ -207,6 +209,10 @@ def remove(name, handler):
     """Remove an Event handler"""
     _handlers.pop(name)
 
+def set_eventfilter(func):
+    global _eventfilter
+    _eventfilter = func
+
 def register_UIHhandler(handler):
     bb.event._ui_handler_seq = bb.event._ui_handler_seq + 1
     _ui_handlers[_ui_handler_seq] = handler
@@ -597,11 +603,11 @@ class MetadataEvent(Event):
     def __init__(self, eventtype, eventdata):
         Event.__init__(self)
         self.type = eventtype
-        self.data = eventdata
+        self._localdata = eventdata
 
 class SanityCheck(Event):
     """
-    Event to runs sanity checks, either raise errors or generate events as return status.
+    Event to run sanity checks, either raise errors or generate events as return status.
     """
     def __init__(self, generateevents = True):
         Event.__init__(self)
@@ -609,7 +615,7 @@ class SanityCheck(Event):
 
 class SanityCheckPassed(Event):
     """
-    Event to indicate sanity check is passed
+    Event to indicate sanity check has passed
     """
 
 class SanityCheckFailed(Event):

bitbake/lib/bb/fetch2/__init__.py

@@ -45,6 +45,13 @@ _checksum_cache = bb.checksum.FileChecksumCache()
 
 logger = logging.getLogger("BitBake.Fetcher")
 
+try:
+    import cPickle as pickle
+except ImportError:
+    import pickle
+    logger.info("Importing cPickle failed. "
+                "Falling back to a very slow implementation.")
+
 class BBFetchException(Exception):
     """Class all fetch exceptions inherit from"""
     def __init__(self, message):
@@ -56,8 +63,11 @@ class BBFetchException(Exception):
 
 class MalformedUrl(BBFetchException):
     """Exception raised when encountering an invalid url"""
-    def __init__(self, url):
-         msg = "The URL: '%s' is invalid and cannot be interpreted" % url
+    def __init__(self, url, message=''):
+         if message:
+             msg = message
+         else:
+             msg = "The URL: '%s' is invalid and cannot be interpreted" % url
          self.url = url
          BBFetchException.__init__(self, msg)
          self.args = (url,)
@@ -371,8 +381,11 @@ def decodeurl(url):
     p = {}
     if parm:
         for s in parm.split(';'):
-            s1, s2 = s.split('=')
-            p[s1] = s2
+            if s:
+                if not '=' in s:
+                    raise MalformedUrl(url, "The URL: '%s' is invalid: parameter %s does not specify a value (missing '=')" % (url, s))
+                s1, s2 = s.split('=')
+                p[s1] = s2
 
     return type, host, urllib.unquote(path), user, pswd, p
 
@@ -519,7 +532,7 @@ def fetcher_compare_revisions(d):
 def mirror_from_string(data):
     return [ i.split() for i in (data or "").replace('\\n','\n').split('\n') if i ]
 
-def verify_checksum(ud, d):
+def verify_checksum(ud, d, precomputed={}):
     """
     verify the MD5 and SHA256 checksum for downloaded src
 
@@ -527,18 +540,33 @@ def verify_checksum(ud, d):
     the downloaded file, or if BB_STRICT_CHECKSUM is set and there are no
     checksums specified.
 
+    Returns a dict of checksums that can be stored in a done stamp file and
+    passed in as precomputed parameter in a later call to avoid re-computing
+    the checksums from the file. This allows verifying the checksums of the
+    file against those in the recipe each time, rather than only after
+    downloading. See https://bugzilla.yoctoproject.org/show_bug.cgi?id=5571.
     """
 
-    if not ud.method.supports_checksum(ud):
-        return
+    _MD5_KEY = "md5"
+    _SHA256_KEY = "sha256"
 
-    md5data = bb.utils.md5_file(ud.localpath)
-    sha256data = bb.utils.sha256_file(ud.localpath)
+    if ud.ignore_checksums or not ud.method.supports_checksum(ud):
+        return {}
+
+    if _MD5_KEY in precomputed:
+        md5data = precomputed[_MD5_KEY]
+    else:
+        md5data = bb.utils.md5_file(ud.localpath)
+
+    if _SHA256_KEY in precomputed:
+        sha256data = precomputed[_SHA256_KEY]
+    else:
+        sha256data = bb.utils.sha256_file(ud.localpath)
 
     if ud.method.recommends_checksum(ud):
         # If strict checking enabled and neither sum defined, raise error
-        strict = d.getVar("BB_STRICT_CHECKSUM", True) or None
-        if strict and not (ud.md5_expected or ud.sha256_expected):
+        strict = d.getVar("BB_STRICT_CHECKSUM", True) or "0"
+        if (strict == "1") and not (ud.md5_expected or ud.sha256_expected):
             logger.error('No checksum specified for %s, please add at least one to the recipe:\n'
                              'SRC_URI[%s] = "%s"\nSRC_URI[%s] = "%s"' %
                              (ud.localpath, ud.md5_name, md5data,
@@ -583,6 +611,72 @@ def verify_checksum(ud, d):
     if len(msg):
         raise ChecksumError('Checksum mismatch!%s' % msg, ud.url, md5data)
 
+    return {
+        _MD5_KEY: md5data,
+        _SHA256_KEY: sha256data
+    }
+
+
+def verify_donestamp(ud, d):
+    """
+    Check whether the done stamp file has the right checksums (if the fetch
+    method supports them). If it doesn't, delete the done stamp and force
+    a re-download.
+
+    Returns True, if the donestamp exists and is valid, False otherwise. When
+    returning False, any existing done stamps are removed.
+    """
+    if not os.path.exists(ud.donestamp):
+        return False
+
+    if not ud.method.supports_checksum(ud):
+        # done stamp exists, checksums not supported; assume the local file is
+        # current
+        return True
+
+    if not os.path.exists(ud.localpath):
+        # done stamp exists, but the downloaded file does not; the done stamp
+        # must be incorrect, re-trigger the download
+        bb.utils.remove(ud.donestamp)
+        return False
+
+    precomputed_checksums = {}
+    # Only re-use the precomputed checksums if the donestamp is newer than the
+    # file. Do not rely on the mtime of directories, though. If ud.localpath is
+    # a directory, there will probably not be any checksums anyway.
+    if (os.path.isdir(ud.localpath) or
+            os.path.getmtime(ud.localpath) < os.path.getmtime(ud.donestamp)):
+        try:
+            with open(ud.donestamp, "rb") as cachefile:
+                pickled = pickle.Unpickler(cachefile)
+                precomputed_checksums.update(pickled.load())
+        except Exception as e:
+            # Avoid the warnings on the upgrade path from emtpy done stamp
+            # files to those containing the checksums.
+            if not isinstance(e, EOFError):
+                # Ignore errors, they aren't fatal
+                logger.warn("Couldn't load checksums from donestamp %s: %s "
+                            "(msg: %s)" % (ud.donestamp, type(e).__name__,
+                                           str(e)))
+
+    try:
+        checksums = verify_checksum(ud, d, precomputed_checksums)
+        # If the cache file did not have the checksums, compute and store them
+        # as an upgrade path from the previous done stamp file format.
+        if checksums != precomputed_checksums:
+            with open(ud.donestamp, "wb") as cachefile:
+                p = pickle.Pickler(cachefile, pickle.HIGHEST_PROTOCOL)
+                p.dump(checksums)
+        return True
+    except ChecksumError as e:
+        # Checksums failed to verify, trigger re-download and remove the
+        # incorrect stamp file.
+        logger.warn("Checksum mismatch for local file %s\n"
+                    "Cleaning and trying again." % ud.localpath)
+        rename_bad_checksum(ud, e.checksum)
+        bb.utils.remove(ud.donestamp)
+    return False
+
 
 def update_stamp(ud, d):
     """
@@ -597,8 +691,11 @@ def update_stamp(ud, d):
             # Errors aren't fatal here
             pass
     else:
-        verify_checksum(ud, d)
-        open(ud.donestamp, 'w').close()
+        checksums = verify_checksum(ud, d)
+        # Store the checksums for later re-verification against the recipe
+        with open(ud.donestamp, "wb") as cachefile:
+            p = pickle.Pickler(cachefile, pickle.HIGHEST_PROTOCOL)
+            p.dump(checksums)
 
 def subprocess_setup():
     # Python installs a SIGPIPE handler by default. This is usually not what
@@ -614,11 +711,13 @@ def get_autorev(d):
 
 def get_srcrev(d):
     """
-    Return the version string for the current package
-    (usually to be used as PV)
+    Return the revsion string, usually for use in the version string (PV) of the current package
     Most packages usually only have one SCM so we just pass on the call.
     In the multi SCM case, we build a value based on SRCREV_FORMAT which must
     have been set.
+
+    The idea here is that we put the string "AUTOINC+" into return value if the revisions are not 
+    incremental, other code is then responsible for turning that into an increasing value (if needed)
     """
 
     scms = []
@@ -797,7 +896,7 @@ def try_mirror_url(origud, ud, ld, check = False):
 
         os.chdir(ld.getVar("DL_DIR", True))
 
-        if not os.path.exists(ud.donestamp) or ud.method.need_update(ud, ld):
+        if not verify_donestamp(ud, ld) or ud.method.need_update(ud, ld):
             ud.method.download(ud, ld)
             if hasattr(ud.method,"build_mirror_data"):
                 ud.method.build_mirror_data(ud, ld)
@@ -813,12 +912,13 @@ def try_mirror_url(origud, ud, ld, check = False):
         dldir = ld.getVar("DL_DIR", True)
         if origud.mirrortarball and os.path.basename(ud.localpath) == os.path.basename(origud.mirrortarball) \
                 and os.path.basename(ud.localpath) != os.path.basename(origud.localpath):
+            # Create donestamp in old format to avoid triggering a re-download
             bb.utils.mkdirhier(os.path.dirname(ud.donestamp))
             open(ud.donestamp, 'w').close()
             dest = os.path.join(dldir, os.path.basename(ud.localpath))
             if not os.path.exists(dest):
                 os.symlink(ud.localpath, dest)
-            if not os.path.exists(origud.donestamp) or origud.method.need_update(origud, ld):
+            if not verify_donestamp(origud, ld) or origud.method.need_update(origud, ld):
                 origud.method.download(origud, ld)
                 if hasattr(origud.method,"build_mirror_data"):
                     origud.method.build_mirror_data(origud, ld)
@@ -930,22 +1030,21 @@ def get_checksum_file_list(d):
         ud = fetch.ud[u]
 
         if ud and isinstance(ud.method, local.Local):
-            ud.setup_localpath(d)
-            f = ud.localpath
-            pth = ud.decodedurl
-            if '*' in pth:
-                f = os.path.join(os.path.abspath(f), pth)
-            if f.startswith(dl_dir):
-                # The local fetcher's behaviour is to return a path under DL_DIR if it couldn't find the file anywhere else
-                if os.path.exists(f):
-                    bb.warn("Getting checksum for %s SRC_URI entry %s: file not found except in DL_DIR" % (d.getVar('PN', True), os.path.basename(f)))
-                else:
-                    bb.warn("Unable to get checksum for %s SRC_URI entry %s: file could not be found" % (d.getVar('PN', True), os.path.basename(f)))
-            filelist.append(f)
+            paths = ud.method.localpaths(ud, d)
+            for f in paths:
+                pth = ud.decodedurl
+                if '*' in pth:
+                    f = os.path.join(os.path.abspath(f), pth)
+                if f.startswith(dl_dir):
+                    # The local fetcher's behaviour is to return a path under DL_DIR if it couldn't find the file anywhere else
+                    if os.path.exists(f):
+                        bb.warn("Getting checksum for %s SRC_URI entry %s: file not found except in DL_DIR" % (d.getVar('PN', True), os.path.basename(f)))
+                    else:
+                        bb.warn("Unable to get checksum for %s SRC_URI entry %s: file could not be found" % (d.getVar('PN', True), os.path.basename(f)))
+                filelist.append(f + ":" + str(os.path.exists(f)))
 
     return " ".join(filelist)
 
-
 def get_file_checksums(filelist, pn):
     """Get a list of the checksums for a list of local files
 
@@ -975,7 +1074,10 @@ def get_file_checksums(filelist, pn):
 
     checksums = []
     for pth in filelist.split():
-        checksum = None
+        exist = pth.split(":")[1]
+        if exist == "False":
+            continue
+        pth = pth.split(":")[0]
         if '*' in pth:
             # Handle globs
             for f in glob.glob(pth):
@@ -983,16 +1085,11 @@ def get_file_checksums(filelist, pn):
                     checksums.extend(checksum_dir(f))
                 else:
                     checksum = checksum_file(f)
-                    if checksum:
-                        checksums.append((f, checksum))
-            continue
+                    checksums.append((f, checksum))
         elif os.path.isdir(pth):
             checksums.extend(checksum_dir(pth))
-            continue
         else:
             checksum = checksum_file(pth)
-
-        if checksum:
             checksums.append((pth, checksum))
 
     checksums.sort(key=operator.itemgetter(1))
@@ -1039,6 +1136,7 @@ class FetchData(object):
             self.sha256_expected = None
         else:
             self.sha256_expected = d.getVarFlag("SRC_URI", self.sha256_name)
+        self.ignore_checksums = False
 
         self.names = self.parm.get("name",'default').split(',')
 
@@ -1195,9 +1293,9 @@ class FetchMethod(object):
             bb.fatal("Invalid value for 'unpack' parameter for %s: %s" %
                      (file, urldata.parm.get('unpack')))
 
-        dots = file.split(".")
-        if dots[-1] in ['gz', 'bz2', 'Z', 'xz']:
-            efile = os.path.join(rootdir, os.path.basename('.'.join(dots[0:-1])))
+        base, ext = os.path.splitext(file)
+        if ext in ['.gz', '.bz2', '.Z', '.xz', '.lz']:
+            efile = os.path.join(rootdir, os.path.basename(base))
         else:
             efile = file
         cmd = None
@@ -1217,6 +1315,10 @@ class FetchMethod(object):
                 cmd = 'xz -dc %s | tar x --no-same-owner -f -' % file
             elif file.endswith('.xz'):
                 cmd = 'xz -dc %s > %s' % (file, efile)
+            elif file.endswith('.tar.lz'):
+                cmd = 'lzip -dc %s | tar x --no-same-owner -f -' % file
+            elif file.endswith('.lz'):
+                cmd = 'lzip -dc %s > %s' % (file, efile)
             elif file.endswith('.zip') or file.endswith('.jar'):
                 try:
                     dos = bb.utils.to_boolean(urldata.parm.get('dos'), False)
@@ -1255,17 +1357,22 @@ class FetchMethod(object):
                         destdir = destdir.strip('/')
                     if destdir != "." and not os.access("%s/%s" % (rootdir, destdir), os.F_OK):
                         os.makedirs("%s/%s" % (rootdir, destdir))
-                    cmd = 'cp -pPR %s %s/%s/' % (file, rootdir, destdir)
+                    cmd = 'cp -fpPR %s %s/%s/' % (file, rootdir, destdir)
                     #cmd = 'tar -cf - -C "%d" -ps . | tar -xf - -C "%s/%s/"' % (file, rootdir, destdir)
                 else:
                     # The "destdir" handling was specifically done for FILESPATH
                     # items.  So, only do so for file:// entries.
                     if urldata.type == "file" and urldata.path.find("/") != -1:
                        destdir = urldata.path.rsplit("/", 1)[0]
+                       if urldata.parm.get('subdir') != None:
+                          destdir = urldata.parm.get('subdir') + "/" + destdir
                     else:
-                       destdir = "."
+                       if urldata.parm.get('subdir') != None:
+                          destdir = urldata.parm.get('subdir')
+                       else:
+                          destdir = "."
                     bb.utils.mkdirhier("%s/%s" % (rootdir, destdir))
-                    cmd = 'cp %s %s/%s/' % (file, rootdir, destdir)
+                    cmd = 'cp -f %s %s/%s/' % (file, rootdir, destdir)
 
         if not cmd:
             return
@@ -1407,7 +1514,7 @@ class Fetch(object):
             try:
                 self.d.setVar("BB_NO_NETWORK", network)
  
-                if os.path.exists(ud.donestamp) and not m.need_update(ud, self.d):
+                if verify_donestamp(ud, self.d) and not m.need_update(ud, self.d):
                     localpath = ud.localpath
                 elif m.try_premirror(ud, self.d):
                     logger.debug(1, "Trying PREMIRRORS")
@@ -1420,7 +1527,7 @@ class Fetch(object):
                 os.chdir(self.d.getVar("DL_DIR", True))
 
                 firsterr = None
-                if not localpath and ((not os.path.exists(ud.donestamp)) or m.need_update(ud, self.d)):
+                if not localpath and ((not verify_donestamp(ud, self.d)) or m.need_update(ud, self.d)):
                     try:
                         logger.debug(1, "Trying Upstream")
                         m.download(ud, self.d)
@@ -1558,6 +1665,7 @@ from . import bzr
 from . import hg
 from . import osc
 from . import repo
+from . import clearcase
 
 methods.append(local.Local())
 methods.append(wget.Wget())
@@ -1573,3 +1681,4 @@ methods.append(bzr.Bzr())
 methods.append(hg.Hg())
 methods.append(osc.Osc())
 methods.append(repo.Repo())
+methods.append(clearcase.ClearCase())

bitbake/lib/bb/fetch2/clearcase.py

@@ -0,0 +1,263 @@
+# ex:ts=4:sw=4:sts=4:et
+# -*- tab-width: 4; c-basic-offset: 4; indent-tabs-mode: nil -*-
+"""
+BitBake 'Fetch' clearcase implementation
+
+The clearcase fetcher is used to retrieve files from a ClearCase repository.
+
+Usage in the recipe:
+
+    SRC_URI = "ccrc://cc.example.org/ccrc;vob=/example_vob;module=/example_module"
+    SRCREV = "EXAMPLE_CLEARCASE_TAG"
+    PV = "${@d.getVar("SRCREV").replace("/", "+")}"
+
+The fetcher uses the rcleartool or cleartool remote client, depending on which one is available.
+
+Supported SRC_URI options are:
+
+- vob
+    (required) The name of the clearcase VOB (with prepending "/")
+
+- module
+    The module in the selected VOB (with prepending "/")
+
+    The module and vob parameters are combined to create
+    the following load rule in the view config spec:
+                load <vob><module>
+
+- proto
+    http or https
+
+Related variables:
+
+    CCASE_CUSTOM_CONFIG_SPEC
+            Write a config spec to this variable in your recipe to use it instead
+            of the default config spec generated by this fetcher.
+            Please note that the SRCREV loses its functionality if you specify
+            this variable. SRCREV is still used to label the archive after a fetch,
+            but it doesn't define what's fetched.
+
+User credentials:
+    cleartool:
+            The login of cleartool is handled by the system. No special steps needed.
+
+    rcleartool:
+            In order to use rcleartool with authenticated users an `rcleartool login` is
+            necessary before using the fetcher.
+"""
+# Copyright (C) 2014 Siemens AG
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along
+# with this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+#
+
+import os
+import sys
+import shutil
+import bb
+from   bb import data
+from   bb.fetch2 import FetchMethod
+from   bb.fetch2 import FetchError
+from   bb.fetch2 import runfetchcmd
+from   bb.fetch2 import logger
+from   distutils import spawn
+
+class ClearCase(FetchMethod):
+    """Class to fetch urls via 'clearcase'"""
+    def init(self, d):
+        pass
+
+    def supports(self, ud, d):
+        """
+        Check to see if a given url can be fetched with Clearcase.
+        """
+        return ud.type in ['ccrc']
+
+    def debug(self, msg):
+        logger.debug(1, "ClearCase: %s", msg)
+
+    def urldata_init(self, ud, d):
+        """
+        init ClearCase specific variable within url data
+        """
+        ud.proto = "https"
+        if 'protocol' in ud.parm:
+            ud.proto = ud.parm['protocol']
+        if not ud.proto in ('http', 'https'):
+            raise fetch2.ParameterError("Invalid protocol type", ud.url)
+
+        ud.vob = ''
+        if 'vob' in ud.parm:
+            ud.vob = ud.parm['vob']
+        else:
+            msg = ud.url+": vob must be defined so the fetcher knows what to get."
+            raise MissingParameterError('vob', msg)
+
+        if 'module' in ud.parm:
+            ud.module = ud.parm['module']
+        else:
+            ud.module = ""
+
+        ud.basecmd = d.getVar("FETCHCMD_ccrc", True) or spawn.find_executable("cleartool") or spawn.find_executable("rcleartool")
+
+        if data.getVar("SRCREV", d, True) == "INVALID":
+          raise FetchError("Set a valid SRCREV for the clearcase fetcher in your recipe, e.g. SRCREV = \"/main/LATEST\" or any other label of your choice.")
+
+        ud.label = d.getVar("SRCREV")
+        ud.customspec = d.getVar("CCASE_CUSTOM_CONFIG_SPEC", True)
+
+        ud.server     = "%s://%s%s" % (ud.proto, ud.host, ud.path)
+
+        ud.identifier = "clearcase-%s%s-%s" % ( ud.vob.replace("/", ""),
+                                                ud.module.replace("/", "."),
+                                                ud.label.replace("/", "."))
+
+        ud.viewname         = "%s-view%s" % (ud.identifier, d.getVar("DATETIME", d, True))
+        ud.csname           = "%s-config-spec" % (ud.identifier)
+        ud.ccasedir         = os.path.join(data.getVar("DL_DIR", d, True), ud.type)
+        ud.viewdir          = os.path.join(ud.ccasedir, ud.viewname)
+        ud.configspecfile   = os.path.join(ud.ccasedir, ud.csname)
+        ud.localfile        = "%s.tar.gz" % (ud.identifier)
+
+        self.debug("host            = %s" % ud.host)
+        self.debug("path            = %s" % ud.path)
+        self.debug("server          = %s" % ud.server)
+        self.debug("proto           = %s" % ud.proto)
+        self.debug("type            = %s" % ud.type)
+        self.debug("vob             = %s" % ud.vob)
+        self.debug("module          = %s" % ud.module)
+        self.debug("basecmd         = %s" % ud.basecmd)
+        self.debug("label           = %s" % ud.label)
+        self.debug("ccasedir        = %s" % ud.ccasedir)
+        self.debug("viewdir         = %s" % ud.viewdir)
+        self.debug("viewname        = %s" % ud.viewname)
+        self.debug("configspecfile  = %s" % ud.configspecfile)
+        self.debug("localfile       = %s" % ud.localfile)
+
+        ud.localfile = os.path.join(data.getVar("DL_DIR", d, True), ud.localfile)
+
+    def _build_ccase_command(self, ud, command):
+        """
+        Build up a commandline based on ud
+        command is: mkview, setcs, rmview
+        """
+        options = []
+
+        if "rcleartool" in ud.basecmd:
+            options.append("-server %s" % ud.server)
+
+        basecmd = "%s %s" % (ud.basecmd, command)
+
+        if command is 'mkview':
+            if not "rcleartool" in ud.basecmd:
+                # Cleartool needs a -snapshot view
+                options.append("-snapshot")
+            options.append("-tag %s" % ud.viewname)
+            options.append(ud.viewdir)
+
+        elif command is 'rmview':
+            options.append("-force")
+            options.append("%s" % ud.viewdir)
+
+        elif command is 'setcs':
+            options.append("-overwrite")
+            options.append(ud.configspecfile)
+
+        else:
+            raise FetchError("Invalid ccase command %s" % command)
+
+        ccasecmd = "%s %s" % (basecmd, " ".join(options))
+        self.debug("ccasecmd = %s" % ccasecmd)
+        return ccasecmd
+
+    def _write_configspec(self, ud, d):
+        """
+        Create config spec file (ud.configspecfile) for ccase view
+        """
+        config_spec = ""
+        custom_config_spec = d.getVar("CCASE_CUSTOM_CONFIG_SPEC", d)
+        if custom_config_spec is not None:
+            for line in custom_config_spec.split("\\n"):
+                config_spec += line+"\n"
+            bb.warn("A custom config spec has been set, SRCREV is only relevant for the tarball name.")
+        else:
+            config_spec += "element * CHECKEDOUT\n"
+            config_spec += "element * %s\n" % ud.label
+            config_spec += "load %s%s\n" % (ud.vob, ud.module)
+
+        logger.info("Using config spec: \n%s" % config_spec)
+
+        with open(ud.configspecfile, 'w') as f:
+            f.write(config_spec)
+
+    def _remove_view(self, ud, d):
+        if os.path.exists(ud.viewdir):
+            os.chdir(ud.ccasedir)
+            cmd = self._build_ccase_command(ud, 'rmview');
+            logger.info("cleaning up [VOB=%s label=%s view=%s]", ud.vob, ud.label, ud.viewname)
+            bb.fetch2.check_network_access(d, cmd, ud.url)
+            output = runfetchcmd(cmd, d)
+            logger.info("rmview output: %s", output)
+
+    def need_update(self, ud, d):
+        if ("LATEST" in ud.label) or (ud.customspec and "LATEST" in ud.customspec):
+            ud.identifier += "-%s" % d.getVar("DATETIME",d, True)
+            return True
+        if os.path.exists(ud.localpath):
+            return False
+        return True
+
+    def supports_srcrev(self):
+        return True
+
+    def sortable_revision(self, ud, d, name):
+        return False, ud.identifier
+
+    def download(self, ud, d):
+        """Fetch url"""
+
+        # Make a fresh view
+        bb.utils.mkdirhier(ud.ccasedir)
+        self._write_configspec(ud, d)
+        cmd = self._build_ccase_command(ud, 'mkview')
+        logger.info("creating view [VOB=%s label=%s view=%s]", ud.vob, ud.label, ud.viewname)
+        bb.fetch2.check_network_access(d, cmd, ud.url)
+        try:
+            runfetchcmd(cmd, d)
+        except FetchError as e:
+            if "CRCLI2008E" in e.msg:
+                raise FetchError("%s\n%s\n" % (e.msg, "Call `rcleartool login` in your console to authenticate to the clearcase server before running bitbake."))
+            else:
+                raise e
+
+        # Set configspec: Setting the configspec effectively fetches the files as defined in the configspec
+        os.chdir(ud.viewdir)
+        cmd = self._build_ccase_command(ud, 'setcs');
+        logger.info("fetching data [VOB=%s label=%s view=%s]", ud.vob, ud.label, ud.viewname)
+        bb.fetch2.check_network_access(d, cmd, ud.url)
+        output = runfetchcmd(cmd, d)
+        logger.info("%s", output)
+
+        # Copy the configspec to the viewdir so we have it in our source tarball later
+        shutil.copyfile(ud.configspecfile, os.path.join(ud.viewdir, ud.csname))
+
+        # Clean clearcase meta-data before tar
+
+        runfetchcmd('tar -czf "%s" .' % (ud.localpath), d, cleanup = [ud.localpath])
+
+        # Clean up so we can create a new view next time
+        self.clean(ud, d);
+
+    def clean(self, ud, d):
+        self._remove_view(ud, d)
+        bb.utils.remove(ud.configspecfile)

bitbake/lib/bb/fetch2/git.py

@@ -67,6 +67,7 @@ Supported SRC_URI options are:
 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 
 import os
+import re
 import bb
 from   bb    import data
 from   bb.fetch2 import FetchMethod
@@ -123,7 +124,7 @@ class Git(FetchMethod):
             ud.branches[name] = branch
             ud.unresolvedrev[name] = branch
 
-        ud.basecmd = data.getVar("FETCHCMD_git", d, True) or "git"
+        ud.basecmd = data.getVar("FETCHCMD_git", d, True) or "git -c core.fsyncobjectfiles=0"
 
         ud.write_tarballs = ((data.getVar("BB_GENERATE_MIRROR_TARBALLS", d, True) or "0") != "0") or ud.rebaseable
 
@@ -245,7 +246,7 @@ class Git(FetchMethod):
         subdir = ud.parm.get("subpath", "")
         if subdir != "":
             readpathspec = ":%s" % (subdir)
-            def_destsuffix = "%s/" % os.path.basename(subdir)
+            def_destsuffix = "%s/" % os.path.basename(subdir.rstrip('/'))
         else:
             readpathspec = ""
             def_destsuffix = "git/"
@@ -275,7 +276,7 @@ class Git(FetchMethod):
             os.symlink(ud.clonedir, indirectiondir)
             clonedir = indirectiondir
 
-        runfetchcmd("git clone %s %s/ %s" % (cloneflags, clonedir, destdir), d)
+        runfetchcmd("%s clone %s %s/ %s" % (ud.basecmd, cloneflags, clonedir, destdir), d)
         if not ud.nocheckout:
             os.chdir(destdir)
             if subdir != "":
@@ -339,17 +340,63 @@ class Git(FetchMethod):
         """
         Compute the HEAD revision for the url
         """
-        search = "refs/heads/%s refs/tags/%s^{}" % (ud.unresolvedrev[name], ud.unresolvedrev[name])
-        output = self._lsremote(ud, d, search)
-        return output.split()[0]
+        output = self._lsremote(ud, d, "")
+        # Tags of the form ^{} may not work, need to fallback to other form
+        if ud.unresolvedrev[name][:5] == "refs/":
+            head = ud.unresolvedrev[name]
+            tag = ud.unresolvedrev[name]
+        else:
+            head = "refs/heads/%s" % ud.unresolvedrev[name]
+            tag = "refs/tags/%s" % ud.unresolvedrev[name]
+        for s in [head, tag + "^{}", tag]:
+            for l in output.split('\n'):
+                if s in l:
+                    return l.split()[0]
+        raise bb.fetch2.FetchError("Unable to resolve '%s' in upstream git repository in git ls-remote output" % ud.unresolvedrev[name])
+
+    def latest_versionstring(self, ud, d):
+        """
+        Compute the latest release name like "x.y.x" in "x.y.x+gitHASH"
+        by searching through the tags output of ls-remote, comparing
+        versions and returning the highest match.
+        """
+        verstring = ""
+        tagregex = re.compile(d.getVar('GITTAGREGEX', True) or "(?P<pver>([0-9][\.|_]?)+)")
+        try:
+            output = self._lsremote(ud, d, "refs/tags/*^{}")
+        except bb.fetch2.FetchError or bb.fetch2.NetworkAccess:
+            return ""
+
+        for line in output.split("\n"):
+            if not line:
+                break
+
+            line = line.split("/")[-1]
+            # Ignore non-released branches
+            m = re.search("(alpha|beta|rc|final)+", line)
+            if m:
+                continue
+
+            # search for version in the line
+            tag = tagregex.search(line)
+            if tag == None:
+                continue
+
+            tag = tag.group('pver')
+            tag = tag.replace("_", ".")
+
+            if verstring and bb.utils.vercmp(("0", tag, ""), ("0", verstring, "")) < 0:
+                continue
+            verstring = tag
+
+        return verstring
 
     def _build_revision(self, ud, d, name):
         return ud.revisions[name]
 
     def checkstatus(self, ud, d):
-        fetchcmd = "%s ls-remote %s" % (ud.basecmd, ud.url)
         try:
-            runfetchcmd(fetchcmd, d, quiet=True)
+            self._lsremote(ud, d, "")
             return True
         except FetchError:
             return False

bitbake/lib/bb/fetch2/gitsm.py

@@ -2,6 +2,16 @@
 # -*- tab-width: 4; c-basic-offset: 4; indent-tabs-mode: nil -*-
 """
 BitBake 'Fetch' git submodules implementation
+
+Inherits from and extends the Git fetcher to retrieve submodules of a git repository
+after cloning.
+
+SRC_URI = "gitsm://<see Git fetcher for syntax>"
+
+See the Git fetcher, git://, for usage documentation.
+
+NOTE: Switching a SRC_URI from "git://" to "gitsm://" requires a clean of your recipe.
+
 """
 
 # Copyright (C) 2013 Richard Purdie

bitbake/lib/bb/fetch2/hg.py

@@ -110,7 +110,10 @@ class Hg(FetchMethod):
             options.append("-r %s" % ud.revision)
 
         if command == "fetch":
-            cmd = "%s clone %s %s://%s/%s %s" % (basecmd, " ".join(options), proto, hgroot, ud.module, ud.module)
+            if ud.user and ud.pswd:
+                cmd = "%s --config auth.default.prefix=* --config auth.default.username=%s --config auth.default.password=%s --config \"auth.default.schemes=%s\" clone %s %s://%s/%s %s" % (basecmd, ud.user, ud.pswd, proto, " ".join(options), proto, hgroot, ud.module, ud.module)
+            else:
+                cmd = "%s clone %s %s://%s/%s %s" % (basecmd, " ".join(options), proto, hgroot, ud.module, ud.module)	      
         elif command == "pull":
             # do not pass options list; limiting pull to rev causes the local
             # repo not to contain it and immediately following "update" command
@@ -120,7 +123,10 @@ class Hg(FetchMethod):
             else:
                 cmd = "%s pull" % (basecmd)
         elif command == "update":
-            cmd = "%s update -C %s" % (basecmd, " ".join(options))
+            if ud.user and ud.pswd:
+                cmd = "%s --config auth.default.prefix=* --config auth.default.username=%s --config auth.default.password=%s --config \"auth.default.schemes=%s\" update -C %s" % (basecmd, ud.user, ud.pswd, proto, " ".join(options))
+            else:
+                cmd = "%s update -C %s" % (basecmd, " ".join(options))
         else:
             raise FetchError("Invalid hg command %s" % command, ud.url)
 

bitbake/lib/bb/fetch2/local.py

@@ -51,29 +51,41 @@ class Local(FetchMethod):
         """
         Return the local filename of a given url assuming a successful fetch.
         """
+        return self.localpaths(urldata, d)[-1]
+
+    def localpaths(self, urldata, d):
+        """
+        Return the local filename of a given url assuming a successful fetch.
+        """
+        searched = []
         path = urldata.decodedurl
         newpath = path
-        if path[0] != "/":
-            filespath = data.getVar('FILESPATH', d, True)
-            if filespath:
-                logger.debug(2, "Searching for %s in paths:    \n%s" % (path, "\n    ".join(filespath.split(":"))))
-                newpath = bb.utils.which(filespath, path)
-            if not newpath:
-                filesdir = data.getVar('FILESDIR', d, True)
-                if filesdir:
-                    logger.debug(2, "Searching for %s in path: %s" % (path, filesdir))
-                    newpath = os.path.join(filesdir, path)
-            if (not newpath or not os.path.exists(newpath)) and path.find("*") != -1:
-                # For expressions using '*', best we can do is take the first directory in FILESPATH that exists
-                newpath = bb.utils.which(filespath, ".")
-                logger.debug(2, "Searching for %s in path: %s" % (path, newpath))
-                return newpath
-            if not os.path.exists(newpath):
-                dldirfile = os.path.join(d.getVar("DL_DIR", True), path)
-                logger.debug(2, "Defaulting to %s for %s" % (dldirfile, path))
-                bb.utils.mkdirhier(os.path.dirname(dldirfile))
-                return dldirfile
-        return newpath
+        if path[0] == "/":
+            return [path]
+        filespath = data.getVar('FILESPATH', d, True)
+        if filespath:
+            logger.debug(2, "Searching for %s in paths:\n    %s" % (path, "\n    ".join(filespath.split(":"))))
+            newpath, hist = bb.utils.which(filespath, path, history=True)
+            searched.extend(hist)
+        if not newpath:
+            filesdir = data.getVar('FILESDIR', d, True)
+            if filesdir:
+                logger.debug(2, "Searching for %s in path: %s" % (path, filesdir))
+                newpath = os.path.join(filesdir, path)
+                searched.append(newpath)
+        if (not newpath or not os.path.exists(newpath)) and path.find("*") != -1:
+            # For expressions using '*', best we can do is take the first directory in FILESPATH that exists
+            newpath, hist = bb.utils.which(filespath, ".", history=True)
+            searched.extend(hist)
+            logger.debug(2, "Searching for %s in path: %s" % (path, newpath))
+            return searched
+        if not os.path.exists(newpath):
+            dldirfile = os.path.join(d.getVar("DL_DIR", True), path)
+            logger.debug(2, "Defaulting to %s for %s" % (dldirfile, path))
+            bb.utils.mkdirhier(os.path.dirname(dldirfile))
+            searched.append(dldirfile)
+            return searched
+        return searched
 
     def need_update(self, ud, d):
         if ud.url.find("*") != -1:

bitbake/lib/bb/fetch2/perforce.py

@@ -48,7 +48,7 @@ class Perforce(FetchMethod):
             (user, pswd, host, port) = path.split('@')[0].split(":")
             path = path.split('@')[1]
         else:
-            (host, port) = data.getVar('P4PORT', d).split(':')
+            (host, port) = d.getVar('P4PORT').split(':')
             user = ""
             pswd = ""
 
@@ -81,7 +81,7 @@ class Perforce(FetchMethod):
         if host:
             p4opt += " -p %s" % (host)
 
-        p4date = data.getVar("P4DATE", d, True)
+        p4date = d.getVar("P4DATE", True)
         if "revision" in parm:
             depot += "#%s" % (parm["revision"])
         elif "label" in parm:
@@ -89,7 +89,7 @@ class Perforce(FetchMethod):
         elif p4date:
             depot += "@%s" % (p4date)
 
-        p4cmd = data.getVar('FETCHCMD_p4', d, True)
+        p4cmd = d.getVar('FETCHCMD_p4', True) or "p4"
         logger.debug(1, "Running %s%s changes -m 1 %s", p4cmd, p4opt, depot)
         p4file, errors = bb.process.run("%s%s changes -m 1 %s" % (p4cmd, p4opt, depot))
         cset = p4file.strip()
@@ -103,22 +103,15 @@ class Perforce(FetchMethod):
     def urldata_init(self, ud, d):
         (host, path, user, pswd, parm) = Perforce.doparse(ud.url, d)
 
-        # If a label is specified, we use that as our filename
-
+        base_path = path.replace('/...', '')
+        base_path = self._strip_leading_slashes(base_path)
+        
         if "label" in parm:
-            ud.localfile = "%s.tar.gz" % (parm["label"])
-            return
+            version = parm["label"]
+        else:
+            version = Perforce.getcset(d, path, host, user, pswd, parm)
 
-        base = path
-        which = path.find('/...')
-        if which != -1:
-            base = path[:which-1]
-
-        base = self._strip_leading_slashes(base)
-
-        cset = Perforce.getcset(d, path, host, user, pswd, parm)
-
-        ud.localfile = data.expand('%s+%s+%s.tar.gz' % (host, base.replace('/', '.'), cset), d)
+        ud.localfile = data.expand('%s+%s+%s.tar.gz' % (host, base_path.replace('/', '.'), version), d)
 
     def download(self, ud, d):
         """
@@ -145,7 +138,7 @@ class Perforce(FetchMethod):
         if host:
             p4opt += " -p %s" % (host)
 
-        p4cmd = data.getVar('FETCHCMD_p4', d, True)
+        p4cmd = d.getVar('FETCHCMD_p4', True) or "p4"
 
         # create temp directory
         logger.debug(2, "Fetch: creating temporary directory")

bitbake/lib/bb/fetch2/ssh.py

@@ -87,7 +87,8 @@ class SSH(FetchMethod):
         m = __pattern__.match(urldata.url)
         path = m.group('path')
         host = m.group('host')
-        urldata.localpath = os.path.join(d.getVar('DL_DIR', True), os.path.basename(path))
+        urldata.localpath = os.path.join(d.getVar('DL_DIR', True),
+                os.path.basename(os.path.normpath(path)))
 
     def download(self, urldata, d):
         dldir = d.getVar('DL_DIR', True)

bitbake/lib/bb/fetch2/svn.py

@@ -101,7 +101,8 @@ class Svn(FetchMethod):
                 suffix = "@%s" % (ud.revision)
 
             if command == "fetch":
-                svncmd = "%s co %s %s://%s/%s%s %s" % (ud.basecmd, " ".join(options), proto, svnroot, ud.module, suffix, ud.module)
+                transportuser = ud.parm.get("transportuser", "")
+                svncmd = "%s co %s %s://%s%s/%s%s %s" % (ud.basecmd, " ".join(options), proto, transportuser, svnroot, ud.module, suffix, ud.module)
             elif command == "update":
                 svncmd = "%s update %s" % (ud.basecmd, " ".join(options))
             else:

bitbake/lib/bb/fetch2/wget.py

@@ -25,6 +25,9 @@ BitBake build tools.
 #
 # Based on functions from the base bb module, Copyright 2003 Holger Schurig
 
