fix: improve OCR indexing and evidence review

backend/wisegrade/llm.py

@@ -1,6 +1,7 @@
 import base64
 import json
 import time
+import unicodedata
 from pathlib import Path
 from typing import Any
 
@@ -105,8 +106,38 @@ def validate_score(result: ScoreResult, criterion: dict, chunks: list[dict]):
     if result.criterion_id != criterion["criterion_id"] or result.max_score != criterion["max_score"]:
         raise ModelError("模型评分项或满分与规则版本不一致")
     by_id = {chunk["chunk_id"]: chunk for chunk in chunks}
+
+    def locate_quote(text: str, quote: str):
+        def comparable(value: str):
+            return "".join(char for original in value for char in unicodedata.normalize("NFKC", original)
+                           if not char.isspace() and not unicodedata.category(char).startswith("P"))
+
+        if quote in text:
+            return quote
+        needle = comparable(quote)
+        if len(needle) < 4:
+            return None
+        positions = []
+        normalized = []
+        for index, original in enumerate(text):
+            for char in unicodedata.normalize("NFKC", original):
+                if not char.isspace() and not unicodedata.category(char).startswith("P"):
+                    normalized.append(char)
+                    positions.append(index)
+        start = "".join(normalized).find(needle)
+        if start < 0:
+            return None
+        return text[positions[start]:positions[start + len(needle) - 1] + 1]
+
     for evidence in result.evidence:
         chunk = by_id.get(evidence.chunk_id)
-        if not chunk or evidence.page != chunk["page"] or evidence.quote not in chunk["text"]:
+        quote = locate_quote(chunk["text"], evidence.quote) if chunk else None
+        if quote is None and len(evidence.quote) >= 8:
+            matches = [(candidate, located) for candidate in chunks
+                       if (located := locate_quote(candidate["text"], evidence.quote)) is not None]
+            if len(matches) == 1:
+                chunk, quote = matches[0]
+        if quote is None:
             raise ModelError("模型证据未能匹配检索原文")
+        evidence.chunk_id, evidence.page, evidence.quote = chunk["chunk_id"], chunk["page"], quote
     return result