This patch will read the begining of source files and try to find
the SPDX-License-Identifier to populate the licenseInfoInFiles
field for each source file. This does not populate licenseConcluded
at this time, nor rolls it up to package level.

We read as binary file since some source code seem to have some
binary characters, the license is then converted to ascii strings.

Signed-off-by: Saul Wold <saul.w...@windriver.com>
---
v2: Clean up commit message
v3: Really fix up regex based on Peter's feedback!

 meta/classes/create-spdx.bbclass | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/meta/classes/create-spdx.bbclass b/meta/classes/create-spdx.bbclass
index 8b4203fdb5..64aada8593 100644
--- a/meta/classes/create-spdx.bbclass
+++ b/meta/classes/create-spdx.bbclass
@@ -37,6 +37,23 @@ SPDX_SUPPLIER[doc] = "The SPDX PackageSupplier field for 
SPDX packages created f
 
 do_image_complete[depends] = "virtual/kernel:do_create_spdx"
 
+def extract_licenses(filename):
+    import re
+
+    lic_regex = re.compile(b'^\W*SPDX-License-Identifier:\s*([ 
\w\d.()+-]+?)(?:\s+\W*)?$', re.MULTILINE)
+
+    try:
+        with open(filename, 'rb') as f:
+            size = min(15000, os.stat(filename).st_size)
+            txt = f.read(size)
+            licenses = re.findall(lic_regex, txt)
+            if licenses:
+                ascii_licenses = [lic.decode('ascii') for lic in licenses]
+                return ascii_licenses
+    except Exception as e:
+        bb.warn(f"Exception reading {filename}: {e}")
+    return None
+
 def get_doc_namespace(d, doc):
     import uuid
     namespace_uuid = uuid.uuid5(uuid.NAMESPACE_DNS, 
d.getVar("SPDX_UUID_NAMESPACE"))
@@ -232,6 +249,11 @@ def add_package_files(d, doc, spdx_pkg, topdir, 
get_spdxid, get_types, *, archiv
                         checksumValue=bb.utils.sha256_file(filepath),
                     ))
 
+                if "SOURCE" in spdx_file.fileTypes:
+                    extracted_lics = extract_licenses(filepath)
+                    if extracted_lics:
+                        spdx_file.licenseInfoInFiles = extracted_lics
+
                 doc.files.append(spdx_file)
                 doc.add_relationship(spdx_pkg, "CONTAINS", spdx_file)
                 spdx_pkg.hasFiles.append(spdx_file.SPDXID)
-- 
2.31.1

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#161513): 
https://lists.openembedded.org/g/openembedded-core/message/161513
Mute This Topic: https://lists.openembedded.org/mt/88997967/21656
Group Owner: openembedded-core+ow...@lists.openembedded.org
Unsubscribe: https://lists.openembedded.org/g/openembedded-core/unsub 
[arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Reply via email to