⬆ Upgrade requirements.txt (python-docx) and dev_requirements

dev_requirements/requirements-coverage.txt

@@ -1,8 +1,9 @@
+# SHA1:6dafbcf610e9f81897b65ee9142715ab2e793f9e
 #
-# This file is autogenerated by pip-compile with python 3.10
+# This file is autogenerated by pip-compile-multi
 # To update, run:
 #
-#    pip-compile requirements-coverage.in
+#    pip-compile-multi
 #
-coverage==7.5.0
-    # via -r dev_requirements/requirements-coverage.in
+coverage==7.5.1
+    # via -r dev_requirements\requirements-coverage.in

dev_requirements/requirements-formatting.txt

@@ -1,20 +1,23 @@
+# SHA1:2c7ffcd29222de3114c7f7994911f1b69d06b6b3
 #
-# This file is autogenerated by pip-compile with python 3.10
+# This file is autogenerated by pip-compile-multi
 # To update, run:
 #
-#    pip-compile requirements-formatting.in
+#    pip-compile-multi
 #
 black==24.4.2
-    # via -r dev_requirements/requirements-formatting.in
+    # via -r dev_requirements\requirements-formatting.in
 click==8.1.7
     # via black
+colorama==0.4.6
+    # via click
 isort==5.13.2
-    # via -r dev_requirements/requirements-formatting.in
+    # via -r dev_requirements\requirements-formatting.in
 mypy-extensions==1.0.0
     # via black
-packaging==23.0
+packaging==24.0
     # via black
-pathspec==0.11.0
+pathspec==0.12.1
     # via black
-platformdirs==3.1.0
+platformdirs==4.2.1
     # via black

dev_requirements/requirements-linting.txt

@@ -1,20 +1,23 @@
+# SHA1:0e15f8789b9d62fe90d1f1b0b6a7e32f13b99b19
 #
-# This file is autogenerated by pip-compile with python 3.10
+# This file is autogenerated by pip-compile-multi
 # To update, run:
 #
-#    pip-compile requirements-linting.in
+#    pip-compile-multi
 #
 astroid==3.1.0
     # via pylint
-dill==0.3.7
+colorama==0.4.6
+    # via pylint
+dill==0.3.8
     # via pylint
 isort==5.13.2
     # via pylint
 mccabe==0.7.0
     # via pylint
-platformdirs==3.1.0
+platformdirs==4.2.1
     # via pylint
 pylint==3.1.0
-    # via -r dev_requirements/requirements-linting.in
-tomlkit==0.11.6
+    # via -r dev_requirements\requirements-linting.in
+tomlkit==0.12.4
     # via pylint

dev_requirements/requirements-packaging.txt

@@ -1,55 +1,58 @@
+# SHA1:93e4fbf2b6cce1574fe3d5315360512fa9927699
 #
-# This file is autogenerated by pip-compile with Python 3.12
-# by the following command:
+# This file is autogenerated by pip-compile-multi
+# To update, run:
 #
-#    pip-compile dev_requirements/requirements-packaging.in
+#    pip-compile-multi
 #
+backports-tarfile==1.1.1
+    # via jaraco-context
 build==1.2.1
-    # via -r dev_requirements/requirements-packaging.in
+    # via -r dev_requirements\requirements-packaging.in
 certifi==2024.2.2
     # via requests
-cffi==1.16.0
-    # via cryptography
 charset-normalizer==3.3.2
     # via requests
-cryptography==42.0.5
-    # via secretstorage
-docutils==0.20.1
+colorama==0.4.6
+    # via build
+docutils==0.21.2
     # via readme-renderer
 idna==3.7
     # via requests
-importlib-metadata==7.0.2
+importlib-metadata==7.1.0
     # via
     #   keyring
     #   twine
-jaraco-classes==3.3.1
+jaraco-classes==3.4.0
     # via keyring
-jeepney==0.8.0
-    # via
-    #   keyring
-    #   secretstorage
-keyring==24.3.1
+jaraco-context==5.3.0
+    # via keyring
+jaraco-functools==4.0.1
+    # via keyring
+keyring==25.2.0
     # via twine
 markdown-it-py==3.0.0
     # via rich
 mdurl==0.1.2
     # via markdown-it-py
 more-itertools==10.2.0
-    # via jaraco-classes
-nh3==0.2.15
+    # via
+    #   jaraco-classes
+    #   jaraco-functools
+nh3==0.2.17
     # via readme-renderer
 packaging==24.0
     # via build
 pkginfo==1.10.0
     # via twine
-pycparser==2.21
-    # via cffi
-pygments==2.17.2
+pygments==2.18.0
     # via
     #   readme-renderer
     #   rich
-pyproject-hooks==1.0.0
+pyproject-hooks==1.1.0
     # via build
+pywin32-ctypes==0.2.2
+    # via keyring
 readme-renderer==43.0
     # via twine
 requests==2.31.0
@@ -62,10 +65,8 @@ rfc3986==2.0.0
     # via twine
 rich==13.7.1
     # via twine
-secretstorage==3.3.3
-    # via keyring
 twine==5.0.0
-    # via -r dev_requirements/requirements-packaging.in
+    # via -r dev_requirements\requirements-packaging.in
 urllib3==2.2.1
     # via
     #   requests

