oxidize-pdf 2.6.0

A pure Rust PDF generation and manipulation library with zero external dependencies
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
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
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315

//! Tests for text extraction functionality

use oxidize_pdf::parser::PdfReader;
use oxidize_pdf::text::{ExtractionOptions, TextExtractor};
use oxidize_pdf::{Document, Font, Page};
use tempfile::TempDir;

#[test]
fn test_extract_text_from_generated_pdf() {
    // Create a simple PDF with text
    let mut doc = Document::new();
    let mut page = Page::a4();

    // Add some text
    page.text()
        .set_font(Font::Helvetica, 12.0)
        .at(100.0, 700.0)
        .write("Hello, World!")
        .unwrap()
        .at(100.0, 680.0)
        .write("This is a test PDF.")
        .unwrap()
        .at(100.0, 660.0)
        .write("Testing text extraction.")
        .unwrap();

    doc.add_page(page);

    // Save to temporary file
    let temp_dir = TempDir::new().unwrap();
    let pdf_path = temp_dir.path().join("test.pdf");
    doc.save(&pdf_path).unwrap();

    // Open and extract text
    let pdf_doc = PdfReader::open_document(&pdf_path).unwrap();

    let mut extractor = TextExtractor::new();
    let extracted = extractor.extract_from_page(&pdf_doc, 0).unwrap();

    // Verify extracted text contains what we wrote
    assert!(extracted.text.contains("Hello, World!"));
    assert!(extracted.text.contains("This is a test PDF."));
    assert!(extracted.text.contains("Testing text extraction."));
}

#[test]
fn test_extract_with_layout_preservation() {
    let mut doc = Document::new();
    let mut page = Page::a4();

    // Add text at different positions
    page.text()
        .set_font(Font::Helvetica, 14.0)
        .at(50.0, 700.0)
        .write("Left text")
        .unwrap()
        .at(300.0, 700.0)
        .write("Right text")
        .unwrap()
        .at(50.0, 600.0)
        .write("Lower text")
        .unwrap();

    doc.add_page(page);

    // Save and reopen
    let temp_dir = TempDir::new().unwrap();
    let pdf_path = temp_dir.path().join("layout_test.pdf");
    doc.save(&pdf_path).unwrap();

    let pdf_doc = PdfReader::open_document(&pdf_path).unwrap();

    // Extract with layout preservation
    let options = ExtractionOptions {
        preserve_layout: true,
        ..Default::default()
    };

    let mut extractor = TextExtractor::with_options(options);
    let extracted = extractor.extract_from_page(&pdf_doc, 0).unwrap();

    // Should have fragments with position info
    assert!(!extracted.fragments.is_empty());

    // Check that fragments are at different positions
    let positions: Vec<(f64, f64)> = extracted.fragments.iter().map(|f| (f.x, f.y)).collect();

    // Verify we have multiple fragments
    assert!(positions.len() >= 3, "Expected at least 3 text fragments");
}

#[test]
fn test_extract_multiple_pages() {
    let mut doc = Document::new();

    // Create 3 pages with different text
    for i in 0..3 {
        let mut page = Page::a4();
        page.text()
            .set_font(Font::Helvetica, 12.0)
            .at(100.0, 700.0)
            .write(&format!("This is page {}", i + 1))
            .unwrap();
        doc.add_page(page);
    }

    // Save and reopen
    let temp_dir = TempDir::new().unwrap();
    let pdf_path = temp_dir.path().join("multipage_test.pdf");
    doc.save(&pdf_path).unwrap();

    let pdf_doc = PdfReader::open_document(&pdf_path).unwrap();

    // Extract all pages
    let mut extractor = TextExtractor::new();
    let all_pages = extractor.extract_from_document(&pdf_doc).unwrap();

    // Should have 3 pages
    assert_eq!(all_pages.len(), 3);

    // Each page should have correct text
    for (i, extracted) in all_pages.iter().enumerate() {
        assert!(extracted.text.contains(&format!("This is page {}", i + 1)));
    }
}

#[test]
fn test_extract_empty_page() {
    let mut doc = Document::new();
    let page = Page::a4(); // Empty page
    doc.add_page(page);

    // Save and reopen
    let temp_dir = TempDir::new().unwrap();
    let pdf_path = temp_dir.path().join("empty_test.pdf");
    doc.save(&pdf_path).unwrap();

    let pdf_doc = PdfReader::open_document(&pdf_path).unwrap();

    // Extract from empty page
    let mut extractor = TextExtractor::new();
    let extracted = extractor.extract_from_page(&pdf_doc, 0).unwrap();

