ODS 完成

This commit is contained in:
Neo
2025-11-30 07:19:05 +08:00
parent b9b050bb5d
commit a6ad343092
81 changed files with 15695 additions and 227180 deletions

View File

@@ -39,10 +39,22 @@ def parse_args():
parser.add_argument("--api-token", "--token", dest="api_token", help="API令牌Bearer Token")
parser.add_argument("--api-timeout", type=int, help="API超时(秒)")
parser.add_argument("--api-page-size", type=int, help="分页大小")
parser.add_argument("--api-retry-max", type=int, help="API重试最大次数")
# 目录参数
parser.add_argument("--export-root", help="导出根目录")
parser.add_argument("--log-root", help="日志根目录")
# 抓取/清洗管线
parser.add_argument("--pipeline-flow", choices=["FULL", "FETCH_ONLY", "INGEST_ONLY"], help="流水线模式")
parser.add_argument("--fetch-root", help="抓取JSON输出根目录")
parser.add_argument("--ingest-source", help="本地清洗入库源目录")
parser.add_argument("--write-pretty-json", action="store_true", help="抓取JSON美化输出")
# 运行窗口
parser.add_argument("--idle-start", help="闲时窗口开始(HH:MM)")
parser.add_argument("--idle-end", help="闲时窗口结束(HH:MM)")
parser.add_argument("--allow-empty-advance", action="store_true", help="允许空结果推进窗口")
return parser.parse_args()
@@ -77,12 +89,32 @@ def build_cli_overrides(args) -> dict:
overrides.setdefault("api", {})["timeout_sec"] = args.api_timeout
if args.api_page_size:
overrides.setdefault("api", {})["page_size"] = args.api_page_size
if args.api_retry_max:
overrides.setdefault("api", {}).setdefault("retries", {})["max_attempts"] = args.api_retry_max
# 目录
if args.export_root:
overrides.setdefault("io", {})["export_root"] = args.export_root
if args.log_root:
overrides.setdefault("io", {})["log_root"] = args.log_root
# 抓取/清洗管线
if args.pipeline_flow:
overrides.setdefault("pipeline", {})["flow"] = args.pipeline_flow.upper()
if args.fetch_root:
overrides.setdefault("pipeline", {})["fetch_root"] = args.fetch_root
if args.ingest_source:
overrides.setdefault("pipeline", {})["ingest_source_dir"] = args.ingest_source
if args.write_pretty_json:
overrides.setdefault("io", {})["write_pretty_json"] = True
# 运行窗口
if args.idle_start:
overrides.setdefault("run", {}).setdefault("idle_window", {})["start"] = args.idle_start
if args.idle_end:
overrides.setdefault("run", {}).setdefault("idle_window", {})["end"] = args.idle_end
if args.allow_empty_advance:
overrides.setdefault("run", {})["allow_empty_result_advance"] = True
# 任务
if args.tasks: