心是桃源，处处水云

1
cargo new md-processor --bin
2
cd md-processor

1
[dependencies]
2
walkdir = "2"           # 遍历目录
3
gray_matter = "0.2"     # 解析 frontmatter
4
regex = "1"             # 正则匹配
5
rayon = "1.7"           # 并行处理
6
serde = { version = "1", features = ["derive"] }
7
serde_json = "1"

1
def process_file(path):
2
    with open(path, 'r', encoding='utf-8') as f:
3
        content = f.read()
4

5
    # 提取 frontmatter
6
    matter = frontmatter.loads(content)
7

8
    # 统计字数
9
    text = re.sub(r'[^\\u4e00-\\u9fa5a-zA-Z0-9]', '', matter.content)
10
    word_count = len(text)
11

12
    return {
13
        'path': path,
14
        'title': matter.get('title', ''),
15
        'words': word_count
16
    }
17

18
# 串行处理
19
results = [process_file(f) for f in files]

1
use rayon::prelude::*;
2
use std::fs;
3

4
#[derive(Debug, Serialize)]
5
struct FileInfo {
6
    path: String,
7
    title: String,
8
    words: usize,
9
}
10

11
fn process_file(path: &Path) -> Result<FileInfo> {
12
    let content = fs::read_to_string(path)?;
13

14
    // 解析 frontmatter
15
    let matter = gray_matter::Matter::<gray_matter::engine::YAML>::new();
16
    let parsed = matter.parse(&content);
17

18
    // 统计字数（只保留中英文和数字）
19
    let text: String = parsed.content
20
        .chars()
21
        .filter(|c| c.is_alphanumeric() || (*c >= '\\u{4e00}' && *c <= '\\u{9fa5}'))
22
        .collect();
23

24
    Ok(FileInfo {
25
        path: path.display().to_string(),
26
        title: parsed.data
27
            .as_ref()
28
            .and_then(|d| d.get("title"))
29
            .and_then(|t| t.as_str())
30
            .unwrap_or("")
31
            .to_string(),
32
        words: text.len(),
33
    })
34
}
35

36
fn main() -> Result<()> {
37
    let files: Vec<_> = WalkDir::new("posts")
38
        .into_iter()
39
        .filter_map(|e| e.ok())
40
        .filter(|e| e.path().extension() == Some(OsStr::new("md")))
41
        .collect();
42

43
    // 并行处理
44
    let results: Vec<_> = files
45
        .par_iter()
46
        .filter_map(|entry| process_file(entry.path()).ok())
47
        .collect();
48

49
    println!("处理完成：{} 个文件", results.len());
50
    Ok(())
51
}

1
let char = content[0]; // ❌ 编译错误

1
let char = content.chars().next(); // ✅

1
let results: Vec<_> = files
2
    .par_iter()
3
    .filter_map(|entry| process_file(entry.path()).ok()) // 忽略错误
4
    .collect();

1
let results = if files.len() > 50 {
2
    files.par_iter().filter_map(|e| process_file(e).ok()).collect()
3
} else {
4
    files.iter().filter_map(|e| process_file(e).ok()).collect()
5
};

1
拉取代码 (5s) → 安装依赖 (15s) → 处理文件 (2.3s) → 构建 (30s)
2
总计：52.3s

1
拉取代码 (5s) → 下载二进制 (1s) → 处理文件 (0.04s) → 构建 (30s)
2
总计：36s