+import re
+import tempfile
+import subprocess
 import os
 import logging
 import bb
@@ -34,6 +37,7 @@ from   bb.fetch2 import FetchMethod
 from   bb.fetch2 import FetchError
 from   bb.fetch2 import logger
 from   bb.fetch2 import runfetchcmd
+from   bs4 import BeautifulSoup
 
 class Wget(FetchMethod):
     """Class to fetch urls via 'wget'"""
@@ -104,3 +108,274 @@ class Wget(FetchMethod):
         self._runwget(ud, d, fetchcmd, True)
 
         return True
+
+    def _parse_path(self, regex, s):
+        """
+        Find and group name, version and archive type in the given string s
+        """
+
+        m = regex.search(s)
+        if m:
+            pname = ''
+            pver = ''
+            ptype = ''
+
+            mdict = m.groupdict()
+            if 'name' in mdict.keys():
+                pname = mdict['name']
+            if 'pver' in mdict.keys():
+                pver = mdict['pver']
+            if 'type' in mdict.keys():
+                ptype = mdict['type']
+
+            bb.debug(3, "_parse_path: %s, %s, %s" % (pname, pver, ptype))
+
+            return (pname, pver, ptype)
+
+        return None
+
+    def _modelate_version(self, version):
+        if version[0] in ['.', '-']:
+            if version[1].isdigit():
+                version = version[1] + version[0] + version[2:len(version)]
+            else:
+                version = version[1:len(version)]
+
+        version = re.sub('-', '.', version)
+        version = re.sub('_', '.', version)
+        version = re.sub('(rc)+', '.1000.', version)
+        version = re.sub('(beta)+', '.100.', version)
+        version = re.sub('(alpha)+', '.10.', version)
+        if version[0] == 'v':
+            version = version[1:len(version)]
+        return version
+
+    def _vercmp(self, old, new):
+        """
+        Check whether 'new' is newer than 'old' version. We use existing vercmp() for the
+        purpose. PE is cleared in comparison as it's not for build, and PR is cleared too
+        for simplicity as it's somehow difficult to get from various upstream format
+        """
+
+        (oldpn, oldpv, oldsuffix) = old
+        (newpn, newpv, newsuffix) = new
+
+        """
+        Check for a new suffix type that we have never heard of before
+        """
+        if (newsuffix):
+            m = self.suffix_regex_comp.search(newsuffix)
+            if not m:
+                bb.warn("%s has a possible unknown suffix: %s" % (newpn, newsuffix))
+                return False
+
+        """
+        Not our package so ignore it
+        """
+        if oldpn != newpn:
+            return False
+
+        oldpv = self._modelate_version(oldpv)
+        newpv = self._modelate_version(newpv)
+
+        return bb.utils.vercmp(("0", oldpv, ""), ("0", newpv, ""))
+
+    def _fetch_index(self, uri, ud, d):
+        """
+        Run fetch checkstatus to get directory information
+        """
+        f = tempfile.NamedTemporaryFile()
+
+        agent = "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.2.12) Gecko/20101027 Ubuntu/9.10 (karmic) Firefox/3.6.12"
+        fetchcmd = self.basecmd
+        fetchcmd += " -O " + f.name + " --user-agent='" + agent + "' '" + uri + "'"
+        try:
+            self._runwget(ud, d, fetchcmd, True)
+            fetchresult = f.read()
+        except bb.fetch2.BBFetchException:
+            fetchresult = ""
+
+        f.close()
+        return fetchresult
+
+    def _check_latest_version(self, url, package, package_regex, current_version, ud, d):
+        """
+        Return the latest version of a package inside a given directory path
+        If error or no version, return ""
+        """
+        valid = 0
+        version = ['', '', '']
+
+        bb.debug(3, "VersionURL: %s" % (url))
+        soup = BeautifulSoup(self._fetch_index(url, ud, d))
+        if not soup:
+            bb.debug(3, "*** %s NO SOUP" % (url))
+            return ""
+
+        for line in soup.find_all('a', href=True):
+            bb.debug(3, "line['href'] = '%s'" % (line['href']))
+            bb.debug(3, "line = '%s'" % (str(line)))
+
+            newver = self._parse_path(package_regex, line['href'])
+            if not newver:
+                newver = self._parse_path(package_regex, str(line))
+
+            if newver:
+                bb.debug(3, "Upstream version found: %s" % newver[1])
+                if valid == 0:
+                    version = newver
+                    valid = 1
+                elif self._vercmp(version, newver) < 0:
+                    version = newver
+                
+        pupver = re.sub('_', '.', version[1])
+
+        bb.debug(3, "*** %s -> UpstreamVersion = %s (CurrentVersion = %s)" %
+                (package, pupver or "N/A", current_version[1]))
+
+        if valid:
+            return pupver
+
+        return ""
+
+    def _check_latest_version_by_dir(self, dirver, package, package_regex,
+            current_version, ud, d):
+        """
+            Scan every directory in order to get upstream version.
+        """
+        version_dir = ['', '', '']
+        version = ['', '', '']
+
+        dirver_regex = re.compile("(\D*)((\d+[\.-_])+(\d+))")
+        s = dirver_regex.search(dirver)
+        if s:
+            version_dir[1] = s.group(2)
+        else:
+            version_dir[1] = dirver
+
+        dirs_uri = bb.fetch.encodeurl([ud.type, ud.host,
+                ud.path.split(dirver)[0], ud.user, ud.pswd, {}])
+        bb.debug(3, "DirURL: %s, %s" % (dirs_uri, package))
+
+        soup = BeautifulSoup(self._fetch_index(dirs_uri, ud, d))
+        if not soup:
+            return version[1]
+
+        for line in soup.find_all('a', href=True):
+            s = dirver_regex.search(line['href'].strip("/"))
+            if s:
+                version_dir_new = ['', s.group(2), '']
+                if self._vercmp(version_dir, version_dir_new) <= 0:
+                    dirver_new = s.group(1) + s.group(2)
+                    path = ud.path.replace(dirver, dirver_new, True) \
+                        .split(package)[0]
+                    uri = bb.fetch.encodeurl([ud.type, ud.host, path,
+                        ud.user, ud.pswd, {}])
+
+                    pupver = self._check_latest_version(uri,
+                            package, package_regex, current_version, ud, d)
+                    if pupver:
+                        version[1] = pupver
+
+                    version_dir = version_dir_new
+
+        return version[1]
+
+    def _init_regexes(self, package, ud, d):
+        """
+        Match as many patterns as possible such as:
+                gnome-common-2.20.0.tar.gz (most common format)
+                gtk+-2.90.1.tar.gz
+                xf86-input-synaptics-12.6.9.tar.gz
+                dri2proto-2.3.tar.gz
+                blktool_4.orig.tar.gz
+                libid3tag-0.15.1b.tar.gz
+                unzip552.tar.gz
+                icu4c-3_6-src.tgz
+                genext2fs_1.3.orig.tar.gz
+                gst-fluendo-mp3
+        """
+        # match most patterns which uses "-" as separator to version digits
+        pn_prefix1 = "[a-zA-Z][a-zA-Z0-9]*([-_][a-zA-Z]\w+)*\+?[-_]"
+        # a loose pattern such as for unzip552.tar.gz
+        pn_prefix2 = "[a-zA-Z]+"
+        # a loose pattern such as for 80325-quicky-0.4.tar.gz
+        pn_prefix3 = "[0-9]+[-]?[a-zA-Z]+"
+        # Save the Package Name (pn) Regex for use later
+        pn_regex = "(%s|%s|%s)" % (pn_prefix1, pn_prefix2, pn_prefix3)
+
+        # match version
+        pver_regex = "(([A-Z]*\d+[a-zA-Z]*[\.-_]*)+)"
+
+        # match arch
+        parch_regex = "-source|_all_"
+
+        # src.rpm extension was added only for rpm package. Can be removed if the rpm
+        # packaged will always be considered as having to be manually upgraded
+        psuffix_regex = "(tar\.gz|tgz|tar\.bz2|zip|xz|rpm|bz2|orig\.tar\.gz|tar\.xz|src\.tar\.gz|src\.tgz|svnr\d+\.tar\.bz2|stable\.tar\.gz|src\.rpm)"
+
+        # match name, version and archive type of a package
+        package_regex_comp = re.compile("(?P<name>%s?\.?v?)(?P<pver>%s)(?P<arch>%s)?[\.-](?P<type>%s$)"
+                                                    % (pn_regex, pver_regex, parch_regex, psuffix_regex))
+        self.suffix_regex_comp = re.compile(psuffix_regex)
+
+        # compile regex, can be specific by package or generic regex
+        pn_regex = d.getVar('REGEX', True)
+        if pn_regex:
+            package_custom_regex_comp = re.compile(pn_regex)
+        else:
+            version = self._parse_path(package_regex_comp, package)
+            if version:
+                package_custom_regex_comp = re.compile(
+                    "(?P<name>%s)(?P<pver>%s)(?P<arch>%s)?[\.-](?P<type>%s)" %
+                    (re.escape(version[0]), pver_regex, parch_regex, psuffix_regex))
+            else:
+                package_custom_regex_comp = None
+
+        return package_custom_regex_comp
+
+    def latest_versionstring(self, ud, d):
+        """
+        Manipulate the URL and try to obtain the latest package version
+
+        sanity check to ensure same name and type.
+        """
+        package = ud.path.split("/")[-1]
+        current_version = ['', d.getVar('PV', True), '']
+
+        """possible to have no version in pkg name, such as spectrum-fw"""
+        if not re.search("\d+", package):
+            current_version[1] = re.sub('_', '.', current_version[1])
+            current_version[1] = re.sub('-', '.', current_version[1])
+            return current_version[1]
+
+        package_regex = self._init_regexes(package, ud, d)
+        if package_regex is None:
+            bb.warn("latest_versionstring: package %s don't match pattern" % (package))
+            return ""
+        bb.debug(3, "latest_versionstring, regex: %s" % (package_regex.pattern))
+
+        uri = ""
+        regex_uri = d.getVar("REGEX_URI", True)
+        if not regex_uri:
+            path = ud.path.split(package)[0]
+
+            # search for version matches on folders inside the path, like:
+            # "5.7" in http://download.gnome.org/sources/${PN}/5.7/${PN}-${PV}.tar.gz
+            dirver_regex = re.compile("(?P<dirver>[^/]*(\d+\.)*\d+([-_]r\d+)*)/")
+            m = dirver_regex.search(path)
+            if m:
+                pn = d.getVar('PN', True)
+                dirver = m.group('dirver')
+
+                dirver_pn_regex = re.compile("%s\d?" % (re.escape(pn)))
+                if not dirver_pn_regex.search(dirver):
+                    return self._check_latest_version_by_dir(dirver,
+                        package, package_regex, current_version, ud, d)
+
+            uri = bb.fetch.encodeurl([ud.type, ud.host, path, ud.user, ud.pswd, {}])
+        else:
+            uri = regex_uri
+
+        return self._check_latest_version(uri, package, package_regex,
+                current_version, ud, d)

bitbake/lib/bb/main.py

@@ -0,0 +1,391 @@
+#!/usr/bin/env python
+# ex:ts=4:sw=4:sts=4:et
+# -*- tab-width: 4; c-basic-offset: 4; indent-tabs-mode: nil -*-
+#
+# Copyright (C) 2003, 2004  Chris Larson
+# Copyright (C) 2003, 2004  Phil Blundell
+# Copyright (C) 2003 - 2005 Michael 'Mickey' Lauer
+# Copyright (C) 2005        Holger Hans Peter Freyther
+# Copyright (C) 2005        ROAD GmbH
+# Copyright (C) 2006        Richard Purdie
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along
+# with this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+import os
+import sys
+import logging
+import optparse
+import warnings
+
+import bb
+from bb import event
+import bb.msg
+from bb import cooker
+from bb import ui
+from bb import server
+from bb import cookerdata
+
+__version__ = "1.26.0"
+logger = logging.getLogger("BitBake")
+
+class BBMainException(bb.BBHandledException):
+    pass
+
+def get_ui(config):
+    if not config.ui:
+        # modify 'ui' attribute because it is also read by cooker
+        config.ui = os.environ.get('BITBAKE_UI', 'knotty')
+
+    interface = config.ui
+
+    try:
+        # Dynamically load the UI based on the ui name. Although we
+        # suggest a fixed set this allows you to have flexibility in which
+        # ones are available.
+        module = __import__("bb.ui", fromlist = [interface])
+        return getattr(module, interface)
+    except AttributeError:
+        raise BBMainException("FATAL: Invalid user interface '%s' specified.\n"
+                 "Valid interfaces: depexp, goggle, ncurses, hob, knotty [default]." % interface)
+
+
+# Display bitbake/OE warnings via the BitBake.Warnings logger, ignoring others"""
+warnlog = logging.getLogger("BitBake.Warnings")
+_warnings_showwarning = warnings.showwarning
+def _showwarning(message, category, filename, lineno, file=None, line=None):
+    if file is not None:
+        if _warnings_showwarning is not None:
+            _warnings_showwarning(message, category, filename, lineno, file, line)
+    else:
+        s = warnings.formatwarning(message, category, filename, lineno)
+        warnlog.warn(s)
+
+warnings.showwarning = _showwarning
+warnings.filterwarnings("ignore")
+warnings.filterwarnings("default", module="(<string>$|(oe|bb)\.)")
+warnings.filterwarnings("ignore", category=PendingDeprecationWarning)
+warnings.filterwarnings("ignore", category=ImportWarning)
+warnings.filterwarnings("ignore", category=DeprecationWarning, module="<string>$")
+warnings.filterwarnings("ignore", message="With-statements now directly support multiple context managers")
+
+class BitBakeConfigParameters(cookerdata.ConfigParameters):
+
+    def parseCommandLine(self, argv=sys.argv):
+        parser = optparse.OptionParser(
+            version = "BitBake Build Tool Core version %s, %%prog version %s" % (bb.__version__, __version__),
+            usage = """%prog [options] [recipename/target ...]
+
+    Executes the specified task (default is 'build') for a given set of target recipes (.bb files).
+    It is assumed there is a conf/bblayers.conf available in cwd or in BBPATH which
+    will provide the layer, BBFILES and other configuration information.""")
+
+        parser.add_option("-b", "--buildfile", help = "Execute tasks from a specific .bb recipe directly. WARNING: Does not handle any dependencies from other recipes.",
+                   action = "store", dest = "buildfile", default = None)
+
+        parser.add_option("-k", "--continue", help = "Continue as much as possible after an error. While the target that failed and anything depending on it cannot be built, as much as possible will be built before stopping.",
+                   action = "store_false", dest = "abort", default = True)
+
+        parser.add_option("-a", "--tryaltconfigs", help = "Continue with builds by trying to use alternative providers where possible.",
+                   action = "store_true", dest = "tryaltconfigs", default = False)
+
+        parser.add_option("-f", "--force", help = "Force the specified targets/task to run (invalidating any existing stamp file).",
+                   action = "store_true", dest = "force", default = False)
+
+        parser.add_option("-c", "--cmd", help = "Specify the task to execute. The exact options available depend on the metadata. Some examples might be 'compile' or 'populate_sysroot' or 'listtasks' may give a list of the tasks available.",
+                   action = "store", dest = "cmd")
+
+        parser.add_option("-C", "--clear-stamp", help = "Invalidate the stamp for the specified task such as 'compile' and then run the default task for the specified target(s).",
+                    action = "store", dest = "invalidate_stamp")
+
+        parser.add_option("-r", "--read", help = "Read the specified file before bitbake.conf.",
+                   action = "append", dest = "prefile", default = [])
+
+        parser.add_option("-R", "--postread", help = "Read the specified file after bitbake.conf.",
+                          action = "append", dest = "postfile", default = [])
+
+        parser.add_option("-v", "--verbose", help = "Output more log message data to the terminal.",
+                   action = "store_true", dest = "verbose", default = False)
+
+        parser.add_option("-D", "--debug", help = "Increase the debug level. You can specify this more than once.",
+                   action = "count", dest="debug", default = 0)
+
+        parser.add_option("-n", "--dry-run", help = "Don't execute, just go through the motions.",
+                   action = "store_true", dest = "dry_run", default = False)
+
+        parser.add_option("-S", "--dump-signatures", help = "Dump out the signature construction information, with no task execution. The SIGNATURE_HANDLER parameter is passed to the handler. Two common values are none and printdiff but the handler may define more/less. none means only dump the signature, printdiff means compare the dumped signature with the cached one.",
+                   action = "append", dest = "dump_signatures", default = [], metavar="SIGNATURE_HANDLER")
+
+        parser.add_option("-p", "--parse-only", help = "Quit after parsing the BB recipes.",
+                   action = "store_true", dest = "parse_only", default = False)
+
+        parser.add_option("-s", "--show-versions", help = "Show current and preferred versions of all recipes.",
+                   action = "store_true", dest = "show_versions", default = False)
+
+        parser.add_option("-e", "--environment", help = "Show the global or per-recipe environment complete with information about where variables were set/changed.",
+                   action = "store_true", dest = "show_environment", default = False)
+
+        parser.add_option("-g", "--graphviz", help = "Save dependency tree information for the specified targets in the dot syntax.",
+                    action = "store_true", dest = "dot_graph", default = False)
+
+        parser.add_option("-I", "--ignore-deps", help = """Assume these dependencies don't exist and are already provided (equivalent to ASSUME_PROVIDED). Useful to make dependency graphs more appealing""",
+                    action = "append", dest = "extra_assume_provided", default = [])
+
+        parser.add_option("-l", "--log-domains", help = """Show debug logging for the specified logging domains""",
+                    action = "append", dest = "debug_domains", default = [])
+
+        parser.add_option("-P", "--profile", help = "Profile the command and save reports.",
+                   action = "store_true", dest = "profile", default = False)
+
+        parser.add_option("-u", "--ui", help = "The user interface to use (e.g. knotty, hob, depexp).",
+                   action = "store", dest = "ui")
+
+        parser.add_option("-t", "--servertype", help = "Choose which server to use, process or xmlrpc.",
+                   action = "store", dest = "servertype")
+
+        parser.add_option("", "--token", help = "Specify the connection token to be used when connecting to a remote server.",
+                   action = "store", dest = "xmlrpctoken")
+
+        parser.add_option("", "--revisions-changed", help = "Set the exit code depending on whether upstream floating revisions have changed or not.",
+                   action = "store_true", dest = "revisions_changed", default = False)
+
+        parser.add_option("", "--server-only", help = "Run bitbake without a UI, only starting a server (cooker) process.",
+                   action = "store_true", dest = "server_only", default = False)
+
+        parser.add_option("-B", "--bind", help = "The name/address for the bitbake server to bind to.",
+                   action = "store", dest = "bind", default = False)
+
+        parser.add_option("", "--no-setscene", help = "Do not run any setscene tasks. sstate will be ignored and everything needed, built.",
+                   action = "store_true", dest = "nosetscene", default = False)
+
+        parser.add_option("", "--remote-server", help = "Connect to the specified server.",
+                   action = "store", dest = "remote_server", default = False)
+
+        parser.add_option("-m", "--kill-server", help = "Terminate the remote server.",
+                    action = "store_true", dest = "kill_server", default = False)
+
+        parser.add_option("", "--observe-only", help = "Connect to a server as an observing-only client.",
+                   action = "store_true", dest = "observe_only", default = False)
+
+        parser.add_option("", "--status-only", help = "Check the status of the remote bitbake server.",
+                   action = "store_true", dest = "status_only", default = False)
+
+        parser.add_option("-w", "--write-log", help = "Writes the event log of the build to a bitbake event json file. Use '' (empty string) to assign the name automatically.",
+                   action = "store", dest = "writeeventlog")
+
+        options, targets = parser.parse_args(argv)
+
+        # some environmental variables set also configuration options
+        if "BBSERVER" in os.environ:
+            options.servertype = "xmlrpc"
+            options.remote_server = os.environ["BBSERVER"]
+
+        if "BBTOKEN" in os.environ:
+            options.xmlrpctoken = os.environ["BBTOKEN"]
+
+        if "BBEVENTLOG" is os.environ:
+            options.writeeventlog = os.environ["BBEVENTLOG"]
+
+        # fill in proper log name if not supplied
+        if options.writeeventlog is not None and len(options.writeeventlog) == 0:
+            import datetime
+            options.writeeventlog = "bitbake_eventlog_%s.json" % datetime.datetime.now().strftime("%Y%m%d%H%M%S")
+
+        # if BBSERVER says to autodetect, let's do that
+        if options.remote_server:
+            [host, port] = options.remote_server.split(":", 2)
+            port = int(port)
+            # use automatic port if port set to -1, means read it from
+            # the bitbake.lock file; this is a bit tricky, but we always expect
+            # to be in the base of the build directory if we need to have a
+            # chance to start the server later, anyway
+            if port == -1:
+                lock_location = "./bitbake.lock"
+                # we try to read the address at all times; if the server is not started,
+                # we'll try to start it after the first connect fails, below
+                try:
+                    lf = open(lock_location, 'r')
+                    remotedef = lf.readline()
+                    [host, port] = remotedef.split(":")
+                    port = int(port)
+                    lf.close()
+                    options.remote_server = remotedef
+                except Exception as e:
+                    raise BBMainException("Failed to read bitbake.lock (%s), invalid port" % str(e))
+
+        return options, targets[1:]
+
+
+def start_server(servermodule, configParams, configuration, features):
+    server = servermodule.BitBakeServer()
+    if configParams.bind:
+        (host, port) = configParams.bind.split(':')
+        server.initServer((host, int(port)))
+        configuration.interface = [ server.serverImpl.host, server.serverImpl.port ]
+    else:
+        server.initServer()
+        configuration.interface = []
+
+    try:
+        configuration.setServerRegIdleCallback(server.getServerIdleCB())
+
+        cooker = bb.cooker.BBCooker(configuration, features)
+
+        server.addcooker(cooker)
+        server.saveConnectionDetails()
+    except Exception as e:
+        exc_info = sys.exc_info()
+        while hasattr(server, "event_queue"):
+            try:
+                import queue
+            except ImportError:
+                import Queue as queue
+            try:
+                event = server.event_queue.get(block=False)
+            except (queue.Empty, IOError):
+                break
+            if isinstance(event, logging.LogRecord):
+                logger.handle(event)
+        raise exc_info[1], None, exc_info[2]
+    server.detach()
+    cooker.lock.close()
+    return server
+
+
+def bitbake_main(configParams, configuration):
+
+    # Python multiprocessing requires /dev/shm on Linux
+    if sys.platform.startswith('linux') and not os.access('/dev/shm', os.W_OK | os.X_OK):
+        raise BBMainException("FATAL: /dev/shm does not exist or is not writable")
+
+    # Unbuffer stdout to avoid log truncation in the event
+    # of an unorderly exit as well as to provide timely
+    # updates to log files for use with tail
+    try:
+        if sys.stdout.name == '<stdout>':
+            sys.stdout = os.fdopen(sys.stdout.fileno(), 'w', 0)
+    except:
+        pass
+
+
+    configuration.setConfigParameters(configParams)
+
+    ui_module = get_ui(configParams)
+
+    # Server type can be xmlrpc or process currently, if nothing is specified,
+    # the default server is process
+    if configParams.servertype:
+        server_type = configParams.servertype
+    else:
+        server_type = 'process'
+
+    try:
+        module = __import__("bb.server", fromlist = [server_type])
+        servermodule = getattr(module, server_type)
+    except AttributeError:
+        raise BBMainException("FATAL: Invalid server type '%s' specified.\n"
+                              "Valid interfaces: xmlrpc, process [default]." % server_type)
+
+    if configParams.server_only:
+        if configParams.servertype != "xmlrpc":
+            raise BBMainException("FATAL: If '--server-only' is defined, we must set the "
+                                  "servertype as 'xmlrpc'.\n")
+        if not configParams.bind:
+            raise BBMainException("FATAL: The '--server-only' option requires a name/address "
+                                  "to bind to with the -B option.\n")
+        if configParams.remote_server:
+            raise BBMainException("FATAL: The '--server-only' option conflicts with %s.\n" %
+                                  ("the BBSERVER environment variable" if "BBSERVER" in os.environ \
+                                   else "the '--remote-server' option" ))
+
+    if configParams.bind and configParams.servertype != "xmlrpc":
+        raise BBMainException("FATAL: If '-B' or '--bind' is defined, we must "
+                              "set the servertype as 'xmlrpc'.\n")
+
+    if configParams.remote_server and configParams.servertype != "xmlrpc":
+        raise BBMainException("FATAL: If '--remote-server' is defined, we must "
+                              "set the servertype as 'xmlrpc'.\n")
+
+    if configParams.observe_only and (not configParams.remote_server or configParams.bind):
+        raise BBMainException("FATAL: '--observe-only' can only be used by UI clients "
+                              "connecting to a server.\n")
+
+    if configParams.kill_server and not configParams.remote_server:
+        raise BBMainException("FATAL: '--kill-server' can only be used to terminate a remote server")
+
+    if "BBDEBUG" in os.environ:
+        level = int(os.environ["BBDEBUG"])
+        if level > configuration.debug:
+            configuration.debug = level
+
+    bb.msg.init_msgconfig(configParams.verbose, configuration.debug,
+                         configuration.debug_domains)
+
+    # Ensure logging messages get sent to the UI as events
+    handler = bb.event.LogHandler()
+    if not configParams.status_only:
+        # In status only mode there are no logs and no UI
+        logger.addHandler(handler)
+
+    # Clear away any spurious environment variables while we stoke up the cooker
+    cleanedvars = bb.utils.clean_environment()
+
+    featureset = []
+    if not configParams.server_only:
+        # Collect the feature set for the UI
+        featureset = getattr(ui_module, "featureSet", [])
+
+    if not configParams.remote_server:
+        # we start a server with a given configuration
+        server = start_server(servermodule, configParams, configuration, featureset)
+        bb.event.ui_queue = []
+    else:
+        # we start a stub server that is actually a XMLRPClient that connects to a real server
+        server = servermodule.BitBakeXMLRPCClient(configParams.observe_only, configParams.xmlrpctoken)
+        server.saveConnectionDetails(configParams.remote_server)
+
+
+    if not configParams.server_only:
+        try:
+            server_connection = server.establishConnection(featureset)
+        except Exception as e:
+            if configParams.kill_server:
+                return 0
+            bb.fatal("Could not connect to server %s: %s" % (configParams.remote_server, str(e)))
+
+        # Restore the environment in case the UI needs it
+        for k in cleanedvars:
+            os.environ[k] = cleanedvars[k]
+
+        logger.removeHandler(handler)
+
+
+        if configParams.status_only:
+            server_connection.terminate()
+            return 0
+
+        if configParams.kill_server:
+            server_connection.connection.terminateServer()
+            bb.event.ui_queue = []
+            return 0
+
+        try:
+            return ui_module.main(server_connection.connection, server_connection.events, configParams)
+        finally:
+            bb.event.ui_queue = []
+            server_connection.terminate()
+    else:
+        print("Bitbake server address: %s, server port: %s" % (server.serverImpl.host, server.serverImpl.port))
+        return 0
+
+    return 1

bitbake/lib/bb/monitordisk.py

@@ -52,10 +52,10 @@ def getMountedDev(path):
     parentDev = os.stat(path).st_dev
     currentDev = parentDev
     # When the current directory's device is different from the
-    # parrent's, then the current directory is a mount point
+    # parent's, then the current directory is a mount point
     while parentDev == currentDev:
         mountPoint = path
-        # Use dirname to get the parrent's directory
+        # Use dirname to get the parent's directory
         path = os.path.dirname(path)
         # Reach the "/"
         if path == mountPoint:
@@ -77,7 +77,7 @@ def getDiskData(BBDirs, configuration):
     """Prepare disk data for disk space monitor"""
 
     # Save the device IDs, need the ID to be unique (the dictionary's key is
-    # unique), so that when more than one directories are located in the same
+    # unique), so that when more than one directory is located on the same
     # device, we just monitor it once
     devDict = {}
     for pathSpaceInode in BBDirs.split():
@@ -187,11 +187,11 @@ class diskMonitor:
                 if self.spaceInterval and self.inodeInterval:
                     self.enableMonitor = True
                     # These are for saving the previous disk free space and inode, we
-                    # use them to avoid print too many warning messages
+                    # use them to avoid printing too many warning messages
                     self.preFreeS = {}
                     self.preFreeI = {}
-                    # This is for STOPTASKS and ABORT, to avoid print the message repeatly
-                    # during waiting the tasks to finish
+                    # This is for STOPTASKS and ABORT, to avoid printing the message
+                    # repeatedly while waiting for the tasks to finish
                     self.checked = {}
                     for k in self.devDict:
                         self.preFreeS[k] = 0
@@ -239,11 +239,9 @@ class diskMonitor:
                 freeInode = st.f_favail
 
                 if minInode and freeInode < minInode:
-                    # Some fs formats' (e.g., btrfs) statvfs.f_files (inodes) is
-                    # zero, this is a feature of the fs, we disable the inode
-                    # checking for such a fs.
+                    # Some filesystems use dynamic inodes so can't run out
+                    # (e.g. btrfs). This is reported by the inode count being 0.
                     if st.f_files == 0:
-                        logger.info("Inode check for %s is unavaliable, will remove it from disk monitor" % path)
                         self.devDict[k][2] = None
                         continue
                     # Always show warning, the self.checked would always be False if the action is WARN

bitbake/lib/bb/namedtuple_with_abc.py

@@ -202,8 +202,8 @@ if __name__ == '__main__':
     print(rec5._replace(k=222)._my_custom_method())  # MyMixIn's
     print(rec5._replace(k=222).count(2))  # MyMixIn's
 
-    # None that behavior: the standard namedtuple methods cannot be
-    # overriden by a foreign mix-in -- even if the mix-in is declared
+    # Note that behavior: the standard namedtuple methods cannot be
+    # overridden by a foreign mix-in -- even if the mix-in is declared
     # as the leftmost base class (but, obviously, you can override them
     # in the defined class or its subclasses):
 

bitbake/lib/bb/parse/__init__.py

@@ -49,8 +49,11 @@ class ParseError(Exception):
         else:
             return "ParseError in %s: %s" % (self.filename, self.msg)
 
-class SkipPackage(Exception):
-    """Exception raised to skip this package"""
+class SkipRecipe(Exception):
+    """Exception raised to skip this recipe"""
+
+class SkipPackage(SkipRecipe):
+    """Exception raised to skip this recipe (use SkipRecipe in new code)"""
 
 __mtime_cache = {}
 def cached_mtime(f):
@@ -70,6 +73,11 @@ def update_mtime(f):
     __mtime_cache[f] = os.stat(f)[stat.ST_MTIME]
     return __mtime_cache[f]
 
+def update_cache(f):
+    if f in __mtime_cache:
+        logger.debug(1, "Updating mtime cache for %s" % f)
+        update_mtime(f)
+
 def mark_dependency(d, f):
     if f.startswith('./'):
         f = "%s/%s" % (os.getcwd(), f[2:])
@@ -121,7 +129,6 @@ def resolve_file(fn, d):
     if not os.path.isfile(fn):
         raise IOError("file %s not found" % fn)
 
-    logger.debug(2, "LOAD %s", fn)
     return fn
 
 # Used by OpenEmbedded metadata

bitbake/lib/bb/parse/ast.py

@@ -128,7 +128,7 @@ class DataNode(AstNode):
         if 'flag' in groupd and groupd['flag'] != None:
             flag = groupd['flag']
         elif groupd["lazyques"]:
-            flag = "defaultval"
+            flag = "_defaultval"
 
         loginfo['op'] = op
         loginfo['detail'] = groupd["value"]
@@ -139,7 +139,7 @@ class DataNode(AstNode):
             data.setVar(key, val, **loginfo)
 
 class MethodNode(AstNode):
-    tr_tbl = string.maketrans('/.+-@%', '______')
+    tr_tbl = string.maketrans('/.+-@%&', '_______')
 
     def __init__(self, filename, lineno, func_name, body):
         AstNode.__init__(self, filename, lineno)
@@ -226,6 +226,8 @@ class ExportFuncsNode(AstNode):
             if data.getVarFlag(calledfunc, "python"):
                 data.setVar(func, "    bb.build.exec_func('" + calledfunc + "', d)\n")
             else:
+                if "-" in self.classname:
+                   bb.fatal("The classname %s contains a dash character and is calling an sh function %s using EXPORT_FUNCTIONS. Since a dash is illegal in sh function names, this cannot work, please rename the class or don't use EXPORT_FUNCTIONS." % (self.classname, calledfunc))
                 data.setVar(func, "    " + calledfunc + "\n")
             data.setVarFlag(func, 'export_func', '1')
 
@@ -337,8 +339,10 @@ def finalize(fn, d, variant = None):
 
     bb.event.fire(bb.event.RecipeParsed(fn), d)
 
-def _create_variants(datastores, names, function):
+def _create_variants(datastores, names, function, onlyfinalise):
     def create_variant(name, orig_d, arg = None):
+        if onlyfinalise and name not in onlyfinalise:
+            return
         new_d = bb.data.createCopy(orig_d)
         function(arg or name, new_d)
         datastores[name] = new_d
@@ -375,7 +379,7 @@ def _expand_versions(versions):
 def multi_finalize(fn, d):
     appends = (d.getVar("__BBAPPEND", True) or "").split()
     for append in appends:
-        logger.debug(2, "Appending .bbappend file %s to %s", append, fn)
+        logger.debug(1, "Appending .bbappend file %s to %s", append, fn)
         bb.parse.BBHandler.handle(append, d, True)
 
     onlyfinalise = d.getVar("__ONLYFINALISE", False)
@@ -384,7 +388,7 @@ def multi_finalize(fn, d):
     d = bb.data.createCopy(safe_d)
     try:
         finalize(fn, d)
-    except bb.parse.SkipPackage as e:
+    except bb.parse.SkipRecipe as e:
         d.setVar("__SKIPPED", e.args[0])
     datastores = {"": safe_d}
 
@@ -427,10 +431,10 @@ def multi_finalize(fn, d):
             verfunc(pv, d, safe_d)
             try:
                 finalize(fn, d)
-            except bb.parse.SkipPackage as e:
+            except bb.parse.SkipRecipe as e:
                 d.setVar("__SKIPPED", e.args[0])
 
-        _create_variants(datastores, versions, verfunc)
+        _create_variants(datastores, versions, verfunc, onlyfinalise)
 
     extended = d.getVar("BBCLASSEXTEND", True) or ""
     if extended:
@@ -460,14 +464,14 @@ def multi_finalize(fn, d):
             bb.parse.BBHandler.inherit(extendedmap[name], fn, 0, d)
 
         safe_d.setVar("BBCLASSEXTEND", extended)
-        _create_variants(datastores, extendedmap.keys(), extendfunc)
+        _create_variants(datastores, extendedmap.keys(), extendfunc, onlyfinalise)
 
     for variant, variant_d in datastores.iteritems():
         if variant:
             try:
                 if not onlyfinalise or variant in onlyfinalise:
                     finalize(fn, variant_d, variant)
-            except bb.parse.SkipPackage as e:
+            except bb.parse.SkipRecipe as e:
                 variant_d.setVar("__SKIPPED", e.args[0])
 
     if len(datastores) > 1:

bitbake/lib/bb/parse/parse_py/BBHandler.py

@@ -86,7 +86,7 @@ def inherit(files, fn, lineno, d):
                 file = abs_fn
 
         if not file in __inherit_cache:
-            logger.log(logging.DEBUG -1, "BB %s:%d: inheriting %s", fn, lineno, file)
+            logger.debug(1, "Inheriting %s (from %s:%d)" % (file, fn, lineno))
             __inherit_cache.append( file )
             d.setVar('__inherit_cache', __inherit_cache)
             include(fn, file, lineno, d, "inherit")
@@ -124,12 +124,6 @@ def handle(fn, d, include):
     __classname__ = ""
     __residue__ = []
 
-
-    if include == 0:
-        logger.debug(2, "BB %s: handle(data)", fn)
-    else:
-        logger.debug(2, "BB %s: handle(data, include)", fn)
-
     base_name = os.path.basename(fn)
     (root, ext) = os.path.splitext(base_name)
     init(d)
@@ -160,7 +154,7 @@ def handle(fn, d, include):
 
     try:
         statements.eval(d)
-    except bb.parse.SkipPackage:
+    except bb.parse.SkipRecipe:
         bb.data.setVar("__SKIPPED", True, d)
         if include == 0:
             return { "" : d }

bitbake/lib/bb/parse/parse_py/ConfHandler.py

@@ -27,7 +27,7 @@
 import re, os
 import logging
 import bb.utils
-from bb.parse import ParseError, resolve_file, ast, logger
+from bb.parse import ParseError, resolve_file, ast, logger, handle
 
 __config_regexp__  = re.compile( r"""
     ^
@@ -66,38 +66,36 @@ def init(data):
 def supports(fn, d):
     return fn[-5:] == ".conf"
 
-def include(oldfn, fn, lineno, data, error_out):
+def include(parentfn, fn, lineno, data, error_out):
     """
     error_out: A string indicating the verb (e.g. "include", "inherit") to be
     used in a ParseError that will be raised if the file to be included could
     not be included. Specify False to avoid raising an error in this case.
     """
-    if oldfn == fn: # prevent infinite recursion
+    if parentfn == fn: # prevent infinite recursion
         return None
 
-    import bb
     fn = data.expand(fn)
-    oldfn = data.expand(oldfn)
+    parentfn = data.expand(parentfn)
 
     if not os.path.isabs(fn):
-        dname = os.path.dirname(oldfn)
+        dname = os.path.dirname(parentfn)
         bbpath = "%s:%s" % (dname, data.getVar("BBPATH", True))
         abs_fn, attempts = bb.utils.which(bbpath, fn, history=True)
         if abs_fn and bb.parse.check_dependency(data, abs_fn):
-            bb.warn("Duplicate inclusion for %s in %s" % (abs_fn, data.getVar('FILE', True)))
+            logger.warn("Duplicate inclusion for %s in %s" % (abs_fn, data.getVar('FILE', True)))
         for af in attempts:
             bb.parse.mark_dependency(data, af)
         if abs_fn:
             fn = abs_fn
     elif bb.parse.check_dependency(data, fn):
-        bb.warn("Duplicate inclusion for %s in %s" % (fn, data.getVar('FILE', True)))
+        logger.warn("Duplicate inclusion for %s in %s" % (fn, data.getVar('FILE', True)))
 
-    from bb.parse import handle
     try:
-        ret = handle(fn, data, True)
+        ret = bb.parse.handle(fn, data, True)
     except (IOError, OSError):
         if error_out:
-            raise ParseError("Could not %(error_out)s file %(fn)s" % vars(), oldfn, lineno)
+            raise ParseError("Could not %(error_out)s file %(fn)s" % vars(), parentfn, lineno)
         logger.debug(2, "CONF file '%s' not found", fn)
         bb.parse.mark_dependency(data, fn)
 

bitbake/lib/bb/persist_data.py

@@ -199,7 +199,9 @@ class PersistData(object):
         del self.data[domain][key]
 
 def connect(database):
-    return sqlite3.connect(database, timeout=5, isolation_level=None)
+    connection = sqlite3.connect(database, timeout=5, isolation_level=None)
+    connection.execute("pragma synchronous = off;")
+    return connection
 
 def persist(domain, d):
     """Convenience factory for SQLTable objects based upon metadata"""

bitbake/lib/bb/pysh/sherrors.py

@@ -38,4 +38,4 @@ class ExitSignal(ShellError):
     
 class ReturnSignal(ShellError):
     """Exit signal."""
-    pass
+    pass

bitbake/lib/bb/runqueue.py

@@ -97,7 +97,7 @@ class RunQueueScheduler(object):
     def __init__(self, runqueue, rqdata):
         """
         The default scheduler just returns the first buildable task (the
-        priority map is sorted by task numer)
+        priority map is sorted by task number)
         """
         self.rq = runqueue
         self.rqdata = rqdata
@@ -139,7 +139,7 @@ class RunQueueScheduler(object):
         bestprio = None
         for taskid in self.buildable:
             prio = self.rev_prio_map[taskid]
-            if not bestprio or bestprio > prio:
+            if bestprio is None or bestprio > prio:
                 stamp = self.stamps[taskid]
                 if stamp in self.rq.build_stamps.itervalues():
                     continue
@@ -186,7 +186,7 @@ class RunQueueSchedulerCompletion(RunQueueSchedulerSpeed):
     """
     A scheduler optimised to complete .bb files are quickly as possible. The
     priority map is sorted by task weight, but then reordered so once a given
-    .bb file starts to build, its completed as quickly as possible. This works
+    .bb file starts to build, it's completed as quickly as possible. This works
     well where disk space is at a premium and classes like OE's rm_work are in
     force.
     """
@@ -370,11 +370,11 @@ class RunQueueData:
 
         for listid in xrange(numTasks):
             task_done.append(False)
-            weight.append(0)
+            weight.append(1)
             deps_left.append(len(self.runq_revdeps[listid]))
 
         for listid in endpoints:
-            weight[listid] = 1
+            weight[listid] = 10
             task_done[listid] = True
 
         while True:
@@ -430,7 +430,7 @@ class RunQueueData:
             # Nothing to do
             return 0
 
-        logger.info("Preparing runqueue")
+        logger.info("Preparing RunQueue")
 
         # Step A - Work out a list of tasks to run
         #
@@ -795,7 +795,7 @@ class RunQueueData:
                 for st in self.cooker.configuration.invalidate_stamp.split(','):
                     invalidate_task(fn, "do_%s" % st, True)
 
-        # Interate over the task list and call into the siggen code
+        # Iterate over the task list and call into the siggen code
         dealtwith = set()
         todeal = set(range(len(self.runq_fnid)))
         while len(todeal) > 0:
@@ -859,15 +859,18 @@ class RunQueue:
 
     def _start_worker(self, fakeroot = False, rqexec = None):
         logger.debug(1, "Starting bitbake-worker")
+        magic = "decafbad"
+        if self.cooker.configuration.profile:
+            magic = "decafbadbad"
         if fakeroot:
             fakerootcmd = self.cfgData.getVar("FAKEROOTCMD", True)
             fakerootenv = (self.cfgData.getVar("FAKEROOTBASEENV", True) or "").split()
             env = os.environ.copy()
             for key, value in (var.split('=') for var in fakerootenv):
                 env[key] = value
-            worker = subprocess.Popen([fakerootcmd, "bitbake-worker", "decafbad"], stdout=subprocess.PIPE, stdin=subprocess.PIPE, env=env)
+            worker = subprocess.Popen([fakerootcmd, "bitbake-worker", magic], stdout=subprocess.PIPE, stdin=subprocess.PIPE, env=env)
         else:
-            worker = subprocess.Popen(["bitbake-worker", "decafbad"], stdout=subprocess.PIPE, stdin=subprocess.PIPE)
+            worker = subprocess.Popen(["bitbake-worker", magic], stdout=subprocess.PIPE, stdin=subprocess.PIPE)
         bb.utils.nonblockingfd(worker.stdout)
         workerpipe = runQueuePipe(worker.stdout, None, self.cfgData, self, rqexec)
 
@@ -876,9 +879,7 @@ class RunQueue:
             "fakerootenv" : self.rqdata.dataCache.fakerootenv,
             "fakerootdirs" : self.rqdata.dataCache.fakerootdirs,
             "fakerootnoenv" : self.rqdata.dataCache.fakerootnoenv,
-            "hashes" : bb.parse.siggen.taskhash,
-            "hash_deps" : bb.parse.siggen.runtaskdeps,
-            "sigchecksums" : bb.parse.siggen.file_checksum_values,
+            "sigdata" : bb.parse.siggen.get_taskdata(),
             "runq_hash" : self.rqdata.runq_hash,
             "logdefaultdebug" : bb.msg.loggerDefaultDebugLevel,
             "logdefaultverbose" : bb.msg.loggerDefaultVerbose,
@@ -967,11 +968,11 @@ class RunQueue:
 
         stampfile = bb.build.stampfile(taskname, self.rqdata.dataCache, fn)
 
-        # If the stamp is missing its not current
+        # If the stamp is missing, it's not current
         if not os.access(stampfile, os.F_OK):
             logger.debug(2, "Stampfile %s not available", stampfile)
             return False
-        # If its a 'nostamp' task, it's not current
+        # If it's a 'nostamp' task, it's not current
         taskdep = self.rqdata.dataCache.task_deps[fn]
         if 'nostamp' in taskdep and taskname in taskdep['nostamp']:
             logger.debug(2, "%s.%s is nostamp\n", fn, taskname)
@@ -1063,9 +1064,9 @@ class RunQueue:
             retval = self.rqexe.execute()
 
         if self.state is runQueueCleanUp:
-           self.rqexe.finish()
+            retval = self.rqexe.finish()
 
-        if self.state is runQueueComplete or self.state is runQueueFailed:
+        if (self.state is runQueueComplete or self.state is runQueueFailed) and self.rqexe:
             self.teardown_workers()
             if self.rqexe.stats.failed:
                 logger.info("Tasks Summary: Attempted %d tasks of which %d didn't need to be rerun and %d failed.", self.rqexe.stats.completed + self.rqexe.stats.failed, self.rqexe.stats.skipped, self.rqexe.stats.failed)
@@ -1106,6 +1107,7 @@ class RunQueue:
 
     def finish_runqueue(self, now = False):
         if not self.rqexe:
+            self.state = runQueueComplete
             return
 
         if now:
@@ -1153,7 +1155,7 @@ class RunQueue:
             sq_taskname.append(taskname)
             sq_task.append(task)
         call = self.hashvalidate + "(sq_fn, sq_task, sq_hash, sq_hashfn, d)"
-        locs = { "sq_fn" : sq_fn, "sq_task" : sq_taskname, "sq_hash" : sq_hash, "sq_hashfn" : sq_hashfn, "d" : self.cooker.data }
+        locs = { "sq_fn" : sq_fn, "sq_task" : sq_taskname, "sq_hash" : sq_hash, "sq_hashfn" : sq_hashfn, "d" : self.cooker.expanded_data }
         valid = bb.utils.better_eval(call, locs)
         for v in valid:
             valid_new.add(sq_task[v])
@@ -1240,6 +1242,8 @@ class RunQueue:
                 prevh = __find_md5__.search(latestmatch).group(0)
                 output = bb.siggen.compare_sigfiles(latestmatch, match, recursecb)
                 bb.plain("\nTask %s:%s couldn't be used from the cache because:\n  We need hash %s, closest matching task was %s\n  " % (pn, taskname, h, prevh) + '\n  '.join(output))
+            else:
+                bb.plain("Error, can't find multiple tasks at divergence point? Was there a previously run task?")
 
 class RunQueueExecute:
 
@@ -1304,15 +1308,14 @@ class RunQueueExecute:
         if self.stats.active > 0:
             bb.event.fire(runQueueExitWait(self.stats.active), self.cfgData)
             self.rq.read_workers()
-
-            return
+            return self.rq.active_fds()
 
         if len(self.failed_fnids) != 0:
             self.rq.state = runQueueFailed
-            return
+            return True
 
         self.rq.state = runQueueComplete
-        return
+        return True
 
     def check_dependencies(self, task, taskdeps, setscene = False):
         if not self.rq.depvalidate:
@@ -1330,7 +1333,7 @@ class RunQueueExecute:
             taskname = self.rqdata.runq_task[depid]
             taskdata[dep] = [pn, taskname, fn]
         call = self.rq.depvalidate + "(task, taskdata, notneeded, d)"
-        locs = { "task" : task, "taskdata" : taskdata, "notneeded" : self.scenequeue_notneeded, "d" : self.cooker.data }
+        locs = { "task" : task, "taskdata" : taskdata, "notneeded" : self.scenequeue_notneeded, "d" : self.cooker.expanded_data }
         valid = bb.utils.better_eval(call, locs)
         return valid
 
