🧹 Switch to mypy --strict

src/kohlrahbi/__init__.py

@@ -12,7 +12,7 @@
 
 @click.group()
 @click.version_option(version=version)
-def cli():
+def cli() -> None:
  """Kohlrahbi CLI tool"""
 
 

src/kohlrahbi/ahb/__init__.py

@@ -48,7 +48,7 @@ def process_ahb_table(
  pruefi: str,
  output_path: Path,
  file_type: str,
-):
+) -> None:
  """
  Process the ahb table.
  """
@@ -98,7 +98,7 @@ def process_pruefi(
  path_to_ahb_docx_file: Path,
  output_path: Path,
  file_type: str,
-):
+) -> None:
  """
  Process one pruefi.
  If the input path ends with .docx, we assume that the file containing the pruefi is given.
@@ -183,7 +183,7 @@ def extract_pruefis_from_table(table: Table) -> list[str]:
 
 def table_header_contains_text_pruefidentifikator(table: Table) -> bool:
  """Checks if the table header contains the text 'Prüfidentifikator'."""
- return table.row_cells(0)[-1].paragraphs[-1].text.startswith("Prüfidentifikator")
+ return table.row_cells(0)[-1].paragraphs[-1].text.startswith("Prüfidentifikator") # type:ignore[no-any-return]
 
 
 def get_pruefi_to_file_mapping(basic_input_path: Path, format_version: EdifactFormatVersion) -> dict[str, str]:

src/kohlrahbi/ahb/command.py

@@ -12,7 +12,7 @@
 from kohlrahbi.enums.ahbexportfileformat import AhbExportFileFormat
 
 
-def check_python_version():
+def check_python_version() -> None:
  """
  Check if the Python interpreter is greater or equal to 3.11
  """
@@ -24,7 +24,7 @@ def check_python_version():
 
 
 # pylint: disable=unused-argument
-def validate_path(ctx, param, value):
+def validate_path(ctx, param, value) -> Path: # type:ignore[no-untyped-def]
  """
  Ensure the path exists or offer to create it.
  """
@@ -97,7 +97,7 @@ def ahb(
  format_version: EdifactFormatVersion | str,
  assume_yes: bool, # pylint: disable=unused-argument
  # it is used by the callback function of the output-path
-):
+) -> None:
  """
  Scrape AHB documents for pruefidentifikatoren.
  This is a command line interface for the pruefis module.

src/kohlrahbi/ahbtable/ahbcondtions.py

@@ -53,10 +53,11 @@ def collect_conditions(
  logger.info("The package conditions for %s were collected.", edifact_format)
  return conditions_dict
 
- def include_condition_dict(self, to_add=dict[EdifactFormat, dict[str, str]] | None) -> None:
+ def include_condition_dict(self, to_add: dict[EdifactFormat, dict[str, str]] | None) -> None:
  """ " Include a dict of conditions to the conditions_dict"""
  if to_add is None:
  logger.info("Conditions dict to be added is empty.")
+ return
  for edifact_format, edi_cond_dict in to_add.items():
  for condition_key, condition_text in edi_cond_dict.items():
  if edifact_format in self.conditions_dict:

src/kohlrahbi/ahbtable/ahbpackagetable.py

@@ -52,7 +52,7 @@ def provide_conditions(self, edifact_format: EdifactFormat) -> dict[EdifactForma
  logger.info("The package conditions for %s were collected.", edifact_format)
  return conditions_dict
 
- def provide_packages(self, edifact_format: EdifactFormat):
+ def provide_packages(self, edifact_format: EdifactFormat) -> None:
  """collect conditions from package table and store them in conditions dict."""
  package_dict: dict[EdifactFormat, dict[str, str]] = {edifact_format: {}}
 
@@ -80,10 +80,11 @@ def provide_packages(self, edifact_format: EdifactFormat):
  logger.info("Packages for %s were collected.", edifact_format)
  self.package_dict = package_dict
 
