linting with ruff

pyproject.toml

@@ -14,12 +14,18 @@ license = "Beerware"
 requires = [
     "pyperclip >=1.8.0",
     "click >= 7.1.2",
-    "black",
+    "pandas",
+    "openpyxl",
+    "ruff",
     "py-gitea",
+    "PyPDFForm",
 ]
 
 
 [tool.flit.scripts]
+form_inspect = "work_helpers.fill_forms:inspect"
+form_prepare_payments = "work_helpers.fill_forms:prepare_payments"
+form_fill_payments = "work_helpers.fill_forms:payments"
 nice_path = "work_helpers.nice_path:make_nice_path"
 random_password = "work_helpers.password:get_random_password"
 random_ints = "work_helpers.random_int:generate_random_number_list"
@@ -30,3 +36,50 @@ sg_mbp_issue_ref = "work_helpers.sg_mbp_issue:sg_mbp_issue_ref"
 xls2changelog = "work_helpers.excel2changelog:cli"
 xls2markdown = "work_helpers.excel2markdown:cli"
 xls2pylist = "work_helpers.excel2pylist:cli"
+
+
+
+[tool.ruff]
+# see https://docs.astral.sh/ruff/configuration/
+
+line-length = 80
+indent-width = 4
+
+fix = true
+
+[tool.ruff.lint]
+# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
+# Unlike Flake8, Ruff doesn't enable pycodestyle warnings (`W`) or
+# McCabe complexity (`C901`) by default.
+fixable = ["ALL"]
+select = ["ALL"]
+ignore = [
+    # ignored for now, should be activated in the future
+    # docstrings
+    "D",
+
+    # don't complain about not annotating self or cls
+    "ANN101",
+    "ANN102",
+
+    # ignored, "ruff format" will handle this
+    "COM812", 
+    "ISC001",
+
+    # ignored, due to Windows / WSL2 setup
+    # flake8-executable
+    "EXE",
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "pep257"  # Accepts: "google", "numpy", or "pep257".
+
+[tool.ruff.lint.per-file-ignores]
+# see https://github.com/charliermarsh/ruff
+"tests/*" = ["FBT003", "INP001", "PLR2004", "S101", "SLF001", "ANN"]
+"noxfile.py" = ["ANN"]
+
+
+[tool.ruff.format]
+indent-style = "space"
+

work_helpers/__init__.py

@@ -1,3 +1,3 @@
-""" Some helper scripts for the day to day work with Ubuntu in WSL2 """
+"""Some helper scripts for the day to day work with Ubuntu in WSL2"""
 
 __version__ = "0.0.2"

work_helpers/_natural_sort.py

@@ -1,4 +1,4 @@
-""" Sort the content of an list in a natural way
+"""Sort the content of an list in a natural way
 
 > l = ["A2", "A10", "A1", "A3"]
 > sorted(l)
@@ -21,7 +21,8 @@ def _nartural_sort_convert(text):
 
 def _nartural_sort_alphanum_key(text):
     return tuple(
-        _nartural_sort_convert(part) for part in _NATURAL_SORT_REGEX_DIGITS.split(text)
+        _nartural_sort_convert(part)
+        for part in _NATURAL_SORT_REGEX_DIGITS.split(text)
     )
 
 

work_helpers/excel2changelog.py

@@ -13,13 +13,13 @@ sheet = "Input_Data_*"
 col_start = "A"
 row_start = 8
 
+
 def xls_formula_spacing(formula):
     for c in "();=":
         formula = formula.replace(c, f"{c} ")
     return formula
 
 
-
 def text_to_changelog(
     raw_text, sheet, start_column, start_row, compact=False, keep=False
 ):
@@ -55,9 +55,13 @@ def text_to_changelog(
         prev = current
 
 
-def clipboard_to_changelog(sheet, start_column, start_row, compact=False, keep=False):
+def clipboard_to_changelog(
+    sheet, start_column, start_row, compact=False, keep=False
+):
     xls = pyperclip.paste()
-    result = list(text_to_changelog(xls, sheet, start_column, start_row, compact, keep))
+    result = list(
+        text_to_changelog(xls, sheet, start_column, start_row, compact, keep)
+    )
     line_count = len(result)
     if line_count == 1:
         print(f"Copied one line to the clipboard")
@@ -74,7 +78,9 @@ def clipboard_to_changelog(sheet, start_column, start_row, compact=False, keep=F
 
