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
|
// This file is part of ICU4X. For terms of use, please see the file
// called LICENSE at the top level of the ICU4X source tree
// (online at: https://github.com/unicode-org/icu4x/blob/main/LICENSE ).
#[diplomat::bridge]
pub mod ffi {
use crate::errors::ffi::ICU4XError;
use crate::provider::ffi::ICU4XDataProvider;
use alloc::boxed::Box;
use core::convert::TryFrom;
use icu_segmenter::{
WordBreakIteratorLatin1, WordBreakIteratorPotentiallyIllFormedUtf8, WordBreakIteratorUtf16,
WordSegmenter, WordType,
};
#[diplomat::enum_convert(WordType, needs_wildcard)]
#[diplomat::rust_link(icu::segmenter::WordType, Enum)]
pub enum ICU4XSegmenterWordType {
None = 0,
Number = 1,
Letter = 2,
}
#[diplomat::opaque]
/// An ICU4X word-break segmenter, capable of finding word breakpoints in strings.
#[diplomat::rust_link(icu::segmenter::WordSegmenter, Struct)]
pub struct ICU4XWordSegmenter(WordSegmenter);
#[diplomat::opaque]
#[diplomat::rust_link(icu::segmenter::WordBreakIterator, Struct)]
#[diplomat::rust_link(
icu::segmenter::WordBreakIteratorPotentiallyIllFormedUtf8,
Typedef,
hidden
)]
pub struct ICU4XWordBreakIteratorUtf8<'a>(WordBreakIteratorPotentiallyIllFormedUtf8<'a, 'a>);
#[diplomat::opaque]
#[diplomat::rust_link(icu::segmenter::WordBreakIterator, Struct)]
#[diplomat::rust_link(icu::segmenter::WordBreakIteratorUtf16, Typedef, hidden)]
pub struct ICU4XWordBreakIteratorUtf16<'a>(WordBreakIteratorUtf16<'a, 'a>);
#[diplomat::opaque]
#[diplomat::rust_link(icu::segmenter::WordBreakIterator, Struct)]
#[diplomat::rust_link(icu::segmenter::WordBreakIteratorLatin1, Typedef, hidden)]
pub struct ICU4XWordBreakIteratorLatin1<'a>(WordBreakIteratorLatin1<'a, 'a>);
impl ICU4XWordSegmenter {
/// Construct an [`ICU4XWordSegmenter`] with automatically selecting the best available LSTM
/// or dictionary payload data.
///
/// Note: currently, it uses dictionary for Chinese and Japanese, and LSTM for Burmese,
/// Khmer, Lao, and Thai.
#[diplomat::rust_link(icu::segmenter::WordSegmenter::new_auto, FnInStruct)]
pub fn create_auto(
provider: &ICU4XDataProvider,
) -> Result<Box<ICU4XWordSegmenter>, ICU4XError> {
Ok(Box::new(ICU4XWordSegmenter(call_constructor!(
WordSegmenter::new_auto [r => Ok(r)],
WordSegmenter::try_new_auto_with_any_provider,
WordSegmenter::try_new_auto_with_buffer_provider,
provider
)?)))
}
/// Construct an [`ICU4XWordSegmenter`] with LSTM payload data for Burmese, Khmer, Lao, and
/// Thai.
///
/// Warning: [`ICU4XWordSegmenter`] created by this function doesn't handle Chinese or
/// Japanese.
#[diplomat::rust_link(icu::segmenter::WordSegmenter::new_lstm, FnInStruct)]
pub fn create_lstm(
provider: &ICU4XDataProvider,
) -> Result<Box<ICU4XWordSegmenter>, ICU4XError> {
Ok(Box::new(ICU4XWordSegmenter(call_constructor!(
WordSegmenter::new_lstm [r => Ok(r)],
WordSegmenter::try_new_lstm_with_any_provider,
WordSegmenter::try_new_lstm_with_buffer_provider,
provider,
)?)))
}
/// Construct an [`ICU4XWordSegmenter`] with dictionary payload data for Chinese, Japanese,
/// Burmese, Khmer, Lao, and Thai.
#[diplomat::rust_link(icu::segmenter::WordSegmenter::new_dictionary, FnInStruct)]
pub fn create_dictionary(
provider: &ICU4XDataProvider,
) -> Result<Box<ICU4XWordSegmenter>, ICU4XError> {
Ok(Box::new(ICU4XWordSegmenter(call_constructor!(
WordSegmenter::new_dictionary [r => Ok(r)],
WordSegmenter::try_new_dictionary_with_any_provider,
WordSegmenter::try_new_dictionary_with_buffer_provider,
provider,
)?)))
}
/// Segments a (potentially ill-formed) UTF-8 string.
