Fix errors

Signed-off-by: Tushar Goel <tushar.goel.dav@gmail.com>

Author: TG1999

vulnerabilities/pipelines/__init__.py

@@ -20,6 +20,7 @@
 from aboutcode.pipeline import PipelineDefinition
 from aboutcode.pipeline import humanize_time
 
+from vulnerabilities.importer import AdvisoryDataV2
 from vulnerabilities.models import PipelineRun
 from vulnerabilities.models import PipelineSchedule
 from vulnerabilities.pipes.advisory import insert_advisory_v2
@@ -196,17 +197,17 @@ def steps(cls):
             # Add step for removing downloaded/cloned resource as required.
         )
 
-    def collect_advisories(self) -> Iterable[AdvisoryData]:
+    def collect_advisories(self) -> Iterable[AdvisoryDataV2]:
         """
-        Yield AdvisoryData for importer pipeline.
+        Yield AdvisoryDataV2 for importer pipeline.
 
-        Populate the `self.collected_advisories_count` field and yield AdvisoryData
+        Populate the `self.collected_advisories_count` field and yield AdvisoryDataV2
         """
         raise NotImplementedError
 
     def advisories_count(self) -> int:
         """
-        Return the estimated AdvisoryData to be yielded by ``collect_advisories``.
+        Return the estimated AdvisoryDataV2 to be yielded by ``collect_advisories``.
 
         Used by ``collect_and_store_advisories`` to log the progress of advisory collection.
         """

vulnerabilities/pipelines/v2_importers/alpine_linux_importer.py

@@ -109,7 +109,7 @@ def check_for_attributes(record, logger) -> bool:
 
 def process_record(record: dict, url: str, logger: callable) -> Iterable[AdvisoryDataV2]:
     """
-    Return a list of AdvisoryData objects by processing data
+    Return a list of AdvisoryDataV2 objects by processing data
     present in that `record`
     """
     if not record.get("packages"):
@@ -147,7 +147,7 @@ def load_advisories(
     logger: callable,
 ) -> Iterable[AdvisoryDataV2]:
     """
-    Yield AdvisoryData by mapping data from `pkg_infos`
+    Yield AdvisoryDataV2 by mapping data from `pkg_infos`
     and form PURL for AffectedPackages by using
     `distroversion`, `reponame`, `archs`
     """

vulnerabilities/pipes/osv_v2.py

@@ -65,7 +65,7 @@ def parse_advisory_data_v3(
     advisory_id: Optional[str] = None,
 ) -> Optional[AdvisoryDataV2]:
     """
-    Return an AdvisoryData build from a ``raw_data`` mapping of OSV advisory and
+    Return an AdvisoryDataV2 build from a ``raw_data`` mapping of OSV advisory and
     a ``supported_ecosystem`` string.
     """
     adv_id = raw_data.get("id")
@@ -215,7 +215,7 @@ def parse_advisory_data_v3(
             or json.dumps(raw_data, indent=2, ensure_ascii=False),
         )
     except Exception as e:
-        logger.error(f"Invalid AdvisoryData for {advisory_id}: {e}")
+        logger.error(f"Invalid AdvisoryDataV2 for {advisory_id}: {e}")
 
 
 def extract_events(range_data) -> Iterable[str]:

vulnerabilities/pipes/vcs_collector_utils.py

@@ -99,9 +99,9 @@ def collect_fix_commits(self):
 
     def collect_advisories(self):
         """
-        Generate AdvisoryData objects for each vulnerability ID grouped with its related commits.
+        Generate AdvisoryDataV2 objects for each vulnerability ID grouped with its related commits.
         """
-        self.log("Generating AdvisoryData objects from grouped commits.")
+        self.log("Generating AdvisoryDataV2 objects from grouped commits.")
         grouped_commits = self.collect_fix_commits()
         purl = url2purl(self.repo_url)
         for vuln_id, commits_data in grouped_commits.items():

vulnerabilities/tests/pipelines/v2_importers/test_nvd_importer_v2.py

@@ -25,7 +25,7 @@ def load_test_data(file):
 
 def sorted_advisory_data(advisory_data):
     """
-    Return ``advisory_data`` of AdvisoryData mappings where each mapping nested
+    Return ``advisory_data`` of AdvisoryDataV2 mappings where each mapping nested
     list is sorted for stable testing results.
     """
     sorter = lambda dct: tuple(dct.items())

vulnerabilities/tests/pipelines/v2_importers/test_pypa_importer_pipeline_v2.py

@@ -88,7 +88,7 @@ def test_collect_advisories(mock_pathlib, mock_vcs_response, mock_fetch_via_vcs)
     # Mock `vcs_response.dest_dir` to point to the temporary directory
     mock_vcs_response.dest_dir = str(mock_pathlib.parent)
 
