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
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
//! # nom, eating data byte by byte
//!
//! nom is a parser combinator library with a focus on safe parsing,
//! streaming patterns, and as much as possible zero copy.
//!
//! ## Example
//!
//! ```rust
//! extern crate nom;
//!
//! use nom::{
//!   IResult,
//!   bytes::complete::{tag, take_while_m_n},
//!   combinator::map_res,
//!   sequence::tuple};
//!
//! #[derive(Debug,PartialEq)]
//! pub struct Color {
//!   pub red:     u8,
//!   pub green:   u8,
//!   pub blue:    u8,
//! }
//!
//! fn from_hex(input: &str) -> Result<u8, std::num::ParseIntError> {
//!   u8::from_str_radix(input, 16)
//! }
//!
//! fn is_hex_digit(c: char) -> bool {
//!   c.is_digit(16)
//! }
//!
//! fn hex_primary(input: &str) -> IResult<&str, u8> {
//!   map_res(
//!     take_while_m_n(2, 2, is_hex_digit),
//!     from_hex
//!   )(input)
//! }
//!
//! fn hex_color(input: &str) -> IResult<&str, Color> {
//!   let (input, _) = tag("#")(input)?;
//!   let (input, (red, green, blue)) = tuple((hex_primary, hex_primary, hex_primary))(input)?;
//!
//!   Ok((input, Color { red, green, blue }))
//! }
//!
//! fn main() {
//!   assert_eq!(hex_color("#2F14DF"), Ok(("", Color {
//!     red: 47,
//!     green: 20,
//!     blue: 223,
//!   })));
//! }
//! ```
//!
//! The code is available on [Github](https://github.com/Geal/nom)
//!
//! There are a few [guides](https://github.com/Geal/nom/tree/master/doc) with more details
//! about [the design of nom macros](https://github.com/Geal/nom/blob/master/doc/how_nom_macros_work.md),
//! [how to write parsers](https://github.com/Geal/nom/blob/master/doc/making_a_new_parser_from_scratch.md),
//! or the [error management system](https://github.com/Geal/nom/blob/master/doc/error_management.md).
//!
//! **Looking for a specific combinator? Read the
//! ["choose a combinator" guide](https://github.com/Geal/nom/blob/master/doc/choosing_a_combinator.md)**
//!
//! If you are upgrading to nom 5.0, please read the
//! [migration document](https://github.com/Geal/nom/blob/master/doc/upgrading_to_nom_5.md).
//!
//! See also the [FAQ](https://github.com/Geal/nom/blob/master/doc/FAQ.md).
//!
//! ## Parser combinators
//!
//! Parser combinators are an approach to parsers that is very different from
//! software like [lex](https://en.wikipedia.org/wiki/Lex_(software)) and
//! [yacc](https://en.wikipedia.org/wiki/Yacc). Instead of writing the grammar
//! in a separate syntax and generating the corresponding code, you use very small
//! functions with a very specific purpose, like "take 5 bytes", or "recognize the
//! word 'HTTP'", and assemble then in meaningful patterns like "recognize
//! 'HTTP', then a space, then a version".
//! The resulting code is small, and looks like the grammar you would have
//! written with other parser approaches.
//!
//! This gives us a few advantages:
//!
//! - the parsers are small and easy to write
//! - the parsers components are easy to reuse (if they're general enough, please add them to nom!)
//! - the parsers components are easy to test separately (unit tests and property-based tests)
//! - the parser combination code looks close to the grammar you would have written
//! - you can build partial parsers, specific to the data you need at the moment, and ignore the rest
//!
//! Here is an example of one such parser, to recognize text between parentheses:
//!
//! ```rust
//! use nom::{
//!   IResult,
//!   sequence::delimited,
//!   // see the "streaming/complete" paragraph lower for an explanation of these submodules
//!   character::complete::char,
//!   bytes::complete::is_not
//! };
//!
//! fn parens(input: &str) -> IResult<&str, &str> {
//!   delimited(char('('), is_not(")"), char(')'))(input)
//! }
//! ```
//!
