undoc 0.2.0

High-performance Microsoft Office document extraction to Markdown
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159

//! Benchmarks for undoc parsing performance.
//!
//! Run with: cargo bench
//!
//! These benchmarks test parsing performance at various document sizes.

use criterion::{black_box, criterion_group, criterion_main, BenchmarkId, Criterion, Throughput};
use std::io::Cursor;

/// Creates a synthetic DOCX document with the given number of paragraphs.
fn create_test_docx(paragraph_count: usize) -> Vec<u8> {
    use std::io::Write;
    use zip::write::SimpleFileOptions;
    use zip::ZipWriter;

    let mut buffer = Vec::new();
    let mut zip = ZipWriter::new(Cursor::new(&mut buffer));

    let options = SimpleFileOptions::default().compression_method(zip::CompressionMethod::Stored);

    // [Content_Types].xml
    zip.start_file("[Content_Types].xml", options).unwrap();
    zip.write_all(
        br#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
  <Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
  <Default Extension="xml" ContentType="application/xml"/>
  <Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>
</Types>"#,
    )
    .unwrap();

    // _rels/.rels
    zip.start_file("_rels/.rels", options).unwrap();
    zip.write_all(
        br#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
  <Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/>
</Relationships>"#,
    )
    .unwrap();

    // word/_rels/document.xml.rels
    zip.start_file("word/_rels/document.xml.rels", options)
        .unwrap();
    zip.write_all(
        br#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
</Relationships>"#,
    )
    .unwrap();

    // Generate document content
    let mut content = String::from(
        r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
  <w:body>"#,
    );

    for i in 0..paragraph_count {
        content.push_str(&format!(
            r#"
    <w:p>
      <w:r>
        <w:t>This is paragraph {} with some test content for benchmarking purposes.</w:t>
      </w:r>
    </w:p>"#,
            i
        ));
    }

    content.push_str(
        r#"
  </w:body>
</w:document>"#,
    );

    zip.start_file("word/document.xml", options).unwrap();
    zip.write_all(content.as_bytes()).unwrap();

    zip.finish().unwrap();
    buffer
}

/// Benchmark DOCX parsing at various sizes.
fn bench_docx_parsing(c: &mut Criterion) {
    let mut group = c.benchmark_group("docx_parsing");

    for para_count in [10, 100, 500, 1000].iter() {
        let data = create_test_docx(*para_count);
        let size = data.len() as u64;

        group.throughput(Throughput::Bytes(size));
        group.bench_with_input(
            BenchmarkId::new("paragraphs", para_count),
            &data,
            |b, data| {
                b.iter(|| {
                    let _ = undoc::parse_bytes(black_box(data));
                });
            },
        );
    }

    group.finish();
}

/// Benchmark document rendering to Markdown.
fn bench_markdown_rendering(c: &mut Criterion) {
    let mut group = c.benchmark_group("markdown_rendering");

    for para_count in [10, 100, 500].iter() {
        let data = create_test_docx(*para_count);
        let document = undoc::parse_bytes(&data).unwrap();

        group.bench_with_input(
            BenchmarkId::new("paragraphs", para_count),
            &document,
            |b, doc| {
                b.iter(|| {
                    let options = undoc::render::RenderOptions::default();
                    let _ = undoc::render::to_markdown(black_box(doc), &options);
                });
            },
        );
    }

    group.finish();
}

/// Benchmark text extraction.
fn bench_text_extraction(c: &mut Criterion) {
    let mut group = c.benchmark_group("text_extraction");

    for para_count in [10, 100, 500, 1000].iter() {
        let data = create_test_docx(*para_count);
        let document = undoc::parse_bytes(&data).unwrap();

        group.bench_with_input(
            BenchmarkId::new("paragraphs", para_count),
            &document,
            |b, doc| {
                b.iter(|| {
                    let _ = black_box(doc).plain_text();
                });
            },
        );
    }

    group.finish();
}

criterion_group!(
    benches,
    bench_docx_parsing,
    bench_markdown_rendering,
    bench_text_extraction,
);
criterion_main!(benches);