added updates to fix issue #358

.github/workflows/publish.yml

@@ -59,7 +59,7 @@ jobs:
       # - app-tag.zip
       # - app-tag-info.whl
       - name: Archive package
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
             name: dist
             path: ./dist
@@ -79,7 +79,7 @@ jobs:
 
       # download artifacts from job: build
       - name: Download artifacts from build
-        uses: actions/download-artifact@v2
+        uses: actions/download-artifact@v4
         with:
           name: dist
           path: dist
@@ -110,7 +110,7 @@ jobs:
         uses: actions/checkout@v2
 
       - name: Download artifacts from release
-        uses: actions/download-artifact@v2
+        uses: actions/download-artifact@v4
         with:
           name: dist
           path: dist

.github/workflows/test.yml

@@ -27,7 +27,7 @@ jobs:
     runs-on: ubuntu-latest
 
     container:
-      image: python:3.8
+      image: python:3.10
 
     steps:
       - name: Check out code
@@ -36,6 +36,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
+          pip install setuptools wheel
           pip install -r requirements.txt
           pip install pytest
           python setup.py develop
@@ -53,7 +54,7 @@ jobs:
 
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
 
     steps:
       - name: Check out code
@@ -67,6 +68,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
+          pip install setuptools wheel
           pip install -r requirements.txt
           pip install pytest pytest-cov
           python setup.py develop
@@ -82,7 +84,7 @@ jobs:
 
       # upload docx for further job
       - name: Archive package
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
-            name: outputs
+            name: outputs-py${{ matrix.python-version }}
             path: ./test/outputs

pdf2docx/table/Cell.py

@@ -19,6 +19,16 @@ def __init__(self, raw:dict=None):
         self.border_width = raw.get('border_width', (0,0,0,0)) # type: tuple [float]
         self.merged_cells = raw.get('merged_cells', (1,1)) # type: tuple [int]
 
+    def _block_text(self, block):
+        '''Get text from a block, always returning a str (for join).'''
+        if not hasattr(block, 'text'):
+            return '<NEST TABLE>'
+        t = block.text
+        if t is None:
+            return ''
+        if isinstance(t, list):
+            return '\n'.join(str(x) for x in t)
+        return str(t)
 
     @property
     def text(self):
@@ -28,8 +38,9 @@ def text(self):
         # fixme: prev code did `if block.is_text_block`, but sometimes
         # there is no `is_text_block` member; would be good to ensure
         # this member is always present and avoid use of `hasattr()`.
-        return '\n'.join([block.text if hasattr(block, 'text') else '<NEST TABLE>'
-                                for block in self.blocks])
+        return '\n'.join([self._block_text(block) for block in self.blocks])
+        # return '\n'.join([block.text if hasattr(block, 'text') else '<NEST TABLE>'
+        #                         for block in self.blocks])
 
 
     @property

requirements.txt

@@ -1,4 +1,4 @@
-PyMuPDF>=1.19.0
+PyMuPDF>=1.26.7
 python-docx>=0.8.10
 fonttools>=4.24.0
 numpy>=1.17.2

setup.py

@@ -50,7 +50,7 @@ def load_requirements(fname):
     include_package_data=True,
     zip_safe=False,
     install_requires=load_requirements("requirements.txt"),
-    python_requires=">=3.6",
+    python_requires=">=3.10",
     entry_points={
         "console_scripts": [
             "pdf2docx=pdf2docx.main:main"

test/test.py

@@ -247,6 +247,21 @@ def test_extracting_table(self):
             ['Description F', '1.00', '0.86', '0.37', '0.78', '0.01']
         ]
         assert table==sample
+
+    # ------------------------------------------
+    # extract tables with empty/none cells
+    # ------------------------------------------
+    def test_extract_tables_empty_cell(self):
+        '''Test extracting tables from demo-table-empty-cell.pdf (no crash, returns list).'''
+        # Test that extract_tables() handles tables with empty cells correctly.
+        filename = 'demo-table-empty-cell'
+        pdf_file = os.path.join(sample_path, f'{filename}.pdf')
+        cv = Converter(pdf_file)
+        tables = cv.extract_tables()
+        cv.close()
+        assert isinstance(tables, list), 'extract_tables() should return a list'
+        # At least one table expected from this sample
+        assert len(tables) >= 1, f'expected at least 1 table, got {len(tables)}'
 
 
     # ------------------------------------------