| 1 | //! Character specific parsers and combinators, complete input version. |
| 2 | //! |
| 3 | //! Functions recognizing specific characters. |
| 4 | |
| 5 | use crate::branch::alt; |
| 6 | use crate::combinator::opt; |
| 7 | use crate::error::ErrorKind; |
| 8 | use crate::error::ParseError; |
| 9 | use crate::internal::{Err, IResult}; |
| 10 | use crate::lib::std::ops::{Range, RangeFrom, RangeTo}; |
| 11 | use crate::traits::{ |
| 12 | AsChar, FindToken, InputIter, InputLength, InputTake, InputTakeAtPosition, Slice, |
| 13 | }; |
| 14 | use crate::traits::{Compare, CompareResult}; |
| 15 | |
| 16 | /// Recognizes one character. |
| 17 | /// |
| 18 | /// *Complete version*: Will return an error if there's not enough input data. |
| 19 | /// # Example |
| 20 | /// |
| 21 | /// ``` |
| 22 | /// # use nom::{Err, error::{ErrorKind, Error}, IResult}; |
| 23 | /// # use nom::character::complete::char; |
| 24 | /// fn parser(i: &str) -> IResult<&str, char> { |
| 25 | /// char('a' )(i) |
| 26 | /// } |
| 27 | /// assert_eq!(parser("abc" ), Ok(("bc" , 'a' ))); |
| 28 | /// assert_eq!(parser(" abc" ), Err(Err::Error(Error::new(" abc" , ErrorKind::Char)))); |
| 29 | /// assert_eq!(parser("bc" ), Err(Err::Error(Error::new("bc" , ErrorKind::Char)))); |
| 30 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::Char)))); |
| 31 | /// ``` |
| 32 | pub fn char<I, Error: ParseError<I>>(c: char) -> impl Fn(I) -> IResult<I, char, Error> |
| 33 | where |
| 34 | I: Slice<RangeFrom<usize>> + InputIter, |
| 35 | <I as InputIter>::Item: AsChar, |
| 36 | { |
| 37 | move |i: I| match (i).iter_elements().next().map(|t: impl AsChar| { |
| 38 | let b: bool = t.as_char() == c; |
| 39 | (&c, b) |
| 40 | }) { |
| 41 | Some((c: &char, true)) => Ok((i.slice(range:c.len()..), c.as_char())), |
| 42 | _ => Err(Err::Error(Error::from_char(input:i, c))), |
| 43 | } |
| 44 | } |
| 45 | |
| 46 | /// Recognizes one character and checks that it satisfies a predicate |
| 47 | /// |
| 48 | /// *Complete version*: Will return an error if there's not enough input data. |
| 49 | /// # Example |
| 50 | /// |
| 51 | /// ``` |
| 52 | /// # use nom::{Err, error::{ErrorKind, Error}, Needed, IResult}; |
| 53 | /// # use nom::character::complete::satisfy; |
| 54 | /// fn parser(i: &str) -> IResult<&str, char> { |
| 55 | /// satisfy(|c| c == 'a' || c == 'b' )(i) |
| 56 | /// } |
| 57 | /// assert_eq!(parser("abc" ), Ok(("bc" , 'a' ))); |
| 58 | /// assert_eq!(parser("cd" ), Err(Err::Error(Error::new("cd" , ErrorKind::Satisfy)))); |
| 59 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::Satisfy)))); |
| 60 | /// ``` |
| 61 | pub fn satisfy<F, I, Error: ParseError<I>>(cond: F) -> impl Fn(I) -> IResult<I, char, Error> |
| 62 | where |
| 63 | I: Slice<RangeFrom<usize>> + InputIter, |
| 64 | <I as InputIter>::Item: AsChar, |
| 65 | F: Fn(char) -> bool, |
| 66 | { |
| 67 | move |i: I| match (i).iter_elements().next().map(|t: impl AsChar| { |
| 68 | let c: char = t.as_char(); |
| 69 | let b: bool = cond(c); |
| 70 | (c, b) |
| 71 | }) { |
| 72 | Some((c: char, true)) => Ok((i.slice(range:c.len()..), c)), |
| 73 | _ => Err(Err::Error(Error::from_error_kind(input:i, kind:ErrorKind::Satisfy))), |
| 74 | } |
| 75 | } |
| 76 | |
| 77 | /// Recognizes one of the provided characters. |
| 78 | /// |
| 79 | /// *Complete version*: Will return an error if there's not enough input data. |
| 80 | /// # Example |
| 81 | /// |
| 82 | /// ``` |
| 83 | /// # use nom::{Err, error::ErrorKind}; |
| 84 | /// # use nom::character::complete::one_of; |
| 85 | /// assert_eq!(one_of::<_, _, (&str, ErrorKind)>("abc" )("b" ), Ok(("" , 'b' ))); |
| 86 | /// assert_eq!(one_of::<_, _, (&str, ErrorKind)>("a" )("bc" ), Err(Err::Error(("bc" , ErrorKind::OneOf)))); |
| 87 | /// assert_eq!(one_of::<_, _, (&str, ErrorKind)>("a" )("" ), Err(Err::Error(("" , ErrorKind::OneOf)))); |
| 88 | /// ``` |
| 89 | pub fn one_of<I, T, Error: ParseError<I>>(list: T) -> impl Fn(I) -> IResult<I, char, Error> |
| 90 | where |
| 91 | I: Slice<RangeFrom<usize>> + InputIter, |
| 92 | <I as InputIter>::Item: AsChar + Copy, |
| 93 | T: FindToken<<I as InputIter>::Item>, |
| 94 | { |
| 95 | move |i: I| match (i).iter_elements().next().map(|c: impl AsChar + Copy| (c, list.find_token(c))) { |
| 96 | Some((c: impl AsChar + Copy, true)) => Ok((i.slice(range:c.len()..), c.as_char())), |
| 97 | _ => Err(Err::Error(Error::from_error_kind(input:i, kind:ErrorKind::OneOf))), |
| 98 | } |
| 99 | } |
| 100 | |
| 101 | /// Recognizes a character that is not in the provided characters. |
| 102 | /// |
| 103 | /// *Complete version*: Will return an error if there's not enough input data. |
| 104 | /// # Example |
| 105 | /// |
| 106 | /// ``` |
| 107 | /// # use nom::{Err, error::ErrorKind}; |
| 108 | /// # use nom::character::complete::none_of; |
| 109 | /// assert_eq!(none_of::<_, _, (&str, ErrorKind)>("abc" )("z" ), Ok(("" , 'z' ))); |
| 110 | /// assert_eq!(none_of::<_, _, (&str, ErrorKind)>("ab" )("a" ), Err(Err::Error(("a" , ErrorKind::NoneOf)))); |
| 111 | /// assert_eq!(none_of::<_, _, (&str, ErrorKind)>("a" )("" ), Err(Err::Error(("" , ErrorKind::NoneOf)))); |
| 112 | /// ``` |
| 113 | pub fn none_of<I, T, Error: ParseError<I>>(list: T) -> impl Fn(I) -> IResult<I, char, Error> |
| 114 | where |
| 115 | I: Slice<RangeFrom<usize>> + InputIter, |
| 116 | <I as InputIter>::Item: AsChar + Copy, |
| 117 | T: FindToken<<I as InputIter>::Item>, |
| 118 | { |
| 119 | move |i: I| match (i).iter_elements().next().map(|c: impl AsChar + Copy| (c, !list.find_token(c))) { |
| 120 | Some((c: impl AsChar + Copy, true)) => Ok((i.slice(range:c.len()..), c.as_char())), |
| 121 | _ => Err(Err::Error(Error::from_error_kind(input:i, kind:ErrorKind::NoneOf))), |
| 122 | } |
| 123 | } |
| 124 | |
| 125 | /// Recognizes the string "\r\n". |
| 126 | /// |
| 127 | /// *Complete version*: Will return an error if there's not enough input data. |
| 128 | /// # Example |
| 129 | /// |
| 130 | /// ``` |
| 131 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult}; |
| 132 | /// # use nom::character::complete::crlf; |
| 133 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 134 | /// crlf(input) |
| 135 | /// } |
| 136 | /// |
| 137 | /// assert_eq!(parser(" \r\nc" ), Ok(("c" , " \r\n" ))); |
