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
// 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 ).
use alloc::vec::Vec;
use icu_locale_core::LanguageIdentifier;
use icu_provider::prelude::*;
use crate::indices::{Latin1Indices, Utf16Indices};
use crate::iterator_helpers::derive_usize_iterator_with_type;
use crate::provider::*;
use crate::rule_segmenter::*;
use utf8_iter::Utf8CharIndices;
/// Options to tailor sentence breaking behavior.
#[non_exhaustive]
#[derive(Copy, Clone, PartialEq, Eq, Debug, Default)]
pub struct SentenceBreakOptions<'a> {
/// Content locale for sentence segmenter.
pub content_locale: Option<&'a LanguageIdentifier>,
}
/// Implements the [`Iterator`] trait over the sentence boundaries of the given string.
///
/// Lifetimes:
///
/// - `'l` = lifetime of the segmenter object from which this iterator was created
/// - `'s` = lifetime of the string being segmented
///
/// The [`Iterator::Item`] is an [`usize`] representing index of a code unit
/// _after_ the boundary (for a boundary at the end of text, this index is the length
/// of the [`str`] or array of code units).
///
/// For examples of use, see [`SentenceSegmenter`].
#[derive(Debug)]
pub struct SentenceBreakIterator<'l, 's, Y: RuleBreakType<'l, 's> + ?Sized>(
RuleBreakIterator<'l, 's, Y>,
);
derive_usize_iterator_with_type!(SentenceBreakIterator);
/// Sentence break iterator for an `str` (a UTF-8 string).
///
/// For examples of use, see [`SentenceSegmenter`].
pub type SentenceBreakIteratorUtf8<'l, 's> = SentenceBreakIterator<'l, 's, RuleBreakTypeUtf8>;
/// Sentence break iterator for a potentially invalid UTF-8 string.
///
/// For examples of use, see [`SentenceSegmenter`].
pub type SentenceBreakIteratorPotentiallyIllFormedUtf8<'l, 's> =
SentenceBreakIterator<'l, 's, RuleBreakTypePotentiallyIllFormedUtf8>;
/// Sentence break iterator for a Latin-1 (8-bit) string.
///
/// For examples of use, see [`SentenceSegmenter`].
pub type SentenceBreakIteratorLatin1<'l, 's> = SentenceBreakIterator<'l, 's, RuleBreakTypeLatin1>;
/// Sentence break iterator for a UTF-16 string.
///
/// For examples of use, see [`SentenceSegmenter`].
pub type SentenceBreakIteratorUtf16<'l, 's> = SentenceBreakIterator<'l, 's, RuleBreakTypeUtf16>;
/// Supports loading sentence break data, and creating sentence break iterators for different string
/// encodings.
///
/// # Examples
///
/// Segment a string:
///
/// ```rust
/// use icu::segmenter::SentenceSegmenter;
/// let segmenter = SentenceSegmenter::new();
///
/// let breakpoints: Vec<usize> =
/// segmenter.segment_str("Hello World").collect();
/// assert_eq!(&breakpoints, &[0, 11]);
/// ```
///
/// Segment a Latin1 byte string:
///
/// ```rust
/// use icu::segmenter::SentenceSegmenter;
/// let segmenter = SentenceSegmenter::new();
///
/// let breakpoints: Vec<usize> =
/// segmenter.segment_latin1(b"Hello World").collect();
/// assert_eq!(&breakpoints, &[0, 11]);
/// ```
///
/// Successive boundaries can be used to retrieve the sentences.
/// In particular, the first boundary is always 0, and the last one is the
/// length of the segmented text in code units.
///
/// ```rust
/// # use icu::segmenter::SentenceSegmenter;
/// # let segmenter = SentenceSegmenter::new();
/// use itertools::Itertools;
/// let text = "Ceci tuera cela. Le livre tuera l’édifice.";
/// let sentences: Vec<&str> = segmenter
/// .segment_str(text)
/// .tuple_windows()
/// .map(|(i, j)| &text[i..j])
/// .collect();
/// assert_eq!(
/// &sentences,
/// &["Ceci tuera cela. ", "Le livre tuera l’édifice."]
/// );
/// ```
#[derive(Debug)]
pub struct SentenceSegmenter {
payload: DataPayload<SentenceBreakDataV2Marker>,
payload_locale_override: Option<DataPayload<SentenceBreakDataOverrideV1Marker>>,
}
#[cfg(feature = "compiled_data")]
impl Default for SentenceSegmenter {
fn default() -> Self {
Self::new()
}
}
impl SentenceSegmenter {
/// Constructs a [`SentenceSegmenter`] with an invariant locale and compiled data.