- def include_package_dict(self, to_add=dict[EdifactFormat, dict[str, str]] | None) -> None:
+ def include_package_dict(self, to_add: dict[EdifactFormat, dict[str, str]] | None) -> None:
  """Include a dict of conditions to the conditions_dict"""
  if to_add is None:
  logger.info("Packages dict to be added is empty.")
+ return
  for edifact_format, edi_cond_dict in to_add.items():
  for package_key, package_conditions in edi_cond_dict.items():
  if edifact_format in self.package_dict:

src/kohlrahbi/ahbtable/ahbsubtable.py

@@ -6,11 +6,12 @@
 
 import pandas as pd
 from docx.table import Table as DocxTable
-from docx.table import _Cell
+from docx.table import _Cell, _Row
 from pydantic import BaseModel, ConfigDict
 
 from kohlrahbi.ahbtable.ahbtablerow import AhbTableRow
-from kohlrahbi.row_type_checker import RowType, get_row_type
+from kohlrahbi.enums import RowType
+from kohlrahbi.row_type_checker import get_row_type
 from kohlrahbi.seed import Seed
 
 
@@ -122,7 +123,7 @@ def from_headless_table(cls, tmd: Seed, docx_table: DocxTable) -> "AhbSubTable":
  return cls(table_meta_data=tmd, table=ahb_table_dataframe)
 
  @staticmethod
- def iter_visible_cells(row) -> Generator[_Cell, None, None]:
+ def iter_visible_cells(row: _Row) -> Generator[_Cell, None, None]:
  """
  This function makes sure that you will iterate over the cells you see in the word document.
  For more information go to https://github.com/python-openxml/python-docx/issues/970#issuecomment-877386927

src/kohlrahbi/ahbtable/ahbtablerow.py

@@ -9,7 +9,7 @@
 from pydantic import BaseModel, ConfigDict
 
 from kohlrahbi.docxtablecells import BedingungCell, BodyCell, EdifactStrukturCell
-from kohlrahbi.row_type_checker import RowType
+from kohlrahbi.enums import RowType
 from kohlrahbi.seed import Seed
 
 

src/kohlrahbi/changehistory/command.py

@@ -47,7 +47,7 @@ def changehistory(
  format_version: EdifactFormatVersion | str,
  assume_yes: bool, # pylint: disable=unused-argument
  # it is used by the callback function of the output-path
-):
+) -> None:
  """
  Scrape change histories from the input path and save them to the output path.
 

src/kohlrahbi/conditions/__init__.py

@@ -45,7 +45,6 @@ def scrape_conditions(
  for edifact_format, files in all_format_files.items():
  for file in files:
  # pylint: disable=too-many-function-args
- # type: ignore[call-arg, arg-type]
  path: Path = basic_input_path / path_to_file / Path(file)
  doc = docx.Document(str(path.absolute()))
  logger.info("Start scraping conditions for %s in %s", edifact_format, file)

src/kohlrahbi/conditions/command.py

@@ -28,7 +28,7 @@
 from kohlrahbi.conditions import scrape_conditions
 
 
-def check_python_version():
+def check_python_version() -> None:
  """
  Check if the Python interpreter is greater or equal to 3.11
  """
@@ -40,7 +40,7 @@ def check_python_version():
 
 
 # pylint: disable=unused-argument
-def validate_path(ctx, param, value):
+def validate_path(ctx, param, value) -> Path: # type:ignore[no-untyped-def]
  """
  Ensure the path exists or offer to create it.
  """
@@ -91,7 +91,7 @@ def validate_path(ctx, param, value):
 )
 def conditions(
  edi_energy_mirror_path: Path, output_path: Path, format_version: EdifactFormatVersion | str, assume_yes: bool
-):
+) -> None:
  """
  Scrape AHB documents for conditions.
  """

src/kohlrahbi/docxfilefinder.py

@@ -138,7 +138,7 @@ def filter_docx_files_for_edifact_format(self, edifact_format: EdifactFormat) ->
 
  self.paths_to_docx_files = [path for path in self.paths_to_docx_files if str(edifact_format) in path.name]
 
- def remove_temporary_files(self):
+ def remove_temporary_files(self) -> None:
  """
  This method removes all temporary files from paths_to_docx_files.
  Temporary files lead to the exception `BadZipFile: File is not a zip file`.

src/kohlrahbi/docxtablecells/__init__.py

@@ -5,3 +5,5 @@
 from .bedinungscell import BedingungCell
 from .bodycell import BodyCell
 from .edifactstrukturcell import EdifactStrukturCell
+
+__all__ = ["BedingungCell", "BodyCell", "EdifactStrukturCell"]

src/kohlrahbi/docxtablecells/bodycell.py

@@ -4,6 +4,7 @@
 
 import pandas as pd
 from docx.table import _Cell
+from docx.text.paragraph import Paragraph
 from maus.reader.flat_ahb_reader import FlatAhbCsvReader
 from pydantic import BaseModel, ConfigDict
 
