External/SnapOtter
1
0
Fork 0
mirror of https://github.com/snapotter-hq/SnapOtter.git synced 2026-08-03 07:46:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

feat(tools): 2.0 phase 5 wave 2 - pdf depth (21 tools) (#220)

Browse Source
This commit is contained in:
SnapOtter
2026-06-13 10:18:55 +08:00
parent ae1337901d
commit 2f39e38162
128 changed files with 11381 additions and 778 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docker/Dockerfile
+22 -3
View File
@@ -10,6 +10,17 @@
# Multi-arch (amd64 + arm64) static builds for video/audio processing.
FROM mwader/static-ffmpeg:8.0 AS ffmpeg
# ============================================
# Stage 0b: Static pdfcpu binary (pure Go, no CGO)
# ============================================
# CGO_ENABLED=0 produces a fully static binary; no cross-compiler needed.
FROM --platform=$BUILDPLATFORM golang:1.25-bookworm@sha256:a1ae6b6c564f3e0072d70081036827a2705dbcf6b38aaa6d97f5de97fe9abdb4 AS pdfcpu-builder
ARG TARGETOS=linux
ARG TARGETARCH
RUN CGO_ENABLED=0 GOOS=$TARGETOS GOARCH=$TARGETARCH \
go install github.com/pdfcpu/pdfcpu/cmd/pdfcpu@v0.13.0 \
&& cp "$(find /go/bin -type f -name pdfcpu | head -1)" /tmp/pdfcpu
# ============================================
# Stage 1: Build the frontend (Vite + React)
# ============================================
@@ -201,9 +212,11 @@ RUN for i in 1 2 3; do apt-get -o Acquire::Retries=3 update && break || sleep $(
python3 python3-pip python3-venv python3-dev \
tesseract-ocr tesseract-ocr-eng tesseract-ocr-deu tesseract-ocr-fra tesseract-ocr-spa \
tesseract-ocr-chi-sim tesseract-ocr-jpn tesseract-ocr-kor \
# Document engine: qpdf + LibreOffice headless
# WeasyPrint/calibre/pdfcpu arrive with the tools that need them (Phase 4+)
# Document engine: qpdf + LibreOffice headless + WeasyPrint runtime deps
# calibre deferred (ebook wave)
qpdf \
libpango-1.0-0 libpangocairo-1.0-0 libcairo2 libgdk-pixbuf-2.0-0 \
fonts-dejavu-core \
libreoffice-writer libreoffice-calc \
gcc g++ \
libgl1 libglib2.0-0 libgles2 \
@@ -241,6 +254,9 @@ COPY --from=caire-builder /tmp/caire /usr/local/bin/caire
COPY --from=ffmpeg /ffmpeg /usr/local/bin/ffmpeg
COPY --from=ffmpeg /ffprobe /usr/local/bin/ffprobe
# pdfcpu static binary (PDF layout: crop, n-up, booklet, stamps)
COPY --from=pdfcpu-builder /tmp/pdfcpu /usr/local/bin/pdfcpu
# libheif tools (heif-convert, heif-dec, heif-enc) built from source.
# LD_LIBRARY_PATH ensures our custom 1.21.2 libs take precedence over distro libheif1.
COPY --from=libheif-builder /opt/libheif/bin/ /usr/local/bin/
@@ -259,7 +275,10 @@ RUN --mount=type=cache,target=/root/.cache/pip \
numpy==1.26.4 \
opencv-python-headless==4.10.0.84 \
pikepdf==10.8.0 \
PyMuPDF==1.27.2.3
PyMuPDF==1.27.2.3 \
weasyprint==69.0 \
pdf2docx==0.5.13 \
markdown==3.10.2
# On-demand AI feature installer and manifest
COPY docker/feature-manifest.json /app/docker/feature-manifest.json