Merge pull request 'feat(upload): accept legacy .doc, convert via LibreOffice in container' (#53) from feat/doc-upload-support into main

Dockerfile

@@ -32,9 +32,10 @@ RUN pip install --no-cache-dir ./mcp-server
 FROM python:3.12-slim AS runner
 WORKDIR /app
 
-# Install Node.js 20.x
+# Install Node.js 20.x + LibreOffice Writer (headless .doc→.docx conversion
+# in extractor.py:_extract_doc — needed for legacy Hebrew .doc precedents).
 RUN apt-get update && apt-get install -y --no-install-recommends \
-      curl ca-certificates git \
+      curl ca-certificates git libreoffice-writer-nogui \
  && curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
  && apt-get install -y --no-install-recommends nodejs \
  && rm -rf /var/lib/apt/lists/*

mcp-server/src/legal_mcp/services/extractor.py

@@ -262,8 +262,15 @@ def _ocr_with_google_vision(image_bytes: bytes, page_num: int) -> str:
 def _extract_doc(path: Path) -> str:
     """Extract text from legacy .doc file by converting to .docx via LibreOffice."""
     with tempfile.TemporaryDirectory() as tmp_dir:
+        # Isolate the LibreOffice user profile per call: headless soffice
+        # locks a single shared profile, so concurrent .doc conversions would
+        # otherwise fail with a profile-lock error.
         result = subprocess.run(
-            ["libreoffice", "--headless", "--convert-to", "docx", str(path), "--outdir", tmp_dir],
+            [
+                "libreoffice",
+                f"-env:UserInstallation=file://{tmp_dir}/lo-profile",
+                "--headless", "--convert-to", "docx", str(path), "--outdir", tmp_dir,
+            ],
             capture_output=True, text=True, timeout=120,
         )
         if result.returncode != 0:

web/app.py

@@ -72,7 +72,7 @@ from web.paperclip_client import (
 logger = logging.getLogger(__name__)
 
 UPLOAD_DIR = config.DATA_DIR / "uploads"
-ALLOWED_EXTENSIONS = {".pdf", ".docx", ".rtf", ".txt", ".md"}
+ALLOWED_EXTENSIONS = {".pdf", ".docx", ".doc", ".rtf", ".txt", ".md"}
 MAX_FILE_SIZE = 50 * 1024 * 1024  # 50MB
 
 # Progress tracking — backed by Redis with TTL.