fix(application-form-fill): 优先路由填表提示并支持rar预览

review_agent/file_summary/services/attachment_reader.py

@@ -2,16 +2,18 @@ from __future__ import annotations
 
 import csv
 import logging
+from tempfile import TemporaryDirectory
 from dataclasses import asdict, dataclass, field
 from pathlib import Path
 
 from django.conf import settings
 
 from review_agent.models import FileAttachment
+from review_agent.file_summary.services.archive import ARCHIVE_EXTENSIONS, extract_archive
 
 
 TEXT_EXTENSIONS = {"txt", "md", "csv", "json", "log"}
-SUPPORTED_EXTENSIONS = TEXT_EXTENSIONS | {"pdf", "docx", "xlsx", "pptx"}
+SUPPORTED_EXTENSIONS = TEXT_EXTENSIONS | {"pdf", "docx", "xlsx", "pptx"} | ARCHIVE_EXTENSIONS
 MAX_PREVIEW_CHARS = 3000
 MAX_ROWS_PER_SHEET = 20
 
@@ -72,6 +74,8 @@ def read_attachment_details(attachment: FileAttachment) -> AttachmentReadResult:
             sections = _read_pptx(file_path)
         elif file_type == "csv":
             sections = _read_csv(file_path)
+        elif file_type in ARCHIVE_EXTENSIONS:
+            sections = _read_archive(file_path)
         else:
             sections = _read_text(file_path)
     except Exception as exc:
@@ -208,6 +212,44 @@ def _read_pptx(path: Path) -> list[dict[str, object]]:
     return sections
 
 
+def _read_archive(path: Path) -> list[dict[str, object]]:
+    sections: list[dict[str, object]] = []
+    with TemporaryDirectory(prefix="attachment-reader-") as temp_dir:
+        extracted = extract_archive(path, Path(temp_dir))
+        if not extracted:
+            return [{"type": "archive", "name": path.name, "text": "压缩包未解出任何可读取文件。"}]
+        for item in extracted:
+            file_type = item.suffix.lower().lstrip(".")
+            if file_type not in SUPPORTED_EXTENSIONS or file_type in ARCHIVE_EXTENSIONS:
+                sections.append(
+                    {
+                        "type": "file",
+                        "name": item.name,
+                        "text": f"暂不支持预览压缩包内的 .{file_type or 'unknown'} 文件。",
+                    }
+                )
+                continue
+            for section in _read_supported_file(item, file_type):
+                section = dict(section)
+                section["name"] = f"{item.name} / {section.get('name', item.name)}"
+                sections.append(section)
+    return sections
+
+
+def _read_supported_file(path: Path, file_type: str) -> list[dict[str, object]]:
+    if file_type == "pdf":
+        return _read_pdf(path)
+    if file_type == "docx":
+        return _read_docx(path)
+    if file_type == "xlsx":
+        return _read_xlsx(path)
+    if file_type == "pptx":
+        return _read_pptx(path)
+    if file_type == "csv":
+        return _read_csv(path)
+    return _read_text(path)
+
+
 def _build_preview(sections: list[dict[str, object]]) -> str:
     parts: list[str] = []
     for section in sections: