classes/cve-check: Move get_patches_cves to library

Moving the function will allow other classes to capture which CVEs have
been patched, in particular SBoM generation.

Also add a function to capture the CPE ID from the CVE Product and
Version

(From OE-Core rev: 75d34259a715120be1d023e4fd7b6b4b125f2443)

Signed-off-by: Joshua Watt <JPEWhacker@gmail.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
(cherry picked from commit fa6c07bc1a585f204dbdc28704f61448edb8fdc8)
Signed-off-by: Akash Hadke <akash.hadke@kpit.com>
Signed-off-by: Steve Sakoman <steve@sakoman.com>

2 files changed, 84 insertions, 60 deletions

diff --git a/meta/classes/cve-check.bbclass b/meta/classes/cve-check.bbclass
index 1688fe2dfe..9eb9a95574 100644
--- a/meta/classes/cve-check.bbclass
+++ b/meta/classes/cve-check.bbclass
@@ -136,10 +136,11 @@ python do_cve_check () {
     """
     Check recipe for patched and unpatched CVEs
     """
+    from oe.cve_check import get_patched_cves
 
     if os.path.exists(d.getVar("CVE_CHECK_DB_FILE")):
         try:
-            patched_cves = get_patches_cves(d)
+            patched_cves = get_patched_cves(d)
         except FileNotFoundError:
             bb.fatal("Failure in searching patches")
         whitelisted, patched, unpatched, status = check_cves(d, patched_cves)
@@ -247,65 +248,6 @@ ROOTFS_POSTPROCESS_COMMAND_prepend = "${@'cve_check_write_rootfs_manifest; ' if
 do_rootfs[recrdeptask] += "${@'do_cve_check' if d.getVar('CVE_CHECK_CREATE_MANIFEST') == '1' else ''}"
 do_populate_sdk[recrdeptask] += "${@'do_cve_check' if d.getVar('CVE_CHECK_CREATE_MANIFEST') == '1' else ''}"
 
