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
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
use super::*;
use crate::util;
use crate::util::ByteBuffer;
use crate::LavaTorrentError;
use std::borrow::Cow;
use std::collections::HashMap;
use std::fs::File;
use std::io::{BufReader, Read};
use std::iter::FromIterator;
use std::path::Path;

impl BencodeElem {
    /// Parse `bytes` and return all `BencodeElem` found.
    ///
    /// If `bytes` is empty, then `Ok(vec)` will be returned, but
    /// `vec` would be empty as well.
    ///
    /// If `bytes` contains any malformed bencode, or if any other
    /// error is encountered (e.g. `IOError`), then `Err(error)`
    /// will be returned.
    pub fn from_bytes<B>(bytes: B) -> Result<Vec<BencodeElem>, LavaTorrentError>
    where
        B: AsRef<[u8]>,
    {
        let mut bytes = ByteBuffer::new(bytes.as_ref());
        let mut elements = Vec::new();

        while !bytes.is_empty() {
            let element = BencodeElem::parse(&mut bytes)?;
            elements.push(element);
        }

        Ok(elements)
    }

    /// Parse the content of the file at `path` and return all `BencodeElem` found.
    ///
    /// If the file at `path` is empty, then `Ok(vec)` will be returned, but
    /// `vec` would be empty as well.
    ///
    /// If the file at `path` contains any malformed bencode, or if any other
    /// error is encountered (e.g. `IOError`), then `Err(error)`
    /// will be returned.
    pub fn from_file<P>(path: P) -> Result<Vec<BencodeElem>, LavaTorrentError>
    where
        P: AsRef<Path>,
    {
        let file = File::open(&path)?;
        let mut bytes = Vec::new();

        BufReader::new(file).read_to_end(&mut bytes)?;
        Self::from_bytes(bytes)
    }

    fn peek_byte(bytes: &mut ByteBuffer) -> Result<u8, LavaTorrentError> {
        match bytes.peek() {
            Some(&byte) => Ok(byte),
            None => Err(LavaTorrentError::MalformedBencode(Cow::Borrowed(
                "Expected more bytes, but none found.",
            ))),
        }
    }

    fn parse(bytes: &mut ByteBuffer) -> Result<BencodeElem, LavaTorrentError> {
        match Self::peek_byte(bytes)? {
            DICTIONARY_PREFIX => {
                bytes.advance(1);
                Ok(Self::decode_dictionary(bytes)?)
            }
            LIST_PREFIX => {
                bytes.advance(1);
                Ok(Self::decode_list(bytes)?)
            }
            INTEGER_PREFIX => {
                bytes.advance(1);
                Ok(Self::decode_integer(bytes, INTEGER_POSTFIX)?)
            }
            _ => Ok(Self::decode_string(bytes)?),
        }
    }

    fn decode_dictionary(bytes: &mut ByteBuffer) -> Result<BencodeElem, LavaTorrentError> {
        let mut entries = Vec::new();

        while Self::peek_byte(bytes)? != DICTIONARY_POSTFIX {
            // more to parse
            match Self::decode_bytes(bytes) {
                Ok(BencodeElem::Bytes(key)) => entries.push((key, Self::parse(bytes)?)),
                Ok(_) => {
                    return Err(LavaTorrentError::MalformedBencode(Cow::Borrowed(
                        "Non-string dictionary key.",
                    )));
                }
                Err(e) => return Err(e),
            }
        }
        bytes.advance(1); // consume the postfix

        // check that the dictionary is sorted
        for (i, j) in (1..entries.len()).enumerate() {
            let ((k1, _), (k2, _)) = (&entries[i], &entries[j]);
            // "sorted as raw strings, not alphanumerics"
            if k1 > k2 {
                return Err(LavaTorrentError::MalformedBencode(Cow::Borrowed(
                    "A dictionary is not properly sorted.",
                )));
            }
        }

        // convert to Dictionary if possible
        let mut entries2 = Vec::new();
        for (k, v) in &entries {
            match String::from_utf8(k.to_owned()) {
                Ok(s) => entries2.push((s, v.to_owned())),
                Err(_) => {
                    return Ok(BencodeElem::RawDictionary(HashMap::from_iter(
                        entries.into_iter(),
                    )));
                }
            }
        }
        Ok(BencodeElem::Dictionary(HashMap::from_iter(
            entries2.into_iter(),
        )))
    }

    fn decode_list(bytes: &mut ByteBuffer) -> Result<BencodeElem, LavaTorrentError> {
        let mut list = Vec::new();

        while Self::peek_byte(bytes)? != LIST_POSTFIX {
            // more to parse
            list.push(Self::parse(bytes)?);
        }
        bytes.advance(1); //consume the postfix

