Update wehago matching logic and exclude reports

2026-07-03 09:07:04 +09:00
parent a09190ecd3
commit da073ad6ef
62 changed files with 36940 additions and 1554 deletions
@@ -0,0 +1,152 @@
+from __future__ import annotations
+
+import sqlite3
+from datetime import date, datetime
+from pathlib import Path
+from typing import Any
+
+from openpyxl import load_workbook
+
+ROOT = Path(__file__).resolve().parents[1]
+DB_PATH = ROOT / "data.db"
+SOURCE_XLSX = ROOT / "reports" / "wehago_account_fixes" / "2025_137_20260617_092619" / "137_주.종단기채권.xlsx"
+YEAR = 2025
+ACCOUNT_CODE = "137"
+ACCOUNT_NAME = "주.종단기채권"
+
+
+def clean(value: Any) -> str:
+    return "" if value is None else str(value).strip()
+
+
+def parse_amount(value: Any) -> float:
+    if value is None or value == "":
+        return 0.0
+    if isinstance(value, (int, float)):
+        return float(value)
+    text = clean(value).replace(",", "")
+    try:
+        return float(text)
+    except ValueError:
+        return 0.0
+
+
+def parse_ledger_date(value: Any) -> str | None:
+    if value is None or clean(value) == "":
+        return None
+    if isinstance(value, datetime):
+        return value.date().isoformat()
+    if isinstance(value, date):
+        return value.isoformat()
+    text = clean(value).replace(".", "-").replace("/", "-")
+    parts = [part for part in text.split("-") if part]
+    if len(parts) == 2:
+        month, day = parts
+        return f"{YEAR}-{int(month):02d}-{int(day):02d}"
+    if len(parts) == 3:
+        year, month, day = parts
+        return f"{int(year):04d}-{int(month):02d}-{int(day):02d}"
+    return text
+
+
+def compare_voucher_no(ledger_date: str | None, voucher_no: str) -> str:
+    if not ledger_date or not voucher_no:
+        return ""
+    return f"{ledger_date.replace('-', '')}-{voucher_no}"
+
+
+def normalize_text(value: Any) -> str:
+    return " ".join(clean(value).split())
+
+
+def main() -> int:
+    wb = load_workbook(SOURCE_XLSX, read_only=True, data_only=True)
+    try:
+        ws = wb.worksheets[0]
+        source_rows = list(ws.iter_rows(min_row=2, values_only=True))
+    finally:
+        wb.close()
+
+    conn = sqlite3.connect(DB_PATH, timeout=300)
+    try:
+        conn.execute("PRAGMA busy_timeout = 300000")
+        source_id_row = conn.execute(
+            """
+            SELECT source_file_id
+            FROM wehago_ledger_rows
+            WHERE fiscal_year = ? AND account_code = ?
+            GROUP BY source_file_id
+            ORDER BY COUNT(*) DESC
+            LIMIT 1
+            """,
+            (YEAR, ACCOUNT_CODE),
+        ).fetchone()
+        source_file_id = int(source_id_row[0]) if source_id_row else 0
+        if not source_file_id:
+            source_file_id = int(
+                conn.execute(
+                    "SELECT source_file_id FROM wehago_ledger_rows WHERE fiscal_year = ? LIMIT 1",
+                    (YEAR,),
+                ).fetchone()[0]
+            )
+
+        with conn:
+            deleted = conn.execute(
+                "DELETE FROM wehago_ledger_rows WHERE fiscal_year = ? AND account_code = ?",
+                (YEAR, ACCOUNT_CODE),
+            ).rowcount
+            inserted = 0
+            for row_number, values in enumerate(source_rows, start=2):
+                if not any(clean(item) for item in values):
+                    continue
+                ledger_date = parse_ledger_date(values[0] if len(values) > 0 else None)
+                description = clean(values[1] if len(values) > 1 else "")
+                vendor_name = clean(values[2] if len(values) > 2 else "")
+                debit = parse_amount(values[3] if len(values) > 3 else 0)
+                credit = parse_amount(values[4] if len(values) > 4 else 0)
+                balance = parse_amount(values[5] if len(values) > 5 else 0)
+                voucher_no = clean(values[6] if len(values) > 6 else "")
+                account_code = clean(values[7] if len(values) > 7 else ACCOUNT_CODE) or ACCOUNT_CODE
+                account_name = clean(values[8] if len(values) > 8 else ACCOUNT_NAME) or ACCOUNT_NAME
+                conn.execute(
+                    """
+                    INSERT INTO wehago_ledger_rows (
+                        source_file_id, sheet_name, row_number, ledger_date, description,
+                        vendor_name, debit, credit, balance, voucher_no, account_code,
+                        account_name, compare_voucher_no, compare_amount, compare_side,
+                        compare_vendor, compare_desc, fiscal_year
+                    ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+                    """,
+                    (
+                        source_file_id,
+                        ws.title,
+                        row_number,
+                        ledger_date,
+                        description,
+                        vendor_name,
+                        debit,
+                        credit,
+                        balance,
+                        voucher_no,
+                        account_code,
+                        account_name,
+                        compare_voucher_no(ledger_date, voucher_no),
+                        debit if debit else credit,
+                        "debit" if debit else ("credit" if credit else ""),
+                        normalize_text(vendor_name),
+                        normalize_text(description),
+                        YEAR,
+                    ),
+                )
+                inserted += 1
+        print(f"source={SOURCE_XLSX}")
+        print(f"source_file_id={source_file_id}")
+        print(f"deleted={deleted}")
+        print(f"inserted={inserted}")
+    finally:
+        conn.close()
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())