    // Should be empty
    assert!(extracted.text.is_empty());
    assert!(extracted.fragments.is_empty());
}

#[test]
fn test_extract_from_manual_pdf() {
    // Create a simple valid PDF manually to bypass writer issues
    let pdf_content = b"%PDF-1.4
1 0 obj
<< /Type /Catalog /Pages 2 0 R >>
endobj
2 0 obj
<< /Type /Pages /Kids [3 0 R] /Count 1 >>
endobj
3 0 obj
<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>
endobj
4 0 obj
<< /Length 44 >>
stream
BT
/F1 12 Tf
100 700 Td
(Hello World) Tj
ET
endstream
endobj
5 0 obj
<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>
endobj
xref
0 6
0000000000 65535 f 
0000000009 00000 n 
0000000058 00000 n 
0000000115 00000 n 
0000000241 00000 n 
0000000334 00000 n 
trailer
<< /Size 6 /Root 1 0 R >>
startxref
404
%%EOF";

    // Write to a temporary file
    let temp_dir = TempDir::new().unwrap();
    let pdf_path = temp_dir.path().join("manual_test.pdf");
    std::fs::write(&pdf_path, pdf_content).unwrap();

    // Parse the PDF
    let document = PdfReader::open_document(&pdf_path).unwrap();

    // Extract text
    let mut extractor = TextExtractor::new();
    let extracted_text = extractor.extract_from_document(&document).unwrap();

    // Verify extraction
    assert_eq!(extracted_text.len(), 1);
    assert_eq!(extracted_text[0].text.trim(), "Hello World");
}

#[test]
fn test_extract_with_multiple_text_operations() {
    // Create a PDF with multiple text operations
    let pdf_content = b"%PDF-1.4
1 0 obj
<< /Type /Catalog /Pages 2 0 R >>
endobj
2 0 obj
<< /Type /Pages /Kids [3 0 R] /Count 1 >>
endobj
3 0 obj
<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>
endobj
4 0 obj
<< /Length 93 >>
stream
BT
/F1 12 Tf
100 700 Td
(First line) Tj
0 -20 Td
(Second line) Tj
200 0 Td
(Third line) Tj
ET
endstream
endobj
5 0 obj
<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>
endobj
xref
0 6
0000000000 65535 f 
0000000009 00000 n 
0000000058 00000 n 
0000000115 00000 n 
0000000241 00000 n 
0000000384 00000 n 
trailer
<< /Size 6 /Root 1 0 R >>
startxref
454
%%EOF";

    let temp_dir = TempDir::new().unwrap();
    let pdf_path = temp_dir.path().join("multi_text.pdf");
    std::fs::write(&pdf_path, pdf_content).unwrap();

    // Parse the PDF
    let document = PdfReader::open_document(&pdf_path).unwrap();

    // Extract with preserve layout option
    let options = ExtractionOptions {
        preserve_layout: true,
        ..Default::default()
    };
    let mut extractor = TextExtractor::with_options(options);
    let extracted_text = extractor.extract_from_document(&document).unwrap();

    // Verify extraction
    assert_eq!(extracted_text.len(), 1);
    let page_text = &extracted_text[0];

    // Check text content
    assert!(page_text.text.contains("First line"));
    assert!(page_text.text.contains("Second line"));
    assert!(page_text.text.contains("Third line"));

    // Should have fragments for layout
    assert!(page_text.fragments.len() >= 3);
}

#[test]
fn test_extract_text_from_page_with_options() {
    // Create a PDF with text
    let mut doc = Document::new();
    let mut page = Page::a4();

    page.text()
        .set_font(Font::Helvetica, 12.0)
        .at(100.0, 700.0)
        .write("Test content for extraction")
        .unwrap();

    doc.add_page(page);

    // Save to temporary file
    let temp_dir = TempDir::new().unwrap();
    let pdf_path = temp_dir.path().join("options_test.pdf");
    doc.save(&pdf_path).unwrap();

    // Open document
    let pdf_doc = PdfReader::open_document(&pdf_path).unwrap();

    // Test with custom space_threshold
    let options = ExtractionOptions {
        space_threshold: 0.4,
        preserve_layout: true,
        ..Default::default()
    };

    // Use the new convenience method
    let extracted = pdf_doc
        .extract_text_from_page_with_options(0, options)
        .unwrap();

    // Verify extraction worked
    assert!(extracted.text.contains("Test content for extraction"));
    assert!(!extracted.fragments.is_empty());
}