[PATCH v2] create-spdx: Get SPDX-License-Identifier from source

[Saul Wold <saul.wold@windriver.com>]

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.wold@windriver.com>
---
v2: Updated commit message, and fixed REGEX based on Peter's suggetion

 meta/classes/create-spdx.bbclass | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/meta/classes/create-spdx.bbclass b/meta/classes/create-spdx.bbclass
index 8b4203fdb5..588489cc2b 100644
--- a/meta/classes/create-spdx.bbclass
+++ b/meta/classes/create-spdx.bbclass
@@ -37,6 +37,24 @@ 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
+    import oe.spdx
+
+    lic_regex = re.compile(b'SPDX-License-Identifier:\s+([-A-Za-z\d. ]+)[ |\n|\r\n]*?')
+
+    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 +250,11 @@ 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