| 138 | /// assert_eq!(parser("ab \r\nc" ), Err(Err::Error(Error::new("ab \r\nc" , ErrorKind::CrLf)))); |
| 139 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::CrLf)))); |
| 140 | /// ``` |
| 141 | pub fn crlf<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 142 | where |
| 143 | T: Slice<Range<usize>> + Slice<RangeFrom<usize>>, |
| 144 | T: InputIter, |
| 145 | T: Compare<&'static str>, |
| 146 | { |
| 147 | match input.compare(" \r\n" ) { |
| 148 | //FIXME: is this the right index? |
| 149 | CompareResult::Ok => Ok((input.slice(range:2..), input.slice(range:0..2))), |
| 150 | _ => { |
| 151 | let e: ErrorKind = ErrorKind::CrLf; |
| 152 | Err(Err::Error(E::from_error_kind(input, kind:e))) |
| 153 | } |
| 154 | } |
| 155 | } |
| 156 | |
| 157 | //FIXME: there's still an incomplete |
| 158 | /// Recognizes a string of any char except '\r\n' or '\n'. |
| 159 | /// |
| 160 | /// *Complete version*: Will return an error if there's not enough input data. |
| 161 | /// # Example |
| 162 | /// |
| 163 | /// ``` |
| 164 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 165 | /// # use nom::character::complete::not_line_ending; |
| 166 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 167 | /// not_line_ending(input) |
| 168 | /// } |
| 169 | /// |
| 170 | /// assert_eq!(parser("ab \r\nc" ), Ok((" \r\nc" , "ab" ))); |
| 171 | /// assert_eq!(parser("ab \nc" ), Ok((" \nc" , "ab" ))); |
| 172 | /// assert_eq!(parser("abc" ), Ok(("" , "abc" ))); |
| 173 | /// assert_eq!(parser("" ), Ok(("" , "" ))); |
| 174 | /// assert_eq!(parser("a \rb \nc" ), Err(Err::Error(Error { input: "a \rb \nc" , code: ErrorKind::Tag }))); |
| 175 | /// assert_eq!(parser("a \rbc" ), Err(Err::Error(Error { input: "a \rbc" , code: ErrorKind::Tag }))); |
| 176 | /// ``` |
| 177 | pub fn not_line_ending<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 178 | where |
| 179 | T: Slice<Range<usize>> + Slice<RangeFrom<usize>> + Slice<RangeTo<usize>>, |
| 180 | T: InputIter + InputLength, |
| 181 | T: Compare<&'static str>, |
| 182 | <T as InputIter>::Item: AsChar, |
| 183 | <T as InputIter>::Item: AsChar, |
| 184 | { |
| 185 | match input.position(|item| { |
| 186 | let c = item.as_char(); |
| 187 | c == ' \r' || c == ' \n' |
| 188 | }) { |
| 189 | None => Ok((input.slice(input.input_len()..), input)), |
| 190 | Some(index) => { |
| 191 | let mut it = input.slice(index..).iter_elements(); |
| 192 | let nth = it.next().unwrap().as_char(); |
| 193 | if nth == ' \r' { |
| 194 | let sliced = input.slice(index..); |
| 195 | let comp = sliced.compare(" \r\n" ); |
| 196 | match comp { |
| 197 | //FIXME: calculate the right index |
| 198 | CompareResult::Ok => Ok((input.slice(index..), input.slice(..index))), |
| 199 | _ => { |
| 200 | let e: ErrorKind = ErrorKind::Tag; |
| 201 | Err(Err::Error(E::from_error_kind(input, e))) |
| 202 | } |
| 203 | } |
| 204 | } else { |
| 205 | Ok((input.slice(index..), input.slice(..index))) |
| 206 | } |
| 207 | } |
| 208 | } |
| 209 | } |
| 210 | |
| 211 | /// Recognizes an end of line (both '\n' and '\r\n'). |
| 212 | /// |
| 213 | /// *Complete version*: Will return an error if there's not enough input data. |
| 214 | /// # Example |
| 215 | /// |
| 216 | /// ``` |
| 217 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 218 | /// # use nom::character::complete::line_ending; |
| 219 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 220 | /// line_ending(input) |
| 221 | /// } |
| 222 | /// |
| 223 | /// assert_eq!(parser(" \r\nc" ), Ok(("c" , " \r\n" ))); |
| 224 | /// assert_eq!(parser("ab \r\nc" ), Err(Err::Error(Error::new("ab \r\nc" , ErrorKind::CrLf)))); |
| 225 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::CrLf)))); |
| 226 | /// ``` |
| 227 | pub fn line_ending<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 228 | where |
| 229 | T: Slice<Range<usize>> + Slice<RangeFrom<usize>> + Slice<RangeTo<usize>>, |
| 230 | T: InputIter + InputLength, |
| 231 | T: Compare<&'static str>, |
| 232 | { |
| 233 | match input.compare(" \n" ) { |
| 234 | CompareResult::Ok => Ok((input.slice(range:1..), input.slice(range:0..1))), |
| 235 | CompareResult::Incomplete => Err(Err::Error(E::from_error_kind(input, kind:ErrorKind::CrLf))), |
| 236 | CompareResult::Error => { |
| 237 | match input.compare(" \r\n" ) { |
| 238 | //FIXME: is this the right index? |
| 239 | CompareResult::Ok => Ok((input.slice(range:2..), input.slice(range:0..2))), |
| 240 | _ => Err(Err::Error(E::from_error_kind(input, kind:ErrorKind::CrLf))), |
| 241 | } |
| 242 | } |
| 243 | } |
| 244 | } |
| 245 | |
| 246 | /// Matches a newline character '\n'. |
| 247 | /// |
| 248 | /// *Complete version*: Will return an error if there's not enough input data. |
| 249 | /// # Example |
| 250 | /// |
| 251 | /// ``` |
| 252 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 253 | /// # use nom::character::complete::newline; |
| 254 | /// fn parser(input: &str) -> IResult<&str, char> { |
| 255 | /// newline(input) |
| 256 | /// } |
| 257 | /// |
| 258 | /// assert_eq!(parser(" \nc" ), Ok(("c" , ' \n' ))); |
| 259 | /// assert_eq!(parser(" \r\nc" ), Err(Err::Error(Error::new(" \r\nc" , ErrorKind::Char)))); |
| 260 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::Char)))); |
| 261 | /// ``` |
| 262 | pub fn newline<I, Error: ParseError<I>>(input: I) -> IResult<I, char, Error> |
| 263 | where |
| 264 | I: Slice<RangeFrom<usize>> + InputIter, |
| 265 | <I as InputIter>::Item: AsChar, |
| 266 | { |
| 267 | char(' \n' )(input) |
| 268 | } |
| 269 | |
| 270 | /// Matches a tab character '\t'. |
| 271 | /// |
| 272 | /// *Complete version*: Will return an error if there's not enough input data. |
| 273 | /// # Example |
| 274 | /// |
| 275 | /// ``` |
| 276 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 277 | /// # use nom::character::complete::tab; |
| 278 | /// fn parser(input: &str) -> IResult<&str, char> { |
| 279 | /// tab(input) |
| 280 | /// } |
| 281 | /// |
| 282 | /// assert_eq!(parser(" \tc" ), Ok(("c" , ' \t' ))); |
| 283 | /// assert_eq!(parser(" \r\nc" ), Err(Err::Error(Error::new(" \r\nc" , ErrorKind::Char)))); |
| 284 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::Char)))); |
| 285 | /// ``` |
