From aa589406b90c1bcc7cbccfcf252ac4a690564c60 Mon Sep 17 00:00:00 2001 From: Baohua Yang Date: Sun, 15 Feb 2026 09:09:02 -0800 Subject: [PATCH] release v1.5.3: fix CI image paths and update config --- .github/CODEOWNERS | 38 +- .github/workflows/ci.yaml | 21 +- CHANGELOG.md | 6 + README.md | 2 +- combine.py | 1001 +++++++++++++++++++++++++++++++++++++ package.json | 4 +- 6 files changed, 1036 insertions(+), 36 deletions(-) create mode 100644 combine.py diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS index bf8cf1d..5dd82ba 100644 --- a/.github/CODEOWNERS +++ b/.github/CODEOWNERS @@ -2,28 +2,22 @@ /.github/* @khs1994 /.travis/* @khs1994 /.vuepress/* @khs1994 -/advanced_network/* @yeasy @khs1994 -/appendix/* @yeasy @khs1994 -/archive/* @khs1994 -/basic_concept/* @yeasy @khs1994 -/buildx/* @khs1994 -/cases/* @yeasy @khs1994 -/cloud/* @khs1994 -/compose/* @yeasy @khs1994 -/container/* @yeasy @khs1994 -/coreos/* @khs1994 -/data_management/* @khs1994 -/etcd/* @khs1994 -/IDE/* @khs1994 -/image/* @yeasy @khs1994 -/install/* @khs1994 -/introduction/* @yeasy @khs1994 -/kubernetes/* @yeasy @khs1994 -/network/* @yeasy @khs1994 -/opensource/* @khs1994 -/repository/* @khs1994 -/security/* @yeasy @khs1994 -/underly/* @yeasy @khs1994 +/01_introduction/* @yeasy @khs1994 +/02_basic_concept/* @yeasy @khs1994 +/03_install/* @khs1994 +/04_image/* @yeasy @khs1994 +/05_container/* @yeasy @khs1994 +/06_repository/* @khs1994 +/07_dockerfile/* @yeasy @khs1994 +/08_data_network/* @yeasy @khs1994 +/09_buildx/* @khs1994 +/10_compose/* @yeasy @khs1994 +/11_ops/* @yeasy @khs1994 +/12_orchestration/* @yeasy @khs1994 +/13_ecosystem/* @khs1994 +/14_implementation/* @yeasy @khs1994 +/15_cases/* @yeasy @khs1994 +/16_appendix/* @yeasy @khs1994 /.drone.yml @khs1994 /.editorconfig/ @khs1994 /.gitattributes @khs1994 diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml index 52fc980..09f043e 100644 --- a/.github/workflows/ci.yaml +++ b/.github/workflows/ci.yaml @@ -81,17 +81,16 @@ jobs: echo "vuepress.mirror.docker-practice.com" > .vuepress/dist/CNAME cp -r _images .vuepress/dist - cp -r appendix/_images .vuepress/dist/appendix - cp -r cases/ci/drone/_images .vuepress/dist/cases/ci/drone - cp -r cases/os/_images .vuepress/dist/cases/os - cp -r cloud/_images .vuepress/dist/cloud - cp -r data_management/_images .vuepress/dist/data_management - cp -r etcd/_images .vuepress/dist/etcd - cp -r image/_images .vuepress/dist/image - cp -r install/_images .vuepress/dist/install - cp -r introduction/_images .vuepress/dist/introduction - cp -r kubernetes/_images .vuepress/dist/kubernetes - cp -r underly/_images .vuepress/dist/underly + cp -r 16_appendix/_images .vuepress/dist/appendix + cp -r 15_cases/ci/drone/_images .vuepress/dist/cases/ci/drone + cp -r 15_cases/os/_images .vuepress/dist/cases/os + cp -r 13_ecosystem/cloud/_images .vuepress/dist/cloud + cp -r 08_data_network/data/_images .vuepress/dist/data_management + cp -r 12_orchestration/etcd/_images .vuepress/dist/etcd + cp -r 04_image/_images .vuepress/dist/image + cp -r 03_install/_images .vuepress/dist/install + cp -r 12_orchestration/kubernetes/_images .vuepress/dist/kubernetes + cp -r 14_implementation/_images .vuepress/dist/underly echo "include: [_images]" > .vuepress/dist/_config.yml - name: Upload Vuepress dist diff --git a/CHANGELOG.md b/CHANGELOG.md index 2ab6ba8..6e3119d 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,11 @@ # 修订记录 + +* 1.5.3 2026-02-15 + * 修复 CI 流程中的图片引用路径错误 + * 修复 CODEOWNERS 文件路径匹配问题 + * 更新项目配置版本号 + * 1.5.0 2026-02-05 * 全面重构章节目录结构 (01-15) * 支持 Docker Engine v30.x diff --git a/README.md b/README.md index 584a582..ea326ac 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ [![](https://img.shields.io/github/stars/yeasy/docker_practice.svg?style=social&label=Stars)](https://github.com/yeasy/docker_practice) [![](https://img.shields.io/github/release/yeasy/docker_practice/all.svg)](https://github.com/yeasy/docker_practice/releases) [![](https://img.shields.io/badge/Based-Docker%20CE%20v30.x-blue.svg)](https://github.com/docker/docker-ce) [![](https://img.shields.io/badge/Docker%20%E6%8A%80%E6%9C%AF%E5%85%A5%E9%97%A8%E4%B8%8E%E5%AE%9E%E6%88%98-jd.com-red.svg)][1] -**v1.5.2** +**v1.5.3** [Docker](https://www.docker.com) 是个划时代的开源项目，它彻底释放了计算虚拟化的威力，极大提高了应用的维护效率，降低了云计算应用开发的成本！