@@ -1399,7 +1402,7 @@ class RunQueueExecuteTasks(RunQueueExecute):
 
             call = self.rq.setsceneverify + "(covered, tasknames, fnids, fns, d, invalidtasks=invalidtasks)"
             call2 = self.rq.setsceneverify + "(covered, tasknames, fnids, fns, d)"
-            locs = { "covered" : self.rq.scenequeue_covered, "tasknames" : self.rqdata.runq_task, "fnids" : self.rqdata.runq_fnid, "fns" : self.rqdata.taskData.fn_index, "d" : self.cooker.data, "invalidtasks" : invalidtasks }
+            locs = { "covered" : self.rq.scenequeue_covered, "tasknames" : self.rqdata.runq_task, "fnids" : self.rqdata.runq_fnid, "fns" : self.rqdata.taskData.fn_index, "d" : self.cooker.expanded_data, "invalidtasks" : invalidtasks }
             # Backwards compatibility with older versions without invalidtasks
             try:
                 covered_remove = bb.utils.better_eval(call, locs)
@@ -1551,7 +1554,8 @@ class RunQueueExecuteTasks(RunQueueExecute):
                 bb.event.fire(startevent, self.cfgData)
                 self.runq_running[task] = 1
                 self.stats.taskActive()
-                bb.build.make_stamp(taskname, self.rqdata.dataCache, fn)
+                if not self.cooker.configuration.dry_run:
+                    bb.build.make_stamp(taskname, self.rqdata.dataCache, fn)
                 self.task_complete(task)
                 return True
             else:
@@ -1686,7 +1690,7 @@ class RunQueueExecuteScenequeue(RunQueueExecute):
 
         process_endpoints(endpoints)
 
-        # Build a list of setscene tasks which as "unskippable"
+        # Build a list of setscene tasks which are "unskippable"
         # These are direct endpoints referenced by the build
         endpoints2 = {}
         sq_revdeps2 = []
@@ -1818,7 +1822,7 @@ class RunQueueExecuteScenequeue(RunQueueExecute):
                 sq_taskname.append(taskname)
                 sq_task.append(task)
             call = self.rq.hashvalidate + "(sq_fn, sq_task, sq_hash, sq_hashfn, d)"
-            locs = { "sq_fn" : sq_fn, "sq_task" : sq_taskname, "sq_hash" : sq_hash, "sq_hashfn" : sq_hashfn, "d" : self.cooker.data }
+            locs = { "sq_fn" : sq_fn, "sq_task" : sq_taskname, "sq_hash" : sq_hash, "sq_hashfn" : sq_hashfn, "d" : self.cooker.expanded_data }
             valid = bb.utils.better_eval(call, locs)
 
             valid_new = stamppresent
@@ -1842,6 +1846,10 @@ class RunQueueExecuteScenequeue(RunQueueExecute):
                 realtask = self.rqdata.runq_setscene[task]
                 realdep = self.rqdata.runq_setscene[dep]
                 logger.debug(2, "%s was unavailable and is a hard dependency of %s so skipping" % (self.rqdata.get_user_idstring(realtask), self.rqdata.get_user_idstring(realdep)))
+                self.scenequeue_updatecounters(dep, fail)
+                continue
+            if task not in self.sq_revdeps2[dep]:
+                # May already have been removed by the fail case above
                 continue
             self.sq_revdeps2[dep].remove(task)
             if len(self.sq_revdeps2[dep]) == 0:
@@ -1983,6 +1991,10 @@ class RunQueueExecuteScenequeue(RunQueueExecute):
         logger.debug(1, 'We can skip tasks %s', sorted(self.rq.scenequeue_covered))
 
         self.rq.state = runQueueRunInit
+
+        completeevent = sceneQueueComplete(self.stats, self.rq)
+        bb.event.fire(completeevent, self.cfgData)
+
         return True
 
     def runqueue_process_waitpid(self, task, status):
@@ -2035,7 +2047,7 @@ class sceneQueueEvent(runQueueEvent):
 
 class runQueueTaskStarted(runQueueEvent):
     """
-    Event notifing a task was started
+    Event notifying a task was started
     """
     def __init__(self, task, stats, rq, noexec=False):
         runQueueEvent.__init__(self, task, stats, rq)
@@ -2043,7 +2055,7 @@ class runQueueTaskStarted(runQueueEvent):
 
 class sceneQueueTaskStarted(sceneQueueEvent):
     """
-    Event notifing a setscene task was started
+    Event notifying a setscene task was started
     """
     def __init__(self, task, stats, rq, noexec=False):
         sceneQueueEvent.__init__(self, task, stats, rq)
@@ -2051,7 +2063,7 @@ class sceneQueueTaskStarted(sceneQueueEvent):
 
 class runQueueTaskFailed(runQueueEvent):
     """
-    Event notifing a task failed
+    Event notifying a task failed
     """
     def __init__(self, task, stats, exitcode, rq):
         runQueueEvent.__init__(self, task, stats, rq)
@@ -2059,25 +2071,33 @@ class runQueueTaskFailed(runQueueEvent):
 
 class sceneQueueTaskFailed(sceneQueueEvent):
     """
-    Event notifing a setscene task failed
+    Event notifying a setscene task failed
     """
     def __init__(self, task, stats, exitcode, rq):
         sceneQueueEvent.__init__(self, task, stats, rq)
         self.exitcode = exitcode
 
+class sceneQueueComplete(sceneQueueEvent):
+    """
+    Event when all the sceneQueue tasks are complete
+    """
+    def __init__(self, stats, rq):
+        self.stats = stats.copy()
+        bb.event.Event.__init__(self)
+
 class runQueueTaskCompleted(runQueueEvent):
     """
-    Event notifing a task completed
+    Event notifying a task completed
     """
 
 class sceneQueueTaskCompleted(sceneQueueEvent):
     """
-    Event notifing a setscene task completed
+    Event notifying a setscene task completed
     """
 
 class runQueueTaskSkipped(runQueueEvent):
     """
-    Event notifing a task was skipped
+    Event notifying a task was skipped
     """
     def __init__(self, task, stats, rq, reason):
         runQueueEvent.__init__(self, task, stats, rq)

bitbake/lib/bb/server/process.py

@@ -38,14 +38,18 @@ from . import BitBakeBaseServer, BitBakeBaseServerConnection, BaseImplServer
 logger = logging.getLogger('BitBake')
 
 class ServerCommunicator():
-    def __init__(self, connection, event_handle):
+    def __init__(self, connection, event_handle, server):
         self.connection = connection
         self.event_handle = event_handle
+        self.server = server
 
     def runCommand(self, command):
         # @todo try/except
         self.connection.send(command)
 
+        if not self.server.is_alive():
+            raise SystemExit
+
         while True:
             # don't let the user ctrl-c while we're waiting for a response
             try:
@@ -111,7 +115,7 @@ class ProcessServer(Process, BaseImplServer):
                     self.quitout.recv()
                     self.quit = True
 
-                self.idle_commands(.1, [self.event_queue._reader, self.command_channel, self.quitout])
+                self.idle_commands(.1, [self.command_channel, self.quitout])
             except Exception:
                 logger.exception('Running command %s', command)
 
@@ -131,6 +135,9 @@ class ProcessServer(Process, BaseImplServer):
                     nextsleep = None
                 elif retval is True:
                     nextsleep = None
+                elif isinstance(retval, float):
+                    if (retval < nextsleep):
+                        nextsleep = retval
                 elif nextsleep is None:
                     continue
                 else:
@@ -139,6 +146,8 @@ class ProcessServer(Process, BaseImplServer):
                 raise
             except Exception:
                 logger.exception('Running idle function')
+                del self._idlefuns[function]
+                self.quit = True
 
         if nextsleep is not None:
             select.select(fds,[],[],nextsleep)
@@ -158,7 +167,7 @@ class BitBakeProcessServerConnection(BitBakeBaseServerConnection):
         self.procserver = serverImpl
         self.ui_channel = ui_channel
         self.event_queue = event_queue
-        self.connection = ServerCommunicator(self.ui_channel, self.procserver.event_handle)
+        self.connection = ServerCommunicator(self.ui_channel, self.procserver.event_handle, self.procserver)
         self.events = self.event_queue
 
     def sigterm_terminate(self):
@@ -197,14 +206,20 @@ class ProcessEventQueue(multiprocessing.queues.Queue):
 
     def waitEvent(self, timeout):
         if self.exit:
-            raise KeyboardInterrupt()
+            sys.exit(1)
         try:
+            if not self.server.is_alive():
+                self.setexit()
+                return None
             return self.get(True, timeout)
         except Empty:
             return None
 
     def getEvent(self):
         try:
+            if not self.server.is_alive():
+                self.setexit()
+                return None
             return self.get(False)
         except Empty:
             return None
@@ -219,6 +234,7 @@ class BitBakeServer(BitBakeBaseServer):
         self.ui_channel, self.server_channel = Pipe()
         self.event_queue = ProcessEventQueue(0)
         self.serverImpl = ProcessServer(self.server_channel, self.event_queue, None)
+        self.event_queue.server = self.serverImpl
 
     def detach(self):
         self.serverImpl.start()

bitbake/lib/bb/server/xmlrpc.py

@@ -80,7 +80,7 @@ class BBTransport(xmlrpclib.Transport):
 
 def _create_server(host, port, timeout = 60):
     t = BBTransport(timeout)
-    s = xmlrpclib.Server("http://%s:%d/" % (host, port), transport=t, allow_none=True)
+    s = xmlrpclib.ServerProxy("http://%s:%d/" % (host, port), transport=t, allow_none=True)
     return s, t
 
 class BitBakeServerCommands():
@@ -235,12 +235,16 @@ class XMLRPCServer(SimpleXMLRPCServer, BaseImplServer):
             fds = [self]
             nextsleep = 0.1
             for function, data in self._idlefuns.items():
+                retval = None
                 try:
                     retval = function(self, data, False)
                     if retval is False:
                         del self._idlefuns[function]
                     elif retval is True:
                         nextsleep = 0
+                    elif isinstance(retval, float):
+                        if (retval < nextsleep):
+                            nextsleep = retval
                     else:
                         fds = fds + retval
                 except SystemExit:
@@ -248,14 +252,21 @@ class XMLRPCServer(SimpleXMLRPCServer, BaseImplServer):
                 except:
                     import traceback
                     traceback.print_exc()
+                    if retval == None:
+                        # the function execute failed; delete it
+                        del self._idlefuns[function]
                     pass
 
             socktimeout = self.socket.gettimeout() or nextsleep
             socktimeout = min(socktimeout, nextsleep)
             # Mirror what BaseServer handle_request would do
-            fd_sets = select.select(fds, [], [], socktimeout)
-            if fd_sets[0] and self in fd_sets[0]:
-                self._handle_request_noblock()
+            try:
+                fd_sets = select.select(fds, [], [], socktimeout)
+                if fd_sets[0] and self in fd_sets[0]:
+                    self._handle_request_noblock()
+            except IOError:
+                # we ignore interrupted calls
+                pass
 
         # Tell idle functions we're exiting
         for function, data in self._idlefuns.items():
@@ -277,13 +288,16 @@ class BitBakeXMLRPCServerConnection(BitBakeBaseServerConnection):
         self.observer_only = observer_only
         self.featureset = featureset
 
-    def connect(self):
-        if not self.observer_only:
-            token = self.connection.addClient()
-        else:
-            token = "observer"
+    def connect(self, token = None):
+        if token is None:
+            if self.observer_only:
+                token = "observer"
+            else:
+                token = self.connection.addClient()
+
         if token is None:
             return None
+
         self.transport.set_connection_token(token)
 
         self.events = uievent.BBUIEventQueue(self.connection, self.clientinfo)
@@ -292,6 +306,8 @@ class BitBakeXMLRPCServerConnection(BitBakeBaseServerConnection):
 
         _, error = self.connection.runCommand(["setFeatures", self.featureset])
         if error:
+            # disconnect the client, we can't make the setFeature work
+            self.connection.removeClient()
             # no need to log it here, the error shall be sent to the client
             raise BaseException(error)
 
@@ -332,7 +348,9 @@ class BitBakeServer(BitBakeBaseServer):
 
 class BitBakeXMLRPCClient(BitBakeBaseServer):
 
-    def __init__(self, observer_only = False):
+    def __init__(self, observer_only = False, token = None):
+        self.token = token
+
         self.observer_only = observer_only
         # if we need extra caches, just tell the server to load them all
         pass
@@ -340,37 +358,14 @@ class BitBakeXMLRPCClient(BitBakeBaseServer):
     def saveConnectionDetails(self, remote):
         self.remote = remote
 
-    def saveConnectionConfigParams(self, configParams):
-        self.configParams = configParams
-
     def establishConnection(self, featureset):
         # The format of "remote" must be "server:port"
         try:
             [host, port] = self.remote.split(":")
             port = int(port)
         except Exception as e:
-            bb.fatal("Failed to read remote definition (%s)" % str(e))
-
-        # use automatic port if port set to -1, meaning read it from
-        # the bitbake.lock file
-        if port == -1:
-            lock_location = "%s/bitbake.lock" % self.configParams.environment.get('BUILDDIR')
-            lock = bb.utils.lockfile(lock_location, False, False)
-            if lock:
-                # This means there is no server running which we can
-                # connect to on the local system.
-                bb.utils.unlockfile(lock)
-                return None
-
-            try:
-                lf = open(lock_location, 'r')
-                remotedef = lf.readline()
-                [host, port] = remotedef.split(":")
-                port = int(port)
-                lf.close()
-                self.remote = remotedef
-            except Exception as e:
-                bb.fatal("Failed to read bitbake.lock (%s)" % str(e))
+            bb.warn("Failed to read remote definition (%s)" % str(e))
+            raise e
 
         # We need our IP for the server connection. We get the IP
         # by trying to connect with the server
@@ -380,13 +375,15 @@ class BitBakeXMLRPCClient(BitBakeBaseServer):
             ip = s.getsockname()[0]
             s.close()
         except Exception as e:
-            bb.fatal("Could not create socket for %s:%s (%s)" % (host, port, str(e)))
+            bb.warn("Could not create socket for %s:%s (%s)" % (host, port, str(e)))
+            raise e
         try:
             self.serverImpl = XMLRPCProxyServer(host, port)
             self.connection = BitBakeXMLRPCServerConnection(self.serverImpl, (ip, 0), self.observer_only, featureset)
-            return self.connection.connect()
+            return self.connection.connect(self.token)
         except Exception as e:
-            bb.fatal("Could not connect to server at %s:%s (%s)" % (host, port, str(e)))
+            bb.warn("Could not connect to server at %s:%s (%s)" % (host, port, str(e)))
+            raise e
 
     def endSession(self):
         self.connection.removeClient()

bitbake/lib/bb/siggen.py

@@ -62,6 +62,13 @@ class SignatureGenerator(object):
     def dump_sigs(self, dataCache, options):
         return
 
+    def get_taskdata(self):
+       return (self.runtaskdeps, self.taskhash, self.file_checksum_values)
+
+    def set_taskdata(self, data):
+        self.runtaskdeps, self.taskhash, self.file_checksum_values = data
+
+
 class SignatureGeneratorBasic(SignatureGenerator):
     """
     """
@@ -185,22 +192,25 @@ class SignatureGeneratorBasic(SignatureGenerator):
             checksums = bb.fetch2.get_file_checksums(dataCache.file_checksums[fn][task], recipename)
             for (f,cs) in checksums:
                 self.file_checksum_values[k][f] = cs
-                data = data + cs
+                if cs:
+                    data = data + cs
+
+        taskdep = dataCache.task_deps[fn]
+        if 'nostamp' in taskdep and task in taskdep['nostamp']:
+            # Nostamp tasks need an implicit taint so that they force any dependent tasks to run
+            import uuid
+            data = data + str(uuid.uuid4())
 
         taint = self.read_taint(fn, task, dataCache.stamp[fn])
         if taint:
             data = data + taint
+            logger.warn("%s is tainted from a forced run" % k)
 
         h = hashlib.md5(data).hexdigest()
         self.taskhash[k] = h
         #d.setVar("BB_TASKHASH_task-%s" % task, taskhash[task])
         return h
 
-    def set_taskdata(self, hashes, deps, checksums):
-        self.runtaskdeps = deps
-        self.taskhash = hashes
-        self.file_checksum_values = checksums
-
     def dump_sigtask(self, fn, task, stampbase, runtime):
         k = fn + "." + task
         if runtime == "customfile":
@@ -293,10 +303,9 @@ def dump_this_task(outfile, d):
     bb.parse.siggen.dump_sigtask(fn, task, outfile, "customfile")
 
 def clean_basepath(a):
+    b = a.rsplit("/", 2)[1] + a.rsplit("/", 2)[2]
     if a.startswith("virtual:"):
-        b = a.rsplit(":", 1)[0] + ":" + a.rsplit("/", 1)[1]
-    else:
-        b = a.rsplit("/", 1)[1]
+        b = b + ":" + a.rsplit(":", 1)[0]
     return b
 
 def clean_basepaths(a):
@@ -305,6 +314,12 @@ def clean_basepaths(a):
         b[clean_basepath(x)] = a[x]
     return b
 
+def clean_basepaths_list(a):
+    b = []
+    for x in a:
+        b.append(clean_basepath(x))
+    return b
+
 def compare_sigfiles(a, b, recursecb = None):
     output = []
 
@@ -404,6 +419,17 @@ def compare_sigfiles(a, b, recursecb = None):
         for f in removed:
             output.append("Dependency on checksum of file %s was removed" % (f))
 
+    changed = []
+    for idx, task in enumerate(a_data['runtaskdeps']):
+        a = a_data['runtaskdeps'][idx]
+        b = b_data['runtaskdeps'][idx]
+        if a_data['runtaskhashes'][a] != b_data['runtaskhashes'][b]:
+            changed.append("%s with hash %s\n changed to\n%s with hash %s" % (a, a_data['runtaskhashes'][a], b, b_data['runtaskhashes'][b]))
+
+    if changed:
+        output.append("runtaskdeps changed from %s to %s" % (clean_basepaths_list(a_data['runtaskdeps']), clean_basepaths_list(b_data['runtaskdeps'])))
+        output.append("\n".join(changed))
+
 
     if 'runtaskhashes' in a_data and 'runtaskhashes' in b_data:
         a = a_data['runtaskhashes']
@@ -480,4 +506,17 @@ def dump_sigfile(a):
     if 'taint' in a_data:
         output.append("Tainted (by forced/invalidated task): %s" % a_data['taint'])
 
+    data = a_data['basehash']
+    for dep in a_data['runtaskdeps']:
+        data = data + a_data['runtaskhashes'][dep]
+
+    for c in a_data['file_checksum_values']:
+        data = data + c[1]
+
+    if 'taint' in a_data:
+        data = data + a_data['taint']
+
+    h = hashlib.md5(data).hexdigest()
+    output.append("Computed Hash is %s" % h)
+
     return output

bitbake/lib/bb/tests/data.py

@@ -121,6 +121,12 @@ class DataExpansions(unittest.TestCase):
         keys = self.d.keys()
         self.assertEqual(keys, ['value_of_foo', 'foo', 'bar'])
 
+    def test_keys_deletion(self):
+        newd = bb.data.createCopy(self.d)
+        newd.delVar("bar")
+        keys = newd.keys()
+        self.assertEqual(keys, ['value_of_foo', 'foo'])
+
 class TestNestedExpansions(unittest.TestCase):
     def setUp(self):
         self.d = bb.data.init()
@@ -253,6 +259,25 @@ class TestConcatOverride(unittest.TestCase):
         bb.data.update_data(self.d)
         self.assertEqual(self.d.getVar("TEST_TEST", True), "bar bar")
 
+    def test_empty_remove(self):
+        self.d.setVar("TEST", "")
+        self.d.setVar("TEST_remove", "val")
+        bb.data.update_data(self.d)
+        self.assertEqual(self.d.getVar("TEST", True), "")
+
+    def test_remove_expansion(self):
+        self.d.setVar("BAR", "Z")
+        self.d.setVar("TEST", "${BAR}/X Y")
+        self.d.setVar("TEST_remove", "${BAR}/X")
+        bb.data.update_data(self.d)
+        self.assertEqual(self.d.getVar("TEST", True), "Y")
+
+    def test_remove_expansion_items(self):
+        self.d.setVar("TEST", "A B C D")
+        self.d.setVar("BAR", "B D")
+        self.d.setVar("TEST_remove", "${BAR}")
+        bb.data.update_data(self.d)
+        self.assertEqual(self.d.getVar("TEST", True), "A C")
 
 class TestOverrides(unittest.TestCase):
     def setUp(self):
@@ -294,3 +319,39 @@ class TestFlags(unittest.TestCase):
         self.assertEqual(self.d.getVarFlag("foo", "flag2"), None)
 
 
+class Contains(unittest.TestCase):
+    def setUp(self):
+        self.d = bb.data.init()
+        self.d.setVar("SOMEFLAG", "a b c")
+
+    def test_contains(self):
+        self.assertTrue(bb.utils.contains("SOMEFLAG", "a", True, False, self.d))
+        self.assertTrue(bb.utils.contains("SOMEFLAG", "b", True, False, self.d))
+        self.assertTrue(bb.utils.contains("SOMEFLAG", "c", True, False, self.d))
+
+        self.assertTrue(bb.utils.contains("SOMEFLAG", "a b", True, False, self.d))
+        self.assertTrue(bb.utils.contains("SOMEFLAG", "b c", True, False, self.d))
+        self.assertTrue(bb.utils.contains("SOMEFLAG", "c a", True, False, self.d))
+
+        self.assertTrue(bb.utils.contains("SOMEFLAG", "a b c", True, False, self.d))
+        self.assertTrue(bb.utils.contains("SOMEFLAG", "c b a", True, False, self.d))
+
+        self.assertFalse(bb.utils.contains("SOMEFLAG", "x", True, False, self.d))
+        self.assertFalse(bb.utils.contains("SOMEFLAG", "a x", True, False, self.d))
+        self.assertFalse(bb.utils.contains("SOMEFLAG", "x c b", True, False, self.d))
+        self.assertFalse(bb.utils.contains("SOMEFLAG", "x c b a", True, False, self.d))
+
+    def test_contains_any(self):
+        self.assertTrue(bb.utils.contains_any("SOMEFLAG", "a", True, False, self.d))
+        self.assertTrue(bb.utils.contains_any("SOMEFLAG", "b", True, False, self.d))
+        self.assertTrue(bb.utils.contains_any("SOMEFLAG", "c", True, False, self.d))
+
+        self.assertTrue(bb.utils.contains_any("SOMEFLAG", "a b", True, False, self.d))
+        self.assertTrue(bb.utils.contains_any("SOMEFLAG", "b c", True, False, self.d))
+        self.assertTrue(bb.utils.contains_any("SOMEFLAG", "c a", True, False, self.d))
+
+        self.assertTrue(bb.utils.contains_any("SOMEFLAG", "a x", True, False, self.d))
+        self.assertTrue(bb.utils.contains_any("SOMEFLAG", "x c", True, False, self.d))
+
+        self.assertFalse(bb.utils.contains_any("SOMEFLAG", "x", True, False, self.d))
+        self.assertFalse(bb.utils.contains_any("SOMEFLAG", "x y z", True, False, self.d))

bitbake/lib/bb/tests/fetch.py

@@ -24,6 +24,7 @@ import tempfile
 import subprocess
 import os
 from bb.fetch2 import URI
+from bb.fetch2 import FetchMethod
 import bb
 
 class URITest(unittest.TestCase):
@@ -444,6 +445,13 @@ class FetcherLocalTest(FetcherTest):
         tree = self.fetchUnpack(['file://dir/subdir/e'])
         self.assertEqual(tree, ['dir/subdir/e'])
 
+    def test_local_subdirparam(self):
+        tree = self.fetchUnpack(['file://a;subdir=bar'])
+        self.assertEqual(tree, ['bar/a'])
+
+    def test_local_deepsubdirparam(self):
+        tree = self.fetchUnpack(['file://dir/subdir/e;subdir=bar'])
+        self.assertEqual(tree, ['bar/dir/subdir/e'])
 
 class FetcherNetworkTest(FetcherTest):
 
@@ -558,5 +566,83 @@ class URLHandle(unittest.TestCase):
             result = bb.fetch.encodeurl(v)
             self.assertEqual(result, k)
 
+class FetchMethodTest(FetcherTest):
 
+    test_git_uris = {
+        # version pattern "X.Y.Z"
+        ("mx-1.0", "git://github.com/clutter-project/mx.git;branch=mx-1.4", "9b1db6b8060bd00b121a692f942404a24ae2960f", "")
+            : "1.99.4",
+        # version pattern "vX.Y"
+        ("mtd-utils", "git://git.infradead.org/mtd-utils.git", "ca39eb1d98e736109c64ff9c1aa2a6ecca222d8f", "")
+            : "1.5.0",
+        # version pattern "pkg_name-X.Y"
+        ("presentproto", "git://anongit.freedesktop.org/git/xorg/proto/presentproto", "24f3a56e541b0a9e6c6ee76081f441221a120ef9", "")
+            : "1.0",
+        # version pattern "pkg_name-vX.Y.Z"
+        ("dtc", "git://git.qemu.org/dtc.git", "65cc4d2748a2c2e6f27f1cf39e07a5dbabd80ebf", "")
+            : "1.4.0",
+        # combination version pattern
+        ("sysprof", "git://git.gnome.org/sysprof", "cd44ee6644c3641507fb53b8a2a69137f2971219", "")
+            : "1.2.0",
+        ("u-boot-mkimage", "git://git.denx.de/u-boot.git;branch=master;protocol=git", "62c175fbb8a0f9a926c88294ea9f7e88eb898f6c", "")
+            : "2014.01",
+        # version pattern "yyyymmdd"
+        ("mobile-broadband-provider-info", "git://git.gnome.org/mobile-broadband-provider-info", "4ed19e11c2975105b71b956440acdb25d46a347d", "")
+            : "20120614",
+        # packages with a valid GITTAGREGEX
+        ("xf86-video-omap", "git://anongit.freedesktop.org/xorg/driver/xf86-video-omap", "ae0394e687f1a77e966cf72f895da91840dffb8f", "(?P<pver>(\d+\.(\d\.?)*))")
+            : "0.4.3",
+        ("build-appliance-image", "git://git.yoctoproject.org/poky", "b37dd451a52622d5b570183a81583cc34c2ff555", "(?P<pver>(([0-9][\.|_]?)+[0-9]))")
+            : "11.0.0",
+        ("chkconfig-alternatives-native", "git://github.com/kergoth/chkconfig;branch=sysroot", "cd437ecbd8986c894442f8fce1e0061e20f04dee", "chkconfig\-(?P<pver>((\d+[\.\-_]*)+))")
+            : "1.3.59",
+        ("remake", "git://github.com/rocky/remake.git", "f05508e521987c8494c92d9c2871aec46307d51d", "(?P<pver>(\d+\.(\d+\.)*\d*(\+dbg\d+(\.\d+)*)*))")
+            : "3.82+dbg0.9",
+    }
 
+    test_wget_uris = {
+        # packages with versions inside directory name
+        ("util-linux", "http://kernel.org/pub/linux/utils/util-linux/v2.23/util-linux-2.24.2.tar.bz2", "", "")
+            : "2.24.2",
+        ("enchant", "http://www.abisource.com/downloads/enchant/1.6.0/enchant-1.6.0.tar.gz", "", "")
+            : "1.6.0",
+        ("cmake", "http://www.cmake.org/files/v2.8/cmake-2.8.12.1.tar.gz", "", "")
+            : "2.8.12.1",
+        # packages with versions only in current directory
+        ("eglic", "http://downloads.yoctoproject.org/releases/eglibc/eglibc-2.18-svnr23787.tar.bz2", "", "")
+            : "2.19",
+        ("gnu-config", "http://downloads.yoctoproject.org/releases/gnu-config/gnu-config-20120814.tar.bz2", "", "")
+            : "20120814",
+        # packages with "99" in the name of possible version
+        ("pulseaudio", "http://freedesktop.org/software/pulseaudio/releases/pulseaudio-4.0.tar.xz", "", "")
+            : "5.0",
+        ("xserver-xorg", "http://xorg.freedesktop.org/releases/individual/xserver/xorg-server-1.15.1.tar.bz2", "", "")
+            : "1.15.1",
+        # packages with valid REGEX_URI and REGEX
+        ("cups", "http://www.cups.org/software/1.7.2/cups-1.7.2-source.tar.bz2", "http://www.cups.org/software.php", "(?P<name>cups\-)(?P<pver>((\d+[\.\-_]*)+))\-source\.tar\.gz")
+            : "2.0.0",
+        ("db", "http://download.oracle.com/berkeley-db/db-5.3.21.tar.gz", "http://www.oracle.com/technetwork/products/berkeleydb/downloads/index-082944.html", "http://download.oracle.com/otn/berkeley-db/(?P<name>db-)(?P<pver>((\d+[\.\-_]*)+))\.tar\.gz")
+            : "6.1.19",
+    }
+    if os.environ.get("BB_SKIP_NETTESTS") == "yes":
+        print("Unset BB_SKIP_NETTESTS to run network tests")
+    else:
+        def test_git_latest_versionstring(self):
+            for k, v in self.test_git_uris.items():
+                self.d.setVar("PN", k[0])
+                self.d.setVar("SRCREV", k[2])
+                self.d.setVar("GITTAGREGEX", k[3])
+                ud = bb.fetch2.FetchData(k[1], self.d)
+                verstring = ud.method.latest_versionstring(ud, self.d)
+                r = bb.utils.vercmp_string(v, verstring)
+                self.assertTrue(r == -1 or r == 0, msg="Package %s, version: %s <= %s" % (k[0], v, verstring))
+
+        def test_wget_latest_versionstring(self):
+            for k, v in self.test_wget_uris.items():
+                self.d.setVar("PN", k[0])
+                self.d.setVar("REGEX_URI", k[2])
+                self.d.setVar("REGEX", k[3])
+                ud = bb.fetch2.FetchData(k[1], self.d)
+                verstring = ud.method.latest_versionstring(ud, self.d)
+                r = bb.utils.vercmp_string(v, verstring)
+                self.assertTrue(r == -1 or r == 0, msg="Package %s, version: %s <= %s" % (k[0], v, verstring))

bitbake/lib/bb/tests/utils.py

@@ -21,6 +21,7 @@
 
 import unittest
 import bb
+import os
 
 class VerCmpString(unittest.TestCase):
 
@@ -35,6 +36,10 @@ class VerCmpString(unittest.TestCase):
         self.assertTrue(result < 0)
         result = bb.utils.vercmp_string('1.1', '1_p2')
         self.assertTrue(result < 0)
+        result = bb.utils.vercmp_string('1.0', '1.0+1.1-beta1')
+        self.assertTrue(result < 0)
+        result = bb.utils.vercmp_string('1.1', '1.0+1.1-beta1')
+        self.assertTrue(result > 0)
 
     def test_explode_dep_versions(self):
         correctresult = {"foo" : ["= 1.10"]}
@@ -51,3 +56,52 @@ class VerCmpString(unittest.TestCase):
         result = bb.utils.explode_dep_versions2("foo ( =1.10 )")
         self.assertEqual(result, correctresult)
 
+    def test_vercmp_string_op(self):
+        compareops = [('1', '1', '=', True),
+                      ('1', '1', '==', True),
+                      ('1', '1', '!=', False),
+                      ('1', '1', '>', False),
+                      ('1', '1', '<', False),
+                      ('1', '1', '>=', True),
+                      ('1', '1', '<=', True),
+                      ('1', '0', '=', False),
+                      ('1', '0', '==', False),
+                      ('1', '0', '!=', True),
+                      ('1', '0', '>', True),
+                      ('1', '0', '<', False),
+                      ('1', '0', '>>', True),
+                      ('1', '0', '<<', False),
+                      ('1', '0', '>=', True),
+                      ('1', '0', '<=', False),
+                      ('0', '1', '=', False),
+                      ('0', '1', '==', False),
+                      ('0', '1', '!=', True),
+                      ('0', '1', '>', False),
+                      ('0', '1', '<', True),
+                      ('0', '1', '>>', False),
+                      ('0', '1', '<<', True),
+                      ('0', '1', '>=', False),
+                      ('0', '1', '<=', True)]
+
+        for arg1, arg2, op, correctresult in compareops:
+            result = bb.utils.vercmp_string_op(arg1, arg2, op)
+            self.assertEqual(result, correctresult, 'vercmp_string_op("%s", "%s", "%s") != %s' % (arg1, arg2, op, correctresult))
+
+        # Check that clearly invalid operator raises an exception
+        self.assertRaises(bb.utils.VersionStringException, bb.utils.vercmp_string_op, '0', '0', '$')
+
+
+class Path(unittest.TestCase):
+    def test_unsafe_delete_path(self):
+        checkitems = [('/', True),
+                      ('//', True),
+                      ('///', True),
+                      (os.getcwd().count(os.sep) * ('..' + os.sep), True),
+                      (os.environ.get('HOME', '/home/test'), True),
+                      ('/home/someone', True),
+                      ('/home/other/', True),
+                      ('/home/other/subdir', False),
+                      ('', False)]
+        for arg1, correctresult in checkitems:
+            result = bb.utils._check_unsafe_delete_path(arg1)
+            self.assertEqual(result, correctresult, '_check_unsafe_delete_path("%s") != %s' % (arg1, correctresult))

bitbake/lib/bb/tinfoil.py

@@ -25,12 +25,12 @@ import bb.cache
 import bb.cooker
 import bb.providers
 import bb.utils
-from bb.cooker import state, BBCooker
+from bb.cooker import state, BBCooker, CookerFeatures
 from bb.cookerdata import CookerConfiguration, ConfigParameters
 import bb.fetch2
 
 class Tinfoil:
-    def __init__(self, output=sys.stdout):
+    def __init__(self, output=sys.stdout, tracking=False):
         # Needed to avoid deprecation warnings with python 2.6
         warnings.filterwarnings("ignore", category=DeprecationWarning)
 
@@ -48,7 +48,10 @@ class Tinfoil:
         configparams = TinfoilConfigParameters(parse_only=True)
         self.config.setConfigParameters(configparams)
         self.config.setServerRegIdleCallback(self.register_idle_function)
-        self.cooker = BBCooker(self.config)
+        features = []
+        if tracking:
+            features.append(CookerFeatures.BASEDATASTORE_TRACKING)
+        self.cooker = BBCooker(self.config, features)
         self.config_data = self.cooker.data
         bb.providers.logger.setLevel(logging.ERROR)
         self.cooker_data = None
@@ -81,13 +84,18 @@ class Tinfoil:
             else:
                 self.parseRecipes()
 
+    def shutdown(self):
+        self.cooker.shutdown(force=True)
+        self.cooker.post_serve()
+        self.cooker.unlockBitbake()
+
 class TinfoilConfigParameters(ConfigParameters):
 
     def __init__(self, **options):
         self.initial_options = options
         super(TinfoilConfigParameters, self).__init__()
 
-    def parseCommandLine(self):
+    def parseCommandLine(self, argv=sys.argv):
         class DummyOptions:
             def __init__(self, initial_options):
                 for key, val in initial_options.items():

bitbake/lib/bb/ui/buildinfohelper.py

@@ -22,16 +22,24 @@ import bb
 import re
 import ast
 
-os.environ.setdefault("DJANGO_SETTINGS_MODULE", "toaster.toastermain.settings")
+os.environ["DJANGO_SETTINGS_MODULE"] = "toaster.toastermain.settings"
 
 import toaster.toastermain.settings as toaster_django_settings
 from toaster.orm.models import Build, Task, Recipe, Layer_Version, Layer, Target, LogMessage, HelpText
-from toaster.orm.models import Target_Image_File
+from toaster.orm.models import Target_Image_File, BuildArtifact
 from toaster.orm.models import Variable, VariableHistory
 from toaster.orm.models import Package, Package_File, Target_Installed_Package, Target_File
 from toaster.orm.models import Task_Dependency, Package_Dependency
 from toaster.orm.models import Recipe_Dependency
 from bb.msg import BBLogFormatter as format
+from django.db import models
+from pprint import pformat
+import logging
+
+from django.db import transaction, connection
+
+logger = logging.getLogger("BitBake")
+
 
 class NotExisting(Exception):
     pass
@@ -43,10 +51,59 @@ class ORMWrapper(object):
     """
 
     def __init__(self):
+        self.layer_version_objects = []
+        self.task_objects = {}
+        self.recipe_objects = {}
         pass
 
+    @staticmethod
+    def _build_key(**kwargs):
+        key = "0"
+        for k in sorted(kwargs.keys()):
+            if isinstance(kwargs[k], models.Model):
+                key += "-%d" % kwargs[k].id
+            else:
+                key += "-%s" % str(kwargs[k])
+        return key
 
-    def create_build_object(self, build_info):
+
+    def _cached_get_or_create(self, clazz, **kwargs):
+        """ This is a memory-cached get_or_create. We assume that the objects will not be created in the
+            database through any other means.
+        """
+
+        assert issubclass(clazz, models.Model), "_cached_get_or_create needs to get the class as first argument"
+
+        key = ORMWrapper._build_key(**kwargs)
+        dictname = "objects_%s" % clazz.__name__
+        if not dictname in vars(self).keys():
+            vars(self)[dictname] = {}
+
+        created = False
+        if not key in vars(self)[dictname].keys():
+            vars(self)[dictname][key] = clazz.objects.create(**kwargs)
+            created = True
+
+        return (vars(self)[dictname][key], created)
+
+
+    def _cached_get(self, clazz, **kwargs):
+        """ This is a memory-cached get. We assume that the objects will not change  in the database between gets.
+        """
+        assert issubclass(clazz, models.Model), "_cached_get needs to get the class as first argument"
+
+        key = ORMWrapper._build_key(**kwargs)
+        dictname = "objects_%s" % clazz.__name__
+
+        if not dictname in vars(self).keys():
+            vars(self)[dictname] = {}
+
+        if not key in vars(self)[dictname].keys():
+            vars(self)[dictname][key] = clazz.objects.get(**kwargs)
+
+        return vars(self)[dictname][key]
+
+    def create_build_object(self, build_info, brbe):
         assert 'machine' in build_info
         assert 'distro' in build_info
         assert 'distro_version' in build_info
@@ -65,6 +122,18 @@ class ORMWrapper(object):
                                     build_name=build_info['build_name'],
                                     bitbake_version=build_info['bitbake_version'])
 
+        logger.debug(1, "buildinfohelper: build is created %s" % build)
+        if brbe is not None:
+            logger.debug(1, "buildinfohelper: brbe is %s" % brbe)
+            from bldcontrol.models import BuildEnvironment, BuildRequest
+            br, be = brbe.split(":")
+
+            buildrequest = BuildRequest.objects.get(pk = br)
+            buildrequest.build = build
+            buildrequest.save()
+
+            build.project_id = buildrequest.project_id
+            build.save()
         return build
 
     def create_target_objects(self, target_info):
@@ -76,7 +145,7 @@ class ORMWrapper(object):
             tgt_object = Target.objects.create( build = target_info['build'],
                                     target = tgt_name,
                                     is_image = False,
-                                    );
+                                    )
             targets.append(tgt_object)
         return targets
 
@@ -96,8 +165,7 @@ class ORMWrapper(object):
         build.outcome = outcome
         build.save()
 
-    def update_target_object(self, target, license_manifest_path):
-
+    def update_target_set_license_manifest(self, target, license_manifest_path):
         target.license_manifest_path = license_manifest_path
         target.save()
 
@@ -106,39 +174,47 @@ class ORMWrapper(object):
         assert 'recipe' in task_information
         assert 'task_name' in task_information
 
-        task_object, created = Task.objects.get_or_create(
-                                build=task_information['build'],
-                                recipe=task_information['recipe'],
-                                task_name=task_information['task_name'],
-                                )
-
-        if must_exist and created:
-            task_information['debug'] = "build id %d, recipe id %d" % (task_information['build'].pk, task_information['recipe'].pk)
-            task_object.delete()
-            raise NotExisting("Task object created when expected to exist", task_information)
+        # we use must_exist info for database look-up optimization
+        task_object, created = self._cached_get_or_create(Task,
+                        build=task_information['build'],
+                        recipe=task_information['recipe'],
+                        task_name=task_information['task_name']
+                        )
+        if created and must_exist:
+                task_information['debug'] = "build id %d, recipe id %d" % (task_information['build'].pk, task_information['recipe'].pk)
+                raise NotExisting("Task object created when expected to exist", task_information)
 
+        object_changed = False
         for v in vars(task_object):
             if v in task_information.keys():
-                vars(task_object)[v] = task_information[v]
+                if vars(task_object)[v] != task_information[v]:
+                    vars(task_object)[v] = task_information[v]
+                    object_changed = True
 
-        # update setscene-related information
-        if 1 == Task.objects.related_setscene(task_object).count():
-            if task_object.outcome == Task.OUTCOME_COVERED:
-                task_object.outcome = Task.OUTCOME_CACHED
+        # update setscene-related information if the task has a setscene
+        if task_object.outcome == Task.OUTCOME_COVERED and 1 == task_object.get_related_setscene().count():
+            task_object.outcome = Task.OUTCOME_CACHED
+            object_changed = True
 
             outcome_task_setscene = Task.objects.get(task_executed=True, build = task_object.build,
                                     recipe = task_object.recipe, task_name=task_object.task_name+"_setscene").outcome
             if outcome_task_setscene == Task.OUTCOME_SUCCESS:
                 task_object.sstate_result = Task.SSTATE_RESTORED
+                object_changed = True
             elif outcome_task_setscene == Task.OUTCOME_FAILED:
                 task_object.sstate_result = Task.SSTATE_FAILED
+                object_changed = True
 
         # mark down duration if we have a start time and a current time
         if 'start_time' in task_information.keys() and 'end_time' in task_information.keys():
             duration = task_information['end_time'] - task_information['start_time']
             task_object.elapsed_time = duration
+            object_changed = True
+            del task_information['start_time']
+            del task_information['end_time']
 
-        task_object.save()
+        if object_changed:
+            task_object.save()
         return task_object
 
 
@@ -146,20 +222,22 @@ class ORMWrapper(object):
         assert 'layer_version' in recipe_information
         assert 'file_path' in recipe_information
 
+        if recipe_information['file_path'].startswith(recipe_information['layer_version'].layer.local_path):
+            recipe_information['file_path'] = recipe_information['file_path'][len(recipe_information['layer_version'].layer.local_path):].lstrip("/")
 
-        recipe_object, created = Recipe.objects.get_or_create(
-                                         layer_version=recipe_information['layer_version'],
-                                         file_path=recipe_information['file_path'])
-
-        if must_exist and created:
-            recipe_object.delete()
+        recipe_object, created = self._cached_get_or_create(Recipe, layer_version=recipe_information['layer_version'],
+                                     file_path=recipe_information['file_path'])
+        if created and must_exist:
             raise NotExisting("Recipe object created when expected to exist", recipe_information)
 
+        object_changed = False
         for v in vars(recipe_object):
             if v in recipe_information.keys():
+                object_changed = True
                 vars(recipe_object)[v] = recipe_information[v]
 
-        recipe_object.save()
+        if object_changed:
+            recipe_object.save()
 
         return recipe_object
 
@@ -178,19 +256,53 @@ class ORMWrapper(object):
                                     priority = layer_version_information['priority']
                                     )
 
+        self.layer_version_objects.append(layer_version_object)
+
         return layer_version_object
 
-    def get_update_layer_object(self, layer_information):
+    def get_update_layer_object(self, layer_information, brbe):
         assert 'name' in layer_information
         assert 'local_path' in layer_information
         assert 'layer_index_url' in layer_information
 