@@ -103,9 +104,9 @@ def parse(self, ahb_row_dataframe: pd.DataFrame) -> pd.DataFrame:
 
  return ahb_row_dataframe
 
- def has_paragraph_tabstops(self, paragraph) -> bool:
+ def has_paragraph_tabstops(self, paragraph: Paragraph) -> bool:
  """
  Checks if the given paragraph contains tabstops
  """
  tab_stops = list(paragraph.paragraph_format.tab_stops)
- return len(tab_stops) > 0
+ return any(tab_stops)

src/kohlrahbi/enums/__init__.py

@@ -4,3 +4,5 @@
 
 from .row_type import RowType
 from .row_type_color import RowTypeColor
+
+__all__ = ["RowType", "RowTypeColor"]

src/kohlrahbi/read_functions.py

@@ -48,7 +48,7 @@ def table_header_starts_with_text_edifact_struktur(table: Table) -> bool:
  return table.cell(row_idx=0, col_idx=0).text.strip() == "EDIFACT Struktur"
 
 
-def is_item_header_of_change_history_section(item: Paragraph | Table | None, style_name: str) -> bool:
+def is_item_header_of_change_history_section(item: Paragraph | Table | None, style_name: str) -> TypeGuard[Paragraph]:
  """
  Checks if the given item is a header of the change history section.
  """
@@ -57,14 +57,14 @@ def is_item_header_of_change_history_section(item: Paragraph | Table | None, sty
  return isinstance(item, Paragraph) and "Änderungshistorie" in item.text and "Heading" in style_name
 
 
-def is_item_text_paragraph(item: Paragraph | Table | None, style_name: str) -> bool:
+def is_item_text_paragraph(item: Paragraph | Table | None, style_name: str) -> TypeGuard[Paragraph]:
  """
  Checks if the given item is a text paragraph.
  """
  return isinstance(item, Paragraph) and "Heading" not in style_name
 
 
-def is_item_table_with_pruefidentifikatoren(item: Paragraph | Table | None) -> bool:
+def is_item_table_with_pruefidentifikatoren(item: Paragraph | Table | None) -> TypeGuard[Table]:
  """
  Check if the item is a Table and contains Pruefidentifikatoren.
 
@@ -81,7 +81,7 @@ def is_item_headless_table(
  item: Paragraph | Table | None,
  # seed: Seed | None,
  ahb_table: AhbTable | None,
-) -> bool:
+) -> TypeGuard[Table]:
  """
  Checks if the given item is a headless table.
 
@@ -97,7 +97,7 @@ def is_item_headless_table(
  return isinstance(item, Table) and ahb_table is not None
 
 
-def get_ahb_table(document, pruefi: str) -> Optional[AhbTable]:
+def get_ahb_table(document: Document, pruefi: str) -> Optional[AhbTable]:
  """
  Reads a docx file and extracts all information for a given Prüfidentifikator.
  If the Prüfidentifikator is not found or we reach the end of the AHB document
@@ -111,8 +111,8 @@ def get_ahb_table(document, pruefi: str) -> Optional[AhbTable]:
  AhbTable or None: The extracted AHB table or None if not found
  """
 
- ahb_table = None
- seed = None
+ ahb_table: AhbTable | None = None
+ seed: Seed | None = None
  searched_pruefi_is_found = False
 
  for item in get_all_paragraphs_and_tables(document):
@@ -133,37 +133,47 @@ def get_ahb_table(document, pruefi: str) -> Optional[AhbTable]:
 
  searched_pruefi_is_found, ahb_table = process_table(item, pruefi, searched_pruefi_is_found, ahb_table, seed)
 
- if ahb_table:
+ if ahb_table is not None:
  ahb_table.sanitize()
  return ahb_table
 
  log_pruefi_not_found(pruefi)
  return None
 
 
-def get_style_name(item) -> str:
+def get_style_name(item: Paragraph | Table) -> str:
  """Extracts and normalizes the style name of a document item."""
- return item.style.name if item.style else "None"
+ return item.style.name if item.style else "None" # type:ignore[no-any-return]
 
 
-def reached_end_of_document(style_name, item) -> bool:
+def reached_end_of_document(style_name: str, item: Paragraph | Table | None) -> bool:
  """Checks if the current item marks the end of the document."""
  return is_item_header_of_change_history_section(item, style_name)
 
