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
// 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_provider::prelude::*;
use crate::indices::{Latin1Indices, Utf16Indices};
use crate::iterator_helpers::derive_usize_iterator_with_type;
use crate::rule_segmenter::*;
use crate::{provider::*, SegmenterError};
use utf8_iter::Utf8CharIndices;
/// Implements the [`Iterator`] trait over the grapheme cluster 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 [`GraphemeClusterSegmenter`].
#[derive(Debug)]
pub struct GraphemeClusterBreakIterator<'l, 's, Y: RuleBreakType<'l, 's> + ?Sized>(
RuleBreakIterator<'l, 's, Y>,
);
derive_usize_iterator_with_type!(GraphemeClusterBreakIterator);
/// Grapheme cluster break iterator for an `str` (a UTF-8 string).
///
/// For examples of use, see [`GraphemeClusterSegmenter`].
pub type GraphemeClusterBreakIteratorUtf8<'l, 's> =
GraphemeClusterBreakIterator<'l, 's, RuleBreakTypeUtf8>;
/// Grapheme cluster break iterator for a potentially invalid UTF-8 string.
///
/// For examples of use, see [`GraphemeClusterSegmenter`].
pub type GraphemeClusterBreakIteratorPotentiallyIllFormedUtf8<'l, 's> =
GraphemeClusterBreakIterator<'l, 's, RuleBreakTypePotentiallyIllFormedUtf8>;
/// Grapheme cluster break iterator for a Latin-1 (8-bit) string.
///
/// For examples of use, see [`GraphemeClusterSegmenter`].
pub type GraphemeClusterBreakIteratorLatin1<'l, 's> =
GraphemeClusterBreakIterator<'l, 's, RuleBreakTypeLatin1>;
/// Grapheme cluster break iterator for a UTF-16 string.
///
/// For examples of use, see [`GraphemeClusterSegmenter`].
pub type GraphemeClusterBreakIteratorUtf16<'l, 's> =
GraphemeClusterBreakIterator<'l, 's, RuleBreakTypeUtf16>;
/// Segments a string into grapheme clusters.
///
/// Supports loading grapheme cluster break data, and creating grapheme cluster break iterators for
/// different string encodings.
///
/// # Examples
///
/// Segment a string:
///
/// ```rust
/// use icu::segmenter::GraphemeClusterSegmenter;
/// let segmenter = GraphemeClusterSegmenter::new();
///
/// let breakpoints: Vec<usize> = segmenter.segment_str("Hello 🗺").collect();
/// // World Map (U+1F5FA) is encoded in four bytes in UTF-8.
/// assert_eq!(&breakpoints, &[0, 1, 2, 3, 4, 5, 6, 10]);
/// ```
///
/// Segment a Latin1 byte string:
///
/// ```rust
/// use icu::segmenter::GraphemeClusterSegmenter;
/// let segmenter = GraphemeClusterSegmenter::new();
///
/// let breakpoints: Vec<usize> =
/// segmenter.segment_latin1(b"Hello World").collect();
/// assert_eq!(&breakpoints, &[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]);
/// ```
///
/// Successive boundaries can be used to retrieve the grapheme clusters.
/// 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::GraphemeClusterSegmenter;
/// # let segmenter =
/// # GraphemeClusterSegmenter::new();
/// use itertools::Itertools;
/// let text = "मांजर";
/// let grapheme_clusters: Vec<&str> = segmenter
/// .segment_str(text)
/// .tuple_windows()
/// .map(|(i, j)| &text[i..j])
/// .collect();
/// assert_eq!(&grapheme_clusters, &["मां", "ज", "र"]);
/// ```
///
/// This segmenter applies all rules provided to the constructor.
/// Thus, if the data supplied by the provider comprises all
/// [grapheme cluster boundary rules][Rules] from Unicode Standard Annex #29,
/// _Unicode Text Segmentation_, which is the case of default data
/// (both test data and data produced by `icu_datagen`), the `segment_*`
/// functions return extended grapheme cluster boundaries, as opposed to
/// legacy grapheme cluster boundaries. See [_Section 3, Grapheme Cluster
/// Boundaries_][GC], and [_Table 1a, Sample Grapheme Clusters_][Sample_GC],
/// in Unicode Standard Annex #29, _Unicode Text Segmentation_.
///
/// [Rules]: https://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundary_Rules
/// [GC]: https://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries
/// [Sample_GC]: https://www.unicode.org/reports/tr29/#Table_Sample_Grapheme_Clusters
///
/// ```rust
/// use icu::segmenter::GraphemeClusterSegmenter;
/// let segmenter =
/// GraphemeClusterSegmenter::new();
///
/// // நி (TAMIL LETTER NA, TAMIL VOWEL SIGN I) is an extended grapheme cluster,
/// // but not a legacy grapheme cluster.
/// let ni = "நி";
/// let egc_boundaries: Vec<usize> = segmenter.segment_str(ni).collect();
/// assert_eq!(&egc_boundaries, &[0, ni.len()]);
/// ```
#[derive(Debug)]
pub struct GraphemeClusterSegmenter {
payload: DataPayload<GraphemeClusterBreakDataV1Marker>,
}
#[cfg(feature = "compiled_data")]
impl Default for GraphemeClusterSegmenter {
fn default() -> Self {
Self::new()
}
}
impl GraphemeClusterSegmenter {
/// Constructs a [`GraphemeClusterSegmenter`] with an invariant locale from 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_SEGMENTER_GRAPHEME_V1,
),
}
}
icu_provider::gen_any_buffer_data_constructors!(locale: skip, options: skip, error: SegmenterError,
#[cfg(skip)]
functions: [
new,
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, SegmenterError>
where
D: DataProvider<GraphemeClusterBreakDataV1Marker> + ?Sized,
{
let payload = provider.load(Default::default())?.take_payload()?;
Ok(Self { payload })
}
/// Creates a grapheme cluster break iterator for an `str` (a UTF-8 string).
pub fn segment_str<'l, 's>(
&'l self,
input: &'s str,
) -> GraphemeClusterBreakIteratorUtf8<'l, 's> {
GraphemeClusterSegmenter::new_and_segment_str(input, self.payload.get())
}
/// Creates a grapheme cluster break iterator from grapheme cluster rule payload.
///
/// There are always breakpoints at 0 and the string length, or only at 0 for the empty string.
pub(crate) fn new_and_segment_str<'l, 's>(
input: &'s str,
payload: &'l RuleBreakDataV1<'l>,
) -> GraphemeClusterBreakIteratorUtf8<'l, 's> {
GraphemeClusterBreakIterator(RuleBreakIterator {
iter: input.char_indices(),
len: input.len(),
current_pos_data: None,
result_cache: Vec::new(),
data: payload,
complex: None,
boundary_property: 0,
})
}
/// Creates a grapheme cluster 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],
) -> GraphemeClusterBreakIteratorPotentiallyIllFormedUtf8<'l, 's> {
GraphemeClusterBreakIterator(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,
})
}
/// Creates a grapheme cluster 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],
) -> GraphemeClusterBreakIteratorLatin1<'l, 's> {
GraphemeClusterBreakIterator(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,
})
}
/// Creates a grapheme cluster 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],
) -> GraphemeClusterBreakIteratorUtf16<'l, 's> {
GraphemeClusterSegmenter::new_and_segment_utf16(input, self.payload.get())
}
/// Creates a grapheme cluster break iterator from grapheme cluster rule payload.
pub(crate) fn new_and_segment_utf16<'l, 's>(
input: &'s [u16],
payload: &'l RuleBreakDataV1<'l>,
) -> GraphemeClusterBreakIteratorUtf16<'l, 's> {
GraphemeClusterBreakIterator(RuleBreakIterator {
iter: Utf16Indices::new(input),
len: input.len(),
current_pos_data: None,
result_cache: Vec::new(),
data: payload,
complex: None,
boundary_property: 0,
})
}
}
#[test]
fn empty_string() {
let segmenter = GraphemeClusterSegmenter::new();
let breaks: Vec<usize> = segmenter.segment_str("").collect();
assert_eq!(breaks, [0]);
}
#[test]
fn emoji_flags() {
// https://github.com/unicode-org/icu4x/issues/4780
let segmenter = GraphemeClusterSegmenter::new();
let breaks: Vec<usize> = segmenter.segment_str("🇺🇸🏴").collect();
assert_eq!(breaks, [0, 8, 36]);
}