feat(regulatory): 增加法规核查基础服务

review_agent/regulatory_review/services/text_extract.py

@@ -0,0 +1,31 @@
+from __future__ import annotations
+
+import hashlib
+from dataclasses import dataclass
+from pathlib import Path
+
+from .rag_index import extract_text_from_path
+
+
+@dataclass(frozen=True)
+class ExtractedText:
+    path: Path
+    text: str
+    status: str
+    content_hash: str = ""
+    error_message: str = ""
+
+
+SUPPORTED_EXTENSIONS = {".txt", ".md", ".pdf", ".docx", ".pptx", ".xlsx", ".doc"}
+
+
+def extract_text(path: str | Path) -> ExtractedText:
+    file_path = Path(path)
+    if file_path.suffix.lower() not in SUPPORTED_EXTENSIONS:
+        return ExtractedText(path=file_path, text="", status="unsupported")
+    try:
+        text = extract_text_from_path(file_path)
+    except Exception as exc:
+        return ExtractedText(path=file_path, text="", status="failed", error_message=str(exc))
+    content_hash = hashlib.sha256(text.encode("utf-8")).hexdigest() if text else ""
+    return ExtractedText(path=file_path, text=text, status="success", content_hash=content_hash)