Files
aho_corasick
atty
beef
bitflags
bstr
byteorder
cfg_if
clap
clap_derive
codespan
codespan_reporting
crc_any
crypto_hash
csv
csv_core
debug_helper
filepath
fixed
fixed_macro
fixed_macro_impl
fixed_macro_types
fnv
foreign_types
foreign_types_shared
getrandom
glob
hashbrown
heck
hex
indexmap
itoa
lazy_static
libc
linked_hash_map
linked_hash_set
logos
logos_derive
lrl_test_compiler
maplit
memchr
memoffset
once_cell
openssl
openssl_sys
os_str_bytes
paste
pest
pest_derive
pest_generator
pest_meta
phf
phf_generator
phf_macros
phf_shared
ppv_lite86
proc_macro2
proc_macro_error
proc_macro_error_attr
proc_macro_hack
quote
rand
rand_chacha
rand_core
regex
regex_automata
regex_syntax
remove_dir_all
ring
rowan
rustc_hash
ryu
semver
semver_parser
serde
serde_derive
serde_json
siphasher
smallvec
smawk
smol_str
spin
stable_deref_trait
strsim
syn
taplo
tempfile
termcolor
text_size
textwrap
toml
triomphe
typenum
ucd_trie
unicode_linebreak
unicode_segmentation
unicode_width
unicode_xid
untrusted
utf8_ranges
vec_map
  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
//! **heck** is a case conversion library.
//!
//! This library exists to provide case conversion between common cases like
//! CamelCase and snake_case. It is intended to be unicode aware, internally,
//! consistent, and reasonably well performing.
//!
//! ## Definition of a word boundary
//!
//! Word boundaries are defined as the "unicode words" defined in the
//! `unicode_segmentation` library, as well as within those words in this manner:
//!
//! 1. All underscore characters are considered word boundaries.
//! 2. If an uppercase character is followed by lowercase letters, a word boundary
//! is considered to be just prior to that uppercase character.
//! 3. If multiple uppercase characters are consecutive, they are considered to be
//! within a single word, except that the last will be part of the next word if it
//! is followed by lowercase characters (see rule 2).
//!
//! That is, "HelloWorld" is segmented `Hello|World` whereas "XMLHttpRequest" is
//! segmented `XML|Http|Request`.
//!
//! Characters not within words (such as spaces, punctuations, and underscores)
//! are not included in the output string except as they are a part of the case
//! being converted to. Multiple adjacent word boundaries (such as a series of
//! underscores) are folded into one. ("hello__world" in snake case is therefore
//! "hello_world", not the exact same string). Leading or trailing word boundary
//! indicators are dropped, except insofar as CamelCase capitalizes the first word.
//!
//! ### Cases contained in this library:
//!
//! 1. CamelCase
//! 2. snake_case
//! 3. kebab-case
//! 4. SHOUTY_SNAKE_CASE
//! 5. mixedCase
//! 6. Title Case
//! 7. SHOUTY-KEBAB-CASE
#![deny(missing_docs)]

mod camel;
mod kebab;
mod mixed;
mod shouty_kebab;
mod shouty_snake;
mod snake;
mod title;

pub use camel::CamelCase;
pub use kebab::KebabCase;
pub use mixed::MixedCase;
pub use shouty_kebab::ShoutyKebabCase;
pub use shouty_snake::{ShoutySnakeCase, ShoutySnekCase};
pub use snake::{SnakeCase, SnekCase};
pub use title::TitleCase;

use unicode_segmentation::UnicodeSegmentation;

fn transform<F, G>(s: &str, with_word: F, boundary: G) -> String
where
    F: Fn(&str, &mut String),
    G: Fn(&mut String)
{

    /// Tracks the current 'mode' of the transformation algorithm as it scans the input string.
    ///
    /// The mode is a tri-state which tracks the case of the last cased character of the current
    /// word. If there is no cased character (either lowercase or uppercase) since the previous
    /// word boundary, than the mode is `Boundary`. If the last cased character is lowercase, then
    /// the mode is `Lowercase`. Othertherwise, the mode is `Uppercase`.
    #[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 out = String::new();
    let mut first_word = true;

    for word in s.unicode_words() {
        let mut char_indices = word.char_indices().peekable();
        let mut init = 0;
        let mut mode = WordMode::Boundary;

        while let Some((i, c)) = char_indices.next() {
            // Skip underscore characters
            if c == '_' {
                if init == i { init += 1; }
                continue
            }

            if let Some(&(next_i, next)) = char_indices.peek() {

                // The mode including the current character, assuming the current character does
                // not result in a word boundary.
                let next_mode = if c.is_lowercase() {
                    WordMode::Lowercase
                } else if c.is_uppercase() {
                    WordMode::Uppercase
                } else {
                    mode
                };

                // Word boundary after if next is underscore or current is
                // not uppercase and next is uppercase
                if next == '_' || (next_mode == WordMode::Lowercase && next.is_uppercase()) {
                    if !first_word { boundary(&mut out); }
                    with_word(&word[init..next_i], &mut out);
                    first_word = false;
                    init = next_i;
                    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() {
                    if !first_word { boundary(&mut out); }
                    else { first_word = false; }
                    with_word(&word[init..i], &mut out);
                    init = i;
                    mode = WordMode::Boundary;

                // Otherwise no word boundary, just update the mode
                } else {
                    mode = next_mode;
                }
            } else {
                // Collect trailing characters as a word
                if !first_word { boundary(&mut out); }
                else { first_word = false; }
                with_word(&word[init..], &mut out);
                break;
            }
        }
    }

    out
}

fn lowercase(s: &str, out: &mut String) {
    let mut chars = s.chars().peekable();
    while let Some(c) = chars.next() {
        if c == 'Σ' && chars.peek().is_none() {
            out.push('ς');
        } else {
            out.extend(c.to_lowercase());
        }
    }
}

fn uppercase(s: &str, out: &mut String ) {
    for c in s.chars() {
        out.extend(c.to_uppercase())
    }
}

fn capitalize(s: &str, out: &mut String) {
    let mut char_indices = s.char_indices();
    if let Some((_, c)) = char_indices.next() {
        out.extend(c.to_uppercase());
        if let Some((i, _)) = char_indices.next() {
            lowercase(&s[i..], out);
        }
    }
}