-        layer_object, created = Layer.objects.get_or_create(
+        if brbe is None:
+            layer_object, created = Layer.objects.get_or_create(
                                 name=layer_information['name'],
                                 local_path=layer_information['local_path'],
                                 layer_index_url=layer_information['layer_index_url'])
+            return layer_object
+        else:
+            # we are under managed mode; we must match the layer used in the Project Layer
+            from bldcontrol.models import BuildEnvironment, BuildRequest
+            br_id, be_id = brbe.split(":")
+
+            # find layer by checkout path;
+            from bldcontrol import bbcontroller
+            bc = bbcontroller.getBuildEnvironmentController(pk = be_id)
+
+            # we might have a race condition here, as the project layers may change between the build trigger and the actual build execution
+            # but we can only match on the layer name, so the worst thing can happen is a mis-identification of the layer, not a total failure
+
+            # note that this is different
+            buildrequest = BuildRequest.objects.get(pk = br_id)
+            for brl in buildrequest.brlayer_set.all():
+                localdirname = os.path.join(bc.getGitCloneDirectory(brl.giturl, brl.commit), brl.dirpath)
+                # we get a relative path, unless running in HEAD mode where the path is absolute
+                if not localdirname.startswith("/"):
+                    localdirname = os.path.join(bc.be.sourcedir, localdirname)
+                #logger.debug(1, "Localdirname %s lcal_path %s" % (localdirname, layer_information['local_path']))
+                if localdirname.startswith(layer_information['local_path']):
+                    # we matched the BRLayer, but we need the layer_version that generated this BR; reverse of the Project.schedule_build()
+                    #logger.debug(1, "Matched %s to BRlayer %s" % (pformat(layer_information["local_path"]), localdirname))
+                    for pl in buildrequest.project.projectlayer_set.filter(layercommit__layer__name = brl.name):
+                        if pl.layercommit.layer.vcs_url == brl.giturl :
+                            layer = pl.layercommit.layer
+                            layer.local_path = layer_information['local_path']
+                            layer.save()
+                            return layer
+
+            raise NotExisting("Unidentified layer %s" % pformat(layer_information))
 
-        return layer_object
 
     def save_target_file_information(self, build_obj, target_obj, filedata):
         assert isinstance(build_obj, Build)
@@ -222,7 +334,7 @@ class ORMWrapper(object):
             parent_path = "/".join(path.split("/")[:len(path.split("/")) - 1])
             if len(parent_path) == 0:
                 parent_path = "/"
-            parent_obj = Target_File.objects.get(target = target_obj, path = parent_path, inodetype = Target_File.ITYPE_DIRECTORY)
+            parent_obj = self._cached_get(Target_File, target = target_obj, path = parent_path, inodetype = Target_File.ITYPE_DIRECTORY)
             tf_obj = Target_File.objects.create(
                         target = target_obj,
                         path = path,
@@ -256,7 +368,7 @@ class ORMWrapper(object):
                         permission = permission,
                         owner = user,
                         group = group)
-            parent_obj = Target_File.objects.get(target = target_obj, path = parent_path, inodetype = Target_File.ITYPE_DIRECTORY)
+            parent_obj = self._cached_get(Target_File, target = target_obj, path = parent_path, inodetype = Target_File.ITYPE_DIRECTORY)
             tf_obj.directory = parent_obj
             tf_obj.save()
 
@@ -311,8 +423,7 @@ class ORMWrapper(object):
                 searchname = pkgpnmap[p]['OPKGN']
 
             packagedict[p]['object'], created = Package.objects.get_or_create( build = build_obj, name = searchname )
-            if created:
-                # package was not build in the current build, but
+            if created or packagedict[p]['object'].size == -1:    # save the data anyway we can, not just if it was not created here; bug [YOCTO #6887]
                 # fill in everything we can from the runtime-reverse package data
                 try:
                     packagedict[p]['object'].recipe = recipes[pkgpnmap[p]['PN']]
@@ -326,11 +437,14 @@ class ORMWrapper(object):
                     packagedict[p]['object'].size = int(pkgpnmap[p]['PKGSIZE'])
 
                 # no files recorded for this package, so save files info
+                    packagefile_objects = []
                     for targetpath in pkgpnmap[p]['FILES_INFO']:
                         targetfilesize = pkgpnmap[p]['FILES_INFO'][targetpath]
-                        Package_File.objects.create( package = packagedict[p]['object'],
+                        packagefile_objects.append(Package_File( package = packagedict[p]['object'],
                             path = targetpath,
-                            size = targetfilesize)
+                            size = targetfilesize))
+                    if len(packagefile_objects):
+                        Package_File.objects.bulk_create(packagefile_objects)
                 except KeyError as e:
                     errormsg += "  stpi: Key error, package %s key %s \n" % ( p, e )
 
@@ -340,6 +454,7 @@ class ORMWrapper(object):
 
             Target_Installed_Package.objects.create(target = target_obj, package = packagedict[p]['object'])
 
+        packagedeps_objs = []
         for p in packagedict:
             for (px,deptype) in packagedict[p]['depends']:
                 if deptype == 'depends':
@@ -347,19 +462,32 @@ class ORMWrapper(object):
                 elif deptype == 'recommends':
                     tdeptype = Package_Dependency.TYPE_TRECOMMENDS
 
-                Package_Dependency.objects.create( package = packagedict[p]['object'],
+                packagedeps_objs.append(Package_Dependency( package = packagedict[p]['object'],
                                         depends_on = packagedict[px]['object'],
                                         dep_type = tdeptype,
-                                        target = target_obj);
+                                        target = target_obj))
+
+        if len(packagedeps_objs) > 0:
+            Package_Dependency.objects.bulk_create(packagedeps_objs)
 
         if (len(errormsg) > 0):
-            raise Exception(errormsg)
+            logger.warn("buildinfohelper: target_package_info could not identify recipes: \n%s" % errormsg)
 
     def save_target_image_file_information(self, target_obj, file_name, file_size):
         target_image_file = Target_Image_File.objects.create( target = target_obj,
                             file_name = file_name,
                             file_size = file_size)
-        target_image_file.save()
+
+    def save_artifact_information(self, build_obj, file_name, file_size):
+        # we skip the image files from other builds
+        if Target_Image_File.objects.filter(file_name = file_name).count() > 0:
+            return
+
+        # do not update artifacts found in other builds
+        if BuildArtifact.objects.filter(file_name = file_name).count() > 0:
+            return
+
+        BuildArtifact.objects.create(build = build_obj, file_name = file_name, file_size = file_size)
 
     def create_logmessage(self, log_information):
         assert 'build' in log_information
@@ -401,10 +529,13 @@ class ORMWrapper(object):
         bp_object.save()
 
         # save any attached file information
+        packagefile_objects = []
         for path in package_info['FILES_INFO']:
-                fo = Package_File.objects.create( package = bp_object,
+                packagefile_objects.append(Package_File( package = bp_object,
                                         path = path,
-                                        size = package_info['FILES_INFO'][path] )
+                                        size = package_info['FILES_INFO'][path] ))
+        if len(packagefile_objects):
+            Package_File.objects.bulk_create(packagefile_objects)
 
         def _po_byname(p):
             pkg, created = Package.objects.get_or_create(build = build_obj, name = p)
@@ -413,39 +544,44 @@ class ORMWrapper(object):
                 pkg.save()
             return pkg
 
+        packagedeps_objs = []
         # save soft dependency information
         if 'RDEPENDS' in package_info and package_info['RDEPENDS']:
             for p in bb.utils.explode_deps(package_info['RDEPENDS']):
-                Package_Dependency.objects.get_or_create( package = bp_object,
-                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RDEPENDS)
+                packagedeps_objs.append(Package_Dependency(  package = bp_object,
+                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RDEPENDS))
         if 'RPROVIDES' in package_info and package_info['RPROVIDES']:
             for p in bb.utils.explode_deps(package_info['RPROVIDES']):
-                Package_Dependency.objects.get_or_create( package = bp_object,
-                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RPROVIDES)
+                packagedeps_objs.append(Package_Dependency(  package = bp_object,
+                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RPROVIDES))
         if 'RRECOMMENDS' in package_info and package_info['RRECOMMENDS']:
             for p in bb.utils.explode_deps(package_info['RRECOMMENDS']):
-                Package_Dependency.objects.get_or_create( package = bp_object,
-                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RRECOMMENDS)
+                packagedeps_objs.append(Package_Dependency(  package = bp_object,
+                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RRECOMMENDS))
         if 'RSUGGESTS' in package_info and package_info['RSUGGESTS']:
             for p in bb.utils.explode_deps(package_info['RSUGGESTS']):
-                Package_Dependency.objects.get_or_create( package = bp_object,
-                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RSUGGESTS)
+                packagedeps_objs.append(Package_Dependency(  package = bp_object,
+                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RSUGGESTS))
         if 'RREPLACES' in package_info and package_info['RREPLACES']:
             for p in bb.utils.explode_deps(package_info['RREPLACES']):
-                Package_Dependency.objects.get_or_create( package = bp_object,
-                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RREPLACES)
+                packagedeps_objs.append(Package_Dependency(  package = bp_object,
+                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RREPLACES))
         if 'RCONFLICTS' in package_info and package_info['RCONFLICTS']:
             for p in bb.utils.explode_deps(package_info['RCONFLICTS']):
-                Package_Dependency.objects.get_or_create( package = bp_object,
-                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RCONFLICTS)
+                packagedeps_objs.append(Package_Dependency(  package = bp_object,
+                    depends_on = _po_byname(p), dep_type = Package_Dependency.TYPE_RCONFLICTS))
+
+        if len(packagedeps_objs) > 0:
+            Package_Dependency.objects.bulk_create(packagedeps_objs)
 
         return bp_object
 
     def save_build_variables(self, build_obj, vardump):
         assert isinstance(build_obj, Build)
 
+        helptext_objects = []
         for k in vardump:
-            desc = vardump[k]['doc'];
+            desc = vardump[k]['doc']
             if desc is None:
                 var_words = [word for word in k.split('_')]
                 root_var = "_".join([word for word in var_words if word.isupper()])
@@ -453,25 +589,33 @@ class ORMWrapper(object):
                     desc = vardump[root_var]['doc']
             if desc is None:
                 desc = ''
-            if desc:
-                helptext_obj = HelpText.objects.create(build=build_obj,
+            if len(desc):
+                helptext_objects.append(HelpText(build=build_obj,
                     area=HelpText.VARIABLE,
                     key=k,
-                    text=desc)
+                    text=desc))
             if not bool(vardump[k]['func']):
-                value = vardump[k]['v'];
+                value = vardump[k]['v']
                 if value is None:
                     value = ''
                 variable_obj = Variable.objects.create( build = build_obj,
                     variable_name = k,
                     variable_value = value,
                     description = desc)
+
+                varhist_objects = []
                 for vh in vardump[k]['history']:
                     if not 'documentation.conf' in vh['file']:
-                        VariableHistory.objects.create( variable = variable_obj,
+                        varhist_objects.append(VariableHistory( variable = variable_obj,
                                 file_name = vh['file'],
                                 line_number = vh['line'],
-                                operation = vh['op'])
+                                operation = vh['op']))
+                if len(varhist_objects):
+                    VariableHistory.objects.bulk_create(varhist_objects)
+
+        HelpText.objects.bulk_create(helptext_objects)
+
+class MockEvent: pass           # sometimes we mock an event, declare it here
 
 class BuildInfoHelper(object):
     """ This class gathers the build information from the server and sends it
@@ -480,15 +624,23 @@ class BuildInfoHelper(object):
         Keeps in memory all data that needs matching before writing it to the database
     """
 
+
     def __init__(self, server, has_build_history = False):
         self._configure_django()
         self.internal_state = {}
         self.internal_state['taskdata'] = {}
         self.task_order = 0
+        self.autocommit_step = 1
         self.server = server
+        # we use manual transactions if the database doesn't autocommit on us
+        if not connection.features.autocommits_when_autocommit_is_off:
+            transaction.set_autocommit(False)
         self.orm_wrapper = ORMWrapper()
         self.has_build_history = has_build_history
         self.tmp_dir = self.server.runCommand(["getVariable", "TMPDIR"])[0]
+        self.brbe    = self.server.runCommand(["getVariable", "TOASTER_BRBE"])[0]
+        logger.debug(1, "buildinfohelper: Build info helper inited %s" % vars(self))
+
 
     def _configure_django(self):
         # Add toaster to sys path for importing modules
@@ -532,19 +684,47 @@ class BuildInfoHelper(object):
         assert path.startswith("/")
         assert 'build' in self.internal_state
 
-        def _slkey(layer_version):
-            assert isinstance(layer_version, Layer_Version)
-            return len(layer_version.layer.local_path)
+        if self.brbe is None:
+            def _slkey_interactive(layer_version):
+                assert isinstance(layer_version, Layer_Version)
+                return len(layer_version.layer.local_path)
 
-        # Heuristics: we always match recipe to the deepest layer path that
-        # we can match to the recipe file path
-        for bl in sorted(Layer_Version.objects.filter(build = self.internal_state['build']), reverse=True, key=_slkey):
-            if (path.startswith(bl.layer.local_path)):
-                return bl
+            # Heuristics: we always match recipe to the deepest layer path in the discovered layers
+            for lvo in sorted(self.orm_wrapper.layer_version_objects, reverse=True, key=_slkey_interactive):
+                # we can match to the recipe file path
+                if path.startswith(lvo.layer.local_path):
+                    return lvo
 
-        #TODO: if we get here, we didn't read layers correctly
-        assert False
-        return None
+        else:
+            br_id, be_id = self.brbe.split(":")
+            from bldcontrol.bbcontroller import getBuildEnvironmentController
+            from bldcontrol.models import BuildRequest
+            bc = getBuildEnvironmentController(pk = be_id)
+
+            def _slkey_managed(layer_version):
+                return len(bc.getGitCloneDirectory(layer_version.giturl, layer_version.commit) + layer_version.dirpath)
+
+            # Heuristics: we match the path to where the layers have been checked out
+            for brl in sorted(BuildRequest.objects.get(pk = br_id).brlayer_set.all(), reverse = True, key = _slkey_managed):
+                localdirname = os.path.join(bc.getGitCloneDirectory(brl.giturl, brl.commit), brl.dirpath)
+                # we get a relative path, unless running in HEAD mode where the path is absolute
+                if not localdirname.startswith("/"):
+                    localdirname = os.path.join(bc.be.sourcedir, localdirname)
+                if path.startswith(localdirname):
+                    #logger.warn("-- managed: matched path %s with layer %s " % (path, localdirname))
+                    # we matched the BRLayer, but we need the layer_version that generated this br
+                    for lvo in self.orm_wrapper.layer_version_objects:
+                        if brl.name == lvo.layer.name:
+                            return lvo
+
+        #if we get here, we didn't read layers correctly; dump whatever information we have on the error log
+        logger.error("Could not match layer version for recipe path %s : %s" % (path, self.orm_wrapper.layer_version_objects))
+
+        #mockup the new layer
+        unknown_layer, created = Layer.objects.get_or_create(name="__FIXME__unidentified_layer", local_path="/", layer_index_url="")
+        unknown_layer_version_obj, created = Layer_Version.objects.get_or_create(layer = unknown_layer, build = self.internal_state['build'])
+
+        return unknown_layer_version_obj
 
     def _get_recipe_information_from_taskfile(self, taskfile):
         localfilepath = taskfile.split(":")[-1]
@@ -587,27 +767,43 @@ class BuildInfoHelper(object):
 
     ################################
     ## external available methods to store information
+    @staticmethod
+    def _get_data_from_event(event):
+        evdata = None
+        if '_localdata' in vars(event):
+            evdata = event._localdata
+        elif 'data' in vars(event):
+            evdata = event.data
+        else:
+            raise Exception("Event with neither _localdata or data properties")
+        return evdata
 
     def store_layer_info(self, event):
-        assert 'data' in vars(event)
-        layerinfos = event.data
+        layerinfos = BuildInfoHelper._get_data_from_event(event)
         self.internal_state['lvs'] = {}
         for layer in layerinfos:
-            self.internal_state['lvs'][self.orm_wrapper.get_update_layer_object(layerinfos[layer])] = layerinfos[layer]['version']
+            try:
+                self.internal_state['lvs'][self.orm_wrapper.get_update_layer_object(layerinfos[layer], self.brbe)] = layerinfos[layer]['version']
+            except NotExisting as nee:
+                logger.warn("buildinfohelper: cannot identify layer exception:%s " % nee)
 
 
     def store_started_build(self, event):
         assert '_pkgs' in vars(event)
         build_information = self._get_build_information()
 
-        build_obj = self.orm_wrapper.create_build_object(build_information)
+        build_obj = self.orm_wrapper.create_build_object(build_information, self.brbe)
+
         self.internal_state['build'] = build_obj
 
         # save layer version information for this build
-        for layer_obj in self.internal_state['lvs']:
-            self.orm_wrapper.get_update_layer_version_object(build_obj, layer_obj, self.internal_state['lvs'][layer_obj])
+        if not 'lvs' in self.internal_state:
+            logger.error("Layer version information not found; Check if the bitbake server was configured to inherit toaster.bbclass.")
+        else:
+            for layer_obj in self.internal_state['lvs']:
+                self.orm_wrapper.get_update_layer_version_object(build_obj, layer_obj, self.internal_state['lvs'][layer_obj])
 
-        del self.internal_state['lvs']
+            del self.internal_state['lvs']
 
         # create target information
         target_information = {}
@@ -617,16 +813,27 @@ class BuildInfoHelper(object):
         self.internal_state['targets'] = self.orm_wrapper.create_target_objects(target_information)
 
         # Save build configuration
-        self.orm_wrapper.save_build_variables(build_obj, self.server.runCommand(["getAllKeysWithFlags", ["doc", "func"]])[0])
+        data = self.server.runCommand(["getAllKeysWithFlags", ["doc", "func"]])[0]
+        self.orm_wrapper.save_build_variables(build_obj, data)
+
+        return self.brbe
+
 
     def update_target_image_file(self, event):
         image_fstypes = self.server.runCommand(["getVariable", "IMAGE_FSTYPES"])[0]
+        evdata = BuildInfoHelper._get_data_from_event(event)
+
         for t in self.internal_state['targets']:
             if t.is_image == True:
-                output_files = list(event.data.viewkeys())
+                output_files = list(evdata.viewkeys())
                 for output in output_files:
-                    if t.target in output and output.split('.rootfs.')[1] in image_fstypes:
-                        self.orm_wrapper.save_target_image_file_information(t, output, event.data[output])
+                    if t.target in output and 'rootfs' in output and not output.endswith(".manifest"):
+                        self.orm_wrapper.save_target_image_file_information(t, output, evdata[output])
+
+    def update_artifact_image_file(self, event):
+        evdata = BuildInfoHelper._get_data_from_event(event)
+        for artifact_path in evdata.keys():
+            self.orm_wrapper.save_artifact_information(self.internal_state['build'], artifact_path, evdata[artifact_path])
 
     def update_build_information(self, event, errors, warnings, taskfailures):
         if 'build' in self.internal_state:
@@ -634,12 +841,12 @@ class BuildInfoHelper(object):
 
 
     def store_license_manifest_path(self, event):
-        deploy_dir = event.data['deploy_dir']
-        image_name =  event.data['image_name']
-        path = deploy_dir + "/licenses/" + image_name + "/"
+        deploy_dir = BuildInfoHelper._get_data_from_event(event)['deploy_dir']
+        image_name = BuildInfoHelper._get_data_from_event(event)['image_name']
+        path = deploy_dir + "/licenses/" + image_name + "/license.manifest"
         for target in self.internal_state['targets']:
             if target.target in image_name:
-                self.orm_wrapper.update_target_object(target, path)
+                self.orm_wrapper.update_target_set_license_manifest(target, path)
 
 
     def store_started_task(self, event):
@@ -683,14 +890,21 @@ class BuildInfoHelper(object):
 
 
     def store_tasks_stats(self, event):
-        for (taskfile, taskname, taskstats, recipename) in event.data:
+        for (taskfile, taskname, taskstats, recipename) in BuildInfoHelper._get_data_from_event(event):
             localfilepath = taskfile.split(":")[-1]
             assert localfilepath.startswith("/")
 
             recipe_information = self._get_recipe_information_from_taskfile(taskfile)
-            recipe_object = Recipe.objects.get(layer_version = recipe_information['layer_version'],
+            try:
+                if recipe_information['file_path'].startswith(recipe_information['layer_version'].layer.local_path):
+                    recipe_information['file_path'] = recipe_information['file_path'][len(recipe_information['layer_version'].layer.local_path):].lstrip("/")
+
+                recipe_object = Recipe.objects.get(layer_version = recipe_information['layer_version'],
                             file_path__endswith = recipe_information['file_path'],
                             name = recipename)
+            except Recipe.DoesNotExist:
+                logger.error("Could not find recipe for recipe_information %s name %s" % (pformat(recipe_information), recipename))
+                raise
 
             task_information = {}
             task_information['build'] = self.internal_state['build']
@@ -698,6 +912,8 @@ class BuildInfoHelper(object):
             task_information['task_name'] = taskname
             task_information['cpu_usage'] = taskstats['cpu_usage']
             task_information['disk_io'] = taskstats['disk_io']
+            if 'elapsed_time' in taskstats:
+                task_information['elapsed_time'] = taskstats['elapsed_time']
             task_obj = self.orm_wrapper.get_update_task_object(task_information, True)  # must exist
 
     def update_and_store_task(self, event):
@@ -751,16 +967,22 @@ class BuildInfoHelper(object):
                 task_information['outcome'] = Task.OUTCOME_FAILED
                 del self.internal_state['taskdata'][identifier]
 
+        if not connection.features.autocommits_when_autocommit_is_off:
+            # we force a sync point here, to get the progress bar to show
+            if self.autocommit_step % 3 == 0:
+                transaction.set_autocommit(True)
+                transaction.set_autocommit(False)
+            self.autocommit_step += 1
+
         self.orm_wrapper.get_update_task_object(task_information, True) # must exist
 
 
     def store_missed_state_tasks(self, event):
-        for (fn, taskname, taskhash, sstatefile) in event.data['missed']:
+        for (fn, taskname, taskhash, sstatefile) in BuildInfoHelper._get_data_from_event(event)['missed']:
 
             identifier = fn + taskname + "_setscene"
             recipe_information = self._get_recipe_information_from_taskfile(fn)
             recipe = self.orm_wrapper.get_update_recipe_object(recipe_information)
-            class MockEvent: pass
             mevent = MockEvent()
             mevent.taskname = taskname
             mevent.taskhash = taskhash
@@ -774,12 +996,11 @@ class BuildInfoHelper(object):
 
             self.orm_wrapper.get_update_task_object(task_information)
 
-        for (fn, taskname, taskhash, sstatefile) in event.data['found']:
+        for (fn, taskname, taskhash, sstatefile) in BuildInfoHelper._get_data_from_event(event)['found']:
 
             identifier = fn + taskname + "_setscene"
             recipe_information = self._get_recipe_information_from_taskfile(fn)
             recipe = self.orm_wrapper.get_update_recipe_object(recipe_information)
-            class MockEvent: pass
             mevent = MockEvent()
             mevent.taskname = taskname
             mevent.taskhash = taskhash
@@ -791,15 +1012,14 @@ class BuildInfoHelper(object):
 
 
     def store_target_package_data(self, event):
-        assert 'data' in vars(event)
         # for all image targets
         for target in self.internal_state['targets']:
             if target.is_image:
                 try:
-                    pkgdata = event.data['pkgdata']
-                    imgdata = event.data['imgdata'][target.target]
+                    pkgdata = BuildInfoHelper._get_data_from_event(event)['pkgdata']
+                    imgdata = BuildInfoHelper._get_data_from_event(event)['imgdata'][target.target]
                     self.orm_wrapper.save_target_package_information(self.internal_state['build'], target, imgdata, pkgdata, self.internal_state['recipes'])
-                    filedata = event.data['filedata'][target.target]
+                    filedata = BuildInfoHelper._get_data_from_event(event)['filedata'][target.target]
                     self.orm_wrapper.save_target_file_information(self.internal_state['build'], target, filedata)
                 except KeyError:
                     # we must have not got the data for this image, nothing to save
@@ -835,14 +1055,29 @@ class BuildInfoHelper(object):
 
             recipe_info = {}
             recipe_info['name'] = pn
-            recipe_info['version'] = event._depgraph['pn'][pn]['version'].lstrip(":")
             recipe_info['layer_version'] = layer_version_obj
-            recipe_info['summary'] = event._depgraph['pn'][pn]['summary']
-            recipe_info['license'] = event._depgraph['pn'][pn]['license']
-            recipe_info['description'] = event._depgraph['pn'][pn]['description']
-            recipe_info['section'] = event._depgraph['pn'][pn]['section']
-            recipe_info['homepage'] = event._depgraph['pn'][pn]['homepage']
-            recipe_info['bugtracker'] = event._depgraph['pn'][pn]['bugtracker']
+
+            if 'version' in event._depgraph['pn'][pn]:
+                recipe_info['version'] = event._depgraph['pn'][pn]['version'].lstrip(":")
+
+            if 'summary' in event._depgraph['pn'][pn]:
+                recipe_info['summary'] = event._depgraph['pn'][pn]['summary']
+
+            if 'license' in event._depgraph['pn'][pn]:
+                recipe_info['license'] = event._depgraph['pn'][pn]['license']
+
+            if 'description' in event._depgraph['pn'][pn]:
+                recipe_info['description'] = event._depgraph['pn'][pn]['description']
+
+            if 'section' in event._depgraph['pn'][pn]:
+                recipe_info['section'] = event._depgraph['pn'][pn]['section']
+
+            if 'homepage' in event._depgraph['pn'][pn]:
+                recipe_info['homepage'] = event._depgraph['pn'][pn]['homepage']
+
+            if 'bugtracker' in event._depgraph['pn'][pn]:
+                recipe_info['bugtracker'] = event._depgraph['pn'][pn]['bugtracker']
+
             recipe_info['file_path'] = file_name
             recipe = self.orm_wrapper.get_update_recipe_object(recipe_info)
             recipe.is_image = False
@@ -864,20 +1099,22 @@ class BuildInfoHelper(object):
 
         # save recipe dependency
         # buildtime
+        recipedeps_objects = []
         for recipe in event._depgraph['depends']:
             try:
                 target = self.internal_state['recipes'][recipe]
                 for dep in event._depgraph['depends'][recipe]:
                     dependency = self.internal_state['recipes'][dep]
-                    Recipe_Dependency.objects.get_or_create( recipe = target,
-                            depends_on = dependency, dep_type = Recipe_Dependency.TYPE_DEPENDS)
+                    recipedeps_objects.append(Recipe_Dependency( recipe = target,
+                            depends_on = dependency, dep_type = Recipe_Dependency.TYPE_DEPENDS))
             except KeyError as e:
                 if e not in assume_provided and not str(e).startswith("virtual/"):
                     errormsg += "  stpd: KeyError saving recipe dependency for %s, %s \n" % (recipe, e)
+        Recipe_Dependency.objects.bulk_create(recipedeps_objects)
 
         # save all task information
         def _save_a_task(taskdesc):
-            spec = re.split(r'\.', taskdesc);
+            spec = re.split(r'\.', taskdesc)
             pn = ".".join(spec[0:-1])
             taskname = spec[-1]
             e = event
@@ -894,6 +1131,7 @@ class BuildInfoHelper(object):
             tasks[taskdesc] = _save_a_task(taskdesc)
 
         # create dependencies between tasks
+        taskdeps_objects = []
         for taskdesc in event._depgraph['tdepends']:
             target = tasks[taskdesc]
             for taskdep in event._depgraph['tdepends'][taskdesc]:
@@ -902,63 +1140,111 @@ class BuildInfoHelper(object):
                     dep = _save_a_task(taskdep)
                 else:
                     dep = tasks[taskdep]
-                Task_Dependency.objects.get_or_create( task = target, depends_on = dep )
+                taskdeps_objects.append(Task_Dependency( task = target, depends_on = dep ))
+        Task_Dependency.objects.bulk_create(taskdeps_objects)
 
         if (len(errormsg) > 0):
-            raise Exception(errormsg)
+            logger.warn("buildinfohelper: dependency info not identify recipes: \n%s" % errormsg)
 
 
     def store_build_package_information(self, event):
-        assert 'data' in vars(event)
-        package_info = event.data
+        package_info = BuildInfoHelper._get_data_from_event(event)
         self.orm_wrapper.save_build_package_information(self.internal_state['build'],
                             package_info,
                             self.internal_state['recipes'],
                             )
 
-    def _store_log_information(self, level, text):
-        log_information = {}
-        log_information['build'] = self.internal_state['build']
-        log_information['level'] = level
-        log_information['message'] = text
-        self.orm_wrapper.create_logmessage(log_information)
+    def _store_build_done(self, errorcode):
+        br_id, be_id = self.brbe.split(":")
+        from bldcontrol.models import BuildEnvironment, BuildRequest
+        be = BuildEnvironment.objects.get(pk = be_id)
+        be.lock = BuildEnvironment.LOCK_LOCK
+        be.save()
+        br = BuildRequest.objects.get(pk = br_id)
+        if errorcode == 0:
+            # request archival of the project artifacts
+            br.state = BuildRequest.REQ_ARCHIVE
+        else:
+            br.state = BuildRequest.REQ_FAILED
+        br.save()
 
-    def store_log_info(self, text):
-        self._store_log_information(LogMessage.INFO, text)
-
-    def store_log_warn(self, text):
-        self._store_log_information(LogMessage.WARNING, text)
 
     def store_log_error(self, text):
-        self._store_log_information(LogMessage.ERROR, text)
+        mockevent = MockEvent()
+        mockevent.levelno = format.ERROR
+        mockevent.msg = text
+        mockevent.pathname = '-- None'
+        mockevent.lineno = -1
+        self.store_log_event(mockevent)
+
+    def store_log_exception(self, text, backtrace = ""):
+        mockevent = MockEvent()
+        mockevent.levelno = -1
+        mockevent.msg = text
+        mockevent.pathname = backtrace
+        mockevent.lineno = -1
+        self.store_log_event(mockevent)
+
 
     def store_log_event(self, event):
-        if 'build' in self.internal_state and 'backlog' in self.internal_state:
-            if len(self.internal_state['backlog']):
-                tempevent = self.internal_state['backlog'].pop()
-                print "Saving stored event ", tempevent
-                self.store_log_event(tempevent)
-            else:
-                del self.internal_state['backlog']
-
         if event.levelno < format.WARNING:
             return
 
+        if 'args' in vars(event):
+            event.msg = event.msg % event.args
+
         if not 'build' in self.internal_state:
-            print "Save event for later"
-            if not 'backlog' in self.internal_state:
-                self.internal_state['backlog'] = []
-            self.internal_state['backlog'].append(event)
+            if self.brbe is None:
+                if not 'backlog' in self.internal_state:
+                    self.internal_state['backlog'] = []
+                self.internal_state['backlog'].append(event)
+            else:   # we're under Toaster control, post the errors to the build request
+                from bldcontrol.models import BuildRequest, BRError
+                br, be = self.brbe.split(":")
+                buildrequest = BuildRequest.objects.get(pk = br)
+                brerror = BRError.objects.create(req = buildrequest, errtype="build", errmsg = event.msg)
 
             return
+
+        if 'build' in self.internal_state and 'backlog' in self.internal_state:
+            # if we have a backlog of events, do our best to save them here
+            if len(self.internal_state['backlog']):
+                tempevent = self.internal_state['backlog'].pop()
+                logger.debug(1, "buildinfohelper: Saving stored event %s " % tempevent)
+                self.store_log_event(tempevent)
+            else:
+                logger.error("buildinfohelper: Events not saved: %s" % self.internal_state['backlog'])
+                del self.internal_state['backlog']
+
         log_information = {}
         log_information['build'] = self.internal_state['build']
-        if event.levelno >= format.ERROR:
+        if event.levelno == format.ERROR:
             log_information['level'] = LogMessage.ERROR
         elif event.levelno == format.WARNING:
             log_information['level'] = LogMessage.WARNING
+        elif event.levelno == -1:   # toaster self-logging
+            log_information['level'] = -1
+        else:
+            log_information['level'] = LogMessage.INFO
+
         log_information['message'] = event.msg
         log_information['pathname'] = event.pathname
         log_information['lineno'] = event.lineno
         self.orm_wrapper.create_logmessage(log_information)
 
+    def close(self, errorcode):
+        if self.brbe is not None:
+            self._store_build_done(errorcode)
+
+        if 'backlog' in self.internal_state:
+            if 'build' in self.internal_state:
+                # we save missed events in the database for the current build
+                tempevent = self.internal_state['backlog'].pop()
+                self.store_log_event(tempevent)
+            else:
+                # we have no build, and we still have events; something amazingly wrong happend
+                for event in self.internal_state['backlog']:
+                   logger.error("UNSAVED log: %s", event.msg)
+
+        if not connection.features.autocommits_when_autocommit_is_off:
+            transaction.set_autocommit(True)

bitbake/lib/bb/ui/crumbs/hig/simplesettingsdialog.py

@@ -230,10 +230,7 @@ class SimpleSettingsDialog (CrumbsDialog, SettingsUIHelper):
         self.configuration.sstatemirror = ""
         for mirror in self.sstatemirrors_list:
             if mirror[1] != "" and mirror[2].startswith("file://"):
-                if mirror[1].endswith("\\1"):
-                    smirror = mirror[2] + " " + mirror[1] + " \\n "
-                else:
-                    smirror = mirror[2] + " " + mirror[1] + "\\1 \\n "
+                smirror = mirror[2] + " " + mirror[1] + " \\n "
                 self.configuration.sstatemirror += smirror
         self.configuration.bbthread = self.bb_spinner.get_value_as_int()
         self.configuration.pmake = self.pmake_spinner.get_value_as_int()

bitbake/lib/bb/ui/depexp.py

@@ -17,6 +17,7 @@
 # with this program; if not, write to the Free Software Foundation, Inc.,
 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 
+import sys
 import gobject
 import gtk
 import Queue
@@ -198,7 +199,7 @@ def main(server, eventHandler, params):
             print("Nothing to do.  Use 'bitbake world' to build everything, or run 'bitbake --help' for usage information.")
             return 1
         if 'msg' in cmdline and cmdline['msg']:
-            logger.error(cmdline['msg'])
+            print(cmdline['msg'])
             return 1
         cmdline = cmdline['action']
         if not cmdline or cmdline[0] != "generateDotGraph":
@@ -215,6 +216,12 @@ def main(server, eventHandler, params):
         print("XMLRPC Fault getting commandline:\n %s" % x)
         return
 
+    try:
+        gtk.init_check()
+    except RuntimeError:
+        sys.stderr.write("Please set DISPLAY variable before running this command \n")
+        return
+
     shutdown = 0
 
     gtkgui = gtkthread(shutdown)
@@ -236,7 +243,7 @@ def main(server, eventHandler, params):
         try:
             event = eventHandler.waitEvent(0.25)
             if gtkthread.quit.isSet():
-                _, error = server.runCommand(["stateStop"])
+                _, error = server.runCommand(["stateForceShutdown"])
                 if error:
                     print('Unable to cleanly stop: %s' % error)
                 break

bitbake/lib/bb/ui/knotty.py

@@ -271,7 +271,7 @@ def main(server, eventHandler, params, tf = TerminalFilter):
         server.terminateServer()
         return
 
-    if consolelogfile and not params.options.show_environment:
+    if consolelogfile and not params.options.show_environment and not params.options.show_versions:
         bb.utils.mkdirhier(os.path.dirname(consolelogfile))
         conlogformat = bb.msg.BBLogFormatter(format_str)
         consolelog = logging.FileHandler(consolelogfile)
@@ -284,6 +284,7 @@ def main(server, eventHandler, params, tf = TerminalFilter):
 
     if not params.observe_only:
         params.updateFromServer(server)
+        params.updateToServer(server, os.environ.copy())
         cmdline = params.parseActions()
         if not cmdline:
             print("Nothing to do.  Use 'bitbake world' to build everything, or run 'bitbake --help' for usage information.")
@@ -321,8 +322,8 @@ def main(server, eventHandler, params, tf = TerminalFilter):
                     break
                 termfilter.updateFooter()
                 event = eventHandler.waitEvent(0.25)
-            if event is None:
-                continue
+                if event is None:
+                    continue
             helper.eventHandler(event)
             if isinstance(event, bb.runqueue.runQueueExitWait):
                 if not main.shutdown:
@@ -351,7 +352,7 @@ def main(server, eventHandler, params, tf = TerminalFilter):
                 # For "normal" logging conditions, don't show note logs from tasks
                 # but do show them if the user has changed the default log level to
                 # include verbose/debug messages
-                if event.taskpid != 0 and event.levelno <= format.NOTE:
+                if event.taskpid != 0 and event.levelno <= format.NOTE and (event.levelno < llevel or (event.levelno == format.NOTE and llevel != format.VERBOSE)):
                     continue
                 logger.handle(event)
                 continue
@@ -507,7 +508,11 @@ def main(server, eventHandler, params, tf = TerminalFilter):
             termfilter.clearFooter()
             # ignore interrupted io
             if ioerror.args[0] == 4:
-                pass
+                continue
+            sys.stderr.write(str(ioerror))
+            if not params.observe_only:
+                _, error = server.runCommand(["stateForceShutdown"])
+            main.shutdown = 2
         except KeyboardInterrupt:
             termfilter.clearFooter()
             if params.observe_only:
@@ -526,25 +531,34 @@ def main(server, eventHandler, params, tf = TerminalFilter):
                     logger.error("Unable to cleanly shutdown: %s" % error)
             main.shutdown = main.shutdown + 1
             pass
+        except Exception as e:
+            sys.stderr.write(str(e))
+            if not params.observe_only:
+                _, error = server.runCommand(["stateForceShutdown"])
+            main.shutdown = 2
+    try:
+        summary = ""
+        if taskfailures:
+            summary += pluralise("\nSummary: %s task failed:",
+                                 "\nSummary: %s tasks failed:", len(taskfailures))
+            for failure in taskfailures:
+                summary += "\n  %s" % failure
+        if warnings:
+            summary += pluralise("\nSummary: There was %s WARNING message shown.",
+                                 "\nSummary: There were %s WARNING messages shown.", warnings)
+        if return_value and errors:
+            summary += pluralise("\nSummary: There was %s ERROR message shown, returning a non-zero exit code.",
+                                 "\nSummary: There were %s ERROR messages shown, returning a non-zero exit code.", errors)
+        if summary:
+            print(summary)
 
-    summary = ""
-    if taskfailures:
-        summary += pluralise("\nSummary: %s task failed:",
-                             "\nSummary: %s tasks failed:", len(taskfailures))
-        for failure in taskfailures:
-            summary += "\n  %s" % failure
-    if warnings:
-        summary += pluralise("\nSummary: There was %s WARNING message shown.",
-                             "\nSummary: There were %s WARNING messages shown.", warnings)
-    if return_value and errors:
-        summary += pluralise("\nSummary: There was %s ERROR message shown, returning a non-zero exit code.",
-                             "\nSummary: There were %s ERROR messages shown, returning a non-zero exit code.", errors)
-    if summary:
-        print(summary)
-
-    if interrupted:
-        print("Execution was interrupted, returning a non-zero exit code.")
-        if return_value == 0:
-            return_value = 1
+        if interrupted:
+            print("Execution was interrupted, returning a non-zero exit code.")
+            if return_value == 0:
+                return_value = 1
+    except IOError as e:
+        import errno
+        if e.errno == errno.EPIPE:
+            pass
 
     return return_value

bitbake/lib/bb/ui/ncurses.py

@@ -361,13 +361,13 @@ class NCursesUI:
                 shutdown = shutdown + 1
                 pass
 
-def main(server, eventHandler):
+def main(server, eventHandler, params):
     if not os.isatty(sys.stdout.fileno()):
         print("FATAL: Unable to run 'ncurses' UI without a TTY.")
         return
     ui = NCursesUI()
     try:
-        curses.wrapper(ui.main, server, eventHandler)
+        curses.wrapper(ui.main, server, eventHandler, params)
     except:
         import traceback
         traceback.print_exc()

bitbake/lib/bb/ui/toasterui.py

@@ -41,7 +41,7 @@ import sys
 import time
 import xmlrpclib
 
-featureSet = [bb.cooker.CookerFeatures.HOB_EXTRA_CACHES, bb.cooker.CookerFeatures.SEND_DEPENDS_TREE, bb.cooker.CookerFeatures.BASEDATASTORE_TRACKING]
+featureSet = [bb.cooker.CookerFeatures.HOB_EXTRA_CACHES, bb.cooker.CookerFeatures.SEND_DEPENDS_TREE, bb.cooker.CookerFeatures.BASEDATASTORE_TRACKING, bb.cooker.CookerFeatures.SEND_SANITYEVENTS]
 
 logger = logging.getLogger("BitBake")
 interactive = sys.stdout.isatty()
@@ -58,19 +58,15 @@ def _log_settings_from_server(server):
     if error:
         logger.error("Unable to get the value of BBINCLUDELOGS_LINES variable: %s" % error)
         raise BaseException(error)
-    return includelogs, loglines
+    consolelogfile, error = server.runCommand(["getVariable", "BB_CONSOLELOG"])
+    if error:
+        logger.error("Unable to get the value of BB_CONSOLELOG variable: %s" % error)
+        raise BaseException(error)
+    return includelogs, loglines, consolelogfile
+
 
 def main(server, eventHandler, params ):
 
-    includelogs, loglines = _log_settings_from_server(server)
-
-    # verify and warn
-    build_history_enabled = True
-    inheritlist, error = server.runCommand(["getVariable", "INHERIT"])
-    if not "buildhistory" in inheritlist.split(" "):
-        logger.warn("buildhistory is not enabled. Please enable INHERIT += \"buildhistory\" to see image details.")
-        build_history_enabled = False
-
     helper = uihelper.BBUIHelper()
 
     console = logging.StreamHandler(sys.stdout)
@@ -80,6 +76,16 @@ def main(server, eventHandler, params ):
     console.setFormatter(format)
     logger.addHandler(console)
 
+    includelogs, loglines, consolelogfile = _log_settings_from_server(server)
+
+    # verify and warn
+    build_history_enabled = True
+    inheritlist, error = server.runCommand(["getVariable", "INHERIT"])
+
+    if not "buildhistory" in inheritlist.split(" "):
+        logger.warn("buildhistory is not enabled. Please enable INHERIT += \"buildhistory\" to see image details.")
+        build_history_enabled = False
+
     if not params.observe_only:
         logger.error("ToasterUI can only work in observer mode")
         return
@@ -91,13 +97,26 @@ def main(server, eventHandler, params ):
     errors = 0
     warnings = 0
     taskfailures = []
+    first = True
 
     buildinfohelper = BuildInfoHelper(server, build_history_enabled)
 
+    if buildinfohelper.brbe is not None and consolelogfile:
+        # if we are under managed mode we have no other UI and we need to write our own file
+        bb.utils.mkdirhier(os.path.dirname(consolelogfile))
+        conlogformat = bb.msg.BBLogFormatter(format_str)
+        consolelog = logging.FileHandler(consolelogfile)
+        bb.msg.addDefaultlogFilter(consolelog)
+        consolelog.setFormatter(conlogformat)
+        logger.addHandler(consolelog)
+
 
     while True:
         try:
             event = eventHandler.waitEvent(0.25)
+            if first:
+                first = False
+                logger.info("ToasterUI waiting for events")
 
             if event is None:
                 if main.shutdown > 0:
@@ -111,8 +130,12 @@ def main(server, eventHandler, params ):
 
             if isinstance(event, (bb.build.TaskStarted, bb.build.TaskSucceeded, bb.build.TaskFailedSilent)):
                 buildinfohelper.update_and_store_task(event)
+                logger.warn("Logfile for task %s" % event.logfile)
                 continue
 
