Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commit50058a5

Browse files
committed
Adds unicode_sentences and split_sentence_bound_indices
1 parent7ac6f29 commit50058a5

File tree

2 files changed

+87
-1
lines changed

2 files changed

+87
-1
lines changed

‎src/lib.rs

Lines changed: 26 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -67,7 +67,7 @@ pub use grapheme::{Graphemes, GraphemeIndices};
6767
pubuse grapheme::{GraphemeCursor,GraphemeIncomplete};
6868
pubuse tables::UNICODE_VERSION;
6969
pubuse word::{UWordBounds,UWordBoundIndices,UnicodeWords};
70-
pubuse sentence::{USentenceBounds};
70+
pubuse sentence::{USentenceBounds,USentenceBoundIndices,UnicodeSentences};
7171

7272
mod grapheme;
7373
mod tables;
@@ -181,7 +181,22 @@ pub trait UnicodeSegmentation {
181181
/// [UAX#29 sentence boundaries](http://www.unicode.org/reports/tr29/#Sentence_Boundaries).
182182
///
183183
/// The concatenation of the substrings returned by this function is just the original string.
184+
fnunicode_sentences<'a>(&'aself) ->UnicodeSentences<'a>;
185+
186+
/// Returns an iterator over substrings of `self` separated on
187+
/// [UAX#29 sentence boundaries](http://www.unicode.org/reports/tr29/#Sentence_Boundaries).
188+
///
189+
/// Here, "sentences" are just those substrings which, after splitting on
190+
/// UAX#29 sentence boundaries, contain any alphanumeric characters. That is, the
191+
/// substring must contain at least one character with the
192+
/// [Alphabetic](http://unicode.org/reports/tr44/#Alphabetic)
193+
/// property, or with
194+
/// [General_Category=Number](http://unicode.org/reports/tr44/#General_Category_Values).
184195
fnsplit_sentence_bounds<'a>(&'aself) ->USentenceBounds<'a>;
196+
197+
/// Returns an iterator over substrings of `self`, split on UAX#29 sentence boundaries,
198+
/// and their offsets. See `split_sentence_bounds()` for more information.
199+
fnsplit_sentence_bound_indices<'a>(&'aself) ->USentenceBoundIndices<'a>;
185200
}
186201

187202
implUnicodeSegmentationforstr{
@@ -210,8 +225,18 @@ impl UnicodeSegmentation for str {
210225
word::new_word_bound_indices(self)
211226
}
212227

228+
#[inline]
229+
fnunicode_sentences(&self) ->UnicodeSentences{
230+
sentence::new_unicode_sentences(self)
231+
}
232+
213233
#[inline]
214234
fnsplit_sentence_bounds(&self) ->USentenceBounds{
215235
sentence::new_sentence_bounds(self)
216236
}
237+
238+
#[inline]
239+
fnsplit_sentence_bound_indices(&self) ->USentenceBoundIndices{
240+
sentence::new_sentence_bound_indices(self)
241+
}
217242
}

‎src/sentence.rs

Lines changed: 61 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,7 @@
99
// except according to those terms.
1010

1111
use core::cmp;
12+
use core::iter::Filter;
1213

1314
// All of the logic for forward iteration over sentences
1415
mod fwd{
@@ -40,6 +41,7 @@ mod fwd {
4041
StatePart::Sot
4142
]);
4243

44+
#[derive(Clone)]
4345
pubstructSentenceBreaks<'a>{
4446
pubstring:&'astr,
4547
pos:usize,
@@ -256,13 +258,32 @@ mod fwd {
256258

257259
}
258260

261+
/// An iterator over the substrings of a string which, after splitting the string on
262+
/// [sentence boundaries](http://www.unicode.org/reports/tr29/#Sentence_Boundaries),
263+
/// contain any characters with the
264+
/// [Alphabetic](http://unicode.org/reports/tr44/#Alphabetic)
265+
/// property, or with
266+
/// [General_Category=Number](http://unicode.org/reports/tr44/#General_Category_Values).
267+
#[derive(Clone)]
268+
pubstructUnicodeSentences<'a>{
269+
inner:Filter<USentenceBounds<'a>,fn(&&str) ->bool>,
270+
}
271+
259272
/// External iterator for a string's
260273
/// [sentence boundaries](http://www.unicode.org/reports/tr29/#Sentence_Boundaries).
274+
#[derive(Clone)]
261275
pubstructUSentenceBounds<'a>{
262276
iter: fwd::SentenceBreaks<'a>,
263277
sentence_start:Option<usize>
264278
}
265279

280+
/// External iterator for sentence boundaries and byte offsets.
281+
#[derive(Clone)]
282+
pubstructUSentenceBoundIndices<'a>{
283+
start_offset:usize,
284+
iter:USentenceBounds<'a>,
285+
}
286+
266287
#[inline]
267288
pubfnnew_sentence_bounds<'a>(source:&'astr) ->USentenceBounds<'a>{
268289
USentenceBounds{
@@ -271,6 +292,32 @@ pub fn new_sentence_bounds<'a>(source: &'a str) -> USentenceBounds<'a> {
271292
}
272293
}
273294

295+
#[inline]
296+
pubfnnew_sentence_bound_indices<'a>(source:&'astr) ->USentenceBoundIndices<'a>{
297+
USentenceBoundIndices{
298+
start_offset: source.as_ptr()asusize,
299+
iter:new_sentence_bounds(source)
300+
}
301+
}
302+
303+
#[inline]
304+
pubfnnew_unicode_sentences<'b>(s:&'bstr) ->UnicodeSentences<'b>{
305+
usesuper::UnicodeSegmentation;
306+
use tables::util::is_alphanumeric;
307+
308+
fnhas_alphanumeric(s:&&str) ->bool{ s.chars().any(|c|is_alphanumeric(c))}
309+
let has_alphanumeric:fn(&&str) ->bool = has_alphanumeric;// coerce to fn pointer
310+
311+
UnicodeSentences{inner: s.split_sentence_bounds().filter(has_alphanumeric)}
312+
}
313+
314+
impl<'a>IteratorforUnicodeSentences<'a>{
315+
typeItem =&'astr;
316+
317+
#[inline]
318+
fnnext(&mutself) ->Option<&'astr>{self.inner.next()}
319+
}
320+
274321
impl<'a>IteratorforUSentenceBounds<'a>{
275322
typeItem =&'astr;
276323

@@ -300,3 +347,17 @@ impl<'a> Iterator for USentenceBounds<'a> {
300347
}
301348
}
302349
}
350+
351+
impl<'a>IteratorforUSentenceBoundIndices<'a>{
352+
typeItem =(usize,&'astr);
353+
354+
#[inline]
355+
fnnext(&mutself) ->Option<(usize,&'astr)>{
356+
self.iter.next().map(|s|(s.as_ptr()asusize -self.start_offset, s))
357+
}
358+
359+
#[inline]
360+
fnsize_hint(&self) ->(usize,Option<usize>){
361+
self.iter.size_hint()
362+
}
363+
}

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp