refine fonts and language support
This commit is contained in:
Your Name
parent
6933f5cc75
commit
e792dfedf1
10 changed files with 1365 additions and 65 deletions
99
Dockerfile
99
Dockerfile
|
|
@ -1,26 +1,28 @@
|
|||
# ==============================================================================
|
||||
# ConvertX-CN 完整版 Dockerfile
|
||||
# 內建所有轉換依賴：LibreOffice / TexLive Full / OCR / CJK 字型
|
||||
# 支援 linux/amd64, linux/arm64 multi-arch build
|
||||
# ConvertX-CN 精簡版 Dockerfile
|
||||
# 優化版本：移除 texlive-full，精簡字型與語言支援
|
||||
# 目標：在 GitHub Actions 中穩定建構（解決 no space left on device）
|
||||
# 支援語言：中文（繁/簡）、日文、韓文、英文、德文、法文
|
||||
# ==============================================================================
|
||||
|
||||
FROM debian:trixie-slim AS base
|
||||
LABEL org.opencontainers.image.source="https://github.com/pi-docket/ConvertX-CN"
|
||||
LABEL org.opencontainers.image.description="ConvertX-CN - 完整版檔案轉換服務，內建所有依賴"
|
||||
LABEL org.opencontainers.image.description="ConvertX-CN - 精簡版檔案轉換服務"
|
||||
WORKDIR /app
|
||||
|
||||
# install bun
|
||||
RUN apt-get update && apt-get install -y \
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
curl \
|
||||
unzip \
|
||||
ca-certificates \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# if architecture is arm64, use the arm64 version of bun
|
||||
RUN ARCH=$(uname -m) && \
|
||||
if [ "$ARCH" = "aarch64" ]; then \
|
||||
curl -fsSL -o bun-linux-aarch64.zip https://github.com/oven-sh/bun/releases/download/bun-v1.2.2/bun-linux-aarch64.zip; \
|
||||
curl -fsSL -o bun-linux-aarch64.zip https://github.com/oven-sh/bun/releases/download/bun-v1.2.2/bun-linux-aarch64.zip; \
|
||||
else \
|
||||
curl -fsSL -o bun-linux-x64-baseline.zip https://github.com/oven-sh/bun/releases/download/bun-v1.2.2/bun-linux-x64-baseline.zip; \
|
||||
curl -fsSL -o bun-linux-x64-baseline.zip https://github.com/oven-sh/bun/releases/download/bun-v1.2.2/bun-linux-x64-baseline.zip; \
|
||||
fi
|
||||
|
||||
RUN unzip -j bun-linux-*.zip -d /usr/local/bin && \
|
||||
|
|
@ -51,8 +53,9 @@ RUN bun run build
|
|||
FROM base AS release
|
||||
|
||||
# ==============================================================================
|
||||
# 完整依賴安裝（單一 RUN 層，優化 cache）
|
||||
# 包含：轉換工具 + TexLive Full + LibreOffice + OCR + CJK 字型
|
||||
# 精簡依賴安裝（單一 RUN 層，優化 cache 與空間）
|
||||
# ❌ 已移除：texlive-full, fonts-noto-extra, 多餘語言包
|
||||
# ✅ 保留：核心轉換工具 + 最小 TexLive + 必要字型
|
||||
# ==============================================================================
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
# === 基礎轉換工具 ===
|
||||
|
|
@ -77,13 +80,34 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
|
|||
resvg \
|
||||
# === LibreOffice (headless) ===
|
||||
libreoffice \
|
||||
# === TexLive 完整版（支援所有 LaTeX 需求）===
|
||||
texlive-full \
|
||||
# === TexLive 最小集合（取代 texlive-full）===
|
||||
# texlive-base: LaTeX 核心
|
||||
# texlive-latex-base: 基本 LaTeX 類別
|
||||
# texlive-latex-recommended: 常用套件（geometry, hyperref 等）
|
||||
# texlive-fonts-recommended: 基本字型（Computer Modern 等）
|
||||
# texlive-xetex: XeTeX 引擎（Unicode/CJK 支援必需）
|
||||
# texlive-lang-cjk: 中日韓 LaTeX 支援
|
||||
# texlive-lang-german: 德文 LaTeX 支援
|
||||
# texlive-lang-french: 法文 LaTeX 支援
|
||||
texlive-base \
|
||||
texlive-latex-base \
|
||||
texlive-latex-recommended \
|
||||
texlive-fonts-recommended \
|
||||
texlive-xetex \
|
||||
texlive-lang-cjk \
|
||||
texlive-lang-german \
|
||||
texlive-lang-french \
|
||||
latexmk \
|
||||
lmodern \
|
||||
# === Pandoc 文件轉換 ===
|
||||
pandoc \
|
||||
# === OCR 支援（Tesseract + 多語言包）===
|
||||
# === OCR 支援（僅限指定語言）===
|
||||
# eng: 英文
|
||||
# chi_tra/chi_sim: 繁/簡中文
|
||||
# jpn: 日文
|
||||
# kor: 韓文
|
||||
# deu: 德文
|
||||
# fra: 法文
|
||||
tesseract-ocr \
