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

//* # UTF8 Slice
//* A lightweight heapless way to do slicing on unicode strings in Rust.
//*
//* # What does the library provide
//* This library provides 4 utility functions to deal with unicode slices.
//*
//* ## `utf8_slice::slice(s: &str, begin: usize, end: usize) -> &str`
//* This will do the same as `&s[begin..end]`, but now taking into account utf8 characters.
//*
//* ## `utf8_slice::from(s: &str, begin: usize) -> &str`
//* This will do the same as `&s[begin..]`, but now taking into account utf8 characters.
//*
//* ## `utf8_slice::till(s: &str, end: usize) -> &str`
//* This will do the same as `&s[..end]`, but now taking into account utf8 characters.
//*
//* ## `utf8_slice::len(s: &str) -> usize`
//* This will do the same as `s.len()`, but now taking into account utf8 characters.
//* # License
//* MIT
//*
//* # Examples
//*
//* ```
//* let s = "The 🚀 goes to the 🌑!";
//*
//* let rocket = utf8_slice::slice(s, 4, 5);
//* # assert_eq!(utf8_slice::slice(s, 4, 5), "🚀");
//* // Will equal "🚀"
//* ```

/// Fetches a slice of a string from a begin to an end index
/// taking into account utf8/unicode character indices.
///
/// # Arguments
///
/// * `s` - An input string to take the slice from
/// * `begin` - Where the slice begins
/// * `end` - Where the slice ends
///
/// # Examples
///
/// ```
/// let s = "The 🚀 goes to the 🌑!";
///
/// let rocket = utf8_slice::slice(s, 4, 5);
/// # assert_eq!(utf8_slice::slice(s, 4, 5), "🚀");
/// // Will equal "🚀"
/// ```
///
/// # Note
/// * Will return an empty string for invalid indices *
pub fn slice(s: &str, begin: usize, end: usize) -> &str {
    if end < begin {
        return "";
    }

    s.char_indices()
        .nth(begin)
        .and_then(|(start_pos, _)| {
            if end >= len(s) {
                return Some(&s[start_pos..]);
            }

            s[start_pos..]
                .char_indices()
                .nth(end - begin)
                .map(|(end_pos, _)| &s[start_pos..start_pos + end_pos])
        })
        .unwrap_or("")
}

/// Fetches a slice of a string from a starting index
/// taking into account utf8/unicode character indices.
///
/// # Arguments
///
/// * `s` - An input string to take the slice from
/// * `begin` - Where the slice begins
///
/// # Examples
///
/// ```
/// let s = "The 🚀 goes to the 🌑!";
///
/// let rocket_goes_to_the_moon = utf8_slice::from(s, 4);
/// # assert_eq!(utf8_slice::from(s, 4), "🚀 goes to the 🌑!");
/// // Will equal "🚀 goes to the 🌑!"
/// ```
///
/// # Note
/// * Will return an empty string for invalid indices *
pub fn from(s: &str, begin: usize) -> &str {
    slice(s, begin, len(s))
}

/// Fetches a slice of a string until an ending index
/// taking into account utf8/unicode character indices.
///
/// # Arguments
///
/// * `s` - An input string to take the slice from
/// * `end` - Where the slice ends
///
/// # Examples
///
/// ```
/// let s = "The 🚀 goes to the 🌑!";
///
/// let the_rocket = utf8_slice::till(s, 5);
/// # assert_eq!(utf8_slice::till(s, 4), "The 🚀");
/// // Will equal "The 🚀"
/// ```
///
/// # Note
/// * Will return an empty string for invalid indices *
pub fn till(s: &str, end: usize) -> &str {
    slice(s, 0, end)
}

/// Fetches the length in characters of an utf8/unicode string
///
/// # Arguments
///
/// * `s` - The string of which to fetch the length
pub fn len(s: &str) -> usize {
    s.chars().count()
}

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

    #[test]
    fn test_same_as_std_slice() {
        let s = "xjfdlskfaj sdfjlkj";
        for i in 0..s.len() {
            for j in i..s.len() + 1 {
                assert_eq!(&s[i..j], slice(s, i, j));
            }
        }
    }

    #[test]
    fn test_slice() {
        assert_eq!(slice("\u{345}ab\u{898}xyz", 1, 4), "ab\u{898}");
        assert_eq!(slice("\u{345}ab\u{898}xyz", 0, 4), "\u{345}ab\u{898}");
        assert_eq!(slice("\u{345}ab\u{898}xyz", 5, 4), "");
        assert_eq!(slice("\u{345}ab   \u{898}xyz", 0, 1), "\u{345}");
        assert_eq!(slice("abcdef", 0, 6), "abcdef");
        assert_eq!(slice("\u{345}ab\u{898}xyz", 1, 7), "ab\u{898}xyz");
    }

    #[test]
    fn test_from() {
        assert_eq!(from("\u{345}ab\u{898}xyz", 1), "ab\u{898}xyz");
        assert_eq!(from("\u{345}ab\u{898}xyz", 3), "\u{898}xyz");
        assert_eq!(from("\u{345}ab\u{898}xyz", 10), "");
        assert_eq!(from("\u{345}ab   \u{898}xyz", 0), "\u{345}ab   \u{898}xyz");
    }

    #[test]
    fn test_till() {
        assert_eq!(till("\u{345}ab\u{898}xyz", 1), "\u{345}");
        assert_eq!(till("\u{345}ab\u{898}xyz", 3), "\u{345}ab");
        assert_eq!(till("\u{345}ab\u{898}xyz", 0), "");
    }

    #[test]
    fn test_len() {
        assert_eq!(len(""), 0);
        assert_eq!(len("👨‍🚀"), 3);
        assert_eq!(len("abc"), 3);
        assert_eq!(len("abd👨‍🚀"), 6);
    }
}