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

use super::errors::{ErrorKind, ParserError};
use super::Result;
use std::str;

pub struct ParserStream<'p> {
    pub source: &'p [u8],
    pub length: usize,
    pub ptr: usize,
}

impl<'p> ParserStream<'p> {
    pub fn new(stream: &'p str) -> Self {
        ParserStream {
            source: stream.as_bytes(),
            length: stream.len(),
            ptr: 0,
        }
    }

    pub fn is_current_byte(&self, b: u8) -> bool {
        self.source.get(self.ptr) == Some(&b)
    }

    pub fn is_byte_at(&self, b: u8, pos: usize) -> bool {
        self.source.get(pos) == Some(&b)
    }

    pub fn expect_byte(&mut self, b: u8) -> Result<()> {
        if !self.is_current_byte(b) {
            return error!(ErrorKind::ExpectedToken(b as char), self.ptr);
        }
        self.ptr += 1;
        Ok(())
    }

    pub fn take_byte_if(&mut self, b: u8) -> bool {
        if self.is_current_byte(b) {
            self.ptr += 1;
            true
        } else {
            false
        }
    }

    pub fn skip_blank_block(&mut self) -> usize {
        let mut count = 0;
        loop {
            let start = self.ptr;
            self.skip_blank_inline();
            if !self.skip_eol() {
                self.ptr = start;
                break;
            }
            count += 1;
        }
        count
    }

    pub fn skip_blank(&mut self) {
        loop {
            match self.source.get(self.ptr) {
                Some(b) if [b' ', b'\n'].contains(b) => self.ptr += 1,
                _ => break,
            }
        }
    }

    pub fn skip_blank_inline(&mut self) -> usize {
        let start = self.ptr;
        while let Some(b' ') = self.source.get(self.ptr) {
            self.ptr += 1;
        }
        self.ptr - start
    }

    pub fn skip_to_next_entry_start(&mut self) {
        while let Some(b) = self.source.get(self.ptr) {
            let new_line = self.ptr == 0 || self.source.get(self.ptr - 1) == Some(&b'\n');

            if new_line && (b.is_ascii_alphabetic() || [b'-', b'#'].contains(b)) {
                break;
            }

            self.ptr += 1;
        }
    }

    pub fn skip_eol(&mut self) -> bool {
        match self.source.get(self.ptr) {
            Some(b'\n') => {
                self.ptr += 1;
                true
            }
            Some(b'\r') if self.is_byte_at(b'\n', self.ptr + 1) => {
                self.ptr += 2;
                true
            }
            _ => false,
        }
    }

    pub fn skip_unicode_escape_sequence(&mut self, length: usize) -> Result<()> {
        let start = self.ptr;
        for _ in 0..length {
            match self.source.get(self.ptr) {
                Some(b) if b.is_ascii_hexdigit() => self.ptr += 1,
                _ => break,
            }
        }
        if self.ptr - start != length {
            let end = if self.ptr >= self.length {
                self.ptr
            } else {
                self.ptr + 1
            };
            return error!(
                ErrorKind::InvalidUnicodeEscapeSequence(self.get_slice(start, end).to_owned()),
                self.ptr
            );
        }
        Ok(())
    }

    pub fn is_identifier_start(&self) -> bool {
        match self.source.get(self.ptr) {
            Some(b) if b.is_ascii_alphabetic() => true,
            _ => false,
        }
    }

    pub fn is_byte_pattern_continuation(&self, b: u8) -> bool {
        ![b'}', b'.', b'[', b'*'].contains(&b)
    }

    pub fn is_number_start(&self) -> bool {
        match self.source.get(self.ptr) {
            Some(b) if (b == &b'-') || b.is_ascii_digit() => true,
            _ => false,
        }
    }

    pub fn is_eol(&self) -> bool {
        match self.source.get(self.ptr) {
            Some(b'\n') => true,
            Some(b'\r') if self.is_byte_at(b'\n', self.ptr + 1) => true,
            _ => false,
        }
    }

    pub fn get_slice(&self, start: usize, end: usize) -> &'p str {
        str::from_utf8(&self.source[start..end]).expect("Slicing the source failed")
    }

    pub fn skip_digits(&mut self) -> Result<()> {
        let start = self.ptr;
        loop {
            match self.source.get(self.ptr) {
                Some(b) if b.is_ascii_digit() => self.ptr += 1,
                _ => break,
            }
        }
        if start == self.ptr {
            error!(
                ErrorKind::ExpectedCharRange {
                    range: "0-9".to_string()
                },
                self.ptr
            )
        } else {
            Ok(())
        }
    }
}