ezer-mishpati/legal-ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request 'feat(upload): accept legacy .doc, convert via LibreOffice in container' (#53) from feat/doc-upload-support into main
All checks were successful
Build & Deploy / build-and-deploy (push) Successful in 2m3s
Details

Browse Source
This commit was merged in pull request #53.
This commit is contained in:
chaim
2026-06-03 13:48:26 +00:00
parent db6bad5d1e 476c2fc5d1
commit e25507f9ad
3 changed files with 12 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
Dockerfile
View File

@@ -32,9 +32,10 @@ RUN pip install --no-cache-dir ./mcp-server
FROM python:3.12-slim AS runner FROM python:3.12-slim AS runner
WORKDIR /app 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 \ 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 - \ && curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
&& apt-get install -y --no-install-recommends nodejs \ && apt-get install -y --no-install-recommends nodejs \
&& rm -rf /var/lib/apt/lists/* && rm -rf /var/lib/apt/lists/*

9
mcp-server/src/legal_mcp/services/extractor.py
View File

@@ -262,8 +262,15 @@ def _ocr_with_google_vision(image_bytes: bytes, page_num: int) -> str:
def _extract_doc(path: Path) -> str: def _extract_doc(path: Path) -> str:
"""Extract text from legacy .doc file by converting to .docx via LibreOffice.""" """Extract text from legacy .doc file by converting to .docx via LibreOffice."""
with tempfile.TemporaryDirectory() as tmp_dir: 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( 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, capture_output=True, text=True, timeout=120,
) )
if result.returncode != 0: if result.returncode != 0:

2
web/app.py
View File

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