///
/// ✨ *Enabled with the `compiled_data` Cargo feature.*
///
/// [📚 Help choosing a constructor](icu_provider::constructors)
#[cfg(feature = "compiled_data")]
pub fn new() -> Self {
Self {
payload: DataPayload::from_static_ref(
crate::provider::Baked::SINGLETON_SENTENCE_BREAK_DATA_V2_MARKER,
),
payload_locale_override: None,
}
}
icu_provider::gen_any_buffer_data_constructors!(() -> error: DataError,
functions: [
new: skip,
try_new_with_any_provider,
try_new_with_buffer_provider,
try_new_unstable,
Self,
]
);
#[doc = icu_provider::gen_any_buffer_unstable_docs!(UNSTABLE, Self::new)]
pub fn try_new_unstable<D>(provider: &D) -> Result<Self, DataError>
where
D: DataProvider<SentenceBreakDataV2Marker> + ?Sized,
{
let payload = provider.load(Default::default())?.payload;
Ok(Self {
payload,
payload_locale_override: None,
})
}
icu_provider::gen_any_buffer_data_constructors!(
(options: SentenceBreakOptions) -> error: DataError,
/// Constructs a [`SentenceSegmenter`] for a given options and using compiled data.
functions: [
try_new_with_options,
try_new_with_options_with_any_provider,
try_new_with_options_with_buffer_provider,
try_new_with_options_unstable,
Self
]
);
#[doc = icu_provider::gen_any_buffer_unstable_docs!(UNSTABLE, Self::try_new_with_options)]
pub fn try_new_with_options_unstable<D>(
provider: &D,
options: SentenceBreakOptions,
) -> Result<Self, DataError>
where
D: DataProvider<SentenceBreakDataV2Marker>
+ DataProvider<SentenceBreakDataOverrideV1Marker>
+ ?Sized,
{
let payload = provider.load(Default::default())?.payload;
let payload_locale_override = if let Some(locale) = options.content_locale {
let locale = DataLocale::from(locale);
let req = DataRequest {
id: DataIdentifierBorrowed::for_locale(&locale),
metadata: {
let mut metadata = DataRequestMetadata::default();
metadata.silent = true;
metadata
},
};
provider
.load(req)
.allow_identifier_not_found()?
.map(|r| r.payload)
} else {
None
};
Ok(Self {
payload,
payload_locale_override,
})
}
/// Creates a sentence break iterator for an `str` (a UTF-8 string).
///
/// There are always breakpoints at 0 and the string length, or only at 0 for the empty string.
pub fn segment_str<'l, 's>(&'l self, input: &'s str) -> SentenceBreakIteratorUtf8<'l, 's> {
let locale_override = self
.payload_locale_override
.as_ref()
.map(|payload| payload.get());
SentenceBreakIterator(RuleBreakIterator {
iter: input.char_indices(),
len: input.len(),
current_pos_data: None,
result_cache: Vec::new(),
data: self.payload.get(),
complex: None,
boundary_property: 0,
locale_override,
})
}
/// Creates a sentence break iterator for a potentially ill-formed UTF8 string
///
/// Invalid characters are treated as REPLACEMENT CHARACTER
///
/// There are always breakpoints at 0 and the string length, or only at 0 for the empty string.
pub fn segment_utf8<'l, 's>(
&'l self,
input: &'s [u8],
) -> SentenceBreakIteratorPotentiallyIllFormedUtf8<'l, 's> {
let locale_override = self
.payload_locale_override
.as_ref()
.map(|payload| payload.get());
SentenceBreakIterator(RuleBreakIterator {
iter: Utf8CharIndices::new(input),
len: input.len(),
current_pos_data: None,
result_cache: Vec::new(),
data: self.payload.get(),
complex: None,
boundary_property: 0,
locale_override,
})
}
/// Creates a sentence break iterator for a Latin-1 (8-bit) string.
///
/// There are always breakpoints at 0 and the string length, or only at 0 for the empty string.
pub fn segment_latin1<'l, 's>(
&'l self,
input: &'s [u8],
) -> SentenceBreakIteratorLatin1<'l, 's> {
let locale_override = self
.payload_locale_override
.as_ref()
.map(|payload| payload.get());
SentenceBreakIterator(RuleBreakIterator {
iter: Latin1Indices::new(input),
len: input.len(),
current_pos_data: None,
result_cache: Vec::new(),
data: self.payload.get(),
complex: None,
boundary_property: 0,
locale_override,
})
}
/// Creates a sentence break iterator for a UTF-16 string.
///
/// There are always breakpoints at 0 and the string length, or only at 0 for the empty string.
pub fn segment_utf16<'l, 's>(&'l self, input: &'s [u16]) -> SentenceBreakIteratorUtf16<'l, 's> {
let locale_override = self
.payload_locale_override
.as_ref()
.map(|payload| payload.get());
SentenceBreakIterator(RuleBreakIterator {
iter: Utf16Indices::new(input),
len: input.len(),
current_pos_data: None,
result_cache: Vec::new(),
data: self.payload.get(),
complex: None,
boundary_property: 0,
locale_override,
})
}
}
#[cfg(all(test, feature = "serde"))]
#[test]
fn empty_string() {
let segmenter = SentenceSegmenter::new();
let breaks: Vec<usize> = segmenter.segment_str("").collect();
assert_eq!(breaks, [0]);
}