| 286 | pub fn tab<I, Error: ParseError<I>>(input: I) -> IResult<I, char, Error> |
| 287 | where |
| 288 | I: Slice<RangeFrom<usize>> + InputIter, |
| 289 | <I as InputIter>::Item: AsChar, |
| 290 | { |
| 291 | char(' \t' )(input) |
| 292 | } |
| 293 | |
| 294 | /// Matches one byte as a character. Note that the input type will |
| 295 | /// accept a `str`, but not a `&[u8]`, unlike many other nom parsers. |
| 296 | /// |
| 297 | /// *Complete version*: Will return an error if there's not enough input data. |
| 298 | /// # Example |
| 299 | /// |
| 300 | /// ``` |
| 301 | /// # use nom::{character::complete::anychar, Err, error::{Error, ErrorKind}, IResult}; |
| 302 | /// fn parser(input: &str) -> IResult<&str, char> { |
| 303 | /// anychar(input) |
| 304 | /// } |
| 305 | /// |
| 306 | /// assert_eq!(parser("abc" ), Ok(("bc" ,'a' ))); |
| 307 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::Eof)))); |
| 308 | /// ``` |
| 309 | pub fn anychar<T, E: ParseError<T>>(input: T) -> IResult<T, char, E> |
| 310 | where |
| 311 | T: InputIter + InputLength + Slice<RangeFrom<usize>>, |
| 312 | <T as InputIter>::Item: AsChar, |
| 313 | { |
| 314 | let mut it: impl AsChar = input.iter_indices(); |
| 315 | match it.next() { |
| 316 | None => Err(Err::Error(E::from_error_kind(input, kind:ErrorKind::Eof))), |
| 317 | Some((_, c: impl AsChar)) => match it.next() { |
| 318 | None => Ok((input.slice(range:input.input_len()..), c.as_char())), |
| 319 | Some((idx: usize, _)) => Ok((input.slice(range:idx..), c.as_char())), |
| 320 | }, |
| 321 | } |
| 322 | } |
| 323 | |
| 324 | /// Recognizes zero or more lowercase and uppercase ASCII alphabetic characters: a-z, A-Z |
| 325 | /// |
| 326 | /// *Complete version*: Will return the whole input if no terminating token is found (a non |
| 327 | /// alphabetic character). |
| 328 | /// # Example |
| 329 | /// |
| 330 | /// ``` |
| 331 | /// # use nom::{Err, error::ErrorKind, IResult, Needed}; |
| 332 | /// # use nom::character::complete::alpha0; |
| 333 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 334 | /// alpha0(input) |
| 335 | /// } |
| 336 | /// |
| 337 | /// assert_eq!(parser("ab1c" ), Ok(("1c" , "ab" ))); |
| 338 | /// assert_eq!(parser("1c" ), Ok(("1c" , "" ))); |
| 339 | /// assert_eq!(parser("" ), Ok(("" , "" ))); |
| 340 | /// ``` |
| 341 | pub fn alpha0<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 342 | where |
| 343 | T: InputTakeAtPosition, |
| 344 | <T as InputTakeAtPosition>::Item: AsChar, |
| 345 | { |
| 346 | input.split_at_position_complete(|item: impl AsChar| !item.is_alpha()) |
| 347 | } |
| 348 | |
| 349 | /// Recognizes one or more lowercase and uppercase ASCII alphabetic characters: a-z, A-Z |
| 350 | /// |
| 351 | /// *Complete version*: Will return an error if there's not enough input data, |
| 352 | /// or the whole input if no terminating token is found (a non alphabetic character). |
| 353 | /// # Example |
| 354 | /// |
| 355 | /// ``` |
| 356 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 357 | /// # use nom::character::complete::alpha1; |
| 358 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 359 | /// alpha1(input) |
| 360 | /// } |
| 361 | /// |
| 362 | /// assert_eq!(parser("aB1c" ), Ok(("1c" , "aB" ))); |
| 363 | /// assert_eq!(parser("1c" ), Err(Err::Error(Error::new("1c" , ErrorKind::Alpha)))); |
| 364 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::Alpha)))); |
| 365 | /// ``` |
| 366 | pub fn alpha1<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 367 | where |
| 368 | T: InputTakeAtPosition, |
| 369 | <T as InputTakeAtPosition>::Item: AsChar, |
| 370 | { |
| 371 | input.split_at_position1_complete(|item| !item.is_alpha(), e:ErrorKind::Alpha) |
| 372 | } |
| 373 | |
| 374 | /// Recognizes zero or more ASCII numerical characters: 0-9 |
| 375 | /// |
| 376 | /// *Complete version*: Will return an error if there's not enough input data, |
| 377 | /// or the whole input if no terminating token is found (a non digit character). |
| 378 | /// # Example |
| 379 | /// |
| 380 | /// ``` |
| 381 | /// # use nom::{Err, error::ErrorKind, IResult, Needed}; |
| 382 | /// # use nom::character::complete::digit0; |
| 383 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 384 | /// digit0(input) |
| 385 | /// } |
| 386 | /// |
| 387 | /// assert_eq!(parser("21c" ), Ok(("c" , "21" ))); |
| 388 | /// assert_eq!(parser("21" ), Ok(("" , "21" ))); |
| 389 | /// assert_eq!(parser("a21c" ), Ok(("a21c" , "" ))); |
| 390 | /// assert_eq!(parser("" ), Ok(("" , "" ))); |
| 391 | /// ``` |
| 392 | pub fn digit0<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 393 | where |
| 394 | T: InputTakeAtPosition, |
| 395 | <T as InputTakeAtPosition>::Item: AsChar, |
| 396 | { |
| 397 | input.split_at_position_complete(|item: impl AsChar| !item.is_dec_digit()) |
| 398 | } |
| 399 | |
| 400 | /// Recognizes one or more ASCII numerical characters: 0-9 |
| 401 | /// |
| 402 | /// *Complete version*: Will return an error if there's not enough input data, |
| 403 | /// or the whole input if no terminating token is found (a non digit character). |
| 404 | /// # Example |
| 405 | /// |
| 406 | /// ``` |
| 407 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 408 | /// # use nom::character::complete::digit1; |
| 409 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 410 | /// digit1(input) |
| 411 | /// } |
| 412 | /// |
| 413 | /// assert_eq!(parser("21c" ), Ok(("c" , "21" ))); |
| 414 | /// assert_eq!(parser("c1" ), Err(Err::Error(Error::new("c1" , ErrorKind::Digit)))); |
| 415 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::Digit)))); |
| 416 | /// ``` |
| 417 | /// |
| 418 | /// ## Parsing an integer |
| 419 | /// You can use `digit1` in combination with [`map_res`] to parse an integer: |
| 420 | /// |
| 421 | /// ``` |
| 422 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 423 | /// # use nom::combinator::map_res; |
| 424 | /// # use nom::character::complete::digit1; |
| 425 | /// fn parser(input: &str) -> IResult<&str, u32> { |
| 426 | /// map_res(digit1, str::parse)(input) |
| 427 | /// } |
| 428 | /// |
| 429 | /// assert_eq!(parser("416" ), Ok(("" , 416))); |
| 430 | /// assert_eq!(parser("12b" ), Ok(("b" , 12))); |
