aboutsummaryrefslogtreecommitdiffstats
path: root/components/util/str.rs
blob: fe23c1b5ff6789899c28a9713318c6560984887f (plain) (blame)
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
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

use app_units::Au;
use libc::c_char;
use num_traits::ToPrimitive;
use std::borrow::ToOwned;
use std::convert::AsRef;
use std::ffi::CStr;
use std::iter::{Filter, Peekable};
use std::ops::Deref;
use std::str::{Split, from_utf8};

pub type StaticCharVec = &'static [char];
pub type StaticStringVec = &'static [&'static str];

/// A "space character" according to:
///
/// https://html.spec.whatwg.org/multipage/#space-character
pub static HTML_SPACE_CHARACTERS: StaticCharVec = &[
    '\u{0020}',
    '\u{0009}',
    '\u{000a}',
    '\u{000c}',
    '\u{000d}',
];

#[inline]
pub fn char_is_whitespace(c: char) -> bool {
    HTML_SPACE_CHARACTERS.contains(&c)
}

pub fn is_whitespace(s: &str) -> bool {
    s.chars().all(char_is_whitespace)
}

pub fn split_html_space_chars<'a>(s: &'a str) ->
                                  Filter<Split<'a, StaticCharVec>, fn(&&str) -> bool> {
    fn not_empty(&split: &&str) -> bool { !split.is_empty() }
    s.split(HTML_SPACE_CHARACTERS).filter(not_empty as fn(&&str) -> bool)
}


fn is_ascii_digit(c: &char) -> bool {
    match *c {
        '0'...'9' => true,
        _ => false,
    }
}

fn is_decimal_point(c: char) -> bool {
    c == '.'
}

fn is_exponent_char(c: char) -> bool {
    match c {
        'e' | 'E' => true,
        _ => false,
    }
}

pub fn read_numbers<I: Iterator<Item=char>>(mut iter: Peekable<I>) -> (Option<i64>, usize) {
    match iter.peek() {
        Some(c) if is_ascii_digit(c) => (),
        _ => return (None, 0),
    }

    iter.take_while(is_ascii_digit).map(|d| {
        d as i64 - '0' as i64
    }).fold((Some(0i64), 0), |accumulator, d| {
        let digits = accumulator.0.and_then(|accumulator| {
            accumulator.checked_mul(10)
        }).and_then(|accumulator| {
            accumulator.checked_add(d)
        });
        (digits, accumulator.1 + 1)
    })
}

pub fn read_fraction<I: Iterator<Item=char>>(mut iter: Peekable<I>,
                                             mut divisor: f64,
                                             value: f64) -> (f64, usize) {
    match iter.peek() {
        Some(c) if is_decimal_point(*c) => (),
        _ => return (value, 0),
    }
    iter.next();

    iter.take_while(is_ascii_digit).map(|d|
        d as i64 - '0' as i64
    ).fold((value, 1), |accumulator, d| {
        divisor *= 10f64;
        (accumulator.0 + d as f64 / divisor,
            accumulator.1 + 1)
    })
}

pub fn read_exponent<I: Iterator<Item=char>>(mut iter: Peekable<I>) -> Option<i32> {
    match iter.peek() {
        Some(c) if is_exponent_char(*c) => (),
        _ => return None,
    }
    iter.next();

    match iter.peek() {
        None => None,
        Some(&'-') => {
            iter.next();
            read_numbers(iter).0.map(|exp| -exp.to_i32().unwrap_or(0))
        }
        Some(&'+') => {
            iter.next();
            read_numbers(iter).0.map(|exp| exp.to_i32().unwrap_or(0))
        }
        Some(_) => read_numbers(iter).0.map(|exp| exp.to_i32().unwrap_or(0))
    }
}

#[derive(Clone, Copy, Debug, HeapSizeOf, PartialEq)]
pub enum LengthOrPercentageOrAuto {
    Auto,
    Percentage(f32),
    Length(Au),
}

#[derive(Clone, Eq, PartialEq, Hash, Debug, Deserialize, Serialize)]
pub struct LowercaseString {
    inner: String,
}

impl LowercaseString {
    pub fn new(s: &str) -> LowercaseString {
        LowercaseString {
            inner: s.to_lowercase(),
        }
    }
}

impl Deref for LowercaseString {
    type Target = str;

    #[inline]
    fn deref(&self) -> &str {
        &*self.inner
    }
}

/// Creates a String from the given null-terminated buffer.
/// Panics if the buffer does not contain UTF-8.
pub unsafe fn c_str_to_string(s: *const c_char) -> String {
    from_utf8(CStr::from_ptr(s).to_bytes()).unwrap().to_owned()
}

pub fn str_join<I, T>(strs: I, join: &str) -> String
    where I: IntoIterator<Item=T>, T: AsRef<str>,
{
    strs.into_iter().enumerate().fold(String::new(), |mut acc, (i, s)| {
        if i > 0 { acc.push_str(join); }
        acc.push_str(s.as_ref());
        acc
    })
}