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
|
// Copyright 2012-2014 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
use core::cmp;
use core::iter::Filter;
// All of the logic for forward iteration over sentences
mod fwd {
use crate::tables::sentence::SentenceCat;
use core::cmp;
// Describe a parsed part of source string as described in this table:
// https://unicode.org/reports/tr29/#Default_Sentence_Boundaries
#[derive(Clone, Copy, PartialEq, Eq)]
enum StatePart {
Sot,
Eot,
Other,
CR,
LF,
Sep,
ATerm,
UpperLower,
ClosePlus,
SpPlus,
STerm,
}
#[derive(Clone, PartialEq, Eq)]
struct SentenceBreaksState(pub [StatePart; 4]);
const INITIAL_STATE: SentenceBreaksState = SentenceBreaksState([
StatePart::Sot,
StatePart::Sot,
StatePart::Sot,
StatePart::Sot,
]);
#[derive(Clone)]
pub struct SentenceBreaks<'a> {
pub string: &'a str,
pos: usize,
state: SentenceBreaksState,
}
impl SentenceBreaksState {
// Attempt to advance the internal state by one part
// Whitespace and some punctutation will be collapsed
fn next(&self, cat: SentenceCat) -> SentenceBreaksState {
let &SentenceBreaksState(parts) = self;
let parts = match (parts[3], cat) {
(StatePart::ClosePlus, SentenceCat::SC_Close) => parts,
(StatePart::SpPlus, SentenceCat::SC_Sp) => parts,
_ => [
parts[1],
parts[2],
parts[3],
match cat {
SentenceCat::SC_CR => StatePart::CR,
SentenceCat::SC_LF => StatePart::LF,
SentenceCat::SC_Sep => StatePart::Sep,
SentenceCat::SC_ATerm => StatePart::ATerm,
SentenceCat::SC_Upper | SentenceCat::SC_Lower => StatePart::UpperLower,
SentenceCat::SC_Close => StatePart::ClosePlus,
SentenceCat::SC_Sp => StatePart::SpPlus,
SentenceCat::SC_STerm => StatePart::STerm,
_ => StatePart::Other,
},
],
};
SentenceBreaksState(parts)
}
fn end(&self) -> SentenceBreaksState {
let &SentenceBreaksState(parts) = self;
SentenceBreaksState([parts[1], parts[2], parts[3], StatePart::Eot])
}
// Helper function to check if state head matches a single `StatePart`
fn match1(&self, part: StatePart) -> bool {
let &SentenceBreaksState(parts) = self;
part == parts[3]
}
// Helper function to check if first two `StateParts` in state match
// the given two
fn match2(&self, part1: StatePart, part2: StatePart) -> bool {
let &SentenceBreaksState(parts) = self;
part1 == parts[2] && part2 == parts[3]
}
}
// https://unicode.org/reports/tr29/#SB8
// TODO cache this, it is currently quadratic
fn match_sb8(state: &SentenceBreaksState, ahead: &str) -> bool {
let &SentenceBreaksState(parts) = state;
let mut idx = if parts[3] == StatePart::SpPlus { 2 } else { 3 };
if parts[idx] == StatePart::ClosePlus {
idx -= 1
}
if parts[idx] == StatePart::ATerm {
use crate::tables::sentence as se;
for next_char in ahead.chars() {
//( ¬(OLetter | Upper | Lower | ParaSep | SATerm) )* Lower
match se::sentence_category(next_char).2 {
se::SC_Lower => return true,
se::SC_OLetter
| se::SC_Upper
| se::SC_Sep
| se::SC_CR
| se::SC_LF
| se::SC_STerm
| se::SC_ATerm => return false,
_ => continue,
}
}
}
false
}
// https://unicode.org/reports/tr29/#SB8a
fn match_sb8a(state: &SentenceBreaksState) -> bool {
// SATerm Close* Sp*
let &SentenceBreaksState(parts) = state;
let mut idx = if parts[3] == StatePart::SpPlus { 2 } else { 3 };
if parts[idx] == StatePart::ClosePlus {
idx -= 1
}
parts[idx] == StatePart::STerm || parts[idx] == StatePart::ATerm
}
// https://unicode.org/reports/tr29/#SB9
fn match_sb9(state: &SentenceBreaksState) -> bool {
// SATerm Close*
let &SentenceBreaksState(parts) = state;
let idx = if parts[3] == StatePart::ClosePlus {
2
} else {
3
};
parts[idx] == StatePart::STerm || parts[idx] == StatePart::ATerm
}
// https://unicode.org/reports/tr29/#SB11
fn match_sb11(state: &SentenceBreaksState) -> bool {
// SATerm Close* Sp* ParaSep?
