pmat 3.11.0

PMAT - Zero-config AI context generation and code quality toolkit (CLI, MCP, HTTP)
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
215
216
217
218
219
220
221
222
223
224
225

// ── Tests ──────────────────────────────────────────────────────

#[cfg(test)]
mod tests {
    use super::*;
    use std::io::Write;

    #[test]
    fn test_is_document_file() {
        assert!(is_document_file(Path::new("docs/spec.pdf")));
        assert!(is_document_file(Path::new("diagram.svg")));
        assert!(is_document_file(Path::new("screenshot.png")));
        assert!(is_document_file(Path::new("photo.jpg")));
        assert!(is_document_file(Path::new("photo.JPEG")));
        assert!(is_document_file(Path::new("README.md")));
        assert!(is_document_file(Path::new("notes.txt")));
        assert!(is_document_file(Path::new("doc.rst")));
        assert!(is_document_file(Path::new("doc.adoc")));
        assert!(!is_document_file(Path::new("main.rs")));
        assert!(!is_document_file(Path::new("lib.py")));
        assert!(!is_document_file(Path::new("Cargo.toml")));
    }

    #[test]
    fn test_extract_svg_with_text() {
        let dir = tempfile::tempdir().unwrap();
        let svg_path = dir.path().join("diagram.svg");
        std::fs::write(
            &svg_path,
            r#"<svg><text x="10" y="20">Hello World</text><tspan>Sub text</tspan></svg>"#,
        )
        .unwrap();

        let chunks = extract_svg(&svg_path, "diagram.svg", "abc123").unwrap();
        assert_eq!(chunks.len(), 1);
        assert!(chunks[0].text_content.contains("Hello World"));
        assert!(chunks[0].text_content.contains("Sub text"));
        assert_eq!(chunks[0].doc_type, DocumentType::Svg);
    }

    #[test]
    fn test_extract_svg_no_text() {
        let dir = tempfile::tempdir().unwrap();
        let svg_path = dir.path().join("empty.svg");
        std::fs::write(&svg_path, r#"<svg><rect width="100" height="100"/></svg>"#).unwrap();

        let chunks = extract_svg(&svg_path, "empty.svg", "def456").unwrap();
        assert_eq!(chunks.len(), 1);
        assert!(chunks[0].text_content.contains("no text content"));
        assert_eq!(chunks[0].extraction_quality, 0.2);
    }

    #[test]
    fn test_extract_svg_with_title() {
        let dir = tempfile::tempdir().unwrap();
        let svg_path = dir.path().join("titled.svg");
        std::fs::write(
            &svg_path,
            r#"<svg><title>Architecture Diagram</title><text>Node A</text></svg>"#,
        )
        .unwrap();

        let chunks = extract_svg(&svg_path, "titled.svg", "ghi789").unwrap();
        assert_eq!(chunks.len(), 1);
        assert!(chunks[0].text_content.contains("Architecture Diagram"));
        assert!(chunks[0].text_content.contains("Node A"));
    }

    #[test]
    fn test_extract_image_metadata() {
        let dir = tempfile::tempdir().unwrap();
        let img_path = dir.path().join("screenshot.png");
        std::fs::write(&img_path, b"fake png data").unwrap();

        let chunks =
            extract_image_metadata(&img_path, "docs/screenshots/screenshot.png", "hash1").unwrap();
        assert_eq!(chunks.len(), 1);
        assert!(chunks[0].text_content.contains("screenshot.png"));
        assert!(chunks[0].text_content.contains("docs/screenshots"));
        assert_eq!(chunks[0].extraction_quality, 0.3);
        assert_eq!(chunks[0].doc_type, DocumentType::Image);
    }

    #[test]
    fn test_extract_markdown_with_headings() {
        let dir = tempfile::tempdir().unwrap();
        let md_path = dir.path().join("doc.md");
        std::fs::write(
            &md_path,
            "# Title\n\nIntro paragraph.\n\n## Section A\n\nContent A.\n\n## Section B\n\nContent B.\n",
        )
        .unwrap();

        let chunks = extract_markdown(&md_path, "doc.md", "hash2").unwrap();
        assert!(chunks.len() >= 2);
        // First chunk should be the "Title" section with "Intro paragraph"
        assert_eq!(chunks[0].section_heading, Some("Title".to_string()));
        assert!(chunks[0].text_content.contains("Intro paragraph"));
        // Second chunk should be "Section A"
        assert_eq!(chunks[1].section_heading, Some("Section A".to_string()));
        assert!(chunks[1].text_content.contains("Content A"));
    }

