summaryrefslogtreecommitdiffstats
path: root/vendor/ucd-parse/src/unicode_data.rs
blob: 9151f60b269c61b396c212c4c2bacaa7d38595fe (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
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
use std::fmt;
use std::iter;
use std::ops::Range;
use std::path::Path;
use std::str::FromStr;

use once_cell::sync::Lazy;
use regex::Regex;

use crate::common::{Codepoint, CodepointIter, UcdFile, UcdFileByCodepoint};
use crate::error::Error;

/// Represents a single row in the `UnicodeData.txt` file.
///
/// These fields were taken from UAX44, Table 9, as part of the documentation
/// for the
/// [`UnicodeData.txt` file](https://www.unicode.org/reports/tr44/#UnicodeData.txt).
#[derive(Clone, Debug, Default, Eq, PartialEq)]
pub struct UnicodeData {
    /// The codepoint corresponding to this row.
    pub codepoint: Codepoint,
    /// The name of this codepoint.
    pub name: String,
    /// The "general category" of this codepoint.
    pub general_category: String,
    /// The class of this codepoint used in the Canonical Ordering Algorithm.
    ///
    /// Note that some classes map to a particular symbol. See
    /// [UAX44, Table 15](https://www.unicode.org/reports/tr44/#Canonical_Combining_Class_Values).
    pub canonical_combining_class: u8,
    /// The bidirectional class of this codepoint.
    ///
    /// Possible values are listed in
    /// [UAX44, Table 13](https://www.unicode.org/reports/tr44/#Bidi_Class_Values).
    pub bidi_class: String,
    /// The decomposition mapping for this codepoint. This includes its
    /// formatting tag (if present).
    pub decomposition: UnicodeDataDecomposition,
    /// A decimal numeric representation of this codepoint, if it has the
    /// property `Numeric_Type=Decimal`.
    pub numeric_type_decimal: Option<u8>,
    /// A decimal numeric representation of this codepoint, if it has the
    /// property `Numeric_Type=Digit`. Note that while this field is still
    /// populated for existing codepoints, no new codepoints will have this
    /// field populated.
    pub numeric_type_digit: Option<u8>,
    /// A decimal or rational numeric representation of this codepoint, if it
    /// has the property `Numeric_Type=Numeric`.
    pub numeric_type_numeric: Option<UnicodeDataNumeric>,
    /// A boolean indicating whether this codepoint is "mirrored" in
    /// bidirectional text.
    pub bidi_mirrored: bool,
    /// The "old" Unicode 1.0 or ISO 6429 name of this codepoint. Note that
    /// this field is empty unless it is significantly different from
    /// the `name` field.
    pub unicode1_name: String,
    /// The ISO 10464 comment field. This no longer contains any non-NULL
    /// values.
    pub iso_comment: String,
    /// This codepoint's simple uppercase mapping, if it exists.
    pub simple_uppercase_mapping: Option<Codepoint>,
    /// This codepoint's simple lowercase mapping, if it exists.
    pub simple_lowercase_mapping: Option<Codepoint>,
    /// This codepoint's simple titlecase mapping, if it exists.
    pub simple_titlecase_mapping: Option<Codepoint>,
}

impl UcdFile for UnicodeData {
    fn relative_file_path() -> &'static Path {
        Path::new("UnicodeData.txt")
    }
}

impl UcdFileByCodepoint for UnicodeData {
    fn codepoints(&self) -> CodepointIter {
        self.codepoint.into_iter()
    }
}

impl UnicodeData {
    /// Returns true if and only if this record corresponds to the start of a
    /// range.
    pub fn is_range_start(&self) -> bool {
        self.name.starts_with('<')
            && self.name.ends_with('>')
            && self.name.contains("First")
    }