 
 @click.command()
-@click.option("-s", "--sheet", prompt=True, required=True, default="Input_Data_*")
+@click.option(
+    "-s", "--sheet", prompt=True, required=True, default="Input_Data_*"
+)
 @click.option("-w", "--well", prompt=True, required=True, default="A1")
 @click.option("-c", "--compact", is_flag=True)
 @click.option("-k", "--keep", is_flag=True)

work_helpers/excel2pylist.py

@@ -1,12 +1,15 @@
 import click
 import pyperclip
 
+
 def _strip_parts(iterable):
     return [item.strip() for item in iterable]
 
+
 def _replace_empty_strings(iterable, replacement="None"):
     return [i or replacement for i in iterable]
 
+
 def prepare(text):
     lines = text.splitlines()
 
@@ -31,13 +34,17 @@ def pad_field(index, t):
     else:
         return value.ljust(length)
 
+
 def pad_fields(iterable, lengths):
     return [pad_field(i, t) for i, t in enumerate(zip(iterable, lengths))]
 
+
 def build_list(table, lengths):
     padded = (pad_fields(l, lengths) for l in table)
     padded_lines = (", ".join(l) for l in padded)
-    lines_as_list = (f"    [{l}],  # noqa: E201, E202, E203, E501," for l in padded_lines)
+    lines_as_list = (
+        f"    [{l}],  # noqa: E201, E202, E203, E501," for l in padded_lines
+    )
     list_content = "\n".join(lines_as_list)
     return f"[\n{list_content}\n]\n"
 

