summaryrefslogtreecommitdiffstats
path: root/servo/components/style/str.rs
blob: fe598f546ee9f116ab30c1d9af0dccb840ffaac6 (plain)
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
176
177
178
179
180
/* 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 https://mozilla.org/MPL/2.0/. */

//! String utils for attributes and similar stuff.

#![deny(missing_docs)]

use num_traits::ToPrimitive;
use std::borrow::Cow;
use std::iter::{Filter, Peekable};
use std::str::Split;

/// A static slice of characters.
pub type StaticCharVec = &'static [char];

/// A static slice of `str`s.
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}'];

/// Whether a character is a HTML whitespace character.
#[inline]
pub fn char_is_whitespace(c: char) -> bool {
    HTML_SPACE_CHARACTERS.contains(&c)
}

/// Whether all the string is HTML whitespace.
#[inline]
pub fn is_whitespace(s: &str) -> bool {
    s.chars().all(char_is_whitespace)
}

#[inline]
fn not_empty(&split: &&str) -> bool {
    !split.is_empty()
}

/// Split a string on HTML whitespace.
#[inline]
pub fn split_html_space_chars<'a>(
    s: &'a str,
) -> Filter<Split<'a, StaticCharVec>, fn(&&str) -> bool> {
    s.split(HTML_SPACE_CHARACTERS)
        .filter(not_empty as fn(&&str) -> bool)
}

/// Split a string on commas.
#[inline]
pub fn split_commas<'a>(s: &'a str) -> Filter<Split<'a, char>, fn(&&str) -> bool> {
    s.split(',').filter(not_empty as fn(&&str) -> bool)
}

/// Character is ascii digit
pub 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,
    }
}

/// Read a set of ascii digits and read them into a number.
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)
        })
}

/// Read a decimal fraction.
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)
        })
}

/// Reads an exponent from an iterator over chars, for example `e100`.
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)),
    }
}

/// Join a set of strings with a given delimiter `join`.
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
        })
}

/// Returns true if a given string has a given prefix with case-insensitive match.
pub fn starts_with_ignore_ascii_case(string: &str, prefix: &str) -> bool {
    string.len() >= prefix.len() &&
        string.as_bytes()[0..prefix.len()].eq_ignore_ascii_case(prefix.as_bytes())
}

/// Returns an ascii lowercase version of a string, only allocating if needed.
pub fn string_as_ascii_lowercase<'a>(input: &'a str) -> Cow<'a, str> {
    if input.bytes().any(|c| matches!(c, b'A'..=b'Z')) {
        input.to_ascii_lowercase().into()
    } else {
        // Already ascii lowercase.
        Cow::Borrowed(input)
    }
}

/// To avoid accidentally instantiating multiple monomorphizations of large
/// serialization routines, we define explicit concrete types and require
/// them in those routines. This avoids accidental mixing of String and
/// nsACString arguments in Gecko, which would cause code size to blow up.
#[cfg(feature = "gecko")]
pub type CssStringWriter = ::nsstring::nsACString;

/// String type that coerces to CssStringWriter, used when serialization code
/// needs to allocate a temporary string.
#[cfg(feature = "gecko")]
pub type CssString = ::nsstring::nsCString;