支持自动生成一整本PDF 电子书

.github/workflows/build-pdf.yaml

@@ -0,0 +1,143 @@
+name: Build and Release PDF
+
+on:
+  push:
+    tags:
+      - 'v*'
+      - 'release*'
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+jobs:
+  build-pdf:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install dependencies
+        run: |
+          # Install pandoc
+          wget -q https://github.com/jgm/pandoc/releases/download/3.1.11/pandoc-3.1.11-1-amd64.deb
+          sudo dpkg -i pandoc-3.1.11-1-amd64.deb
+          rm pandoc-3.1.11-1-amd64.deb
+
+          # Install TeX Live with XeLaTeX and Chinese support
+          sudo apt-get update
+          sudo apt-get install -y \
+            texlive-xetex \
+            texlive-lang-chinese \
+            texlive-fonts-recommended \
+            texlive-fonts-extra \
+            fonts-noto-cjk \
+            fonts-noto-cjk-extra
+
+          # Verify installations
+          pandoc --version
+          xelatex --version
+
+      - name: Build PDF
+        run: |
+          chmod +x bin/pdf bin/preprocess-epub.py
+          mkdir -p output output/temp
+
+          # Preprocess Markdown files
+          python3 bin/preprocess-epub.py content/zh output/temp
+
+          # Generate PDF with CI-specific fonts (Noto CJK)
+          pandoc -o output/ddia.pdf \
+            --metadata-file=metadata.yaml \
+            -H bin/header-ci.tex \
+            --toc \
+            --toc-depth=2 \
+            --top-level-division=chapter \
+            --file-scope=true \
+            --pdf-engine=xelatex \
+            -V geometry:margin=1in \
+            -V linestretch=1.5 \
+            output/temp/_index.md \
+            output/temp/preface.md \
+            output/temp/part-i.md \
+            output/temp/ch1.md \
+            output/temp/ch2.md \
+            output/temp/ch3.md \
+            output/temp/ch4.md \
+            output/temp/part-ii.md \
+            output/temp/ch5.md \
+            output/temp/ch6.md \
+            output/temp/ch7.md \
+            output/temp/ch8.md \
+            output/temp/ch9.md \
+            output/temp/part-iii.md \
+            output/temp/ch10.md \
+            output/temp/ch11.md \
+            output/temp/ch12.md \
+            output/temp/ch13.md \
+            output/temp/ch14.md \
+            output/temp/colophon.md \
+            output/temp/glossary.md
+
+          rm -rf output/temp
+
+          if [ ! -f "output/ddia.pdf" ]; then
+            echo "Error: PDF file was not created"
+            exit 1
+          fi
+
+          ls -lh output/ddia.pdf
+          file output/ddia.pdf
+
+      - name: Upload PDF artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: ddia-pdf
+          path: output/ddia.pdf
+          retention-days: 30
+
+      - name: Create/Update Release
+        if: startsWith(github.ref, 'refs/tags/')
+        uses: softprops/action-gh-release@v1
+        with:
+          files: output/ddia.pdf
+          name: ${{ github.ref_name }}
+          body: |
+            ## 《设计数据密集型应用》PDF 版本
+
+            此版本为自动生成的 PDF 电子书。
+
+            ### 文件信息
+            - 文件名: `ddia.pdf`
+            - 生成时间: ${{ github.event.head_commit.timestamp }}
+            - 标签: ${{ github.ref_name }}
+
+            ### 依赖工具
+            - Pandoc 3.1.11
+            - XeLaTeX (TeX Live)
+            - 中文字体: Noto CJK
+
+            ### 本地生成
+            如需本地生成 PDF，请确保安装以下依赖：
+            ```bash
+            # macOS
+            brew install pandoc
+            brew install --cask mactex
+
+            # Ubuntu/Debian
+            sudo apt install pandoc texlive-xetex texlive-lang-chinese
+
+            # 生成 PDF
+            make pdf
+            ```
+          draft: false
+          prerelease: false
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -10,4 +10,7 @@ public/
 CLAUDE.md
 content/cn/
 zh.md
-en.md
+en.md
+.venv
+AGENTS.md
+

Makefile

@@ -17,4 +17,7 @@ translate:
 epub:
 	bin/epub
 
-.PHONY: default doc translate
+pdf:
+	bin/pdf
+
+.PHONY: default doc translate epub pdf

README.md

@@ -12,6 +12,19 @@
 
 **阅读**：访问 [https://ddia.vonng.com](https://ddia.vonng.com) 阅读本书在线版本，或使用 [hugo](https://gohugo.io/documentation/) / [hextra](https://imfing.github.io/hextra/zh-cn/) 主题自行构建。
 
+**下载**：可以使用以下命令生成 PDF 电子书：
+
+```bash
+# 安装依赖
+brew install pandoc
+brew install poppler  # 用于 pdftotext
+
+# 生成 PDF
+make pdf
+```
+
+生成的 PDF 文件位于 `output/ddia.pdf`
+
 > [!NOTE] 
 > [**DDIA 第二版**](https://ddia.vonng.com) 正在翻译中（翻译至至第十章），欢迎阅览并提出您的宝贵意见！[点击此处阅览第一版](https://ddia.vonng.com/v1)。
 

bin/header-ci.tex

@@ -0,0 +1,31 @@
+% Chinese support with xeCJK
+\usepackage{xeCJK}
+\setCJKmainfont{Noto Serif CJK SC}
+\setCJKsansfont{Noto Sans CJK SC}
+
+% Enable Chinese line breaking
+\XeTeXlinebreaklocale "zh"
+
+% Paragraph settings
+\usepackage{parskip}
+\setlength{\parindent}{2em}
+\usepackage{ragged2e}
+
+% Chinese punctuation style
+\punctstyle{quanjiao}
+
+% Cover page
+\AtBeginDocument{%
+  \thispagestyle{empty}
+  \begin{center}
+    \vspace*{0.4\textheight}
+    {\Huge\bfseries 设计数据密集型应用}
+    \vspace{1cm}
+    {\LARGE 第二版}
+    \vspace{2cm}
+    {\Large Martin Kleppmann}
+    \vspace{0.5cm}
+    {\large 冯若航 译}
+  \end{center}
+  \clearpage
+}

