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
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
//! Module containing parsers specialized on character streams.

use crate::{
    error::ParseError,
    parser::{
        combinator::no_partial,
        repeat::skip_many,
        token::{satisfy, token, tokens_cmp, Token},
    },
    stream::Stream,
    Parser,
};

/// Parses a character and succeeds if the character is equal to `c`.
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::char;
/// assert_eq!(char('!').parse("!"), Ok(('!', "")));
/// assert!(char('A').parse("!").is_err());
/// ```
pub fn char<Input>(c: char) -> Token<Input>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    token(c)
}

parser! {
    #[derive(Copy, Clone)]
    pub struct Digit;
    /// Parses a base-10 digit.
    ///
    /// ```
    /// use combine::Parser;
    /// use combine::parser::char::digit;
    /// assert_eq!(digit().parse("9"), Ok(('9', "")));
    /// assert!(digit().parse("A").is_err());
    /// ```
    pub fn digit[Input]()(Input) -> char
    where
        [Input: Stream<Token = char>,]
    {
        satisfy(|c: char| c.is_digit(10)).expected("digit")
    }
}

/// Parse a single whitespace according to [`std::char::is_whitespace`].
///
/// This includes space characters, tabs and newlines.
///
/// [`std::char::is_whitespace`]: https://doc.rust-lang.org/std/primitive.char.html#method.is_whitespace
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::space;
/// assert_eq!(space().parse(" "), Ok((' ', "")));
/// assert_eq!(space().parse("  "), Ok((' ', " ")));
/// assert!(space().parse("!").is_err());
/// assert!(space().parse("").is_err());
/// ```
pub fn space<Input>() -> impl Parser<Input, Output = char, PartialState = ()>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    let f: fn(char) -> bool = char::is_whitespace;
    satisfy(f).expected("whitespace")
}

/// Skips over zero or more spaces according to [`std::char::is_whitespace`].
///
/// This includes space characters, tabs and newlines.
///
/// [`std::char::is_whitespace`]: https://doc.rust-lang.org/std/primitive.char.html#method.is_whitespace
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::spaces;
/// assert_eq!(spaces().parse(""), Ok(((), "")));
/// assert_eq!(spaces().parse("   "), Ok(((), "")));
/// ```
pub fn spaces<Input>() -> impl Parser<Input, Output = ()>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    skip_many(space()).expected("whitespaces")
}

/// Parses a newline character (`'\n'`).
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::newline;
/// assert_eq!(newline().parse("\n"), Ok(('\n', "")));
/// assert!(newline().parse("\r").is_err());
/// ```
pub fn newline<Input>() -> impl Parser<Input, Output = char, PartialState = ()>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    satisfy(|ch: char| ch == '\n').expected("lf newline")
}

/// Parses carriage return and newline (`"\r\n"`), returning the newline character.
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::crlf;
/// assert_eq!(crlf().parse("\r\n"), Ok(('\n', "")));
/// assert!(crlf().parse("\r").is_err());
/// assert!(crlf().parse("\n").is_err());
/// ```
pub fn crlf<Input>() -> impl Parser<Input, Output = char, PartialState = ()>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    no_partial(satisfy(|ch: char| ch == '\r').with(newline())).expected("crlf newline")
}

/// Parses a tab character (`'\t'`).
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::tab;
/// assert_eq!(tab().parse("\t"), Ok(('\t', "")));
/// assert!(tab().parse(" ").is_err());
/// ```
pub fn tab<Input>() -> impl Parser<Input, Output = char, PartialState = ()>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    satisfy(|ch: char| ch == '\t').expected("tab")
}

/// Parses an uppercase letter according to [`std::char::is_uppercase`].
///
/// [`std::char::is_uppercase`]: https://doc.rust-lang.org/std/primitive.char.html#method.is_uppercase
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::upper;
/// assert_eq!(upper().parse("A"), Ok(('A', "")));
/// assert!(upper().parse("a").is_err());
/// ```
pub fn upper<Input>() -> impl Parser<Input, Output = char, PartialState = ()>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    satisfy(|ch: char| ch.is_uppercase()).expected("uppercase letter")
}

/// Parses an lowercase letter according to [`std::char::is_lowercase`].
///
/// [`std::char::is_lowercase`]: https://doc.rust-lang.org/std/primitive.char.html#method.is_lowercase
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::lower;
/// assert_eq!(lower().parse("a"), Ok(('a', "")));
/// assert!(lower().parse("A").is_err());
/// ```
pub fn lower<Input>() -> impl Parser<Input, Output = char, PartialState = ()>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    satisfy(|ch: char| ch.is_lowercase()).expected("lowercase letter")
}

