Allow for filtering out specific Axe measurement entities through reg…

…ular expressions (#5894)

components/collector/src/source_collectors/axe_core/accessibility.py

@@ -27,6 +27,12 @@ def _include_entity(self, entity: Entity) -> bool:
             for tag in tags:
                 if match_string_or_regular_expression(tag, tags_to_ignore):
                     return False
+        if element_include_filter := self._parameter("element_include_filter"):
+            if not match_string_or_regular_expression(entity["element"], element_include_filter):
+                return False
+        if element_exclude_filter := self._parameter("element_exclude_filter"):
+            if match_string_or_regular_expression(entity["element"], element_exclude_filter):
+                return False
         return True
 
 

components/collector/src/source_collectors/axe_csv/accessibility.py

@@ -5,13 +5,26 @@
 from io import StringIO
 
 from base_collectors import CSVFileSourceCollector
-from collector_utilities.functions import md5_hash
+from collector_utilities.functions import md5_hash, match_string_or_regular_expression
 from model import Entities, Entity, SourceResponses
 
 
 class AxeCSVAccessibility(CSVFileSourceCollector):
     """Collector class to get accessibility violations."""
 
+    def _include_entity(self, entity: Entity) -> bool:
+        """Return whether to include the violation."""
+        impact = entity["impact"]
+        if impact and impact not in self._parameter("impact"):
+            return False
+        if element_include_filter := self._parameter("element_include_filter"):
+            if not match_string_or_regular_expression(entity["element"], element_include_filter):
+                return False
+        if element_exclude_filter := self._parameter("element_exclude_filter"):
+            if match_string_or_regular_expression(entity["element"], element_exclude_filter):
+                return False
+        return True
+
     async def _parse_entities(self, responses: SourceResponses) -> Entities:
         """Override to parse the CSV and create the entities."""
         entity_attributes = [
@@ -31,11 +44,11 @@ async def _parse_entities(self, responses: SourceResponses) -> Entities:
             for attributes in entity_attributes
         )
 
-    async def __parse_csv(self, responses: SourceResponses) -> list[dict[str, str]]:
+    @staticmethod
+    async def __parse_csv(responses: SourceResponses) -> list[dict[str, str]]:
         """Parse the CSV and return the rows and parsed items ."""
-        impact_levels = self._parameter("impact")
         rows = []
         for response in responses:
             csv_text = (await response.text()).strip()
             rows.extend(list(csv.DictReader(StringIO(csv_text, newline=""))))
-        return [row for row in rows if row["Impact"] in impact_levels]
+        return rows

components/collector/tests/source_collectors/axe_core/test_accessibility.py

@@ -117,6 +117,18 @@ async def test_filter_by_tag_ignore(self):
         response = await self.collect(get_request_json_return_value=self.json)
         self.assert_measurement(response, value="1", entities=[self.expected_entities[1]])
 
+    async def test_element_include_filter(self):
+        """Test that violations can be filtered by element."""
+        self.set_source_parameter("element_include_filter", ["html1"])
+        response = await self.collect(get_request_json_return_value=self.json)
+        self.assert_measurement(response, value="1", entities=[self.expected_entities[0]])
+
+    async def test_element_exclude_filter(self):
+        """Test that violations can be filtered by element."""
+        self.set_source_parameter("element_exclude_filter", ["html1"])
+        response = await self.collect(get_request_json_return_value=self.json)
+        self.assert_measurement(response, value="1", entities=[self.expected_entities[1]])
+
     async def test_zipped_json(self):
         """Test that a zip archive with JSON files is processed correctly."""
         self.set_source_parameter("url", "axe.zip")

components/collector/tests/source_collectors/axe_csv/test_accessibility.py

@@ -70,6 +70,18 @@ async def test_filter_by_impact(self):
         response = await self.collect(get_request_text=self.csv)
         self.assert_measurement(response, value="1")
 
