breakpilot-core/pitch-deck/scripts/apply-number-formatting.py

#!/usr/bin/env python3
"""Apply Euro / Count / Percent number formatting to Finanzplan Excel files.

Per-sheet defaults + per-row classification based on column-A labels:

- Sheets with mostly EUR values: Dashboard, Umsatzerlöse, Personalkosten,
  Investitionen, Materialaufwand, Betriebliche Aufwendungen, Liquidität, GuV.
- Kunden sheet: counts by default, with helper rows (rates) as percent.
- Treiber sheet: row-by-row classification by label (no sheet default).
- Skip: Formelübersicht (docs).

Label patterns drive the classification:
  - 'EUR/', 'EUR ', 'Startpreis', 'Preis/Monat' → euro
  - 'rate', 'satz', 'quote', 'inflation', 'erhöhung', 'provision', '% vom',
    'anteil', 'förderquote' → percent
  - 'headcount', 'anzahl', 'mitarbeiter je', 'neukunden/monat', 'neukunden ',
    'bestandskunden', 'churn ' → count
  - 'faktor' → skip (it's a multiplier, leave default)

Inputs sections (Personalkosten rows 5-24, Investitionen 5-29) are skipped
because they contain mixed text/dates/numbers per row that would mis-format
under a single classification.

Usage:
    python3 pitch-deck/scripts/apply-number-formatting.py --dry-run
    python3 pitch-deck/scripts/apply-number-formatting.py
"""

from __future__ import annotations

import argparse
import shutil
import sys
from datetime import datetime
from pathlib import Path

from openpyxl import load_workbook

EXPORTS = Path(__file__).resolve().parent.parent / "exports"

EURO_FORMAT = '#,##0 "€";-#,##0 "€"'
COUNT_FORMAT = '#,##0'
PERCENT_FORMAT = '0.0%'

SHEET_CONFIG: dict[str, dict] = {
    "Dashboard":                {"default": "euro",  "start_row": 4},
    "Umsatzerlöse":             {"default": "euro",  "start_row": 4},
    "Personalkosten":           {"default": "euro",  "start_row": 27},
    "Investitionen":            {"default": "euro",  "start_row": 31},
    "Materialaufwand":          {"default": "euro",  "start_row": 4},
    "Betriebliche Aufwendungen":{"default": "euro",  "start_row": 4},
    "Liquidität":               {"default": "euro",  "start_row": 4},
    "GuV":                      {"default": "euro",  "start_row": 2},
    "Kunden":                   {"default": "count", "start_row": 4},
    "Treiber":                  {"default": None,    "start_row": 1},
}

SKIP_SHEETS = {"Formelübersicht"}

FORMAT_MAP = {"euro": EURO_FORMAT, "count": COUNT_FORMAT, "percent": PERCENT_FORMAT}


def classify_kunden_row(label: str | None) -> str:
    """Kunden sheet is always counts/rates regardless of stray 'EUR' substrings."""
    if not label:
        return "skip"
    s = str(label).lower()
    if "rate" in s or "helper" in s:
        return "percent"
    return "count"


def classify_label(label: str | None, sheet_default: str | None) -> str:
    if not label:
        return "skip"
    s = str(label).lower()

    # 1. Explicit Euro markers
    if any(k in s for k in ("eur/", " eur ", "eur ", " eur", "startpreis", "preis/monat", "preis (")):
        return "euro"

    # 2. Multipliers — skip (preserve existing format)
    if "faktor" in s:
        return "skip"

    # 3. Percent patterns. Use precise tokens to avoid substring traps:
    #    'satz' alone matches 'Umsatz' — use '-satz' / 'steuersatz' instead.
    #    'inflation' as substring matches 'Büromiete (+Inflation)' annotation —
    #    require the label to START with 'inflation' (covers 'Inflation 2027' driver rows).
    if s.startswith("inflation"):
        return "percent"
    # Note: 'provision' alone is too broad — it matches the BA channel-partner
    # provision row whose value is in EUR. Use 'anteil' (matches Treiber's
    # 'Channel-Provision (Anteil vom Umsatz)') instead.
    if any(k in s for k in ("-rate", "rate ", "rate(", "-satz", "steuersatz",
                            "quote", "erhöhung",
                            "% vom", "anteil")):
        return "percent"