dev_requirements/requirements-tests.txt

@@ -1,23 +1,26 @@
+# SHA1:237de32e0e58475d734882e72523b53d0f1187a3
 #
-# This file is autogenerated by pip-compile with Python 3.11
-# by the following command:
+# This file is autogenerated by pip-compile-multi
+# To update, run:
 #
-#    pip-compile requirements-tests.in
+#    pip-compile-multi
 #
 attrs==23.2.0
     # via pytest-subtests
+colorama==0.4.6
+    # via pytest
 iniconfig==2.0.0
     # via pytest
-packaging==23.0
+packaging==24.0
     # via pytest
 pluggy==1.5.0
     # via pytest
 pytest==8.2.0
     # via
-    #   -r dev_requirements/requirements-tests.in
+    #   -r dev_requirements\requirements-tests.in
     #   pytest-datafiles
     #   pytest-subtests
 pytest-datafiles==3.0.0
-    # via -r dev_requirements/requirements-tests.in
+    # via -r dev_requirements\requirements-tests.in
 pytest-subtests==0.12.1
-    # via -r dev_requirements/requirements-tests.in
+    # via -r dev_requirements\requirements-tests.in

dev_requirements/requirements-type_check.txt

@@ -1,12 +1,13 @@
+# SHA1:7983aaa01d64547827c20395d77e248c41b2572f
 #
-# This file is autogenerated by pip-compile with Python 3.11
-# by the following command:
+# This file is autogenerated by pip-compile-multi
+# To update, run:
 #
-#    pip-compile requirements-type_check.in
+#    pip-compile-multi
 #
 mypy==1.10.0
-    # via -r dev_requirements/requirements-type_check.in
+    # via -r dev_requirements\requirements-type_check.in
 mypy-extensions==1.0.0
     # via mypy
-typing-extensions==4.8.0
+typing-extensions==4.11.0
     # via mypy

requirements.txt

@@ -2,12 +2,12 @@
 # This file is autogenerated by pip-compile with Python 3.11
 # by the following command:
 #
-#    pip-compile '.\requirements.in'
+#    pip-compile pyproject.toml
 #
 attrs==23.2.0
     # via
-    #   -r requirements.in
     #   cattrs
+    #   ebdamame (pyproject.toml)
     #   ebdtable2graph
 cattrs==22.2.0
     # via ebdtable2graph
@@ -16,9 +16,11 @@ certifi==2023.7.22
 charset-normalizer==2.1.1
     # via requests
 click==8.1.7
-    # via -r requirements.in
+    # via ebdamame (pyproject.toml)
+colorama==0.4.6
+    # via click
 ebdtable2graph==0.1.20
-    # via -r requirements.in
+    # via ebdamame (pyproject.toml)
 idna==3.7
     # via requests
 lxml==4.9.3
@@ -27,16 +29,16 @@ lxml==4.9.3
     #   python-docx
     #   svgutils
 more-itertools==10.2.0
-    # via -r requirements.in
+    # via ebdamame (pyproject.toml)
 networkx==2.8.8
     # via ebdtable2graph
-python-docx==1.1.0
-    # via -r requirements.in
+python-docx==1.1.2
+    # via ebdamame (pyproject.toml)
 requests==2.31.0
     # via ebdtable2graph
 svgutils==0.3.4
     # via ebdtable2graph
-typing-extensions==4.8.0
+typing-extensions==4.11.0
     # via python-docx
 urllib3==1.26.18
     # via requests

src/ebdamame/__init__.py

@@ -10,15 +10,16 @@
 from typing import Dict, Generator, Iterable, List, Optional, Tuple, Union
 
 import attrs
-from docx import Document  # type:ignore[import]
-from docx.oxml import CT_P, CT_Tbl  # type:ignore[import]
-from docx.table import Table, _Cell  # type:ignore[import]
-from docx.text.paragraph import Paragraph  # type:ignore[import]
+import docx
+from docx.document import Document as DocumentType
+from docx.oxml import CT_P, CT_Tbl
+from docx.table import Table, _Cell
+from docx.text.paragraph import Paragraph
 