    #[test]
    fn test_extract_markdown_no_headings() {
        let dir = tempfile::tempdir().unwrap();
        let md_path = dir.path().join("flat.md");
        std::fs::write(&md_path, "Just some plain text\nwith no headings.\n").unwrap();

        let chunks = extract_markdown(&md_path, "flat.md", "hash3").unwrap();
        assert_eq!(chunks.len(), 1);
        assert!(chunks[0].text_content.contains("plain text"));
        assert_eq!(chunks[0].section_heading, None);
    }

    #[test]
    fn test_extract_markdown_empty() {
        let dir = tempfile::tempdir().unwrap();
        let md_path = dir.path().join("empty.md");
        std::fs::write(&md_path, "").unwrap();

        let chunks = extract_markdown(&md_path, "empty.md", "hash4").unwrap();
        assert!(chunks.is_empty());
    }

    #[test]
    fn test_extract_plaintext() {
        let dir = tempfile::tempdir().unwrap();
        let txt_path = dir.path().join("notes.txt");
        std::fs::write(&txt_path, "Line 1\nLine 2\nLine 3\n").unwrap();

        let chunks = extract_plaintext(&txt_path, "notes.txt", "hash5").unwrap();
        assert_eq!(chunks.len(), 1);
        assert!(chunks[0].text_content.contains("Line 1"));
        assert_eq!(chunks[0].doc_type, DocumentType::PlainText);
    }

    #[test]
    fn test_extract_plaintext_empty() {
        let dir = tempfile::tempdir().unwrap();
        let txt_path = dir.path().join("empty.txt");
        std::fs::write(&txt_path, "  \n  \n").unwrap();

        let chunks = extract_plaintext(&txt_path, "empty.txt", "hash6").unwrap();
        assert!(chunks.is_empty());
    }

    #[test]
    fn test_split_into_chunks_large_content() {
        // Create content larger than MAX_CHUNK_SIZE
        let mut content = String::new();
        for i in 0..500 {
            content.push_str(&format!(
                "Line {i}: This is a test line with some content.\n"
            ));
        }
        assert!(content.len() > MAX_CHUNK_SIZE);

        let chunks = split_into_chunks(&content, "big.txt", DocumentType::PlainText, "hash7", 1.0);
        assert!(chunks.len() > 1);
        for chunk in &chunks {
            assert!(chunk.text_content.len() <= MAX_CHUNK_SIZE + 100); // allow some slack for last line
        }
    }

    #[test]
    fn test_truncate_to_max_chunk() {
        let short = "hello world";
        assert_eq!(truncate_to_max_chunk(short), "hello world");

        let long = "a ".repeat(MAX_CHUNK_SIZE);
        let truncated = truncate_to_max_chunk(&long);
        assert!(truncated.len() <= MAX_CHUNK_SIZE);
    }

    #[test]
    fn test_extract_document_dispatcher() {
        let dir = tempfile::tempdir().unwrap();

        // SVG dispatch
        let svg_path = dir.path().join("test.svg");
        std::fs::write(&svg_path, "<svg><text>Hello</text></svg>").unwrap();
        assert!(extract_document(&svg_path, "test.svg", "h1").is_ok());

        // Markdown dispatch
        let md_path = dir.path().join("test.md");
        std::fs::write(&md_path, "# Hello\nWorld").unwrap();
        assert!(extract_document(&md_path, "test.md", "h2").is_ok());

        // Plaintext dispatch
        let txt_path = dir.path().join("test.txt");
        std::fs::write(&txt_path, "Hello").unwrap();
        assert!(extract_document(&txt_path, "test.txt", "h3").is_ok());

        // Image dispatch
        let img_path = dir.path().join("test.png");
        std::fs::write(&img_path, b"PNG").unwrap();
        assert!(extract_document(&img_path, "test.png", "h4").is_ok());

        // Unsupported
        let rs_path = dir.path().join("test.rs");
        std::fs::write(&rs_path, "fn main() {}").unwrap();
        assert!(extract_document(&rs_path, "test.rs", "h5").is_err());
    }

    #[test]
    fn test_pdf_without_feature() {
        // Without doc-indexing feature, should return metadata-only chunk
        let dir = tempfile::tempdir().unwrap();
        let pdf_path = dir.path().join("test.pdf");
        let mut f = std::fs::File::create(&pdf_path).unwrap();
        f.write_all(b"%PDF-1.4 fake").unwrap();

        let result = extract_pdf(&pdf_path, "test.pdf", "hashpdf");
        // Without the doc-indexing feature, this returns a metadata-only result
        // With the feature, it would attempt real extraction (and likely fail on fake data)
        #[cfg(not(feature = "doc-indexing"))]
        {
            let chunks = result.unwrap();
            assert_eq!(chunks.len(), 1);
            assert!(chunks[0].text_content.contains("doc-indexing"));
            assert_eq!(chunks[0].extraction_quality, 0.1);
        }
    }
}