-def get_patches_cves(d):
-    """
-    Get patches that solve CVEs using the "CVE: " tag.
-    """
-
-    import re
-
-    pn = d.getVar("PN")
-    cve_match = re.compile("CVE:( CVE\-\d{4}\-\d+)+")
-
-    # Matches the last "CVE-YYYY-ID" in the file name, also if written
-    # in lowercase. Possible to have multiple CVE IDs in a single
-    # file name, but only the last one will be detected from the file name.
-    # However, patch files contents addressing multiple CVE IDs are supported
-    # (cve_match regular expression)
-
-    cve_file_name_match = re.compile(".*([Cc][Vv][Ee]\-\d{4}\-\d+)")
-
-    patched_cves = set()
-    bb.debug(2, "Looking for patches that solves CVEs for %s" % pn)
-    for url in src_patches(d):
-        patch_file = bb.fetch.decodeurl(url)[2]
-
-        if not os.path.isfile(patch_file):
-            bb.error("File Not found: %s" % patch_file)
-            raise FileNotFoundError
-
-        # Check patch file name for CVE ID
-        fname_match = cve_file_name_match.search(patch_file)
-        if fname_match:
-            cve = fname_match.group(1).upper()
-            patched_cves.add(cve)
-            bb.debug(2, "Found CVE %s from patch file name %s" % (cve, patch_file))
-
-        with open(patch_file, "r", encoding="utf-8") as f:
-            try:
-                patch_text = f.read()
-            except UnicodeDecodeError:
-                bb.debug(1, "Failed to read patch %s using UTF-8 encoding"
-                        " trying with iso8859-1" %  patch_file)
-                f.close()
-                with open(patch_file, "r", encoding="iso8859-1") as f:
-                    patch_text = f.read()
-
-        # Search for one or more "CVE: " lines
-        text_match = False
-        for match in cve_match.finditer(patch_text):
-            # Get only the CVEs without the "CVE: " tag
-            cves = patch_text[match.start()+5:match.end()]
-            for cve in cves.split():
-                bb.debug(2, "Patch %s solves %s" % (patch_file, cve))
-                patched_cves.add(cve)
-                text_match = True
-
-        if not fname_match and not text_match:
-            bb.debug(2, "Patch %s doesn't solve CVEs" % patch_file)
-
-    return patched_cves
-
 def check_cves(d, patched_cves):
     """
     Connect to the NVD database and find unpatched cves.
diff --git a/meta/lib/oe/cve_check.py b/meta/lib/oe/cve_check.py
index b17390de90..a4b831831b 100644
--- a/meta/lib/oe/cve_check.py
+++ b/meta/lib/oe/cve_check.py
@@ -89,3 +89,85 @@ def update_symlinks(target_path, link_path):
         if os.path.exists(os.path.realpath(link_path)):
             os.remove(link_path)
         os.symlink(os.path.basename(target_path), link_path)
+
+def get_patched_cves(d):
+    """
+    Get patches that solve CVEs using the "CVE: " tag.
+    """
+
+    import re
+    import oe.patch
+
+    pn = d.getVar("PN")
+    cve_match = re.compile("CVE:( CVE\-\d{4}\-\d+)+")
+
+    # Matches the last "CVE-YYYY-ID" in the file name, also if written
+    # in lowercase. Possible to have multiple CVE IDs in a single
+    # file name, but only the last one will be detected from the file name.
+    # However, patch files contents addressing multiple CVE IDs are supported
+    # (cve_match regular expression)
+
+    cve_file_name_match = re.compile(".*([Cc][Vv][Ee]\-\d{4}\-\d+)")
+
+    patched_cves = set()
+    bb.debug(2, "Looking for patches that solves CVEs for %s" % pn)
+    for url in oe.patch.src_patches(d):
+        patch_file = bb.fetch.decodeurl(url)[2]
+
+        if not os.path.isfile(patch_file):
+            bb.error("File Not found: %s" % patch_file)
+            raise FileNotFoundError
+
+        # Check patch file name for CVE ID
+        fname_match = cve_file_name_match.search(patch_file)
+        if fname_match:
+            cve = fname_match.group(1).upper()
+            patched_cves.add(cve)
+            bb.debug(2, "Found CVE %s from patch file name %s" % (cve, patch_file))
+
+        with open(patch_file, "r", encoding="utf-8") as f:
+            try:
+                patch_text = f.read()
+            except UnicodeDecodeError:
+                bb.debug(1, "Failed to read patch %s using UTF-8 encoding"
+                        " trying with iso8859-1" %  patch_file)
+                f.close()
+                with open(patch_file, "r", encoding="iso8859-1") as f:
+                    patch_text = f.read()
+
+        # Search for one or more "CVE: " lines
+        text_match = False
+        for match in cve_match.finditer(patch_text):
+            # Get only the CVEs without the "CVE: " tag
+            cves = patch_text[match.start()+5:match.end()]
+            for cve in cves.split():
+                bb.debug(2, "Patch %s solves %s" % (patch_file, cve))
+                patched_cves.add(cve)
+                text_match = True
+
+        if not fname_match and not text_match:
+            bb.debug(2, "Patch %s doesn't solve CVEs" % patch_file)
+
+    return patched_cves
+
+
+def get_cpe_ids(cve_product, version):
+    """
+    Get list of CPE identifiers for the given product and version
+    """
+
+    version = version.split("+git")[0]
+
+    cpe_ids = []
+    for product in cve_product.split():
+        # CVE_PRODUCT in recipes may include vendor information for CPE identifiers. If not,
+        # use wildcard for vendor.
+        if ":" in product:
+            vendor, product = product.split(":", 1)
+        else:
+            vendor = "*"
+
+        cpe_id = f'cpe:2.3:a:{vendor}:{product}:{version}:*:*:*:*:*:*:*'
+        cpe_ids.append(cpe_id)
+
+    return cpe_ids