Version 3.27.0rc0

.github/workflows/ci-cd.yaml

@@ -69,10 +69,10 @@ jobs:
 #        python-version: ['3.12']
         os: [ubuntu-latest]
         disable-gil: [false]
-        # 29-oct-24 lxml does not build for free-threaded (requires libxml2 and libxslt development packages
-        include:
+        # 29-oct-24 lxml does not build for free-threaded even with libxml2 and libxslt1 development packages
+#        include:
           # Free-threaded from https://github.com/actions/setup-python/issues/771#issuecomment-2439954031
-          - { os: ubuntu-latest, python-version: '3.13', disable-gil: true }
+#          - { os: ubuntu-latest, python-version: '3.13', disable-gil: true }
 
     # Set up Redis per https://docs.github.com/en/actions/guides/creating-redis-service-containers
     # If you are using GitHub-hosted runners, you must use an Ubuntu runner
@@ -145,22 +145,10 @@ jobs:
           sudo apt-get -y install python3-dbus build-essential libpoppler-cpp-dev pkg-config python3-dev tesseract-ocr
           pip install --upgrade pdftotext pytesseract
 
-      - name: Install distribution's lxml for Python 3.13t (Linux Python latest free-threaded)
-        # https://lxml.de/installation.html#installation
-        if: matrix.disable-gil && matrix.python-version == '3.13' && runner.os == 'Linux'
-        run: |
-          sudo apt-get -y install python3-lxml
-
-      - name: Install all other dependencies (gil)
-        if: "${{ !matrix.disable-gil }}"
+      - name: Install all other dependencies
         run: |
           pip install --upgrade coveralls -r requirements.txt -r tests/requirements_pytest.txt
 
-      - name: Install all other dependencies (free-threaded)
-        if: "${{ matrix.disable-gil }}"
-        run: |
-          pip install --upgrade coveralls -r requirements.txt -r tests/requirements_pytest.txt 'lxml==4.8.0-1build1'
-
 #      - name: Install all other dependencies (py12)
 #        if: matrix.python-version == '3.12'
 #        run: |

tests/data/docs_filters_testdata.yaml

@@ -387,7 +387,9 @@ https://example.net/pdf-test-keep-monospace.pdf:
   output: A PDF Document that can be turned into plain text.
 https://example.net/pdf-no-multiple-spaces.pdf:
   filename: pdf-test-multiple-spaces.pdf
-  output: This PDF document has lots of multiple spaces.
+  output: >-
+    This PDF document has lots of multiple
+    spaces.
 https://example.net/ocr-test.png:
   # Image taken from https://stackoverflow.com/q/39754903/1047040
   filename: ocr-test.png