#!/usr/bin/env python3 """ Export the SPU ledger into review CSV files and ready import JSON. """ from __future__ import annotations import argparse import csv import json import sqlite3 from pathlib import Path STATUS_EXPORTS = { "ready": "ready", "needs_review": "needs-review", "skipped": "skipped", "duplicate": "duplicate", "delete_candidate": "delete-candidate", } def json_dumps(value) -> str: return json.dumps(value, ensure_ascii=False, indent=2) def latest_run_id(conn: sqlite3.Connection) -> str: row = conn.execute( "SELECT run_id FROM spu_ledger_runs ORDER BY started_at DESC LIMIT 1" ).fetchone() if not row: raise SystemExit("台账数据库里没有扫描 run") return str(row["run_id"]) def read_items(conn: sqlite3.Connection, run_id: str) -> list[sqlite3.Row]: return conn.execute( """ SELECT * FROM spu_ledger_items WHERE run_id = ? ORDER BY source_root_name, relative_workspace_path, spu """, (run_id,), ).fetchall() def read_files(conn: sqlite3.Connection, item_id: int, asset_group: str) -> list[sqlite3.Row]: return conn.execute( """ SELECT * FROM spu_ledger_files WHERE item_id = ? AND asset_group = ? ORDER BY sort_order, relative_file_path """, (item_id, asset_group), ).fetchall() def csv_headers() -> list[str]: return [ "status（状态）", "spu（SPU）", "store（店铺）", "product_category（产品品类）", "author（作者）", "task_detail_source_type（出图方式）", "version_label（版本/工作区）", "main_count（主图数量）", "sku_count（SKU图数量）", "detail_count（详情图数量）", "source_count（PS源文件数量）", "status_reason（判断原因）", "spu_source（SPU来源）", "store_evidence（店铺证据）", "author_evidence（作者证据）", "task_detail_source_type_evidence（出图方式证据）", "source_batch（来源批次）", "source_root（来源根目录）", "workspace_path（工作区完整路径）", "relative_workspace_path（工作区相对路径）", "fingerprint（台账指纹）", ] def item_to_csv_row(item: sqlite3.Row) -> dict[str, object]: return { "status（状态）": item["status"], "spu（SPU）": item["spu"], "store（店铺）": item["store"], "product_category（产品品类）": item["product_category"], "author（作者）": item["author"], "task_detail_source_type（出图方式）": item["task_detail_source_type"], "version_label（版本/工作区）": item["version_label"], "main_count（主图数量）": item["main_count"], "sku_count（SKU图数量）": item["sku_count"], "detail_count（详情图数量）": item["detail_count"], "source_count（PS源文件数量）": item["source_count"], "status_reason（判断原因）": item["status_reason"], "spu_source（SPU来源）": item["spu_source"], "store_evidence（店铺证据）": item["store_evidence"], "author_evidence（作者证据）": item["author_evidence"], "task_detail_source_type_evidence（出图方式证据）": item["task_detail_source_type_evidence"], "source_batch（来源批次）": item["source_batch"], "source_root（来源根目录）": item["source_root"], "workspace_path（工作区完整路径）": item["workspace_path"], "relative_workspace_path（工作区相对路径）": item["relative_workspace_path"], "fingerprint（台账指纹）": item["fingerprint"], } def write_csv(path: Path, rows: list[dict[str, object]], headers: list[str]) -> None: path.parent.mkdir(parents=True, exist_ok=True) with path.open("w", encoding="utf-8-sig", newline="") as handle: writer = csv.DictWriter(handle, fieldnames=headers) writer.writeheader() for row in rows: writer.writerow(row) def to_image_input(file_row: sqlite3.Row) -> dict[str, object]: payload = { "localFilePath": file_row["file_path"], "fileName": file_row["file_name"], "fileSize": int(file_row["file_size"] or 0), "sortOrder": int(file_row["sort_order"] or 0), } if file_row["asset_group"] == "sku": payload["skuCode"] = file_row["sku_code"] or "" payload["barcodes"] = [] return payload def to_source_input(file_row: sqlite3.Row) -> dict[str, object]: return { "localFilePath": file_row["file_path"], "fileName": file_row["file_name"], "fileSize": int(file_row["file_size"] or 0), } def build_import_record(conn: sqlite3.Connection, item: sqlite3.Row) -> dict[str, object]: main = [to_image_input(row) for row in read_files(conn, item["id"], "main")] sku = [to_image_input(row) for row in read_files(conn, item["id"], "sku")] detail = [to_image_input(row) for