feat: 补齐DOCX精确页数识别与待复核策略

apps/documents/services.py

@@ -316,6 +316,28 @@ def _estimate_page_count(text: str) -> int:
     return max(1, line_count)
 
 
+def _resolve_page_count(document: UploadedDocument, text: str) -> tuple[int, str]:
+    """
+    按文件类型返回页数与可信度。
+
+    - PDF：优先统计真实页数
+    - DOCX：优先读取 Word 页数元数据
+    - 其他类型：退回估算
+    """
+    extension = document.file_type.lower()
+    if extension == "pdf":
+        page_count = _extract_pdf_page_count(Path(document.file.path))
+        if page_count > 0:
+            return page_count, "exact"
+        return _estimate_page_count(text), "estimated"
+    if extension == "docx":
+        page_count = _extract_docx_page_count(Path(document.file.path))
+        if page_count > 0:
+            return page_count, "exact"
+        return _estimate_page_count(text), "estimated"
+    return _estimate_page_count(text), "estimated"
+
+
 def _expand_uploaded_files(uploaded_files: list) -> list[dict]:
     expanded_files = []
     warnings = []
@@ -368,13 +390,18 @@ def _ingest_files_into_batch(
             relative_path=relative_path,
         )
         text = extract_text(document)
-        page_count = _estimate_page_count(text)
+        page_count, page_count_confidence = _resolve_page_count(document, text)
         document.page_count = page_count
-        document.page_count_confidence = "estimated"
+        document.page_count_confidence = page_count_confidence
         document.document_role = _detect_document_role(document.relative_path)
         document.chapter_code = _detect_chapter_code(document.relative_path, text)
         document.chapter_match_status = "matched" if document.chapter_code else "unknown"
-        document.needs_manual_review = not bool(document.chapter_code)
+        document.needs_manual_review = (
+            not bool(document.chapter_code)
+            or (document.file_type.lower() == "docx" and page_count_confidence != "exact")
+        )
+        if document.file_type.lower() == "docx" and page_count_confidence != "exact":
+            warnings.append(f"DOCX 页数无法精确统计：{document.relative_path}")
         document.save(
             update_fields=[
                 "page_count",
@@ -622,6 +649,17 @@ def _extract_pdf_text(path: Path) -> str:
         return _read_binary_text_fallback(path)
 
 
+def _extract_pdf_page_count(path: Path) -> int:
+    """优先使用 pypdf 统计 PDF 真实页数。"""
+    try:
+        import pypdf
+
+        reader = pypdf.PdfReader(str(path))
+        return len(reader.pages)
+    except Exception:
+        return 0
+
+
 def _extract_docx_text(path: Path) -> str:
     """提取 Word XML 中的可见文字内容，不追求保留样式。"""
     try:
@@ -635,6 +673,26 @@ def _extract_docx_text(path: Path) -> str:
         return _read_binary_text_fallback(path)
 
 
+def _extract_docx_page_count(path: Path) -> int:
+    """
+    从 Word 扩展属性中提取真实页数。
+
+    常见 docx 会在 `docProps/app.xml` 中写入 `<Pages>`。
+    若缺失该元数据，则由上层回退为估算并进入待复核。
+    """
+    try:
+        with ZipFile(path) as archive:
+            app_xml = archive.read("docProps/app.xml")
+        root = ET.fromstring(app_xml)
+        namespace = {"ep": "http://schemas.openxmlformats.org/officeDocument/2006/extended-properties"}
+        pages_node = root.find(".//ep:Pages", namespace)
+        if pages_node is None or not (pages_node.text or "").strip():
+            return 0
+        return int((pages_node.text or "").strip())
+    except (BadZipFile, KeyError, ET.ParseError, ValueError):
+        return 0
+
+
 def _read_binary_text_fallback(path: Path) -> str:
     """
     当结构化抽取失败时，退回到“尽可能保留纯文本”的保底方案。