superx-budget-overview/superx_budget/superx.py

""" SuperX Parser """

from datetime import datetime
from collections import namedtuple

from .helpers import get_sheet_of_file, strip_excel_value
from .exceptions import SuperXParserError

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",
        "actual_value",
    ],
)


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


def _get_export_metadata(row):
    """extracts the metadata from the second row of the excel sheet"""
    data = row[0]
    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 SuperXParserError(f"unexpected metadata: '{data}'")
    if metadata["Gruppierung"] != EXPECTED_EXPORT_GROUPING:
        raise SuperXParserError(
            f"unexpected grouping: {metadata['Gruppierung']}"
        )
    date_part, *rest = metadata["Stand"].split(",")
    return SuperXResult(
        metadata["Haushaltsjahr"],
        datetime.strptime(date_part.strip(), "%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 == EXPECTED_DATA_TABLE_HEADER:
            break
    else:
        raise SuperXParserError("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]:
            continue
        data = [strip_excel_value(value) for value in line[:10]]
        yield SuperXData(*data)


def parse_export_data(xls_sheet):
    """parses the exported superx data"""
    rows = xls_sheet.values
    _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)


def parse_exported_file(file_path):
    """parses the budget file"""
    sheet = get_sheet_of_file(file_path, sheet=None)
    return parse_export_data(sheet)