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
macro_rules! define_set {
    ($name:ident, $builder_mod:ident, $text_ty:ty, $as_bytes:expr,
     $(#[$doc_regexset_example:meta])* ) => {
        pub mod $name {
            use std::fmt;
            use std::iter;
            use std::slice;
            use std::vec;

            use error::Error;
            use exec::Exec;
            use re_builder::$builder_mod::RegexSetBuilder;
            use re_trait::RegularExpression;

/// Match multiple (possibly overlapping) regular expressions in a single scan.
///
/// A regex set corresponds to the union of two or more regular expressions.
/// That is, a regex set will match text where at least one of its
/// constituent regular expressions matches. A regex set as its formulated here
/// provides a touch more power: it will also report *which* regular
/// expressions in the set match. Indeed, this is the key difference between
/// regex sets and a single `Regex` with many alternates, since only one
/// alternate can match at a time.
///
/// For example, consider regular expressions to match email addresses and
/// domains: `[a-z]+@[a-z]+\.(com|org|net)` and `[a-z]+\.(com|org|net)`. If a
/// regex set is constructed from those regexes, then searching the text
/// `foo@example.com` will report both regexes as matching. Of course, one
/// could accomplish this by compiling each regex on its own and doing two
/// searches over the text. The key advantage of using a regex set is that it
/// will report the matching regexes using a *single pass through the text*.
/// If one has hundreds or thousands of regexes to match repeatedly (like a URL
/// router for a complex web application or a user agent matcher), then a regex
/// set can realize huge performance gains.
///
/// # Example
///
/// This shows how the above two regexes (for matching email addresses and
/// domains) might work:
///
$(#[$doc_regexset_example])*
///
/// Note that it would be possible to adapt the above example to using `Regex`
/// with an expression like:
///
/// ```ignore
/// (?P<email>[a-z]+@(?P<email_domain>[a-z]+[.](com|org|net)))|(?P<domain>[a-z]+[.](com|org|net))
/// ```
///
/// After a match, one could then inspect the capture groups to figure out
/// which alternates matched. The problem is that it is hard to make this
/// approach scale when there are many regexes since the overlap between each
/// alternate isn't always obvious to reason about.
///
/// # Limitations
///
/// Regex sets are limited to answering the following two questions:
///
/// 1. Does any regex in the set match?
/// 2. If so, which regexes in the set match?
///
/// As with the main `Regex` type, it is cheaper to ask (1) instead of (2)
/// since the matching engines can stop after the first match is found.
///
/// Other features like finding the location of successive matches or their
/// sub-captures aren't supported. If you need this functionality, the
/// recommended approach is to compile each regex in the set independently and
/// selectively match them based on which regexes in the set matched.
///
/// # Performance
///
/// A `RegexSet` has the same performance characteristics as `Regex`. Namely,
/// search takes `O(mn)` time, where `m` is proportional to the size of the
/// regex set and `n` is proportional to the length of the search text.
#[derive(Clone)]
pub struct RegexSet(Exec);

impl RegexSet {
    /// Create a new regex set with the given regular expressions.
    ///
    /// This takes an iterator of `S`, where `S` is something that can produce
    /// a `&str`. If any of the strings in the iterator are not valid regular
    /// expressions, then an error is returned.
    ///
    /// # Example
    ///
    /// Create a new regex set from an iterator of strings:
    ///
    /// ```rust
    /// # use regex::RegexSet;
    /// let set = RegexSet::new(&[r"\w+", r"\d+"]).unwrap();
    /// assert!(set.is_match("foo"));
    /// ```
    pub fn new<I, S>(exprs: I) -> Result<RegexSet, Error>
            where S: AsRef<str>, I: IntoIterator<Item=S> {
        RegexSetBuilder::new(exprs).build()
    }

    /// Create a new empty regex set.
    ///
    /// # Example
    ///
    /// ```rust
    /// # use regex::RegexSet;
    /// let set = RegexSet::empty();
    /// assert!(set.is_empty());
    /// ```
    pub fn empty() -> RegexSet {
        RegexSetBuilder::new(&[""; 0]).build().unwrap()
    }

    /// Returns true if and only if one of the regexes in this set matches
    /// the text given.
    ///
    /// This method should be preferred if you only need to test whether any
    /// of the regexes in the set should match, but don't care about *which*
    /// regexes matched. This is because the underlying matching engine will
    /// quit immediately after seeing the first match instead of continuing to
    /// find all matches.
    ///
    /// Note that as with searches using `Regex`, the expression is unanchored
    /// by default. That is, if the regex does not start with `^` or `\A`, or
    /// end with `$` or `\z`, then it is permitted to match anywhere in the
    /// text.
    ///
    /// # Example
    ///
    /// Tests whether a set matches some text:
    ///
    /// ```rust
    /// # use regex::RegexSet;
    /// let set = RegexSet::new(&[r"\w+", r"\d+"]).unwrap();
    /// assert!(set.is_match("foo"));
    /// assert!(!set.is_match("☃"));
    /// ```
    pub fn is_match(&self, text: $text_ty) -> bool {
        self.is_match_at(text, 0)
    }