-    # Mock `parse_advisory_data` to return an AdvisoryData object
+    # Mock `parse_advisory_data` to return an AdvisoryDataV2 object
     with patch(
         "vulnerabilities.pipelines.v2_importers.pypa_importer.parse_advisory_data_v3"
     ) as mock_parse:

vulnerabilities/tests/pipelines/v2_importers/test_pysec_importer_v2.py

@@ -78,7 +78,7 @@ def test_collect_advisories(mock_requests_get, mock_zip_data):
     # Fetch the zip data
     pipeline.fetch_zip()
 
-    # Mock the `parse_advisory_data_v2` function to return a dummy AdvisoryData
+    # Mock the `parse_advisory_data_v2` function to return a dummy AdvisoryDataV2
     with patch(
         "vulnerabilities.pipelines.v2_importers.pysec_importer.parse_advisory_data_v3"
     ) as mock_parse:

vulnerabilities/tests/pipelines/v2_importers/test_vulnrichment_importer_v2.py

@@ -99,7 +99,7 @@ def test_collect_advisories(mock_pathlib, mock_vcs_response, mock_fetch_via_vcs)
     # Mock `vcs_response.dest_dir` to point to the temporary directory
     mock_vcs_response.dest_dir = str(mock_pathlib.parent)
 
-    # Mock `parse_cve_advisory` to return an AdvisoryData object
+    # Mock `parse_cve_advisory` to return an AdvisoryDataV2 object
     with patch(
         "vulnerabilities.pipelines.v2_importers.vulnrichment_importer.VulnrichImporterPipeline.parse_cve_advisory"
     ) as mock_parse:

vulnerabilities/utils.py

@@ -643,54 +643,6 @@ def sha256_digest(normalized_data):
     return hashlib.sha256(normalized_json.encode("utf-8")).hexdigest()
 
 
-def compute_content_id(advisory_data):
-    """
-    Compute a unique content_id for an advisory by normalizing its data and hashing it.
-
-    :param advisory_data: An AdvisoryData object
-    :return: SHA-256 hash digest as content_id
-    """
-
-    # Normalize fields
-    from vulnerabilities.importer import AdvisoryData
-    from vulnerabilities.models import Advisory
-
-    if isinstance(advisory_data, Advisory):
-        normalized_data = {
-            "aliases": normalize_list(advisory_data.aliases),
-            "summary": normalize_text(advisory_data.summary),
-            "affected_packages": [
-                pkg for pkg in normalize_list(advisory_data.affected_packages) if pkg
-            ],
-            "references": [ref for ref in normalize_list(advisory_data.references) if ref],
-            "weaknesses": normalize_list(advisory_data.weaknesses),
-        }
-        normalized_data["url"] = advisory_data.url
-
-    elif isinstance(advisory_data, AdvisoryData):
-        normalized_data = {
-            "aliases": normalize_list(advisory_data.aliases),
-            "summary": normalize_text(advisory_data.summary),
-            "affected_packages": [
-                pkg.to_dict() for pkg in normalize_list(advisory_data.affected_packages) if pkg
-            ],
-            "references": [
-                ref.to_dict() for ref in normalize_list(advisory_data.references) if ref
-            ],
-            "weaknesses": normalize_list(advisory_data.weaknesses),
-        }
-
-        normalized_data["url"] = advisory_data.url
-
-    else:
-        raise ValueError("Unsupported advisory data type for content ID computation")
-
-    normalized_json = json.dumps(normalized_data, separators=(",", ":"), sort_keys=True)
-    content_id = hashlib.sha256(normalized_json.encode("utf-8")).hexdigest()
-
-    return content_id
-
-
 def compute_content_id_v2(advisory_data):
     """
     Compute a unique content_id for an advisory by normalizing its data and hashing it.