row in read_files(conn, item["id"], "detail")] sources = [to_source_input(row) for row in read_files(conn, item["id"], "source")] return { "fingerprint": item["fingerprint"], "spu": item["spu"], "sourcePath": item["workspace_path"], "relativeSourcePath": item["relative_workspace_path"], "guessedStore": item["store"], "productCategoryName": item["product_category"], "authorName": item["author"] or "历史导入", "taskDetailSourceType": item["task_detail_source_type"] or "渲染", "storeConfidence": 1, "storeCandidates": [item["store"]] if item["store"] else [], "mainCount": item["main_count"], "skuCount": item["sku_count"], "detailCount": item["detail_count"], "sourceCount": item["source_count"], "status": item["status"], "skipReason": None if item["status"] == "ready" else item["status_reason"], "mainImages": main, "skuImages": sku, "detailImages": detail, "psdSources": sources, "seenInYya": False, "ledger": { "runId": item["run_id"], "sourceBatch": item["source_batch"], "spuSource": item["spu_source"], "spuEvidence": json.loads(item["spu_evidence_json"] or "[]"), "pathFlags": json.loads(item["path_flags_json"] or "{}"), }, } def write_batch_csvs(output_dir: Path, prefix: str, items: list[sqlite3.Row], batch_size: int) -> None: if batch_size <= 0: return headers = csv_headers() pending = [item for item in items if item["status"] in ("ready", "needs_review")] for start in range(0, len(pending), batch_size): batch_no = start // batch_size + 1 batch = pending[start : start + batch_size] rows = [item_to_csv_row(item) for item in batch] write_csv(output_dir / f"{prefix}-batch-{batch_no:03d}.csv", rows, headers) def parse_args() -> argparse.Namespace: parser = argparse.ArgumentParser(description="Export SPU ledger review files.") parser.add_argument("--db-path", required=True) parser.add_argument("--output-dir", default=str(Path.cwd() / "output")) parser.add_argument("--prefix", default="spu-ledger") parser.add_argument("--run-id", default="") parser.add_argument("--batch-size", type=int, default=20) return parser.parse_args() def main() -> int: args = parse_args() db_path = Path(args.db_path) output_dir = Path(args.output_dir) output_dir.mkdir(parents=True, exist_ok=True) conn = sqlite3.connect(str(db_path)) conn.row_factory = sqlite3.Row run_id = args.run_id or latest_run_id(conn) items = read_items(conn, run_id) headers = csv_headers() status_counts: dict[str, int] = {} store_counts: dict[str, int] = {} category_counts: dict[str, int] = {} for item in items: status_counts[item["status"]] = status_counts.get(item["status"], 0) + 1 store_counts[item["store"]] = store_counts.get(item["store"], 0) + 1 category = item["product_category"] or "未识别" category_counts[category] = category_counts.get(category, 0) + 1 for status, suffix in STATUS_EXPORTS.items(): rows = [item_to_csv_row(item) for item in items if item["status"] == status] write_csv(output_dir / f"{args.prefix}-{suffix}.csv", rows, headers) write_csv(output_dir / f"{args.prefix}-all.csv", [item_to_csv_row(item) for item in items], headers) write_batch_csvs(output_dir, args.prefix, items, args.batch_size) ready_records = [build_import_record(conn, item) for item in items if item["status"] == "ready"] ready_json_path = output_dir / f"{args.prefix}-ready-import-records.json" ready_json_path.write_text(json_dumps(ready_records), encoding="utf-8") summary = { "runId": run_id, "dbPath": str(db_path), "total": len(items), "status": status_counts, "store": store_counts, "productCategory": category_counts, "readyImportRecords": str(ready_json_path), } summary_path = output_dir / f"{args.prefix}-summary.json" summary_path.write_text(json_dumps(summary), encoding="utf-8") conn.close() print("SPU 台账导出完成") print(f"- run_id: {run_id}") print(f"- total: {len(items)}") print(f"- ready_import_records: {ready_json_path}") print(f"- summary: {summary_path}") return 0 if __name__ == "__main__": raise SystemExit(main())