| 431 | /// assert!(parser("b" ).is_err()); |
| 432 | /// ``` |
| 433 | /// |
| 434 | /// [`map_res`]: crate::combinator::map_res |
| 435 | pub fn digit1<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 436 | where |
| 437 | T: InputTakeAtPosition, |
| 438 | <T as InputTakeAtPosition>::Item: AsChar, |
| 439 | { |
| 440 | input.split_at_position1_complete(|item| !item.is_dec_digit(), e:ErrorKind::Digit) |
| 441 | } |
| 442 | |
| 443 | /// Recognizes zero or more ASCII hexadecimal numerical characters: 0-9, A-F, a-f |
| 444 | /// |
| 445 | /// *Complete version*: Will return the whole input if no terminating token is found (a non hexadecimal digit character). |
| 446 | /// # Example |
| 447 | /// |
| 448 | /// ``` |
| 449 | /// # use nom::{Err, error::ErrorKind, IResult, Needed}; |
| 450 | /// # use nom::character::complete::hex_digit0; |
| 451 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 452 | /// hex_digit0(input) |
| 453 | /// } |
| 454 | /// |
| 455 | /// assert_eq!(parser("21cZ" ), Ok(("Z" , "21c" ))); |
| 456 | /// assert_eq!(parser("Z21c" ), Ok(("Z21c" , "" ))); |
| 457 | /// assert_eq!(parser("" ), Ok(("" , "" ))); |
| 458 | /// ``` |
| 459 | pub fn hex_digit0<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 460 | where |
| 461 | T: InputTakeAtPosition, |
| 462 | <T as InputTakeAtPosition>::Item: AsChar, |
| 463 | { |
| 464 | input.split_at_position_complete(|item: impl AsChar| !item.is_hex_digit()) |
| 465 | } |
| 466 | /// Recognizes one or more ASCII hexadecimal numerical characters: 0-9, A-F, a-f |
| 467 | /// |
| 468 | /// *Complete version*: Will return an error if there's not enough input data, |
| 469 | /// or the whole input if no terminating token is found (a non hexadecimal digit character). |
| 470 | /// # Example |
| 471 | /// |
| 472 | /// ``` |
| 473 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 474 | /// # use nom::character::complete::hex_digit1; |
| 475 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 476 | /// hex_digit1(input) |
| 477 | /// } |
| 478 | /// |
| 479 | /// assert_eq!(parser("21cZ" ), Ok(("Z" , "21c" ))); |
| 480 | /// assert_eq!(parser("H2" ), Err(Err::Error(Error::new("H2" , ErrorKind::HexDigit)))); |
| 481 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::HexDigit)))); |
| 482 | /// ``` |
| 483 | pub fn hex_digit1<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 484 | where |
| 485 | T: InputTakeAtPosition, |
| 486 | <T as InputTakeAtPosition>::Item: AsChar, |
| 487 | { |
| 488 | input.split_at_position1_complete(|item| !item.is_hex_digit(), e:ErrorKind::HexDigit) |
| 489 | } |
| 490 | |
| 491 | /// Recognizes zero or more octal characters: 0-7 |
| 492 | /// |
| 493 | /// *Complete version*: Will return the whole input if no terminating token is found (a non octal |
| 494 | /// digit character). |
| 495 | /// # Example |
| 496 | /// |
| 497 | /// ``` |
| 498 | /// # use nom::{Err, error::ErrorKind, IResult, Needed}; |
| 499 | /// # use nom::character::complete::oct_digit0; |
| 500 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 501 | /// oct_digit0(input) |
| 502 | /// } |
| 503 | /// |
| 504 | /// assert_eq!(parser("21cZ" ), Ok(("cZ" , "21" ))); |
| 505 | /// assert_eq!(parser("Z21c" ), Ok(("Z21c" , "" ))); |
| 506 | /// assert_eq!(parser("" ), Ok(("" , "" ))); |
| 507 | /// ``` |
| 508 | pub fn oct_digit0<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 509 | where |
| 510 | T: InputTakeAtPosition, |
| 511 | <T as InputTakeAtPosition>::Item: AsChar, |
| 512 | { |
| 513 | input.split_at_position_complete(|item: impl AsChar| !item.is_oct_digit()) |
| 514 | } |
| 515 | |
| 516 | /// Recognizes one or more octal characters: 0-7 |
| 517 | /// |
| 518 | /// *Complete version*: Will return an error if there's not enough input data, |
| 519 | /// or the whole input if no terminating token is found (a non octal digit character). |
| 520 | /// # Example |
| 521 | /// |
| 522 | /// ``` |
| 523 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 524 | /// # use nom::character::complete::oct_digit1; |
| 525 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 526 | /// oct_digit1(input) |
| 527 | /// } |
| 528 | /// |
| 529 | /// assert_eq!(parser("21cZ" ), Ok(("cZ" , "21" ))); |
| 530 | /// assert_eq!(parser("H2" ), Err(Err::Error(Error::new("H2" , ErrorKind::OctDigit)))); |
| 531 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::OctDigit)))); |
| 532 | /// ``` |
| 533 | pub fn oct_digit1<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 534 | where |
| 535 | T: InputTakeAtPosition, |
| 536 | <T as InputTakeAtPosition>::Item: AsChar, |
| 537 | { |
| 538 | input.split_at_position1_complete(|item| !item.is_oct_digit(), e:ErrorKind::OctDigit) |
| 539 | } |
| 540 | |
| 541 | /// Recognizes zero or more ASCII numerical and alphabetic characters: 0-9, a-z, A-Z |
| 542 | /// |
| 543 | /// *Complete version*: Will return the whole input if no terminating token is found (a non |
| 544 | /// alphanumerical character). |
| 545 | /// # Example |
| 546 | /// |
| 547 | /// ``` |
| 548 | /// # use nom::{Err, error::ErrorKind, IResult, Needed}; |
| 549 | /// # use nom::character::complete::alphanumeric0; |
| 550 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 551 | /// alphanumeric0(input) |
| 552 | /// } |
| 553 | /// |
| 554 | /// assert_eq!(parser("21cZ%1" ), Ok(("%1" , "21cZ" ))); |
| 555 | /// assert_eq!(parser("&Z21c" ), Ok(("&Z21c" , "" ))); |
| 556 | /// assert_eq!(parser("" ), Ok(("" , "" ))); |
| 557 | /// ``` |
| 558 | pub fn alphanumeric0<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 559 | where |
| 560 | T: InputTakeAtPosition, |
| 561 | <T as InputTakeAtPosition>::Item: AsChar, |
| 562 | { |
| 563 | input.split_at_position_complete(|item: impl AsChar| !item.is_alphanum()) |
| 564 | } |
| 565 | |
| 566 | /// Recognizes one or more ASCII numerical and alphabetic characters: 0-9, a-z, A-Z |
| 567 | /// |
| 568 | /// *Complete version*: Will return an error if there's not enough input data, |
| 569 | /// or the whole input if no terminating token is found (a non alphanumerical character). |
| 570 | /// # Example |
| 571 | /// |
| 572 | /// ``` |
| 573 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 574 | /// # use nom::character::complete::alphanumeric1; |
