summaryrefslogtreecommitdiffstats
path: root/vendor/unic-langid-impl/src/lib.rs
blob: 0a6d0b34aff15b83d35c766d16d92d5eef0a8497 (plain)
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
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
mod errors;
mod layout_table;
#[cfg(feature = "likelysubtags")]
pub mod likelysubtags;
#[doc(hidden)]
pub mod parser;
#[cfg(feature = "serde")]
mod serde;
pub mod subtags;

pub use crate::errors::LanguageIdentifierError;
use std::fmt::Write;
use std::iter::Peekable;
use std::str::FromStr;

/// Enum representing available character direction orientations.
#[derive(Debug, PartialEq)]
pub enum CharacterDirection {
    /// Right To Left
    ///
    /// Used in languages such as Arabic, Hebrew, Fula, Kurdish etc.
    RTL,
    /// Left To Right
    ///
    /// Used in languages such as French, Spanish, English, German etc.
    LTR,
}

type PartsTuple = (
    subtags::Language,
    Option<subtags::Script>,
    Option<subtags::Region>,
    Vec<subtags::Variant>,
);

/// `LanguageIdentifier` is a core struct representing a Unicode Language Identifier.
///
/// # Examples
///
/// ```
/// use unic_langid_impl::LanguageIdentifier;
///
/// let li: LanguageIdentifier = "en-US".parse()
///     .expect("Failed to parse.");
///
/// assert_eq!(li.language, "en");
/// assert_eq!(li.script, None);
/// assert_eq!(li.region.as_ref().map(Into::into), Some("US"));
/// assert_eq!(li.variants().len(), 0);
/// ```
///
/// # Parsing
///
/// Unicode recognizes three levels of standard conformance for any language identifier:
///
///  * *well-formed* - syntactically correct
///  * *valid* - well-formed and only uses registered language subtags, extensions, keywords, types...
///  * *canonical* - valid and no deprecated codes or structure.
///
/// At the moment parsing normalizes a well-formed language identifier converting
/// `_` separators to `-` and adjusting casing to conform to the Unicode standard.
///
/// Any bogus subtags will cause the parsing to fail with an error.
/// No subtag validation is performed.
///
/// # Examples:
///
/// ```
/// use unic_langid_impl::LanguageIdentifier;
///
/// let li: LanguageIdentifier = "eN_latn_Us-Valencia".parse()
///     .expect("Failed to parse.");
///
/// assert_eq!(li.language, "en");
/// assert_eq!(li.script.as_ref().map(Into::into), Some("Latn"));
/// assert_eq!(li.region.as_ref().map(Into::into), Some("US"));
/// assert_eq!(li.variants().map(|v| v.as_str()).collect::<Vec<_>>(), &["valencia"]);
/// ```
#[derive(Default, Debug, PartialEq, Eq, Clone, Hash, PartialOrd, Ord)]
pub struct LanguageIdentifier {
    pub language: subtags::Language,
    pub script: Option<subtags::Script>,
    pub region: Option<subtags::Region>,
    variants: Option<Box<[subtags::Variant]>>,
}

impl LanguageIdentifier {
    /// A constructor which takes a utf8 slice, parses it and
    /// produces a well-formed `LanguageIdentifier`.
    ///
    /// # Examples
    ///
    /// ```
    /// use unic_langid_impl::LanguageIdentifier;
    ///
    /// let li = LanguageIdentifier::from_bytes("en-US".as_bytes())
    ///     .expect("Parsing failed.");
    ///
    /// assert_eq!(li.to_string(), "en-US");
    /// ```
    pub fn from_bytes(v: &[u8]) -> Result<Self, LanguageIdentifierError> {
        Ok(parser::parse_language_identifier(v)?)
    }

    /// A constructor which takes optional subtags as `AsRef<[u8]>`, parses them and
    /// produces a well-formed `LanguageIdentifier`.
    ///
    /// # Examples
    ///
    /// ```
    /// use unic_langid_impl::LanguageIdentifier;
    ///
    /// let li = LanguageIdentifier::from_parts(
    ///     "fr".parse().expect("Parsing failed."),
    ///     None,
    ///     Some("CA".parse().expect("Parsing failed.")),
    ///     &[]
    /// );
    ///
    /// assert_eq!(li.to_string(), "fr-CA");
    /// ```
    pub fn from_parts(
        language: subtags::Language,
        script: Option<subtags::Script>,
        region: Option<subtags::Region>,
        variants: &[subtags::Variant],
    ) -> Self {
        let variants = if !variants.is_empty() {
            let mut v = variants.to_vec();
            v.sort_unstable();
            v.dedup();
            Some(v.into_boxed_slice())
        } else {
            None
        };

        Self {
            language,
            script,
            region,
            variants,
        }
    }

    /// # Unchecked
    ///
    /// This function accepts subtags expecting variants
    /// to be deduplicated and ordered.
    pub const fn from_raw_parts_unchecked(
        language: subtags::Language,
        script: Option<subtags::Script>,
        region: Option<subtags::Region>,
        variants: Option<Box<[subtags::Variant]>>,
    ) -> Self {
        Self {
            language,
            script,
            region,
            variants,
        }
    }

    #[doc(hidden)]
    /// This method is used by `unic-locale` to handle partial
    /// subtag iterator.
    ///
    /// Not stable.
    pub fn try_from_iter<'a>(
        iter: &mut Peekable<impl Iterator<Item = &'a [u8]>>,
        allow_extension: bool,
    ) -> Result<LanguageIdentifier, LanguageIdentifierError> {
        Ok(parser::parse_language_identifier_from_iter(
            iter,
            allow_extension,
        )?)
    }

    /// Consumes `LanguageIdentifier` and produces raw internal representations
    /// of all subtags in form of `u64`/`u32`.
    ///
    /// Primarily used for storing internal representation and restoring via
    /// `from_raw_parts_unchecked`.
    ///
    /// # Examples
    ///
    /// ```
    /// use unic_langid_impl::LanguageIdentifier;
    /// use tinystr::{TinyStr8, TinyStr4};
    ///
    /// let li: LanguageIdentifier = "en-US".parse()
    ///     .expect("Parsing failed.");
    ///
    /// let (lang, script, region, variants) = li.into_parts();
    ///
    /// // let li2 = LanguageIdentifier::from_raw_parts_unchecked(
    /// //     lang.map(|l| unsafe { TinyStr8::new_unchecked(l) }),
    /// //    script.map(|s| unsafe { TinyStr4::new_unchecked(s) }),
    /// //    region.map(|r| unsafe { TinyStr4::new_unchecked(r) }),
    /// //    variants.map(|v| v.into_iter().map(|v| unsafe { TinyStr8::new_unchecked(*v) }).collect()),
    /// //);
    ///
    /// //assert_eq!(li2.to_string(), "en-US");
    /// ```
    pub fn into_parts(self) -> PartsTuple {
        (
            self.language,
            self.script,
            self.region,
            self.variants.map_or_else(Vec::new, |v| v.to_vec()),
        )
    }

    /// Compares a `LanguageIdentifier` to another `AsRef<LanguageIdentifier`
    /// allowing for either side to use the missing fields as wildcards.
    ///
    /// This allows for matching between `en` (treated as `en-*-*-*`) and `en-US`.
    ///
    /// # Examples
    ///
    /// ```
    /// use unic_langid_impl::LanguageIdentifier;
    ///
    /// let li1: LanguageIdentifier = "en".parse()
    ///     .expect("Parsing failed.");
    ///
    /// let li2: LanguageIdentifier = "en-US".parse()
    ///     .expect("Parsing failed.");
    ///
    /// assert_ne!(li1, li2); // "en" != "en-US"
    /// assert_ne!(li1.to_string(), li2.to_string()); // "en" != "en-US"
    ///
    /// assert_eq!(li1.matches(&li2, false, false), false); // "en" != "en-US"
    /// assert_eq!(li1.matches(&li2, true, false), true); // "en-*-*-*" == "en-US"
    /// assert_eq!(li1.matches(&li2, false, true), false); // "en" != "en-*-US-*"
    /// assert_eq!(li1.matches(&li2, true, true), true); // "en-*-*-*" == "en-*-US-*"
    /// ```
    pub fn matches<O: AsRef<Self>>(
        &self,
        other: &O,
        self_as_range: bool,
        other_as_range: bool,
    ) -> bool {
        let other = other.as_ref();
        self.language
            .matches(&other.language, self_as_range, other_as_range)
            && subtag_matches(&self.script, &other.script, self_as_range, other_as_range)
            && subtag_matches(&self.region, &other.region, self_as_range, other_as_range)
            && subtags_match(
                &self.variants,
                &other.variants,
                self_as_range,
                other_as_range,
            )
    }