    /// Returns the same as is_match, but starts the search at the given
    /// offset.
    ///
    /// The significance of the starting point is that it takes the surrounding
    /// context into consideration. For example, the `\A` anchor can only
    /// match when `start == 0`.
    #[doc(hidden)]
    pub fn is_match_at(&self, text: $text_ty, start: usize) -> bool {
        self.0.searcher().is_match_at($as_bytes(text), start)
    }

    /// Returns the set of regular expressions that match in the given text.
    ///
    /// The set returned contains the index of each regular expression that
    /// matches in the given text. The index is in correspondence with the
    /// order of regular expressions given to `RegexSet`'s constructor.
    ///
    /// The set can also be used to iterate over the matched indices.
    ///
    /// Note that as with searches using `Regex`, the expression is unanchored
    /// by default. That is, if the regex does not start with `^` or `\A`, or
    /// end with `$` or `\z`, then it is permitted to match anywhere in the
    /// text.
    ///
    /// # Example
    ///
    /// Tests which regular expressions match the given text:
    ///
    /// ```rust
    /// # use regex::RegexSet;
    /// let set = RegexSet::new(&[
    ///     r"\w+",
    ///     r"\d+",
    ///     r"\pL+",
    ///     r"foo",
    ///     r"bar",
    ///     r"barfoo",
    ///     r"foobar",
    /// ]).unwrap();
    /// let matches: Vec<_> = set.matches("foobar").into_iter().collect();
    /// assert_eq!(matches, vec![0, 2, 3, 4, 6]);
    ///
    /// // You can also test whether a particular regex matched:
    /// let matches = set.matches("foobar");
    /// assert!(!matches.matched(5));
    /// assert!(matches.matched(6));
    /// ```
    pub fn matches(&self, text: $text_ty) -> SetMatches {
        let mut matches = vec![false; self.0.regex_strings().len()];
        let any = self.read_matches_at(&mut matches, text, 0);
        SetMatches {
            matched_any: any,
            matches: matches,
        }
    }

    /// Returns the same as matches, but starts the search at the given
    /// offset and stores the matches into the slice given.
    ///
    /// The significance of the starting point is that it takes the surrounding
    /// context into consideration. For example, the `\A` anchor can only
    /// match when `start == 0`.
    ///
    /// `matches` must have a length that is at least the number of regexes
    /// in this set.
    ///
    /// This method returns true if and only if at least one member of
    /// `matches` is true after executing the set against `text`.
    #[doc(hidden)]
    pub fn read_matches_at(
        &self,
        matches: &mut [bool],
        text: $text_ty,
        start: usize,
    ) -> bool {
        self.0.searcher().many_matches_at(matches, $as_bytes(text), start)
    }

    /// Returns the total number of regular expressions in this set.
    pub fn len(&self) -> usize {
        self.0.regex_strings().len()
    }

    /// Returns `true` if this set contains no regular expressions.
    pub fn is_empty(&self) -> bool {
        self.0.regex_strings().is_empty()
    }

    /// Returns the patterns that this set will match on.
    ///
    /// This function can be used to determine the pattern for a match. The
    /// slice returned has exactly as many patterns givens to this regex set,
    /// and the order of the slice is the same as the order of the patterns
    /// provided to the set.
    ///
    /// # Example
    ///
    /// ```rust
    /// # use regex::RegexSet;
    /// let set = RegexSet::new(&[
    ///     r"\w+",
    ///     r"\d+",
    ///     r"\pL+",
    ///     r"foo",
    ///     r"bar",
    ///     r"barfoo",
    ///     r"foobar",
    /// ]).unwrap();
    /// let matches: Vec<_> = set
    ///     .matches("foobar")
    ///     .into_iter()
    ///     .map(|match_idx| &set.patterns()[match_idx])
    ///     .collect();
    /// assert_eq!(matches, vec![r"\w+", r"\pL+", r"foo", r"bar", r"foobar"]);
    /// ```
    pub fn patterns(&self) -> &[String] {
        self.0.regex_strings()
    }
}

/// A set of matches returned by a regex set.
#[derive(Clone, Debug)]
pub struct SetMatches {
    matched_any: bool,
    matches: Vec<bool>,
}

impl SetMatches {
    /// Whether this set contains any matches.
    pub fn matched_any(&self) -> bool {
        self.matched_any
    }

    /// Whether the regex at the given index matched.
    ///
    /// The index for a regex is determined by its insertion order upon the
    /// initial construction of a `RegexSet`, starting at `0`.
    ///
    /// # Panics
    ///
    /// If `regex_index` is greater than or equal to `self.len()`.
    pub fn matched(&self, regex_index: usize) -> bool {
        self.matches[regex_index]
    }

    /// The total number of regexes in the set that created these matches.
    pub fn len(&self) -> usize {
        self.matches.len()
    }

