feat(regulatory-info-package): 完善目录页码与组成成分填充

review_agent/regulatory_info_package/services/field_extract.py

@@ -13,6 +13,11 @@ from review_agent.regulatory_info_package.schemas import InstructionExtractResul
 
 FIELD_PATTERNS = {
     "product_name": ("产品名称", r"产品名称[:：\s]*([^\n\r]+)"),
+    "applicant_name": ("申请人名称", r"(?:申请人名称|注册人/售后服务单位名称|注册人名称|售后服务单位名称|生产企业名称)[:：\s]*([^\n\r]+)"),
+    "manufacturer_name": ("生产企业名称", r"生产企业名称[:：\s]*([^\n\r]+)"),
+    "applicant_address": ("申请人住所", r"(?:申请人住所|注册人住所|生产企业住所)[:：\s]*([^\n\r]+)"),
+    "applicant_contact": ("申请人联系方式", r"(?:联系方式|联系电话|电话)[:：\s]*([^\n\r]+)"),
+    "production_address": ("生产地址", r"生产地址[:：\s]*([^\n\r]+)"),
     "storage_condition": ("储存条件", r"(?:储存条件|贮存条件|保存条件)[:：\s]*([^\n\r]+)"),
     "intended_use": ("预期用途", r"预期用途[:：\s]*([^\n\r]+)"),
     "package_specification": ("包装规格", r"(?:包装规格|规格)[:：\s]*([^\n\r]+)"),
@@ -47,6 +52,24 @@ def extract_fields_by_rules(instruction: InstructionExtractResult) -> dict[str,
                     "confidence": 0.75,
                     "source": "rule",
                 }
+    component_table = _best_component_table(instruction.component_tables)
+    if component_table:
+        results["component_table"] = {
+            "label": "主要组成成分",
+            "value": json.dumps(component_table, ensure_ascii=False),
+            "evidence": "说明书【主要组成成分】表格",
+            "confidence": 0.86,
+            "source": "rule",
+        }
+    component_notes = _component_notes(instruction.sections)
+    if component_notes:
+        results["component_notes"] = {
+            "label": "主要组成成分备注",
+            "value": component_notes,
+            "evidence": "说明书【主要组成成分】段落",
+            "confidence": 0.8,
+            "source": "rule",
+        }
     return results
 
 
@@ -133,3 +156,16 @@ def _parse_json_object(raw: str) -> dict:
     if start == -1 or end == -1:
         return {}
     return json.loads(text[start : end + 1])
+
+
+def _best_component_table(component_tables: list[dict]) -> dict:
+    if not component_tables:
+        return {}
+    return max(component_tables, key=lambda table: len(table.get("rows") or []))
+
+
+def _component_notes(sections: dict[str, str]) -> str:
+    for key, value in sections.items():
+        if "主要组成" in key:
+            return value.strip()
+    return ""