feat:新增投顾agent和nl2sqlagent

nl2sql/metadata.py

@@ -0,0 +1,113 @@
+"""将 MySQL information_schema 结果标准化为 NL2SQL 元数据 chunk。"""
+from __future__ import annotations
+
+import hashlib
+import json
+from typing import Any
+
+
+def _value(row: dict[str, Any], name: str, default: Any = None) -> Any:
+    if name in row:
+        return row[name]
+    upper = name.upper()
+    lower = name.lower()
+    return row.get(upper, row.get(lower, default))
+
+
+def normalize_table_row(row: dict[str, Any]) -> dict[str, Any] | None:
+    table_name = str(_value(row, "table_name", "") or "").strip()
+    table_type = str(_value(row, "table_type", "BASE TABLE") or "").upper()
+    if not table_name or table_type != "BASE TABLE":
+        return None
+    return {
+        "table_name": table_name,
+        "table_comment": str(_value(row, "table_comment", "") or "").strip(),
+        "is_valid": True,
+    }
+
+
+def normalize_column_row(row: dict[str, Any]) -> dict[str, Any]:
+    nullable = str(_value(row, "is_nullable", "NO") or "NO").upper() == "YES"
+    return {
+        "table_name": str(_value(row, "table_name", "") or "").strip(),
+        "field_name": str(
+            _value(row, "column_name", _value(row, "field_name", "")) or ""
+        ).strip(),
+        "column_comment": str(_value(row, "column_comment", "") or "").strip(),
+        "data_type": str(_value(row, "data_type", "") or "").strip(),
+        "is_nullable": nullable,
+        "ordinal_position": int(_value(row, "ordinal_position", 0) or 0),
+    }
+
+
+def _hash_text(text: str) -> str:
+    return hashlib.sha256(text.encode("utf-8")).hexdigest()
+
+
+def _chunk_id(chunk_type: str, table_name: str, field_name: str = "") -> str:
+    raw = f"{chunk_type}:{table_name}:{field_name}"
+    return hashlib.sha256(raw.encode("utf-8")).hexdigest()[:64]
+
+
+def build_metadata_chunks(
+    tables: list[dict[str, Any]], columns: list[dict[str, Any]]
+) -> list[dict[str, Any]]:
+    valid_tables = sorted(
+        (table for table in (normalize_table_row(row) for row in tables) if table),
+        key=lambda item: item["table_name"],
+    )
+    valid_table_names = {table["table_name"] for table in valid_tables}
+    normalized_columns = sorted(
+        (
+            column
+            for column in (normalize_column_row(row) for row in columns)
+            if column["table_name"] in valid_table_names and column["field_name"]
+        ),
+        key=lambda item: (item["table_name"], item["ordinal_position"], item["field_name"]),
+    )
+
+    chunks: list[dict[str, Any]] = []
+    for table in valid_tables:
+        text = f"表名：{table['table_name']}\n表说明：{table['table_comment']}"
+        chunks.append(
+            {
+                "id": _chunk_id("table_meta", table["table_name"]),
+                "chunk_type": "table_meta",
+                "table_name": table["table_name"],
+                "field_name": "",
+                "text": text,
+                "content_hash": _hash_text(text),
+                "is_valid": table["is_valid"],
+                "is_deprecated": False,
+            }
+        )
+
+    for column in normalized_columns:
+        text = (
+            f"表名：{column['table_name']}\n"
+            f"字段名：{column['field_name']}\n"
+            f"字段说明：{column['column_comment']}\n"
+            f"字段类型：{column['data_type']}\n"
+            f"允许为空：{'是' if column['is_nullable'] else '否'}"
+        )
+        chunks.append(
+            {
+                "id": _chunk_id(
+                    "field_meta", column["table_name"], column["field_name"]
+                ),
+                "chunk_type": "field_meta",
+                "table_name": column["table_name"],
+                "field_name": column["field_name"],
+                "text": text,
+                "content_hash": _hash_text(text),
+                "is_valid": True,
+                "is_deprecated": False,
+            }
+        )
+    return chunks
+
+
+def metadata_signature(chunk: dict[str, Any]) -> str:
+    """返回用于比较 chunk 内容的稳定签名字符串。"""
+    payload = {key: chunk[key] for key in ("chunk_type", "table_name", "field_name", "text")}
+    return json.dumps(payload, ensure_ascii=False, sort_keys=True, separators=(",", ":"))