+    async def test_element_include_filter(self):
+        """Test that violations can be filtered by element."""
+        self.set_source_parameter("element_include_filter", ["dom2"])
+        response = await self.collect(get_request_text=self.csv)
+        self.assert_measurement(response, value="1", entities=[self.expected_entities[1]])
+
+    async def test_element_exclude_filter(self):
+        """Test that violations can be filtered by element."""
+        self.set_source_parameter("element_exclude_filter", ["dom2"])
+        response = await self.collect(get_request_text=self.csv)
+        self.assert_measurement(response, value="1", entities=[self.expected_entities[0]])
+
     async def test_zipped_csv(self):
         """Test that a zip archive with CSV files is processed correctly."""
         self.set_source_parameter("url", "https://example.org/axecsv.zip")

components/shared_data_model/src/shared_data_model/sources/axe.py

@@ -31,6 +31,22 @@
     metrics=["accessibility"],
 )
 
+ELEMENT_INCLUDE_FILTER = MultipleChoiceWithAdditionParameter(
+    name="Elements to include (regular expressions)",
+    short_name="element include filter",
+    help="Elements to include can be specified by regular expression.",
+    placeholder="all",
+    metrics=["accessibility"],
+)
+
+ELEMENT_EXCLUDE_FILTER = MultipleChoiceWithAdditionParameter(
+    name="Elements to exclude (regular expressions)",
+    short_name="element exclude filter",
+    help="Elements to exclude can be specified by regular expression.",
+    placeholder="none",
+    metrics=["accessibility"],
+)
+
 RESULT_TYPES = MultipleChoiceParameter(
     name="Result types",
     help="Limit which result types to count.",
@@ -101,6 +117,8 @@
     parameters=dict(
         tags_to_include=TAGS_TO_INCLUDE,
         tags_to_ignore=TAGS_TO_IGNORE,
+        element_include_filter=ELEMENT_INCLUDE_FILTER,
+        element_exclude_filter=ELEMENT_EXCLUDE_FILTER,
         impact=IMPACT,
         result_types=RESULT_TYPES,
         **access_parameters(ALL_AXE_CORE_METRICS, source_type="an Axe-core report", source_type_format="JSON")
@@ -115,6 +133,8 @@
     parameters=dict(
         tags_to_include=TAGS_TO_INCLUDE,
         tags_to_ignore=TAGS_TO_IGNORE,
+        element_include_filter=ELEMENT_INCLUDE_FILTER,
+        element_exclude_filter=ELEMENT_EXCLUDE_FILTER,
         impact=IMPACT,
         result_types=RESULT_TYPES,
         **access_parameters(["accessibility"], source_type="an Axe report", source_type_format="HTML")
@@ -127,7 +147,10 @@
     description="An Axe accessibility report in CSV format.",
     url="https://github.com/ICTU/axe-reports",
     parameters=dict(
-        impact=IMPACT, **access_parameters(["accessibility"], source_type="an Axe report", source_type_format="CSV")
+        element_include_filter=ELEMENT_INCLUDE_FILTER,
+        element_exclude_filter=ELEMENT_EXCLUDE_FILTER,
+        impact=IMPACT,
+        **access_parameters(["accessibility"], source_type="an Axe report", source_type_format="CSV")
     ),
     entities=dict(
         accessibility=dict(

docs/src/changelog.md

@@ -26,6 +26,7 @@ If your currently installed *Quality-time* version is v4.0.0 or older, please re
 
 - Add the possibility in metrics of type missing metrics to exclude certain subjects from a report. Closes [#5119](https://github.com/ICTU/quality-time/issues/5119).
 - Add SonarQube issue status rationale to entity data of suppressed violations. Closes [#4926](https://github.com/ICTU/quality-time/issues/4926).
+- Allow for filtering out specific Axe measurement entities through regular expressions. Closes [#3328](https://github.com/ICTU/quality-time/issues/3328).
 
 ### Changed