Merge pull request #389 from demo-zexuan/main

恢复 EPUB 导出功能并修复图片显示问题

bin/epub

@@ -1,12 +1,20 @@
 #!/usr/bin/env bash
 
+set -e
+
 # Set the directory containing Markdown files
 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_epub() {
 	# convert all EPUB files into a single EPUB book
@@ -24,28 +32,32 @@ convert_to_epub() {
 		--css="$css_file" \
 		--webtex \
 		--wrap=preserve \
-		"${INPUT_DIR}"/SUMMARY.md \
-		"${INPUT_DIR}"/README.md \
-		"${INPUT_DIR}"/preface.md \
-		"${INPUT_DIR}"/part-i.md \
-		"${INPUT_DIR}"/ch1.md \
-		"${INPUT_DIR}"/ch2.md \
-		"${INPUT_DIR}"/ch3.md \
-		"${INPUT_DIR}"/ch4.md \
-		"${INPUT_DIR}"/part-ii.md \
-		"${INPUT_DIR}"/ch5.md \
-		"${INPUT_DIR}"/ch6.md \
-		"${INPUT_DIR}"/ch7.md \
-		"${INPUT_DIR}"/ch8.md \
-		"${INPUT_DIR}"/ch9.md \
-		"${INPUT_DIR}"/part-iii.md \
-		"${INPUT_DIR}"/ch10.md \
-		"${INPUT_DIR}"/ch11.md \
-		"${INPUT_DIR}"/ch12.md \
-		"${INPUT_DIR}"/colophon.md \
-		"${INPUT_DIR}"/glossary.md
+		"${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 "Converted EPUB book created at $OUTPUT_BOOK."
 }
 
 convert_to_epub
+
+# Clean up temporary files
+rm -rf "$TEMP_DIR"

bin/preprocess-epub.py

@@ -0,0 +1,114 @@
+#!/usr/bin/env python3
+"""
+预处理 Markdown 文件，将 Hugo shortcode 转换为 Pandoc 可识别的格式
+
+处理两种 shortcode：
+1. {{< figure src="/fig/xxx.png" caption="xxx" >}} → ![xxx](static/fig/xxx.png)
+2. {{< figure ... >}} (无 src) → 移除（通常用于代码示例）
+"""
+
+import re
+import sys
+import os
+from pathlib import Path
+
+def convert_figure_shortcode(text):
+    """
+    转换 Hugo figure shortcode 为 Markdown 图片语法
+
+    Args:
+        text: Markdown 文本内容
+
+    Returns:
+        转换后的文本
+    """
+
+    # 先处理有 caption 的 figure shortcode
+    # 例如: {{< figure src="/fig/ddia_0302.png" caption="图 3-2. xxx" >}}
+    pattern_with_caption = r'\{\{< figure\s+src="([^"]+)"[^>]*\scaption="([^"]*)"[^>]*>\}\}'
+
+    def replace_with_caption(match):
+        src = match.group(1)
+        caption = match.group(2)
+
+        # 移除开头的斜杠，添加 static 前缀
+        if src.startswith('/'):
+            src = 'static' + src
+
+        # 返回 Markdown 图片语法
+        return f'![{caption}]({src})'
+
+    text = re.sub(pattern_with_caption, replace_with_caption, text)
+
+    # 再处理没有 caption 的 figure shortcode
+    pattern_without_caption = r'\{\{< figure\s+src="([^"]+)"[^>]*>\}\}'
+
+    def replace_without_caption(match):
+        src = match.group(1)
+
+        if src.startswith('/'):
+            src = 'static' + src
+
+        return f'[]({src})'
+
+    text = re.sub(pattern_without_caption, replace_without_caption, text)
+
+    # 移除完全没有 src 属性的 figure shortcode（例如用于代码块的）
+    pattern_no_src = r'\{\{< figure[^>]*>\}\}'
+    text = re.sub(pattern_no_src, '', text)
+
+    return text
+
+def process_file(input_path, output_path):
+    """
+    处理单个 Markdown 文件
+
+    Args:
+        input_path: 输入文件路径
+        output_path: 输出文件路径
+    """
+    with open(input_path, 'r', encoding='utf-8') as f:
+        content = f.read()
+
+    # 转换内容
+    converted_content = convert_figure_shortcode(content)
+
+    # 写入输出文件
+    os.makedirs(os.path.dirname(output_path), exist_ok=True)
+    with open(output_path, 'w', encoding='utf-8') as f:
+        f.write(converted_content)
+
+    print(f"Processed: {input_path} -> {output_path}")
+
+def main():
+    """主函数"""
+    if len(sys.argv) < 2:
+        print("Usage: preprocess.py <input_file> [output_file]")
+        print("   or: preprocess.py <input_dir> <output_dir>")
+        sys.exit(1)
+
+    input_path = sys.argv[1]
+
+    if os.path.isfile(input_path):
+        # 处理单个文件
+        output_path = sys.argv[2] if len(sys.argv) > 2 else input_path
+        process_file(input_path, output_path)
+    elif os.path.isdir(input_path):
+        # 处理目录
+        output_dir = sys.argv[2]
+        input_dir = Path(input_path)
+
+        # 获取所有 .md 文件
+        md_files = list(input_dir.glob('*.md'))
+
+        for md_file in md_files:
+            output_file = os.path.join(output_dir, md_file.name)
+            process_file(str(md_file), output_file)
+
+        print(f"\nTotal processed: {len(md_files)} files")
+    else:
+        print(f"Error: {input_path} is not a valid file or directory")
+        sys.exit(1)
+
+if __name__ == '__main__':
+    main()

