summaryrefslogtreecommitdiffstats
path: root/third_party/rust/cssparser/src/unicode_range.rs
blob: b0a2017cbf3403e4c63d9ba92db641639bfd5f8d (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
181
/* 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/. */

//! https://drafts.csswg.org/css-syntax/#urange

use crate::tokenizer::Token;
use crate::{BasicParseError, Parser, ToCss};
use std::char;
use std::fmt;

/// One contiguous range of code points.
///
/// Can not be empty. Can represent a single code point when start == end.
#[derive(PartialEq, Eq, Clone, Hash)]
#[repr(C)]
pub struct UnicodeRange {
    /// Inclusive start of the range. In [0, end].
    pub start: u32,

    /// Inclusive end of the range. In [0, 0x10FFFF].
    pub end: u32,
}

impl UnicodeRange {
    /// https://drafts.csswg.org/css-syntax/#urange-syntax
    pub fn parse<'i, 't>(input: &mut Parser<'i, 't>) -> Result<Self, BasicParseError<'i>> {
        // <urange> =
        //   u '+' <ident-token> '?'* |
        //   u <dimension-token> '?'* |
        //   u <number-token> '?'* |
        //   u <number-token> <dimension-token> |
        //   u <number-token> <number-token> |
        //   u '+' '?'+

        input.expect_ident_matching("u")?;
        let after_u = input.position();
        parse_tokens(input)?;

        // This deviates from the spec in case there are CSS comments
        // between tokens in the middle of one <unicode-range>,
        // but oh well…
        let concatenated_tokens = input.slice_from(after_u);

        let range = match parse_concatenated(concatenated_tokens.as_bytes()) {
            Ok(range) => range,
            Err(()) => {
                return Err(input
                    .new_basic_unexpected_token_error(Token::Ident(concatenated_tokens.into())))
            }
        };
        if range.end > char::MAX as u32 || range.start > range.end {
            Err(input.new_basic_unexpected_token_error(Token::Ident(concatenated_tokens.into())))
        } else {
            Ok(range)
        }
    }
}

fn parse_tokens<'i, 't>(input: &mut Parser<'i, 't>) -> Result<(), BasicParseError<'i>> {
    match input.next_including_whitespace()?.clone() {
        Token::Delim('+') => {
            match *input.next_including_whitespace()? {
                Token::Ident(_) => {}
                Token::Delim('?') => {}
                ref t => {
                    let t = t.clone();
                    return Err(input.new_basic_unexpected_token_error(t));
                }
            }
            parse_question_marks(input)
        }
        Token::Dimension { .. } => parse_question_marks(input),
        Token::Number { .. } => {
            let after_number = input.state();
            match input.next_including_whitespace() {
                Ok(&Token::Delim('?')) => parse_question_marks(input),
                Ok(&Token::Dimension { .. }) => {}
                Ok(&Token::Number { .. }) => {}
                _ => input.reset(&after_number),
            }
        }
        t => return Err(input.new_basic_unexpected_token_error(t)),
    }
    Ok(())
}

/// Consume as many '?' as possible
fn parse_question_marks(input: &mut Parser) {
    loop {
        let start = input.state();
        match input.next_including_whitespace() {
            Ok(&Token::Delim('?')) => {}
            _ => {
                input.reset(&start);
                return;
            }
        }
    }
}

fn parse_concatenated(text: &[u8]) -> Result<UnicodeRange, ()> {
    let mut text = match text.split_first() {
        Some((&b'+', text)) => text,
        _ => return Err(()),
    };
    let (first_hex_value, hex_digit_count) = consume_hex(&mut text);
    let question_marks = consume_question_marks(&mut text);
    let consumed = hex_digit_count + question_marks;
    if consumed == 0 || consumed > 6 {
        return Err(());
    }

    if question_marks > 0 {
        if text.is_empty() {
            return Ok(UnicodeRange {
                start: first_hex_value << (question_marks * 4),
                end: ((first_hex_value + 1) << (question_marks * 4)) - 1,
            });
        }
    } else if text.is_empty() {
        return Ok(UnicodeRange {
            start: first_hex_value,
            end: first_hex_value,
        });
    } else {
        if let Some((&b'-', mut text)) = text.split_first() {
            let (second_hex_value, hex_digit_count) = consume_hex(&mut text);
            if hex_digit_count > 0 && hex_digit_count <= 6 && text.is_empty() {
                return Ok(UnicodeRange {
                    start: first_hex_value,
                    end: second_hex_value,
                });
            }
        }
    }
    Err(())
}

fn consume_hex(text: &mut &[u8]) -> (u32, usize) {
    let mut value = 0;
    let mut digits = 0;
    while let Some((&byte, rest)) = text.split_first() {
        if let Some(digit_value) = (byte as char).to_digit(16) {
            value = value * 0x10 + digit_value;
            digits += 1;
            *text = rest
        } else {
            break;
        }
    }
    (value, digits)
}

fn consume_question_marks(text: &mut &[u8]) -> usize {
    let mut question_marks = 0;
    while let Some((&b'?', rest)) = text.split_first() {
        question_marks += 1;
        *text = rest
    }
    question_marks
}

impl fmt::Debug for UnicodeRange {
    fn fmt(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
        self.to_css(formatter)
    }
}

impl ToCss for UnicodeRange {
    fn to_css<W>(&self, dest: &mut W) -> fmt::Result
    where
        W: fmt::Write,
    {
        write!(dest, "U+{:X}", self.start)?;
        if self.end != self.start {
            write!(dest, "-{:X}", self.end)?;
        }
        Ok(())
    }
}