lakehouse/data/_catalog/manifests/3b12ae24-17d4-4325-92bf-f3155982f3bf.json
root 0bd753294b Robust SQL extraction: handles explanations, markdown, prefixes
clean_sql now uses 3 strategies in priority order:
1. Extract from ```sql...``` markdown blocks
2. Find first SELECT/WITH/INSERT statement in text
3. Strip leading "sql" keyword fallback

Tested against 5 real model output patterns:
- Clean SQL ✓
- "sql" prefixed ✓
- Markdown fenced ✓
- Explanation before ```sql block ✓
- Explanation with SELECT buried in text ✓

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-27 20:42:11 -05:00

65 lines
1.5 KiB
JSON

{
"id": "3b12ae24-17d4-4325-92bf-f3155982f3bf",
"name": "users",
"schema_fingerprint": "30c0e31f0963e6f4af02131bbb9ea246fbbd068b849b833565a4b28211fbc90b",
"objects": [
{
"bucket": "data",
"key": "datasets/users.parquet",
"size_bytes": 2012,
"created_at": "2026-03-28T01:38:59.904968123Z"
}
],
"created_at": "2026-03-28T01:38:59.904968680Z",
"updated_at": "2026-03-28T01:38:59.905221340Z",
"description": "",
"owner": "",
"sensitivity": null,
"columns": [
{
"name": "id",
"data_type": "Int32",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "username",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "password_hash",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "role",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
},
{
"name": "created_at",
"data_type": "Utf8",
"sensitivity": null,
"description": "",
"is_pii": false
}
],
"lineage": {
"source_system": "postgresql",
"source_file": "127.0.0.1:5432/knowledge_base.users",
"ingest_job": "pg-import-1774661939904",
"ingest_timestamp": "2026-03-28T01:38:59.904968123Z",
"parent_datasets": []
},
"freshness": null,
"tags": [],
"row_count": 1
}