superx-budget-overview/superx_budget/__init__.py

""" superx_budget

Creating a budget overview from a SuperX export
"""

__version__ = "0.0.1"

from datetime import datetime
from collections import namedtuple

EXPECTED_HEADLINE = "Verwendungsnachweis und Kassenstand SAP"
EXPECTED_METADATA_KEYS = {"Haushaltsjahr", "Stand", "Gruppierung"}
EXPECTED_EXPORT_GROUPING = "automatisch"
EXPECTED_DATA_TABLE_HEADER = "Kostenstelle"


SuperXResult = namedtuple(
    "SuperXResult", ["account_year", "export_date", "data"]
)
SuperXData = namedtuple(
    "SuperXData",
    [
        "cost_center",
        "fonds",
        "project",
        "kind",
        "budget_year",
        "obligo",
        "expenses",
        "revenue_actual",
        "revenue_target",
        "acutal_value",
    ],
)


class SuperXError(ValueError):
    pass


def _check_export_headline(row):
    """ checks the first line of the excel data if it's what we'd expect """
    headline = row[0].value
    if headline != EXPECTED_HEADLINE:
        raise SuperXError(f"unexpected headline: '{headline}'")


def _get_export_metadata(row):
    """ extracts the metadata from the second row of the excel sheet """
    data = row[0].value
    entries = data.split(";")
    parts = [entry.split(":", 1) for entry in entries]
    metadata = {key.strip(): value.strip() for key, value in parts}
    if EXPECTED_METADATA_KEYS - set(metadata.keys()):
        raise SuperXError(f"unexpected metadata: '{data}'")
    if metadata["Gruppierung"] != EXPECTED_EXPORT_GROUPING:
        raise SuperXError(f"unexpected grouping: {metadata['Gruppierung']}")
    return SuperXResult(
        metadata["Haushaltsjahr"],
        datetime.strptime(metadata["Stand"], "%d.%m.%Y"),
        None,
    )


def _skip_export_data_until_table_header(rows):
    """ skip rows until data table headers """
    for line in rows:
        first_cell = line[0]
        if first_cell.value == EXPECTED_DATA_TABLE_HEADER:
            break
    else:
        raise SuperXError("could not find table header")


def _parse_data_table(rows):
    """ parses non-empty lines of the data table """
    for line in rows:
        if not line[0].value:
            continue
        data = [cell.value for cell in line[:10]]
        yield SuperXData(*data)


def parse_export_data(xls_sheet):
    """ parses the exported superx data """
    rows = xls_sheet.rows
    _check_export_headline(next(rows))
    metadata = _get_export_metadata(next(rows))
    _skip_export_data_until_table_header(rows)
    data = list(_parse_data_table(rows))
    return SuperXResult(metadata.account_year, metadata.export_date, data)