ccdown 0.6.5

A polite and user-friendly downloader for Common Crawl data.
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
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
use flate2::write::GzEncoder;
use flate2::Compression;
use std::io::Write;
use std::path::Path;
use tempfile::TempDir;
use wiremock::matchers::{method, path};
use wiremock::{Mock, MockServer, ResponseTemplate};

use ccdown::download::{download, download_paths, DownloadOptions};

/// Helper: create a gzip file containing lines (simulating a .paths.gz file)
fn create_paths_gz(dir: &Path, filename: &str, lines: &[&str]) -> std::path::PathBuf {
    let file_path = dir.join(filename);
    let file = std::fs::File::create(&file_path).unwrap();
    let mut encoder = GzEncoder::new(file, Compression::default());
    for line in lines {
        writeln!(encoder, "{}", line).unwrap();
    }
    encoder.finish().unwrap();
    file_path
}

#[tokio::test]
async fn download_paths_fetches_gz_file() {
    let server = MockServer::start().await;
    let body = b"fake gzip content for paths";

    // Mock HEAD (for status check)
    Mock::given(method("HEAD"))
        .and(path("/crawl-data/CC-MAIN-2025-08/warc.paths.gz"))
        .respond_with(ResponseTemplate::new(200).set_body_bytes(body.to_vec()))
        .mount(&server)
        .await;

    // Mock GET (for actual download)
    Mock::given(method("GET"))
        .and(path("/crawl-data/CC-MAIN-2025-08/warc.paths.gz"))
        .respond_with(ResponseTemplate::new(200).set_body_bytes(body.to_vec()))
        .mount(&server)
        .await;

    let dst = TempDir::new().unwrap();

    let options = DownloadOptions {
        snapshot: "CC-MAIN-2025-08".to_string(),
        data_type: "warc",
        dst: dst.path(),
        base_url: Some(format!("{}/", server.uri())),
        max_retries: 1,
        ..Default::default()
    };

    download_paths(options).await.unwrap();

    let downloaded = dst.path().join("warc.paths.gz");
    assert!(downloaded.exists(), "paths file should be downloaded");
    let content = std::fs::read(&downloaded).unwrap();
    assert_eq!(content, body);
}

#[tokio::test]
async fn download_paths_reformats_news_snapshot() {
    let server = MockServer::start().await;
    let body = b"news paths content";

    // CC-NEWS-2025-01 should become CC-NEWS/2025/01 in the URL
    Mock::given(method("HEAD"))
        .and(path("/crawl-data/CC-NEWS/2025/01/warc.paths.gz"))
        .respond_with(ResponseTemplate::new(200).set_body_bytes(body.to_vec()))
        .mount(&server)
        .await;

    Mock::given(method("GET"))
        .and(path("/crawl-data/CC-NEWS/2025/01/warc.paths.gz"))
        .respond_with(ResponseTemplate::new(200).set_body_bytes(body.to_vec()))
        .mount(&server)
        .await;

    let dst = TempDir::new().unwrap();

    let options = DownloadOptions {
        snapshot: "CC-NEWS-2025-01".to_string(),
        data_type: "warc",
        dst: dst.path(),
        base_url: Some(format!("{}/", server.uri())),
        max_retries: 1,
        ..Default::default()
    };

    download_paths(options).await.unwrap();

    let downloaded = dst.path().join("warc.paths.gz");
    assert!(downloaded.exists());
    assert_eq!(std::fs::read(&downloaded).unwrap(), body);
}

#[tokio::test]
async fn download_paths_returns_error_on_404() {
    let server = MockServer::start().await;

    Mock::given(method("HEAD"))
        .and(path("/crawl-data/CC-MAIN-2099-01/warc.paths.gz"))
        .respond_with(ResponseTemplate::new(404))
        .mount(&server)
        .await;

    let dst = TempDir::new().unwrap();

    let options = DownloadOptions {
        snapshot: "CC-MAIN-2099-01".to_string(),
        data_type: "warc",
        dst: dst.path(),
        base_url: Some(format!("{}/", server.uri())),
        max_retries: 1,
        ..Default::default()
    };

    let result = download_paths(options).await;
    assert!(result.is_err());
    let err_msg = result.unwrap_err().to_string();
    assert!(
        err_msg.contains("Doesn't seem to exist"),
        "expected 404 message, got: {}",
        err_msg
    );
}

#[tokio::test]
async fn download_fetches_files_from_paths_gz() {
    let server = MockServer::start().await;

    let file_a_body = b"contents of file A";
    let file_b_body = b"contents of file B";