        Ok(BencodeElem::List(list))
    }

    fn decode_integer(
        bytes: &mut ByteBuffer,
        delimiter: u8,
    ) -> Result<BencodeElem, LavaTorrentError> {
        let old_pos = bytes.pos();
        let read: Vec<u8> = bytes.take_while(|&&b| b != delimiter).cloned().collect();
        let bytes_read = bytes.pos() - old_pos;

        if read.len() == bytes_read {
            Err(LavaTorrentError::MalformedBencode(Cow::Borrowed(
                "Integer delimiter not found.",
            )))
        } else {
            match String::from_utf8(read) {
                Ok(int_string) => {
                    if int_string.starts_with("-0") {
                        Err(LavaTorrentError::MalformedBencode(Cow::Borrowed(
                            "-0 found.",
                        )))
                    } else if (int_string.starts_with('0')) && (int_string.len() != 1) {
                        Err(LavaTorrentError::MalformedBencode(Cow::Borrowed(
                            "Integer with leading zero(s) found.",
                        )))
                    } else {
                        match int_string.parse() {
                            Ok(int) => Ok(BencodeElem::Integer(int)),
                            Err(_) => Err(LavaTorrentError::MalformedBencode(Cow::Owned(format!(
                                "Input contains invalid integer: {}.",
                                int_string
                            )))),
                        }
                    }
                }
                Err(_) => Err(LavaTorrentError::MalformedBencode(Cow::Borrowed(
                    "Input contains invalid UTF-8.",
                ))),
            }
        }
    }

    fn decode_string(bytes: &mut ByteBuffer) -> Result<BencodeElem, LavaTorrentError> {
        match Self::decode_bytes(bytes) {
            Ok(BencodeElem::Bytes(string_bytes)) => match String::from_utf8(string_bytes) {
                Ok(string) => Ok(BencodeElem::String(string)),
                Err(e) => Ok(BencodeElem::Bytes(e.into_bytes())),
            },
            Ok(_) => panic!("decode_bytes() did not return bytes."),
            Err(e) => Err(e),
        }
    }

    fn decode_bytes(bytes: &mut ByteBuffer) -> Result<BencodeElem, LavaTorrentError> {
        match Self::decode_integer(bytes, STRING_DELIMITER) {
            Ok(BencodeElem::Integer(len)) => {
                if let Ok(len) = util::i64_to_usize(len) {
                    Ok(BencodeElem::Bytes(bytes.take(len).cloned().collect()))
                } else {
                    Err(LavaTorrentError::MalformedBencode(Cow::Borrowed(
                        "A string's length does not fit into `usize`.",
                    )))
                }
            }
            Ok(_) => panic!("decode_integer() did not return an integer."),
            Err(e) => Err(e),
        }
    }
}

#[cfg(test)]
mod bencode_elem_read_tests {
    // @note: `from_bytes()` and `from_file()` are not tested
    // as they are best left to integration tests (in `tests/`,
    // implicitly tested with `Torrent::read_from_bytes()`
    // and `Torrent::read_from_file()`).
    use super::*;

    #[test]
    fn peek_byte_ok() {
        let bytes = "a".as_bytes();
        assert_eq!(
            BencodeElem::peek_byte(&mut ByteBuffer::new(bytes)).unwrap(),
            b'a'
        );
    }

    #[test]
    fn peek_byte_err() {
        let bytes = "".as_bytes();
        match BencodeElem::peek_byte(&mut ByteBuffer::new(bytes)) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Expected more bytes, but none found.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_integer_ok() {
        let bytes = "0e".as_bytes();
        assert_eq!(
            BencodeElem::decode_integer(&mut ByteBuffer::new(bytes), INTEGER_POSTFIX).unwrap(),
            bencode_elem!(0_i64)
        );
    }

    #[test]
    fn decode_integer_ok_2() {
        let bytes = "-4e".as_bytes();
        assert_eq!(
            BencodeElem::decode_integer(&mut ByteBuffer::new(bytes), INTEGER_POSTFIX).unwrap(),
            bencode_elem!(-4_i64)
        );
    }