js/epub.css

@@ -0,0 +1,221 @@
+/* This defines styles and classes used in the book */
+@page {
+  margin: 10px;
+}
+html, body, div, span, applet, object, iframe, h1, h2, h3, h4, h5, h6, p,
+blockquote, pre, a, abbr, acronym, address, big, cite, code, del, dfn, em, img,
+ins, kbd, q, s, samp, small, strike, strong, sub, sup, tt, var, b, u, i, center,
+fieldset, form, label, legend, table, caption, tbody, tfoot, thead, tr, th, td,
+article, aside, canvas, details, embed, figure, figcaption, footer, header,
+hgroup, menu, nav, output, ruby, section, summary, time, mark, audio, video, ol,
+ul, li, dl, dt, dd {
+  margin: 0;
+  padding: 0;
+  border: 0;
+  font-size: 100%;
+  vertical-align: baseline;
+}
+html {
+  line-height: 1.2;
+  font-family: Georgia, serif;
+  color: #1a1a1a;
+}
+p {
+  text-indent: 0;
+  margin: 1em 0;
+  widows: 2;
+  orphans: 2;
+}
+a, a:visited {
+  color: #1a1a1a;
+}
+img {
+  max-width: 100%;
+}
+sup {
+  vertical-align: super;
+  font-size: smaller;
+}
+sub {
+  vertical-align: sub;
+  font-size: smaller;
+}
+h1 {
+  margin: 3em 0 0 0;
+  font-size: 2em;
+  page-break-before: always;
+  line-height: 150%;
+}
+h2 {
+  margin: 1.5em 0 0 0;
+  font-size: 1.5em;
+  line-height: 135%;
+}
+h3 {
+  margin: 1.3em 0 0 0;
+  font-size: 1.3em;
+}
+h4 {
+  margin: 1.2em 0 0 0;
+  font-size: 1.2em;
+}
+h5 {
+  margin: 1.1em 0 0 0;
+  font-size: 1.1em;
+}
+h6 {
+  font-size: 1em;
+}
+h1, h2, h3, h4, h5, h6 {
+  text-indent: 0;
+  text-align: left;
+  font-weight: bold;
+  page-break-after: avoid;
+  page-break-inside: avoid;
+}
+
+ol, ul {
+  margin: 1em 0 0 1.7em;
+}
+li > ol, li > ul {
+  margin-top: 0;
+}
+blockquote {
+  margin: 1em 0 1em 1.7em;
+}
+code {
+  font-family: Menlo, Monaco, 'Lucida Console', Consolas, monospace;
+  font-size: 85%;
+  margin: 0;
+  hyphens: manual;
+}
+/*pre {*/
+/*  margin: 1em 0;*/
+/*  overflow: auto;*/
+/*}*/
+pre code {
+  white-space: pre-wrap;
+  word-wrap: break-word;
+  background-color: #f5f5f5;
+  padding: 1em;
+}
+.sourceCode {
+  background-color: transparent;
+  overflow: visible;
+}
+hr {
+  background-color: #1a1a1a;
+  border: none;
+  height: 1px;
+  margin: 1em 0;
+}
+table {
+  margin: 1em 0;
+  border-collapse: collapse;
+  width: 100%;
+  overflow-x: auto;
+  display: block;
+}
+table caption {
+  margin-bottom: 0.75em;
+}
+tbody {
+  margin-top: 0.5em;
+  border-top: 1px solid #1a1a1a;
+  border-bottom: 1px solid #1a1a1a;
+}
+th, td {
+  padding: 0.25em 0.5em 0.25em 0.5em;
+}
+th {
+  border-top: 1px solid #1a1a1a;
+}
+header {
+  margin-bottom: 4em;
+  text-align: center;
+}
+#TOC li {
+  list-style: none;
+}
+#TOC ul {
+  padding-left: 1.3em;
+}
+#TOC > ul {
+  padding-left: 0;
+}
+#TOC a:not(:hover) {
+  text-decoration: none;
+}
+code {
+  white-space: pre-wrap;
+}
+span.smallcaps {
+  font-variant: small-caps;
+}
+
+/* This is the most compatible CSS, but it only allows two columns: */
+div.column {
+  display: inline-block;
+  vertical-align: top;
+  width: 50%;
+}
+/* If you can rely on CSS3 support, use this instead: */
+/* div.columns {
+  display: flex;
+  gap: min(4vw, 1.5em);
+}
+div.column {
+  flex: auto;
+  overflow-x: auto;
+} */
+
+div.hanging-indent {
+  margin-left: 1.5em;
+  text-indent: -1.5em;
+}
+ul.task-list {
+  list-style: none;
+}
+ul.task-list li input[type="checkbox"] {
+  width: 0.8em;
+  margin: 0 0.8em 0.2em -1.6em;
+  vertical-align: middle;
+}
+.display.math {
+  display: block;
+  text-align: center;
+  margin: 0.5rem auto;
+}
+
+/* For title, author, and date on the cover page */
+h1.title { }
+p.author { }
+p.date { }
+
+nav#toc ol, nav#landmarks ol {
+  padding: 0;
+  margin-left: 1em;
+}
+nav#toc ol li, nav#landmarks ol li {
+  list-style-type: none;
+  margin: 0;
+  padding: 0;
+}
+a.footnote-ref {
+  vertical-align: super;
+}
+em, em em em, em em em em em {
+  font-style: italic;
+}
+em em, em em em em {
+  font-style: normal;
+}
+q {
+  quotes: """''"'";
+}
+@media screen { /* Workaround for iBooks issue; see #6242 */
+  .sourceCode {
+    overflow: visible !important;
+    white-space: pre-wrap !important;
+  }
+}

metadata.yaml

@@ -0,0 +1,6 @@
+---
+title: 设计数据密集型应用
+author: Martin Kleppmann
+rights:  Creative Commons Non-Commercial Share Alike 3.0
+language: zh
+cover-image: ./static/title.jpg