added scripts for travel forms

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())