+            if isinstance(event, bb.build.TaskBase):
+                logger.info(event._message)
+
             if isinstance(event, bb.event.LogExecTTY):
                 logger.warn(event.msg)
                 continue
@@ -158,7 +181,12 @@ def main(server, eventHandler, params ):
             if isinstance(event, bb.event.CacheLoadCompleted):
                 continue
             if isinstance(event, bb.event.MultipleProviders):
+                logger.info("multiple providers are available for %s%s (%s)", event._is_runtime and "runtime " or "",
+                            event._item,
+                            ", ".join(event._candidates))
+                logger.info("consider defining a PREFERRED_PROVIDER entry to match %s", event._item)
                 continue
+
             if isinstance(event, bb.event.NoProvider):
                 return_value = 1
                 errors = errors + 1
@@ -216,21 +244,34 @@ def main(server, eventHandler, params ):
             if isinstance(event, (bb.command.CommandCompleted,
                                   bb.command.CommandFailed,
                                   bb.command.CommandExit)):
+                errorcode = 0
                 if (isinstance(event, bb.command.CommandFailed)):
                     event.levelno = format.ERROR
-                    event.msg = event.error
+                    event.msg = "Command Failed " + event.error
                     event.pathname = ""
                     event.lineno = 0
                     buildinfohelper.store_log_event(event)
                     errors += 1
+                    errorcode = 1
+                    logger.error("Command execution failed: %s", event.error)
 
                 buildinfohelper.update_build_information(event, errors, warnings, taskfailures)
+                buildinfohelper.close(errorcode)
+                # mark the log output; controllers may kill the toasterUI after seeing this log
+                logger.info("ToasterUI build done")
 
                 # we start a new build info
-                errors = 0
-                warnings = 0
-                taskfailures = []
-                buildinfohelper = BuildInfoHelper(server, build_history_enabled)
+                if buildinfohelper.brbe is not None:
+
+                    logger.debug(1, "ToasterUI under BuildEnvironment management - exiting after the build")
+                    server.terminateServer()
+                else:
+                    logger.debug(1, "ToasterUI prepared for new build")
+                    errors = 0
+                    warnings = 0
+                    taskfailures = []
+                    buildinfohelper = BuildInfoHelper(server, build_history_enabled)
+
                 continue
 
             if isinstance(event, bb.event.MetadataEvent):
@@ -246,8 +287,12 @@ def main(server, eventHandler, params ):
                     buildinfohelper.store_missed_state_tasks(event)
                 elif event.type == "ImageFileSize":
                     buildinfohelper.update_target_image_file(event)
+                elif event.type == "ArtifactFileSize":
+                    buildinfohelper.update_artifact_image_file(event)
                 elif event.type == "LicenseManifestPath":
                     buildinfohelper.store_license_manifest_path(event)
+                else:
+                    logger.error("Unprocessed MetadataEvent %s " % str(event))
                 continue
 
             if isinstance(event, bb.cooker.CookerExit):
@@ -280,9 +325,25 @@ def main(server, eventHandler, params ):
             main.shutdown = 1
             pass
         except Exception as e:
-            logger.error(e)
+            # print errors to log
             import traceback
-            traceback.print_exc()
+            from pprint import pformat
+            exception_data = traceback.format_exc()
+            logger.error("%s\n%s" % (e, exception_data))
+
+            exc_type, exc_value, tb = sys.exc_info()
+            if tb is not None:
+                curr = tb
+                while curr is not None:
+                    logger.warn("Error data dump %s\n%s\n" % (traceback.format_tb(curr,1), pformat(curr.tb_frame.f_locals)))
+                    curr = curr.tb_next
+
+            # save them to database, if possible; if it fails, we already logged to console.
+            try:
+                buildinfohelper.store_log_exception("%s\n%s" % (str(e), exception_data))
+            except Exception as ce:
+                logger.error("CRITICAL - Failed to to save toaster exception to the database: %s" % str(ce))
+
             pass
 
     if interrupted:

bitbake/lib/bb/ui/uievent.py

@@ -44,10 +44,27 @@ class BBUIEventQueue:
         server.register_function( self.send_event, "event.sendpickle" )
         server.socket.settimeout(1)
 
-        self.EventHandle = self.BBServer.registerEventHandler(self.host, self.port)
+        self.EventHandler = None
+        count_tries = 0
 
-        if (self.EventHandle == None):
-            bb.fatal("Could not register UI event handler")
+        # the event handler registration may fail here due to cooker being in invalid state
+        # this is a transient situation, and we should retry a couple of times before
+        # giving up
+
+        while self.EventHandler == None and count_tries < 5:
+            self.EventHandle = self.BBServer.registerEventHandler(self.host, self.port)
+
+            if (self.EventHandle != None):
+                break
+
+            bb.warn("Could not register UI event handler %s:%d, retry" % (self.host, self.port))
+            count_tries += 1
+            import time
+            time.sleep(1)
+
+
+        if self.EventHandle == None:
+            raise Exception("Could not register UI event handler")
 
         self.server = server
 
@@ -89,7 +106,12 @@ class BBUIEventQueue:
 
         self.server.timeout = 1
         while not self.server.quit:
-            self.server.handle_request()
+            try:
+                self.server.handle_request()
+            except Exception as e:
+                import traceback
+                logger.error("BBUIEventQueue.startCallbackHandler: Exception while trying to handle request: %s\n%s" % (e, traceback.format_exc(e)))
+
         self.server.server_close()
 
     def system_quit( self ):

bitbake/lib/bb/utils.py

@@ -31,6 +31,7 @@ import subprocess
 import glob
 import traceback
 import errno
+import signal
 from commands import getstatusoutput
 from contextlib import contextmanager
 
@@ -53,6 +54,9 @@ def set_context(ctx):
 # Context used in better_exec, eval
 _context = clean_context()
 
+class VersionStringException(Exception):
+    """Exception raised when an invalid version specification is found"""
+
 def explode_version(s):
     r = []
     alpha_regexp = re.compile('^([a-zA-Z]+)(.*)$')
@@ -128,6 +132,28 @@ def vercmp_string(a, b):
     tb = split_version(b)
     return vercmp(ta, tb)
 
+def vercmp_string_op(a, b, op):
+    """
+    Compare two versions and check if the specified comparison operator matches the result of the comparison.
+    This function is fairly liberal about what operators it will accept since there are a variety of styles
+    depending on the context.
+    """
+    res = vercmp_string(a, b)
+    if op in ('=', '=='):
+        return res == 0
+    elif op == '<=':
+        return res <= 0
+    elif op == '>=':
+        return res >= 0
+    elif op in ('>', '>>'):
+        return res > 0
+    elif op in ('<', '<<'):
+        return res < 0
+    elif op == '!=':
+        return res != 0
+    else:
+        raise VersionStringException('Unsupported comparison operator "%s"' % op)
+
 def explode_deps(s):
     """
     Take an RDEPENDS style string of format:
@@ -188,6 +214,7 @@ def explode_dep_versions2(s):
                 i = i[1:]
             else:
                 # This is an unsupported case!
+                raise VersionStringException('Invalid version specification in "(%s" - invalid or missing operator' % i)
                 lastcmp = (i or "")
                 i = ""
             i.strip()
@@ -264,7 +291,7 @@ def _print_trace(body, line):
 def better_compile(text, file, realfile, mode = "exec"):
     """
     A better compile method. This method
-    will print  the offending lines.
+    will print the offending lines.
     """
     try:
         return compile(text, file, mode)
@@ -354,14 +381,11 @@ def better_exec(code, context, text = None, realfile = "<code>"):
         code = better_compile(code, realfile, realfile)
     try:
         exec(code, get_context(), context)
-    except bb.BBHandledException:
-        # Error already shown so passthrough
+    except (bb.BBHandledException, bb.parse.SkipRecipe, bb.build.FuncFailed, bb.data_smart.ExpansionError):
+        # Error already shown so passthrough, no need for traceback
         raise
     except Exception as e:
         (t, value, tb) = sys.exc_info()
-
-        if t in [bb.parse.SkipPackage, bb.build.FuncFailed]:
-            raise
         try:
             _print_exception(t, value, tb, realfile, text, context)
         except Exception as e:
@@ -389,10 +413,30 @@ def fileslocked(files):
     for lock in locks:
         bb.utils.unlockfile(lock)
 
-def lockfile(name, shared=False, retry=True):
+@contextmanager
+def timeout(seconds):
+    def timeout_handler(signum, frame):
+        pass
+
+    original_handler = signal.signal(signal.SIGALRM, timeout_handler)
+
+    try:
+        signal.alarm(seconds)
+        yield
+    finally:
+        signal.alarm(0)
+        signal.signal(signal.SIGALRM, original_handler)
+
+def lockfile(name, shared=False, retry=True, block=False):
     """
-    Use the file fn as a lock file, return when the lock has been acquired.
-    Returns a variable to pass to unlockfile().
+    Use the specified file as a lock file, return when the lock has
+    been acquired. Returns a variable to pass to unlockfile().
+    Parameters:
+        retry: True to re-try locking if it fails, False otherwise
+        block: True to block until the lock succeeds, False otherwise
+    The retry and block parameters are kind of equivalent unless you
+    consider the possibility of sending a signal to the process to break
+    out - at which point you want block=True rather than retry=True.
     """
     dirname = os.path.dirname(name)
     mkdirhier(dirname)
@@ -405,7 +449,7 @@ def lockfile(name, shared=False, retry=True):
     op = fcntl.LOCK_EX
     if shared:
         op = fcntl.LOCK_SH
-    if not retry:
+    if not retry and not block:
         op = op | fcntl.LOCK_NB
 
     while True:
@@ -525,7 +569,7 @@ def filter_environment(good_vars):
         os.unsetenv(key)
         del os.environ[key]
 
-    if len(removed_vars):
+    if removed_vars:
         logger.debug(1, "Removed the following variables from the environment: %s", ", ".join(removed_vars.keys()))
 
     return removed_vars
@@ -533,7 +577,7 @@ def filter_environment(good_vars):
 def approved_variables():
     """
     Determine and return the list of whitelisted variables which are approved
-    to remain in the envrionment.
+    to remain in the environment.
     """
     if 'BB_PRESERVE_ENV' in os.environ:
         return os.environ.keys()
@@ -578,11 +622,30 @@ def build_environment(d):
         if export:
             os.environ[var] = d.getVar(var, True) or ""
 
+def _check_unsafe_delete_path(path):
+    """
+    Basic safeguard against recursively deleting something we shouldn't. If it returns True,
+    the caller should raise an exception with an appropriate message.
+    NOTE: This is NOT meant to be a security mechanism - just a guard against silly mistakes
+    with potentially disastrous results.
+    """
+    extra = ''
+    # HOME might not be /home/something, so in case we can get it, check against it
+    homedir = os.environ.get('HOME', '')
+    if homedir:
+        extra = '|%s' % homedir
+    if re.match('(/|//|/home|/home/[^/]*%s)$' % extra, os.path.abspath(path)):
+        return True
+    return False
+
 def remove(path, recurse=False):
     """Equivalent to rm -f or rm -rf"""
     if not path:
         return
     if recurse:
+        for name in glob.glob(path):
+            if _check_unsafe_delete_path(path):
+                raise Exception('bb.utils.remove: called with dangerous path "%s" and recurse=True, refusing to delete!' % path)
         # shutil.rmtree(name) would be ideal but its too slow
         subprocess.call(['rm', '-rf'] + glob.glob(path))
         return
@@ -596,6 +659,8 @@ def remove(path, recurse=False):
 def prunedir(topdir):
     # Delete everything reachable from the directory named in 'topdir'.
     # CAUTION:  This is dangerous!
+    if _check_unsafe_delete_path(topdir):
+        raise Exception('bb.utils.prunedir: called with dangerous path "%s", refusing to delete!' % topdir)
     for root, dirs, files in os.walk(topdir, topdown = False):
         for name in files:
             os.remove(os.path.join(root, name))
@@ -845,6 +910,19 @@ def contains(variable, checkvalues, truevalue, falsevalue, d):
         return truevalue
     return falsevalue
 
+def contains_any(variable, checkvalues, truevalue, falsevalue, d):
+    val = d.getVar(variable, True)
+    if not val:
+        return falsevalue
+    val = set(val.split())
+    if isinstance(checkvalues, basestring):
+        checkvalues = set(checkvalues.split())
+    else:
+        checkvalues = set(checkvalues)
+    if checkvalues & val:
+        return truevalue
+    return falsevalue
+
 def cpu_count():
     return multiprocessing.cpu_count()
 
@@ -852,21 +930,16 @@ def nonblockingfd(fd):
     fcntl.fcntl(fd, fcntl.F_SETFL, fcntl.fcntl(fd, fcntl.F_GETFL) | os.O_NONBLOCK)
 
 def process_profilelog(fn):
-    # Redirect stdout to capture profile information
     pout = open(fn + '.processed', 'w')
-    so = sys.stdout.fileno()
-    orig_so = os.dup(sys.stdout.fileno())
-    os.dup2(pout.fileno(), so)
    
     import pstats
-    p = pstats.Stats(fn)
+    p = pstats.Stats(fn, stream=pout)
     p.sort_stats('time')
     p.print_stats()
     p.print_callers()
     p.sort_stats('cumulative')
     p.print_stats()
 
-    os.dup2(orig_so, so)
     pout.flush()
     pout.close()  
 
@@ -874,5 +947,198 @@ def process_profilelog(fn):
 # Was present to work around multiprocessing pool bugs in python < 2.7.3
 #
 def multiprocessingpool(*args, **kwargs):
+
+    import multiprocessing.pool
+    #import multiprocessing.util
+    #multiprocessing.util.log_to_stderr(10)
+    # Deal with a multiprocessing bug where signals to the processes would be delayed until the work
+    # completes. Putting in a timeout means the signals (like SIGINT/SIGTERM) get processed.
+    def wrapper(func):
+        def wrap(self, timeout=None):
+            return func(self, timeout=timeout if timeout is not None else 1e100)
+        return wrap
+    multiprocessing.pool.IMapIterator.next = wrapper(multiprocessing.pool.IMapIterator.next)
+
     return multiprocessing.Pool(*args, **kwargs)
 
+def exec_flat_python_func(func, *args, **kwargs):
+    """Execute a flat python function (defined with def funcname(args):...)"""
+    # Prepare a small piece of python code which calls the requested function
+    # To do this we need to prepare two things - a set of variables we can use to pass
+    # the values of arguments into the calling function, and the list of arguments for
+    # the function being called
+    context = {}
+    funcargs = []
+    # Handle unnamed arguments
+    aidx = 1
+    for arg in args:
+        argname = 'arg_%s' % aidx
+        context[argname] = arg
+        funcargs.append(argname)
+        aidx += 1
+    # Handle keyword arguments
+    context.update(kwargs)
+    funcargs.extend(['%s=%s' % (arg, arg) for arg in kwargs.iterkeys()])
+    code = 'retval = %s(%s)' % (func, ', '.join(funcargs))
+    comp = bb.utils.better_compile(code, '<string>', '<string>')
+    bb.utils.better_exec(comp, context, code, '<string>')
+    return context['retval']
+
+def edit_metadata_file(meta_file, variables, func):
+    """Edit a recipe or config file and modify one or more specified
+    variable values set in the file using a specified callback function.
+    The file is only written to if the value(s) actually change.
+    """
+    var_res = {}
+    for var in variables:
+        var_res[var] = re.compile(r'^%s[ \t]*[?+]*=' % var)
+
+    updated = False
+    varset_start = ''
+    varlines = []
+    newlines = []
+    in_var = None
+    full_value = ''
+
+    def handle_var_end():
+        (newvalue, indent, minbreak) = func(in_var, full_value)
+        if newvalue != full_value:
+            if isinstance(newvalue, list):
+                intentspc = ' ' * indent
+                if minbreak:
+                    # First item on first line
+                    if len(newvalue) == 1:
+                        newlines.append('%s "%s"\n' % (varset_start, newvalue[0]))
+                    else:
+                        newlines.append('%s "%s\\\n' % (varset_start, newvalue[0]))
+                        for item in newvalue[1:]:
+                            newlines.append('%s%s \\\n' % (intentspc, item))
+                        newlines.append('%s"\n' % indentspc)
+                else:
+                    # No item on first line
+                    newlines.append('%s " \\\n' % varset_start)
+                    for item in newvalue:
+                        newlines.append('%s%s \\\n' % (intentspc, item))
+                    newlines.append('%s"\n' % intentspc)
+            else:
+                newlines.append('%s "%s"\n' % (varset_start, newvalue))
+            return True
+        else:
+            # Put the old lines back where they were
+            newlines.extend(varlines)
+            return False
+
+    with open(meta_file, 'r') as f:
+        for line in f:
+            if in_var:
+                value = line.rstrip()
+                varlines.append(line)
+                full_value += value[:-1]
+                if value.endswith('"') or value.endswith("'"):
+                    full_value = full_value[:-1]
+                    if handle_var_end():
+                        updated = True
+                    in_var = None
+            else:
+                matched = False
+                for (varname, var_re) in var_res.iteritems():
+                    if var_re.match(line):
+                        splitvalue = line.split('"', 1)
+                        varset_start = splitvalue[0].rstrip()
+                        value = splitvalue[1].rstrip()
+                        if value.endswith('\\'):
+                            value = value[:-1]
+                        full_value = value
+                        varlines = [line]
+                        in_var = varname
+                        if value.endswith('"') or value.endswith("'"):
+                            full_value = full_value[:-1]
+                            if handle_var_end():
+                                updated = True
+                            in_var = None
+                        matched = True
+                        break
+                if not matched:
+                    newlines.append(line)
+    if updated:
+        with open(meta_file, 'w') as f:
+            f.writelines(newlines)
+
+def edit_bblayers_conf(bblayers_conf, add, remove):
+    """Edit bblayers.conf, adding and/or removing layers"""
+
+    import fnmatch
+
+    def remove_trailing_sep(pth):
+        if pth and pth[-1] == os.sep:
+            pth = pth[:-1]
+        return pth
+
+    def layerlist_param(value):
+        if not value:
+            return []
+        elif isinstance(value, list):
+            return [remove_trailing_sep(x) for x in value]
+        else:
+            return [remove_trailing_sep(value)]
+
+    notadded = []
+    notremoved = []
+
+    addlayers = layerlist_param(add)
+    removelayers = layerlist_param(remove)
+
+    # Need to use a list here because we can't set non-local variables from a callback in python 2.x
+    bblayercalls = []
+
+    def handle_bblayers(varname, origvalue):
+        bblayercalls.append(varname)
+        updated = False
+        bblayers = [remove_trailing_sep(x) for x in origvalue.split()]
+        if removelayers:
+            for removelayer in removelayers:
+                matched = False
+                for layer in bblayers:
+                    if fnmatch.fnmatch(layer, removelayer):
+                        updated = True
+                        matched = True
+                        bblayers.remove(layer)
+                        break
+                if not matched:
+                    notremoved.append(removelayer)
+        if addlayers:
+            for addlayer in addlayers:
+                if addlayer not in bblayers:
+                    updated = True
+                    bblayers.append(addlayer)
+                else:
+                    notadded.append(addlayer)
+
+        if updated:
+            return (bblayers, 2, False)
+        else:
+            return (origvalue, 2, False)
+
+    edit_metadata_file(bblayers_conf, ['BBLAYERS'], handle_bblayers)
+
+    if not bblayercalls:
+        raise Exception('Unable to find BBLAYERS in %s' % bblayers_conf)
+
+    return (notadded, notremoved)
+
+
+def get_file_layer(filename, d):
+    """Determine the collection (as defined by a layer's layer.conf file) containing the specified file"""
+    collections = (d.getVar('BBFILE_COLLECTIONS', True) or '').split()
+    collection_res = {}
+    for collection in collections:
+        collection_res[collection] = d.getVar('BBFILE_PATTERN_%s' % collection, True) or ''
+
+    # Use longest path so we handle nested layers
+    matchlen = 0
+    match = None
+    for collection, regex in collection_res.iteritems():
+        if len(regex) > matchlen and re.match(regex, filename):
+            matchlen = len(regex)
+            match = collection
+    return match

bitbake/lib/bs4/AUTHORS.txt

@@ -0,0 +1,43 @@
+Behold, mortal, the origins of Beautiful Soup...
+================================================
+
+Leonard Richardson is the primary programmer.
+
+Aaron DeVore is awesome.
+
+Mark Pilgrim provided the encoding detection code that forms the base
+of UnicodeDammit.
+
+Thomas Kluyver and Ezio Melotti finished the work of getting Beautiful
+Soup 4 working under Python 3.
+
+Simon Willison wrote soupselect, which was used to make Beautiful Soup
+support CSS selectors.
+
+Sam Ruby helped with a lot of edge cases.
+
+Jonathan Ellis was awarded the prestigous Beau Potage D'Or for his
+work in solving the nestable tags conundrum.
+
+An incomplete list of people have contributed patches to Beautiful
+Soup:
+
+ Istvan Albert, Andrew Lin, Anthony Baxter, Andrew Boyko, Tony Chang,
+ Zephyr Fang, Fuzzy, Roman Gaufman, Yoni Gilad, Richie Hindle, Peteris
+ Krumins, Kent Johnson, Ben Last, Robert Leftwich, Staffan Malmgren,
+ Ksenia Marasanova, JP Moins, Adam Monsen, John Nagle, "Jon", Ed
+ Oskiewicz, Greg Phillips, Giles Radford, Arthur Rudolph, Marko
+ Samastur, Jouni Sepp<70>nen, Alexander Schmolck, Andy Theyers, Glyn
+ Webster, Paul Wright, Danny Yoo
+
+An incomplete list of people who made suggestions or found bugs or
+found ways to break Beautiful Soup:
+
+ Hanno B<>ck, Matteo Bertini, Chris Curvey, Simon Cusack, Bruce Eckel,
+ Matt Ernst, Michael Foord, Tom Harris, Bill de hOra, Donald Howes,
+ Matt Patterson, Scott Roberts, Steve Strassmann, Mike Williams,
+ warchild at redho dot com, Sami Kuisma, Carlos Rocha, Bob Hutchison,
+ Joren Mc, Michal Migurski, John Kleven, Tim Heaney, Tripp Lilley, Ed
+ Summers, Dennis Sutch, Chris Smith, Aaron Sweep^W Swartz, Stuart
+ Turner, Greg Edwards, Kevin J Kalupson, Nikos Kouremenos, Artur de
+ Sousa Rocha, Yichun Wei, Per Vognsen

bitbake/lib/bs4/COPYING.txt

@@ -0,0 +1,26 @@
+Beautiful Soup is made available under the MIT license:
+
+ Copyright (c) 2004-2012 Leonard Richardson
+
+ Permission is hereby granted, free of charge, to any person obtaining
+ a copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to
+ permit persons to whom the Software is furnished to do so, subject to
+ the following conditions:
+
+ The above copyright notice and this permission notice shall be
+ included in all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ SOFTWARE, DAMMIT.
+
+Beautiful Soup incorporates code from the html5lib library, which is
+also made available under the MIT license.

bitbake/lib/bs4/__init__.py

@@ -0,0 +1,406 @@
+"""Beautiful Soup
+Elixir and Tonic
+"The Screen-Scraper's Friend"
+http://www.crummy.com/software/BeautifulSoup/
+
+Beautiful Soup uses a pluggable XML or HTML parser to parse a
+(possibly invalid) document into a tree representation. Beautiful Soup
+provides provides methods and Pythonic idioms that make it easy to
+navigate, search, and modify the parse tree.
+
+Beautiful Soup works with Python 2.6 and up. It works better if lxml
+and/or html5lib is installed.
+
+For more than you ever wanted to know about Beautiful Soup, see the
+documentation:
+http://www.crummy.com/software/BeautifulSoup/bs4/doc/
+"""
+
+__author__ = "Leonard Richardson (leonardr@segfault.org)"
+__version__ = "4.3.2"
+__copyright__ = "Copyright (c) 2004-2013 Leonard Richardson"
+__license__ = "MIT"
+
+__all__ = ['BeautifulSoup']
+
+import os
+import re
+import warnings
+
+from .builder import builder_registry, ParserRejectedMarkup
+from .dammit import UnicodeDammit
+from .element import (
+    CData,
+    Comment,
+    DEFAULT_OUTPUT_ENCODING,
+    Declaration,
+    Doctype,
+    NavigableString,
+    PageElement,
+    ProcessingInstruction,
+    ResultSet,
+    SoupStrainer,
+    Tag,
+    )
+
+# The very first thing we do is give a useful error if someone is
+# running this code under Python 3 without converting it.
+syntax_error = u'You are trying to run the Python 2 version of Beautiful Soup under Python 3. This will not work. You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).'
+
+class BeautifulSoup(Tag):
+    """
+    This class defines the basic interface called by the tree builders.
+
+    These methods will be called by the parser:
+      reset()
+      feed(markup)
+
+    The tree builder may call these methods from its feed() implementation:
+      handle_starttag(name, attrs) # See note about return value
+      handle_endtag(name)
+      handle_data(data) # Appends to the current data node
+      endData(containerClass=NavigableString) # Ends the current data node
+
+    No matter how complicated the underlying parser is, you should be
+    able to build a tree using 'start tag' events, 'end tag' events,
+    'data' events, and "done with data" events.
+
+    If you encounter an empty-element tag (aka a self-closing tag,
+    like HTML's <br> tag), call handle_starttag and then
+    handle_endtag.
+    """
+    ROOT_TAG_NAME = u'[document]'
+
+    # If the end-user gives no indication which tree builder they
+    # want, look for one with these features.
+    DEFAULT_BUILDER_FEATURES = ['html', 'fast']
+
+    ASCII_SPACES = '\x20\x0a\x09\x0c\x0d'
+
+    def __init__(self, markup="", features=None, builder=None,
+                 parse_only=None, from_encoding=None, **kwargs):
+        """The Soup object is initialized as the 'root tag', and the
+        provided markup (which can be a string or a file-like object)
+        is fed into the underlying parser."""
+
+        if 'convertEntities' in kwargs:
+            warnings.warn(
+                "BS4 does not respect the convertEntities argument to the "
+                "BeautifulSoup constructor. Entities are always converted "
+                "to Unicode characters.")
+
+        if 'markupMassage' in kwargs:
+            del kwargs['markupMassage']
+            warnings.warn(
+                "BS4 does not respect the markupMassage argument to the "
+                "BeautifulSoup constructor. The tree builder is responsible "
+                "for any necessary markup massage.")
+
+        if 'smartQuotesTo' in kwargs:
+            del kwargs['smartQuotesTo']
+            warnings.warn(
+                "BS4 does not respect the smartQuotesTo argument to the "
+                "BeautifulSoup constructor. Smart quotes are always converted "
+                "to Unicode characters.")
+
+        if 'selfClosingTags' in kwargs:
+            del kwargs['selfClosingTags']
+            warnings.warn(
+                "BS4 does not respect the selfClosingTags argument to the "
+                "BeautifulSoup constructor. The tree builder is responsible "
+                "for understanding self-closing tags.")
+
+        if 'isHTML' in kwargs:
+            del kwargs['isHTML']
+            warnings.warn(
+                "BS4 does not respect the isHTML argument to the "
+                "BeautifulSoup constructor. You can pass in features='html' "
+                "or features='xml' to get a builder capable of handling "
+                "one or the other.")
+
+        def deprecated_argument(old_name, new_name):
+            if old_name in kwargs:
+                warnings.warn(
+                    'The "%s" argument to the BeautifulSoup constructor '
+                    'has been renamed to "%s."' % (old_name, new_name))
+                value = kwargs[old_name]
+                del kwargs[old_name]
+                return value
+            return None
+
+        parse_only = parse_only or deprecated_argument(
+            "parseOnlyThese", "parse_only")
+
+        from_encoding = from_encoding or deprecated_argument(
+            "fromEncoding", "from_encoding")
+
+        if len(kwargs) > 0:
+            arg = kwargs.keys().pop()
+            raise TypeError(
+                "__init__() got an unexpected keyword argument '%s'" % arg)
+
+        if builder is None:
+            if isinstance(features, basestring):
+                features = [features]
+            if features is None or len(features) == 0:
+                features = self.DEFAULT_BUILDER_FEATURES
+            builder_class = builder_registry.lookup(*features)
+            if builder_class is None:
+                raise FeatureNotFound(
+                    "Couldn't find a tree builder with the features you "
+                    "requested: %s. Do you need to install a parser library?"
+                    % ",".join(features))
+            builder = builder_class()
+        self.builder = builder
+        self.is_xml = builder.is_xml
+        self.builder.soup = self
+
+        self.parse_only = parse_only
+
+        if hasattr(markup, 'read'):        # It's a file-type object.
+            markup = markup.read()
+        elif len(markup) <= 256:
+            # Print out warnings for a couple beginner problems
+            # involving passing non-markup to Beautiful Soup.
+            # Beautiful Soup will still parse the input as markup,
+            # just in case that's what the user really wants.
+            if (isinstance(markup, unicode)
+                and not os.path.supports_unicode_filenames):
+                possible_filename = markup.encode("utf8")
+            else:
+                possible_filename = markup
+            is_file = False
+            try:
+                is_file = os.path.exists(possible_filename)
+            except Exception, e:
+                # This is almost certainly a problem involving
+                # characters not valid in filenames on this
+                # system. Just let it go.
+                pass
+            if is_file:
+                warnings.warn(
+                    '"%s" looks like a filename, not markup. You should probably open this file and pass the filehandle into Beautiful Soup.' % markup)
+            if markup[:5] == "http:" or markup[:6] == "https:":
+                # TODO: This is ugly but I couldn't get it to work in
+                # Python 3 otherwise.
+                if ((isinstance(markup, bytes) and not b' ' in markup)
+                    or (isinstance(markup, unicode) and not u' ' in markup)):
+                    warnings.warn(
+                        '"%s" looks like a URL. Beautiful Soup is not an HTTP client. You should probably use an HTTP client to get the document behind the URL, and feed that document to Beautiful Soup.' % markup)
+
+        for (self.markup, self.original_encoding, self.declared_html_encoding,
+         self.contains_replacement_characters) in (
+            self.builder.prepare_markup(markup, from_encoding)):
+            self.reset()
+            try:
+                self._feed()
+                break
+            except ParserRejectedMarkup:
+                pass
+
+        # Clear out the markup and remove the builder's circular
+        # reference to this object.
+        self.markup = None
+        self.builder.soup = None
+
+    def _feed(self):
+        # Convert the document to Unicode.
+        self.builder.reset()
+
+        self.builder.feed(self.markup)
+        # Close out any unfinished strings and close all the open tags.
+        self.endData()
+        while self.currentTag.name != self.ROOT_TAG_NAME:
+            self.popTag()
+
+    def reset(self):
+        Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME)
+        self.hidden = 1
+        self.builder.reset()
+        self.current_data = []
+        self.currentTag = None
+        self.tagStack = []
+        self.preserve_whitespace_tag_stack = []
+        self.pushTag(self)
+
+    def new_tag(self, name, namespace=None, nsprefix=None, **attrs):
+        """Create a new tag associated with this soup."""
+        return Tag(None, self.builder, name, namespace, nsprefix, attrs)
+
+    def new_string(self, s, subclass=NavigableString):
+        """Create a new NavigableString associated with this soup."""
+        navigable = subclass(s)
+        navigable.setup()
+        return navigable
+
+    def insert_before(self, successor):
+        raise NotImplementedError("BeautifulSoup objects don't support insert_before().")
+
+    def insert_after(self, successor):
+        raise NotImplementedError("BeautifulSoup objects don't support insert_after().")
+
+    def popTag(self):
+        tag = self.tagStack.pop()
+        if self.preserve_whitespace_tag_stack and tag == self.preserve_whitespace_tag_stack[-1]:
+            self.preserve_whitespace_tag_stack.pop()
+        #print "Pop", tag.name
+        if self.tagStack:
+            self.currentTag = self.tagStack[-1]
+        return self.currentTag
+
+    def pushTag(self, tag):
+        #print "Push", tag.name
+        if self.currentTag:
+            self.currentTag.contents.append(tag)
+        self.tagStack.append(tag)
+        self.currentTag = self.tagStack[-1]
+        if tag.name in self.builder.preserve_whitespace_tags:
+            self.preserve_whitespace_tag_stack.append(tag)
+
+    def endData(self, containerClass=NavigableString):
+        if self.current_data:
+            current_data = u''.join(self.current_data)
+            # If whitespace is not preserved, and this string contains
+            # nothing but ASCII spaces, replace it with a single space
+            # or newline.
+            if not self.preserve_whitespace_tag_stack:
+                strippable = True
+                for i in current_data:
+                    if i not in self.ASCII_SPACES:
+                        strippable = False
+                        break
+                if strippable:
+                    if '\n' in current_data:
+                        current_data = '\n'
+                    else:
+                        current_data = ' '
+
+            # Reset the data collector.
+            self.current_data = []
+
+            # Should we add this string to the tree at all?
+            if self.parse_only and len(self.tagStack) <= 1 and \
+                   (not self.parse_only.text or \
+                    not self.parse_only.search(current_data)):
+                return
+
+            o = containerClass(current_data)
+            self.object_was_parsed(o)
+
+    def object_was_parsed(self, o, parent=None, most_recent_element=None):
+        """Add an object to the parse tree."""
+        parent = parent or self.currentTag
+        most_recent_element = most_recent_element or self._most_recent_element
+        o.setup(parent, most_recent_element)
+
+        if most_recent_element is not None:
+            most_recent_element.next_element = o
+        self._most_recent_element = o
+        parent.contents.append(o)
+
+    def _popToTag(self, name, nsprefix=None, inclusivePop=True):
+        """Pops the tag stack up to and including the most recent
+        instance of the given tag. If inclusivePop is false, pops the tag
+        stack up to but *not* including the most recent instqance of
+        the given tag."""
+        #print "Popping to %s" % name
+        if name == self.ROOT_TAG_NAME:
+            # The BeautifulSoup object itself can never be popped.
+            return
+
+        most_recently_popped = None
+
+        stack_size = len(self.tagStack)
+        for i in range(stack_size - 1, 0, -1):
+            t = self.tagStack[i]
+            if (name == t.name and nsprefix == t.prefix):
+                if inclusivePop:
+                    most_recently_popped = self.popTag()
+                break
+            most_recently_popped = self.popTag()
+
+        return most_recently_popped
+
+    def handle_starttag(self, name, namespace, nsprefix, attrs):
+        """Push a start tag on to the stack.
+
+        If this method returns None, the tag was rejected by the
+        SoupStrainer. You should proceed as if the tag had not occured
+        in the document. For instance, if this was a self-closing tag,
+        don't call handle_endtag.
+        """
+
+        # print "Start tag %s: %s" % (name, attrs)
+        self.endData()
+
+        if (self.parse_only and len(self.tagStack) <= 1
+            and (self.parse_only.text
+                 or not self.parse_only.search_tag(name, attrs))):
+            return None
+
+        tag = Tag(self, self.builder, name, namespace, nsprefix, attrs,
+                  self.currentTag, self._most_recent_element)
+        if tag is None:
+            return tag
+        if self._most_recent_element:
+            self._most_recent_element.next_element = tag
+        self._most_recent_element = tag
+        self.pushTag(tag)
+        return tag
+
+    def handle_endtag(self, name, nsprefix=None):
+        #print "End tag: " + name
+        self.endData()
+        self._popToTag(name, nsprefix)
+
+    def handle_data(self, data):
+        self.current_data.append(data)
+
+    def decode(self, pretty_print=False,
+               eventual_encoding=DEFAULT_OUTPUT_ENCODING,
+               formatter="minimal"):
+        """Returns a string or Unicode representation of this document.
+        To get Unicode, pass None for encoding."""
+
+        if self.is_xml:
+            # Print the XML declaration
+            encoding_part = ''
+            if eventual_encoding != None:
+                encoding_part = ' encoding="%s"' % eventual_encoding
+            prefix = u'<?xml version="1.0"%s?>\n' % encoding_part
+        else:
+            prefix = u''
+        if not pretty_print:
+            indent_level = None
+        else:
+            indent_level = 0
+        return prefix + super(BeautifulSoup, self).decode(
+            indent_level, eventual_encoding, formatter)
+
+# Alias to make it easier to type import: 'from bs4 import _soup'
+_s = BeautifulSoup
+_soup = BeautifulSoup
+
+class BeautifulStoneSoup(BeautifulSoup):
+    """Deprecated interface to an XML parser."""
+
+    def __init__(self, *args, **kwargs):
+        kwargs['features'] = 'xml'
+        warnings.warn(
+            'The BeautifulStoneSoup class is deprecated. Instead of using '
+            'it, pass features="xml" into the BeautifulSoup constructor.')
+        super(BeautifulStoneSoup, self).__init__(*args, **kwargs)
+
+
+class StopParsing(Exception):
+    pass
+
+class FeatureNotFound(ValueError):
+    pass
+
+
+#By default, act as an HTML pretty-printer.
+if __name__ == '__main__':
+    import sys
+    soup = BeautifulSoup(sys.stdin)
+    print soup.prettify()

bitbake/lib/bs4/builder/__init__.py

@@ -0,0 +1,321 @@
+from collections import defaultdict
+import itertools
+import sys
+from bs4.element import (
+    CharsetMetaAttributeValue,
+    ContentMetaAttributeValue,
+    whitespace_re
+    )
+
+__all__ = [
+    'HTMLTreeBuilder',
+    'SAXTreeBuilder',
+    'TreeBuilder',
+    'TreeBuilderRegistry',
+    ]
+
+# Some useful features for a TreeBuilder to have.
+FAST = 'fast'
+PERMISSIVE = 'permissive'
+STRICT = 'strict'
+XML = 'xml'
+HTML = 'html'
+HTML_5 = 'html5'
+
+
+class TreeBuilderRegistry(object):
+
+    def __init__(self):
+        self.builders_for_feature = defaultdict(list)
+        self.builders = []
+
+    def register(self, treebuilder_class):
+        """Register a treebuilder based on its advertised features."""
+        for feature in treebuilder_class.features:
+            self.builders_for_feature[feature].insert(0, treebuilder_class)
+        self.builders.insert(0, treebuilder_class)
+
+    def lookup(self, *features):
+        if len(self.builders) == 0:
+            # There are no builders at all.
+            return None
+
+        if len(features) == 0:
+            # They didn't ask for any features. Give them the most
+            # recently registered builder.
+            return self.builders[0]
+
+        # Go down the list of features in order, and eliminate any builders
+        # that don't match every feature.
+        features = list(features)
+        features.reverse()
+        candidates = None
+        candidate_set = None
+        while len(features) > 0:
+            feature = features.pop()
+            we_have_the_feature = self.builders_for_feature.get(feature, [])
+            if len(we_have_the_feature) > 0:
+                if candidates is None:
+                    candidates = we_have_the_feature
+                    candidate_set = set(candidates)
+                else:
+                    # Eliminate any candidates that don't have this feature.
+                    candidate_set = candidate_set.intersection(
+                        set(we_have_the_feature))
+
+        # The only valid candidates are the ones in candidate_set.
+        # Go through the original list of candidates and pick the first one
+        # that's in candidate_set.
+        if candidate_set is None:
+            return None
+        for candidate in candidates:
+            if candidate in candidate_set:
+                return candidate
+        return None
+
+# The BeautifulSoup class will take feature lists from developers and use them
+# to look up builders in this registry.
+builder_registry = TreeBuilderRegistry()
+
+class TreeBuilder(object):
+    """Turn a document into a Beautiful Soup object tree."""
+
+    features = []
+
+    is_xml = False
+    preserve_whitespace_tags = set()
+    empty_element_tags = None # A tag will be considered an empty-element
+                              # tag when and only when it has no contents.
+
+    # A value for these tag/attribute combinations is a space- or
+    # comma-separated list of CDATA, rather than a single CDATA.
+    cdata_list_attributes = {}
+
+
+    def __init__(self):
+        self.soup = None
+
+    def reset(self):
+        pass
+
+    def can_be_empty_element(self, tag_name):
+        """Might a tag with this name be an empty-element tag?
+
+        The final markup may or may not actually present this tag as
+        self-closing.
+
+        For instance: an HTMLBuilder does not consider a <p> tag to be
+        an empty-element tag (it's not in
+        HTMLBuilder.empty_element_tags). This means an empty <p> tag
+        will be presented as "<p></p>", not "<p />".
+
+        The default implementation has no opinion about which tags are
+        empty-element tags, so a tag will be presented as an
+        empty-element tag if and only if it has no contents.
+        "<foo></foo>" will become "<foo />", and "<foo>bar</foo>" will
+        be left alone.
+        """
+        if self.empty_element_tags is None:
+            return True
+        return tag_name in self.empty_element_tags
+
+    def feed(self, markup):
+        raise NotImplementedError()
+
+    def prepare_markup(self, markup, user_specified_encoding=None,
+                       document_declared_encoding=None):
+        return markup, None, None, False
+
+    def test_fragment_to_document(self, fragment):
+        """Wrap an HTML fragment to make it look like a document.
+
+        Different parsers do this differently. For instance, lxml
+        introduces an empty <head> tag, and html5lib
+        doesn't. Abstracting this away lets us write simple tests
+        which run HTML fragments through the parser and compare the
+        results against other HTML fragments.
+
+        This method should not be used outside of tests.
+        """
+        return fragment
+
+    def set_up_substitutions(self, tag):
+        return False
+
+    def _replace_cdata_list_attribute_values(self, tag_name, attrs):
+        """Replaces class="foo bar" with class=["foo", "bar"]
+
+        Modifies its input in place.
+        """
+        if not attrs:
+            return attrs
+        if self.cdata_list_attributes:
+            universal = self.cdata_list_attributes.get('*', [])
+            tag_specific = self.cdata_list_attributes.get(
+                tag_name.lower(), None)
+            for attr in attrs.keys():
+                if attr in universal or (tag_specific and attr in tag_specific):
+                    # We have a "class"-type attribute whose string
+                    # value is a whitespace-separated list of
+                    # values. Split it into a list.
+                    value = attrs[attr]
+                    if isinstance(value, basestring):
+                        values = whitespace_re.split(value)
+                    else:
+                        # html5lib sometimes calls setAttributes twice
+                        # for the same tag when rearranging the parse
+                        # tree. On the second call the attribute value
+                        # here is already a list.  If this happens,
+                        # leave the value alone rather than trying to
+                        # split it again.
+                        values = value
+                    attrs[attr] = values
+        return attrs
+
+class SAXTreeBuilder(TreeBuilder):
+    """A Beautiful Soup treebuilder that listens for SAX events."""
+
+    def feed(self, markup):
+        raise NotImplementedError()
+
+    def close(self):
+        pass
+
+    def startElement(self, name, attrs):
+        attrs = dict((key[1], value) for key, value in list(attrs.items()))
+        #print "Start %s, %r" % (name, attrs)
+        self.soup.handle_starttag(name, attrs)
+
+    def endElement(self, name):
+        #print "End %s" % name
+        self.soup.handle_endtag(name)
+
+    def startElementNS(self, nsTuple, nodeName, attrs):
+        # Throw away (ns, nodeName) for now.
+        self.startElement(nodeName, attrs)
+
+    def endElementNS(self, nsTuple, nodeName):
+        # Throw away (ns, nodeName) for now.
+        self.endElement(nodeName)
+        #handler.endElementNS((ns, node.nodeName), node.nodeName)
+
+    def startPrefixMapping(self, prefix, nodeValue):
+        # Ignore the prefix for now.
+        pass
+
+    def endPrefixMapping(self, prefix):
+        # Ignore the prefix for now.
+        # handler.endPrefixMapping(prefix)
+        pass
+
+    def characters(self, content):
+        self.soup.handle_data(content)
+
+    def startDocument(self):
+        pass
+
+    def endDocument(self):
+        pass
+
+
+class HTMLTreeBuilder(TreeBuilder):
+    """This TreeBuilder knows facts about HTML.
+
+    Such as which tags are empty-element tags.
+    """
+
+    preserve_whitespace_tags = set(['pre', 'textarea'])
+    empty_element_tags = set(['br' , 'hr', 'input', 'img', 'meta',
+                              'spacer', 'link', 'frame', 'base'])
+
+    # The HTML standard defines these attributes as containing a
+    # space-separated list of values, not a single value. That is,
+    # class="foo bar" means that the 'class' attribute has two values,
+    # 'foo' and 'bar', not the single value 'foo bar'.  When we
+    # encounter one of these attributes, we will parse its value into
+    # a list of values if possible. Upon output, the list will be
+    # converted back into a string.
+    cdata_list_attributes = {
+        "*" : ['class', 'accesskey', 'dropzone'],
+        "a" : ['rel', 'rev'],
+        "link" :  ['rel', 'rev'],
+        "td" : ["headers"],
+        "th" : ["headers"],
+        "td" : ["headers"],
+        "form" : ["accept-charset"],
+        "object" : ["archive"],
+
+        # These are HTML5 specific, as are *.accesskey and *.dropzone above.
+        "area" : ["rel"],
+        "icon" : ["sizes"],
+        "iframe" : ["sandbox"],
+        "output" : ["for"],
+        }
+
+    def set_up_substitutions(self, tag):
+        # We are only interested in <meta> tags
+        if tag.name != 'meta':
+            return False
+
+        http_equiv = tag.get('http-equiv')
+        content = tag.get('content')
+        charset = tag.get('charset')
+
+        # We are interested in <meta> tags that say what encoding the
+        # document was originally in. This means HTML 5-style <meta>
+        # tags that provide the "charset" attribute. It also means
+        # HTML 4-style <meta> tags that provide the "content"
+        # attribute and have "http-equiv" set to "content-type".
+        #
+        # In both cases we will replace the value of the appropriate
+        # attribute with a standin object that can take on any
+        # encoding.
+        meta_encoding = None
+        if charset is not None:
+            # HTML 5 style:
+            # <meta charset="utf8">
+            meta_encoding = charset
+            tag['charset'] = CharsetMetaAttributeValue(charset)
+
+        elif (content is not None and http_equiv is not None
+              and http_equiv.lower() == 'content-type'):
+            # HTML 4 style:
+            # <meta http-equiv="content-type" content="text/html; charset=utf8">
+            tag['content'] = ContentMetaAttributeValue(content)
+
+        return (meta_encoding is not None)
+
+def register_treebuilders_from(module):
+    """Copy TreeBuilders from the given module into this module."""
+    # I'm fairly sure this is not the best way to do this.
+    this_module = sys.modules['bs4.builder']
+    for name in module.__all__:
+        obj = getattr(module, name)
+
+        if issubclass(obj, TreeBuilder):
+            setattr(this_module, name, obj)
+            this_module.__all__.append(name)
+            # Register the builder while we're at it.
+            this_module.builder_registry.register(obj)
+
+class ParserRejectedMarkup(Exception):
+    pass
+
+# Builders are registered in reverse order of priority, so that custom
+# builder registrations will take precedence. In general, we want lxml
+# to take precedence over html5lib, because it's faster. And we only
+# want to use HTMLParser as a last result.
+from . import _htmlparser
+register_treebuilders_from(_htmlparser)
+try:
+    from . import _html5lib
+    register_treebuilders_from(_html5lib)
+except ImportError:
+    # They don't have html5lib installed.
+    pass
+try:
+    from . import _lxml
+    register_treebuilders_from(_lxml)
+except ImportError:
+    # They don't have lxml installed.
+    pass