bin/header.tex

@@ -0,0 +1,31 @@
+% Chinese support with xeCJK
+\usepackage{xeCJK}
+\setCJKmainfont{PingFang SC}
+\setCJKsansfont{Heiti SC}
+
+% Enable Chinese line breaking
+\XeTeXlinebreaklocale "zh"
+
+% Paragraph settings
+\usepackage{parskip}
+\setlength{\parindent}{2em}
+\usepackage{ragged2e}
+
+% Chinese punctuation style
+\punctstyle{quanjiao}
+
+% Cover page
+\AtBeginDocument{%
+  \thispagestyle{empty}
+  \begin{center}
+    \vspace*{0.4\textheight}
+    {\Huge\bfseries 设计数据密集型应用}
+    \vspace{1cm}
+    {\LARGE 第二版}
+    \vspace{2cm}
+    {\Large Martin Kleppmann}
+    \vspace{0.5cm}
+    {\large 冯若航 译}
+  \end{center}
+  \clearpage
+}

bin/pdf

@@ -0,0 +1,108 @@
+#!/usr/bin/env bash
+
+set -e
+
+# Check for required dependencies
+check_dependencies() {
+	local missing_deps=()
+
+	if ! command -v pandoc &> /dev/null; then
+		missing_deps+=("pandoc")
+	fi
+
+	if ! command -v xelatex &> /dev/null; then
+		# Try lualatex as fallback
+		if ! command -v lualatex &> /dev/null; then
+			missing_deps+=("xelatex or lualatex (LaTeX engine)")
+		fi
+	fi
+
+	if [ ${#missing_deps[@]} -ne 0 ]; then
+		echo "Error: Missing required dependencies:"
+		for dep in "${missing_deps[@]}"; do
+			echo "  - $dep"
+		done
+		echo ""
+		echo "Installation:"
+		echo "  macOS: brew install pandoc"
+		echo "  macOS: brew install --cask mactex"
+		echo ""
+		echo "  Linux: apt install pandoc texlive-xetex"
+		exit 1
+	fi
+}
+
+check_dependencies
+
+# Detect available PDF engine
+if command -v xelatex &> /dev/null; then
+	PDF_ENGINE="xelatex"
+elif command -v lualatex &> /dev/null; then
+	PDF_ENGINE="lualatex"
+else
+	echo "Error: No suitable PDF engine found"
+	exit 1
+fi
+
+SCRIPT_DIR=$(dirname "$0")
+INPUT_DIR=$(cd "$(dirname "$SCRIPT_DIR")" && pwd)
+OUTPUT_DIR="$INPUT_DIR/output"
+TEMP_DIR="$OUTPUT_DIR/temp"
+
+# Create output directory if it doesn't exist
+mkdir -p "$OUTPUT_DIR"
+mkdir -p "$TEMP_DIR"
+
+# Preprocess Markdown files to convert Hugo shortcodes
+echo "Preprocessing Markdown files..."
+python3 "${SCRIPT_DIR}/preprocess-epub.py" "${INPUT_DIR}/content/zh" "$TEMP_DIR"
+
+convert_to_pdf() {
+	# Convert all Markdown files into a single PDF book
+	OUTPUT_BOOK="$OUTPUT_DIR/ddia.pdf"
+	rm -f "$OUTPUT_BOOK"
+	echo "Converting all Markdown files into $OUTPUT_BOOK..."
+
+	local meta_file=${INPUT_DIR}/metadata.yaml
+	local header_file=${SCRIPT_DIR}/header.tex
+
+	# Use xelatex for Chinese support with custom header
+	pandoc -o "$OUTPUT_BOOK" \
+		--metadata-file="$meta_file" \
+		-H "$header_file" \
+		--toc \
+		--toc-depth=2 \
+		--top-level-division=chapter \
+		--file-scope=true \
+		--pdf-engine="$PDF_ENGINE" \
+		-V geometry:margin=1in \
+		-V linestretch=1.5 \
+		"${TEMP_DIR}"/_index.md \
+		"${TEMP_DIR}"/preface.md \
+		"${TEMP_DIR}"/part-i.md \
+		"${TEMP_DIR}"/ch1.md \
+		"${TEMP_DIR}"/ch2.md \
+		"${TEMP_DIR}"/ch3.md \
+		"${TEMP_DIR}"/ch4.md \
+		"${TEMP_DIR}"/part-ii.md \
+		"${TEMP_DIR}"/ch5.md \
+		"${TEMP_DIR}"/ch6.md \
+		"${TEMP_DIR}"/ch7.md \
+		"${TEMP_DIR}"/ch8.md \
+		"${TEMP_DIR}"/ch9.md \
+		"${TEMP_DIR}"/part-iii.md \
+		"${TEMP_DIR}"/ch10.md \
+		"${TEMP_DIR}"/ch11.md \
+		"${TEMP_DIR}"/ch12.md \
+		"${TEMP_DIR}"/ch13.md \
+		"${TEMP_DIR}"/ch14.md \
+		"${TEMP_DIR}"/colophon.md \
+		"${TEMP_DIR}"/glossary.md
+
+	echo "PDF book created at $OUTPUT_BOOK."
+}
+
+convert_to_pdf
+
+# Clean up temporary files
+rm -rf "$TEMP_DIR"