Merge branch 'main' into hf-kklein-patch-4

.gitignore

@@ -132,3 +132,7 @@ dmypy.json
 
 # vscode settings
 .vscode/
+
+# version number for ebdamame; gets auto-generated during the command
+# python -m build
+src/ebdamame/version.py

.pre-commit-config.yaml

@@ -1,18 +1,18 @@
 # to update all repo revisions just run: pre-commit autoupdate
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v5.0.0
     hooks:
       - id: check-yaml
       - id: end-of-file-fixer
       - id: trailing-whitespace
   - repo: https://github.com/psf/black
-    rev: 22.10.0
+    rev: 24.10.0
     hooks:
       - id: black
         language_version: python3
   - repo: https://github.com/pycqa/isort
-    rev: 5.10.1
+    rev: 5.13.2
     hooks:
       - id: isort
         name: isort (python)

README.md

@@ -1,5 +1,7 @@
 # ebdamame
 
+[![License: GPL](https://img.shields.io/badge/License-GPL-yellow.svg)](LICENSE)
+![Python Versions (officially) supported](https://img.shields.io/pypi/pyversions/ebdamame.svg)
 ![Unittests status badge](https://github.com/Hochfrequenz/ebdamame/workflows/Unittests/badge.svg)
 ![Coverage status badge](https://github.com/Hochfrequenz/ebdamame/workflows/Coverage/badge.svg)
 ![Linting status badge](https://github.com/Hochfrequenz/ebdamame/workflows/Linting/badge.svg)

pyproject.toml

@@ -28,7 +28,7 @@ dynamic = ["readme", "version"]
 
 [project.optional-dependencies]
 coverage = [
-    "coverage==7.6.3"
+    "coverage==7.6.4"
 ]
 formatting = [
     "black==24.10.0",
@@ -47,10 +47,11 @@ test_packaging = [
 tests = [
     "pytest==8.3.3",
     "pytest-datafiles==3.0.0",
-    "pytest-subtests==0.13.1"
+    "pytest-subtests==0.13.1",
+    "syrupy==4.7.2"
 ]
 type_check = [
-    "mypy==1.11.2"
+    "mypy==1.13.0"
 ]
 
 [project.urls]
@@ -96,3 +97,7 @@ exclude = ["/unittests"]
 [tool.hatch.build.targets.wheel]
 only-include = ["src"]
 sources = ["src"]
+
+[tool.pytest.ini_options]
+pythonpath = ["."]
+markers = ["snapshot: mark a test as a snapshot test"]

requirements.txt

@@ -17,6 +17,8 @@ charset-normalizer==3.3.2
     # via requests
 click==8.1.7
     # via -r requirements.in
+colorama==0.4.6
+    # via click
 idna==3.7
     # via requests
 lxml==5.2.1
@@ -30,7 +32,7 @@ networkx==3.3
     # via rebdhuhn
 python-docx==1.1.2
     # via -r requirements.in
-rebdhuhn==0.3.0
+rebdhuhn==0.3.1
     # via -r requirements.in
 requests==2.32.0
     # via rebdhuhn

src/ebdamame/__init__.py

@@ -55,7 +55,7 @@ def _get_tables_and_paragraphs(document: DocumentType) -> Generator[Union[Table,
 
 
 _ebd_key_pattern = re.compile(r"^E_\d{4}$")
-_ebd_key_with_heading_pattern = re.compile(r"^(?P<key>E_\d{4})_(?P<title>.*)\s*$")
+_ebd_key_with_heading_pattern = re.compile(r"^(?P<key>E_\d{4})_?(?P<title>.*)\s*$")
 
 
 class TableNotFoundError(Exception):
@@ -255,6 +255,9 @@ def get_all_ebd_keys(docx_file_path: Path) -> Dict[str, Tuple[str, EbdChapterInf
     for paragraph, ebd_kapitel in _enrich_paragraphs_with_sections(document.paragraphs):
         match = _ebd_key_with_heading_pattern.match(paragraph.text)
         if match is None:
+            contains_ebd_number = paragraph.text.lstrip().startswith("E_")
+            if contains_ebd_number:
+                _logger.warning("Found EBD number but could not match: '%s'", paragraph.text)
             continue
         ebd_key = match.groupdict()["key"]
         title = match.groupdict()["title"]

src/ebdamame/docxtableconverter.py

@@ -169,7 +169,10 @@ def __init__(self, docx_tables: List[Table], ebd_key: str, chapter: str, sub_cha
             # remove duplicates. Although there are usually only 5 columns visible, technically there might be even 8.
             # In these cases (e.g. for E_0453) columns like 'Prüfergebnis' simply occur twice in the docx table header.
             distinct_cell_texts: List[str] = [
-                x[0] for x in groupby(first(docx_tables).row_cells(row_index), lambda cell: cell.text)
+                x[0]
+                for x in groupby(
+                    first(docx_tables).rows[row_index].cells, lambda cell: cell.text
+                )  # row_cells() is deprecated and returns false rows
             ]
             for column_index, table_cell_text in enumerate(distinct_cell_texts):
                 if row_index == 0 and _is_pruefende_rolle_cell_text(table_cell_text):
@@ -188,7 +191,8 @@ def __init__(self, docx_tables: List[Table], ebd_key: str, chapter: str, sub_cha
                     self._column_index_result_code = column_index
                 elif table_cell_text == "Hinweis":
                     self._column_index_note = column_index
-
+        # if not self._column_index_step_number:
+        # self._column_index_step_number = 0
         self._metadata = EbdTableMetaData(ebd_code=ebd_key, sub_chapter=sub_chapter, chapter=chapter, role=role)
 
     @staticmethod

tox.ini

@@ -19,6 +19,14 @@ deps =
 setenv = PYTHONPATH = {toxinidir}/src
 commands = python -m pytest --basetemp={envtmpdir} {posargs}
 
+[testenv:snapshots]
+# the tests environment is called by the Github action that runs the unit tests
+deps =
+    -r requirements.txt
+    .[tests]
+setenv = PYTHONPATH = {toxinidir}/src
+commands = python -m pytest -m snapshot --basetemp={envtmpdir} {posargs} --snapshot-update
+
 [testenv:linting]
 # the linting environment is called by the Github Action that runs the linter
 deps =