使用 Docker，可以让应用的部署、测试和分发都变得前所未有的高效和轻松！ diff --git a/combine.py b/combine.py new file mode 100644 index 0000000..14075b0 --- /dev/null +++ b/combine.py @@ -0,0 +1,1001 @@ +#!/usr/bin/env python3 +""" +通用书籍合并工具 (Generic Book Combiner) + +功能： +1. 自动扫描当前或指定目录。 +2. 解析 SUMMARY.md 获取章节结构。 +3. 解析 README.md 获取书籍标题和简介信息。 +4. 生成 single-page.md 和 single-page.html。 +""" + +import re +import html +import argparse +import sys +from pathlib import Path +from datetime import datetime + +# HTML 模板 +HTML_TEMPLATE = """ + + + + + {title} + + + + +
+ + + +
+ +
+

{title}

+

{subtitle}

+
+ +{content} + +
+ + + + + +""" + + +def extract_book_info(project_dir: Path) -> tuple[str, str]: + """ + 从 README.md 或 SUMMARY.md 中提取书籍标题和副标题。 + + Returns: + (title, subtitle) + """ + title = "Untitled Book" + subtitle = "Generated Book" + + # 优先尝试 README.md + readme_path = project_dir / 'README.md' + if readme_path.exists(): + try: + content = readme_path.read_text(encoding='utf-8') + lines = content.split('\n') + for line in lines[:10]: # 只看前10行 + match = re.match(r'^#\s+(.+)$', line) + if match: + title = match.group(1).strip() + break + + # 尝试查找引用块作为副标题 + for line in lines[:20]: + match = re.match(r'^>\s+(.+)$', line) + if match: + subtitle = match.group(1).strip() + break + return title, subtitle + except Exception: + pass + + # 其次尝试 SUMMARY.md + summary_path = project_dir / 'SUMMARY.md' + if summary_path.exists(): + try: + content = summary_path.read_text(encoding='utf-8') + lines = content.split('\n') + for line in lines[:5]: + match = re.match(r'^#\s+(.+)$', line) + if match: + title = match.group(1).strip() + return title, subtitle + except Exception: + pass + + return title, subtitle + + +def parse_summary(summary_path: Path) -> list[tuple[str, str, int]]: + """ + 解析 SUMMARY.md，提取所有章节链接。 + + Returns: + list of (title, file_path, indent_level) + """ + entries = [] + if not summary_path.exists(): + return entries + + content = summary_path.read_text(encoding='utf-8') + + # 匹配 Markdown 链接格式: * [标题](文件路径) 或 - [标题](文件路径) + # 支持多级缩进 + pattern = r'^(\s*)[\*\-]\s*\[([^\]]+)\]\(([^)]+)\)' + + for line in content.split('\n'): + match = re.match(pattern, line) + if match: + indent = len(match.group(1)) + title = match.group(2) + file_path = match.group(3) + + # 跳过外部链接 + if file_path.startswith('http'): + continue + + entries.append((title, file_path, indent)) + + return entries + + +def convert_internal_links_to_anchors(content: str, file_to_anchor_map: dict[str, str]) -> str: + """ + Convert internal markdown file links to anchor links for single-page output. + + Examples: + [Title](1.2_xxx.md) -> [Title](#anchor-id) + [Title](../04_mcp/README.md) -> [Title](#anchor-id) + [Title](file.md#section) -> [Title](#section) + + Args: + content: The markdown content to process + file_to_anchor_map: Mapping from file paths to their anchor IDs + + Returns: + Content with internal links converted to anchors + """ + def replace_link(match): + link_text = match.group(1) + link_target = match.group(2) + + # Skip external URLs and mailto links + if link_target.startswith('http://') or link_target.startswith('https://') or link_target.startswith('mailto:'): + return match.group(0) + + # Skip image links (they start with !) + # Check the character before the match - this is handled by the regex not matching ![]() + + # Handle anchor-only links + if link_target.startswith('#'): + return match.group(0) + + # Split target into file path and anchor + if '#' in link_target: + file_path, anchor = link_target.split('#', 1) + # If there's a specific anchor, use it directly + return f'[{link_text}](#{anchor})' + else: + file_path = link_target + + # Normalize the file path (remove ./, ../ prefixes and get the basename for matching) + # Extract just the filename for simple matching + normalized_path = file_path.replace('\\', '/').strip() + + # Try to find a matching anchor in the map + # First try exact match + if normalized_path in file_to_anchor_map: + return f'[{link_text}](#{file_to_anchor_map[normalized_path]})' + + # Try matching by filename only (for links like ../04_mcp/README.md) + from pathlib import PurePosixPath + filename = PurePosixPath(normalized_path).name + + # Search for matching file in the map + for path, anchor in file_to_anchor_map.items(): + if PurePosixPath(path).name == filename: + # For README.md, we need to be more specific - check parent directory + if filename == 'README.md': + # Try to match by parent directory + parts = normalized_path.replace('../', '').replace('./', '').split('/') + if len(parts) >= 2: + parent_dir = parts[-2] + path_parts = path.split('/') + if len(path_parts) >= 2 and path_parts[-2] == parent_dir: + return f'[{link_text}](#{anchor})' + continue + return f'[{link_text}](#{anchor})' + + # If no match found, generate an anchor from the link text + # This handles cases where the file might not be in the map + fallback_anchor = re.sub(r'[^\w\u4e00-\u9fff]+', '-', link_text.lower()).strip('-') + return f'[{link_text}](#{fallback_anchor})' + + # Match markdown links: [text](target) but not image links ![text](target) + # Use negative lookbehind for ! + pattern = r'(? str: + """ + Fix relative image paths for single-page output. + + When combining files from different directories, relative image paths like + `_images/xxx.png` need to be prefixed with the source file's directory. + + Examples: + If file is from 07_coding/7.4_ide.md: + ![alt](_images/cursor.png) -> ![alt](07_coding/_images/cursor.png) + + Args: + content: The markdown content to process + file_path: The relative path of the source file (e.g., "07_coding/7.4_ide.md") + + Returns: + Content with fixed image paths + """ + from pathlib import PurePosixPath + + # Get the directory of the source file + source_dir = str(PurePosixPath(file_path).parent) + + # If the file is in the root directory, no path fixing needed + if source_dir == '.': + return content + + def replace_image(match): + alt_text = match.group(1) + image_path = match.group(2) + + # Skip external URLs + if image_path.startswith('http://') or image_path.startswith('https://'): + return match.group(0) + + # Skip absolute paths + if image_path.startswith('/'): + return match.group(0) + + # Skip paths that already have a directory prefix (not starting with _images/) + if not image_path.startswith('_images/') and not image_path.startswith('./_images/'): + # Check if it's already a full path like 07_coding/_images/ + if '/_images/' in image_path or image_path.startswith('../'): + return match.group(0) + + # Remove leading ./ if present + clean_path = image_path.lstrip('./') + + # Prepend the source directory + new_path = f"{source_dir}/{clean_path}" + + return f'![{alt_text}]({new_path})' + + # Match markdown image syntax: ![alt](path) + pattern = r'!\[([^\]]*)\]\(([^)]+)\)' + return re.sub(pattern, replace_image, content) + + +def clean_navigation_links(content: str) -> str: + """ + Remove navigation links (Next/Previous, arrows) from the end of the content. + """ + lines = content.rstrip().split('\n') + + # Navigation line patterns + nav_patterns = [ + r'^\s*[-=]{3,}\s*$', # Separator lines + r'^\s*(\*\*|__)?