    /// Returns a vector of variants subtags of the `LanguageIdentifier`.
    ///
    /// # Examples
    ///
    /// ```
    /// use unic_langid_impl::LanguageIdentifier;
    ///
    /// let li1: LanguageIdentifier = "ca-ES-valencia".parse()
    ///     .expect("Parsing failed.");
    ///
    /// assert_eq!(li1.variants().map(|v| v.as_str()).collect::<Vec<_>>(), &["valencia"]);
    ///
    /// let li2: LanguageIdentifier = "de".parse()
    ///     .expect("Parsing failed.");
    ///
    /// assert_eq!(li2.variants().len(), 0);
    /// ```
    pub fn variants(&self) -> impl ExactSizeIterator<Item = &subtags::Variant> {
        let variants: &[_] = match self.variants {
            Some(ref v) => &**v,
            None => &[],
        };

        variants.iter()
    }

    /// Sets variant subtags of the `LanguageIdentifier`.
    ///
    /// # Examples
    ///
    /// ```
    /// use unic_langid_impl::LanguageIdentifier;
    ///
    /// let mut li: LanguageIdentifier = "ca-ES".parse()
    ///     .expect("Parsing failed.");
    ///
    /// li.set_variants(&["valencia".parse().expect("Parsing failed.")]);
    ///
    /// assert_eq!(li.to_string(), "ca-ES-valencia");
    /// ```
    pub fn set_variants(&mut self, variants: &[subtags::Variant]) {
        let mut v = variants.to_vec();

        if v.is_empty() {
            self.variants = None;
        } else {
            v.sort_unstable();
            v.dedup();
            self.variants = Some(v.into_boxed_slice());
        }
    }

    /// Tests if a variant subtag is present in the `LanguageIdentifier`.
    ///
    /// # Examples
    ///
    /// ```
    /// use unic_langid_impl::LanguageIdentifier;
    ///
    /// let mut li: LanguageIdentifier = "ca-ES-macos".parse()
    ///     .expect("Parsing failed.");
    ///
    /// assert_eq!(li.has_variant("valencia".parse().unwrap()), false);
    /// assert_eq!(li.has_variant("macos".parse().unwrap()), true);
    /// ```
    pub fn has_variant(&self, variant: subtags::Variant) -> bool {
        if let Some(variants) = &self.variants {
            variants.contains(&variant)
        } else {
            false
        }
    }

    /// Clears variant subtags of the `LanguageIdentifier`.
    ///
    /// # Examples
    ///
    /// ```
    /// use unic_langid_impl::LanguageIdentifier;
    ///
    /// let mut li: LanguageIdentifier = "ca-ES-valencia".parse()
    ///     .expect("Parsing failed.");
    ///
    /// li.clear_variants();
    ///
    /// assert_eq!(li.to_string(), "ca-ES");
    /// ```
    pub fn clear_variants(&mut self) {
        self.variants = None;
    }

    /// Extends the `LanguageIdentifier` adding likely subtags based
    /// on tables provided by CLDR.
    ///
    /// # Examples
    ///
    /// ```
    /// use unic_langid_impl::LanguageIdentifier;
    ///
    /// let mut li: LanguageIdentifier = "en-US".parse()
    ///     .expect("Parsing failed.");
    ///
    /// assert_eq!(li.maximize(), true);
    /// assert_eq!(li.to_string(), "en-Latn-US");
    /// ```
    #[cfg(feature = "likelysubtags")]
    pub fn maximize(&mut self) -> bool {
        if let Some(new_li) = likelysubtags::maximize(self.language, self.script, self.region) {
            self.language = new_li.0;
            self.script = new_li.1;
            self.region = new_li.2;
            true
        } else {
            false
        }
    }