    /// Returns true if and only if this record corresponds to the end of a
    /// range.
    pub fn is_range_end(&self) -> bool {
        self.name.starts_with('<')
            && self.name.ends_with('>')
            && self.name.contains("Last")
    }
}

impl FromStr for UnicodeData {
    type Err = Error;

    fn from_str(line: &str) -> Result<UnicodeData, Error> {
        static PARTS: Lazy<Regex> = Lazy::new(|| {
            Regex::new(
                r"(?x)
                ^
                ([A-Z0-9]+);  #  1; codepoint
                ([^;]+);      #  2; name
                ([^;]+);      #  3; general category
                ([0-9]+);     #  4; canonical combining class
                ([^;]+);      #  5; bidi class
                ([^;]*);      #  6; decomposition
                ([0-9]*);     #  7; numeric type decimal
                ([0-9]*);     #  8; numeric type digit
                ([-0-9/]*);   #  9; numeric type numeric
                ([YN]);       # 10; bidi mirrored
                ([^;]*);      # 11; unicode1 name
                ([^;]*);      # 12; ISO comment
                ([^;]*);      # 13; simple uppercase mapping
                ([^;]*);      # 14; simple lowercase mapping
                ([^;]*)       # 15; simple titlecase mapping
                $
                ",
            )
            .unwrap()
        });
        let caps = match PARTS.captures(line.trim()) {
            Some(caps) => caps,
            None => return err!("invalid UnicodeData line"),
        };
        let capget = |n| caps.get(n).unwrap().as_str();
        let mut data = UnicodeData::default();

        data.codepoint = capget(1).parse()?;
        data.name = capget(2).to_string();
        data.general_category = capget(3).to_string();
        data.canonical_combining_class = match capget(4).parse() {
            Ok(n) => n,
            Err(err) => {
                return err!(
                    "failed to parse canonical combining class '{}': {}",
                    capget(4),
                    err
                )
            }
        };
        data.bidi_class = capget(5).to_string();
        if !caps[6].is_empty() {
            data.decomposition = caps[6].parse()?;
        } else {
            data.decomposition.push(data.codepoint)?;
        }
        if !capget(7).is_empty() {
            data.numeric_type_decimal = Some(match capget(7).parse() {
                Ok(n) => n,
                Err(err) => {
                    return err!(
                        "failed to parse numeric type decimal '{}': {}",
                        capget(7),
                        err
                    )
                }
            });
        }
        if !capget(8).is_empty() {
            data.numeric_type_digit = Some(match capget(8).parse() {
                Ok(n) => n,
                Err(err) => {
                    return err!(
                        "failed to parse numeric type digit '{}': {}",
                        capget(8),
                        err
                    )
                }
            });
        }
        if !capget(9).is_empty() {
            data.numeric_type_numeric = Some(capget(9).parse()?);
        }
        data.bidi_mirrored = capget(10) == "Y";
        data.unicode1_name = capget(11).to_string();
        data.iso_comment = capget(12).to_string();
        if !capget(13).is_empty() {
            data.simple_uppercase_mapping = Some(capget(13).parse()?);
        }
        if !capget(14).is_empty() {
            data.simple_lowercase_mapping = Some(capget(14).parse()?);
        }
        if !capget(15).is_empty() {
            data.simple_titlecase_mapping = Some(capget(15).parse()?);
        }
        Ok(data)
    }
}

impl fmt::Display for UnicodeData {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        write!(f, "{};", self.codepoint)?;
        write!(f, "{};", self.name)?;
        write!(f, "{};", self.general_category)?;
        write!(f, "{};", self.canonical_combining_class)?;
        write!(f, "{};", self.bidi_class)?;
        if self.decomposition.is_canonical()
            && self.decomposition.mapping() == &[self.codepoint]
        {
            write!(f, ";")?;
        } else {
            write!(f, "{};", self.decomposition)?;
        }
        if let Some(n) = self.numeric_type_decimal {
            write!(f, "{};", n)?;
        } else {
            write!(f, ";")?;
        }
        if let Some(n) = self.numeric_type_digit {
            write!(f, "{};", n)?;
        } else {
            write!(f, ";")?;
        }
        if let Some(n) = self.numeric_type_numeric {
            write!(f, "{};", n)?;
        } else {
            write!(f, ";")?;
        }
        write!(f, "{};", if self.bidi_mirrored { "Y" } else { "N" })?;
        write!(f, "{};", self.unicode1_name)?;
        write!(f, "{};", self.iso_comment)?;
        if let Some(cp) = self.simple_uppercase_mapping {
            write!(f, "{};", cp)?;
        } else {
            write!(f, ";")?;
        }
        if let Some(cp) = self.simple_lowercase_mapping {
            write!(f, "{};", cp)?;
        } else {
            write!(f, ";")?;
        }
        if let Some(cp) = self.simple_titlecase_mapping {
            write!(f, "{}", cp)?;
        }
        Ok(())
    }
}