    #[test]
    fn decode_integer_invalid_int() {
        let bytes = "4ae".as_bytes();
        match BencodeElem::decode_integer(&mut ByteBuffer::new(bytes), INTEGER_POSTFIX) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Input contains invalid integer: 4a.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_integer_invalid_int_2() {
        let bytes = "--1e".as_bytes();
        match BencodeElem::decode_integer(&mut ByteBuffer::new(bytes), INTEGER_POSTFIX) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Input contains invalid integer: --1.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_integer_invalid_int_3() {
        let bytes = "03e".as_bytes();
        match BencodeElem::decode_integer(&mut ByteBuffer::new(bytes), INTEGER_POSTFIX) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Integer with leading zero(s) found.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_integer_invalid_int_4() {
        let bytes = "-0e".as_bytes();
        match BencodeElem::decode_integer(&mut ByteBuffer::new(bytes), INTEGER_POSTFIX) {
            Err(LavaTorrentError::MalformedBencode(m)) => assert_eq!(m, "-0 found."),
            _ => panic!(),
        }
    }

    #[test]
    fn decode_integer_invalid_int_5() {
        let bytes = "-01e".as_bytes();
        match BencodeElem::decode_integer(&mut ByteBuffer::new(bytes), INTEGER_POSTFIX) {
            Err(LavaTorrentError::MalformedBencode(m)) => assert_eq!(m, "-0 found."),
            _ => panic!(),
        }
    }

    #[test]
    fn decode_integer_overflow() {
        let bytes = "9223372036854775808e".as_bytes();
        match BencodeElem::decode_integer(&mut ByteBuffer::new(bytes), INTEGER_POSTFIX) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Input contains invalid integer: 9223372036854775808.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_integer_no_delimiter() {
        let bytes = "9223372036854775807".as_bytes();
        match BencodeElem::decode_integer(&mut ByteBuffer::new(bytes), INTEGER_POSTFIX) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Integer delimiter not found.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_integer_bad_utf8() {
        let bytes = vec![b'4', 0xff, 0xf8, INTEGER_POSTFIX];
        match BencodeElem::decode_integer(&mut ByteBuffer::new(&bytes), INTEGER_POSTFIX) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Input contains invalid UTF-8.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_string_ok() {
        let bytes = "4:spam".as_bytes();
        assert_eq!(
            BencodeElem::decode_string(&mut ByteBuffer::new(bytes)).unwrap(),
            bencode_elem!("spam")
        );
    }

    #[test]
    fn decode_string_invalid_len() {
        let bytes = "a:spam".as_bytes();
        match BencodeElem::decode_string(&mut ByteBuffer::new(bytes)) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Input contains invalid integer: a.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_string_no_len() {
        let bytes = ":spam".as_bytes();
        match BencodeElem::decode_string(&mut ByteBuffer::new(bytes)) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Input contains invalid integer: .");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_string_negative_len() {
        let bytes = "-1:spam".as_bytes();
        match BencodeElem::decode_string(&mut ByteBuffer::new(bytes)) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "A string's length does not fit into `usize`.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_string_no_delimiter() {
        let bytes = "4spam".as_bytes();
        match BencodeElem::decode_string(&mut ByteBuffer::new(bytes)) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Integer delimiter not found.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_string_no_delimiter_2() {
        let bytes = "456".as_bytes();
        match BencodeElem::decode_string(&mut ByteBuffer::new(bytes)) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Integer delimiter not found.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_string_as_bytes() {
        let bytes = vec![b'4', b':', 0xff, 0xf8, 0xff, 0xee]; // bad UTF8 gives bytes
        assert_eq!(
            BencodeElem::decode_string(&mut ByteBuffer::new(&bytes)).unwrap(),
            bencode_elem!((0xff, 0xf8, 0xff, 0xee))
        );
    }

    #[test]
    fn decode_list_ok() {
        let bytes = "4:spam4:eggse".as_bytes();
        assert_eq!(
            BencodeElem::decode_list(&mut ByteBuffer::new(bytes)).unwrap(),
            bencode_elem!(["spam", "eggs"])
        );
    }

    #[test]
    fn decode_list_nested() {
        let bytes = "4:spaml6:cheesee4:eggse".as_bytes();
        assert_eq!(
            BencodeElem::decode_list(&mut ByteBuffer::new(bytes)).unwrap(),
            bencode_elem!(["spam", ["cheese"], "eggs"])
        );
    }

    #[test]
    fn decode_list_empty() {
        let bytes = "e".as_bytes();
        assert_eq!(
            BencodeElem::decode_list(&mut ByteBuffer::new(bytes)).unwrap(),
            bencode_elem!([])
        );
    }

    #[test]
    fn decode_list_bad_structure() {
        let bytes = "4:spaml6:cheese4:eggse".as_bytes();
        match BencodeElem::decode_list(&mut ByteBuffer::new(bytes)) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Expected more bytes, but none found.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_dictionary_ok() {
        let bytes = "3:cow3:moo4:spam4:eggse".as_bytes();
        assert_eq!(
            BencodeElem::decode_dictionary(&mut ByteBuffer::new(bytes)).unwrap(),
            bencode_elem!({ ("cow", "moo"), ("spam", "eggs") })
        );
    }

