spdx: add option to include only compiled sources

When SPDX_INCLUDE_COMPILED_SOURCES is enabled, only include the
source code files that are used during compilation.

It uses debugsource information generated during do_package.

This enables an external tool to use the SPDX information to disregard
vulnerabilities that are not compiled.

As example, when used with the default config with linux-yocto, the spdx size is
reduced from 156MB to 61MB.

Tested with bitbake world on oe-core.

(From OE-Core rev: c6a2f1fca76fae4c3ea471a0c63d0b453beea968)
Adapted to existing files for create-spdx-2.2

CC: Mathieu Dubois-Briand <mathieu.dubois-briand@bootlin.com>
CC: Joshua Watt <JPEWhacker@gmail.com>
(From OE-Core rev: a2866934e58fb377a73e87576c8594988a63ad1b)

Signed-off-by: Daniel Turull <daniel.turull@ericsson.com>
Signed-off-by: Steve Sakoman <steve@sakoman.com>

meta/classes/create-spdx-2.2.bbclass

@@ -100,6 +100,9 @@ python() {
         # Transform the license array to a dictionary
         data["licenses"] = {l["licenseId"]: l for l in data["licenses"]}
         d.setVar("SPDX_LICENSE_DATA", data)
+
+    if d.getVar("SPDX_INCLUDE_COMPILED_SOURCES") == "1":
+        d.setVar("SPDX_INCLUDE_SOURCES", "1")
 }
 
 def convert_license_to_spdx(lic, document, d, existing={}):
@@ -215,6 +218,11 @@ def add_package_files(d, doc, spdx_pkg, topdir, get_spdxid, get_types, *, archiv
     spdx_files = []
 
     file_counter = 1
+
+    check_compiled_sources = d.getVar("SPDX_INCLUDE_COMPILED_SOURCES") == "1"
+    if check_compiled_sources:
+        compiled_sources, types = oe.spdx.get_compiled_sources(d)
+        bb.debug(1, f"Total compiled files: {len(compiled_sources)}")
     for subdir, dirs, files in os.walk(topdir):
         dirs[:] = [d for d in dirs if d not in ignore_dirs]
         if subdir == str(topdir):
@@ -225,6 +233,10 @@ def add_package_files(d, doc, spdx_pkg, topdir, get_spdxid, get_types, *, archiv
             filename = str(filepath.relative_to(topdir))
 
             if not filepath.is_symlink() and filepath.is_file():
+                # Check if file is compiled
+                if check_compiled_sources:
+                     if not oe.spdx.is_compiled_source(filename, compiled_sources, types):
+                          continue
                 spdx_file = oe.spdx.SPDXFile()
                 spdx_file.SPDXID = get_spdxid(file_counter)
                 for t in get_types(filepath):