(Next|Previous|下一[节章页]|上一[节章页])(\*\*|__)?.*$', # Text based + r'^\s*(➡️|→|=>|==>|Example|Download)\s*.*$', # Arrow/Indicator based + r'^\s*\[(Next|Previous|下一[节章]|上一[节章]).*?\]\(.*?\)\s*$', # Link with nav text + ] + + # Also catch "Arrow [Link](Url)" specifically if not caught above + # And purely link lines that look like nav " [Title](Url) " relative short + + while lines: + last_line = lines[-1].strip() + if not last_line: + lines.pop() + continue + + is_nav = False + + # Check explicit patterns + for pattern in nav_patterns: + if re.match(pattern, last_line, re.IGNORECASE): + is_nav = True + break + + # Check "Arrow + Link" specifically (common in this book) + if not is_nav: + # Pattern: Arrow (optional) + Link + # e.g. "➡️ [Title](Link)" + if re.match(r'^\s*(➡️|→|=>|==>)\s*\[.+?\]\(.+?\)\s*$', last_line): + is_nav = True + + if is_nav: + # print(f"DEBUG: Removing nav line: {last_line}") + lines.pop() + else: + # Found a non-nav line, stop checking + break + + return '\n'.join(lines) + + +def clean_redundant_header(content: str, title: str, subtitle: str) -> str: + """ + Remove the title and subtitle from the beginning of the content if they match the book info. + """ + lines = content.split('\n') + + # Remove leading blank lines + while lines and not lines[0].strip(): + lines.pop(0) + + if not lines: + return content + + # Check for Title (H1) + # Case 1: Exact match "# Title" + # Case 2: Match with some whitespace flexibility + if re.match(r'^#\s+' + re.escape(title) + r'\s*$', lines[0].strip(), re.IGNORECASE): + lines.pop(0) + # Remove blank lines after title + while lines and not lines[0].strip(): + lines.pop(0) + + # Check for Subtitle (Blockquote) + if subtitle and lines and lines[0].strip().startswith(">"): + # Clean punctuation for comparison just in case + line_text = lines[0].strip().lstrip('>').strip() + if subtitle in line_text or line_text in subtitle: + lines.pop(0) + # Remove blank lines after subtitle + while lines and not lines[0].strip(): + lines.pop(0) + + # Also remove common separator lines like "---" that often follow the header + if lines and lines[0].strip().replace(' ', '') == '---': + lines.pop(0) + while lines and not lines[0].strip(): + lines.pop(0) + + return '\n'.join(lines) + + +def markdown_to_html(md_content: str) -> str: + """ + 将 Markdown 转换为 HTML。 + 简单实现，不依赖外部库。 + """ + lines = md_content.split('\n') + html_lines = [] + in_code_block = False + code_lang = '' + code_content = [] + in_list = False + in_table = False + table_rows = [] + + def process_inline(text: str) -> str: + """处理行内格式""" + # 代码 + text = re.sub(r'`([^`]+)`', r'\1', text) + # 粗体 + text = re.sub(r'\*\*([^*]+)\*\*', r'\1', text) + # 斜体 + text = re.sub(r'\*([^*]+)\*', r'\1', text) + # 链接 + text = re.sub(r'\[([^\]]+)\]\(([^)]+)\)', r'\1', text) + return text + + i = 0 + while i < len(lines): + line = lines[i] + + # 代码块 + if line.startswith('```'): + if in_code_block: + html_lines.append(f'
{html.escape(chr(10).join(code_content))}
') + code_content = [] + in_code_block = False + else: + code_lang = line[3:].strip() or 'text' + in_code_block = True + i += 1 + continue + + if in_code_block: + code_content.append(line) + i += 1 + continue + + # 表格 + if '|' in line and not line.strip().startswith('```'): + cells = [c.strip() for c in line.split('|')] + cells = [c for c in cells if c] # 移除空单元格 + + if cells and not all(re.match(r'^[-:]+$', c) for c in cells): + if not in_table: + in_table = True + table_rows = [] + table_rows.append(cells) + elif in_table and all(re.match(r'^[-:]+$', c) for c in cells): + pass # 跳过分隔行 + + # 检查下一行是否还是表格 + if i + 1 >= len(lines) or '|' not in lines[i + 1]: + if in_table and table_rows: + html_lines.append('') + for j, row in enumerate(table_rows): + tag = 'th' if j == 0 else 'td' + html_lines.append('') + for cell in row: + html_lines.append(f'<{tag}>{process_inline(cell)}') + html_lines.append('') + html_lines.append('
