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

use std::path::Path;

use crate::{
    common::{
        parse_break_test, parse_codepoint_association, CodepointIter,
        Codepoints, UcdFile, UcdFileByCodepoint,
    },
    error::Error,
};

/// A single row in the `auxiliary/WordBreakProperty.txt` file.
#[derive(Clone, Debug, Default, Eq, PartialEq)]
pub struct WordBreak {
    /// The codepoint or codepoint range for this entry.
    pub codepoints: Codepoints,
    /// The property value assigned to the codepoints in this entry.
    pub value: String,
}

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

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

impl std::str::FromStr for WordBreak {
    type Err = Error;

    fn from_str(line: &str) -> Result<WordBreak, Error> {
        let (codepoints, value) = parse_codepoint_association(line)?;
        Ok(WordBreak { codepoints, value: value.to_string() })
    }
}

/// A single row in the `auxiliary/WordBreakTest.txt` file.
///
/// This file defines tests for the word break algorithm.
#[derive(Clone, Debug, Default, Eq, PartialEq)]
pub struct WordBreakTest {
    /// Each string is a UTF-8 encoded group of codepoints that make up a
    /// single word.
    pub words: Vec<String>,
    /// A human readable description of this test.
    pub comment: String,
}

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

impl std::str::FromStr for WordBreakTest {
    type Err = Error;

    fn from_str(line: &str) -> Result<WordBreakTest, Error> {
        let (groups, comment) = parse_break_test(line)?;
        Ok(WordBreakTest { words: groups, comment })
    }
}

#[cfg(test)]
mod tests {
    use super::{WordBreak, WordBreakTest};

    #[test]
    fn parse_single() {
        let line = "0A83          ; Extend # Mc       GUJARATI SIGN VISARGA\n";
        let row: WordBreak = line.parse().unwrap();
        assert_eq!(row.codepoints, 0x0A83);
        assert_eq!(row.value, "Extend");
    }

    #[test]
    fn parse_range() {
        let line = "104A0..104A9  ; Numeric # Nd  [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE\n";
        let row: WordBreak = line.parse().unwrap();
        assert_eq!(row.codepoints, (0x104A0, 0x104A9));
        assert_eq!(row.value, "Numeric");
    }

    #[test]
    fn parse_test() {
        let line = "÷ 0031 ÷ 0027 × 0308 ÷ 0061 ÷ 0027 × 2060 ÷	#  ÷ [0.2] DIGIT ONE (Numeric) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [999.0] LATIN SMALL LETTER A (ALetter) ÷ [999.0] APOSTROPHE (Single_Quote) × [4.0] WORD JOINER (Format_FE) ÷ [0.3]";

        let row: WordBreakTest = line.parse().unwrap();
        assert_eq!(
            row.words,
            vec![
                "\u{0031}",
                "\u{0027}\u{0308}",
                "\u{0061}",
                "\u{0027}\u{2060}",
            ]
        );
        assert!(row.comment.contains("[4.0] COMBINING DIAERESIS (Extend_FE)"));
    }
}