    /// Returns an iterator over indexes in the regex that matched.
    ///
    /// This will always produces matches in ascending order of index, where
    /// the index corresponds to the index of the regex that matched with
    /// respect to its position when initially building the set.
    pub fn iter(&self) -> SetMatchesIter {
        SetMatchesIter((&*self.matches).into_iter().enumerate())
    }
}

impl IntoIterator for SetMatches {
    type IntoIter = SetMatchesIntoIter;
    type Item = usize;

    fn into_iter(self) -> Self::IntoIter {
        SetMatchesIntoIter(self.matches.into_iter().enumerate())
    }
}

impl<'a> IntoIterator for &'a SetMatches {
    type IntoIter = SetMatchesIter<'a>;
    type Item = usize;

    fn into_iter(self) -> Self::IntoIter {
        self.iter()
    }
}

/// An owned iterator over the set of matches from a regex set.
///
/// This will always produces matches in ascending order of index, where the
/// index corresponds to the index of the regex that matched with respect to
/// its position when initially building the set.
pub struct SetMatchesIntoIter(iter::Enumerate<vec::IntoIter<bool>>);

impl Iterator for SetMatchesIntoIter {
    type Item = usize;

    fn next(&mut self) -> Option<usize> {
        loop {
            match self.0.next() {
                None => return None,
                Some((_, false)) => {}
                Some((i, true)) => return Some(i),
            }
        }
    }

    fn size_hint(&self) -> (usize, Option<usize>) {
        self.0.size_hint()
    }
}

impl DoubleEndedIterator for SetMatchesIntoIter {
    fn next_back(&mut self) -> Option<usize> {
        loop {
            match self.0.next_back() {
                None => return None,
                Some((_, false)) => {}
                Some((i, true)) => return Some(i),
            }
        }
    }
}

/// A borrowed iterator over the set of matches from a regex set.
///
/// The lifetime `'a` refers to the lifetime of a `SetMatches` value.
///
/// This will always produces matches in ascending order of index, where the
/// index corresponds to the index of the regex that matched with respect to
/// its position when initially building the set.
#[derive(Clone)]
pub struct SetMatchesIter<'a>(iter::Enumerate<slice::Iter<'a, bool>>);

impl<'a> Iterator for SetMatchesIter<'a> {
    type Item = usize;

    fn next(&mut self) -> Option<usize> {
        loop {
            match self.0.next() {
                None => return None,
                Some((_, &false)) => {}
                Some((i, &true)) => return Some(i),
            }
        }
    }

    fn size_hint(&self) -> (usize, Option<usize>) {
        self.0.size_hint()
    }
}

impl<'a> DoubleEndedIterator for SetMatchesIter<'a> {
    fn next_back(&mut self) -> Option<usize> {
        loop {
            match self.0.next_back() {
                None => return None,
                Some((_, &false)) => {}
                Some((i, &true)) => return Some(i),
            }
        }
    }
}

#[doc(hidden)]
impl From<Exec> for RegexSet {
    fn from(exec: Exec) -> Self {
        RegexSet(exec)
    }
}

impl fmt::Debug for RegexSet {
    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
        write!(f, "RegexSet({:?})", self.0.regex_strings())
    }
}

#[allow(dead_code)] fn as_bytes_str(text: &str) -> &[u8] { text.as_bytes() }
#[allow(dead_code)] fn as_bytes_bytes(text: &[u8]) -> &[u8] { text }
        }
    }
}

define_set! {
    unicode,
    set_unicode,
    &str,
    as_bytes_str,
/// ```rust
/// # use regex::RegexSet;
/// let set = RegexSet::new(&[
///     r"[a-z]+@[a-z]+\.(com|org|net)",
///     r"[a-z]+\.(com|org|net)",
/// ]).unwrap();
///
/// // Ask whether any regexes in the set match.
/// assert!(set.is_match("foo@example.com"));
///
/// // Identify which regexes in the set match.
/// let matches: Vec<_> = set.matches("foo@example.com").into_iter().collect();
/// assert_eq!(vec![0, 1], matches);
///
/// // Try again, but with text that only matches one of the regexes.
/// let matches: Vec<_> = set.matches("example.com").into_iter().collect();
/// assert_eq!(vec![1], matches);
///
/// // Try again, but with text that doesn't match any regex in the set.
/// let matches: Vec<_> = set.matches("example").into_iter().collect();
/// assert!(matches.is_empty());
/// ```
}

define_set! {
    bytes,
    set_bytes,
    &[u8],
    as_bytes_bytes,
/// ```rust
/// # use regex::bytes::RegexSet;
/// let set = RegexSet::new(&[
///     r"[a-z]+@[a-z]+\.(com|org|net)",
///     r"[a-z]+\.(com|org|net)",
/// ]).unwrap();
///
/// // Ask whether any regexes in the set match.
/// assert!(set.is_match(b"foo@example.com"));
///
/// // Identify which regexes in the set match.
/// let matches: Vec<_> = set.matches(b"foo@example.com").into_iter().collect();
/// assert_eq!(vec![0, 1], matches);
///
/// // Try again, but with text that only matches one of the regexes.
/// let matches: Vec<_> = set.matches(b"example.com").into_iter().collect();
/// assert_eq!(vec![1], matches);
///
/// // Try again, but with text that doesn't match any regex in the set.
/// let matches: Vec<_> = set.matches(b"example").into_iter().collect();
/// assert!(matches.is_empty());
/// ```
}