    # 4. Count patterns
    if any(k in s for k in ("headcount", "anzahl", "mitarbeiter je",
                            "/monat starter", "/monat professional", "/monat enterprise")):
        return "count"

    # 5. Kunden-sheet customer-tracking rows
    if s.startswith(("neukunden", "churn ", "bestandskunden")):
        return "count"

    if sheet_default:
        return sheet_default
    return "skip"


def cell_is_numeric_or_formula(value) -> bool:
    if value is None:
        return True
    if isinstance(value, (int, float)):
        return True
    if isinstance(value, str):
        return value.startswith("=")
    return False


def format_sheet(ws, sheet_name: str) -> dict[str, int]:
    config = SHEET_CONFIG.get(sheet_name)
    if config is None:
        return {"euro": 0, "count": 0, "percent": 0, "skipped_rows": 0}
    start_row = config["start_row"]
    sheet_default = config["default"]
    stats = {"euro": 0, "count": 0, "percent": 0, "skipped_rows": 0}

    for r in range(start_row, ws.max_row + 1):
        label = ws.cell(row=r, column=1).value
        if sheet_name == "Kunden":
            kind = classify_kunden_row(label)
        else:
            kind = classify_label(label, sheet_default)
        if kind == "skip":
            stats["skipped_rows"] += 1
            continue
        fmt = FORMAT_MAP[kind]

        # Treiber: value lives in col B only (apply to row's col B)
        if sheet_name == "Treiber":
            cell = ws.cell(row=r, column=2)
            if cell_is_numeric_or_formula(cell.value) and cell.value is not None:
                cell.number_format = fmt
                stats[kind] += 1
            continue

        # Other sheets: apply across all value columns
        for c in range(2, ws.max_column + 1):
            cell = ws.cell(row=r, column=c)
            if not cell_is_numeric_or_formula(cell.value):
                continue
            cell.number_format = fmt
            stats[kind] += 1

    return stats


def process_file(path: Path, dry_run: bool) -> dict:
    wb = load_workbook(path)
    sheet_stats: dict[str, dict] = {}
    for sheet_name in wb.sheetnames:
        if sheet_name in SKIP_SHEETS:
            continue
        if sheet_name not in SHEET_CONFIG:
            continue
        sheet_stats[sheet_name] = format_sheet(wb[sheet_name], sheet_name)

    if not dry_run:
        wb.save(path)
    return sheet_stats


def backup(path: Path) -> Path:
    ts = datetime.now().strftime("%Y%m%d-%H%M%S")
    bk = path.with_name(f"{path.stem}.BACKUP-pre-formatting-{ts}{path.suffix}")
    shutil.copy2(path, bk)
    return bk


def main() -> int:
    ap = argparse.ArgumentParser(description=__doc__)
    ap.add_argument("--dry-run", action="store_true")
    ap.add_argument("--only", help="Process only this filename")
    ap.add_argument("--no-backup", action="store_true")
    args = ap.parse_args()

    files = sorted(EXPORTS.glob("Finanzplan-*.xlsx"))
    files = [f for f in files if "BACKUP" not in f.name]
    if args.only:
        files = [f for f in files if f.name == args.only]

    for path in files:
        if not args.dry_run and not args.no_backup:
            bk = backup(path)
            print(f"  ✓ backup: {bk.name}")
        stats = process_file(path, dry_run=args.dry_run)
        print(f"\n  === {path.name} ===")
        for sheet, s in stats.items():
            total = s["euro"] + s["count"] + s["percent"]
            if total > 0 or s["skipped_rows"] > 0:
                parts = []
                if s["euro"]:
                    parts.append(f"€:{s['euro']}")
                if s["count"]:
                    parts.append(f"#:{s['count']}")
                if s["percent"]:
                    parts.append(f"%:{s['percent']}")
                if s["skipped_rows"]:
                    parts.append(f"skip:{s['skipped_rows']}")
                print(f"    {sheet}: {' '.join(parts)}")
    return 0


if __name__ == "__main__":
    sys.exit(main())