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

use unicode_segmentation::UnicodeSegmentation;

pub trait TruncateToBoundary {
    fn truncate_to_boundary(&self, chars: usize) -> &Self;
    fn truncate_to_byte_offset(&self, count: usize) -> &Self;
}

impl TruncateToBoundary for str {
    /// Truncates a given string to a set numerical boundary.
    /// If the boundary splits a grapheme (e.g., when a character is a resultant mix of more than 1 utf-8 character, like some emojis)
    /// the truncation will scale back to the previous character.
    /// If the truncation ends with white space - this will be trimmed.
    /// Should the truncation boundary exceed the string's size - the original string will return (including whitespace).
    ///
    /// # Examples:
    ///
    ///
    /// ```
    /// use truncrate::*;
    ///
    /// let s = "🤚🏾a🤚🏾 ";
    ///
    /// assert_eq!(s.truncate_to_boundary(1), "");
    /// assert_eq!(s.truncate_to_boundary(2), "🤚🏾");
    /// assert_eq!(s.truncate_to_boundary(3), "🤚🏾a");
    /// assert_eq!(s.truncate_to_boundary(4), "🤚🏾a");
    /// assert_eq!(s.truncate_to_boundary(5), "🤚🏾a🤚🏾");
    /// assert_eq!(s.truncate_to_boundary(10), s);
    ///```
    fn truncate_to_boundary(&self, chars: usize) -> &Self {
        if chars == 0 {
            return &self[..0];
        }

        let result = match self.char_indices().nth(chars) {
            None => self,
            Some((boundary, _)) => self.truncate_to_byte_offset(boundary)
        };
        result
    }
    /// Truncates a given string based on the provided byte-offset.
    /// If the offset splits a grapheme the truncation will scale back to the previous character.
    /// If the truncation ends with white space - this will be trimmed.
    /// Should the offset exceed the strings size - the original string will return (including whitespace).
    /// # Examples:
    ///
    /// ```
    /// use truncrate::*;
    ///
    /// let s = "🤚🏾a🤚 ";
    ///  // where "🤚🏾" = 8 bytes
    /// assert_eq!(s.truncate_to_byte_offset(0), "");
    /// assert_eq!(s.truncate_to_byte_offset(7), "");
    /// assert_eq!(s.truncate_to_byte_offset(8), "🤚🏾");
    /// assert_eq!(s.truncate_to_byte_offset(9), "🤚🏾a");
    /// assert_eq!(s.truncate_to_byte_offset(10), "🤚🏾a");
    /// assert_eq!(s.truncate_to_byte_offset(18), s);
    /// ```
    fn truncate_to_byte_offset(&self, boundary: usize) -> &Self {

        if boundary > self.len() {
            return &self
        }
        let mut grapheme_iter = self
        .grapheme_indices(true)
        .rev()
        .skip_while(move |(n, _)| *n > boundary);
        let mut bytecount = boundary;
        if let Some((grapheme_boundary, _)) = grapheme_iter.next() {
            bytecount = grapheme_boundary;
        }

        &self[..bytecount].trim_end()
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test() {
        let s = "🤚🏾a🤚🏾 🤚🏾\t 🤚🏾";

        assert_eq!(s.truncate_to_boundary(1), "");
        assert_eq!(s.truncate_to_boundary(2), "🤚🏾");
        assert_eq!(s.truncate_to_boundary(3), "🤚🏾a");
        assert_eq!(s.truncate_to_boundary(4), "🤚🏾a");
        assert_eq!(s.truncate_to_boundary(6), "🤚🏾a🤚🏾");
        assert_eq!(s.truncate_to_boundary(7), "🤚🏾a🤚🏾");
        assert_eq!(s.truncate_to_boundary(8), "🤚🏾a🤚🏾 🤚🏾");
        assert_eq!(s.truncate_to_boundary(9), "🤚🏾a🤚🏾 🤚🏾");
        assert_eq!(s.truncate_to_boundary(10), "🤚🏾a🤚🏾 🤚🏾");
        assert_eq!(s.truncate_to_boundary(11), "🤚🏾a🤚🏾 🤚🏾");
        assert_eq!(s.truncate_to_boundary(12), s);
    }

    #[test]
    fn test_non_trucated_string() {
        let s = "🤚🏾a🤚🏾 🤚🏾  🤚🏾";

        assert_eq!(s.truncate_to_boundary(100), s);
        assert_eq!(s.truncate_to_boundary(s.chars().count()), s);
        assert_eq!(s.truncate_to_boundary(0), "");
    }

    #[test]
    fn truncate_non_split_grapheme() {
        let s = "🤚🏾a🤚 🤚🏾\t 🤚    ";

        assert_eq!(s.truncate_to_boundary(4), "🤚🏾a🤚");
        assert_eq!(s.truncate_to_boundary(5), "🤚🏾a🤚");
        assert_eq!(s.truncate_to_boundary(6), "🤚🏾a🤚");
        assert_eq!(s.truncate_to_boundary(7), "🤚🏾a🤚 🤚🏾");
        assert_eq!(s.truncate_to_boundary(8), "🤚🏾a🤚 🤚🏾");
        assert_eq!(s.truncate_to_boundary(9), "🤚🏾a🤚 🤚🏾");
        assert_eq!(s.truncate_to_boundary(10), "🤚🏾a🤚 🤚🏾\t 🤚");
        assert_eq!(s.truncate_to_boundary(11), "🤚🏾a🤚 🤚🏾\t 🤚");
        assert_eq!(s.truncate_to_boundary(12), "🤚🏾a🤚 🤚🏾\t 🤚");
        assert_eq!(s.truncate_to_boundary(20), s);
    }

    #[test]
    fn truncate_non_split_grapheme_with_whitespace() {
        let s = " 🤚🏾a🤚 🤚🏾\t 🤚    ";

        assert_eq!(s.truncate_to_boundary(5), " 🤚🏾a🤚");
        assert_eq!(s.truncate_to_boundary(6), " 🤚🏾a🤚");
        assert_eq!(s.truncate_to_boundary(7), " 🤚🏾a🤚");
        assert_eq!(s.truncate_to_boundary(8), " 🤚🏾a🤚 🤚🏾");
        assert_eq!(s.truncate_to_boundary(9), " 🤚🏾a🤚 🤚🏾");
        assert_eq!(s.truncate_to_boundary(10), " 🤚🏾a🤚 🤚🏾");
        assert_eq!(s.truncate_to_boundary(11), " 🤚🏾a🤚 🤚🏾\t 🤚");
        assert_eq!(s.truncate_to_boundary(12), " 🤚🏾a🤚 🤚🏾\t 🤚");
        assert_eq!(s.truncate_to_boundary(13), " 🤚🏾a🤚 🤚🏾\t 🤚");
        assert_eq!(s.truncate_to_boundary(21), s);
    }
    #[test]
    fn truncate_to_bytes(){
        let s = "🤚🏾a🤚 ";

        assert_eq!(s.truncate_to_byte_offset(1), "");
        assert_eq!(s.truncate_to_byte_offset(2), "");
        assert_eq!(s.truncate_to_byte_offset(13), "🤚🏾a🤚");
        assert_eq!(s.truncate_to_byte_offset(14), "🤚🏾a🤚");
        assert_eq!(s.truncate_to_byte_offset(18), s);
        assert_eq!(s.truncate_to_byte_offset(100), s);
    }
}