 _logger = logging.getLogger(__name__)
 
 
-def get_document(docx_file_path: Path) -> Document:
+def get_document(docx_file_path: Path) -> DocumentType:
     """
     opens and returns the document specified in the docx_file_path using python-docx
     """
@@ -29,14 +30,14 @@ def get_document(docx_file_path: Path) -> Document:
         # but then switched from StringIO to BytesIO (without explicit 'utf-8') because of:
         # UnicodeDecodeError: 'charmap' codec can't decode byte 0x81 in position 605: character maps to <undefined>
     try:
-        document = Document(source_stream)
+        document = docx.Document(source_stream)
         _logger.info("Successfully read the file '%s'", docx_file_path)
         return document
     finally:
         source_stream.close()
 
 
-def _get_tables_and_paragaphs(document: Document) -> Generator[Union[Table, Paragraph], None, None]:
+def _get_tables_and_paragraphs(document: DocumentType) -> Generator[Union[Table, Paragraph], None, None]:
     """
     Yields tables and paragraphs from the given document in the order in which they occur in the document.
     This is helpful because document.tables and document.paragraphs are de-coupled and give you no information which
@@ -116,7 +117,7 @@ def get_ebd_docx_tables(docx_file_path: Path, ebd_key: str) -> List[Table]:
 
     is_inside_subsection_of_requested_table: bool = False
     tables: List[Table] = []
-    tables_and_paragraphs = _get_tables_and_paragaphs(document)
+    tables_and_paragraphs = _get_tables_and_paragraphs(document)
     for table_or_paragraph in tables_and_paragraphs:
         if isinstance(table_or_paragraph, Paragraph):
             paragraph: Paragraph = table_or_paragraph
@@ -213,7 +214,8 @@ def _enrich_paragraphs_with_sections(
     subsection = 1
     subsection_title: Optional[str] = None
     for paragraph in paragraphs:
-        match paragraph.style.style_id:
+        # since pyton-docx 1.1.2 there are type hints; seems like the style is not guaranteed to be not None
+        match paragraph.style.style_id:  #  type:ignore[union-attr]
             case "berschrift1":
                 chapter = next(chapter_counter)
                 chapter_title = paragraph.text.strip()

src/ebdamame/docxtableconverter.py

@@ -9,7 +9,7 @@
 from typing import Generator, List, Literal, Optional, Tuple
 
 import attrs
-from docx.table import Table, _Cell, _Row  # type:ignore[import]
+from docx.table import Table, _Cell, _Row
 from ebdtable2graph.models import EbdTable, EbdTableRow, EbdTableSubRow
 from ebdtable2graph.models.ebd_table import _STEP_NUMBER_REGEX, EbdCheckResult, EbdTableMetaData, MultiStepInstruction
 from more_itertools import first, first_true, last
@@ -46,6 +46,9 @@ def _get_index_of_first_column_with_step_number(cells: List[_Cell]) -> int:
     first_step_number_cell = first_true(
         cells, pred=lambda cell: _step_number_pattern.match(cell.text.strip()) is not None
     )
+    if first_step_number_cell is None:
+        raise ValueError("No cell containing a valid step number found.")
+
     step_number_column_index = cells.index(first_step_number_cell)
     _logger.debug("The step number is in column %i", step_number_column_index)
     return step_number_column_index

unittests/__init__.py

@@ -6,13 +6,13 @@
 from pathlib import Path
 from typing import Dict, List, Tuple
 
-from docx import Document  # type:ignore[import]
-from docx.table import Table  # type:ignore[import]
+from docx.document import Document as DocumentType
+from docx.table import Table
 
 import ebdamame
 
 
-def get_document(datafiles, filename: str) -> Document:
+def get_document(datafiles, filename: str) -> DocumentType:
     """
     a datafiles compatible wrapper around ebddocx2table.get_document
     """

unittests/test_highlevel.py

@@ -1,7 +1,7 @@
 from typing import List, Tuple
 
 import pytest  # type:ignore[import]
-from docx.table import Table  # type:ignore[import]
+from docx.table import Table
 from ebdtable2graph.models import EbdTable
 
 from ebdamame import EbdChapterInformation, TableNotFoundError