') + table_rows = [] + in_table = False + i += 1 + continue + + # 标题 + heading_match = re.match(r'^(#{1,6})\s+(.+)$', line) + if heading_match: + level = len(heading_match.group(1)) + text = process_inline(heading_match.group(2)) + # 生成简单的 ID + anchor = re.sub(r'[^\w\u4e00-\u9fff]+', '-', heading_match.group(2).lower()).strip('-') + html_lines.append(f'{text}') + i += 1 + continue + + # 引用 + if line.startswith('>'): + quote_text = process_inline(line[1:].strip()) + html_lines.append(f'

{quote_text}

') + i += 1 + continue + + # 水平线 + if re.match(r'^-{3,}$|^\*{3,}$|^_{3,}$', line.strip()): + html_lines.append('
') + i += 1 + continue + + # 无序列表 + list_match = re.match(r'^(\s*)[\*\-]\s+(.+)$', line) + if list_match: + if not in_list: + html_lines.append('') + in_list = False + i += 1 + continue + + # 有序列表 + ol_match = re.match(r'^(\s*)\d+\.\s+(.+)$', line) + if ol_match: + if not in_list: + html_lines.append('
    ') + in_list = True + html_lines.append(f'
  1. {process_inline(ol_match.group(2))}
    2. ') + # 检查下一行 + if i + 1 >= len(lines) or not re.match(r'^\s*\d+\.\s+', lines[i + 1]): + html_lines.append('
') + in_list = False + i += 1 + continue + + # 空行 + if not line.strip(): + i += 1 + continue + + # 注释行（跳过） + if line.strip().startswith('\n") + md_body.append(f'
\n') # 添加锚点 + md_body.append(content) + md_body.append("\n") + + processed_count += 1 + print(f" ✅ {title}") + + except Exception as e: + print(f" ❌ 读取失败 {file_path}: {e}") + skipped_count += 1 + + # 生成 Markdown 文件 (包含标题头) + final_md = '\n'.join(md_header + md_body) + # 规范化空行 + final_md = re.sub(r'\n{4,}', '\n\n\n', final_md) + + md_path = project_dir / output_md + md_path.write_text(final_md, encoding='utf-8') + + # 生成 HTML 文件 (仅使用正文，因为 HTML 模板已有 Header) + print("\n🔄 正在生成 HTML...") + final_html_md = '\n'.join(md_body) + html_content = markdown_to_html(final_html_md) + + # 填充 HTML 模板 + current_date = datetime.now().strftime("%Y-%m-%d") + final_html = HTML_TEMPLATE.format( + title=book_title, + subtitle=book_subtitle, + content=html_content, + date=current_date + ) + + html_path = project_dir / output_html + html_path.write_text(final_html, encoding='utf-8') + + # 统计信息 + md_size = md_path.stat().st_size + html_size = html_path.stat().st_size + + print(f"\n{'=' * 50}") + print(f"📖 合并完成！") + print(f" 输出目录: {project_dir}") + print(f" Markdown: {md_path.name} ({md_size / 1024:.1f} KB)") + print(f" HTML: {html_path.name} ({html_size / 1024:.1f} KB)") + print(f" 处理章节: {processed_count}") + print(f" 跳过文件: {skipped_count}") + print(f"{'=' * 50}") + + +def main(): + parser = argparse.ArgumentParser(description="GitBook 书籍自动合并工具") + parser.add_argument("path", nargs="?", default=".", help="书籍根目录路径 (包含 SUMMARY.md 的目录)") + parser.add_argument("--output-md", default="single-page.md", help="输出 Markdown 文件名") + parser.add_argument("--output-html", default="single-page.html", help="输出 HTML 文件名") + + args = parser.parse_args() + + target_dir = Path(args.path).resolve() + + if not target_dir.is_dir(): + print(f"❌ 错误: 目录不存在: {target_dir}") + sys.exit(1) + + print("=" * 50) + print("通用书籍合并工具 v2.0") + print("=" * 50) + print(f"工作目录: {target_dir}\n") + + combine_book(target_dir, args.output_md, args.output_html) + + +if __name__ == '__main__': + main() diff --git a/package.json b/package.json index a35560b..302eb13 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "docker_practice", - "version": "1.0.0", + "version": "1.5.3", "description": "docker_practice", "main": "index.js", "devDependencies": { @@ -29,4 +29,4 @@ "url": "https://github.com/yeasy/docker_practice/issues" }, "homepage": "https://github.com/yeasy/docker_practice#readme" -} +} \ No newline at end of file