chore: update gitignore; feat: 新增customer_agent业务模块与api路由

rag/document_parser.py

@@ -0,0 +1,51 @@
+"""Knowledge document parsing for supported upload formats."""
+from __future__ import annotations
+
+from pathlib import Path
+from xml.etree import ElementTree
+from zipfile import BadZipFile, ZipFile
+
+from pypdf import PdfReader
+
+SUPPORTED_EXTENSIONS = {".txt", ".md", ".docx", ".pdf"}
+_WORD_NS = "{http://schemas.openxmlformats.org/wordprocessingml/2006/main}"
+
+
+def parse_document(path: str | Path) -> str:
+    """Return document text for a supported knowledge-base upload."""
+    document_path = Path(path)
+    suffix = document_path.suffix.lower()
+    if suffix not in SUPPORTED_EXTENSIONS:
+        raise ValueError(f"Unsupported document type: {suffix or '<none>'}")
+    if not document_path.is_file():
+        raise FileNotFoundError(document_path)
+
+    if suffix in {".txt", ".md"}:
+        return document_path.read_text(encoding="utf-8-sig")
+    if suffix == ".pdf":
+        return _parse_pdf(document_path)
+    return _parse_docx(document_path)
+
+
+def _parse_docx(path: Path) -> str:
+    try:
+        with ZipFile(path) as archive:
+            xml = archive.read("word/document.xml")
+        root = ElementTree.fromstring(xml)
+    except (BadZipFile, KeyError, ElementTree.ParseError) as exc:
+        raise ValueError(f"Invalid DOCX document: {path}") from exc
+
+    paragraphs = []
+    for paragraph in root.iter(f"{_WORD_NS}p"):
+        text = "".join(node.text or "" for node in paragraph.iter(f"{_WORD_NS}t"))
+        if text:
+            paragraphs.append(text)
+    return "\n".join(paragraphs)
+
+
+def _parse_pdf(path: Path) -> str:
+    try:
+        reader = PdfReader(str(path))
+        return "\n".join(page.extract_text() or "" for page in reader.pages).strip()
+    except Exception as exc:  # pypdf raises format-specific exceptions
+        raise ValueError(f"Invalid PDF document: {path}") from exc