let &SentenceBreaksState(parts) = state;
let mut idx = match parts[3] {
StatePart::Sep | StatePart::CR | StatePart::LF => 2,
_ => 3,
};
if parts[idx] == StatePart::SpPlus {
idx -= 1
}
if parts[idx] == StatePart::ClosePlus {
idx -= 1
}
parts[idx] == StatePart::STerm || parts[idx] == StatePart::ATerm
}
impl<'a> Iterator for SentenceBreaks<'a> {
// Returns the index of the character which follows a break
type Item = usize;
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) {
let slen = self.string.len();
// A sentence could be one character
(cmp::min(slen, 2), Some(slen + 1))
}
#[inline]
fn next(&mut self) -> Option<usize> {
use crate::tables::sentence as se;
for next_char in self.string[self.pos..].chars() {
let position_before = self.pos;
let state_before = self.state.clone();
let next_cat = se::sentence_category(next_char).2;
self.pos += next_char.len_utf8();
self.state = self.state.next(next_cat);
match next_cat {
// SB1 https://unicode.org/reports/tr29/#SB1
_ if state_before.match1(StatePart::Sot) => return Some(position_before),
// SB2 is handled when inner iterator (chars) is finished
// SB3 https://unicode.org/reports/tr29/#SB3
SentenceCat::SC_LF if state_before.match1(StatePart::CR) => continue,
// SB4 https://unicode.org/reports/tr29/#SB4
_ if state_before.match1(StatePart::Sep)
|| state_before.match1(StatePart::CR)
|| state_before.match1(StatePart::LF) =>
{
return Some(position_before)
}
// SB5 https://unicode.org/reports/tr29/#SB5
SentenceCat::SC_Extend | SentenceCat::SC_Format => self.state = state_before,
// SB6 https://unicode.org/reports/tr29/#SB6
SentenceCat::SC_Numeric if state_before.match1(StatePart::ATerm) => continue,
// SB7 https://unicode.org/reports/tr29/#SB7
SentenceCat::SC_Upper
if state_before.match2(StatePart::UpperLower, StatePart::ATerm) =>
{
continue
}
// SB8 https://unicode.org/reports/tr29/#SB8
_ if match_sb8(&state_before, &self.string[position_before..]) => continue,
// SB8a https://unicode.org/reports/tr29/#SB8a
SentenceCat::SC_SContinue | SentenceCat::SC_STerm | SentenceCat::SC_ATerm
if match_sb8a(&state_before) =>
{
continue
}
// SB9 https://unicode.org/reports/tr29/#SB9
SentenceCat::SC_Close
| SentenceCat::SC_Sp
| SentenceCat::SC_Sep
| SentenceCat::SC_CR
| SentenceCat::SC_LF
if match_sb9(&state_before) =>
{
continue
}
// SB10 https://unicode.org/reports/tr29/#SB10
SentenceCat::SC_Sp
| SentenceCat::SC_Sep
| SentenceCat::SC_CR
| SentenceCat::SC_LF
if match_sb8a(&state_before) =>
{
continue
}
// SB11 https://unicode.org/reports/tr29/#SB11
_ if match_sb11(&state_before) => return Some(position_before),
// SB998 https://unicode.org/reports/tr29/#SB998
_ => continue,
}
}
// SB2 https://unicode.org/reports/tr29/#SB2
if self.state.match1(StatePart::Sot) {
None
} else if self.state.match1(StatePart::Eot) {
None
} else {
self.state = self.state.end();
Some(self.pos)
}
}
}
pub fn new_sentence_breaks<'a>(source: &'a str) -> SentenceBreaks<'a> {
SentenceBreaks {
string: source,
pos: 0,
state: INITIAL_STATE,
}
}
}
/// An iterator over the substrings of a string which, after splitting the string on
/// [sentence boundaries](http://www.unicode.org/reports/tr29/#Sentence_Boundaries),
/// contain any characters with the
/// [Alphabetic](http://unicode.org/reports/tr44/#Alphabetic)
/// property, or with
/// [General_Category=Number](http://unicode.org/reports/tr44/#General_Category_Values).
