panli 1f64c87d0e Initial commit: 日语词表清洗工具(任务化架构)
- 任务化清洗流程:Task/TaskManager + BatchProcessor 三方法
- 数据目录规范化:data/{db,sources,backup}
- CLI 入口移进包,注册 jclean 命令
- 工作流测试驱动(tests/test_cleaner_workflow.py)
- 40 测试通过
2026-08-19 15:04:18 +08:00

43 lines
1.2 KiB
JSON

{
"task_id": "legacy_batch1",
"name": "遗留批次1(tobe处理中)",
"task_dir": "tasks\\legacy_batch1",
"config": {
"source": "data/backup/xinbiaori_tobe.backup.txt",
"start_line": 1,
"count": 3971,
"auto_done": "tasks\\legacy_batch1\\auto_done.txt",
"skip": "tasks\\legacy_batch1\\skip.txt",
"review_pinyin": "tasks\\legacy_batch1\\review_pinyin.txt",
"review_split": "tasks\\legacy_batch1\\review_split.txt",
"review_verb": "tasks\\legacy_batch1\\review_verb.txt",
"review_special": "tasks\\legacy_batch1\\review_special.txt",
"main": "data/db/vocabulary.txt",
"skipped": "data/db/skipped.txt"
},
"state": {
"status": "reviewing",
"bucket_counts": {
"auto_done": 102,
"skip": 0,
"review_pinyin": 236,
"review_split": 93,
"review_verb": 1,
"review_special": 11
},
"input_valid": 3971,
"validation_ok": false,
"created_at": "2026-08-19T14:03:30.346722",
"updated_at": "2026-08-19T14:03:51.949812",
"history": [
{
"time": "2026-08-19T14:03:30.346722",
"event": "created"
},
{
"time": "2026-08-19T14:03:51.944754",
"event": "migrated existing single-batch data"
}
]
}
}