| 575 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 576 | /// alphanumeric1(input) |
| 577 | /// } |
| 578 | /// |
| 579 | /// assert_eq!(parser("21cZ%1" ), Ok(("%1" , "21cZ" ))); |
| 580 | /// assert_eq!(parser("&H2" ), Err(Err::Error(Error::new("&H2" , ErrorKind::AlphaNumeric)))); |
| 581 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::AlphaNumeric)))); |
| 582 | /// ``` |
| 583 | pub fn alphanumeric1<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 584 | where |
| 585 | T: InputTakeAtPosition, |
| 586 | <T as InputTakeAtPosition>::Item: AsChar, |
| 587 | { |
| 588 | input.split_at_position1_complete(|item| !item.is_alphanum(), e:ErrorKind::AlphaNumeric) |
| 589 | } |
| 590 | |
| 591 | /// Recognizes zero or more spaces and tabs. |
| 592 | /// |
| 593 | /// *Complete version*: Will return the whole input if no terminating token is found (a non space |
| 594 | /// character). |
| 595 | /// # Example |
| 596 | /// |
| 597 | /// ``` |
| 598 | /// # use nom::{Err, error::ErrorKind, IResult, Needed}; |
| 599 | /// # use nom::character::complete::space0; |
| 600 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 601 | /// space0(input) |
| 602 | /// } |
| 603 | /// |
| 604 | /// assert_eq!(parser(" \t21c" ), Ok(("21c" , " \t" ))); |
| 605 | /// assert_eq!(parser("Z21c" ), Ok(("Z21c" , "" ))); |
| 606 | /// assert_eq!(parser("" ), Ok(("" , "" ))); |
| 607 | /// ``` |
| 608 | pub fn space0<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 609 | where |
| 610 | T: InputTakeAtPosition, |
| 611 | <T as InputTakeAtPosition>::Item: AsChar + Clone, |
| 612 | { |
| 613 | input.split_at_position_complete(|item: impl AsChar + Clone| { |
| 614 | let c: char = item.as_char(); |
| 615 | !(c == ' ' || c == ' \t' ) |
| 616 | }) |
| 617 | } |
| 618 | |
| 619 | /// Recognizes one or more spaces and tabs. |
| 620 | /// |
| 621 | /// *Complete version*: Will return an error if there's not enough input data, |
| 622 | /// or the whole input if no terminating token is found (a non space character). |
| 623 | /// # Example |
| 624 | /// |
| 625 | /// ``` |
| 626 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 627 | /// # use nom::character::complete::space1; |
| 628 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 629 | /// space1(input) |
| 630 | /// } |
| 631 | /// |
| 632 | /// assert_eq!(parser(" \t21c" ), Ok(("21c" , " \t" ))); |
| 633 | /// assert_eq!(parser("H2" ), Err(Err::Error(Error::new("H2" , ErrorKind::Space)))); |
| 634 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::Space)))); |
| 635 | /// ``` |
| 636 | pub fn space1<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 637 | where |
| 638 | T: InputTakeAtPosition, |
| 639 | <T as InputTakeAtPosition>::Item: AsChar + Clone, |
| 640 | { |
| 641 | input.split_at_position1_complete( |
| 642 | |item| { |
| 643 | let c = item.as_char(); |
| 644 | !(c == ' ' || c == ' \t' ) |
| 645 | }, |
| 646 | e:ErrorKind::Space, |
| 647 | ) |
| 648 | } |
| 649 | |
| 650 | /// Recognizes zero or more spaces, tabs, carriage returns and line feeds. |
| 651 | /// |
| 652 | /// *Complete version*: will return the whole input if no terminating token is found (a non space |
| 653 | /// character). |
| 654 | /// # Example |
| 655 | /// |
| 656 | /// ``` |
| 657 | /// # use nom::{Err, error::ErrorKind, IResult, Needed}; |
| 658 | /// # use nom::character::complete::multispace0; |
| 659 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 660 | /// multispace0(input) |
| 661 | /// } |
| 662 | /// |
| 663 | /// assert_eq!(parser(" \t\n\r21c" ), Ok(("21c" , " \t\n\r" ))); |
| 664 | /// assert_eq!(parser("Z21c" ), Ok(("Z21c" , "" ))); |
| 665 | /// assert_eq!(parser("" ), Ok(("" , "" ))); |
| 666 | /// ``` |
| 667 | pub fn multispace0<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 668 | where |
| 669 | T: InputTakeAtPosition, |
| 670 | <T as InputTakeAtPosition>::Item: AsChar + Clone, |
| 671 | { |
| 672 | input.split_at_position_complete(|item: impl AsChar + Clone| { |
| 673 | let c: char = item.as_char(); |
| 674 | !(c == ' ' || c == ' \t' || c == ' \r' || c == ' \n' ) |
| 675 | }) |
| 676 | } |
| 677 | |
| 678 | /// Recognizes one or more spaces, tabs, carriage returns and line feeds. |
| 679 | /// |
| 680 | /// *Complete version*: will return an error if there's not enough input data, |
| 681 | /// or the whole input if no terminating token is found (a non space character). |
| 682 | /// # Example |
| 683 | /// |
| 684 | /// ``` |
| 685 | /// # use nom::{Err, error::{Error, ErrorKind}, IResult, Needed}; |
| 686 | /// # use nom::character::complete::multispace1; |
| 687 | /// fn parser(input: &str) -> IResult<&str, &str> { |
| 688 | /// multispace1(input) |
| 689 | /// } |
| 690 | /// |
| 691 | /// assert_eq!(parser(" \t\n\r21c" ), Ok(("21c" , " \t\n\r" ))); |
| 692 | /// assert_eq!(parser("H2" ), Err(Err::Error(Error::new("H2" , ErrorKind::MultiSpace)))); |
| 693 | /// assert_eq!(parser("" ), Err(Err::Error(Error::new("" , ErrorKind::MultiSpace)))); |
| 694 | /// ``` |
| 695 | pub fn multispace1<T, E: ParseError<T>>(input: T) -> IResult<T, T, E> |
| 696 | where |
| 697 | T: InputTakeAtPosition, |
| 698 | <T as InputTakeAtPosition>::Item: AsChar + Clone, |
| 699 | { |
| 700 | input.split_at_position1_complete( |
| 701 | |item| { |
| 702 | let c = item.as_char(); |
| 703 | !(c == ' ' || c == ' \t' || c == ' \r' || c == ' \n' ) |
| 704 | }, |
| 705 | e:ErrorKind::MultiSpace, |
| 706 | ) |
| 707 | } |
| 708 | |
| 709 | pub(crate) fn sign<T, E: ParseError<T>>(input: T) -> IResult<T, bool, E> |
| 710 | where |
| 711 | T: Clone + InputTake, |
| 712 | T: for<'a> dynCompare<&'a [u8]>, |
| 713 | { |
| 714 | use crate::bytes::complete::tag; |
| 715 | use crate::combinator::value; |
| 716 | |
| 717 | let (i: T, opt_sign: Option) = opt(alt(( |
| 718 | value(val:false, parser:tag(&b"-" [..])), |
| 719 | value(val:true, parser:tag(&b"+" [..])), |
| 720 | )))(input)?; |
| 721 | let sign: bool = opt_sign.unwrap_or(default:true); |
| 722 | |
| 723 | Ok((i, sign)) |
| 724 | } |
| 725 | |
| 726 | #[doc (hidden)] |
| 727 | macro_rules! ints { |
| 728 | ($($t:tt)+) => { |
| 729 | $( |
| 730 | /// will parse a number in text form to a number |
| 731 | /// |
| 732 | /// *Complete version*: can parse until the end of input. |
| 733 | pub fn $t<T, E: ParseError<T>>(input: T) -> IResult<T, $t, E> |
| 734 | where |
| 735 | T: InputIter + Slice<RangeFrom<usize>> + InputLength + InputTake + Clone, |
| 736 | <T as InputIter>::Item: AsChar, |
| 737 | T: for <'a> Compare<&'a[u8]>, |
| 738 | { |
| 739 | let (i, sign) = sign(input.clone())?; |
| 740 | |
| 741 | if i.input_len() == 0 { |
| 742 | return Err(Err::Error(E::from_error_kind(input, ErrorKind::Digit))); |
| 743 | } |
| 744 | |
| 745 | let mut value: $t = 0; |
| 746 | if sign { |
| 747 | for (pos, c) in i.iter_indices() { |
| 748 | match c.as_char().to_digit(10) { |
| 749 | None => { |
| 750 | if pos == 0 { |
| 751 | return Err(Err::Error(E::from_error_kind(input, ErrorKind::Digit))); |
| 752 | } else { |
| 753 | return Ok((i.slice(pos..), value)); |
| 754 | } |
| 755 | }, |
| 756 | Some(d) => match value.checked_mul(10).and_then(|v| v.checked_add(d as $t)) { |
| 757 | None => return Err(Err::Error(E::from_error_kind(input, ErrorKind::Digit))), |
| 758 | Some(v) => value = v, |
| 759 | } |
| 760 | } |
| 761 | } |
| 762 | } else { |
| 763 | for (pos, c) in i.iter_indices() { |
| 764 | match c.as_char().to_digit(10) { |
| 765 | None => { |
| 766 | if pos == 0 { |
| 767 | return Err(Err::Error(E::from_error_kind(input, ErrorKind::Digit))); |
| 768 | } else { |
| 769 | return Ok((i.slice(pos..), value)); |
| 770 | } |
| 771 | }, |
| 772 | Some(d) => match value.checked_mul(10).and_then(|v| v.checked_sub(d as $t)) { |
| 773 | None => return Err(Err::Error(E::from_error_kind(input, ErrorKind::Digit))), |
| 774 | Some(v) => value = v, |
| 775 | } |
| 776 | } |
| 777 | } |
| 778 | } |
| 779 | |
| 780 | Ok((i.slice(i.input_len()..), value)) |
| 781 | } |
| 782 | )+ |
| 783 | } |
| 784 | } |
| 785 | |
| 786 | ints! { i8 i16 i32 i64 i128 } |
| 787 | |
| 788 | #[doc (hidden)] |
| 789 | macro_rules! uints { |
| 790 | ($($t:tt)+) => { |
| 791 | $( |
| 792 | /// will parse a number in text form to a number |
| 793 | /// |
| 794 | /// *Complete version*: can parse until the end of input. |
| 795 | pub fn $t<T, E: ParseError<T>>(input: T) -> IResult<T, $t, E> |
| 796 | where |
| 797 | T: InputIter + Slice<RangeFrom<usize>> + InputLength, |
| 798 | <T as InputIter>::Item: AsChar, |
| 799 | { |
| 800 | let i = input; |
| 801 | |
| 802 | if i.input_len() == 0 { |
| 803 | return Err(Err::Error(E::from_error_kind(i, ErrorKind::Digit))); |
| 804 | } |
| 805 | |
| 806 | let mut value: $t = 0; |
| 807 | for (pos, c) in i.iter_indices() { |
| 808 | match c.as_char().to_digit(10) { |
| 809 | None => { |
| 810 | if pos == 0 { |
| 811 | return Err(Err::Error(E::from_error_kind(i, ErrorKind::Digit))); |
| 812 | } else { |
| 813 | return Ok((i.slice(pos..), value)); |
| 814 | } |
| 815 | }, |
| 816 | Some(d) => match value.checked_mul(10).and_then(|v| v.checked_add(d as $t)) { |
| 817 | None => return Err(Err::Error(E::from_error_kind(i, ErrorKind::Digit))), |
| 818 | Some(v) => value = v, |
| 819 | } |
| 820 | } |
| 821 | } |
| 822 | |
| 823 | Ok((i.slice(i.input_len()..), value)) |
| 824 | } |
| 825 | )+ |
| 826 | } |
| 827 | } |
| 828 | |
| 829 | uints! { u8 u16 u32 u64 u128 } |
| 830 | |
| 831 | #[cfg (test)] |
| 832 | mod tests { |
| 833 | use super::*; |
| 834 | use crate::internal::Err; |
| 835 | use crate::traits::ParseTo; |
| 836 | use proptest::prelude::*; |
| 837 | |
| 838 | macro_rules! assert_parse( |
| 839 | ($left: expr, $right: expr) => { |
| 840 | let res: $crate::IResult<_, _, (_, ErrorKind)> = $left; |
| 841 | assert_eq!(res, $right); |
| 842 | }; |
| 843 | ); |
| 844 | |
| 845 | #[test ] |
| 846 | fn character() { |
| 847 | let empty: &[u8] = b"" ; |
| 848 | let a: &[u8] = b"abcd" ; |
| 849 | let b: &[u8] = b"1234" ; |
| 850 | let c: &[u8] = b"a123" ; |
| 851 | let d: &[u8] = "azé12" .as_bytes(); |
| 852 | let e: &[u8] = b" " ; |
| 853 | let f: &[u8] = b" ;" ; |
| 854 | //assert_eq!(alpha1::<_, (_, ErrorKind)>(a), Err(Err::Incomplete(Needed::Size(1)))); |
| 855 | assert_parse!(alpha1(a), Ok((empty, a))); |
| 856 | assert_eq!(alpha1(b), Err(Err::Error((b, ErrorKind::Alpha)))); |
| 857 | assert_eq!(alpha1::<_, (_, ErrorKind)>(c), Ok((&c[1..], &b"a" [..]))); |
| 858 | assert_eq!( |
| 859 | alpha1::<_, (_, ErrorKind)>(d), |
| 860 | Ok(("é12" .as_bytes(), &b"az" [..])) |
| 861 | ); |
| 862 | assert_eq!(digit1(a), Err(Err::Error((a, ErrorKind::Digit)))); |
| 863 | assert_eq!(digit1::<_, (_, ErrorKind)>(b), Ok((empty, b))); |
| 864 | assert_eq!(digit1(c), Err(Err::Error((c, ErrorKind::Digit)))); |
| 865 | assert_eq!(digit1(d), Err(Err::Error((d, ErrorKind::Digit)))); |
| 866 | assert_eq!(hex_digit1::<_, (_, ErrorKind)>(a), Ok((empty, a))); |
| 867 | assert_eq!(hex_digit1::<_, (_, ErrorKind)>(b), Ok((empty, b))); |
| 868 | assert_eq!(hex_digit1::<_, (_, ErrorKind)>(c), Ok((empty, c))); |
| 869 | assert_eq!( |
| 870 | hex_digit1::<_, (_, ErrorKind)>(d), |
| 871 | Ok(("zé12" .as_bytes(), &b"a" [..])) |
| 872 | ); |
| 873 | assert_eq!(hex_digit1(e), Err(Err::Error((e, ErrorKind::HexDigit)))); |
| 874 | assert_eq!(oct_digit1(a), Err(Err::Error((a, ErrorKind::OctDigit)))); |
| 875 | assert_eq!(oct_digit1::<_, (_, ErrorKind)>(b), Ok((empty, b))); |
| 876 | assert_eq!(oct_digit1(c), Err(Err::Error((c, ErrorKind::OctDigit)))); |
| 877 | assert_eq!(oct_digit1(d), Err(Err::Error((d, ErrorKind::OctDigit)))); |
| 878 | assert_eq!(alphanumeric1::<_, (_, ErrorKind)>(a), Ok((empty, a))); |
| 879 | //assert_eq!(fix_error!(b,(), alphanumeric), Ok((empty, b))); |
| 880 | assert_eq!(alphanumeric1::<_, (_, ErrorKind)>(c), Ok((empty, c))); |
| 881 | assert_eq!( |
| 882 | alphanumeric1::<_, (_, ErrorKind)>(d), |
| 883 | Ok(("é12" .as_bytes(), &b"az" [..])) |
| 884 | ); |
| 885 | assert_eq!(space1::<_, (_, ErrorKind)>(e), Ok((empty, e))); |
| 886 | assert_eq!(space1::<_, (_, ErrorKind)>(f), Ok((&b";" [..], &b" " [..]))); |
| 887 | } |
| 888 | |
| 889 | #[cfg (feature = "alloc" )] |
| 890 | #[test ] |
| 891 | fn character_s() { |
| 892 | let empty = "" ; |
| 893 | let a = "abcd" ; |
| 894 | let b = "1234" ; |
| 895 | let c = "a123" ; |
| 896 | let d = "azé12" ; |
| 897 | let e = " " ; |
| 898 | assert_eq!(alpha1::<_, (_, ErrorKind)>(a), Ok((empty, a))); |
| 899 | assert_eq!(alpha1(b), Err(Err::Error((b, ErrorKind::Alpha)))); |
| 900 | assert_eq!(alpha1::<_, (_, ErrorKind)>(c), Ok((&c[1..], &"a" [..]))); |
| 901 | assert_eq!(alpha1::<_, (_, ErrorKind)>(d), Ok(("é12" , &"az" [..]))); |
| 902 | assert_eq!(digit1(a), Err(Err::Error((a, ErrorKind::Digit)))); |
| 903 | assert_eq!(digit1::<_, (_, ErrorKind)>(b), Ok((empty, b))); |
| 904 | assert_eq!(digit1(c), Err(Err::Error((c, ErrorKind::Digit)))); |
| 905 | assert_eq!(digit1(d), Err(Err::Error((d, ErrorKind::Digit)))); |
| 906 | assert_eq!(hex_digit1::<_, (_, ErrorKind)>(a), Ok((empty, a))); |
| 907 | assert_eq!(hex_digit1::<_, (_, ErrorKind)>(b), Ok((empty, b))); |
| 908 | assert_eq!(hex_digit1::<_, (_, ErrorKind)>(c), Ok((empty, c))); |
| 909 | assert_eq!(hex_digit1::<_, (_, ErrorKind)>(d), Ok(("zé12" , &"a" [..]))); |
| 910 | assert_eq!(hex_digit1(e), Err(Err::Error((e, ErrorKind::HexDigit)))); |
| 911 | assert_eq!(oct_digit1(a), Err(Err::Error((a, ErrorKind::OctDigit)))); |
| 912 | assert_eq!(oct_digit1::<_, (_, ErrorKind)>(b), Ok((empty, b))); |
| 913 | assert_eq!(oct_digit1(c), Err(Err::Error((c, ErrorKind::OctDigit)))); |
| 914 | assert_eq!(oct_digit1(d), Err(Err::Error((d, ErrorKind::OctDigit)))); |
| 915 | assert_eq!(alphanumeric1::<_, (_, ErrorKind)>(a), Ok((empty, a))); |
| 916 | //assert_eq!(fix_error!(b,(), alphanumeric), Ok((empty, b))); |
| 917 | assert_eq!(alphanumeric1::<_, (_, ErrorKind)>(c), Ok((empty, c))); |
| 918 | assert_eq!(alphanumeric1::<_, (_, ErrorKind)>(d), Ok(("é12" , "az" ))); |
| 919 | assert_eq!(space1::<_, (_, ErrorKind)>(e), Ok((empty, e))); |
| 920 | } |
| 921 | |
| 922 | use crate::traits::Offset; |
| 923 | #[test ] |
| 924 | fn offset() { |
| 925 | let a = &b"abcd;" [..]; |
| 926 | let b = &b"1234;" [..]; |
| 927 | let c = &b"a123;" [..]; |
| 928 | let d = &b" \t;" [..]; |
| 929 | let e = &b" \t\r\n;" [..]; |
| 930 | let f = &b"123abcDEF;" [..]; |
| 931 | |
| 932 | match alpha1::<_, (_, ErrorKind)>(a) { |
| 933 | Ok((i, _)) => { |
| 934 | assert_eq!(a.offset(i) + i.len(), a.len()); |
| 935 | } |
| 936 | _ => panic!("wrong return type in offset test for alpha" ), |
| 937 | } |
| 938 | match digit1::<_, (_, ErrorKind)>(b) { |
| 939 | Ok((i, _)) => { |
| 940 | assert_eq!(b.offset(i) + i.len(), b.len()); |
| 941 | } |
| 942 | _ => panic!("wrong return type in offset test for digit" ), |
| 943 | } |
| 944 | match alphanumeric1::<_, (_, ErrorKind)>(c) { |
| 945 | Ok((i, _)) => { |
| 946 | assert_eq!(c.offset(i) + i.len(), c.len()); |
| 947 | } |
| 948 | _ => panic!("wrong return type in offset test for alphanumeric" ), |
| 949 | } |
| 950 | match space1::<_, (_, ErrorKind)>(d) { |
| 951 | Ok((i, _)) => { |
| 952 | assert_eq!(d.offset(i) + i.len(), d.len()); |
| 953 | } |
| 954 | _ => panic!("wrong return type in offset test for space" ), |
| 955 | } |
| 956 | match multispace1::<_, (_, ErrorKind)>(e) { |
| 957 | Ok((i, _)) => { |
| 958 | assert_eq!(e.offset(i) + i.len(), e.len()); |
| 959 | } |
| 960 | _ => panic!("wrong return type in offset test for multispace" ), |
| 961 | } |
| 962 | match hex_digit1::<_, (_, ErrorKind)>(f) { |
| 963 | Ok((i, _)) => { |
| 964 | assert_eq!(f.offset(i) + i.len(), f.len()); |
| 965 | } |
| 966 | _ => panic!("wrong return type in offset test for hex_digit" ), |
| 967 | } |
| 968 | match oct_digit1::<_, (_, ErrorKind)>(f) { |
| 969 | Ok((i, _)) => { |
| 970 | assert_eq!(f.offset(i) + i.len(), f.len()); |
| 971 | } |
| 972 | _ => panic!("wrong return type in offset test for oct_digit" ), |
| 973 | } |
| 974 | } |
| 975 | |
| 976 | #[test ] |
| 977 | fn is_not_line_ending_bytes() { |
| 978 | let a: &[u8] = b"ab12cd \nefgh" ; |
| 979 | assert_eq!( |
| 980 | not_line_ending::<_, (_, ErrorKind)>(a), |
| 981 | Ok((&b" \nefgh" [..], &b"ab12cd" [..])) |
| 982 | ); |
| 983 | |
| 984 | let b: &[u8] = b"ab12cd \nefgh \nijkl" ; |
| 985 | assert_eq!( |
| 986 | not_line_ending::<_, (_, ErrorKind)>(b), |
| 987 | Ok((&b" \nefgh \nijkl" [..], &b"ab12cd" [..])) |
| 988 | ); |
| 989 | |
| 990 | let c: &[u8] = b"ab12cd \r\nefgh \nijkl" ; |
| 991 | assert_eq!( |
| 992 | not_line_ending::<_, (_, ErrorKind)>(c), |
| 993 | Ok((&b" \r\nefgh \nijkl" [..], &b"ab12cd" [..])) |
| 994 | ); |
| 995 | |
| 996 | let d: &[u8] = b"ab12cd" ; |
| 997 | assert_eq!( |
| 998 | not_line_ending::<_, (_, ErrorKind)>(d), |
| 999 | Ok((&[][..], &d[..])) |
| 1000 | ); |
| 1001 | } |
| 1002 | |
| 1003 | #[test ] |
| 1004 | fn is_not_line_ending_str() { |
| 1005 | /* |
| 1006 | let a: &str = "ab12cd\nefgh"; |
| 1007 | assert_eq!(not_line_ending(a), Ok((&"\nefgh"[..], &"ab12cd"[..]))); |
| 1008 | |
| 1009 | let b: &str = "ab12cd\nefgh\nijkl"; |
| 1010 | assert_eq!(not_line_ending(b), Ok((&"\nefgh\nijkl"[..], &"ab12cd"[..]))); |
| 1011 | |
| 1012 | let c: &str = "ab12cd\r\nefgh\nijkl"; |
| 1013 | assert_eq!(not_line_ending(c), Ok((&"\r\nefgh\nijkl"[..], &"ab12cd"[..]))); |
| 1014 | |
| 1015 | let d = "βèƒôřè\nÂßÇáƒƭèř"; |
| 1016 | assert_eq!(not_line_ending(d), Ok((&"\nÂßÇáƒƭèř"[..], &"βèƒôřè"[..]))); |
| 1017 | |
| 1018 | let e = "βèƒôřè\r\nÂßÇáƒƭèř"; |
| 1019 | assert_eq!(not_line_ending(e), Ok((&"\r\nÂßÇáƒƭèř"[..], &"βèƒôřè"[..]))); |
| 1020 | */ |
| 1021 | |
| 1022 | let f = "βèƒôřè \rÂßÇáƒƭèř" ; |
| 1023 | assert_eq!(not_line_ending(f), Err(Err::Error((f, ErrorKind::Tag)))); |
| 1024 | |
| 1025 | let g2: &str = "ab12cd" ; |
| 1026 | assert_eq!(not_line_ending::<_, (_, ErrorKind)>(g2), Ok(("" , g2))); |
| 1027 | } |
| 1028 | |
| 1029 | #[test ] |
| 1030 | fn hex_digit_test() { |
| 1031 | let i = &b"0123456789abcdefABCDEF;" [..]; |
| 1032 | assert_parse!(hex_digit1(i), Ok((&b";" [..], &i[..i.len() - 1]))); |
| 1033 | |
| 1034 | let i = &b"g" [..]; |
| 1035 | assert_parse!( |
| 1036 | hex_digit1(i), |
| 1037 | Err(Err::Error(error_position!(i, ErrorKind::HexDigit))) |
| 1038 | ); |
| 1039 | |
| 1040 | let i = &b"G" [..]; |
| 1041 | assert_parse!( |
| 1042 | hex_digit1(i), |
| 1043 | Err(Err::Error(error_position!(i, ErrorKind::HexDigit))) |
| 1044 | ); |
| 1045 | |
| 1046 | assert!(crate::character::is_hex_digit(b'0' )); |
| 1047 | assert!(crate::character::is_hex_digit(b'9' )); |
| 1048 | assert!(crate::character::is_hex_digit(b'a' )); |
| 1049 | assert!(crate::character::is_hex_digit(b'f' )); |
| 1050 | assert!(crate::character::is_hex_digit(b'A' )); |