#[diplomat::rust_link(icu::segmenter::WordSegmenter::segment_utf8, FnInStruct)]
#[diplomat::rust_link(icu::segmenter::WordSegmenter::segment_str, FnInStruct, hidden)]
pub fn segment_utf8<'a>(&'a self, input: &'a str) -> Box<ICU4XWordBreakIteratorUtf8<'a>> {
let input = input.as_bytes(); // #2520
Box::new(ICU4XWordBreakIteratorUtf8(self.0.segment_utf8(input)))
}
/// Segments a UTF-16 string.
#[diplomat::rust_link(icu::segmenter::WordSegmenter::segment_utf16, FnInStruct)]
pub fn segment_utf16<'a>(
&'a self,
input: &'a [u16],
) -> Box<ICU4XWordBreakIteratorUtf16<'a>> {
Box::new(ICU4XWordBreakIteratorUtf16(self.0.segment_utf16(input)))
}
/// Segments a Latin-1 string.
#[diplomat::rust_link(icu::segmenter::WordSegmenter::segment_latin1, FnInStruct)]
pub fn segment_latin1<'a>(
&'a self,
input: &'a [u8],
) -> Box<ICU4XWordBreakIteratorLatin1<'a>> {
Box::new(ICU4XWordBreakIteratorLatin1(self.0.segment_latin1(input)))
}
}
impl<'a> ICU4XWordBreakIteratorUtf8<'a> {
/// Finds the next breakpoint. Returns -1 if at the end of the string or if the index is
/// out of range of a 32-bit signed integer.
#[allow(clippy::should_implement_trait)]
#[diplomat::rust_link(icu::segmenter::WordBreakIterator::next, FnInStruct)]
#[diplomat::rust_link(
icu::segmenter::WordBreakIterator::Item,
AssociatedTypeInStruct,
hidden
)]
pub fn next(&mut self) -> i32 {
self.0
.next()
.and_then(|u| i32::try_from(u).ok())
.unwrap_or(-1)
}
/// Return the status value of break boundary.
#[diplomat::rust_link(icu::segmenter::WordBreakIterator::word_type, FnInStruct)]
pub fn word_type(&self) -> ICU4XSegmenterWordType {
self.0.word_type().into()
}
/// Return true when break boundary is word-like such as letter/number/CJK
#[diplomat::rust_link(icu::segmenter::WordBreakIterator::is_word_like, FnInStruct)]
pub fn is_word_like(&self) -> bool {
self.0.is_word_like()
}
}
impl<'a> ICU4XWordBreakIteratorUtf16<'a> {
/// Finds the next breakpoint. Returns -1 if at the end of the string or if the index is
/// out of range of a 32-bit signed integer.
#[allow(clippy::should_implement_trait)]
#[diplomat::rust_link(icu::segmenter::WordBreakIterator::next, FnInStruct)]
#[diplomat::rust_link(
icu::segmenter::WordBreakIterator::Item,
AssociatedTypeInStruct,
hidden
)]
pub fn next(&mut self) -> i32 {
self.0
.next()
.and_then(|u| i32::try_from(u).ok())
.unwrap_or(-1)
}
/// Return the status value of break boundary.
#[diplomat::rust_link(icu::segmenter::WordBreakIterator::word_type, FnInStruct)]
pub fn word_type(&self) -> ICU4XSegmenterWordType {
self.0.word_type().into()
}
/// Return true when break boundary is word-like such as letter/number/CJK
#[diplomat::rust_link(icu::segmenter::WordBreakIterator::is_word_like, FnInStruct)]
pub fn is_word_like(&self) -> bool {
self.0.is_word_like()
}
}
impl<'a> ICU4XWordBreakIteratorLatin1<'a> {
/// Finds the next breakpoint. Returns -1 if at the end of the string or if the index is
/// out of range of a 32-bit signed integer.
#[allow(clippy::should_implement_trait)]
#[diplomat::rust_link(icu::segmenter::WordBreakIterator::next, FnInStruct)]
#[diplomat::rust_link(
icu::segmenter::WordBreakIterator::Item,
AssociatedTypeInStruct,
hidden
)]
pub fn next(&mut self) -> i32 {
self.0
.next()
.and_then(|u| i32::try_from(u).ok())
.unwrap_or(-1)
}
/// Return the status value of break boundary.
#[diplomat::rust_link(icu::segmenter::WordBreakIterator::word_type, FnInStruct)]
pub fn word_type(&self) -> ICU4XSegmenterWordType {
self.0.word_type().into()
}
/// Return true when break boundary is word-like such as letter/number/CJK
#[diplomat::rust_link(icu::segmenter::WordBreakIterator::is_word_like, FnInStruct)]
pub fn is_word_like(&self) -> bool {
self.0.is_word_like()
}
}
}
|