work_helpers/fill_forms.py

@@ -0,0 +1,230 @@
+import click
+from datetime import datetime
+import pathlib
+import sys
+import shutil
+import pandas as pd
+import warnings
+import re
+
+from PyPDFForm import FormWrapper, PdfWrapper
+
+warnings.filterwarnings("ignore")
+
+Pathlike = pathlib.Path | str
+
+WINHOME = pathlib.Path("/mnt/c/Users/Holgi/")
+DESKTOP = WINHOME / "Desktop"
+
+TODAY = datetime.now().strftime("%Y-%m-%d")
+
+
+def _iso_date_to_german(date: str) -> str:
+    return ".".join(reversed(date.split("-")))
+
+
+def _search_files(
+    folder: Pathlike, partial_name: str, suffix: str
+) -> list[pathlib.Path]:
+    parent = pathlib.Path(folder)
+    if not suffix.startswith("."):
+        suffix = f".{suffix}"
+    files = (item for item in parent.iterdir() if item.is_file())
+    non_hidden = (item for item in files if not item.stem.startswith("."))
+    non_tempfile = (item for item in files if not item.stem.startswith("~"))
+    types = (
+        item for item in non_tempfile if item.suffix.lower() == suffix.lower()
+    )
+    return [item for item in types if partial_name.lower() in item.stem.lower()]
+
+
+def _get_latest_file(
+    folder: Pathlike, partial_name: str, suffix: str
+) -> pathlib.Path | None:
+    results = _search_files(folder, partial_name, suffix)
+    if not results:
+        return None
+    creation_times = [item.stat().st_ctime for item in results]
+    by_creation_time = sorted(zip(creation_times, results))
+    newest_with_time = by_creation_time[-1]  # latest entry
+    return newest_with_time[1]  # the path entry of the tuple
+
+
+def _get_form_path(partial_name: str) -> pathlib.Path:
+    own_parent = pathlib.Path(__file__).parent
+    matches = _search_files(own_parent, partial_name, ".pdf")
+    if len(matches) == 1:
+        return matches[0]
+    counts = len(matches)
+    msg = f"Found {counts} matching pdf forms for '{partial_name}'"
+    raise IOError(msg)
+
+
+def _get_unique(data: pd.DataFrame, column: str) -> str | int | float:
+    uniques = data[column].unique()
+    if len(uniques) != 1:
+        msg = f"Found multiple unique values for '{column}'"
+        raise ValueError(msg)
+    return uniques[0]
+
+
+def _extract_travel_number(data: pd.DataFrame, column: str) -> str:
+    belege = data[column]
+    travel_nr = belege.apply(
+        lambda x: re.search("(5\d{7,8})", x.replace(" ", ""))
+    )
+    match_result = travel_nr[travel_nr.first_valid_index()]
+    return match_result[0]
+
+
+@click.command()
+@click.argument(
+    "form", type=click.Path(exists=True, file_okay=True, dir_okay=False)
+)
+@click.option(
+    "-o",
+    "--output",
+    default=None,
+    help="Output file path, defaults to desktop folder",
+)
+def inspect(form, output):
+    form = pathlib.Path(form)
+    if not output:
+        new_name = f"inspected {form.stem}{form.suffix}"
+        output = DESKTOP / new_name
+    preview_stream = PdfWrapper(str(form)).preview
+    with output.open("wb+") as output_stream:
+        output_stream.write(preview_stream)
+
+
+def payments():
+    downloads = WINHOME / "Downloads"
+    forms = DESKTOP / "Formulare"
+
+    latest_export = _get_latest_file(downloads, "Buchungen_SAP", ".xlsx")
+    if not latest_export:
+        sys.exit("Could not find an SuperX export file, aborting.")
+
+    fields = ["BelegNr", "VorgängerBelegNr", "Kostenstelle", "Fonds", "Projekt"]
+    converters = {field: str for field in fields}
+    data = pd.read_excel(latest_export, skiprows=3, converters=converters)
+
+    travel_nr = _extract_travel_number(data, "BelegNr")
+
+    mask = data["Werttyp"] == "Zahlung"
+    payments = data[mask].copy()
+
+    summary = (
+        payments.groupby("BelegNr")
+        .agg({"Betrag": "sum", "BuDat": "first"})
+        .reset_index()
+        .sort_values("BelegNr")
+    )
+
+    try:
+        cost_center = _get_unique(payments, "Kostenstelle")
+        fonds = _get_unique(payments, "Fonds")
+        project = _get_unique(payments, "Projekt")
+        if not project or len(project) <= 4:
+            project = ""
+    except ValueError as e:
+        sys.exit(str(e))
+
+    form_data = {
+        "Projekt": project,
+        "Kostenstelle": cost_center,
+        "Mittelbindung": travel_nr,
+        "Fonds": fonds,
+    }
+    print(f"Projekt:       {project}")
+    print(f"Kostenstelle:  {cost_center}")
+    print(f"Mittelbindung: {travel_nr}")
+    print(f"Fonds:         {fonds}")
+
+    print("")
+    print(f"    Datum          Betrag    SuperX")
+    print("")
+
+    for i, row in summary.iterrows():
+        index = i + 1
+        form_data.update(
+            {
+                f"Datum{index}": row["BuDat"],
+                f"BelegNr aus SuberX{index}": row["BelegNr"],
+                # no field "Euro{index}"
+                # the automatic form calculation would not work.
+            }
+        )
+        betrag = f"{row['Betrag']:0.2f}".replace(".", ",")
+        print(f"    {row['BuDat']}    {betrag:>7}    {row['BelegNr']}")
+
+    source_path = forms / "Vorlage UK-Abschlag, v2023-01.pdf"
+    destination_path = DESKTOP / f"{TODAY} UK-Abschlag.pdf"
+    form = FormWrapper(str(source_path))
+    filled = form.fill(form_data, flatten=False)
+    destination_path.write_bytes(filled.read())
+
+
+@click.command()
+@click.option("-l", "--search_last_name", prompt=True, required=True)
+@click.option("-d", "--iso_date", prompt=True, required=True)
+@click.option("-p", "--place", prompt=True, required=True)
+def prepare_payments(search_last_name: str, iso_date: str, place: str):
+    forms_path = DESKTOP / "Formulare"
+    templates_path = forms_path / "vorbereitet UK-As"
+
+    templates = _search_files(templates_path, f" {search_last_name}", ".pdf")
+    if len(templates) == 0:
+        sys.exit(
+            f"Could not find a UK-A template for search '{search_last_name}'"
+        )
+    if len(templates) > 1:
+        sys.exit(
+            f"Found multiple UK-A templates for search '{search_last_name}'"
+        )
+    template = templates[0]
+
+    rest, first_name = template.stem.rsplit(",", maxsplit=1)
+    *_, last_name = rest.split()
+    first_name = first_name.strip()
+    last_name = last_name.strip()
+
+    first_last = f"{first_name} {last_name}"
+    last_first = f"{last_name}, {first_name}"
+    travel_short = f"{last_first}, {place}"
+    travel_name = f"{iso_date} {travel_short}"
+    date = _iso_date_to_german(iso_date)
+
+    folder = DESKTOP / f"{travel_name} (abgerechnet)"
+    folder.mkdir()
+
+    rk_path = folder / f" {travel_short}, Reisekostenabrechnung.txt"
+    rk_path.write_text(rk_path.stem)
+
+    uka_hint_path = (
+        folder / f" UK-A {last_first}, Dienstreise {place}, Schlusszahlung.txt"
+    )
+    content = "\t".join(
+        [
+            _iso_date_to_german(TODAY),
+            first_last,
+            f"Schlusszahlung Dienstreise {place}, {date}",
+        ]
+    )
+    uka_hint_path.write_text(content)
+
+    source_path = forms_path / "Vorlage UK-Abschlag, v2023-01.pdf"
+    destination_path = folder / f"{TODAY} {travel_short}, UK-Abschlag.pdf"
+    shutil.copy(source_path, destination_path)
+
+    form = FormWrapper(str(template))
+    form_data = {
+        "Verwendungszweck": f"Schlusszahlung Dienstreise nach {place}",
+        "Begründung": f"Schlusszahlung Dienstreise {first_last} nach {place} am {date}",
+        "Datum_Feststellung": _iso_date_to_german(TODAY),
+        "Datum_Anordnung": _iso_date_to_german(TODAY),
+    }
+    filled = form.fill(form_data, flatten=False)
+
+    uka_path = folder / f"{TODAY} {travel_short}, UK-A Schlusszahlung.pdf"
+    uka_path.write_bytes(filled.read())

work_helpers/nice_path.py

@@ -1,4 +1,4 @@
-""" create a nice path representation from a copied windows path """
+"""create a nice path representation from a copied windows path"""
 
 import click
 import pyperclip
@@ -7,6 +7,7 @@ REPLACEMENTS = {
     "G:": "Google Drive",
 }
 
+
 def replace(segment, replacements=REPLACEMENTS):
     return replacements.get(segment, segment)
 

work_helpers/password.py

@@ -15,7 +15,7 @@ characters = list(lowers + uppers + decimals)
 @click.command()
 @click.option("--length", default=16, type=int)
 def get_random_password(length=16):
-    """ generates a random password and copies it to the clipboard """
+    """generates a random password and copies it to the clipboard"""
     choice = [random.choice(characters) for i in range(length)]
     groups = [iter(choice)] * 4
     grouped = ("".join(g) for g in itertools.zip_longest(*groups, fillvalue=""))
@@ -23,4 +23,3 @@ def get_random_password(length=16):
     pyperclip.copy(password)
     click.echo("Copied to clipboard:", err=True)
     click.echo(password)
-    

work_helpers/random_int.py

@@ -2,14 +2,14 @@ import click
 import random
 import pyperclip
 
+
 @click.command()
 @click.argument("length", default=100, type=int)
 def generate_random_number_list(length=100):
-    """ generates a new line separated list of integers and copies it to the clipboard """
+    """generates a new line separated list of integers and copies it to the clipboard"""
     numbers = list(range(1, length + 1))
     random.shuffle(numbers)
     integer_list = "\n".join(str(i) for i in numbers)
     pyperclip.copy(integer_list)
     click.echo("Copied to clipboard:", err=True)
     click.echo(integer_list)
-    

work_helpers/sensospot_rename.py

@@ -1,4 +1,4 @@
-""" rename sensospot images """
+"""rename sensospot images"""
 
 import click
 import pathlib
@@ -9,26 +9,28 @@ RENAME_MAP_NAME = "rename_map.txt"
 IMAGE_SUFFIXES = {".tif", ".jpg"}
 
 
-def get_map_file_path(directory:str) -> pathlib.Path:
+def get_map_file_path(directory: str) -> pathlib.Path:
     return pathlib.Path(directory) / RENAME_MAP_NAME
 
 
-def list_images(directory:str) -> list[pathlib.Path]:
+def list_images(directory: str) -> list[pathlib.Path]:
     parent = pathlib.Path(directory)
     non_hidden = (i for i in parent.iterdir() if not i.name.startswith("."))
     return [i for i in non_hidden if i.suffix.lower() in IMAGE_SUFFIXES]
 
 
-def get_image_parts(image_path:pathlib.Path) -> tuple[str, str, str]:
+def get_image_parts(image_path: pathlib.Path) -> tuple[str, str, str]:
     return image_path.stem.rsplit("_", maxsplit=2)
 
