gecliht 0.2.0

A disparate collection of text manipulation and formatting algorithms.
Documentation 
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

//! Calculates the set of unique abbreviations for a given set of words.
//! (Borrowed from Ruby's Abbrev.)
//!

use std::collections::{HashMap, HashSet};

/// Given a list of strings, returns a map of unique abbreviations for members of 
/// the given list. 
///
/// # Example
///
/// ```
/// let strings = vec!["car", "cot", "dog"];
/// let result = gecliht::abbrevs(&strings);
///
/// assert_eq!(result["ca"], "car");
/// assert_eq!(result["car"], "car");
/// assert_eq!(result["co"], "cot");
/// assert_eq!(result["d"], "dog");
/// assert_eq!(result["dog"], "dog");
/// ```
/// 
pub fn abbrevs<'a> (strings : &'a [&str]) -> HashMap<String, &'a str> {
    return abbrevs_from_prefix (strings, "");
}

/// Given a list of strings, returns a map of unique abbreviations for members of 
/// the given list. Each abbreviation must begin with the given prefix.
///
/// # Example
///
/// ```
/// let strings = vec!["car", "cot", "dog"];
/// let result = gecliht::abbrevs_from_prefix(&strings, "c");
///
/// assert_eq!(result["ca"], "car");
/// assert_eq!(result["car"], "car");
/// assert_eq!(result["co"], "cot");
/// assert!(!result.contains_key("d"));
/// ```
///
pub fn abbrevs_from_prefix<'a> (strings : &'a [&str], prefix : &str) -> HashMap<String, &'a str>  {
    let mut result = HashMap::new ();
    let mut seen = HashSet::new ();

    for string in strings.iter () {
        for idx in 1..=string.len () {
            let new_abbrev = string.get(0..idx).unwrap ();
            if new_abbrev.starts_with(prefix) { // abbreviations must match the prefix
                if seen.contains(new_abbrev) {
                    // delete abbrev as not unique
                    result.remove_entry (new_abbrev);
                } else {
                    // abbrev not seen before, so add to result
                    result.insert (String::from(new_abbrev), string.clone());
                    seen.insert (new_abbrev);
                }
            }
        }
    }

    return result;
}

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

    #[test]
    fn empty () {
        let strings = vec![];
        let result = abbrevs(&strings);

        assert!(result.is_empty());
    }

    #[test]
    fn empty_prefix () {
        let strings = vec![];
        let result = abbrevs_from_prefix(&strings, "abc");

        assert!(result.is_empty());
    }

    #[test]
    fn one_word () {
        let strings = vec!["abcd"];
        let result = abbrevs(&strings);

        assert_eq!(4, result.len ());
        for abbrev in vec!["a", "ab", "abc", "abcd"] {
            assert_eq!(result.contains_key(abbrev), true);
            assert_eq!(&"abcd", result.get(abbrev).unwrap ());
        }
    }

    #[test]
    fn one_word_prefix () {
        let strings = vec!["abcd"];
        let result = abbrevs_from_prefix(&strings, "ab");

        assert_eq!(3, result.len ());
        for abbrev in vec!["ab", "abc", "abcd"] {
            assert_eq!(result.contains_key(abbrev), true);
            assert_eq!(&"abcd", result.get(abbrev).unwrap ());
        }
    }

    #[test]
    fn two_words () {
        let strings = vec!["car", "cat"];
        let result = abbrevs(&strings);

        assert_eq!(2, result.len ());
        assert_eq!(result.contains_key("car"), true);
        assert_eq!(result.get("car").unwrap (), &"car");
        assert_eq!(result.contains_key("cat"), true);
        assert_eq!(result.get("cat").unwrap (), &"cat");
    }

    #[test]
    fn two_words_more () {
        let strings = vec!["car", "cone"];
        let result = abbrevs(&strings);

        assert_eq!(5, result.len ());
        assert_eq!(result.contains_key("ca"), true);
        assert_eq!(result.get("ca").unwrap (), &"car");
        assert_eq!(result.contains_key("car"), true);
        assert_eq!(result.get("car").unwrap (), &"car");
        assert_eq!(result.contains_key("co"), true);
        assert_eq!(result.get("co").unwrap (), &"cone");
        assert_eq!(result.contains_key("con"), true);
        assert_eq!(result.get("con").unwrap (), &"cone");
        assert_eq!(result.contains_key("cone"), true);
        assert_eq!(result.get("cone").unwrap (), &"cone");
    }

    #[test]
    fn words_with_prefix () {
        let strings = vec!["car", "cat", "dog"];
        let result = abbrevs_from_prefix(&strings, "c");

        assert_eq!(2, result.len ());
        assert_eq!(result.contains_key("car"), true);
        assert_eq!(result.get("car").unwrap (), &"car");
        assert_eq!(result.contains_key("cat"), true);
        assert_eq!(result.get("cat").unwrap (), &"cat");
    }

    #[test]
    fn words_with_prefix2 () {
        let strings = vec!["car", "cat", "dog"];
        let result = abbrevs_from_prefix(&strings, "d");

        assert_eq!(3, result.len ());
        assert_eq!(result.contains_key("d"), true);
        assert_eq!(result.get("d").unwrap (), &"dog");
        assert_eq!(result.contains_key("do"), true);
        assert_eq!(result.get("do").unwrap (), &"dog");
        assert_eq!(result.contains_key("dog"), true);
        assert_eq!(result.get("dog").unwrap (), &"dog");
    }

}