    // Mock HEAD + GET for two files
    for (file_path, body) in [
        ("data/fileA.warc.gz", file_a_body.as_slice()),
        ("data/fileB.warc.gz", file_b_body.as_slice()),
    ] {
        Mock::given(method("HEAD"))
            .and(path(format!("/{}", file_path)))
            .respond_with(
                ResponseTemplate::new(200)
                    .insert_header("content-length", body.len().to_string().as_str())
                    .set_body_bytes(body.to_vec()),
            )
            .mount(&server)
            .await;

        Mock::given(method("GET"))
            .and(path(format!("/{}", file_path)))
            .respond_with(ResponseTemplate::new(200).set_body_bytes(body.to_vec()))
            .mount(&server)
            .await;
    }

    let tmp = TempDir::new().unwrap();
    let dst = TempDir::new().unwrap();

    // Create a .paths.gz file with relative paths (no leading slash, no base URL)
    let paths_file = create_paths_gz(
        tmp.path(),
        "warc.paths.gz",
        &["data/fileA.warc.gz", "data/fileB.warc.gz"],
    );

    let options = DownloadOptions {
        paths: &paths_file,
        dst: dst.path(),
        base_url: Some(format!("{}/", server.uri())),
        max_retries: 1,
        threads: 2,
        ..Default::default()
    };

    download(options).await.unwrap();

    // Files should be at dst/data/fileA.warc.gz and dst/data/fileB.warc.gz
    let file_a = dst.path().join("data/fileA.warc.gz");
    let file_b = dst.path().join("data/fileB.warc.gz");
    assert!(file_a.exists(), "fileA should be downloaded");
    assert!(file_b.exists(), "fileB should be downloaded");
    assert_eq!(std::fs::read(&file_a).unwrap(), file_a_body);
    assert_eq!(std::fs::read(&file_b).unwrap(), file_b_body);
}

#[tokio::test]
async fn download_files_only_flattens_structure() {
    let server = MockServer::start().await;
    let body = b"flat file content";

    Mock::given(method("HEAD"))
        .and(path("/crawl-data/segment/1234/file.warc.gz"))
        .respond_with(
            ResponseTemplate::new(200)
                .insert_header("content-length", body.len().to_string().as_str())
                .set_body_bytes(body.to_vec()),
        )
        .mount(&server)
        .await;

    Mock::given(method("GET"))
        .and(path("/crawl-data/segment/1234/file.warc.gz"))
        .respond_with(ResponseTemplate::new(200).set_body_bytes(body.to_vec()))
        .mount(&server)
        .await;

    let tmp = TempDir::new().unwrap();
    let dst = TempDir::new().unwrap();

    let paths_file = create_paths_gz(
        tmp.path(),
        "warc.paths.gz",
        &["crawl-data/segment/1234/file.warc.gz"],
    );

    let options = DownloadOptions {
        paths: &paths_file,
        dst: dst.path(),
        base_url: Some(format!("{}/", server.uri())),
        max_retries: 1,
        files_only: true,
        ..Default::default()
    };

    download(options).await.unwrap();

    // files_only should put it directly in dst, not nested
    let flat_file = dst.path().join("file.warc.gz");
    assert!(
        flat_file.exists(),
        "file should be directly in dst with files_only"
    );
    assert_eq!(std::fs::read(&flat_file).unwrap(), body);
}

#[tokio::test]
async fn download_numbered_renames_files() {
    let server = MockServer::start().await;
    let body = b"numbered content";

    Mock::given(method("HEAD"))
        .and(path("/data/some/deep/path.wet.gz"))
        .respond_with(
            ResponseTemplate::new(200)
                .insert_header("content-length", body.len().to_string().as_str())
                .set_body_bytes(body.to_vec()),
        )
        .mount(&server)
        .await;

    Mock::given(method("GET"))
        .and(path("/data/some/deep/path.wet.gz"))
        .respond_with(ResponseTemplate::new(200).set_body_bytes(body.to_vec()))
        .mount(&server)
        .await;

    let tmp = TempDir::new().unwrap();
    let dst = TempDir::new().unwrap();

    let paths_file = create_paths_gz(
        tmp.path(),
        "wet.paths.gz",
        &["data/some/deep/path.wet.gz"],
    );

    let options = DownloadOptions {
        paths: &paths_file,
        dst: dst.path(),
        base_url: Some(format!("{}/", server.uri())),
        max_retries: 1,
        numbered: true,
        ..Default::default()
    };

    download(options).await.unwrap();