| 1051 | assert!(crate::character::is_hex_digit(b'F' )); |
| 1052 | assert!(!crate::character::is_hex_digit(b'g' )); |
| 1053 | assert!(!crate::character::is_hex_digit(b'G' )); |
| 1054 | assert!(!crate::character::is_hex_digit(b'/' )); |
| 1055 | assert!(!crate::character::is_hex_digit(b':' )); |
| 1056 | assert!(!crate::character::is_hex_digit(b'@' )); |
| 1057 | assert!(!crate::character::is_hex_digit(b' \x60' )); |
| 1058 | } |
| 1059 | |
| 1060 | #[test ] |
| 1061 | fn oct_digit_test() { |
| 1062 | let i = &b"01234567;" [..]; |
| 1063 | assert_parse!(oct_digit1(i), Ok((&b";" [..], &i[..i.len() - 1]))); |
| 1064 | |
| 1065 | let i = &b"8" [..]; |
| 1066 | assert_parse!( |
| 1067 | oct_digit1(i), |
| 1068 | Err(Err::Error(error_position!(i, ErrorKind::OctDigit))) |
| 1069 | ); |
| 1070 | |
| 1071 | assert!(crate::character::is_oct_digit(b'0' )); |
| 1072 | assert!(crate::character::is_oct_digit(b'7' )); |
| 1073 | assert!(!crate::character::is_oct_digit(b'8' )); |
| 1074 | assert!(!crate::character::is_oct_digit(b'9' )); |
| 1075 | assert!(!crate::character::is_oct_digit(b'a' )); |
| 1076 | assert!(!crate::character::is_oct_digit(b'A' )); |
| 1077 | assert!(!crate::character::is_oct_digit(b'/' )); |
| 1078 | assert!(!crate::character::is_oct_digit(b':' )); |
| 1079 | assert!(!crate::character::is_oct_digit(b'@' )); |
| 1080 | assert!(!crate::character::is_oct_digit(b' \x60' )); |
| 1081 | } |
| 1082 | |
| 1083 | #[test ] |
| 1084 | fn full_line_windows() { |
| 1085 | use crate::sequence::pair; |
| 1086 | fn take_full_line(i: &[u8]) -> IResult<&[u8], (&[u8], &[u8])> { |
| 1087 | pair(not_line_ending, line_ending)(i) |
| 1088 | } |
| 1089 | let input = b"abc \r\n" ; |
| 1090 | let output = take_full_line(input); |
| 1091 | assert_eq!(output, Ok((&b"" [..], (&b"abc" [..], &b" \r\n" [..])))); |
| 1092 | } |
| 1093 | |
| 1094 | #[test ] |
| 1095 | fn full_line_unix() { |
| 1096 | use crate::sequence::pair; |
| 1097 | fn take_full_line(i: &[u8]) -> IResult<&[u8], (&[u8], &[u8])> { |
| 1098 | pair(not_line_ending, line_ending)(i) |
| 1099 | } |
| 1100 | let input = b"abc \n" ; |
| 1101 | let output = take_full_line(input); |
| 1102 | assert_eq!(output, Ok((&b"" [..], (&b"abc" [..], &b" \n" [..])))); |
| 1103 | } |
| 1104 | |
| 1105 | #[test ] |
| 1106 | fn check_windows_lineending() { |
| 1107 | let input = b" \r\n" ; |
| 1108 | let output = line_ending(&input[..]); |
| 1109 | assert_parse!(output, Ok((&b"" [..], &b" \r\n" [..]))); |
| 1110 | } |
| 1111 | |
| 1112 | #[test ] |
| 1113 | fn check_unix_lineending() { |
| 1114 | let input = b" \n" ; |
| 1115 | let output = line_ending(&input[..]); |
| 1116 | assert_parse!(output, Ok((&b"" [..], &b" \n" [..]))); |
| 1117 | } |
| 1118 | |
| 1119 | #[test ] |
| 1120 | fn cr_lf() { |
| 1121 | assert_parse!(crlf(&b" \r\na" [..]), Ok((&b"a" [..], &b" \r\n" [..]))); |
| 1122 | assert_parse!( |
| 1123 | crlf(&b" \r" [..]), |
| 1124 | Err(Err::Error(error_position!(&b" \r" [..], ErrorKind::CrLf))) |
| 1125 | ); |
| 1126 | assert_parse!( |
| 1127 | crlf(&b" \ra" [..]), |
| 1128 | Err(Err::Error(error_position!(&b" \ra" [..], ErrorKind::CrLf))) |
| 1129 | ); |
| 1130 | |
| 1131 | assert_parse!(crlf(" \r\na" ), Ok(("a" , " \r\n" ))); |
| 1132 | assert_parse!( |
| 1133 | crlf(" \r" ), |
| 1134 | Err(Err::Error(error_position!(&" \r" [..], ErrorKind::CrLf))) |
| 1135 | ); |
| 1136 | assert_parse!( |
| 1137 | crlf(" \ra" ), |
| 1138 | Err(Err::Error(error_position!(" \ra" , ErrorKind::CrLf))) |
| 1139 | ); |
| 1140 | } |
| 1141 | |
| 1142 | #[test ] |
| 1143 | fn end_of_line() { |
| 1144 | assert_parse!(line_ending(&b" \na" [..]), Ok((&b"a" [..], &b" \n" [..]))); |
| 1145 | assert_parse!(line_ending(&b" \r\na" [..]), Ok((&b"a" [..], &b" \r\n" [..]))); |
| 1146 | assert_parse!( |
| 1147 | line_ending(&b" \r" [..]), |
| 1148 | Err(Err::Error(error_position!(&b" \r" [..], ErrorKind::CrLf))) |
| 1149 | ); |
| 1150 | assert_parse!( |
| 1151 | line_ending(&b" \ra" [..]), |
| 1152 | Err(Err::Error(error_position!(&b" \ra" [..], ErrorKind::CrLf))) |
| 1153 | ); |
| 1154 | |
| 1155 | assert_parse!(line_ending(" \na" ), Ok(("a" , " \n" ))); |
| 1156 | assert_parse!(line_ending(" \r\na" ), Ok(("a" , " \r\n" ))); |
| 1157 | assert_parse!( |
| 1158 | line_ending(" \r" ), |
| 1159 | Err(Err::Error(error_position!(&" \r" [..], ErrorKind::CrLf))) |
| 1160 | ); |
| 1161 | assert_parse!( |
| 1162 | line_ending(" \ra" ), |
| 1163 | Err(Err::Error(error_position!(" \ra" , ErrorKind::CrLf))) |
| 1164 | ); |
| 1165 | } |
| 1166 | |
| 1167 | fn digit_to_i16(input: &str) -> IResult<&str, i16> { |
| 1168 | let i = input; |
| 1169 | let (i, opt_sign) = opt(alt((char('+' ), char('-' ))))(i)?; |
| 1170 | let sign = match opt_sign { |
| 1171 | Some('+' ) => true, |
| 1172 | Some('-' ) => false, |
| 1173 | _ => true, |
| 1174 | }; |
| 1175 | |
| 1176 | let (i, s) = match digit1::<_, crate::error::Error<_>>(i) { |
| 1177 | Ok((i, s)) => (i, s), |
| 1178 | Err(_) => { |
| 1179 | return Err(Err::Error(crate::error::Error::from_error_kind( |
| 1180 | input, |
| 1181 | ErrorKind::Digit, |
| 1182 | ))) |
| 1183 | } |
| 1184 | }; |
| 1185 | |
| 1186 | match s.parse_to() { |
| 1187 | Some(n) => { |
| 1188 | if sign { |
| 1189 | Ok((i, n)) |
| 1190 | } else { |
| 1191 | Ok((i, -n)) |
| 1192 | } |
| 1193 | } |
| 1194 | None => Err(Err::Error(crate::error::Error::from_error_kind( |
| 1195 | i, |
| 1196 | ErrorKind::Digit, |
| 1197 | ))), |
| 1198 | } |
| 1199 | } |
| 1200 | |
| 1201 | fn digit_to_u32(i: &str) -> IResult<&str, u32> { |
| 1202 | let (i, s) = digit1(i)?; |
| 1203 | match s.parse_to() { |
| 1204 | Some(n) => Ok((i, n)), |
| 1205 | None => Err(Err::Error(crate::error::Error::from_error_kind( |
| 1206 | i, |
| 1207 | ErrorKind::Digit, |
| 1208 | ))), |
| 1209 | } |
| 1210 | } |
| 1211 | |
| 1212 | proptest! { |
| 1213 | #[test] |
| 1214 | fn ints(s in " \\PC*" ) { |
| 1215 | let res1 = digit_to_i16(&s); |
| 1216 | let res2 = i16(s.as_str()); |
| 1217 | assert_eq!(res1, res2); |
| 1218 | } |
| 1219 | |
| 1220 | #[test] |
| 1221 | fn uints(s in " \\PC*" ) { |
| 1222 | let res1 = digit_to_u32(&s); |
| 1223 | let res2 = u32(s.as_str()); |
| 1224 | assert_eq!(res1, res2); |
| 1225 | } |
| 1226 | } |
| 1227 | } |
| 1228 | |