/// Represents a decomposition mapping of a single row in the
/// `UnicodeData.txt` file.
#[derive(Clone, Debug, Default, Eq, PartialEq)]
pub struct UnicodeDataDecomposition {
    /// The formatting tag associated with this mapping, if present.
    pub tag: Option<UnicodeDataDecompositionTag>,
    /// The number of codepoints in this mapping.
    pub len: usize,
    /// The codepoints in the mapping. Entries beyond `len` in the mapping
    /// are always U+0000. If no mapping was present, then this always contains
    /// a single codepoint corresponding to this row's character.
    pub mapping: [Codepoint; 18],
}

impl UnicodeDataDecomposition {
    /// Create a new decomposition mapping with the given tag and codepoints.
    ///
    /// If there are too many codepoints, then an error is returned.
    pub fn new(
        tag: Option<UnicodeDataDecompositionTag>,
        mapping: &[Codepoint],
    ) -> Result<UnicodeDataDecomposition, Error> {
        let mut x = UnicodeDataDecomposition::default();
        x.tag = tag;
        for &cp in mapping {
            x.push(cp)?;
        }
        Ok(x)
    }

    /// Add a new codepoint to this decomposition's mapping.
    ///
    /// If the mapping is already full, then this returns an error.
    pub fn push(&mut self, cp: Codepoint) -> Result<(), Error> {
        if self.len >= self.mapping.len() {
            return err!(
                "invalid decomposition mapping (too many codepoints)"
            );
        }
        self.mapping[self.len] = cp;
        self.len += 1;
        Ok(())
    }

    /// Return the mapping as a slice of codepoints. The slice returned
    /// has length equivalent to the number of codepoints in this mapping.
    pub fn mapping(&self) -> &[Codepoint] {
        &self.mapping[..self.len]
    }

    /// Returns true if and only if this decomposition mapping is canonical.
    pub fn is_canonical(&self) -> bool {
        self.tag.is_none()
    }
}

impl FromStr for UnicodeDataDecomposition {
    type Err = Error;

    fn from_str(s: &str) -> Result<UnicodeDataDecomposition, Error> {
        static WITH_TAG: Lazy<Regex> = Lazy::new(|| {
            Regex::new(r"^(?:<(?P<tag>[^>]+)>)?\s*(?P<chars>[\s0-9A-F]+)$")
                .unwrap()
        });
        static CHARS: Lazy<Regex> =
            Lazy::new(|| Regex::new(r"[0-9A-F]+").unwrap());
        if s.is_empty() {
            return err!(
                "expected non-empty string for \
                 UnicodeDataDecomposition value"
            );
        }
        let caps = match WITH_TAG.captures(s) {
            Some(caps) => caps,
            None => return err!("invalid decomposition value"),
        };
        let mut decomp = UnicodeDataDecomposition::default();
        let mut codepoints = s;
        if let Some(m) = caps.name("tag") {
            decomp.tag = Some(m.as_str().parse()?);
            codepoints = &caps["chars"];
        }
        for m in CHARS.find_iter(codepoints) {
            let cp = m.as_str().parse()?;
            decomp.push(cp)?;
        }
        Ok(decomp)
    }
}

impl fmt::Display for UnicodeDataDecomposition {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        if let Some(ref tag) = self.tag {
            write!(f, "<{}> ", tag)?;
        }
        let mut first = true;
        for cp in self.mapping() {
            if !first {
                write!(f, " ")?;
            }
            first = false;
            write!(f, "{}", cp)?;
        }
        Ok(())
    }
}