/// Parses either an alphabet letter or digit according to [`std::char::is_alphanumeric`].
///
/// [`std::char::is_alphanumeric`]: https://doc.rust-lang.org/std/primitive.char.html#method.is_alphanumeric
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::alpha_num;
/// assert_eq!(alpha_num().parse("A"), Ok(('A', "")));
/// assert_eq!(alpha_num().parse("1"), Ok(('1', "")));
/// assert!(alpha_num().parse("!").is_err());
/// ```
pub fn alpha_num<Input>() -> impl Parser<Input, Output = char, PartialState = ()>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    satisfy(|ch: char| ch.is_alphanumeric()).expected("letter or digit")
}

/// Parses an alphabet letter according to [`std::char::is_alphabetic`].
///
/// [`std::char::is_alphabetic`]: https://doc.rust-lang.org/std/primitive.char.html#method.is_alphabetic
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::letter;
/// assert_eq!(letter().parse("a"), Ok(('a', "")));
/// assert_eq!(letter().parse("A"), Ok(('A', "")));
/// assert!(letter().parse("9").is_err());
/// ```
pub fn letter<Input>() -> impl Parser<Input, Output = char, PartialState = ()>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    satisfy(|ch: char| ch.is_alphabetic()).expected("letter")
}

/// Parses an octal digit.
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::oct_digit;
/// assert_eq!(oct_digit().parse("7"), Ok(('7', "")));
/// assert!(oct_digit().parse("8").is_err());
/// ```
pub fn oct_digit<Input>() -> impl Parser<Input, Output = char, PartialState = ()>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    satisfy(|ch: char| ch.is_digit(8)).expected("octal digit")
}

/// Parses a hexdecimal digit with uppercase and lowercase.
///
/// ```
/// use combine::Parser;
/// use combine::parser::char::hex_digit;
/// assert_eq!(hex_digit().parse("F"), Ok(('F', "")));
/// assert!(hex_digit().parse("H").is_err());
/// ```
pub fn hex_digit<Input>() -> impl Parser<Input, Output = char, PartialState = ()>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    satisfy(|ch: char| ch.is_digit(0x10)).expected("hexadecimal digit")
}

/// Parses the string `s`.
///
/// ```
/// # extern crate combine;
/// # use combine::*;
/// # use combine::parser::char::string;
/// # fn main() {
/// let result = string("rust")
///     .parse("rust")
///     .map(|x| x.0);
/// assert_eq!(result, Ok("rust"));
/// # }
/// ```
pub fn string<'a, Input>(s: &'static str) -> impl Parser<Input, Output = &'a str>
where
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    string_cmp(s, |l, r| l == r)
}

/// Parses the string `s`, using `cmp` to compare each character.
///
/// ```
/// # extern crate combine;
/// # use combine::*;
/// # use combine::parser::char::string_cmp;
/// use std::ascii::AsciiExt;
/// # fn main() {
/// let result = string_cmp("rust", |l, r| l.eq_ignore_ascii_case(&r))
///     .parse("RusT")
///     .map(|x| x.0);
/// assert_eq!(result, Ok("rust"));
/// # }
/// ```
pub fn string_cmp<'a, C, Input>(s: &'static str, cmp: C) -> impl Parser<Input, Output = &'a str>
where
    C: FnMut(char, char) -> bool,
    Input: Stream<Token = char>,
    Input::Error: ParseError<Input::Token, Input::Range, Input::Position>,
{
    tokens_cmp(s.chars(), cmp).map(move |_| s).expected(s)
}

#[cfg(all(feature = "std", test))]
mod tests {

    use crate::{
        parser::EasyParser,
        stream::{
            easy::{Error, Errors},
            position::{self, SourcePosition},
        },
    };

    use super::*;

    #[test]
    fn space_error() {
        let result = space().easy_parse("");
        assert!(result.is_err());
        assert_eq!(
            result.unwrap_err().errors,
            vec![Error::end_of_input(), Error::Expected("whitespace".into())]
        );
    }

    #[test]
    fn string_committed() {
        let result = string("a").easy_parse(position::Stream::new("b"));
        assert!(result.is_err());
        assert_eq!(
            result.unwrap_err().position,
            SourcePosition { line: 1, column: 1 }
        );
    }

    #[test]
    fn string_error() {
        let result = string("abc").easy_parse(position::Stream::new("bc"));
        assert_eq!(
            result,
            Err(Errors {
                position: SourcePosition { line: 1, column: 1 },
                errors: vec![Error::Unexpected('b'.into()), Error::Expected("abc".into())],
            })
        );
    }
}