bitbake/lib/bs4/builder/_html5lib.py

@@ -0,0 +1,285 @@
+__all__ = [
+    'HTML5TreeBuilder',
+    ]
+
+import warnings
+from bs4.builder import (
+    PERMISSIVE,
+    HTML,
+    HTML_5,
+    HTMLTreeBuilder,
+    )
+from bs4.element import NamespacedAttribute
+import html5lib
+from html5lib.constants import namespaces
+from bs4.element import (
+    Comment,
+    Doctype,
+    NavigableString,
+    Tag,
+    )
+
+class HTML5TreeBuilder(HTMLTreeBuilder):
+    """Use html5lib to build a tree."""
+
+    features = ['html5lib', PERMISSIVE, HTML_5, HTML]
+
+    def prepare_markup(self, markup, user_specified_encoding):
+        # Store the user-specified encoding for use later on.
+        self.user_specified_encoding = user_specified_encoding
+        yield (markup, None, None, False)
+
+    # These methods are defined by Beautiful Soup.
+    def feed(self, markup):
+        if self.soup.parse_only is not None:
+            warnings.warn("You provided a value for parse_only, but the html5lib tree builder doesn't support parse_only. The entire document will be parsed.")
+        parser = html5lib.HTMLParser(tree=self.create_treebuilder)
+        doc = parser.parse(markup, encoding=self.user_specified_encoding)
+
+        # Set the character encoding detected by the tokenizer.
+        if isinstance(markup, unicode):
+            # We need to special-case this because html5lib sets
+            # charEncoding to UTF-8 if it gets Unicode input.
+            doc.original_encoding = None
+        else:
+            doc.original_encoding = parser.tokenizer.stream.charEncoding[0]
+
+    def create_treebuilder(self, namespaceHTMLElements):
+        self.underlying_builder = TreeBuilderForHtml5lib(
+            self.soup, namespaceHTMLElements)
+        return self.underlying_builder
+
+    def test_fragment_to_document(self, fragment):
+        """See `TreeBuilder`."""
+        return u'<html><head></head><body>%s</body></html>' % fragment
+
+
+class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder):
+
+    def __init__(self, soup, namespaceHTMLElements):
+        self.soup = soup
+        super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
+
+    def documentClass(self):
+        self.soup.reset()
+        return Element(self.soup, self.soup, None)
+
+    def insertDoctype(self, token):
+        name = token["name"]
+        publicId = token["publicId"]
+        systemId = token["systemId"]
+
+        doctype = Doctype.for_name_and_ids(name, publicId, systemId)
+        self.soup.object_was_parsed(doctype)
+
+    def elementClass(self, name, namespace):
+        tag = self.soup.new_tag(name, namespace)
+        return Element(tag, self.soup, namespace)
+
+    def commentClass(self, data):
+        return TextNode(Comment(data), self.soup)
+
+    def fragmentClass(self):
+        self.soup = BeautifulSoup("")
+        self.soup.name = "[document_fragment]"
+        return Element(self.soup, self.soup, None)
+
+    def appendChild(self, node):
+        # XXX This code is not covered by the BS4 tests.
+        self.soup.append(node.element)
+
+    def getDocument(self):
+        return self.soup
+
+    def getFragment(self):
+        return html5lib.treebuilders._base.TreeBuilder.getFragment(self).element
+
+class AttrList(object):
+    def __init__(self, element):
+        self.element = element
+        self.attrs = dict(self.element.attrs)
+    def __iter__(self):
+        return list(self.attrs.items()).__iter__()
+    def __setitem__(self, name, value):
+        "set attr", name, value
+        self.element[name] = value
+    def items(self):
+        return list(self.attrs.items())
+    def keys(self):
+        return list(self.attrs.keys())
+    def __len__(self):
+        return len(self.attrs)
+    def __getitem__(self, name):
+        return self.attrs[name]
+    def __contains__(self, name):
+        return name in list(self.attrs.keys())
+
+
+class Element(html5lib.treebuilders._base.Node):
+    def __init__(self, element, soup, namespace):
+        html5lib.treebuilders._base.Node.__init__(self, element.name)
+        self.element = element
+        self.soup = soup
+        self.namespace = namespace
+
+    def appendChild(self, node):
+        string_child = child = None
+        if isinstance(node, basestring):
+            # Some other piece of code decided to pass in a string
+            # instead of creating a TextElement object to contain the
+            # string.
+            string_child = child = node
+        elif isinstance(node, Tag):
+            # Some other piece of code decided to pass in a Tag
+            # instead of creating an Element object to contain the
+            # Tag.
+            child = node
+        elif node.element.__class__ == NavigableString:
+            string_child = child = node.element
+        else:
+            child = node.element
+
+        if not isinstance(child, basestring) and child.parent is not None:
+            node.element.extract()
+
+        if (string_child and self.element.contents
+            and self.element.contents[-1].__class__ == NavigableString):
+            # We are appending a string onto another string.
+            # TODO This has O(n^2) performance, for input like
+            # "a</a>a</a>a</a>..."
+            old_element = self.element.contents[-1]
+            new_element = self.soup.new_string(old_element + string_child)
+            old_element.replace_with(new_element)
+            self.soup._most_recent_element = new_element
+        else:
+            if isinstance(node, basestring):
+                # Create a brand new NavigableString from this string.
+                child = self.soup.new_string(node)
+
+            # Tell Beautiful Soup to act as if it parsed this element
+            # immediately after the parent's last descendant. (Or
+            # immediately after the parent, if it has no children.)
+            if self.element.contents:
+                most_recent_element = self.element._last_descendant(False)
+            else:
+                most_recent_element = self.element
+
+            self.soup.object_was_parsed(
+                child, parent=self.element,
+                most_recent_element=most_recent_element)
+
+    def getAttributes(self):
+        return AttrList(self.element)
+
+    def setAttributes(self, attributes):
+        if attributes is not None and len(attributes) > 0:
+
+            converted_attributes = []
+            for name, value in list(attributes.items()):
+                if isinstance(name, tuple):
+                    new_name = NamespacedAttribute(*name)
+                    del attributes[name]
+                    attributes[new_name] = value
+
+            self.soup.builder._replace_cdata_list_attribute_values(
+                self.name, attributes)
+            for name, value in attributes.items():
+                self.element[name] = value
+
+            # The attributes may contain variables that need substitution.
+            # Call set_up_substitutions manually.
+            #
+            # The Tag constructor called this method when the Tag was created,
+            # but we just set/changed the attributes, so call it again.
+            self.soup.builder.set_up_substitutions(self.element)
+    attributes = property(getAttributes, setAttributes)
+
+    def insertText(self, data, insertBefore=None):
+        if insertBefore:
+            text = TextNode(self.soup.new_string(data), self.soup)
+            self.insertBefore(data, insertBefore)
+        else:
+            self.appendChild(data)
+
+    def insertBefore(self, node, refNode):
+        index = self.element.index(refNode.element)
+        if (node.element.__class__ == NavigableString and self.element.contents
+            and self.element.contents[index-1].__class__ == NavigableString):
+            # (See comments in appendChild)
+            old_node = self.element.contents[index-1]
+            new_str = self.soup.new_string(old_node + node.element)
+            old_node.replace_with(new_str)
+        else:
+            self.element.insert(index, node.element)
+            node.parent = self
+
+    def removeChild(self, node):
+        node.element.extract()
+
+    def reparentChildren(self, new_parent):
+        """Move all of this tag's children into another tag."""
+        element = self.element
+        new_parent_element = new_parent.element
+        # Determine what this tag's next_element will be once all the children
+        # are removed.
+        final_next_element = element.next_sibling
+
+        new_parents_last_descendant = new_parent_element._last_descendant(False, False)
+        if len(new_parent_element.contents) > 0:
+            # The new parent already contains children. We will be
+            # appending this tag's children to the end.
+            new_parents_last_child = new_parent_element.contents[-1]
+            new_parents_last_descendant_next_element = new_parents_last_descendant.next_element
+        else:
+            # The new parent contains no children.
+            new_parents_last_child = None
+            new_parents_last_descendant_next_element = new_parent_element.next_element
+
+        to_append = element.contents
+        append_after = new_parent.element.contents
+        if len(to_append) > 0:
+            # Set the first child's previous_element and previous_sibling
+            # to elements within the new parent
+            first_child = to_append[0]
+            first_child.previous_element = new_parents_last_descendant
+            first_child.previous_sibling = new_parents_last_child
+
+            # Fix the last child's next_element and next_sibling
+            last_child = to_append[-1]
+            last_child.next_element = new_parents_last_descendant_next_element
+            last_child.next_sibling = None
+
+        for child in to_append:
+            child.parent = new_parent_element
+            new_parent_element.contents.append(child)
+
+        # Now that this element has no children, change its .next_element.
+        element.contents = []
+        element.next_element = final_next_element
+
+    def cloneNode(self):
+        tag = self.soup.new_tag(self.element.name, self.namespace)
+        node = Element(tag, self.soup, self.namespace)
+        for key,value in self.attributes:
+            node.attributes[key] = value
+        return node
+
+    def hasContent(self):
+        return self.element.contents
+
+    def getNameTuple(self):
+        if self.namespace == None:
+            return namespaces["html"], self.name
+        else:
+            return self.namespace, self.name
+
+    nameTuple = property(getNameTuple)
+
+class TextNode(Element):
+    def __init__(self, element, soup):
+        html5lib.treebuilders._base.Node.__init__(self, None)
+        self.element = element
+        self.soup = soup
+
+    def cloneNode(self):
+        raise NotImplementedError

bitbake/lib/bs4/builder/_htmlparser.py

@@ -0,0 +1,258 @@
+"""Use the HTMLParser library to parse HTML files that aren't too bad."""
+
+__all__ = [
+    'HTMLParserTreeBuilder',
+    ]
+
+from HTMLParser import (
+    HTMLParser,
+    HTMLParseError,
+    )
+import sys
+import warnings
+
+# Starting in Python 3.2, the HTMLParser constructor takes a 'strict'
+# argument, which we'd like to set to False. Unfortunately,
+# http://bugs.python.org/issue13273 makes strict=True a better bet
+# before Python 3.2.3.
+#
+# At the end of this file, we monkeypatch HTMLParser so that
+# strict=True works well on Python 3.2.2.
+major, minor, release = sys.version_info[:3]
+CONSTRUCTOR_TAKES_STRICT = (
+    major > 3
+    or (major == 3 and minor > 2)
+    or (major == 3 and minor == 2 and release >= 3))
+
+from bs4.element import (
+    CData,
+    Comment,
+    Declaration,
+    Doctype,
+    ProcessingInstruction,
+    )
+from bs4.dammit import EntitySubstitution, UnicodeDammit
+
+from bs4.builder import (
+    HTML,
+    HTMLTreeBuilder,
+    STRICT,
+    )
+
+
+HTMLPARSER = 'html.parser'
+
+class BeautifulSoupHTMLParser(HTMLParser):
+    def handle_starttag(self, name, attrs):
+        # XXX namespace
+        attr_dict = {}
+        for key, value in attrs:
+            # Change None attribute values to the empty string
+            # for consistency with the other tree builders.
+            if value is None:
+                value = ''
+            attr_dict[key] = value
+            attrvalue = '""'
+        self.soup.handle_starttag(name, None, None, attr_dict)
+
+    def handle_endtag(self, name):
+        self.soup.handle_endtag(name)
+
+    def handle_data(self, data):
+        self.soup.handle_data(data)
+
+    def handle_charref(self, name):
+        # XXX workaround for a bug in HTMLParser. Remove this once
+        # it's fixed.
+        if name.startswith('x'):
+            real_name = int(name.lstrip('x'), 16)
+        elif name.startswith('X'):
+            real_name = int(name.lstrip('X'), 16)
+        else:
+            real_name = int(name)
+
+        try:
+            data = unichr(real_name)
+        except (ValueError, OverflowError), e:
+            data = u"\N{REPLACEMENT CHARACTER}"
+
+        self.handle_data(data)
+
+    def handle_entityref(self, name):
+        character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
+        if character is not None:
+            data = character
+        else:
+            data = "&%s;" % name
+        self.handle_data(data)
+
+    def handle_comment(self, data):
+        self.soup.endData()
+        self.soup.handle_data(data)
+        self.soup.endData(Comment)
+
+    def handle_decl(self, data):
+        self.soup.endData()
+        if data.startswith("DOCTYPE "):
+            data = data[len("DOCTYPE "):]
+        elif data == 'DOCTYPE':
+            # i.e. "<!DOCTYPE>"
+            data = ''
+        self.soup.handle_data(data)
+        self.soup.endData(Doctype)
+
+    def unknown_decl(self, data):
+        if data.upper().startswith('CDATA['):
+            cls = CData
+            data = data[len('CDATA['):]
+        else:
+            cls = Declaration
+        self.soup.endData()
+        self.soup.handle_data(data)
+        self.soup.endData(cls)
+
+    def handle_pi(self, data):
+        self.soup.endData()
+        if data.endswith("?") and data.lower().startswith("xml"):
+            # "An XHTML processing instruction using the trailing '?'
+            # will cause the '?' to be included in data." - HTMLParser
+            # docs.
+            #
+            # Strip the question mark so we don't end up with two
+            # question marks.
+            data = data[:-1]
+        self.soup.handle_data(data)
+        self.soup.endData(ProcessingInstruction)
+
+
+class HTMLParserTreeBuilder(HTMLTreeBuilder):
+
+    is_xml = False
+    features = [HTML, STRICT, HTMLPARSER]
+
+    def __init__(self, *args, **kwargs):
+        if CONSTRUCTOR_TAKES_STRICT:
+            kwargs['strict'] = False
+        self.parser_args = (args, kwargs)
+
+    def prepare_markup(self, markup, user_specified_encoding=None,
+                       document_declared_encoding=None):
+        """
+        :return: A 4-tuple (markup, original encoding, encoding
+        declared within markup, whether any characters had to be
+        replaced with REPLACEMENT CHARACTER).
+        """
+        if isinstance(markup, unicode):
+            yield (markup, None, None, False)
+            return
+
+        try_encodings = [user_specified_encoding, document_declared_encoding]
+        dammit = UnicodeDammit(markup, try_encodings, is_html=True)
+        yield (dammit.markup, dammit.original_encoding,
+               dammit.declared_html_encoding,
+               dammit.contains_replacement_characters)
+
+    def feed(self, markup):
+        args, kwargs = self.parser_args
+        parser = BeautifulSoupHTMLParser(*args, **kwargs)
+        parser.soup = self.soup
+        try:
+            parser.feed(markup)
+        except HTMLParseError, e:
+            warnings.warn(RuntimeWarning(
+                "Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
+            raise e
+
+# Patch 3.2 versions of HTMLParser earlier than 3.2.3 to use some
+# 3.2.3 code. This ensures they don't treat markup like <p></p> as a
+# string.
+#
+# XXX This code can be removed once most Python 3 users are on 3.2.3.
+if major == 3 and minor == 2 and not CONSTRUCTOR_TAKES_STRICT:
+    import re
+    attrfind_tolerant = re.compile(
+        r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
+        r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
+    HTMLParserTreeBuilder.attrfind_tolerant = attrfind_tolerant
+
+    locatestarttagend = re.compile(r"""
+  <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
+  (?:\s+                             # whitespace before attribute name
+    (?:[a-zA-Z_][-.:a-zA-Z0-9_]*     # attribute name
+      (?:\s*=\s*                     # value indicator
+        (?:'[^']*'                   # LITA-enclosed value
+          |\"[^\"]*\"                # LIT-enclosed value
+          |[^'\">\s]+                # bare value
+         )
+       )?
+     )
+   )*
+  \s*                                # trailing whitespace
+""", re.VERBOSE)
+    BeautifulSoupHTMLParser.locatestarttagend = locatestarttagend
+
+    from html.parser import tagfind, attrfind
+
+    def parse_starttag(self, i):
+        self.__starttag_text = None
+        endpos = self.check_for_whole_start_tag(i)
+        if endpos < 0:
+            return endpos
+        rawdata = self.rawdata
+        self.__starttag_text = rawdata[i:endpos]
+
+        # Now parse the data between i+1 and j into a tag and attrs
+        attrs = []
+        match = tagfind.match(rawdata, i+1)
+        assert match, 'unexpected call to parse_starttag()'
+        k = match.end()
+        self.lasttag = tag = rawdata[i+1:k].lower()
+        while k < endpos:
+            if self.strict:
+                m = attrfind.match(rawdata, k)
+            else:
+                m = attrfind_tolerant.match(rawdata, k)
+            if not m:
+                break
+            attrname, rest, attrvalue = m.group(1, 2, 3)
+            if not rest:
+                attrvalue = None
+            elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
+                 attrvalue[:1] == '"' == attrvalue[-1:]:
+                attrvalue = attrvalue[1:-1]
+            if attrvalue:
+                attrvalue = self.unescape(attrvalue)
+            attrs.append((attrname.lower(), attrvalue))
+            k = m.end()
+
+        end = rawdata[k:endpos].strip()
+        if end not in (">", "/>"):
+            lineno, offset = self.getpos()
+            if "\n" in self.__starttag_text:
+                lineno = lineno + self.__starttag_text.count("\n")
+                offset = len(self.__starttag_text) \
+                         - self.__starttag_text.rfind("\n")
+            else:
+                offset = offset + len(self.__starttag_text)
+            if self.strict:
+                self.error("junk characters in start tag: %r"
+                           % (rawdata[k:endpos][:20],))
+            self.handle_data(rawdata[i:endpos])
+            return endpos
+        if end.endswith('/>'):
+            # XHTML-style empty tag: <span attr="value" />
+            self.handle_startendtag(tag, attrs)
+        else:
+            self.handle_starttag(tag, attrs)
+            if tag in self.CDATA_CONTENT_ELEMENTS:
+                self.set_cdata_mode(tag)
+        return endpos
+
+    def set_cdata_mode(self, elem):
+        self.cdata_elem = elem.lower()
+        self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
+
+    BeautifulSoupHTMLParser.parse_starttag = parse_starttag
+    BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode
+
+    CONSTRUCTOR_TAKES_STRICT = True

bitbake/lib/bs4/builder/_lxml.py

@@ -0,0 +1,233 @@
+__all__ = [
+    'LXMLTreeBuilderForXML',
+    'LXMLTreeBuilder',
+    ]
+
+from io import BytesIO
+from StringIO import StringIO
+import collections
+from lxml import etree
+from bs4.element import Comment, Doctype, NamespacedAttribute
+from bs4.builder import (
+    FAST,
+    HTML,
+    HTMLTreeBuilder,
+    PERMISSIVE,
+    ParserRejectedMarkup,
+    TreeBuilder,
+    XML)
+from bs4.dammit import EncodingDetector
+
+LXML = 'lxml'
+
+class LXMLTreeBuilderForXML(TreeBuilder):
+    DEFAULT_PARSER_CLASS = etree.XMLParser
+
+    is_xml = True
+
+    # Well, it's permissive by XML parser standards.
+    features = [LXML, XML, FAST, PERMISSIVE]
+
+    CHUNK_SIZE = 512
+
+    # This namespace mapping is specified in the XML Namespace
+    # standard.
+    DEFAULT_NSMAPS = {'http://www.w3.org/XML/1998/namespace' : "xml"}
+
+    def default_parser(self, encoding):
+        # This can either return a parser object or a class, which
+        # will be instantiated with default arguments.
+        if self._default_parser is not None:
+            return self._default_parser
+        return etree.XMLParser(
+            target=self, strip_cdata=False, recover=True, encoding=encoding)
+
+    def parser_for(self, encoding):
+        # Use the default parser.
+        parser = self.default_parser(encoding)
+
+        if isinstance(parser, collections.Callable):
+            # Instantiate the parser with default arguments
+            parser = parser(target=self, strip_cdata=False, encoding=encoding)
+        return parser
+
+    def __init__(self, parser=None, empty_element_tags=None):
+        # TODO: Issue a warning if parser is present but not a
+        # callable, since that means there's no way to create new
+        # parsers for different encodings.
+        self._default_parser = parser
+        if empty_element_tags is not None:
+            self.empty_element_tags = set(empty_element_tags)
+        self.soup = None
+        self.nsmaps = [self.DEFAULT_NSMAPS]
+
+    def _getNsTag(self, tag):
+        # Split the namespace URL out of a fully-qualified lxml tag
+        # name. Copied from lxml's src/lxml/sax.py.
+        if tag[0] == '{':
+            return tuple(tag[1:].split('}', 1))
+        else:
+            return (None, tag)
+
+    def prepare_markup(self, markup, user_specified_encoding=None,
+                       document_declared_encoding=None):
+        """
+        :yield: A series of 4-tuples.
+         (markup, encoding, declared encoding,
+          has undergone character replacement)
+
+        Each 4-tuple represents a strategy for parsing the document.
+        """
+        if isinstance(markup, unicode):
+            # We were given Unicode. Maybe lxml can parse Unicode on
+            # this system?
+            yield markup, None, document_declared_encoding, False
+
+        if isinstance(markup, unicode):
+            # No, apparently not. Convert the Unicode to UTF-8 and
+            # tell lxml to parse it as UTF-8.
+            yield (markup.encode("utf8"), "utf8",
+                   document_declared_encoding, False)
+
+        # Instead of using UnicodeDammit to convert the bytestring to
+        # Unicode using different encodings, use EncodingDetector to
+        # iterate over the encodings, and tell lxml to try to parse
+        # the document as each one in turn.
+        is_html = not self.is_xml
+        try_encodings = [user_specified_encoding, document_declared_encoding]
+        detector = EncodingDetector(markup, try_encodings, is_html)
+        for encoding in detector.encodings:
+            yield (detector.markup, encoding, document_declared_encoding, False)
+
+    def feed(self, markup):
+        if isinstance(markup, bytes):
+            markup = BytesIO(markup)
+        elif isinstance(markup, unicode):
+            markup = StringIO(markup)
+
+        # Call feed() at least once, even if the markup is empty,
+        # or the parser won't be initialized.
+        data = markup.read(self.CHUNK_SIZE)
+        try:
+            self.parser = self.parser_for(self.soup.original_encoding)
+            self.parser.feed(data)
+            while len(data) != 0:
+                # Now call feed() on the rest of the data, chunk by chunk.
+                data = markup.read(self.CHUNK_SIZE)
+                if len(data) != 0:
+                    self.parser.feed(data)
+            self.parser.close()
+        except (UnicodeDecodeError, LookupError, etree.ParserError), e:
+            raise ParserRejectedMarkup(str(e))
+
+    def close(self):
+        self.nsmaps = [self.DEFAULT_NSMAPS]
+
+    def start(self, name, attrs, nsmap={}):
+        # Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
+        attrs = dict(attrs)
+        nsprefix = None
+        # Invert each namespace map as it comes in.
+        if len(self.nsmaps) > 1:
+            # There are no new namespaces for this tag, but
+            # non-default namespaces are in play, so we need a
+            # separate tag stack to know when they end.
+            self.nsmaps.append(None)
+        elif len(nsmap) > 0:
+            # A new namespace mapping has come into play.
+            inverted_nsmap = dict((value, key) for key, value in nsmap.items())
+            self.nsmaps.append(inverted_nsmap)
+            # Also treat the namespace mapping as a set of attributes on the
+            # tag, so we can recreate it later.
+            attrs = attrs.copy()
+            for prefix, namespace in nsmap.items():
+                attribute = NamespacedAttribute(
+                    "xmlns", prefix, "http://www.w3.org/2000/xmlns/")
+                attrs[attribute] = namespace
+
+        # Namespaces are in play. Find any attributes that came in
+        # from lxml with namespaces attached to their names, and
+        # turn then into NamespacedAttribute objects.
+        new_attrs = {}
+        for attr, value in attrs.items():
+            namespace, attr = self._getNsTag(attr)
+            if namespace is None:
+                new_attrs[attr] = value
+            else:
+                nsprefix = self._prefix_for_namespace(namespace)
+                attr = NamespacedAttribute(nsprefix, attr, namespace)
+                new_attrs[attr] = value
+        attrs = new_attrs
+
+        namespace, name = self._getNsTag(name)
+        nsprefix = self._prefix_for_namespace(namespace)
+        self.soup.handle_starttag(name, namespace, nsprefix, attrs)
+
+    def _prefix_for_namespace(self, namespace):
+        """Find the currently active prefix for the given namespace."""
+        if namespace is None:
+            return None
+        for inverted_nsmap in reversed(self.nsmaps):
+            if inverted_nsmap is not None and namespace in inverted_nsmap:
+                return inverted_nsmap[namespace]
+        return None
+
+    def end(self, name):
+        self.soup.endData()
+        completed_tag = self.soup.tagStack[-1]
+        namespace, name = self._getNsTag(name)
+        nsprefix = None
+        if namespace is not None:
+            for inverted_nsmap in reversed(self.nsmaps):
+                if inverted_nsmap is not None and namespace in inverted_nsmap:
+                    nsprefix = inverted_nsmap[namespace]
+                    break
+        self.soup.handle_endtag(name, nsprefix)
+        if len(self.nsmaps) > 1:
+            # This tag, or one of its parents, introduced a namespace
+            # mapping, so pop it off the stack.
+            self.nsmaps.pop()
+
+    def pi(self, target, data):
+        pass
+
+    def data(self, content):
+        self.soup.handle_data(content)
+
+    def doctype(self, name, pubid, system):
+        self.soup.endData()
+        doctype = Doctype.for_name_and_ids(name, pubid, system)
+        self.soup.object_was_parsed(doctype)
+
+    def comment(self, content):
+        "Handle comments as Comment objects."
+        self.soup.endData()
+        self.soup.handle_data(content)
+        self.soup.endData(Comment)
+
+    def test_fragment_to_document(self, fragment):
+        """See `TreeBuilder`."""
+        return u'<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
+
+
+class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
+
+    features = [LXML, HTML, FAST, PERMISSIVE]
+    is_xml = False
+
+    def default_parser(self, encoding):
+        return etree.HTMLParser
+
+    def feed(self, markup):
+        encoding = self.soup.original_encoding
+        try:
+            self.parser = self.parser_for(encoding)
+            self.parser.feed(markup)
+            self.parser.close()
+        except (UnicodeDecodeError, LookupError, etree.ParserError), e:
+            raise ParserRejectedMarkup(str(e))
+
+
+    def test_fragment_to_document(self, fragment):
+        """See `TreeBuilder`."""
+        return u'<html><body>%s</body></html>' % fragment

