booky 0.8.0

A tool to analyze English text
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

/// Word kind
#[derive(Clone, Copy, Debug, Eq, PartialEq, PartialOrd, Ord, Hash)]
pub enum Kind {
    /// In Lexicon
    Lexicon,
    /// Foreign (non-English)
    Foreign,
    /// Ordinal number
    Ordinal,
    /// Roman numeral
    Roman,
    /// Number (may include letters)
    Number,
    /// Acronym / Initialism
    Acronym,
    /// Proper noun (name)
    Proper,
    /// Symbol or letter (punctuation, etc.)
    Symbol,
    /// Unknown / Other
    Unknown,
}

impl Kind {
    /// Get all word kinds
    pub fn all() -> &'static [Self] {
        use Kind::*;
        &[
            Lexicon, Foreign, Ordinal, Roman, Number, Acronym, Proper, Symbol,
            Unknown,
        ]
    }

    /// Get code
    pub fn code(self) -> char {
        use Kind::*;
        match self {
            Lexicon => 'l',
            Foreign => 'f',
            Ordinal => 'o',
            Roman => 'r',
            Number => 'n',
            Acronym => 'a',
            Proper => 'p',
            Symbol => 's',
            Unknown => 'u',
        }
    }
}

impl From<&str> for Kind {
    fn from(word: &str) -> Self {
        if is_foreign(word) {
            Kind::Foreign
        } else if is_ordinal_number(word) {
            Kind::Ordinal
        } else if is_roman_numeral(word) {
            Kind::Roman
        } else if is_number(word) {
            Kind::Number
        } else if is_acronym(word) {
            Kind::Acronym
        } else if is_probably_proper(word) {
            Kind::Proper
        } else if word.chars().count() == 1 {
            Kind::Symbol
        } else {
            Kind::Unknown
        }
    }
}

/// Check if a word is foreign (not English)
fn is_foreign(word: &str) -> bool {
    word.chars().any(|c| c.is_alphabetic() && !c.is_ascii())
}

/// Ordinal suffixes
const ORD_SUFFIXES: &[&str] =
    &["1st", "1ST", "2nd", "2ND", "3rd", "3RD", "th", "TH"];

/// Check if a string is an ordinal number
fn is_ordinal_number(w: &str) -> bool {
    if w.chars().count() >= 3 {
        for suf in ORD_SUFFIXES {
            if let Some(p) = w.strip_suffix(suf) {
                return p.chars().all(|c| c.is_ascii_digit());
            }
        }
    }
    false
}

/// Uppercase roman numerals
const ROMAN_UPPER: &str = "IVXLCDM";

/// Lowercase roman numerals
const ROMAN_LOWER: &str = "ivxlcdm";

/// Check if a string is a romal numeral
fn is_roman_numeral(word: &str) -> bool {
    !word.is_empty()
        && (word.chars().all(|c| ROMAN_UPPER.contains(c))
            || word.chars().all(|c| ROMAN_LOWER.contains(c)))
}

/// Check if a word contains a number
fn is_number(word: &str) -> bool {
    word.chars().any(|c| c.is_ascii_digit())
}

/// Check if a word is an acronym / initialism
fn is_acronym(word: &str) -> bool {
    word.chars().count() >= 2
        && word.chars().all(|c| c.is_uppercase() || c == '.')
}

/// Check if a word is probably proper
fn is_probably_proper(word: &str) -> bool {
    let mut chars = word.chars();
    match chars.next() {
        Some(c) if c.is_uppercase() => chars.any(|c| c.is_lowercase()),
        _ => false,
    }
}