/// The formatting tag on a decomposition mapping.
///
/// This is taken from
/// [UAX44, Table 14](https://www.unicode.org/reports/tr44/#Character_Decomposition_Mappings).
#[derive(Clone, Debug, Eq, PartialEq)]
pub enum UnicodeDataDecompositionTag {
    /// <font>
    Font,
    /// <noBreak>
    NoBreak,
    /// <initial>
    Initial,
    /// <medial>
    Medial,
    /// <final>
    Final,
    /// <isolated>
    Isolated,
    /// <circle>
    Circle,
    /// <super>
    Super,
    /// <sub>
    Sub,
    /// <vertical>
    Vertical,
    /// <wide>
    Wide,
    /// <narrow>
    Narrow,
    /// <small>
    Small,
    /// <square>
    Square,
    /// <fraction>
    Fraction,
    /// <compat>
    Compat,
}

impl FromStr for UnicodeDataDecompositionTag {
    type Err = Error;

    fn from_str(s: &str) -> Result<UnicodeDataDecompositionTag, Error> {
        use self::UnicodeDataDecompositionTag::*;
        Ok(match s {
            "font" => Font,
            "noBreak" => NoBreak,
            "initial" => Initial,
            "medial" => Medial,
            "final" => Final,
            "isolated" => Isolated,
            "circle" => Circle,
            "super" => Super,
            "sub" => Sub,
            "vertical" => Vertical,
            "wide" => Wide,
            "narrow" => Narrow,
            "small" => Small,
            "square" => Square,
            "fraction" => Fraction,
            "compat" => Compat,
            _ => return err!("invalid decomposition formatting tag: {}", s),
        })
    }
}

impl fmt::Display for UnicodeDataDecompositionTag {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        use self::UnicodeDataDecompositionTag::*;
        let s = match *self {
            Font => "font",
            NoBreak => "noBreak",
            Initial => "initial",
            Medial => "medial",
            Final => "final",
            Isolated => "isolated",
            Circle => "circle",
            Super => "super",
            Sub => "sub",
            Vertical => "vertical",
            Wide => "wide",
            Narrow => "narrow",
            Small => "small",
            Square => "square",
            Fraction => "fraction",
            Compat => "compat",
        };
        write!(f, "{}", s)
    }
}

/// A numeric value corresponding to characters with `Numeric_Type=Numeric`.
///
/// A numeric value can either be a signed integer or a rational number.
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
pub enum UnicodeDataNumeric {
    /// An integer.
    Integer(i64),
    /// A rational number. The first is the numerator and the latter is the
    /// denominator.
    Rational(i64, i64),
}

impl FromStr for UnicodeDataNumeric {
    type Err = Error;

    fn from_str(s: &str) -> Result<UnicodeDataNumeric, Error> {
        if s.is_empty() {
            return err!(
                "expected non-empty string for UnicodeDataNumeric value"
            );
        }
        if let Some(pos) = s.find('/') {
            let (snum, sden) = (&s[..pos], &s[pos + 1..]);
            let num = match snum.parse() {
                Ok(num) => num,
                Err(err) => {
                    return err!(
                        "invalid integer numerator '{}': {}",
                        snum,
                        err
                    );
                }
            };
            let den = match sden.parse() {
                Ok(den) => den,
                Err(err) => {
                    return err!(
                        "invalid integer denominator '{}': {}",
                        sden,
                        err
                    );
                }
            };
            Ok(UnicodeDataNumeric::Rational(num, den))
        } else {
            match s.parse() {
                Ok(den) => Ok(UnicodeDataNumeric::Integer(den)),
                Err(err) => {
                    return err!(
                        "invalid integer denominator '{}': {}",
                        s,
                        err
                    );
                }
            }
        }
    }
}

impl fmt::Display for UnicodeDataNumeric {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        match *self {
            UnicodeDataNumeric::Integer(n) => write!(f, "{}", n),
            UnicodeDataNumeric::Rational(n, d) => write!(f, "{}/{}", n, d),
        }
    }
}

/// An iterator adapter that expands rows in `UnicodeData.txt`.
///
/// Throughout `UnicodeData.txt`, some assigned codepoints are not explicitly
/// represented. Instead, they are represented by a pair of rows, indicating
/// a range of codepoints with the same properties. For example, the Hangul
/// syllable codepoints are represented by these two rows:
///
/// ```ignore
/// AC00;<Hangul Syllable, First>;Lo;0;L;;;;;N;;;;;
/// D7A3;<Hangul Syllable, Last>;Lo;0;L;;;;;N;;;;;
/// ```
///
/// This iterator will wrap any iterator of `UnicodeData` and, when a range of
/// Unicode codepoints is found, it will be expanded to the appropriate
/// sequence of `UnicodeData` values. Note that all such expanded records will
/// have an empty name.
pub struct UnicodeDataExpander<I: Iterator> {
    /// The underlying iterator.
    it: iter::Peekable<I>,
    /// A range of codepoints to emit when we've found a pair. Otherwise,
    /// `None`.
    range: CodepointRange,
}

struct CodepointRange {
    /// The codepoint range.
    range: Range<u32>,
    /// The start record. All subsequent records in this range are generated
    /// by cloning this and updating the codepoint/name.
    start_record: UnicodeData,
}

impl<I: Iterator<Item = UnicodeData>> UnicodeDataExpander<I> {
    /// Create a new iterator that expands pairs of `UnicodeData` range
    /// records. All other records are passed through as-is.
    pub fn new<T>(it: T) -> UnicodeDataExpander<I>
    where
        T: IntoIterator<IntoIter = I, Item = I::Item>,
    {
        UnicodeDataExpander {
            it: it.into_iter().peekable(),
            range: CodepointRange {
                range: 0..0,
                start_record: UnicodeData::default(),
            },
        }
    }
}

impl<I: Iterator<Item = UnicodeData>> Iterator for UnicodeDataExpander<I> {
    type Item = UnicodeData;

    fn next(&mut self) -> Option<UnicodeData> {
        if let Some(udata) = self.range.next() {
            return Some(udata);
        }
        let row1 = match self.it.next() {
            None => return None,
            Some(row1) => row1,
        };
        if !row1.is_range_start()
            || !self.it.peek().map_or(false, |row2| row2.is_range_end())
        {
            return Some(row1);
        }
        let row2 = self.it.next().unwrap();
        self.range = CodepointRange {
            range: row1.codepoint.value()..(row2.codepoint.value() + 1),
            start_record: row1,
        };
        self.next()
    }
}

impl Iterator for CodepointRange {
    type Item = UnicodeData;

    fn next(&mut self) -> Option<UnicodeData> {
        let cp = match self.range.next() {
            None => return None,
            Some(cp) => cp,
        };
        Some(UnicodeData {
            codepoint: Codepoint::from_u32(cp).unwrap(),
            name: "".to_string(),
            ..self.start_record.clone()
        })
    }
}

#[cfg(test)]
mod tests {
    use crate::common::Codepoint;

    use super::{
        UnicodeData, UnicodeDataDecomposition, UnicodeDataDecompositionTag,
        UnicodeDataNumeric,
    };

    fn codepoint(n: u32) -> Codepoint {
        Codepoint::from_u32(n).unwrap()
    }

    fn s(string: &str) -> String {
        string.to_string()
    }

    #[test]
    fn parse1() {
        let line = "249D;PARENTHESIZED LATIN SMALL LETTER B;So;0;L;<compat> 0028 0062 0029;;;;N;;;;;\n";
        let data: UnicodeData = line.parse().unwrap();
        assert_eq!(
            data,
            UnicodeData {
                codepoint: codepoint(0x249d),
                name: s("PARENTHESIZED LATIN SMALL LETTER B"),
                general_category: s("So"),
                canonical_combining_class: 0,
                bidi_class: s("L"),
                decomposition: UnicodeDataDecomposition::new(
                    Some(UnicodeDataDecompositionTag::Compat),
                    &[codepoint(0x28), codepoint(0x62), codepoint(0x29)],
                )
                .unwrap(),
                numeric_type_decimal: None,
                numeric_type_digit: None,
                numeric_type_numeric: None,
                bidi_mirrored: false,
                unicode1_name: s(""),
                iso_comment: s(""),
                simple_uppercase_mapping: None,
                simple_lowercase_mapping: None,
                simple_titlecase_mapping: None,
            }
        );
    }

    #[test]
    fn parse2() {
        let line = "000D;<control>;Cc;0;B;;;;;N;CARRIAGE RETURN (CR);;;;\n";
        let data: UnicodeData = line.parse().unwrap();
        assert_eq!(
            data,
            UnicodeData {
                codepoint: codepoint(0x000D),
                name: s("<control>"),
                general_category: s("Cc"),
                canonical_combining_class: 0,
                bidi_class: s("B"),
                decomposition: UnicodeDataDecomposition::new(
                    None,
                    &[codepoint(0x000D)]
                )
                .unwrap(),
                numeric_type_decimal: None,
                numeric_type_digit: None,
                numeric_type_numeric: None,
                bidi_mirrored: false,
                unicode1_name: s("CARRIAGE RETURN (CR)"),
                iso_comment: s(""),
                simple_uppercase_mapping: None,
                simple_lowercase_mapping: None,
                simple_titlecase_mapping: None,
            }
        );
    }

    #[test]
    fn parse3() {
        let line = "00BC;VULGAR FRACTION ONE QUARTER;No;0;ON;<fraction> 0031 2044 0034;;;1/4;N;FRACTION ONE QUARTER;;;;\n";
        let data: UnicodeData = line.parse().unwrap();
        assert_eq!(
            data,
            UnicodeData {
                codepoint: codepoint(0x00BC),
                name: s("VULGAR FRACTION ONE QUARTER"),
                general_category: s("No"),
                canonical_combining_class: 0,
                bidi_class: s("ON"),
                decomposition: UnicodeDataDecomposition::new(
                    Some(UnicodeDataDecompositionTag::Fraction),
                    &[codepoint(0x31), codepoint(0x2044), codepoint(0x34)],
                )
                .unwrap(),
                numeric_type_decimal: None,
                numeric_type_digit: None,
                numeric_type_numeric: Some(UnicodeDataNumeric::Rational(1, 4)),
                bidi_mirrored: false,
                unicode1_name: s("FRACTION ONE QUARTER"),
                iso_comment: s(""),
                simple_uppercase_mapping: None,
                simple_lowercase_mapping: None,
                simple_titlecase_mapping: None,
            }
        );
    }

    #[test]
    fn parse4() {
        let line = "0041;LATIN CAPITAL LETTER A;Lu;0;L;;;;;N;;;;0061;\n";
        let data: UnicodeData = line.parse().unwrap();
        assert_eq!(
            data,
            UnicodeData {
                codepoint: codepoint(0x0041),
                name: s("LATIN CAPITAL LETTER A"),
                general_category: s("Lu"),
                canonical_combining_class: 0,
                bidi_class: s("L"),
                decomposition: UnicodeDataDecomposition::new(
                    None,
                    &[codepoint(0x0041)]
                )
                .unwrap(),
                numeric_type_decimal: None,
                numeric_type_digit: None,
                numeric_type_numeric: None,
                bidi_mirrored: false,
                unicode1_name: s(""),
                iso_comment: s(""),
                simple_uppercase_mapping: None,
                simple_lowercase_mapping: Some(codepoint(0x0061)),
                simple_titlecase_mapping: None,
            }
        );
    }

    #[test]
    fn parse5() {
        let line = "0F33;TIBETAN DIGIT HALF ZERO;No;0;L;;;;-1/2;N;;;;;\n";
        let data: UnicodeData = line.parse().unwrap();
        assert_eq!(
            data,
            UnicodeData {
                codepoint: codepoint(0x0F33),
                name: s("TIBETAN DIGIT HALF ZERO"),
                general_category: s("No"),
                canonical_combining_class: 0,
                bidi_class: s("L"),
                decomposition: UnicodeDataDecomposition::new(
                    None,
                    &[codepoint(0x0F33)]
                )
                .unwrap(),
                numeric_type_decimal: None,
                numeric_type_digit: None,
                numeric_type_numeric: Some(UnicodeDataNumeric::Rational(
                    -1, 2
                )),
                bidi_mirrored: false,
                unicode1_name: s(""),
                iso_comment: s(""),
                simple_uppercase_mapping: None,
                simple_lowercase_mapping: None,
                simple_titlecase_mapping: None,
            }
        );
    }

    #[test]
    fn expander() {
        use super::UnicodeDataExpander;
        use crate::common::UcdLineParser;

        let data = "\
ABF9;MEETEI MAYEK DIGIT NINE;Nd;0;L;;9;9;9;N;;;;;
AC00;<Hangul Syllable, First>;Lo;0;L;;;;;N;;;;;
D7A3;<Hangul Syllable, Last>;Lo;0;L;;;;;N;;;;;
D7B0;HANGUL JUNGSEONG O-YEO;Lo;0;L;;;;;N;;;;;
";
        let records = UcdLineParser::new(None, data.as_bytes())
            .collect::<Result<Vec<_>, _>>()
            .unwrap();
        assert_eq!(UnicodeDataExpander::new(records).count(), 11174);
    }
}