bitbake/lib/bs4/dammit.py

@@ -0,0 +1,829 @@
+# -*- coding: utf-8 -*-
+"""Beautiful Soup bonus library: Unicode, Dammit
+
+This library converts a bytestream to Unicode through any means
+necessary. It is heavily based on code from Mark Pilgrim's Universal
+Feed Parser. It works best on XML and XML, but it does not rewrite the
+XML or HTML to reflect a new encoding; that's the tree builder's job.
+"""
+
+import codecs
+from htmlentitydefs import codepoint2name
+import re
+import logging
+import string
+
+# Import a library to autodetect character encodings.
+chardet_type = None
+try:
+    # First try the fast C implementation.
+    #  PyPI package: cchardet
+    import cchardet
+    def chardet_dammit(s):
+        return cchardet.detect(s)['encoding']
+except ImportError:
+    try:
+        # Fall back to the pure Python implementation
+        #  Debian package: python-chardet
+        #  PyPI package: chardet
+        import chardet
+        def chardet_dammit(s):
+            return chardet.detect(s)['encoding']
+        #import chardet.constants
+        #chardet.constants._debug = 1
+    except ImportError:
+        # No chardet available.
+        def chardet_dammit(s):
+            return None
+
+# Available from http://cjkpython.i18n.org/.
+try:
+    import iconv_codec
+except ImportError:
+    pass
+
+xml_encoding_re = re.compile(
+    '^<\?.*encoding=[\'"](.*?)[\'"].*\?>'.encode(), re.I)
+html_meta_re = re.compile(
+    '<\s*meta[^>]+charset\s*=\s*["\']?([^>]*?)[ /;\'">]'.encode(), re.I)
+
+class EntitySubstitution(object):
+
+    """Substitute XML or HTML entities for the corresponding characters."""
+
+    def _populate_class_variables():
+        lookup = {}
+        reverse_lookup = {}
+        characters_for_re = []
+        for codepoint, name in list(codepoint2name.items()):
+            character = unichr(codepoint)
+            if codepoint != 34:
+                # There's no point in turning the quotation mark into
+                # &quot;, unless it happens within an attribute value, which
+                # is handled elsewhere.
+                characters_for_re.append(character)
+                lookup[character] = name
+            # But we do want to turn &quot; into the quotation mark.
+            reverse_lookup[name] = character
+        re_definition = "[%s]" % "".join(characters_for_re)
+        return lookup, reverse_lookup, re.compile(re_definition)
+    (CHARACTER_TO_HTML_ENTITY, HTML_ENTITY_TO_CHARACTER,
+     CHARACTER_TO_HTML_ENTITY_RE) = _populate_class_variables()
+
+    CHARACTER_TO_XML_ENTITY = {
+        "'": "apos",
+        '"': "quot",
+        "&": "amp",
+        "<": "lt",
+        ">": "gt",
+        }
+
+    BARE_AMPERSAND_OR_BRACKET = re.compile("([<>]|"
+                                           "&(?!#\d+;|#x[0-9a-fA-F]+;|\w+;)"
+                                           ")")
+
+    AMPERSAND_OR_BRACKET = re.compile("([<>&])")
+
+    @classmethod
+    def _substitute_html_entity(cls, matchobj):
+        entity = cls.CHARACTER_TO_HTML_ENTITY.get(matchobj.group(0))
+        return "&%s;" % entity
+
+    @classmethod
+    def _substitute_xml_entity(cls, matchobj):
+        """Used with a regular expression to substitute the
+        appropriate XML entity for an XML special character."""
+        entity = cls.CHARACTER_TO_XML_ENTITY[matchobj.group(0)]
+        return "&%s;" % entity
+
+    @classmethod
+    def quoted_attribute_value(self, value):
+        """Make a value into a quoted XML attribute, possibly escaping it.
+
+         Most strings will be quoted using double quotes.
+
+          Bob's Bar -> "Bob's Bar"
+
+         If a string contains double quotes, it will be quoted using
+         single quotes.
+
+          Welcome to "my bar" -> 'Welcome to "my bar"'
+
+         If a string contains both single and double quotes, the
+         double quotes will be escaped, and the string will be quoted
+         using double quotes.
+
+          Welcome to "Bob's Bar" -> "Welcome to &quot;Bob's bar&quot;
+        """
+        quote_with = '"'
+        if '"' in value:
+            if "'" in value:
+                # The string contains both single and double
+                # quotes.  Turn the double quotes into
+                # entities. We quote the double quotes rather than
+                # the single quotes because the entity name is
+                # "&quot;" whether this is HTML or XML.  If we
+                # quoted the single quotes, we'd have to decide
+                # between &apos; and &squot;.
+                replace_with = "&quot;"
+                value = value.replace('"', replace_with)
+            else:
+                # There are double quotes but no single quotes.
+                # We can use single quotes to quote the attribute.
+                quote_with = "'"
+        return quote_with + value + quote_with
+
+    @classmethod
+    def substitute_xml(cls, value, make_quoted_attribute=False):
+        """Substitute XML entities for special XML characters.
+
+        :param value: A string to be substituted. The less-than sign
+          will become &lt;, the greater-than sign will become &gt;,
+          and any ampersands will become &amp;. If you want ampersands
+          that appear to be part of an entity definition to be left
+          alone, use substitute_xml_containing_entities() instead.
+
+        :param make_quoted_attribute: If True, then the string will be
+         quoted, as befits an attribute value.
+        """
+        # Escape angle brackets and ampersands.
+        value = cls.AMPERSAND_OR_BRACKET.sub(
+            cls._substitute_xml_entity, value)
+
+        if make_quoted_attribute:
+            value = cls.quoted_attribute_value(value)
+        return value
+
+    @classmethod
+    def substitute_xml_containing_entities(
+        cls, value, make_quoted_attribute=False):
+        """Substitute XML entities for special XML characters.
+
+        :param value: A string to be substituted. The less-than sign will
+          become &lt;, the greater-than sign will become &gt;, and any
+          ampersands that are not part of an entity defition will
+          become &amp;.
+
+        :param make_quoted_attribute: If True, then the string will be
+         quoted, as befits an attribute value.
+        """
+        # Escape angle brackets, and ampersands that aren't part of
+        # entities.
+        value = cls.BARE_AMPERSAND_OR_BRACKET.sub(
+            cls._substitute_xml_entity, value)
+
+        if make_quoted_attribute:
+            value = cls.quoted_attribute_value(value)
+        return value
+
+    @classmethod
+    def substitute_html(cls, s):
+        """Replace certain Unicode characters with named HTML entities.
+
+        This differs from data.encode(encoding, 'xmlcharrefreplace')
+        in that the goal is to make the result more readable (to those
+        with ASCII displays) rather than to recover from
+        errors. There's absolutely nothing wrong with a UTF-8 string
+        containg a LATIN SMALL LETTER E WITH ACUTE, but replacing that
+        character with "&eacute;" will make it more readable to some
+        people.
+        """
+        return cls.CHARACTER_TO_HTML_ENTITY_RE.sub(
+            cls._substitute_html_entity, s)
+
+
+class EncodingDetector:
+    """Suggests a number of possible encodings for a bytestring.
+
+    Order of precedence:
+
+    1. Encodings you specifically tell EncodingDetector to try first
+    (the override_encodings argument to the constructor).
+
+    2. An encoding declared within the bytestring itself, either in an
+    XML declaration (if the bytestring is to be interpreted as an XML
+    document), or in a <meta> tag (if the bytestring is to be
+    interpreted as an HTML document.)
+
+    3. An encoding detected through textual analysis by chardet,
+    cchardet, or a similar external library.
+
+    4. UTF-8.
+
+    5. Windows-1252.
+    """
+    def __init__(self, markup, override_encodings=None, is_html=False):
+        self.override_encodings = override_encodings or []
+        self.chardet_encoding = None
+        self.is_html = is_html
+        self.declared_encoding = None
+
+        # First order of business: strip a byte-order mark.
+        self.markup, self.sniffed_encoding = self.strip_byte_order_mark(markup)
+
+    def _usable(self, encoding, tried):
+        if encoding is not None:
+            encoding = encoding.lower()
+            if encoding not in tried:
+                tried.add(encoding)
+                return True
+        return False
+
+    @property
+    def encodings(self):
+        """Yield a number of encodings that might work for this markup."""
+        tried = set()
+        for e in self.override_encodings:
+            if self._usable(e, tried):
+                yield e
+
+        # Did the document originally start with a byte-order mark
+        # that indicated its encoding?
+        if self._usable(self.sniffed_encoding, tried):
+            yield self.sniffed_encoding
+
+        # Look within the document for an XML or HTML encoding
+        # declaration.
+        if self.declared_encoding is None:
+            self.declared_encoding = self.find_declared_encoding(
+                self.markup, self.is_html)
+        if self._usable(self.declared_encoding, tried):
+            yield self.declared_encoding
+
+        # Use third-party character set detection to guess at the
+        # encoding.
+        if self.chardet_encoding is None:
+            self.chardet_encoding = chardet_dammit(self.markup)
+        if self._usable(self.chardet_encoding, tried):
+            yield self.chardet_encoding
+
+        # As a last-ditch effort, try utf-8 and windows-1252.
+        for e in ('utf-8', 'windows-1252'):
+            if self._usable(e, tried):
+                yield e
+
+    @classmethod
+    def strip_byte_order_mark(cls, data):
+        """If a byte-order mark is present, strip it and return the encoding it implies."""
+        encoding = None
+        if (len(data) >= 4) and (data[:2] == b'\xfe\xff') \
+               and (data[2:4] != '\x00\x00'):
+            encoding = 'utf-16be'
+            data = data[2:]
+        elif (len(data) >= 4) and (data[:2] == b'\xff\xfe') \
+                 and (data[2:4] != '\x00\x00'):
+            encoding = 'utf-16le'
+            data = data[2:]
+        elif data[:3] == b'\xef\xbb\xbf':
+            encoding = 'utf-8'
+            data = data[3:]
+        elif data[:4] == b'\x00\x00\xfe\xff':
+            encoding = 'utf-32be'
+            data = data[4:]
+        elif data[:4] == b'\xff\xfe\x00\x00':
+            encoding = 'utf-32le'
+            data = data[4:]
+        return data, encoding
+
+    @classmethod
+    def find_declared_encoding(cls, markup, is_html=False, search_entire_document=False):
+        """Given a document, tries to find its declared encoding.
+
+        An XML encoding is declared at the beginning of the document.
+
+        An HTML encoding is declared in a <meta> tag, hopefully near the
+        beginning of the document.
+        """
+        if search_entire_document:
+            xml_endpos = html_endpos = len(markup)
+        else:
+            xml_endpos = 1024
+            html_endpos = max(2048, int(len(markup) * 0.05))
+            
+        declared_encoding = None
+        declared_encoding_match = xml_encoding_re.search(markup, endpos=xml_endpos)
+        if not declared_encoding_match and is_html:
+            declared_encoding_match = html_meta_re.search(markup, endpos=html_endpos)
+        if declared_encoding_match is not None:
+            declared_encoding = declared_encoding_match.groups()[0].decode(
+                'ascii')
+        if declared_encoding:
+            return declared_encoding.lower()
+        return None
+
+class UnicodeDammit:
+    """A class for detecting the encoding of a *ML document and
+    converting it to a Unicode string. If the source encoding is
+    windows-1252, can replace MS smart quotes with their HTML or XML
+    equivalents."""
+
+    # This dictionary maps commonly seen values for "charset" in HTML
+    # meta tags to the corresponding Python codec names. It only covers
+    # values that aren't in Python's aliases and can't be determined
+    # by the heuristics in find_codec.
+    CHARSET_ALIASES = {"macintosh": "mac-roman",
+                       "x-sjis": "shift-jis"}
+
+    ENCODINGS_WITH_SMART_QUOTES = [
+        "windows-1252",
+        "iso-8859-1",
+        "iso-8859-2",
+        ]
+
+    def __init__(self, markup, override_encodings=[],
+                 smart_quotes_to=None, is_html=False):
+        self.smart_quotes_to = smart_quotes_to
+        self.tried_encodings = []
+        self.contains_replacement_characters = False
+        self.is_html = is_html
+
+        self.detector = EncodingDetector(markup, override_encodings, is_html)
+
+        # Short-circuit if the data is in Unicode to begin with.
+        if isinstance(markup, unicode) or markup == '':
+            self.markup = markup
+            self.unicode_markup = unicode(markup)
+            self.original_encoding = None
+            return
+
+        # The encoding detector may have stripped a byte-order mark.
+        # Use the stripped markup from this point on.
+        self.markup = self.detector.markup
+
+        u = None
+        for encoding in self.detector.encodings:
+            markup = self.detector.markup
+            u = self._convert_from(encoding)
+            if u is not None:
+                break
+
+        if not u:
+            # None of the encodings worked. As an absolute last resort,
+            # try them again with character replacement.
+
+            for encoding in self.detector.encodings:
+                if encoding != "ascii":
+                    u = self._convert_from(encoding, "replace")
+                if u is not None:
+                    logging.warning(
+                            "Some characters could not be decoded, and were "
+                            "replaced with REPLACEMENT CHARACTER.")
+                    self.contains_replacement_characters = True
+                    break
+
+        # If none of that worked, we could at this point force it to
+        # ASCII, but that would destroy so much data that I think
+        # giving up is better.
+        self.unicode_markup = u
+        if not u:
+            self.original_encoding = None
+
+    def _sub_ms_char(self, match):
+        """Changes a MS smart quote character to an XML or HTML
+        entity, or an ASCII character."""
+        orig = match.group(1)
+        if self.smart_quotes_to == 'ascii':
+            sub = self.MS_CHARS_TO_ASCII.get(orig).encode()
+        else:
+            sub = self.MS_CHARS.get(orig)
+            if type(sub) == tuple:
+                if self.smart_quotes_to == 'xml':
+                    sub = '&#x'.encode() + sub[1].encode() + ';'.encode()
+                else:
+                    sub = '&'.encode() + sub[0].encode() + ';'.encode()
+            else:
+                sub = sub.encode()
+        return sub
+
+    def _convert_from(self, proposed, errors="strict"):
+        proposed = self.find_codec(proposed)
+        if not proposed or (proposed, errors) in self.tried_encodings:
+            return None
+        self.tried_encodings.append((proposed, errors))
+        markup = self.markup
+        # Convert smart quotes to HTML if coming from an encoding
+        # that might have them.
+        if (self.smart_quotes_to is not None
+            and proposed in self.ENCODINGS_WITH_SMART_QUOTES):
+            smart_quotes_re = b"([\x80-\x9f])"
+            smart_quotes_compiled = re.compile(smart_quotes_re)
+            markup = smart_quotes_compiled.sub(self._sub_ms_char, markup)
+
+        try:
+            #print "Trying to convert document to %s (errors=%s)" % (
+            #    proposed, errors)
+            u = self._to_unicode(markup, proposed, errors)
+            self.markup = u
+            self.original_encoding = proposed
+        except Exception as e:
+            #print "That didn't work!"
+            #print e
+            return None
+        #print "Correct encoding: %s" % proposed
+        return self.markup
+
+    def _to_unicode(self, data, encoding, errors="strict"):
+        '''Given a string and its encoding, decodes the string into Unicode.
+        %encoding is a string recognized by encodings.aliases'''
+        return unicode(data, encoding, errors)
+
+    @property
+    def declared_html_encoding(self):
+        if not self.is_html:
+            return None
+        return self.detector.declared_encoding
+
+    def find_codec(self, charset):
+        value = (self._codec(self.CHARSET_ALIASES.get(charset, charset))
+               or (charset and self._codec(charset.replace("-", "")))
+               or (charset and self._codec(charset.replace("-", "_")))
+               or (charset and charset.lower())
+               or charset
+                )
+        if value:
+            return value.lower()
+        return None
+
+    def _codec(self, charset):
+        if not charset:
+            return charset
+        codec = None
+        try:
+            codecs.lookup(charset)
+            codec = charset
+        except (LookupError, ValueError):
+            pass
+        return codec
+
+
+    # A partial mapping of ISO-Latin-1 to HTML entities/XML numeric entities.
+    MS_CHARS = {b'\x80': ('euro', '20AC'),
+                b'\x81': ' ',
+                b'\x82': ('sbquo', '201A'),
+                b'\x83': ('fnof', '192'),
+                b'\x84': ('bdquo', '201E'),
+                b'\x85': ('hellip', '2026'),
+                b'\x86': ('dagger', '2020'),
+                b'\x87': ('Dagger', '2021'),
+                b'\x88': ('circ', '2C6'),
+                b'\x89': ('permil', '2030'),
+                b'\x8A': ('Scaron', '160'),
+                b'\x8B': ('lsaquo', '2039'),
+                b'\x8C': ('OElig', '152'),
+                b'\x8D': '?',
+                b'\x8E': ('#x17D', '17D'),
+                b'\x8F': '?',
+                b'\x90': '?',
+                b'\x91': ('lsquo', '2018'),
+                b'\x92': ('rsquo', '2019'),
+                b'\x93': ('ldquo', '201C'),
+                b'\x94': ('rdquo', '201D'),
+                b'\x95': ('bull', '2022'),
+                b'\x96': ('ndash', '2013'),
+                b'\x97': ('mdash', '2014'),
+                b'\x98': ('tilde', '2DC'),
+                b'\x99': ('trade', '2122'),
+                b'\x9a': ('scaron', '161'),
+                b'\x9b': ('rsaquo', '203A'),
+                b'\x9c': ('oelig', '153'),
+                b'\x9d': '?',
+                b'\x9e': ('#x17E', '17E'),
+                b'\x9f': ('Yuml', ''),}
+
+    # A parochial partial mapping of ISO-Latin-1 to ASCII. Contains
+    # horrors like stripping diacritical marks to turn á into a, but also
+    # contains non-horrors like turning “ into ".
+    MS_CHARS_TO_ASCII = {
+        b'\x80' : 'EUR',
+        b'\x81' : ' ',
+        b'\x82' : ',',
+        b'\x83' : 'f',
+        b'\x84' : ',,',
+        b'\x85' : '...',
+        b'\x86' : '+',
+        b'\x87' : '++',
+        b'\x88' : '^',
+        b'\x89' : '%',
+        b'\x8a' : 'S',
+        b'\x8b' : '<',
+        b'\x8c' : 'OE',
+        b'\x8d' : '?',
+        b'\x8e' : 'Z',
+        b'\x8f' : '?',
+        b'\x90' : '?',
+        b'\x91' : "'",
+        b'\x92' : "'",
+        b'\x93' : '"',
+        b'\x94' : '"',
+        b'\x95' : '*',
+        b'\x96' : '-',
+        b'\x97' : '--',
+        b'\x98' : '~',
+        b'\x99' : '(TM)',
+        b'\x9a' : 's',
+        b'\x9b' : '>',
+        b'\x9c' : 'oe',
+        b'\x9d' : '?',
+        b'\x9e' : 'z',
+        b'\x9f' : 'Y',
+        b'\xa0' : ' ',
+        b'\xa1' : '!',
+        b'\xa2' : 'c',
+        b'\xa3' : 'GBP',
+        b'\xa4' : '$', #This approximation is especially parochial--this is the
+                       #generic currency symbol.
+        b'\xa5' : 'YEN',
+        b'\xa6' : '|',
+        b'\xa7' : 'S',
+        b'\xa8' : '..',
+        b'\xa9' : '',
+        b'\xaa' : '(th)',
+        b'\xab' : '<<',
+        b'\xac' : '!',
+        b'\xad' : ' ',
+        b'\xae' : '(R)',
+        b'\xaf' : '-',
+        b'\xb0' : 'o',
+        b'\xb1' : '+-',
+        b'\xb2' : '2',
+        b'\xb3' : '3',
+        b'\xb4' : ("'", 'acute'),
+        b'\xb5' : 'u',
+        b'\xb6' : 'P',
+        b'\xb7' : '*',
+        b'\xb8' : ',',
+        b'\xb9' : '1',
+        b'\xba' : '(th)',
+        b'\xbb' : '>>',
+        b'\xbc' : '1/4',
+        b'\xbd' : '1/2',
+        b'\xbe' : '3/4',
+        b'\xbf' : '?',
+        b'\xc0' : 'A',
+        b'\xc1' : 'A',
+        b'\xc2' : 'A',
+        b'\xc3' : 'A',
+        b'\xc4' : 'A',
+        b'\xc5' : 'A',
+        b'\xc6' : 'AE',
+        b'\xc7' : 'C',
+        b'\xc8' : 'E',
+        b'\xc9' : 'E',
+        b'\xca' : 'E',
+        b'\xcb' : 'E',
+        b'\xcc' : 'I',
+        b'\xcd' : 'I',
+        b'\xce' : 'I',
+        b'\xcf' : 'I',
+        b'\xd0' : 'D',
+        b'\xd1' : 'N',
+        b'\xd2' : 'O',
+        b'\xd3' : 'O',
+        b'\xd4' : 'O',
+        b'\xd5' : 'O',
+        b'\xd6' : 'O',
+        b'\xd7' : '*',
+        b'\xd8' : 'O',
+        b'\xd9' : 'U',
+        b'\xda' : 'U',
+        b'\xdb' : 'U',
+        b'\xdc' : 'U',
+        b'\xdd' : 'Y',
+        b'\xde' : 'b',
+        b'\xdf' : 'B',
+        b'\xe0' : 'a',
+        b'\xe1' : 'a',
+        b'\xe2' : 'a',
+        b'\xe3' : 'a',
+        b'\xe4' : 'a',
+        b'\xe5' : 'a',
+        b'\xe6' : 'ae',
+        b'\xe7' : 'c',
+        b'\xe8' : 'e',
+        b'\xe9' : 'e',
+        b'\xea' : 'e',
+        b'\xeb' : 'e',
+        b'\xec' : 'i',
+        b'\xed' : 'i',
+        b'\xee' : 'i',
+        b'\xef' : 'i',
+        b'\xf0' : 'o',
+        b'\xf1' : 'n',
+        b'\xf2' : 'o',
+        b'\xf3' : 'o',
+        b'\xf4' : 'o',
+        b'\xf5' : 'o',
+        b'\xf6' : 'o',
+        b'\xf7' : '/',
+        b'\xf8' : 'o',
+        b'\xf9' : 'u',
+        b'\xfa' : 'u',
+        b'\xfb' : 'u',
+        b'\xfc' : 'u',
+        b'\xfd' : 'y',
+        b'\xfe' : 'b',
+        b'\xff' : 'y',
+        }
+
+    # A map used when removing rogue Windows-1252/ISO-8859-1
+    # characters in otherwise UTF-8 documents.
+    #
+    # Note that \x81, \x8d, \x8f, \x90, and \x9d are undefined in
+    # Windows-1252.
+    WINDOWS_1252_TO_UTF8 = {
+        0x80 : b'\xe2\x82\xac', # €
+        0x82 : b'\xe2\x80\x9a', # ‚
+        0x83 : b'\xc6\x92',     # ƒ
+        0x84 : b'\xe2\x80\x9e', # „
+        0x85 : b'\xe2\x80\xa6', # …
+        0x86 : b'\xe2\x80\xa0', # †
+        0x87 : b'\xe2\x80\xa1', # ‡
+        0x88 : b'\xcb\x86',     # ˆ
+        0x89 : b'\xe2\x80\xb0', # ‰
+        0x8a : b'\xc5\xa0',     # Š
+        0x8b : b'\xe2\x80\xb9', # ‹
+        0x8c : b'\xc5\x92',     # Œ
+        0x8e : b'\xc5\xbd',     # Ž
+        0x91 : b'\xe2\x80\x98', # ‘
+        0x92 : b'\xe2\x80\x99', # ’
+        0x93 : b'\xe2\x80\x9c', # “
+        0x94 : b'\xe2\x80\x9d', # ”
+        0x95 : b'\xe2\x80\xa2', # •
+        0x96 : b'\xe2\x80\x93', # –
+        0x97 : b'\xe2\x80\x94', # —
+        0x98 : b'\xcb\x9c',     # ˜
+        0x99 : b'\xe2\x84\xa2', # ™
+        0x9a : b'\xc5\xa1',     # š
+        0x9b : b'\xe2\x80\xba', # ›
+        0x9c : b'\xc5\x93',     # œ
+        0x9e : b'\xc5\xbe',     # ž
+        0x9f : b'\xc5\xb8',     # Ÿ
+        0xa0 : b'\xc2\xa0',     #  
+        0xa1 : b'\xc2\xa1',     # ¡
+        0xa2 : b'\xc2\xa2',     # ¢
+        0xa3 : b'\xc2\xa3',     # £
+        0xa4 : b'\xc2\xa4',     # ¤
+        0xa5 : b'\xc2\xa5',     # ¥
+        0xa6 : b'\xc2\xa6',     # ¦
+        0xa7 : b'\xc2\xa7',     # §
+        0xa8 : b'\xc2\xa8',     # ¨
+        0xa9 : b'\xc2\xa9',     # ©
+        0xaa : b'\xc2\xaa',     # ª
+        0xab : b'\xc2\xab',     # «
+        0xac : b'\xc2\xac',     # ¬
+        0xad : b'\xc2\xad',     # ­
+        0xae : b'\xc2\xae',     # ®
+        0xaf : b'\xc2\xaf',     # ¯
+        0xb0 : b'\xc2\xb0',     # °
+        0xb1 : b'\xc2\xb1',     # ±
+        0xb2 : b'\xc2\xb2',     # ²
+        0xb3 : b'\xc2\xb3',     # ³
+        0xb4 : b'\xc2\xb4',     # ´
+        0xb5 : b'\xc2\xb5',     # µ
+        0xb6 : b'\xc2\xb6',     # ¶
+        0xb7 : b'\xc2\xb7',     # ·
+        0xb8 : b'\xc2\xb8',     # ¸
+        0xb9 : b'\xc2\xb9',     # ¹
+        0xba : b'\xc2\xba',     # º
+        0xbb : b'\xc2\xbb',     # »
+        0xbc : b'\xc2\xbc',     # ¼
+        0xbd : b'\xc2\xbd',     # ½
+        0xbe : b'\xc2\xbe',     # ¾
+        0xbf : b'\xc2\xbf',     # ¿
+        0xc0 : b'\xc3\x80',     # À
+        0xc1 : b'\xc3\x81',     # Á
+        0xc2 : b'\xc3\x82',     # Â
+        0xc3 : b'\xc3\x83',     # Ã
+        0xc4 : b'\xc3\x84',     # Ä
+        0xc5 : b'\xc3\x85',     # Å
+        0xc6 : b'\xc3\x86',     # Æ
+        0xc7 : b'\xc3\x87',     # Ç
+        0xc8 : b'\xc3\x88',     # È
+        0xc9 : b'\xc3\x89',     # É
+        0xca : b'\xc3\x8a',     # Ê
+        0xcb : b'\xc3\x8b',     # Ë
+        0xcc : b'\xc3\x8c',     # Ì
+        0xcd : b'\xc3\x8d',     # Í
+        0xce : b'\xc3\x8e',     # Î
+        0xcf : b'\xc3\x8f',     # Ï
+        0xd0 : b'\xc3\x90',     # Ð
+        0xd1 : b'\xc3\x91',     # Ñ
+        0xd2 : b'\xc3\x92',     # Ò
+        0xd3 : b'\xc3\x93',     # Ó
+        0xd4 : b'\xc3\x94',     # Ô
+        0xd5 : b'\xc3\x95',     # Õ
+        0xd6 : b'\xc3\x96',     # Ö
+        0xd7 : b'\xc3\x97',     # ×
+        0xd8 : b'\xc3\x98',     # Ø
+        0xd9 : b'\xc3\x99',     # Ù
+        0xda : b'\xc3\x9a',     # Ú
+        0xdb : b'\xc3\x9b',     # Û
+        0xdc : b'\xc3\x9c',     # Ü
+        0xdd : b'\xc3\x9d',     # Ý
+        0xde : b'\xc3\x9e',     # Þ
+        0xdf : b'\xc3\x9f',     # ß
+        0xe0 : b'\xc3\xa0',     # à
+        0xe1 : b'\xa1',     # á
+        0xe2 : b'\xc3\xa2',     # â
+        0xe3 : b'\xc3\xa3',     # ã
+        0xe4 : b'\xc3\xa4',     # ä
+        0xe5 : b'\xc3\xa5',     # å
+        0xe6 : b'\xc3\xa6',     # æ
+        0xe7 : b'\xc3\xa7',     # ç
+        0xe8 : b'\xc3\xa8',     # è
+        0xe9 : b'\xc3\xa9',     # é
+        0xea : b'\xc3\xaa',     # ê
+        0xeb : b'\xc3\xab',     # ë
+        0xec : b'\xc3\xac',     # ì
+        0xed : b'\xc3\xad',     # í
+        0xee : b'\xc3\xae',     # î
+        0xef : b'\xc3\xaf',     # ï
+        0xf0 : b'\xc3\xb0',     # ð
+        0xf1 : b'\xc3\xb1',     # ñ
+        0xf2 : b'\xc3\xb2',     # ò
+        0xf3 : b'\xc3\xb3',     # ó
+        0xf4 : b'\xc3\xb4',     # ô
+        0xf5 : b'\xc3\xb5',     # õ
+        0xf6 : b'\xc3\xb6',     # ö
+        0xf7 : b'\xc3\xb7',     # ÷
+        0xf8 : b'\xc3\xb8',     # ø
+        0xf9 : b'\xc3\xb9',     # ù
+        0xfa : b'\xc3\xba',     # ú
+        0xfb : b'\xc3\xbb',     # û
+        0xfc : b'\xc3\xbc',     # ü
+        0xfd : b'\xc3\xbd',     # ý
+        0xfe : b'\xc3\xbe',     # þ
+        }
+
+    MULTIBYTE_MARKERS_AND_SIZES = [
+        (0xc2, 0xdf, 2), # 2-byte characters start with a byte C2-DF
+        (0xe0, 0xef, 3), # 3-byte characters start with E0-EF
+        (0xf0, 0xf4, 4), # 4-byte characters start with F0-F4
+        ]
+
+    FIRST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[0][0]
+    LAST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[-1][1]
+
+    @classmethod
+    def detwingle(cls, in_bytes, main_encoding="utf8",
+                  embedded_encoding="windows-1252"):
+        """Fix characters from one encoding embedded in some other encoding.
+
+        Currently the only situation supported is Windows-1252 (or its
+        subset ISO-8859-1), embedded in UTF-8.
+
+        The input must be a bytestring. If you've already converted
+        the document to Unicode, you're too late.
+
+        The output is a bytestring in which `embedded_encoding`
+        characters have been converted to their `main_encoding`
+        equivalents.
+        """
+        if embedded_encoding.replace('_', '-').lower() not in (
+            'windows-1252', 'windows_1252'):
+            raise NotImplementedError(
+                "Windows-1252 and ISO-8859-1 are the only currently supported "
+                "embedded encodings.")
+
+        if main_encoding.lower() not in ('utf8', 'utf-8'):
+            raise NotImplementedError(
+                "UTF-8 is the only currently supported main encoding.")
+
+        byte_chunks = []
+
+        chunk_start = 0
+        pos = 0
+        while pos < len(in_bytes):
+            byte = in_bytes[pos]
+            if not isinstance(byte, int):
+                # Python 2.x
+                byte = ord(byte)
+            if (byte >= cls.FIRST_MULTIBYTE_MARKER
+                and byte <= cls.LAST_MULTIBYTE_MARKER):
+                # This is the start of a UTF-8 multibyte character. Skip
+                # to the end.
+                for start, end, size in cls.MULTIBYTE_MARKERS_AND_SIZES:
+                    if byte >= start and byte <= end:
+                        pos += size
+                        break
+            elif byte >= 0x80 and byte in cls.WINDOWS_1252_TO_UTF8:
+                # We found a Windows-1252 character!
+                # Save the string up to this point as a chunk.
+                byte_chunks.append(in_bytes[chunk_start:pos])
+
+                # Now translate the Windows-1252 character into UTF-8
+                # and add it as another, one-byte chunk.
+                byte_chunks.append(cls.WINDOWS_1252_TO_UTF8[byte])
+                pos += 1
+                chunk_start = pos
+            else:
+                # Go on to the next character.
+                pos += 1
+        if chunk_start == 0:
+            # The string is unchanged.
+            return in_bytes
+        else:
+            # Store the final chunk.
+            byte_chunks.append(in_bytes[chunk_start:])
+        return b''.join(byte_chunks)
+

bitbake/lib/bs4/diagnose.py

@@ -0,0 +1,204 @@
+"""Diagnostic functions, mainly for use when doing tech support."""
+import cProfile
+from StringIO import StringIO
+from HTMLParser import HTMLParser
+import bs4
+from bs4 import BeautifulSoup, __version__
+from bs4.builder import builder_registry
+
+import os
+import pstats
+import random
+import tempfile
+import time
+import traceback
+import sys
+import cProfile
+
+def diagnose(data):
+    """Diagnostic suite for isolating common problems."""
+    print "Diagnostic running on Beautiful Soup %s" % __version__
+    print "Python version %s" % sys.version
+
+    basic_parsers = ["html.parser", "html5lib", "lxml"]
+    for name in basic_parsers:
+        for builder in builder_registry.builders:
+            if name in builder.features:
+                break
+        else:
+            basic_parsers.remove(name)
+            print (
+                "I noticed that %s is not installed. Installing it may help." %
+                name)
+
+    if 'lxml' in basic_parsers:
+        basic_parsers.append(["lxml", "xml"])
+        from lxml import etree
+        print "Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))
+
+    if 'html5lib' in basic_parsers:
+        import html5lib
+        print "Found html5lib version %s" % html5lib.__version__
+
+    if hasattr(data, 'read'):
+        data = data.read()
+    elif os.path.exists(data):
+        print '"%s" looks like a filename. Reading data from the file.' % data
+        data = open(data).read()
+    elif data.startswith("http:") or data.startswith("https:"):
+        print '"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data
+        print "You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup."
+        return
+    print
+
+    for parser in basic_parsers:
+        print "Trying to parse your markup with %s" % parser
+        success = False
+        try:
+            soup = BeautifulSoup(data, parser)
+            success = True
+        except Exception, e:
+            print "%s could not parse the markup." % parser
+            traceback.print_exc()
+        if success:
+            print "Here's what %s did with the markup:" % parser
+            print soup.prettify()
+
+        print "-" * 80
+
+def lxml_trace(data, html=True, **kwargs):
+    """Print out the lxml events that occur during parsing.
+
+    This lets you see how lxml parses a document when no Beautiful
+    Soup code is running.
+    """
+    from lxml import etree
+    for event, element in etree.iterparse(StringIO(data), html=html, **kwargs):
+        print("%s, %4s, %s" % (event, element.tag, element.text))
+
+class AnnouncingParser(HTMLParser):
+    """Announces HTMLParser parse events, without doing anything else."""
+
+    def _p(self, s):
+        print(s)
+
+    def handle_starttag(self, name, attrs):
+        self._p("%s START" % name)
+
+    def handle_endtag(self, name):
+        self._p("%s END" % name)
+
+    def handle_data(self, data):
+        self._p("%s DATA" % data)
+
+    def handle_charref(self, name):
+        self._p("%s CHARREF" % name)
+
+    def handle_entityref(self, name):
+        self._p("%s ENTITYREF" % name)
+
+    def handle_comment(self, data):
+        self._p("%s COMMENT" % data)
+
+    def handle_decl(self, data):
+        self._p("%s DECL" % data)
+
+    def unknown_decl(self, data):
+        self._p("%s UNKNOWN-DECL" % data)
+
+    def handle_pi(self, data):
+        self._p("%s PI" % data)
+
+def htmlparser_trace(data):
+    """Print out the HTMLParser events that occur during parsing.
+
+    This lets you see how HTMLParser parses a document when no
+    Beautiful Soup code is running.
+    """
+    parser = AnnouncingParser()
+    parser.feed(data)
+
+_vowels = "aeiou"
+_consonants = "bcdfghjklmnpqrstvwxyz"
+
+def rword(length=5):
+    "Generate a random word-like string."
+    s = ''
+    for i in range(length):
+        if i % 2 == 0:
+            t = _consonants
+        else:
+            t = _vowels
+        s += random.choice(t)
+    return s
+
+def rsentence(length=4):
+    "Generate a random sentence-like string."
+    return " ".join(rword(random.randint(4,9)) for i in range(length))
+        
+def rdoc(num_elements=1000):
+    """Randomly generate an invalid HTML document."""
+    tag_names = ['p', 'div', 'span', 'i', 'b', 'script', 'table']
+    elements = []
+    for i in range(num_elements):
+        choice = random.randint(0,3)
+        if choice == 0:
+            # New tag.
+            tag_name = random.choice(tag_names)
+            elements.append("<%s>" % tag_name)
+        elif choice == 1:
+            elements.append(rsentence(random.randint(1,4)))
+        elif choice == 2:
+            # Close a tag.
+            tag_name = random.choice(tag_names)
+            elements.append("</%s>" % tag_name)
+    return "<html>" + "\n".join(elements) + "</html>"
+
+def benchmark_parsers(num_elements=100000):
+    """Very basic head-to-head performance benchmark."""
+    print "Comparative parser benchmark on Beautiful Soup %s" % __version__
+    data = rdoc(num_elements)
+    print "Generated a large invalid HTML document (%d bytes)." % len(data)
+    
+    for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
+        success = False
+        try:
+            a = time.time()
+            soup = BeautifulSoup(data, parser)
+            b = time.time()
+            success = True
+        except Exception, e:
+            print "%s could not parse the markup." % parser
+            traceback.print_exc()
+        if success:
+            print "BS4+%s parsed the markup in %.2fs." % (parser, b-a)
+
+    from lxml import etree
+    a = time.time()
+    etree.HTML(data)
+    b = time.time()
+    print "Raw lxml parsed the markup in %.2fs." % (b-a)
+
+    import html5lib
+    parser = html5lib.HTMLParser()
+    a = time.time()
+    parser.parse(data)
+    b = time.time()
+    print "Raw html5lib parsed the markup in %.2fs." % (b-a)
+
+def profile(num_elements=100000, parser="lxml"):
+
+    filehandle = tempfile.NamedTemporaryFile()
+    filename = filehandle.name
+
+    data = rdoc(num_elements)
+    vars = dict(bs4=bs4, data=data, parser=parser)
+    cProfile.runctx('bs4.BeautifulSoup(data, parser)' , vars, vars, filename)
+
+    stats = pstats.Stats(filename)
+    # stats.strip_dirs()
+    stats.sort_stats("cumulative")
+    stats.print_stats('_html5lib|bs4', 50)
+
+if __name__ == '__main__':
+    diagnose(sys.stdin.read())

bitbake/lib/bs4/testing.py

@@ -0,0 +1,592 @@
+"""Helper classes for tests."""
+
+import copy
+import functools
+import unittest
+from unittest import TestCase
+from bs4 import BeautifulSoup
+from bs4.element import (
+    CharsetMetaAttributeValue,
+    Comment,
+    ContentMetaAttributeValue,
+    Doctype,
+    SoupStrainer,
+)
+
+from bs4.builder import HTMLParserTreeBuilder
+default_builder = HTMLParserTreeBuilder
+
+
+class SoupTest(unittest.TestCase):
+
+    @property
+    def default_builder(self):
+        return default_builder()
+
+    def soup(self, markup, **kwargs):
+        """Build a Beautiful Soup object from markup."""
+        builder = kwargs.pop('builder', self.default_builder)
+        return BeautifulSoup(markup, builder=builder, **kwargs)
+
+    def document_for(self, markup):
+        """Turn an HTML fragment into a document.
+
+        The details depend on the builder.
+        """
+        return self.default_builder.test_fragment_to_document(markup)
+
+    def assertSoupEquals(self, to_parse, compare_parsed_to=None):
+        builder = self.default_builder
+        obj = BeautifulSoup(to_parse, builder=builder)
+        if compare_parsed_to is None:
+            compare_parsed_to = to_parse
+
+        self.assertEqual(obj.decode(), self.document_for(compare_parsed_to))
+
+
+class HTMLTreeBuilderSmokeTest(object):
+
+    """A basic test of a treebuilder's competence.
+
+    Any HTML treebuilder, present or future, should be able to pass
+    these tests. With invalid markup, there's room for interpretation,
+    and different parsers can handle it differently. But with the
+    markup in these tests, there's not much room for interpretation.
+    """
+
+    def assertDoctypeHandled(self, doctype_fragment):
+        """Assert that a given doctype string is handled correctly."""
+        doctype_str, soup = self._document_with_doctype(doctype_fragment)
+
+        # Make sure a Doctype object was created.
+        doctype = soup.contents[0]
+        self.assertEqual(doctype.__class__, Doctype)
+        self.assertEqual(doctype, doctype_fragment)
+        self.assertEqual(str(soup)[:len(doctype_str)], doctype_str)
+
+        # Make sure that the doctype was correctly associated with the
+        # parse tree and that the rest of the document parsed.
+        self.assertEqual(soup.p.contents[0], 'foo')
+
+    def _document_with_doctype(self, doctype_fragment):
+        """Generate and parse a document with the given doctype."""
+        doctype = '<!DOCTYPE %s>' % doctype_fragment
+        markup = doctype + '\n<p>foo</p>'
+        soup = self.soup(markup)
+        return doctype, soup
+
+    def test_normal_doctypes(self):
+        """Make sure normal, everyday HTML doctypes are handled correctly."""
+        self.assertDoctypeHandled("html")
+        self.assertDoctypeHandled(
+            'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"')
+
+    def test_empty_doctype(self):
+        soup = self.soup("<!DOCTYPE>")
+        doctype = soup.contents[0]
+        self.assertEqual("", doctype.strip())
+
+    def test_public_doctype_with_url(self):
+        doctype = 'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"'
+        self.assertDoctypeHandled(doctype)
+
+    def test_system_doctype(self):
+        self.assertDoctypeHandled('foo SYSTEM "http://www.example.com/"')
+
+    def test_namespaced_system_doctype(self):
+        # We can handle a namespaced doctype with a system ID.
+        self.assertDoctypeHandled('xsl:stylesheet SYSTEM "htmlent.dtd"')
+
+    def test_namespaced_public_doctype(self):
+        # Test a namespaced doctype with a public id.
+        self.assertDoctypeHandled('xsl:stylesheet PUBLIC "htmlent.dtd"')
+
+    def test_real_xhtml_document(self):
+        """A real XHTML document should come out more or less the same as it went in."""
+        markup = b"""<?xml version="1.0" encoding="utf-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head><title>Hello.</title></head>
+<body>Goodbye.</body>
+</html>"""
+        soup = self.soup(markup)
+        self.assertEqual(
+            soup.encode("utf-8").replace(b"\n", b""),
+            markup.replace(b"\n", b""))
+
+    def test_deepcopy(self):
+        """Make sure you can copy the tree builder.
+
+        This is important because the builder is part of a
+        BeautifulSoup object, and we want to be able to copy that.
+        """
+        copy.deepcopy(self.default_builder)
+
+    def test_p_tag_is_never_empty_element(self):
+        """A <p> tag is never designated as an empty-element tag.
+
+        Even if the markup shows it as an empty-element tag, it
+        shouldn't be presented that way.
+        """
+        soup = self.soup("<p/>")
+        self.assertFalse(soup.p.is_empty_element)
+        self.assertEqual(str(soup.p), "<p></p>")
+
+    def test_unclosed_tags_get_closed(self):
+        """A tag that's not closed by the end of the document should be closed.
+
+        This applies to all tags except empty-element tags.
+        """
+        self.assertSoupEquals("<p>", "<p></p>")
+        self.assertSoupEquals("<b>", "<b></b>")
+
+        self.assertSoupEquals("<br>", "<br/>")
+
+    def test_br_is_always_empty_element_tag(self):
+        """A <br> tag is designated as an empty-element tag.
+
+        Some parsers treat <br></br> as one <br/> tag, some parsers as
+        two tags, but it should always be an empty-element tag.
+        """
+        soup = self.soup("<br></br>")
+        self.assertTrue(soup.br.is_empty_element)
+        self.assertEqual(str(soup.br), "<br/>")
+
+    def test_nested_formatting_elements(self):
+        self.assertSoupEquals("<em><em></em></em>")
+
+    def test_comment(self):
+        # Comments are represented as Comment objects.
+        markup = "<p>foo<!--foobar-->baz</p>"
+        self.assertSoupEquals(markup)
+
+        soup = self.soup(markup)
+        comment = soup.find(text="foobar")
+        self.assertEqual(comment.__class__, Comment)
+
+        # The comment is properly integrated into the tree.
+        foo = soup.find(text="foo")
+        self.assertEqual(comment, foo.next_element)
+        baz = soup.find(text="baz")
+        self.assertEqual(comment, baz.previous_element)
+
+    def test_preserved_whitespace_in_pre_and_textarea(self):
+        """Whitespace must be preserved in <pre> and <textarea> tags."""
+        self.assertSoupEquals("<pre>   </pre>")
+        self.assertSoupEquals("<textarea> woo  </textarea>")
+
+    def test_nested_inline_elements(self):
+        """Inline elements can be nested indefinitely."""
+        b_tag = "<b>Inside a B tag</b>"
+        self.assertSoupEquals(b_tag)
+
+        nested_b_tag = "<p>A <i>nested <b>tag</b></i></p>"
+        self.assertSoupEquals(nested_b_tag)
+
+        double_nested_b_tag = "<p>A <a>doubly <i>nested <b>tag</b></i></a></p>"
+        self.assertSoupEquals(nested_b_tag)
+
+    def test_nested_block_level_elements(self):
+        """Block elements can be nested."""
+        soup = self.soup('<blockquote><p><b>Foo</b></p></blockquote>')
+        blockquote = soup.blockquote
+        self.assertEqual(blockquote.p.b.string, 'Foo')
+        self.assertEqual(blockquote.b.string, 'Foo')
+
+    def test_correctly_nested_tables(self):
+        """One table can go inside another one."""
+        markup = ('<table id="1">'
+                  '<tr>'
+                  "<td>Here's another table:"
+                  '<table id="2">'
+                  '<tr><td>foo</td></tr>'
+                  '</table></td>')
+
+        self.assertSoupEquals(
+            markup,
+            '<table id="1"><tr><td>Here\'s another table:'
+            '<table id="2"><tr><td>foo</td></tr></table>'
+            '</td></tr></table>')
+
+        self.assertSoupEquals(
+            "<table><thead><tr><td>Foo</td></tr></thead>"
+            "<tbody><tr><td>Bar</td></tr></tbody>"
+            "<tfoot><tr><td>Baz</td></tr></tfoot></table>")
+
+    def test_deeply_nested_multivalued_attribute(self):
+        # html5lib can set the attributes of the same tag many times
+        # as it rearranges the tree. This has caused problems with
+        # multivalued attributes.
+        markup = '<table><div><div class="css"></div></div></table>'
+        soup = self.soup(markup)
+        self.assertEqual(["css"], soup.div.div['class'])
+
+    def test_angle_brackets_in_attribute_values_are_escaped(self):
+        self.assertSoupEquals('<a b="<a>"></a>', '<a b="&lt;a&gt;"></a>')
+
+    def test_entities_in_attributes_converted_to_unicode(self):
+        expect = u'<p id="pi\N{LATIN SMALL LETTER N WITH TILDE}ata"></p>'
+        self.assertSoupEquals('<p id="pi&#241;ata"></p>', expect)
+        self.assertSoupEquals('<p id="pi&#xf1;ata"></p>', expect)
+        self.assertSoupEquals('<p id="pi&#Xf1;ata"></p>', expect)
+        self.assertSoupEquals('<p id="pi&ntilde;ata"></p>', expect)
+
+    def test_entities_in_text_converted_to_unicode(self):
+        expect = u'<p>pi\N{LATIN SMALL LETTER N WITH TILDE}ata</p>'
+        self.assertSoupEquals("<p>pi&#241;ata</p>", expect)
+        self.assertSoupEquals("<p>pi&#xf1;ata</p>", expect)
+        self.assertSoupEquals("<p>pi&#Xf1;ata</p>", expect)
+        self.assertSoupEquals("<p>pi&ntilde;ata</p>", expect)
+
+    def test_quot_entity_converted_to_quotation_mark(self):
+        self.assertSoupEquals("<p>I said &quot;good day!&quot;</p>",
+                              '<p>I said "good day!"</p>')
+
+    def test_out_of_range_entity(self):
+        expect = u"\N{REPLACEMENT CHARACTER}"
+        self.assertSoupEquals("&#10000000000000;", expect)
+        self.assertSoupEquals("&#x10000000000000;", expect)
+        self.assertSoupEquals("&#1000000000;", expect)
+
+    def test_multipart_strings(self):
+        "Mostly to prevent a recurrence of a bug in the html5lib treebuilder."
+        soup = self.soup("<html><h2>\nfoo</h2><p></p></html>")
+        self.assertEqual("p", soup.h2.string.next_element.name)
+        self.assertEqual("p", soup.p.name)
+
+    def test_basic_namespaces(self):
+        """Parsers don't need to *understand* namespaces, but at the
+        very least they should not choke on namespaces or lose
+        data."""
+
+        markup = b'<html xmlns="http://www.w3.org/1999/xhtml" xmlns:mathml="http://www.w3.org/1998/Math/MathML" xmlns:svg="http://www.w3.org/2000/svg"><head></head><body><mathml:msqrt>4</mathml:msqrt><b svg:fill="red"></b></body></html>'
+        soup = self.soup(markup)
+        self.assertEqual(markup, soup.encode())
+        html = soup.html
+        self.assertEqual('http://www.w3.org/1999/xhtml', soup.html['xmlns'])
+        self.assertEqual(
+            'http://www.w3.org/1998/Math/MathML', soup.html['xmlns:mathml'])
+        self.assertEqual(
+            'http://www.w3.org/2000/svg', soup.html['xmlns:svg'])
+
+    def test_multivalued_attribute_value_becomes_list(self):
+        markup = b'<a class="foo bar">'
+        soup = self.soup(markup)
+        self.assertEqual(['foo', 'bar'], soup.a['class'])
+
+    #
+    # Generally speaking, tests below this point are more tests of
+    # Beautiful Soup than tests of the tree builders. But parsers are
+    # weird, so we run these tests separately for every tree builder
+    # to detect any differences between them.
+    #
+
+    def test_can_parse_unicode_document(self):
+        # A seemingly innocuous document... but it's in Unicode! And
+        # it contains characters that can't be represented in the
+        # encoding found in the  declaration! The horror!
+        markup = u'<html><head><meta encoding="euc-jp"></head><body>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</body>'
+        soup = self.soup(markup)
+        self.assertEqual(u'Sacr\xe9 bleu!', soup.body.string)
+
+    def test_soupstrainer(self):
+        """Parsers should be able to work with SoupStrainers."""
+        strainer = SoupStrainer("b")
+        soup = self.soup("A <b>bold</b> <meta/> <i>statement</i>",
+                         parse_only=strainer)
+        self.assertEqual(soup.decode(), "<b>bold</b>")
+
+    def test_single_quote_attribute_values_become_double_quotes(self):
+        self.assertSoupEquals("<foo attr='bar'></foo>",
+                              '<foo attr="bar"></foo>')
+
+    def test_attribute_values_with_nested_quotes_are_left_alone(self):
+        text = """<foo attr='bar "brawls" happen'>a</foo>"""
+        self.assertSoupEquals(text)
+
+    def test_attribute_values_with_double_nested_quotes_get_quoted(self):
+        text = """<foo attr='bar "brawls" happen'>a</foo>"""
+        soup = self.soup(text)
+        soup.foo['attr'] = 'Brawls happen at "Bob\'s Bar"'
+        self.assertSoupEquals(
+            soup.foo.decode(),
+            """<foo attr="Brawls happen at &quot;Bob\'s Bar&quot;">a</foo>""")
+
+    def test_ampersand_in_attribute_value_gets_escaped(self):
+        self.assertSoupEquals('<this is="really messed up & stuff"></this>',
+                              '<this is="really messed up &amp; stuff"></this>')
+
+        self.assertSoupEquals(
+            '<a href="http://example.org?a=1&b=2;3">foo</a>',
+            '<a href="http://example.org?a=1&amp;b=2;3">foo</a>')
+
+    def test_escaped_ampersand_in_attribute_value_is_left_alone(self):
+        self.assertSoupEquals('<a href="http://example.org?a=1&amp;b=2;3"></a>')
+
+    def test_entities_in_strings_converted_during_parsing(self):
+        # Both XML and HTML entities are converted to Unicode characters
+        # during parsing.
+        text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
+        expected = u"<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>"
+        self.assertSoupEquals(text, expected)
+
+    def test_smart_quotes_converted_on_the_way_in(self):
+        # Microsoft smart quotes are converted to Unicode characters during
+        # parsing.
+        quote = b"<p>\x91Foo\x92</p>"
+        soup = self.soup(quote)
+        self.assertEqual(
+            soup.p.string,
+            u"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}")
+
+    def test_non_breaking_spaces_converted_on_the_way_in(self):
+        soup = self.soup("<a>&nbsp;&nbsp;</a>")
+        self.assertEqual(soup.a.string, u"\N{NO-BREAK SPACE}" * 2)
+
+    def test_entities_converted_on_the_way_out(self):
+        text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
+        expected = u"<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>".encode("utf-8")
+        soup = self.soup(text)
+        self.assertEqual(soup.p.encode("utf-8"), expected)
+
+    def test_real_iso_latin_document(self):
+        # Smoke test of interrelated functionality, using an
+        # easy-to-understand document.
+
+        # Here it is in Unicode. Note that it claims to be in ISO-Latin-1.
+        unicode_html = u'<html><head><meta content="text/html; charset=ISO-Latin-1" http-equiv="Content-type"/></head><body><p>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</p></body></html>'
+
+        # That's because we're going to encode it into ISO-Latin-1, and use
+        # that to test.
+        iso_latin_html = unicode_html.encode("iso-8859-1")
+
+        # Parse the ISO-Latin-1 HTML.
+        soup = self.soup(iso_latin_html)
+        # Encode it to UTF-8.
+        result = soup.encode("utf-8")
+
+        # What do we expect the result to look like? Well, it would
+        # look like unicode_html, except that the META tag would say
+        # UTF-8 instead of ISO-Latin-1.
+        expected = unicode_html.replace("ISO-Latin-1", "utf-8")
+
+        # And, of course, it would be in UTF-8, not Unicode.
+        expected = expected.encode("utf-8")
+
+        # Ta-da!
+        self.assertEqual(result, expected)
+
+    def test_real_shift_jis_document(self):
+        # Smoke test to make sure the parser can handle a document in
+        # Shift-JIS encoding, without choking.
+        shift_jis_html = (
+            b'<html><head></head><body><pre>'
+            b'\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
+            b'\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
+            b'\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B'
+            b'</pre></body></html>')
+        unicode_html = shift_jis_html.decode("shift-jis")
+        soup = self.soup(unicode_html)
+
+        # Make sure the parse tree is correctly encoded to various
+        # encodings.
+        self.assertEqual(soup.encode("utf-8"), unicode_html.encode("utf-8"))
+        self.assertEqual(soup.encode("euc_jp"), unicode_html.encode("euc_jp"))
+
+    def test_real_hebrew_document(self):
+        # A real-world test to make sure we can convert ISO-8859-9 (a
+        # Hebrew encoding) to UTF-8.
+        hebrew_document = b'<html><head><title>Hebrew (ISO 8859-8) in Visual Directionality</title></head><body><h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\xed\xe5\xec\xf9</body></html>'
+        soup = self.soup(
+            hebrew_document, from_encoding="iso8859-8")
+        self.assertEqual(soup.original_encoding, 'iso8859-8')
+        self.assertEqual(
+            soup.encode('utf-8'),
+            hebrew_document.decode("iso8859-8").encode("utf-8"))
+
+    def test_meta_tag_reflects_current_encoding(self):
+        # Here's the <meta> tag saying that a document is
+        # encoded in Shift-JIS.
+        meta_tag = ('<meta content="text/html; charset=x-sjis" '
+                    'http-equiv="Content-type"/>')
+
+        # Here's a document incorporating that meta tag.
+        shift_jis_html = (
+            '<html><head>\n%s\n'
+            '<meta http-equiv="Content-language" content="ja"/>'
+            '</head><body>Shift-JIS markup goes here.') % meta_tag
+        soup = self.soup(shift_jis_html)
+
+        # Parse the document, and the charset is seemingly unaffected.
+        parsed_meta = soup.find('meta', {'http-equiv': 'Content-type'})
+        content = parsed_meta['content']
+        self.assertEqual('text/html; charset=x-sjis', content)
+
+        # But that value is actually a ContentMetaAttributeValue object.
+        self.assertTrue(isinstance(content, ContentMetaAttributeValue))
+
+        # And it will take on a value that reflects its current
+        # encoding.
+        self.assertEqual('text/html; charset=utf8', content.encode("utf8"))
+
+        # For the rest of the story, see TestSubstitutions in
+        # test_tree.py.
+
+    def test_html5_style_meta_tag_reflects_current_encoding(self):
+        # Here's the <meta> tag saying that a document is
+        # encoded in Shift-JIS.
+        meta_tag = ('<meta id="encoding" charset="x-sjis" />')
+
+        # Here's a document incorporating that meta tag.
+        shift_jis_html = (
+            '<html><head>\n%s\n'
+            '<meta http-equiv="Content-language" content="ja"/>'
+            '</head><body>Shift-JIS markup goes here.') % meta_tag
+        soup = self.soup(shift_jis_html)
+
+        # Parse the document, and the charset is seemingly unaffected.
+        parsed_meta = soup.find('meta', id="encoding")
+        charset = parsed_meta['charset']
+        self.assertEqual('x-sjis', charset)
+
+        # But that value is actually a CharsetMetaAttributeValue object.
+        self.assertTrue(isinstance(charset, CharsetMetaAttributeValue))
+
+        # And it will take on a value that reflects its current
+        # encoding.
+        self.assertEqual('utf8', charset.encode("utf8"))
+
+    def test_tag_with_no_attributes_can_have_attributes_added(self):
+        data = self.soup("<a>text</a>")
+        data.a['foo'] = 'bar'
+        self.assertEqual('<a foo="bar">text</a>', data.a.decode())
+
+class XMLTreeBuilderSmokeTest(object):
+
+    def test_docstring_generated(self):
+        soup = self.soup("<root/>")
+        self.assertEqual(
+            soup.encode(), b'<?xml version="1.0" encoding="utf-8"?>\n<root/>')
+
+    def test_real_xhtml_document(self):
+        """A real XHTML document should come out *exactly* the same as it went in."""
+        markup = b"""<?xml version="1.0" encoding="utf-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head><title>Hello.</title></head>
+<body>Goodbye.</body>
+</html>"""
+        soup = self.soup(markup)
+        self.assertEqual(
+            soup.encode("utf-8"), markup)
+
+    def test_formatter_processes_script_tag_for_xml_documents(self):
+        doc = """
+  <script type="text/javascript">
+  </script>
+"""
+        soup = BeautifulSoup(doc, "xml")
+        # lxml would have stripped this while parsing, but we can add
+        # it later.
+        soup.script.string = 'console.log("< < hey > > ");'
+        encoded = soup.encode()
+        self.assertTrue(b"&lt; &lt; hey &gt; &gt;" in encoded)
+
+    def test_can_parse_unicode_document(self):
+        markup = u'<?xml version="1.0" encoding="euc-jp"><root>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</root>'
+        soup = self.soup(markup)
+        self.assertEqual(u'Sacr\xe9 bleu!', soup.root.string)
+
+    def test_popping_namespaced_tag(self):
+        markup = '<rss xmlns:dc="foo"><dc:creator>b</dc:creator><dc:date>2012-07-02T20:33:42Z</dc:date><dc:rights>c</dc:rights><image>d</image></rss>'
+        soup = self.soup(markup)
+        self.assertEqual(
+            unicode(soup.rss), markup)
+
+    def test_docstring_includes_correct_encoding(self):
+        soup = self.soup("<root/>")
+        self.assertEqual(
+            soup.encode("latin1"),
+            b'<?xml version="1.0" encoding="latin1"?>\n<root/>')
+
+    def test_large_xml_document(self):
+        """A large XML document should come out the same as it went in."""
+        markup = (b'<?xml version="1.0" encoding="utf-8"?>\n<root>'
+                  + b'0' * (2**12)
+                  + b'</root>')
+        soup = self.soup(markup)
+        self.assertEqual(soup.encode("utf-8"), markup)
+
+
+    def test_tags_are_empty_element_if_and_only_if_they_are_empty(self):
+        self.assertSoupEquals("<p>", "<p/>")
+        self.assertSoupEquals("<p>foo</p>")
+
+    def test_namespaces_are_preserved(self):
+        markup = '<root xmlns:a="http://example.com/" xmlns:b="http://example.net/"><a:foo>This tag is in the a namespace</a:foo><b:foo>This tag is in the b namespace</b:foo></root>'
+        soup = self.soup(markup)
+        root = soup.root
+        self.assertEqual("http://example.com/", root['xmlns:a'])
+        self.assertEqual("http://example.net/", root['xmlns:b'])
+
+    def test_closing_namespaced_tag(self):
+        markup = '<p xmlns:dc="http://purl.org/dc/elements/1.1/"><dc:date>20010504</dc:date></p>'
+        soup = self.soup(markup)
+        self.assertEqual(unicode(soup.p), markup)
+
+    def test_namespaced_attributes(self):
+        markup = '<foo xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><bar xsi:schemaLocation="http://www.example.com"/></foo>'
+        soup = self.soup(markup)
+        self.assertEqual(unicode(soup.foo), markup)
+
+    def test_namespaced_attributes_xml_namespace(self):
+        markup = '<foo xml:lang="fr">bar</foo>'
+        soup = self.soup(markup)
+        self.assertEqual(unicode(soup.foo), markup)
+
+class HTML5TreeBuilderSmokeTest(HTMLTreeBuilderSmokeTest):
+    """Smoke test for a tree builder that supports HTML5."""
+
+    def test_real_xhtml_document(self):
+        # Since XHTML is not HTML5, HTML5 parsers are not tested to handle
+        # XHTML documents in any particular way.
+        pass
+
+    def test_html_tags_have_namespace(self):
+        markup = "<a>"
+        soup = self.soup(markup)
+        self.assertEqual("http://www.w3.org/1999/xhtml", soup.a.namespace)
+
+    def test_svg_tags_have_namespace(self):
+        markup = '<svg><circle/></svg>'
+        soup = self.soup(markup)
+        namespace = "http://www.w3.org/2000/svg"
+        self.assertEqual(namespace, soup.svg.namespace)
+        self.assertEqual(namespace, soup.circle.namespace)
+
+
+    def test_mathml_tags_have_namespace(self):
+        markup = '<math><msqrt>5</msqrt></math>'
+        soup = self.soup(markup)
+        namespace = 'http://www.w3.org/1998/Math/MathML'
+        self.assertEqual(namespace, soup.math.namespace)
+        self.assertEqual(namespace, soup.msqrt.namespace)
+
+    def test_xml_declaration_becomes_comment(self):
+        markup = '<?xml version="1.0" encoding="utf-8"?><html></html>'
+        soup = self.soup(markup)
+        self.assertTrue(isinstance(soup.contents[0], Comment))
+        self.assertEqual(soup.contents[0], '?xml version="1.0" encoding="utf-8"?')
+        self.assertEqual("html", soup.contents[0].next_element.name)
+
+def skipIf(condition, reason):
+   def nothing(test, *args, **kwargs):
+       return None
+
+   def decorator(test_item):
+       if condition:
+           return nothing
+       else:
+           return test_item
+
+   return decorator

bitbake/lib/bs4/tests/__init__.py

@@ -0,0 +1 @@
+"The beautifulsoup tests."

