dxpdf 0.2.10

A fast DOCX-to-PDF converter powered by Skia
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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214

use std::io::Write;

/// Create a minimal DOCX (ZIP) file in memory with the given document.xml content.
fn make_docx(document_xml: &str) -> Vec<u8> {
    let buf = std::io::Cursor::new(Vec::new());
    let mut zip = zip::ZipWriter::new(buf);

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

    // Content types
    zip.start_file("[Content_Types].xml", options).unwrap();
    zip.write_all(
        br#"<?xml version="1.0" encoding="UTF-8"?>
<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();

    // Relationships
    zip.start_file("_rels/.rels", options).unwrap();
    zip.write_all(
        br#"<?xml version="1.0" encoding="UTF-8"?>
<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();

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

    let cursor = zip.finish().unwrap();
    cursor.into_inner()
}

fn simple_docx(body_content: &str) -> Vec<u8> {
    let xml = format!(
        r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
  <w:body>{body_content}</w:body>
</w:document>"#
    );
    make_docx(&xml)
}

#[test]
fn convert_simple_docx_to_pdf() {
    let docx = simple_docx(r#"<w:p><w:r><w:t>Hello World</w:t></w:r></w:p>"#);
    let pdf = dxpdf::convert(&docx).unwrap();

    // PDF should start with the magic bytes
    assert!(pdf.len() > 4);
    assert_eq!(&pdf[..5], b"%PDF-");
}

#[test]
fn convert_formatted_docx_to_pdf() {
    let docx = simple_docx(
        r#"<w:p>
            <w:pPr><w:jc w:val="center"/></w:pPr>
            <w:r>
                <w:rPr>
                    <w:b/>
                    <w:i/>
                    <w:sz w:val="36"/>
                    <w:color w:val="0000FF"/>
                    <w:rFonts w:ascii="Times New Roman"/>
                </w:rPr>
                <w:t>Formatted Title</w:t>
            </w:r>
        </w:p>
        <w:p>
            <w:r><w:t>Normal paragraph text.</w:t></w:r>
        </w:p>"#,
    );
    let pdf = dxpdf::convert(&docx).unwrap();
    assert_eq!(&pdf[..5], b"%PDF-");
}

#[test]
fn convert_table_docx_to_pdf() {
    let docx = simple_docx(
        r#"<w:tbl>
            <w:tr>
                <w:tc><w:p><w:r><w:t>Cell A1</w:t></w:r></w:p></w:tc>
                <w:tc><w:p><w:r><w:t>Cell B1</w:t></w:r></w:p></w:tc>
            </w:tr>
            <w:tr>
                <w:tc><w:p><w:r><w:t>Cell A2</w:t></w:r></w:p></w:tc>
                <w:tc><w:p><w:r><w:t>Cell B2</w:t></w:r></w:p></w:tc>
            </w:tr>
        </w:tbl>"#,
    );
    let pdf = dxpdf::convert(&docx).unwrap();
    assert_eq!(&pdf[..5], b"%PDF-");
}

#[test]
fn convert_empty_document() {
    let docx = simple_docx("");
    let pdf = dxpdf::convert(&docx).unwrap();
    assert_eq!(&pdf[..5], b"%PDF-");
}

#[test]
fn convert_writes_to_file() {
    let docx = simple_docx(r#"<w:p><w:r><w:t>File test</w:t></w:r></w:p>"#);
    let pdf = dxpdf::convert(&docx).unwrap();

    let dir = tempfile::tempdir().unwrap();
    let out_path = dir.path().join("test.pdf");
    std::fs::write(&out_path, &pdf).unwrap();

    let read_back = std::fs::read(&out_path).unwrap();
    assert_eq!(read_back, pdf);
}

#[test]
fn parse_invalid_zip_returns_error() {
    let result = dxpdf::convert(b"not a zip file");
    assert!(result.is_err());
}

#[test]
fn parse_zip_without_document_xml_returns_error() {
    // Create a valid ZIP but without word/document.xml
    let buf = std::io::Cursor::new(Vec::new());
    let mut zip = zip::ZipWriter::new(buf);
    let options = zip::write::SimpleFileOptions::default();
    zip.start_file("dummy.txt", options).unwrap();
    zip.write_all(b"hello").unwrap();
    let cursor = zip.finish().unwrap();
    let bytes = cursor.into_inner();

    let result = dxpdf::convert(&bytes);
    assert!(result.is_err());
    let err = result.unwrap_err().to_string();
    assert!(
        err.contains("missing required part"),
        "Error should mention a missing part: {err}"
    );
}

/// Regression: a whitespace-only `<w:t xml:space="preserve">` between two
/// other runs must round-trip the literal space into the parsed model.
/// quick-xml's serde Deserializer trims whitespace-only `$text` content,
/// which used to drop the separator and render `Label:Value` instead of
/// `Label: Value`. The whitespace-workaround module substitutes a Private
/// Use Area sentinel before parsing and reverses it during run conversion.
#[test]
fn whitespace_only_run_with_xml_space_preserve_roundtrips_to_space() {
    use dxpdf::model::{Block, Inline, RunElement};

    // Same shape as the failing cell in the Protokoll DIN VDE document:
    // bold label run, whitespace-only run with xml:space="preserve",
    // value run with different formatting.
    let docx = simple_docx(
        r#"<w:p>
            <w:r><w:rPr><w:b/></w:rPr><w:t>Label:</w:t></w:r>
            <w:r><w:t xml:space="preserve"> </w:t></w:r>
            <w:r><w:t>Value</w:t></w:r>
        </w:p>"#,
    );

    let document = dxpdf::docx::parse(&docx).expect("parse");
    let para = match document.body.first().expect("at least one block") {
        Block::Paragraph(p) => p,
        other => panic!("expected paragraph, got {other:?}"),
    };

    let texts: Vec<&str> = para
        .content
        .iter()
        .filter_map(|inline| match inline {
            Inline::TextRun(tr) => tr.content.iter().find_map(|el| match el {
                RunElement::Text(t) => Some(t.as_str()),
                _ => None,
            }),
            _ => None,
        })
        .collect();

    assert_eq!(
        texts,
        vec!["Label:", " ", "Value"],
        "whitespace-only run must survive parsing as a literal space"
    );
}

#[test]
fn convert_multi_paragraph_docx() {
    let mut body = String::new();
    for i in 0..50 {
        body.push_str(&format!(
            r#"<w:p>
                <w:pPr><w:spacing w:before="100" w:after="100"/></w:pPr>
                <w:r><w:t>Paragraph number {i} with some text content to make it wider.</w:t></w:r>
            </w:p>"#
        ));
    }
    let docx = simple_docx(&body);
    let pdf = dxpdf::convert(&docx).unwrap();
    assert_eq!(&pdf[..5], b"%PDF-");
    // Should produce a non-trivial PDF
    assert!(pdf.len() > 100);
}