    #[test]
    fn decode_dictionary_nested() {
        let bytes = "3:cowd3:mooi4ee4:spam4:eggse".as_bytes();
        assert_eq!(
            BencodeElem::decode_dictionary(&mut ByteBuffer::new(bytes)).unwrap(),
            bencode_elem!({ ("cow", { ("moo", 4_i64) }), ("spam", "eggs") })
        );
    }

    #[test]
    fn decode_dictionary_empty() {
        let bytes = "e".as_bytes();
        assert_eq!(
            BencodeElem::decode_dictionary(&mut ByteBuffer::new(bytes)).unwrap(),
            bencode_elem!({})
        );
    }

    #[test]
    fn decode_dictionary_bad_structure() {
        let bytes = "3:cow3:moo4:spame".as_bytes();
        match BencodeElem::decode_dictionary(&mut ByteBuffer::new(bytes)) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Integer delimiter not found.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_dictionary_non_string_key_1() {
        let bytes = "i4e3:moo4:spam4:eggse".as_bytes();
        match BencodeElem::decode_dictionary(&mut ByteBuffer::new(bytes)) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "Input contains invalid integer: i4e3.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_dictionary_not_sorted() {
        let bytes = "3:zoo3:moo4:spam4:eggse".as_bytes();
        match BencodeElem::decode_dictionary(&mut ByteBuffer::new(bytes)) {
            Err(LavaTorrentError::MalformedBencode(m)) => {
                assert_eq!(m, "A dictionary is not properly sorted.");
            }
            _ => panic!(),
        }
    }

    #[test]
    fn decode_raw_dictionary_ok() {
        let mut bytes = vec![b'4', b':', 0xff, 0xf8, 0xff, 0xee];
        bytes.extend("3:mooe".as_bytes());

        assert_eq!(
            BencodeElem::decode_dictionary(&mut ByteBuffer::new(&bytes)).unwrap(),
            bencode_elem!(r{ ([0xff, 0xf8, 0xff, 0xee], "moo") })
        );
    }

    #[test]
    fn decode_raw_dictionary_ok_2() {
        // mix valid utf8 strings and invalid utf8 strings
        let mut bytes = "3:zoo3:moo".as_bytes().to_owned();
        bytes.extend(vec![b'4', b':', 0xff, 0xf8, 0xff, 0xee]);
        bytes.extend("4:eggse".as_bytes());

        assert_eq!(
            BencodeElem::decode_dictionary(&mut ByteBuffer::new(&bytes)).unwrap(),
            bencode_elem!(r{ ([b'z', b'o', b'o'], "moo"), ([0xff, 0xf8, 0xff, 0xee], "eggs") })
        );
    }

    // @note: `parse()` is called by other `decode_*()` methods, so
    // it is implicitly tested by other tests. Still, the following tests
    // are provided. Though these tests are not as comprehensive.
    #[test]
    fn parse_integer_ok() {
        let bytes = "i0e".as_bytes();
        assert_eq!(
            BencodeElem::parse(&mut ByteBuffer::new(bytes)).unwrap(),
            bencode_elem!(0_i64)
        );
    }

    #[test]
    fn parse_string_ok() {
        let bytes = "4:spam".as_bytes();
        assert_eq!(
            BencodeElem::parse(&mut ByteBuffer::new(bytes)).unwrap(),
            bencode_elem!("spam")
        );
    }

    #[test]
    fn parse_bytes_ok() {
        let bytes = vec![b'4', b':', 0xff, 0xf8, 0xff, 0xee]; // bad UTF8 gives bytes
        assert_eq!(
            BencodeElem::parse(&mut ByteBuffer::new(&bytes)).unwrap(),
            bencode_elem!((0xff, 0xf8, 0xff, 0xee))
        );
    }

    #[test]
    fn parse_list_ok() {
        let bytes = "l4:spam4:eggse".as_bytes();
        assert_eq!(
            BencodeElem::parse(&mut ByteBuffer::new(bytes)).unwrap(),
            bencode_elem!(["spam", "eggs"])
        );
    }

    #[test]
    fn parse_dictionary_ok() {
        let bytes = "d3:cow3:moo4:spam4:eggse".as_bytes();
        assert_eq!(
            BencodeElem::parse(&mut ByteBuffer::new(bytes)).unwrap(),
            bencode_elem!({ ("cow", "moo"), ("spam", "eggs") })
        );
    }
}