bitbake/lib/bs4/tests/test_builder_registry.py

@@ -0,0 +1,141 @@
+"""Tests of the builder registry."""
+
+import unittest
+
+from bs4 import BeautifulSoup
+from bs4.builder import (
+    builder_registry as registry,
+    HTMLParserTreeBuilder,
+    TreeBuilderRegistry,
+)
+
+try:
+    from bs4.builder import HTML5TreeBuilder
+    HTML5LIB_PRESENT = True
+except ImportError:
+    HTML5LIB_PRESENT = False
+
+try:
+    from bs4.builder import (
+        LXMLTreeBuilderForXML,
+        LXMLTreeBuilder,
+        )
+    LXML_PRESENT = True
+except ImportError:
+    LXML_PRESENT = False
+
+
+class BuiltInRegistryTest(unittest.TestCase):
+    """Test the built-in registry with the default builders registered."""
+
+    def test_combination(self):
+        if LXML_PRESENT:
+            self.assertEqual(registry.lookup('fast', 'html'),
+                             LXMLTreeBuilder)
+
+        if LXML_PRESENT:
+            self.assertEqual(registry.lookup('permissive', 'xml'),
+                             LXMLTreeBuilderForXML)
+        self.assertEqual(registry.lookup('strict', 'html'),
+                          HTMLParserTreeBuilder)
+        if HTML5LIB_PRESENT:
+            self.assertEqual(registry.lookup('html5lib', 'html'),
+                              HTML5TreeBuilder)
+
+    def test_lookup_by_markup_type(self):
+        if LXML_PRESENT:
+            self.assertEqual(registry.lookup('html'), LXMLTreeBuilder)
+            self.assertEqual(registry.lookup('xml'), LXMLTreeBuilderForXML)
+        else:
+            self.assertEqual(registry.lookup('xml'), None)
+            if HTML5LIB_PRESENT:
+                self.assertEqual(registry.lookup('html'), HTML5TreeBuilder)
+            else:
+                self.assertEqual(registry.lookup('html'), HTMLParserTreeBuilder)
+
+    def test_named_library(self):
+        if LXML_PRESENT:
+            self.assertEqual(registry.lookup('lxml', 'xml'),
+                             LXMLTreeBuilderForXML)
+            self.assertEqual(registry.lookup('lxml', 'html'),
+                             LXMLTreeBuilder)
+        if HTML5LIB_PRESENT:
+            self.assertEqual(registry.lookup('html5lib'),
+                              HTML5TreeBuilder)
+
+        self.assertEqual(registry.lookup('html.parser'),
+                          HTMLParserTreeBuilder)
+
+    def test_beautifulsoup_constructor_does_lookup(self):
+        # You can pass in a string.
+        BeautifulSoup("", features="html")
+        # Or a list of strings.
+        BeautifulSoup("", features=["html", "fast"])
+
+        # You'll get an exception if BS can't find an appropriate
+        # builder.
+        self.assertRaises(ValueError, BeautifulSoup,
+                          "", features="no-such-feature")
+
+class RegistryTest(unittest.TestCase):
+    """Test the TreeBuilderRegistry class in general."""
+
+    def setUp(self):
+        self.registry = TreeBuilderRegistry()
+
+    def builder_for_features(self, *feature_list):
+        cls = type('Builder_' + '_'.join(feature_list),
+                   (object,), {'features' : feature_list})
+
+        self.registry.register(cls)
+        return cls
+
+    def test_register_with_no_features(self):
+        builder = self.builder_for_features()
+
+        # Since the builder advertises no features, you can't find it
+        # by looking up features.
+        self.assertEqual(self.registry.lookup('foo'), None)
+
+        # But you can find it by doing a lookup with no features, if
+        # this happens to be the only registered builder.
+        self.assertEqual(self.registry.lookup(), builder)
+
+    def test_register_with_features_makes_lookup_succeed(self):
+        builder = self.builder_for_features('foo', 'bar')
+        self.assertEqual(self.registry.lookup('foo'), builder)
+        self.assertEqual(self.registry.lookup('bar'), builder)
+
+    def test_lookup_fails_when_no_builder_implements_feature(self):
+        builder = self.builder_for_features('foo', 'bar')
+        self.assertEqual(self.registry.lookup('baz'), None)
+
+    def test_lookup_gets_most_recent_registration_when_no_feature_specified(self):
+        builder1 = self.builder_for_features('foo')
+        builder2 = self.builder_for_features('bar')
+        self.assertEqual(self.registry.lookup(), builder2)
+
+    def test_lookup_fails_when_no_tree_builders_registered(self):
+        self.assertEqual(self.registry.lookup(), None)
+
+    def test_lookup_gets_most_recent_builder_supporting_all_features(self):
+        has_one = self.builder_for_features('foo')
+        has_the_other = self.builder_for_features('bar')
+        has_both_early = self.builder_for_features('foo', 'bar', 'baz')
+        has_both_late = self.builder_for_features('foo', 'bar', 'quux')
+        lacks_one = self.builder_for_features('bar')
+        has_the_other = self.builder_for_features('foo')
+
+        # There are two builders featuring 'foo' and 'bar', but
+        # the one that also features 'quux' was registered later.
+        self.assertEqual(self.registry.lookup('foo', 'bar'),
+                          has_both_late)
+
+        # There is only one builder featuring 'foo', 'bar', and 'baz'.
+        self.assertEqual(self.registry.lookup('foo', 'bar', 'baz'),
+                          has_both_early)
+
+    def test_lookup_fails_when_cannot_reconcile_requested_features(self):
+        builder1 = self.builder_for_features('foo', 'bar')
+        builder2 = self.builder_for_features('foo', 'baz')
+        self.assertEqual(self.registry.lookup('bar', 'baz'), None)

bitbake/lib/bs4/tests/test_docs.py

@@ -0,0 +1,36 @@
+"Test harness for doctests."
+
+# pylint: disable-msg=E0611,W0142
+
+__metaclass__ = type
+__all__ = [
+    'additional_tests',
+    ]
+
+import atexit
+import doctest
+import os
+#from pkg_resources import (
+#    resource_filename, resource_exists, resource_listdir, cleanup_resources)
+import unittest
+
+DOCTEST_FLAGS = (
+    doctest.ELLIPSIS |
+    doctest.NORMALIZE_WHITESPACE |
+    doctest.REPORT_NDIFF)
+
+
+# def additional_tests():
+#     "Run the doc tests (README.txt and docs/*, if any exist)"
+#     doctest_files = [
+#         os.path.abspath(resource_filename('bs4', 'README.txt'))]
+#     if resource_exists('bs4', 'docs'):
+#         for name in resource_listdir('bs4', 'docs'):
+#             if name.endswith('.txt'):
+#                 doctest_files.append(
+#                     os.path.abspath(
+#                         resource_filename('bs4', 'docs/%s' % name)))
+#     kwargs = dict(module_relative=False, optionflags=DOCTEST_FLAGS)
+#     atexit.register(cleanup_resources)
+#     return unittest.TestSuite((
+#         doctest.DocFileSuite(*doctest_files, **kwargs)))

bitbake/lib/bs4/tests/test_html5lib.py

@@ -0,0 +1,85 @@
+"""Tests to ensure that the html5lib tree builder generates good trees."""
+
+import warnings
+
+try:
+    from bs4.builder import HTML5TreeBuilder
+    HTML5LIB_PRESENT = True
+except ImportError, e:
+    HTML5LIB_PRESENT = False
+from bs4.element import SoupStrainer
+from bs4.testing import (
+    HTML5TreeBuilderSmokeTest,
+    SoupTest,
+    skipIf,
+)
+
+@skipIf(
+    not HTML5LIB_PRESENT,
+    "html5lib seems not to be present, not testing its tree builder.")
+class HTML5LibBuilderSmokeTest(SoupTest, HTML5TreeBuilderSmokeTest):
+    """See ``HTML5TreeBuilderSmokeTest``."""
+
+    @property
+    def default_builder(self):
+        return HTML5TreeBuilder()
+
+    def test_soupstrainer(self):
+        # The html5lib tree builder does not support SoupStrainers.
+        strainer = SoupStrainer("b")
+        markup = "<p>A <b>bold</b> statement.</p>"
+        with warnings.catch_warnings(record=True) as w:
+            soup = self.soup(markup, parse_only=strainer)
+        self.assertEqual(
+            soup.decode(), self.document_for(markup))
+
+        self.assertTrue(
+            "the html5lib tree builder doesn't support parse_only" in
+            str(w[0].message))
+
+    def test_correctly_nested_tables(self):
+        """html5lib inserts <tbody> tags where other parsers don't."""
+        markup = ('<table id="1">'
+                  '<tr>'
+                  "<td>Here's another table:"
+                  '<table id="2">'
+                  '<tr><td>foo</td></tr>'
+                  '</table></td>')
+
+        self.assertSoupEquals(
+            markup,
+            '<table id="1"><tbody><tr><td>Here\'s another table:'
+            '<table id="2"><tbody><tr><td>foo</td></tr></tbody></table>'
+            '</td></tr></tbody></table>')
+
+        self.assertSoupEquals(
+            "<table><thead><tr><td>Foo</td></tr></thead>"
+            "<tbody><tr><td>Bar</td></tr></tbody>"
+            "<tfoot><tr><td>Baz</td></tr></tfoot></table>")
+
+    def test_xml_declaration_followed_by_doctype(self):
+        markup = '''<?xml version="1.0" encoding="utf-8"?>
+<!DOCTYPE html>
+<html>
+  <head>
+  </head>
+  <body>
+   <p>foo</p>
+  </body>
+</html>'''
+        soup = self.soup(markup)
+        # Verify that we can reach the <p> tag; this means the tree is connected.
+        self.assertEqual(b"<p>foo</p>", soup.p.encode())
+
+    def test_reparented_markup(self):
+        markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>'
+        soup = self.soup(markup)
+        self.assertEqual(u"<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p></body>", soup.body.decode())
+        self.assertEqual(2, len(soup.find_all('p')))
+
+
+    def test_reparented_markup_ends_with_whitespace(self):
+        markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>\n'
+        soup = self.soup(markup)
+        self.assertEqual(u"<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p>\n</body>", soup.body.decode())
+        self.assertEqual(2, len(soup.find_all('p')))

bitbake/lib/bs4/tests/test_htmlparser.py

@@ -0,0 +1,19 @@
+"""Tests to ensure that the html.parser tree builder generates good
+trees."""
+
+from bs4.testing import SoupTest, HTMLTreeBuilderSmokeTest
+from bs4.builder import HTMLParserTreeBuilder
+
+class HTMLParserTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
+
+    @property
+    def default_builder(self):
+        return HTMLParserTreeBuilder()
+
+    def test_namespaced_system_doctype(self):
+        # html.parser can't handle namespaced doctypes, so skip this one.
+        pass
+
+    def test_namespaced_public_doctype(self):
+        # html.parser can't handle namespaced doctypes, so skip this one.
+        pass

bitbake/lib/bs4/tests/test_lxml.py

@@ -0,0 +1,91 @@
+"""Tests to ensure that the lxml tree builder generates good trees."""
+
+import re
+import warnings
+
+try:
+    import lxml.etree
+    LXML_PRESENT = True
+    LXML_VERSION = lxml.etree.LXML_VERSION
+except ImportError, e:
+    LXML_PRESENT = False
+    LXML_VERSION = (0,)
+
+if LXML_PRESENT:
+    from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
+
+from bs4 import (
+    BeautifulSoup,
+    BeautifulStoneSoup,
+    )
+from bs4.element import Comment, Doctype, SoupStrainer
+from bs4.testing import skipIf
+from bs4.tests import test_htmlparser
+from bs4.testing import (
+    HTMLTreeBuilderSmokeTest,
+    XMLTreeBuilderSmokeTest,
+    SoupTest,
+    skipIf,
+)
+
+@skipIf(
+    not LXML_PRESENT,
+    "lxml seems not to be present, not testing its tree builder.")
+class LXMLTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
+    """See ``HTMLTreeBuilderSmokeTest``."""
+
+    @property
+    def default_builder(self):
+        return LXMLTreeBuilder()
+
+    def test_out_of_range_entity(self):
+        self.assertSoupEquals(
+            "<p>foo&#10000000000000;bar</p>", "<p>foobar</p>")
+        self.assertSoupEquals(
+            "<p>foo&#x10000000000000;bar</p>", "<p>foobar</p>")
+        self.assertSoupEquals(
+            "<p>foo&#1000000000;bar</p>", "<p>foobar</p>")
+
+    # In lxml < 2.3.5, an empty doctype causes a segfault. Skip this
+    # test if an old version of lxml is installed.
+
+    @skipIf(
+        not LXML_PRESENT or LXML_VERSION < (2,3,5,0),
+        "Skipping doctype test for old version of lxml to avoid segfault.")
+    def test_empty_doctype(self):
+        soup = self.soup("<!DOCTYPE>")
+        doctype = soup.contents[0]
+        self.assertEqual("", doctype.strip())
+
+    def test_beautifulstonesoup_is_xml_parser(self):
+        # Make sure that the deprecated BSS class uses an xml builder
+        # if one is installed.
+        with warnings.catch_warnings(record=True) as w:
+            soup = BeautifulStoneSoup("<b />")
+        self.assertEqual(u"<b/>", unicode(soup.b))
+        self.assertTrue("BeautifulStoneSoup class is deprecated" in str(w[0].message))
+
+    def test_real_xhtml_document(self):
+        """lxml strips the XML definition from an XHTML doc, which is fine."""
+        markup = b"""<?xml version="1.0" encoding="utf-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head><title>Hello.</title></head>
+<body>Goodbye.</body>
+</html>"""
+        soup = self.soup(markup)
+        self.assertEqual(
+            soup.encode("utf-8").replace(b"\n", b''),
+            markup.replace(b'\n', b'').replace(
+                b'<?xml version="1.0" encoding="utf-8"?>', b''))
+
+
+@skipIf(
+    not LXML_PRESENT,
+    "lxml seems not to be present, not testing its XML tree builder.")
+class LXMLXMLTreeBuilderSmokeTest(SoupTest, XMLTreeBuilderSmokeTest):
+    """See ``HTMLTreeBuilderSmokeTest``."""
+
+    @property
+    def default_builder(self):
+        return LXMLTreeBuilderForXML()

bitbake/lib/bs4/tests/test_soup.py

@@ -0,0 +1,434 @@
+# -*- coding: utf-8 -*-
+"""Tests of Beautiful Soup as a whole."""
+
+import logging
+import unittest
+import sys
+import tempfile
+
+from bs4 import (
+    BeautifulSoup,
+    BeautifulStoneSoup,
+)
+from bs4.element import (
+    CharsetMetaAttributeValue,
+    ContentMetaAttributeValue,
+    SoupStrainer,
+    NamespacedAttribute,
+    )
+import bs4.dammit
+from bs4.dammit import (
+    EntitySubstitution,
+    UnicodeDammit,
+)
+from bs4.testing import (
+    SoupTest,
+    skipIf,
+)
+import warnings
+
+try:
+    from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
+    LXML_PRESENT = True
+except ImportError, e:
+    LXML_PRESENT = False
+
+PYTHON_2_PRE_2_7 = (sys.version_info < (2,7))
+PYTHON_3_PRE_3_2 = (sys.version_info[0] == 3 and sys.version_info < (3,2))
+
+class TestConstructor(SoupTest):
+
+    def test_short_unicode_input(self):
+        data = u"<h1>éé</h1>"
+        soup = self.soup(data)
+        self.assertEqual(u"éé", soup.h1.string)
+
+    def test_embedded_null(self):
+        data = u"<h1>foo\0bar</h1>"
+        soup = self.soup(data)
+        self.assertEqual(u"foo\0bar", soup.h1.string)
+
+
+class TestDeprecatedConstructorArguments(SoupTest):
+
+    def test_parseOnlyThese_renamed_to_parse_only(self):
+        with warnings.catch_warnings(record=True) as w:
+            soup = self.soup("<a><b></b></a>", parseOnlyThese=SoupStrainer("b"))
+        msg = str(w[0].message)
+        self.assertTrue("parseOnlyThese" in msg)
+        self.assertTrue("parse_only" in msg)
+        self.assertEqual(b"<b></b>", soup.encode())
+
+    def test_fromEncoding_renamed_to_from_encoding(self):
+        with warnings.catch_warnings(record=True) as w:
+            utf8 = b"\xc3\xa9"
+            soup = self.soup(utf8, fromEncoding="utf8")
+        msg = str(w[0].message)
+        self.assertTrue("fromEncoding" in msg)
+        self.assertTrue("from_encoding" in msg)
+        self.assertEqual("utf8", soup.original_encoding)
+
+    def test_unrecognized_keyword_argument(self):
+        self.assertRaises(
+            TypeError, self.soup, "<a>", no_such_argument=True)
+
+class TestWarnings(SoupTest):
+
+    def test_disk_file_warning(self):
+        filehandle = tempfile.NamedTemporaryFile()
+        filename = filehandle.name
+        try:
+            with warnings.catch_warnings(record=True) as w:
+                soup = self.soup(filename)
+            msg = str(w[0].message)
+            self.assertTrue("looks like a filename" in msg)
+        finally:
+            filehandle.close()
+
+        # The file no longer exists, so Beautiful Soup will no longer issue the warning.
+        with warnings.catch_warnings(record=True) as w:
+            soup = self.soup(filename)
+        self.assertEqual(0, len(w))
+
+    def test_url_warning(self):
+        with warnings.catch_warnings(record=True) as w:
+            soup = self.soup("http://www.crummy.com/")
+        msg = str(w[0].message)
+        self.assertTrue("looks like a URL" in msg)
+
+        with warnings.catch_warnings(record=True) as w:
+            soup = self.soup("http://www.crummy.com/ is great")
+        self.assertEqual(0, len(w))
+
+class TestSelectiveParsing(SoupTest):
+
+    def test_parse_with_soupstrainer(self):
+        markup = "No<b>Yes</b><a>No<b>Yes <c>Yes</c></b>"
+        strainer = SoupStrainer("b")
+        soup = self.soup(markup, parse_only=strainer)
+        self.assertEqual(soup.encode(), b"<b>Yes</b><b>Yes <c>Yes</c></b>")
+
+
+class TestEntitySubstitution(unittest.TestCase):
+    """Standalone tests of the EntitySubstitution class."""
+    def setUp(self):
+        self.sub = EntitySubstitution
+
+    def test_simple_html_substitution(self):
+        # Unicode characters corresponding to named HTML entites
+        # are substituted, and no others.
+        s = u"foo\u2200\N{SNOWMAN}\u00f5bar"
+        self.assertEqual(self.sub.substitute_html(s),
+                          u"foo&forall;\N{SNOWMAN}&otilde;bar")
+
+    def test_smart_quote_substitution(self):
+        # MS smart quotes are a common source of frustration, so we
+        # give them a special test.
+        quotes = b"\x91\x92foo\x93\x94"
+        dammit = UnicodeDammit(quotes)
+        self.assertEqual(self.sub.substitute_html(dammit.markup),
+                          "&lsquo;&rsquo;foo&ldquo;&rdquo;")
+
+    def test_xml_converstion_includes_no_quotes_if_make_quoted_attribute_is_false(self):
+        s = 'Welcome to "my bar"'
+        self.assertEqual(self.sub.substitute_xml(s, False), s)
+
+    def test_xml_attribute_quoting_normally_uses_double_quotes(self):
+        self.assertEqual(self.sub.substitute_xml("Welcome", True),
+                          '"Welcome"')
+        self.assertEqual(self.sub.substitute_xml("Bob's Bar", True),
+                          '"Bob\'s Bar"')
+
+    def test_xml_attribute_quoting_uses_single_quotes_when_value_contains_double_quotes(self):
+        s = 'Welcome to "my bar"'
+        self.assertEqual(self.sub.substitute_xml(s, True),
+                          "'Welcome to \"my bar\"'")
+
+    def test_xml_attribute_quoting_escapes_single_quotes_when_value_contains_both_single_and_double_quotes(self):
+        s = 'Welcome to "Bob\'s Bar"'
+        self.assertEqual(
+            self.sub.substitute_xml(s, True),
+            '"Welcome to &quot;Bob\'s Bar&quot;"')
+
+    def test_xml_quotes_arent_escaped_when_value_is_not_being_quoted(self):
+        quoted = 'Welcome to "Bob\'s Bar"'
+        self.assertEqual(self.sub.substitute_xml(quoted), quoted)
+
+    def test_xml_quoting_handles_angle_brackets(self):
+        self.assertEqual(
+            self.sub.substitute_xml("foo<bar>"),
+            "foo&lt;bar&gt;")
+
+    def test_xml_quoting_handles_ampersands(self):
+        self.assertEqual(self.sub.substitute_xml("AT&T"), "AT&amp;T")
+
+    def test_xml_quoting_including_ampersands_when_they_are_part_of_an_entity(self):
+        self.assertEqual(
+            self.sub.substitute_xml("&Aacute;T&T"),
+            "&amp;Aacute;T&amp;T")
+
+    def test_xml_quoting_ignoring_ampersands_when_they_are_part_of_an_entity(self):
+        self.assertEqual(
+            self.sub.substitute_xml_containing_entities("&Aacute;T&T"),
+            "&Aacute;T&amp;T")
+
+    def test_quotes_not_html_substituted(self):
+        """There's no need to do this except inside attribute values."""
+        text = 'Bob\'s "bar"'
+        self.assertEqual(self.sub.substitute_html(text), text)
+
+
+class TestEncodingConversion(SoupTest):
+    # Test Beautiful Soup's ability to decode and encode from various
+    # encodings.
+
+    def setUp(self):
+        super(TestEncodingConversion, self).setUp()
+        self.unicode_data = u'<html><head><meta charset="utf-8"/></head><body><foo>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</foo></body></html>'
+        self.utf8_data = self.unicode_data.encode("utf-8")
+        # Just so you know what it looks like.
+        self.assertEqual(
+            self.utf8_data,
+            b'<html><head><meta charset="utf-8"/></head><body><foo>Sacr\xc3\xa9 bleu!</foo></body></html>')
+
+    def test_ascii_in_unicode_out(self):
+        # ASCII input is converted to Unicode. The original_encoding
+        # attribute is set to 'utf-8', a superset of ASCII.
+        chardet = bs4.dammit.chardet_dammit
+        logging.disable(logging.WARNING)
+        try:
+            def noop(str):
+                return None
+            # Disable chardet, which will realize that the ASCII is ASCII.
+            bs4.dammit.chardet_dammit = noop
+            ascii = b"<foo>a</foo>"
+            soup_from_ascii = self.soup(ascii)
+            unicode_output = soup_from_ascii.decode()
+            self.assertTrue(isinstance(unicode_output, unicode))
+            self.assertEqual(unicode_output, self.document_for(ascii.decode()))
+            self.assertEqual(soup_from_ascii.original_encoding.lower(), "utf-8")
+        finally:
+            logging.disable(logging.NOTSET)
+            bs4.dammit.chardet_dammit = chardet
+
+    def test_unicode_in_unicode_out(self):
+        # Unicode input is left alone. The original_encoding attribute
+        # is not set.
+        soup_from_unicode = self.soup(self.unicode_data)
+        self.assertEqual(soup_from_unicode.decode(), self.unicode_data)
+        self.assertEqual(soup_from_unicode.foo.string, u'Sacr\xe9 bleu!')
+        self.assertEqual(soup_from_unicode.original_encoding, None)
+
+    def test_utf8_in_unicode_out(self):
+        # UTF-8 input is converted to Unicode. The original_encoding
+        # attribute is set.
+        soup_from_utf8 = self.soup(self.utf8_data)
+        self.assertEqual(soup_from_utf8.decode(), self.unicode_data)
+        self.assertEqual(soup_from_utf8.foo.string, u'Sacr\xe9 bleu!')
+
+    def test_utf8_out(self):
+        # The internal data structures can be encoded as UTF-8.
+        soup_from_unicode = self.soup(self.unicode_data)
+        self.assertEqual(soup_from_unicode.encode('utf-8'), self.utf8_data)
+
+    @skipIf(
+        PYTHON_2_PRE_2_7 or PYTHON_3_PRE_3_2,
+        "Bad HTMLParser detected; skipping test of non-ASCII characters in attribute name.")
+    def test_attribute_name_containing_unicode_characters(self):
+        markup = u'<div><a \N{SNOWMAN}="snowman"></a></div>'
+        self.assertEqual(self.soup(markup).div.encode("utf8"), markup.encode("utf8"))
+
+class TestUnicodeDammit(unittest.TestCase):
+    """Standalone tests of UnicodeDammit."""
+
+    def test_unicode_input(self):
+        markup = u"I'm already Unicode! \N{SNOWMAN}"
+        dammit = UnicodeDammit(markup)
+        self.assertEqual(dammit.unicode_markup, markup)
+
+    def test_smart_quotes_to_unicode(self):
+        markup = b"<foo>\x91\x92\x93\x94</foo>"
+        dammit = UnicodeDammit(markup)
+        self.assertEqual(
+            dammit.unicode_markup, u"<foo>\u2018\u2019\u201c\u201d</foo>")
+
+    def test_smart_quotes_to_xml_entities(self):
+        markup = b"<foo>\x91\x92\x93\x94</foo>"
+        dammit = UnicodeDammit(markup, smart_quotes_to="xml")
+        self.assertEqual(
+            dammit.unicode_markup, "<foo>&#x2018;&#x2019;&#x201C;&#x201D;</foo>")
+
+    def test_smart_quotes_to_html_entities(self):
+        markup = b"<foo>\x91\x92\x93\x94</foo>"
+        dammit = UnicodeDammit(markup, smart_quotes_to="html")
+        self.assertEqual(
+            dammit.unicode_markup, "<foo>&lsquo;&rsquo;&ldquo;&rdquo;</foo>")
+
+    def test_smart_quotes_to_ascii(self):
+        markup = b"<foo>\x91\x92\x93\x94</foo>"
+        dammit = UnicodeDammit(markup, smart_quotes_to="ascii")
+        self.assertEqual(
+            dammit.unicode_markup, """<foo>''""</foo>""")
+
+    def test_detect_utf8(self):
+        utf8 = b"\xc3\xa9"
+        dammit = UnicodeDammit(utf8)
+        self.assertEqual(dammit.unicode_markup, u'\xe9')
+        self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
+
+    def test_convert_hebrew(self):
+        hebrew = b"\xed\xe5\xec\xf9"
+        dammit = UnicodeDammit(hebrew, ["iso-8859-8"])
+        self.assertEqual(dammit.original_encoding.lower(), 'iso-8859-8')
+        self.assertEqual(dammit.unicode_markup, u'\u05dd\u05d5\u05dc\u05e9')
+
+    def test_dont_see_smart_quotes_where_there_are_none(self):
+        utf_8 = b"\343\202\261\343\203\274\343\202\277\343\202\244 Watch"
+        dammit = UnicodeDammit(utf_8)
+        self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
+        self.assertEqual(dammit.unicode_markup.encode("utf-8"), utf_8)
+
+    def test_ignore_inappropriate_codecs(self):
+        utf8_data = u"Räksmörgås".encode("utf-8")
+        dammit = UnicodeDammit(utf8_data, ["iso-8859-8"])
+        self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
+
+    def test_ignore_invalid_codecs(self):
+        utf8_data = u"Räksmörgås".encode("utf-8")
+        for bad_encoding in ['.utf8', '...', 'utF---16.!']:
+            dammit = UnicodeDammit(utf8_data, [bad_encoding])
+            self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
+
+    def test_detect_html5_style_meta_tag(self):
+
+        for data in (
+            b'<html><meta charset="euc-jp" /></html>',
+            b"<html><meta charset='euc-jp' /></html>",
+            b"<html><meta charset=euc-jp /></html>",
+            b"<html><meta charset=euc-jp/></html>"):
+            dammit = UnicodeDammit(data, is_html=True)
+            self.assertEqual(
+                "euc-jp", dammit.original_encoding)
+
+    def test_last_ditch_entity_replacement(self):
+        # This is a UTF-8 document that contains bytestrings
+        # completely incompatible with UTF-8 (ie. encoded with some other
+        # encoding).
+        #
+        # Since there is no consistent encoding for the document,
+        # Unicode, Dammit will eventually encode the document as UTF-8
+        # and encode the incompatible characters as REPLACEMENT
+        # CHARACTER.
+        #
+        # If chardet is installed, it will detect that the document
+        # can be converted into ISO-8859-1 without errors. This happens
+        # to be the wrong encoding, but it is a consistent encoding, so the
+        # code we're testing here won't run.
+        #
+        # So we temporarily disable chardet if it's present.
+        doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
+<html><b>\330\250\330\252\330\261</b>
+<i>\310\322\321\220\312\321\355\344</i></html>"""
+        chardet = bs4.dammit.chardet_dammit
+        logging.disable(logging.WARNING)
+        try:
+            def noop(str):
+                return None
+            bs4.dammit.chardet_dammit = noop
+            dammit = UnicodeDammit(doc)
+            self.assertEqual(True, dammit.contains_replacement_characters)
+            self.assertTrue(u"\ufffd" in dammit.unicode_markup)
+
+            soup = BeautifulSoup(doc, "html.parser")
+            self.assertTrue(soup.contains_replacement_characters)
+        finally:
+            logging.disable(logging.NOTSET)
+            bs4.dammit.chardet_dammit = chardet
+
+    def test_byte_order_mark_removed(self):
+        # A document written in UTF-16LE will have its byte order marker stripped.
+        data = b'\xff\xfe<\x00a\x00>\x00\xe1\x00\xe9\x00<\x00/\x00a\x00>\x00'
+        dammit = UnicodeDammit(data)
+        self.assertEqual(u"<a>áé</a>", dammit.unicode_markup)
+        self.assertEqual("utf-16le", dammit.original_encoding)
+
+    def test_detwingle(self):
+        # Here's a UTF8 document.
+        utf8 = (u"\N{SNOWMAN}" * 3).encode("utf8")
+
+        # Here's a Windows-1252 document.
+        windows_1252 = (
+            u"\N{LEFT DOUBLE QUOTATION MARK}Hi, I like Windows!"
+            u"\N{RIGHT DOUBLE QUOTATION MARK}").encode("windows_1252")
+
+        # Through some unholy alchemy, they've been stuck together.
+        doc = utf8 + windows_1252 + utf8
+
+        # The document can't be turned into UTF-8:
+        self.assertRaises(UnicodeDecodeError, doc.decode, "utf8")
+
+        # Unicode, Dammit thinks the whole document is Windows-1252,
+        # and decodes it into "☃☃☃“Hi, I like Windows!”☃☃☃"
+
+        # But if we run it through fix_embedded_windows_1252, it's fixed:
+
+        fixed = UnicodeDammit.detwingle(doc)
+        self.assertEqual(
+            u"☃☃☃“Hi, I like Windows!”☃☃☃", fixed.decode("utf8"))
+
+    def test_detwingle_ignores_multibyte_characters(self):
+        # Each of these characters has a UTF-8 representation ending
+        # in \x93. \x93 is a smart quote if interpreted as
+        # Windows-1252. But our code knows to skip over multibyte
+        # UTF-8 characters, so they'll survive the process unscathed.
+        for tricky_unicode_char in (
+            u"\N{LATIN SMALL LIGATURE OE}", # 2-byte char '\xc5\x93'
+            u"\N{LATIN SUBSCRIPT SMALL LETTER X}", # 3-byte char '\xe2\x82\x93'
+            u"\xf0\x90\x90\x93", # This is a CJK character, not sure which one.
+            ):
+            input = tricky_unicode_char.encode("utf8")
+            self.assertTrue(input.endswith(b'\x93'))
+            output = UnicodeDammit.detwingle(input)
+            self.assertEqual(output, input)
+
+class TestNamedspacedAttribute(SoupTest):
+
+    def test_name_may_be_none(self):
+        a = NamespacedAttribute("xmlns", None)
+        self.assertEqual(a, "xmlns")
+
+    def test_attribute_is_equivalent_to_colon_separated_string(self):
+        a = NamespacedAttribute("a", "b")
+        self.assertEqual("a:b", a)
+
+    def test_attributes_are_equivalent_if_prefix_and_name_identical(self):
+        a = NamespacedAttribute("a", "b", "c")
+        b = NamespacedAttribute("a", "b", "c")
+        self.assertEqual(a, b)
+
+        # The actual namespace is not considered.
+        c = NamespacedAttribute("a", "b", None)
+        self.assertEqual(a, c)
+
+        # But name and prefix are important.
+        d = NamespacedAttribute("a", "z", "c")
+        self.assertNotEqual(a, d)
+
+        e = NamespacedAttribute("z", "b", "c")
+        self.assertNotEqual(a, e)
+
+
+class TestAttributeValueWithCharsetSubstitution(unittest.TestCase):
+
+    def test_content_meta_attribute_value(self):
+        value = CharsetMetaAttributeValue("euc-jp")
+        self.assertEqual("euc-jp", value)
+        self.assertEqual("euc-jp", value.original_value)
+        self.assertEqual("utf8", value.encode("utf8"))
+
+
+    def test_content_meta_attribute_value(self):
+        value = ContentMetaAttributeValue("text/html; charset=euc-jp")
+        self.assertEqual("text/html; charset=euc-jp", value)
+        self.assertEqual("text/html; charset=euc-jp", value.original_value)
+        self.assertEqual("text/html; charset=utf8", value.encode("utf8"))

bitbake/lib/progressbar.py

@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/env python
 # -*- coding: iso-8859-1 -*-
 #
 # progressbar  - Text progressbar library for python.

bitbake/lib/prserv/__init__.py

@@ -11,4 +11,4 @@ def init_logger(logfile, loglevel):
     logging.basicConfig(level=numeric_level, filename=logfile, format=FORMAT)
 
 class NotFoundError(Exception):
-    pass
+    pass

bitbake/lib/prserv/db.py

@@ -19,6 +19,7 @@ class PRTable(object):
     def __init__(self, conn, table, nohist):
         self.conn = conn
         self.nohist = nohist
+        self.dirty = False
         if nohist:
             self.table = "%s_nohist" % table 
         else:
@@ -47,6 +48,11 @@ class PRTable(object):
         self.conn.commit()
         self._execute("BEGIN EXCLUSIVE TRANSACTION")
 
+    def sync_if_dirty(self):
+        if self.dirty:
+            self.sync()
+            self.dirty = False
+
     def _getValueHist(self, version, pkgarch, checksum):
         data=self._execute("SELECT value FROM %s WHERE version=? AND pkgarch=? AND checksum=?;" % self.table,
                            (version, pkgarch, checksum))
@@ -62,6 +68,8 @@ class PRTable(object):
             except sqlite3.IntegrityError as exc:
                 logger.error(str(exc))
 
+            self.dirty = True
+
             data=self._execute("SELECT value FROM %s WHERE version=? AND pkgarch=? AND checksum=?;" % self.table,
                                (version, pkgarch, checksum))
             row=data.fetchone()
@@ -89,6 +97,8 @@ class PRTable(object):
                 logger.error(str(exc))
                 self.conn.rollback()
 
+            self.dirty = True
+
             data=self._execute("SELECT value FROM %s WHERE version=? AND pkgarch=? AND checksum=?;" % self.table,
                                (version, pkgarch, checksum))
             row=data.fetchone()
@@ -118,6 +128,8 @@ class PRTable(object):
             except sqlite3.IntegrityError as exc:
                 logger.error(str(exc))
 
+            self.dirty = True
+
             data = self._execute("SELECT value FROM %s WHERE version=? AND pkgarch=? AND checksum=?;" % self.table,
                            (version, pkgarch, checksum))
             row = data.fetchone()
@@ -139,6 +151,8 @@ class PRTable(object):
             except sqlite3.IntegrityError as exc:
                 logger.error(str(exc))
 
+        self.dirty = True
+
         data = self._execute("SELECT value FROM %s WHERE version=? AND pkgarch=? AND checksum=? AND value>=?;" % self.table,
                             (version,pkgarch,checksum,value))
         row=data.fetchone()
@@ -220,6 +234,8 @@ class PRData(object):
                 raise e
         self.connection=sqlite3.connect(self.filename, isolation_level="EXCLUSIVE", check_same_thread = False)
         self.connection.row_factory=sqlite3.Row
+        self.connection.execute("pragma synchronous = off;")
+        self.connection.execute("PRAGMA journal_mode = WAL;")
         self._tables={}
 
     def __del__(self):

bitbake/lib/prserv/serv.py

@@ -38,8 +38,17 @@ singleton = None
 class PRServer(SimpleXMLRPCServer):
     def __init__(self, dbfile, logfile, interface, daemon=True):
         ''' constructor '''
-        SimpleXMLRPCServer.__init__(self, interface,
-                                    logRequests=False, allow_none=True)
+        import socket
+        try:
+            SimpleXMLRPCServer.__init__(self, interface,
+                                        logRequests=False, allow_none=True)
+        except socket.error:
+            ip=socket.gethostbyname(interface[0])
+            port=interface[1]
+            msg="PR Server unable to bind to %s:%s\n" % (ip, port)
+            sys.stderr.write(msg)
+            raise PRServiceConfigError
+
         self.dbfile=dbfile
         self.daemon=daemon
         self.logfile=logfile
@@ -67,15 +76,27 @@ class PRServer(SimpleXMLRPCServer):
         In addition, exception handling is done here.
 
         """
-        while True:
-            (request, client_address) = self.requestqueue.get()
+        iter_count = 1
+        # 60 iterations between syncs or sync if dirty every ~30 seconds
+        iterations_between_sync = 60
+
+        while not self.quit:
+            try:
+                (request, client_address) = self.requestqueue.get(True, 30)
+            except Queue.Empty:
+                self.table.sync_if_dirty()
+                continue
             try:
                 self.finish_request(request, client_address)
                 self.shutdown_request(request)
+                iter_count = (iter_count + 1) % iterations_between_sync
+                if iter_count == 0:
+                    self.table.sync_if_dirty()
             except:
                 self.handle_error(request, client_address)
                 self.shutdown_request(request)
                 self.table.sync()
+            self.table.sync_if_dirty()
 
     def process_request(self, request, client_address):
         self.requestqueue.put((request, client_address))
@@ -120,7 +141,7 @@ class PRServer(SimpleXMLRPCServer):
         self.handlerthread.start()
         while not self.quit:
             self.handle_request()
-
+        self.handlerthread.join()
         self.table.sync()
         logger.info("PRServer: stopping...")
         self.server_close()