|
||||
tesseract-ocr-eng \
|
||||
tesseract-ocr-chi-tra \
|
||||
|
|
@ -91,41 +115,58 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
|
|||
tesseract-ocr-jpn \
|
||||
tesseract-ocr-kor \
|
||||
tesseract-ocr-deu \
|
||||
# === CJK 字型（中日韓完整支援）===
|
||||
tesseract-ocr-fra \
|
||||
# === 字型（精簡版）===
|
||||
# fonts-noto-cjk: 中日韓統一字型（必需）
|
||||
# fonts-noto-core: Noto Sans/Serif Latin（歐語基礎）
|
||||
# fonts-noto-color-emoji: Emoji 支援（僅此一套）
|
||||
# fonts-liberation: Liberation 字型（Arial/Times 替代）
|
||||
# ❌ 已移除：fonts-noto-extra（包含過多語言）
|
||||
# ❌ 已移除：fonts-liberation2（重複）
|
||||
fonts-noto-cjk \
|
||||
fonts-noto-core \
|
||||
fonts-noto-extra \
|
||||
fonts-noto-color-emoji \
|
||||
# === Liberation 字型（微軟字型開源替代）===
|
||||
fonts-liberation \
|
||||
fonts-liberation2 \
|
||||
# === Python 依賴 ===
|
||||
# === Python 依賴（精簡）===
|
||||
python3 \
|
||||
python3-pip \
|
||||
python3-numpy \
|
||||
python3-tinycss2 \
|
||||
pipx \
|
||||
# === 系統工具 ===
|
||||
ca-certificates \
|
||||
locales \
|
||||
# === 清理 ===
|
||||
&& pipx install "markitdown[all]" \
|
||||
# 清理 apt cache
|
||||
&& apt-get clean \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
&& rm -rf /var/lib/apt/lists/* \
|
||||
# 清理 pip cache
|
||||
&& rm -rf /root/.cache/pip \
|
||||
# 清理 TexLive 文件（節省空間）
|
||||
&& rm -rf /usr/share/doc/texlive* \
|
||||
&& rm -rf /usr/share/texlive/texmf-dist/doc \
|
||||
# 清理其他文件
|
||||
&& rm -rf /usr/share/doc/* \
|
||||
&& rm -rf /usr/share/man/* \
|
||||
&& rm -rf /usr/share/info/*
|
||||
|
||||
# Add pipx bin directory to PATH
|
||||
ENV PATH="/root/.local/bin:${PATH}"
|
||||
|
||||
# ==============================================================================
|
||||
# 設定 locale（避免中文 PDF 亂碼）
|
||||
# 設定 locale（僅限指定語言）
|
||||
# ==============================================================================
|
||||
RUN sed -i 's/# zh_TW.UTF-8 UTF-8/zh_TW.UTF-8 UTF-8/' /etc/locale.gen && \
|
||||
sed -i 's/# zh_CN.UTF-8 UTF-8/zh_CN.UTF-8 UTF-8/' /etc/locale.gen && \
|
||||
sed -i 's/# ja_JP.UTF-8 UTF-8/ja_JP.UTF-8 UTF-8/' /etc/locale.gen && \
|
||||
sed -i 's/# ko_KR.UTF-8 UTF-8/ko_KR.UTF-8 UTF-8/' /etc/locale.gen && \
|
||||
locale-gen
|
||||
RUN sed -i 's/# en_US.UTF-8 UTF-8/en_US.UTF-8 UTF-8/' /etc/locale.gen && \
|
||||
sed -i 's/# zh_TW.UTF-8 UTF-8/zh_TW.UTF-8 UTF-8/' /etc/locale.gen && \
|
||||
sed -i 's/# zh_CN.UTF-8 UTF-8/zh_CN.UTF-8 UTF-8/' /etc/locale.gen && \
|
||||
sed -i 's/# ja_JP.UTF-8 UTF-8/ja_JP.UTF-8 UTF-8/' /etc/locale.gen && \
|
||||
sed -i 's/# ko_KR.UTF-8 UTF-8/ko_KR.UTF-8 UTF-8/' /etc/locale.gen && \
|
||||
sed -i 's/# de_DE.UTF-8 UTF-8/de_DE.UTF-8 UTF-8/' /etc/locale.gen && \
|
||||
sed -i 's/# fr_FR.UTF-8 UTF-8/fr_FR.UTF-8 UTF-8/' /etc/locale.gen && \
|
||||
locale-gen
|
||||
|
||||
ENV LANG=zh_TW.UTF-8
|
||||
ENV LC_ALL=zh_TW.UTF-8
|
||||
ENV LANG=en_US.UTF-8
|
||||
ENV LC_ALL=en_US.UTF-8
|
||||
|
||||
# ==============================================================================
|
||||
# 安裝自訂字型（標楷體等台灣常用字型）
|
||||
|
|
@ -139,9 +180,9 @@ RUN fc-cache -fv
|
|||
# ==============================================================================
|
||||
RUN ARCH=$(uname -m) && \
|
||||
if [ "$ARCH" = "aarch64" ]; then \
|
||||
VTRACER_ASSET="vtracer-aarch64-unknown-linux-musl.tar.gz"; \
|
||||
VTRACER_ASSET="vtracer-aarch64-unknown-linux-musl.tar.gz"; \
|
||||
else \
|
||||
VTRACER_ASSET="vtracer-x86_64-unknown-linux-musl.tar.gz"; \
|
||||
VTRACER_ASSET="vtracer-x86_64-unknown-linux-musl.tar.gz"; \
|
||||
fi && \
|
||||
curl -L -o /tmp/vtracer.tar.gz "https://github.com/visioncortex/vtracer/releases/download/0.6.4/${VTRACER_ASSET}" && \
|
||||
tar -xzf /tmp/vtracer.tar.gz -C /tmp/ && \
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue