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

//! Splits `subject` into an chuncks according to given rules.

/// Splits `subject` into an array of characters.
///
/// # Arguments
///
/// * `subject` - The string to split into characters.
///
/// # Example
///
/// ```
/// use voca_rs::*;
/// split::chars("cloud");
/// // => ["c", "l", "o", "u", "d"]
/// ```
pub fn chars(subject: &str) -> Vec<&str> {
    if subject.is_empty() {
        return vec![""];
    }
    subject.split_terminator("").skip(1).collect::<Vec<_>>()
}

/// Splits `subject` into an array of chunks by `separator`.
///
/// # Arguments
///
/// * `subject` - The string to split into characters.
/// * `pattern` - The pattern to match the separator.
///
/// # Example
///
/// ```rust
/// use voca_rs::*;
/// split::split("rage against the dying of the light", "");
/// // => ["rage", "against", "the", "dying", "of", "the", "light"]
/// ```
pub fn split<'a>(subject: &'a str, pattern: &str) -> Vec<&'a str> {
    if subject.is_empty() {
        return vec![""];
    }
    if pattern.is_empty() {
        return vec![subject];
    }
    subject.split_terminator(pattern).collect::<Vec<_>>()
}

use unicode_segmentation::UnicodeSegmentation;
/// Splits `subject` into an array of words.
///
/// # Arguments
///
/// * `subject` - The string to split into characters.
///
/// # Example
///
/// ```rust
/// use voca_rs::*;
/// split::words("Sześć звёзд are dying");
/// // => ["Sześć", "звёзд", "are", "dying"]
/// split::words("LazyLoad with XMLHttpRequest and snake_case");
/// // => ["Lazy", "Load", "with", "XML", "Http", "Request", "and", "snake", "case"]
/// ```
pub fn words(subject: &str) -> Vec<&str> {
    fn split_camel_case(string: &str) -> Vec<&str> {
        // https://github.com/withoutboats/heck/blob/master/src/lib.rs
        #[derive(Clone, Copy, PartialEq)]
        enum WordMode {
            /// There have been no lowercase or uppercase characters in the current word.
            Boundary,
            /// The previous cased character in the current word is lowercase.
            Lowercase,
            /// The previous cased character in the current word is uppercase.
            Uppercase,
        }
        let mut words = Vec::new();
        let mut word_start = 0;
        let mut char_indices = string.char_indices().peekable();
        let mut mode = WordMode::Boundary;
        while let Some((c_idx, c)) = char_indices.next() {
            if let Some(&(next_idx, next)) = char_indices.peek() {
                let next_mode = if c.is_lowercase() {
                    WordMode::Lowercase
                } else if c.is_uppercase() {
                    WordMode::Uppercase
                } else {
                    mode
                };

                // not uppercase and next is uppercase
                if next_mode == WordMode::Lowercase && next.is_uppercase() {
                    words.push(&string[word_start..next_idx]);
                    word_start = next_idx;
                    mode = WordMode::Boundary;
                // Otherwise if current and previous are uppercase and next
                // is lowercase, word boundary before
                } else if mode == WordMode::Uppercase && c.is_uppercase() && next.is_lowercase() {
                    words.push(&string[word_start..c_idx]);
                    word_start = c_idx;
                    mode = WordMode::Boundary;
                // Otherwise no word boundary, just update the mode
                } else {
                    mode = next_mode;
                }
            }
        }
        words.push(&string[word_start..]);
        words
    }

    let splitting_punctuation = ['-', '_'];

    let split_by_whitespace_and_punctuation = subject
        .unicode_words()
        .flat_map(|w| w.split_terminator(|c| splitting_punctuation.contains(&c)))
        .filter(|w| !w.is_empty());

    let res = split_by_whitespace_and_punctuation.flat_map(split_camel_case);
    res.collect()
}

/// Splits `subject` into an array of graphemes
///
/// # Arguments
///
/// * `subject` - The string to split into characters.
///
/// # Example
///
/// ```rust
/// use voca_rs::*;
/// split::graphemes("a̐éö̲\r\n");
/// // => ["a̐", "é", "ö̲", "\r\n"]
/// ```
pub fn graphemes(subject: &str) -> Vec<&str> {
    if subject.is_empty() {
        return vec![""];
    }
    UnicodeSegmentation::graphemes(subject, true).collect::<Vec<&str>>()
}