    /// Extends the `LanguageIdentifier` removing likely subtags based
    /// on tables provided by CLDR.
    ///
    /// # Examples
    ///
    /// ```
    /// use unic_langid_impl::LanguageIdentifier;
    ///
    /// let mut li: LanguageIdentifier = "en-Latn-US".parse()
    ///     .expect("Parsing failed.");
    ///
    /// assert_eq!(li.minimize(), true);
    /// assert_eq!(li.to_string(), "en");
    /// ```
    #[cfg(feature = "likelysubtags")]
    pub fn minimize(&mut self) -> bool {
        if let Some(new_li) = likelysubtags::minimize(self.language, self.script, self.region) {
            self.language = new_li.0;
            self.script = new_li.1;
            self.region = new_li.2;
            true
        } else {
            false
        }
    }

    /// Returns character direction of the `LanguageIdentifier`.
    ///
    /// # Examples
    ///
    /// ```
    /// use unic_langid_impl::{LanguageIdentifier, CharacterDirection};
    ///
    /// let li1: LanguageIdentifier = "es-AR".parse()
    ///     .expect("Parsing failed.");
    /// let li2: LanguageIdentifier = "fa".parse()
    ///     .expect("Parsing failed.");
    ///
    /// assert_eq!(li1.character_direction(), CharacterDirection::LTR);
    /// assert_eq!(li2.character_direction(), CharacterDirection::RTL);
    /// ```
    pub fn character_direction(&self) -> CharacterDirection {
        match (self.language.into(), self.script) {
            (_, Some(script))
                if layout_table::SCRIPTS_CHARACTER_DIRECTION_RTL.contains(&script.into()) =>
            {
                CharacterDirection::RTL
            }
            (Some(lang), _) if layout_table::LANGS_CHARACTER_DIRECTION_RTL.contains(&lang) => {
                CharacterDirection::RTL
            }
            _ => CharacterDirection::LTR,
        }
    }
}

impl FromStr for LanguageIdentifier {
    type Err = LanguageIdentifierError;

    fn from_str(source: &str) -> Result<Self, Self::Err> {
        Self::from_bytes(source.as_bytes())
    }
}

impl AsRef<LanguageIdentifier> for LanguageIdentifier {
    #[inline(always)]
    fn as_ref(&self) -> &LanguageIdentifier {
        self
    }
}

impl std::fmt::Display for LanguageIdentifier {
    fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
        self.language.fmt(f)?;
        if let Some(ref script) = self.script {
            f.write_char('-')?;
            script.fmt(f)?;
        }
        if let Some(ref region) = self.region {
            f.write_char('-')?;
            region.fmt(f)?;
        }
        if let Some(variants) = &self.variants {
            for variant in variants.iter() {
                f.write_char('-')?;
                variant.fmt(f)?;
            }
        }
        Ok(())
    }
}

impl PartialEq<&str> for LanguageIdentifier {
    fn eq(&self, other: &&str) -> bool {
        self.to_string().as_str() == *other
    }
}

fn subtag_matches<P: PartialEq>(
    subtag1: &Option<P>,
    subtag2: &Option<P>,
    as_range1: bool,
    as_range2: bool,
) -> bool {
    (as_range1 && subtag1.is_none()) || (as_range2 && subtag2.is_none()) || subtag1 == subtag2
}

fn is_option_empty<P: PartialEq>(subtag: &Option<Box<[P]>>) -> bool {
    subtag.as_ref().map_or(true, |t| t.is_empty())
}

fn subtags_match<P: PartialEq>(
    subtag1: &Option<Box<[P]>>,
    subtag2: &Option<Box<[P]>>,
    as_range1: bool,
    as_range2: bool,
) -> bool {
    // or is some and is empty!
    (as_range1 && is_option_empty(subtag1))
        || (as_range2 && is_option_empty(subtag2))
        || subtag1 == subtag2
}

/// This is a best-effort operation that performs all available levels of canonicalization.
///
/// At the moment the operation will normalize casing and the separator, but in the future
/// it may also validate and update from deprecated subtags to canonical ones.
///
/// # Examples
///
/// ```
/// use unic_langid_impl::canonicalize;
///
/// assert_eq!(canonicalize("pL_latn_pl"), Ok("pl-Latn-PL".to_string()));
/// ```
pub fn canonicalize<S: AsRef<[u8]>>(input: S) -> Result<String, LanguageIdentifierError> {
    let lang_id = LanguageIdentifier::from_bytes(input.as_ref())?;
    Ok(lang_id.to_string())
}

#[test]
fn invalid_subtag() {
    assert!(LanguageIdentifier::from_bytes("en-ÁÁÁÁ".as_bytes()).is_err());
}