 
-def get_unique_parts(images:list[pathlib.Path]) -> list[list[str], list[str], list[str]]: 
+def get_unique_parts(
+    images: list[pathlib.Path],
+) -> list[list[str], list[str], list[str]]:
     parts = [get_image_parts(p) for p in images]
     return [sorted(set(items)) for items in zip(*parts)]
 
 
-def write_rename_map(map_file:pathlib.Path) -> None:
+def write_rename_map(map_file: pathlib.Path) -> None:
     images = list_images(map_file.parent)
     parts = get_unique_parts(images)
     headers = ["stems", "wells", "exposures"]
@@ -43,7 +45,7 @@ def write_rename_map(map_file:pathlib.Path) -> None:
     map_file.write_text("\n".join(lines))
 
 
-def _parse_rename_map(content:str) -> tuple[str, str]:
+def _parse_rename_map(content: str) -> tuple[str, str]:
     lines = [line.strip() for line in content.splitlines()]
     for i, line in enumerate(lines, start=1):
         if not line or line.startswith("#"):
@@ -53,19 +55,23 @@ def _parse_rename_map(content:str) -> tuple[str, str]:
         yield line.split("\t", maxsplit=1)
 
 
-def read_rename_map(map_file:pathlib.Path) -> dict[str, str]:
+def read_rename_map(map_file: pathlib.Path) -> dict[str, str]:
     content = map_file.read_text()
     return {k: v for k, v in _parse_rename_map(content)}
 
 
-def prepare_rename(images:list[pathlib.Path], rename_map:dict[str, str], sep="_") -> list[tuple[pathlib.Path, pathlib.Path]]:
+def prepare_rename(
+    images: list[pathlib.Path], rename_map: dict[str, str], sep="_"
+) -> list[tuple[pathlib.Path, pathlib.Path]]:
     for path in images:
         renamed_parts = [rename_map[p] for p in get_image_parts(path)]
         yield path, path.with_stem(sep.join(renamed_parts))
 
 
 @click.command()
-@click.argument("directory", type=click.Path(exists=True, file_okay=False, dir_okay=True))
+@click.argument(
+    "directory", type=click.Path(exists=True, file_okay=False, dir_okay=True)
+)
 def sensospot_rename(directory):
     images = list_images(directory)
     if not images:
@@ -85,7 +91,9 @@ def sensospot_rename(directory):
         try:
             prepared = list(prepare_rename(images, rename_map))
         except Exception:
-            raise click.UsageError("Could not rename images. Please check the image directory and rename map file.")
+            raise click.UsageError(
+                "Could not rename images. Please check the image directory and rename map file."
+            )
 
         for src, dst in prepared:
             click.echo(f"renaming: {src} -> {dst}")

work_helpers/sg_mbp_build.py

@@ -122,7 +122,9 @@ def _extract_changes_from_log(
 
 def _get_group_from_folder(folder: Pathlike) -> str:
     name = pathlib.Path(folder).name
-    middle = name.removeprefix(GROUP_FOLDER_PREFIX).removesuffix(GROUP_FOLDER_SUFFIX)
+    middle = name.removeprefix(GROUP_FOLDER_PREFIX).removesuffix(
+        GROUP_FOLDER_SUFFIX
+    )
     if middle in GROUPS:
         return middle
     msg = f"Folder '{name}' is not an MBP group folder"
@@ -166,7 +168,9 @@ class Version:
 ## functions for `sg_mbp_build`
 
 
-def copy_workbooks(group: str, destination: Pathlike, build_version: str) -> None:
+def copy_workbooks(
+    group: str, destination: Pathlike, build_version: str
+) -> None:
     source = _get_workbook_folder(group)
     all_xls_files = _files_in_folder(source, ".xlsx")
     mbp_files = (f for f in all_xls_files if f.name.lower().startswith("mbp"))
@@ -198,7 +202,9 @@ def copy_workbook_changelogs(
         shutil.copyfile(log_file, new_path)
 
 
-def copy_changelog(cwd: Pathlike, destination: Pathlike, build_version: str) -> None:
+def copy_changelog(
+    cwd: Pathlike, destination: Pathlike, build_version: str
+) -> None:
     changelog = _get_changelog_path(cwd)
     new_path = pathlib.Path(destination) / f"CHANGELOG {build_version}.txt"
     print(changelog.name, "->", new_path)