acorn-lib 0.3.2

ACORN library
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

#![allow(
    clippy::arithmetic_side_effects,
    clippy::expect_used,
    clippy::indexing_slicing,
    clippy::panic,
    clippy::unwrap_used
)]
use crate::analyzer::readability::flesch_kincaid_grade_level;
use crate::io::document::to_markdown;
use crate::test::utils::fixture_path;
use std::io::Write;
use std::path::PathBuf;
use tempfile::{Builder, NamedTempFile};
use zip::write::SimpleFileOptions;
use zip::{CompressionMethod, ZipWriter};

fn write_docx(document_xml: &str) -> NamedTempFile {
    let file = Builder::new().suffix(".docx").tempfile().unwrap();
    let mut archive = ZipWriter::new(file);
    let options = SimpleFileOptions::default().compression_method(CompressionMethod::Stored);
    let content_types = r#"<?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>"#;
    let root_rels = r#"<?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>"#;
    let document_rels = r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
    <Relationship Id="rIdHyper" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/hyperlink" Target="https://example.org" TargetMode="External"/>
</Relationships>"#;
    archive.start_file("[Content_Types].xml", options).unwrap();
    archive.write_all(content_types.as_bytes()).unwrap();
    archive.start_file("_rels/.rels", options).unwrap();
    archive.write_all(root_rels.as_bytes()).unwrap();
    archive.start_file("word/document.xml", options).unwrap();
    archive.write_all(document_xml.as_bytes()).unwrap();
    archive.start_file("word/_rels/document.xml.rels", options).unwrap();
    archive.write_all(document_rels.as_bytes()).unwrap();
    archive.finish().unwrap()
}

#[test]
fn test_extract_sample_fixture() {
    let result = to_markdown(fixture_path("sample.docx"));
    assert!(result.is_err(), "Sample fixture should currently fail parsing");
}
#[test]
fn test_extract_acorn_fixture() {
    let result = to_markdown(fixture_path("acorn.docx"));
    assert!(result.is_ok(), "Acorn fixture should parse");
    let text = result.unwrap();
    assert!(text.contains("ACORN"), "Acorn fixture text should contain ACORN");
    assert!(
        text.contains("Research Activity Data (RAD)"),
        "Acorn fixture text should contain Research Activity Data (RAD)"
    );
}
#[test]
fn test_extract_acorn_fixture_readability() {
    let text = to_markdown(fixture_path("acorn.docx")).unwrap();
    let grade = flesch_kincaid_grade_level(&text);
    assert!((grade - 17.12).abs() < 0.2, "Expected readability near 17.12, got {grade}");
}
#[test]
fn test_extract_nonexistent_file() {
    // Test: Should return error when file doesn't exist
    let nonexistent_path = PathBuf::from("/nonexistent/path/to/file.docx");
    let result = to_markdown(&nonexistent_path);
    assert!(result.is_err(), "Should fail for nonexistent file");
}
#[test]
fn test_extract_invalid_docx() {
    // Test: Should return error when file is not a valid DOCX
    let mut temporary = Builder::new().suffix(".docx").tempfile().unwrap();
    temporary.write_all(b"Not a valid DOCX file").unwrap();
    let result = to_markdown(temporary.path());
    assert!(result.is_err(), "Should fail for invalid DOCX format");
}
#[test]
fn test_extract_empty_zip() {
    // Test: Should handle DOCX-like structure gracefully
    let mut temporary = Builder::new().suffix(".docx").tempfile().unwrap();
    // Write minimal ZIP header (PK signature)
    temporary.write_all(&[0x50, 0x4b, 0x03, 0x04]).unwrap();
    let result = to_markdown(temporary.path());
    // Should either succeed with empty string or return error - both are acceptable
    // The important thing is it doesn't panic
    let _ = result;
}
#[test]
fn test_extract_function_signature() {
    // Test: Verify the function can be called with different path types
    // This tests the impl Into<PathBuf> trait
    let nonexistent = "/fake/path.docx";
    let result = to_markdown(nonexistent);
    assert!(result.is_err(), "Should accept &str and return error for missing file");
}
#[test]
fn test_extract_generated_docx_paragraph_children() {
    let document_xml = r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"
                        xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships">
    <w:body>
        <w:p>
            <w:r><w:t>Alpha</w:t></w:r>
            <w:r><w:tab/></w:r>
            <w:r><w:t>Beta</w:t></w:r>
            <w:r><w:br/></w:r>
            <w:r><w:instrText>Instr</w:instrText></w:r>
            <w:hyperlink r:id="rIdHyper"><w:r><w:t>Link</w:t></w:r></w:hyperlink>
            <w:ins w:id="1"><w:r><w:t>InsertText</w:t></w:r></w:ins>
            <w:del w:id="2"><w:r><w:t>DeleteText</w:t></w:r></w:del>
            <w:moveFrom w:id="3" w:author="Author" w:date="2026-08-01T00:00:00Z"><w:r><w:t>GhostText</w:t></w:r></w:moveFrom>
            <w:moveTo w:id="3" w:author="Author" w:date="2026-08-01T00:00:00Z"><w:r><w:t>MovedText</w:t></w:r></w:moveTo>
            <w:r><w:cr/></w:r>
            <w:r><w:t>AfterCarriageReturn</w:t></w:r>
        </w:p>
        <w:p>
            <w:r><w:t>Tail</w:t></w:r>
        </w:p>
    </w:body>
</w:document>"#;
    let document = write_docx(document_xml);
    let result = to_markdown(document.path());
    assert!(result.is_ok(), "Generated DOCX should parse");
    let text = result.unwrap();
    ["Alpha", "Beta", "Link", "InsertText", "MovedText", "AfterCarriageReturn"]
        .into_iter()
        .for_each(|expected| assert!(text.contains(expected), "Expected extracted text to contain {expected}: {text:?}"));
    ["Instr", "DeleteText", "GhostText"]
        .into_iter()
        .for_each(|excluded| assert!(!text.contains(excluded), "Expected extracted text to omit {excluded}: {text:?}"));
    assert!(text.contains("Tail"));
}
#[test]
fn test_extract_generated_docx_table_children() {
    let document_xml = r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
    <w:body>
        <w:tbl>
            <w:tr>
                <w:tc>
                    <w:p><w:r><w:t>CellOne</w:t></w:r></w:p>
                    <w:tbl>
                        <w:tr>
                            <w:tc>
                                <w:p><w:r><w:t>NestedCell</w:t></w:r></w:p>
                            </w:tc>
                        </w:tr>
                    </w:tbl>
                </w:tc>
            </w:tr>
        </w:tbl>
    </w:body>
</w:document>"#;
    let document = write_docx(document_xml);
    let result = to_markdown(document.path());
    assert!(result.is_ok(), "Generated table DOCX should parse");
    let text = result.unwrap();
    assert!(text.contains("CellOne"));
    assert!(text.contains("NestedCell"));
}