///
/// This struct is created by the [`unicode_sentences`] method on the [`UnicodeSegmentation`]
/// trait. See its documentation for more.
///
/// [`unicode_sentences`]: trait.UnicodeSegmentation.html#tymethod.unicode_sentences
/// [`UnicodeSegmentation`]: trait.UnicodeSegmentation.html
#[derive(Clone)]
pub struct UnicodeSentences<'a> {
inner: Filter<USentenceBounds<'a>, fn(&&str) -> bool>,
}
/// External iterator for a string's
/// [sentence boundaries](http://www.unicode.org/reports/tr29/#Sentence_Boundaries).
///
/// This struct is created by the [`split_sentence_bounds`] method on the [`UnicodeSegmentation`]
/// trait. See its documentation for more.
///
/// [`split_sentence_bounds`]: trait.UnicodeSegmentation.html#tymethod.split_sentence_bounds
/// [`UnicodeSegmentation`]: trait.UnicodeSegmentation.html
#[derive(Clone)]
pub struct USentenceBounds<'a> {
iter: fwd::SentenceBreaks<'a>,
sentence_start: Option<usize>,
}
/// External iterator for sentence boundaries and byte offsets.
///
/// This struct is created by the [`split_sentence_bound_indices`] method on the
/// [`UnicodeSegmentation`] trait. See its documentation for more.
///
/// [`split_sentence_bound_indices`]: trait.UnicodeSegmentation.html#tymethod.split_sentence_bound_indices
/// [`UnicodeSegmentation`]: trait.UnicodeSegmentation.html
#[derive(Clone)]
pub struct USentenceBoundIndices<'a> {
start_offset: usize,
iter: USentenceBounds<'a>,
}
#[inline]
pub fn new_sentence_bounds<'a>(source: &'a str) -> USentenceBounds<'a> {
USentenceBounds {
iter: fwd::new_sentence_breaks(source),
sentence_start: None,
}
}
#[inline]
pub fn new_sentence_bound_indices<'a>(source: &'a str) -> USentenceBoundIndices<'a> {
USentenceBoundIndices {
start_offset: source.as_ptr() as usize,
iter: new_sentence_bounds(source),
}
}
#[inline]
pub fn new_unicode_sentences<'b>(s: &'b str) -> UnicodeSentences<'b> {
use super::UnicodeSegmentation;
use crate::tables::util::is_alphanumeric;
fn has_alphanumeric(s: &&str) -> bool {
s.chars().any(|c| is_alphanumeric(c))
}
let has_alphanumeric: fn(&&str) -> bool = has_alphanumeric; // coerce to fn pointer
UnicodeSentences {
inner: s.split_sentence_bounds().filter(has_alphanumeric),
}
}
impl<'a> Iterator for UnicodeSentences<'a> {
type Item = &'a str;
#[inline]
fn next(&mut self) -> Option<&'a str> {
self.inner.next()
}
}
impl<'a> Iterator for USentenceBounds<'a> {
type Item = &'a str;
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) {
let (lower, upper) = self.iter.size_hint();
(cmp::max(0, lower - 1), upper.map(|u| cmp::max(0, u - 1)))
}
#[inline]
fn next(&mut self) -> Option<&'a str> {
if self.sentence_start == None {
if let Some(start_pos) = self.iter.next() {
self.sentence_start = Some(start_pos)
} else {
return None;
}
}
if let Some(break_pos) = self.iter.next() {
let start_pos = self.sentence_start.unwrap();
let sentence = &self.iter.string[start_pos..break_pos];
self.sentence_start = Some(break_pos);
Some(sentence)
} else {
None
}
}
}
impl<'a> Iterator for USentenceBoundIndices<'a> {
type Item = (usize, &'a str);
#[inline]
fn next(&mut self) -> Option<(usize, &'a str)> {
self.iter
.next()
.map(|s| (s.as_ptr() as usize - self.start_offset, s))
}
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) {
self.iter.size_hint()
}
}
|