基于.NetCore开发 StarBlog 番外篇 (2) 深入解析Markdig源码，优化ToC标题提取和文章目录树生成逻辑

## No.2 cookiecutter-django Github星数: 5735

// 获取heading的原始文本
stripRenderer.Render(headingBlock.Inline);
ReadOnlySpan<char> rawHeadingText = ((FastStringWriter)stripRenderer.Writer).AsSpan();

// 将文本转换为URL友好的格式
string headingText = (_options & AutoIdentifierOptions.GitHub) != 0
    ? LinkHelper.UrilizeAsGfm(rawHeadingText)
    : LinkHelper.Urilize(rawHeadingText, (_options & AutoIdentifierOptions.AllowOnlyAscii) != 0);

// 处理空heading的情况
var baseHeadingId = string.IsNullOrEmpty(headingText) ? "section" : headingText;

// 处理ID冲突
var headingId = baseHeadingId;
if (!identifiers.Add(headingId))
{
    var headingBuffer = new ValueStringBuilder(stackallocchar[ValueStringBuilder.StackallocThreshold]);
    headingBuffer.Append(baseHeadingId);
    headingBuffer.Append('-');
    uint index = 0;
    do
    {
        index++;
        headingBuffer.Append(index);
        headingId = headingBuffer.AsSpan().ToString();
        headingBuffer.Length = baseHeadingId.Length + 1;
    }
    while (!identifiers.Add(headingId));
}

# 1.0 This is a heading

var pipeline = new MarkdownPipelineBuilder()
    .UseAutoIdentifiers()
    .Build();

// 首先需要解析文档
var document = Markdown.Parse(markdownText, pipeline);

// 重要：需要先渲染文档，因为 ID 是在渲染过程中生成的
Markdown.ToHtml(document, pipeline);

// 然后才能获取标题的 ID
foreach (var heading in document.Descendants<HeadingBlock>())
{
    string? headingId = heading.GetAttributes().Id;
    Console.WriteLine($"Heading: {heading.Level}, ID: {headingId}");
}

private void HeadingBlockParser_Closed(BlockProcessor processor, Block block)
{
    // ...
    // Then we register after inline have been processed to actually generate the proper #id
    headingBlock.ProcessInlinesEnd += HeadingBlock_ProcessInlinesEnd;
}

private static string GetHeadingText(HeadingBlock heading) {
if (heading.Inline == null) returnstring.Empty;

var stringBuilder = new StringBuilder();
foreach (var inline in heading.Inline.Descendants<LiteralInline>()) {
    stringBuilder.Append(inline.Content);
  }

return stringBuilder.ToString();
}

publicstatic List<TocNode>? ExtractToc(this Post post) {
if (post.Content == null) returnnull;

var pipeline = new MarkdownPipelineBuilder()
    .UseAutoIdentifiers()
    .Build();

var document = Markdig.Markdown.Parse(post.Content, pipeline);

// Markdig 中获取标题 ID 的正确方式是通过 GetAttributes() 方法，但需要在渲染完成后才能获取。
// 因为 ID 的生成是在 HeadingBlock_ProcessInlinesEnd 阶段完成的 (参考源码: src\Markdig\Extensions\AutoIdentifiers\AutoIdentifierExtension.cs)
  _ = document.ToHtml(pipeline);

// 1. 先将所有标题转换为扁平结构
var headings = document.Descendants<HeadingBlock>()
    .Select((heading, index) => new Heading {
      Id = index,
      Text = GetHeadingText(heading),
      Slug = heading.GetAttributes().Id,
      Level = heading.Level
    })
    .ToList();

// 2. 建立父子关系
for (var i = 0; i < headings.Count; i++) {
    var current = headings[i];
    // 向前查找第一个级别小于当前标题的标题作为父标题
    for (int j = i - 1; j >= 0; j--) {
      if (headings[j].Level < current.Level) {
        current.Pid = headings[j].Id;
        break;
      }
    }
  }

// 3. 转换为树状结构
var tocNodes = new List<TocNode>();
var nodeMap = new Dictionary<int, TocNode>();

foreach (var heading in headings) {
    var node = new TocNode {
      Text = heading.Text,
      Href = $"#{heading.Slug}"
    };
    nodeMap[heading.Id] = node;

    if (heading.Pid == -1) {
      // 根节点
      tocNodes.Add(node);
    }
    else {
      // 子节点
      var parentNode = nodeMap[heading.Pid];
      if (parentNode.Nodes == null) {
        parentNode.Nodes = new List<TocNode>();
      }
      parentNode.Nodes.Add(node);
    }
  }

return tocNodes;
}