    // numbered mode: first file should be 0.txt.gz
    let numbered_file = dst.path().join("0.txt.gz");
    assert!(
        numbered_file.exists(),
        "file should be named 0.txt.gz in numbered mode"
    );
    assert_eq!(std::fs::read(&numbered_file).unwrap(), body);
}

#[tokio::test]
async fn download_strict_mode_aborts_on_404() {
    let server = MockServer::start().await;

    let good_body = b"good file";

    // First file succeeds
    Mock::given(method("HEAD"))
        .and(path("/data/good.warc.gz"))
        .respond_with(
            ResponseTemplate::new(200)
                .insert_header("content-length", good_body.len().to_string().as_str())
                .set_body_bytes(good_body.to_vec()),
        )
        .mount(&server)
        .await;

    Mock::given(method("GET"))
        .and(path("/data/good.warc.gz"))
        .respond_with(ResponseTemplate::new(200).set_body_bytes(good_body.to_vec()))
        .mount(&server)
        .await;

    // Second file 404s
    Mock::given(method("HEAD"))
        .and(path("/data/missing.warc.gz"))
        .respond_with(ResponseTemplate::new(404))
        .mount(&server)
        .await;

    let tmp = TempDir::new().unwrap();
    let dst = TempDir::new().unwrap();

    let paths_file = create_paths_gz(
        tmp.path(),
        "warc.paths.gz",
        &["data/good.warc.gz", "data/missing.warc.gz"],
    );

    let options = DownloadOptions {
        paths: &paths_file,
        dst: dst.path(),
        base_url: Some(format!("{}/", server.uri())),
        max_retries: 1,
        threads: 1, // serialize to make the test deterministic
        strict: true,
        ..Default::default()
    };

    let result = download(options).await;
    assert!(result.is_err(), "strict mode should return error on 404");

    let err = result.unwrap_err();
    assert!(
        err.is_unrecoverable(),
        "error should be marked unrecoverable"
    );
}

#[tokio::test]
async fn download_non_strict_continues_on_404() {
    let server = MockServer::start().await;

    let good_body = b"good file content";

    // good file
    Mock::given(method("HEAD"))
        .and(path("/data/good.warc.gz"))
        .respond_with(
            ResponseTemplate::new(200)
                .insert_header("content-length", good_body.len().to_string().as_str())
                .set_body_bytes(good_body.to_vec()),
        )
        .mount(&server)
        .await;

    Mock::given(method("GET"))
        .and(path("/data/good.warc.gz"))
        .respond_with(ResponseTemplate::new(200).set_body_bytes(good_body.to_vec()))
        .mount(&server)
        .await;

    // missing file
    Mock::given(method("HEAD"))
        .and(path("/data/missing.warc.gz"))
        .respond_with(ResponseTemplate::new(404))
        .mount(&server)
        .await;

    let tmp = TempDir::new().unwrap();
    let dst = TempDir::new().unwrap();

    let paths_file = create_paths_gz(
        tmp.path(),
        "warc.paths.gz",
        &["data/good.warc.gz", "data/missing.warc.gz"],
    );

    let options = DownloadOptions {
        paths: &paths_file,
        dst: dst.path(),
        base_url: Some(format!("{}/", server.uri())),
        max_retries: 1,
        threads: 2,
        strict: false,
        ..Default::default()
    };

    let result = download(options).await;
    assert!(
        result.is_ok(),
        "non-strict mode should succeed despite 404: {:?}",
        result
    );

    // The good file should still have been downloaded
    let good_file = dst.path().join("data/good.warc.gz");
    assert!(good_file.exists(), "good file should still be downloaded");
    assert_eq!(std::fs::read(&good_file).unwrap(), good_body);
}

#[tokio::test]
async fn download_strict_mode_aborts_on_403() {
    let server = MockServer::start().await;

    Mock::given(method("HEAD"))
        .and(path("/data/forbidden.warc.gz"))
        .respond_with(ResponseTemplate::new(403))
        .mount(&server)
        .await;

    let tmp = TempDir::new().unwrap();
    let dst = TempDir::new().unwrap();

    let paths_file = create_paths_gz(
        tmp.path(),
        "warc.paths.gz",
        &["data/forbidden.warc.gz"],
    );

    let options = DownloadOptions {
        paths: &paths_file,
        dst: dst.path(),
        base_url: Some(format!("{}/", server.uri())),
        max_retries: 1,
        strict: true,
        ..Default::default()
    };

    let result = download(options).await;
    assert!(result.is_err());
    let err = result.unwrap_err();
    assert!(err.is_unrecoverable());
    assert!(err.to_string().contains("403"));
}