fix: address review comments on presidio integration

- Regenerate presidio.yml workflow from template (compute-test-matrix job,
  pinned action versions, push trigger, coverage steps)
- Add integration-cov-append-retry script to pyproject.toml
- Drop un-anonymized documents on error in PresidioDocumentCleaner instead
  of passing them through unanonymized
- Clarify warning message in PresidioEntityExtractor to say extraction is
  skipped but document is kept
- Update test to assert failed docs are dropped in PresidioDocumentCleaner

Author: SyedShahmeerAli12

.github/workflows/presidio.yml

@@ -1,3 +1,5 @@
+# This workflow comes from https://github.com/ofek/hatch-mypyc
+# https://github.com/ofek/hatch-mypyc/blob/5a198c0ba8660494d02716cfc9d79ce4adfb1442/.github/workflows/test.yml
 name: Test / presidio
 
 on:
@@ -8,34 +10,66 @@ on:
       - "integrations/presidio/**"
       - "!integrations/presidio/*.md"
       - ".github/workflows/presidio.yml"
+  push:
+    branches:
+      - main
+    paths:
+      - "integrations/presidio/**"
+      - "!integrations/presidio/*.md"
+      - ".github/workflows/presidio.yml"
 
 defaults:
   run:
     working-directory: integrations/presidio
 
 concurrency:
-  group: presidio-${{ github.head_ref }}
+  group: presidio-${{ github.head_ref || github.sha }}
   cancel-in-progress: true
 
 env:
   PYTHONUNBUFFERED: "1"
   FORCE_COLOR: "1"
+  TEST_MATRIX_OS: '["ubuntu-latest", "windows-latest", "macos-latest"]'
+  TEST_MATRIX_PYTHON: '["3.10", "3.14"]'
 
 jobs:
+  compute-test-matrix:
+    runs-on: ubuntu-slim
+    defaults:
+      run:
+        working-directory: .
+    outputs:
+      os: ${{ steps.set.outputs.os }}
+      python-version: ${{ steps.set.outputs.python-version }}
+    steps:
+      - id: set
+        run: |
+          echo 'os=${{ github.event_name == 'push' && '["ubuntu-latest"]' || env.TEST_MATRIX_OS }}' >> "$GITHUB_OUTPUT"
+          echo 'python-version=${{ github.event_name == 'push' && '["3.10"]' || env.TEST_MATRIX_PYTHON }}' >> "$GITHUB_OUTPUT"
+
   run:
     name: Python ${{ matrix.python-version }} on ${{ startsWith(matrix.os, 'macos-') && 'macOS' || startsWith(matrix.os, 'windows-') && 'Windows' || 'Linux' }}
+    needs: compute-test-matrix
+    permissions:
+      contents: write
+      pull-requests: write
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-latest]
-        python-version: ["3.10", "3.14"]
+        os: ${{ fromJSON(needs.compute-test-matrix.outputs.os) }}
+        python-version: ${{ fromJSON(needs.compute-test-matrix.outputs.python-version) }}
 
     steps:
-      - uses: actions/checkout@v4
+      - name: Support longpaths
+        if: matrix.os == 'windows-latest'
+        working-directory: .
+        run: git config --system core.longpaths true
+
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -49,7 +83,34 @@ jobs:
       - name: Run unit tests
         run: hatch run test:unit-cov-retry
 
+      # On PR: generates coverage comment artifact. On push to main: stores coverage baseline on data branch.
+      - name: Store unit tests coverage
+        if: matrix.python-version == '3.10' && runner.os == 'Linux' && github.event_name != 'schedule'
+        uses: py-cov-action/python-coverage-comment-action@7188638f871f721a365d644f505d1ff3df20d683 # v3.40
+        with:
+          GITHUB_TOKEN: ${{ github.token }}
+          COVERAGE_PATH: integrations/presidio
+          SUBPROJECT_ID: presidio
+          COMMENT_ARTIFACT_NAME: coverage-comment-presidio
+          MINIMUM_GREEN: 90
+          MINIMUM_ORANGE: 60
+
+      - name: Run integration tests
+        run: hatch run test:integration-cov-append-retry
+
+      - name: Store combined coverage
+        if: github.event_name == 'push'
+        uses: py-cov-action/python-coverage-comment-action@7188638f871f721a365d644f505d1ff3df20d683 # v3.40
+        with:
+          GITHUB_TOKEN: ${{ github.token }}
+          COVERAGE_PATH: integrations/presidio
+          SUBPROJECT_ID: presidio-combined
+          COMMENT_ARTIFACT_NAME: coverage-comment-presidio-combined
+          MINIMUM_GREEN: 90
+          MINIMUM_ORANGE: 60
+
       - name: Run unit tests with lowest direct dependencies
+        if: github.event_name != 'push'
         run: |
           hatch run uv pip compile pyproject.toml --resolution lowest-direct --output-file requirements_lowest_direct.txt
           hatch -e test env run -- uv pip install -r requirements_lowest_direct.txt
@@ -65,7 +126,7 @@ jobs:
   notify-slack-on-failure:
     needs: run
     if: failure() && github.event_name == 'schedule'
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-slim
     steps:
       - uses: deepset-ai/notify-slack-action@3cda73b77a148f16f703274198e7771340cf862b # v1
         with:

integrations/presidio/pyproject.toml

@@ -69,6 +69,7 @@ unit = 'pytest -m "not integration" {args:tests}'
 integration = 'pytest -m "integration" {args:tests}'
 all = 'pytest {args:tests}'
 unit-cov-retry = 'pytest --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x -m "not integration" {args:tests}'
+integration-cov-append-retry = 'pytest --cov=haystack_integrations --cov-append --reruns 3 --reruns-delay 30 -x -m "integration" {args:tests}'
 types = "mypy -p haystack_integrations.components.preprocessors.presidio {args}"
 
 [tool.mypy]

integrations/presidio/src/haystack_integrations/components/preprocessors/presidio/presidio_document_cleaner.py

@@ -112,5 +112,4 @@ def run(self, documents: list[Document]) -> dict[str, list[Document]]:
                     doc_id=doc.id,
                     error=e,
                 )
-                cleaned.append(doc)
         return {"documents": cleaned}

integrations/presidio/src/haystack_integrations/components/preprocessors/presidio/presidio_entity_extractor.py

@@ -117,7 +117,7 @@ def run(self, documents: list[Document]) -> dict[str, list[Document]]:
                 result_docs.append(replace(doc, meta={**doc.meta, "entities": entities}))
             except Exception as e:
                 logger.warning(
-                    "Could not extract entities from document {doc_id}. Skipping it. Error: {error}",
+                    "Could not extract entities from document {doc_id}. Skipping extraction, keeping document. Error: {error}",
                     doc_id=doc.id,
                     error=e,
                 )

integrations/presidio/tests/test_presidio_document_cleaner.py

@@ -112,8 +112,7 @@ def test_run_skips_on_error(self, caplog):
         with caplog.at_level(logging.WARNING):
             result = cleaner.run(documents=[doc])
 
-        assert len(result["documents"]) == 1
-        assert result["documents"][0].content == "Some text with PII"
+        assert len(result["documents"]) == 0
         assert "Could not anonymize" in caplog.text
 
     def test_run_multiple_documents(self):