feat: поддержка .doc через LibreOffice headless

- extractor.py: добавлена doc_to_markdown() — .doc → .docx (soffice) → docx_to_markdown() - Dockerfile: apt install libreoffice-writer - ARCHITECTURE.md: обновлён статус .doc - bump: 0.0.16 → 0.0.17
2026-07-14 07:21:39 +04:00
parent 444ef4b732
commit 00d54dbfb6
4 changed files with 56 additions and 5 deletions
@@ -1,5 +1,8 @@
 FROM python:3.12-slim
 WORKDIR /app
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libreoffice-writer \
+    && rm -rf /var/lib/apt/lists/*
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 COPY site /app/site