 
-def update_seed(item, seed):
+def update_seed(item: Paragraph | Table | None, seed: Seed | None) -> Seed | None:
  """Updates the seed if the current item is a table with Prüfidentifikatoren."""
  if is_item_table_with_pruefidentifikatoren(item):
  return Seed.from_table(docx_table=item)
  return seed
 
 
-def should_end_search(pruefi, seed, searched_pruefi_is_found):
+def should_end_search(pruefi: str, seed: Seed | None, searched_pruefi_is_found: bool) -> bool:
  """Determines if the search for the AHB table should end."""
- return seed and pruefi not in seed.pruefidentifikatoren and searched_pruefi_is_found
+ if seed is None:
+ return False
+ if pruefi not in seed.pruefidentifikatoren:
+ return False
+ return searched_pruefi_is_found
 
 
-def process_table(item, pruefi, searched_pruefi_is_found, ahb_table, seed=None):
+def process_table(
+ item: Paragraph | Table | None,
+ pruefi: str,
+ searched_pruefi_is_found: bool,
+ ahb_table: AhbTable,
+ seed: Seed | None = None,
+) -> tuple[bool, AhbTable]:
  """Processes tables to find and build the AHB table."""
  if is_item_table_with_pruefidentifikatoren(item):
  seed = Seed.from_table(docx_table=item)
@@ -176,35 +186,36 @@ def process_table(item, pruefi, searched_pruefi_is_found, ahb_table, seed=None):
 
  # elif is_item_headless_table(item, seed, ahb_table):
  elif is_item_headless_table(item, ahb_table):
+ assert seed is not None
  ahb_sub_table = AhbSubTable.from_headless_table(docx_table=item, tmd=seed)
  ahb_table.append_ahb_sub_table(ahb_sub_table=ahb_sub_table)
 
  return searched_pruefi_is_found, ahb_table
 
 
 # Logging functions
-def log_end_of_document(pruefi):
+def log_end_of_document(pruefi: str) -> None:
  """
  Logs that the end of the document was reached before finding the table for a given Prüfi.
  """
  logger.info("Reached the end of the document before finding the table for Prüfi '%s'.", pruefi)
 
 
-def log_end_of_ahb_table(pruefi):
+def log_end_of_ahb_table(pruefi: str) -> None:
  """
  Logs that the end of the AHB table was reached for a given Prüfi.
  """
  logger.info("Reached the end of the AHB table for Prüfi '%s'.", pruefi)
 
 
-def log_found_pruefi(pruefi):
+def log_found_pruefi(pruefi: str) -> None:
  """
  Logs that the AHB table for a given Prüfi was found.
  """
  logger.info("Found the AHB table for Prüfi '%s'.", pruefi)
 
 
-def log_pruefi_not_found(pruefi):
+def log_pruefi_not_found(pruefi: str) -> None:
  """
  Logs that the Prüfi was not found in the provided document.
  """
@@ -275,7 +286,9 @@ def is_last_row_unt_0062(item: Table | Paragraph) -> bool:
  return isinstance(item, Table) and "UNT\t0062" == item.cell(row_idx=-1, col_idx=0).text.strip()
 
 
-def is_relevant_pruefi_table(item: Paragraph | Table, seed: Seed, edifact_format) -> TypeGuard[Table]:
+def is_relevant_pruefi_table(
+ item: Paragraph | Table, seed: Seed | None, edifact_format: EdifactFormat
+) -> TypeGuard[Table]:
  """compares new pruefis to last pruefi and thus checks whether new table"""
  return (
  isinstance(item, Table)

src/kohlrahbi/row_type_checker.py

@@ -10,7 +10,7 @@
 from kohlrahbi.enums import RowType
 
 
-def set_table_header_bg_color(cell, hex_color: str):
+def set_table_header_bg_color(cell: _Cell, hex_color: str) -> _Cell:
  """
  set background shading for Header Rows
  """
@@ -48,7 +48,8 @@ def is_row_segmentname(edifact_struktur_cell: _Cell) -> bool:
  bool:
  """
  try:
- return edifact_struktur_cell.paragraphs[0].runs[0].font.color.rgb == RGBColor(128, 128, 128) # grey
+ colour_is_grey: bool = edifact_struktur_cell.paragraphs[0].runs[0].font.color.rgb == RGBColor(128, 128, 128)
+ return colour_is_grey
  except IndexError:
  return False