//! It defines a function named `parens` which will recognize a sequence of the
//! character `(`, the longest byte array not containing `)`, then the character
//! `)`, and will return the byte array in the middle.
//!
//! Here is another parser, written without using nom's combinators this time:
//!
//! ```rust
//! #[macro_use]
//! extern crate nom;
//!
//! use nom::{IResult, Err, Needed};
//!
//! # fn main() {
//! fn take4(i: &[u8]) -> IResult<&[u8], &[u8]>{
//!   if i.len() < 4 {
//!     Err(Err::Incomplete(Needed::Size(4)))
//!   } else {
//!     Ok((&i[4..], &i[0..4]))
//!   }
//! }
//! # }
//! ```
//!
//! This function takes a byte array as input, and tries to consume 4 bytes.
//! Writing all the parsers manually, like this, is dangerous, despite Rust's
//! safety features. There are still a lot of mistakes one can make. That's why
//! nom provides a list of function and macros to help in developing parsers.
//!
//! With functions, you would write it like this:
//!
//! ```rust
//! use nom::{IResult, bytes::streaming::take};
//! fn take4(input: &str) -> IResult<&str, &str> {
//!   take(4u8)(input)
//! }
//! ```
//!
//! With macros, you would write it like this:
//!
//! ```rust
//! #[macro_use]
//! extern crate nom;
//!
//! # fn main() {
//! named!(take4, take!(4));
//! # }
//! ```
//!
//! nom has used macros for combinators from versions 1 to 4, and from version
//! 5, it proposes new combinators as functions, but still allows the macros style
//! (macros have been rewritten to use the functions under the hood).
//! For new parsers, we recommend using the functions instead of macros, since
//! rustc messages will be much easier to understand.
//!
//!
//! A parser in nom is a function which, for an input type `I`, an output type `O`
//! and an optional error type `E`, will have the following signature:
//!
//! ```rust,ignore
//! fn parser(input: I) -> IResult<I, O, E>;
//! ```
//!
//! Or like this, if you don't want to specify a custom error type (it will be `u32` by default):
//!
//! ```rust,ignore
//! fn parser(input: I) -> IResult<I, O>;
//! ```
//!
//! `IResult` is an alias for the `Result` type:
//!
//! ```rust
//! use nom::{Needed, error::ErrorKind};
//!
//! type IResult<I, O, E = (I,ErrorKind)> = Result<(I, O), Err<E>>;
//!
//! enum Err<E> {
//!   Incomplete(Needed),
//!   Error(E),
//!   Failure(E),
//! }
//! ```
//!
//! It can have the following values:
//!
//! - a correct result `Ok((I,O))` with the first element being the remaining of the input (not parsed yet), and the second the output value;
//! - an error `Err(Err::Error(c))` with `c` an error that can be built from the input position and a parser specific error
//! - an error `Err(Err::Incomplete(Needed))` indicating that more input is necessary. `Needed` can indicate how much data is needed
//! - an error `Err(Err::Failure(c))`. It works like the `Error` case, except it indicates an unrecoverable error: we cannot backtrack and test another parser
//!
//! Please refer to the ["choose a combinator" guide](https://github.com/Geal/nom/blob/master/doc/choosing_a_combinator.md) for an exhaustive list of parsers.
//! See also the rest of the documentation [here](https://github.com/Geal/nom/blob/master/doc).
//! .
//!
//! ## Making new parsers with function combinators
//!
//! nom is based on functions that generate parsers, with a signature like
//! this: `(arguments) -> impl Fn(Input) -> IResult<Input, Output, Error>`.
//! The arguments of a combinator can be direct values (like `take` which uses
//! a number of bytes or character as argument) or even other parsers (like
//! `delimited` which takes as argument 3 parsers, and returns the result of
//! the second one if all are successful).
//!
//! Here are some examples:
//!
//! ```rust
//! use nom::IResult;
//! use nom::bytes::complete::{tag, take};
//! fn abcd_parser(i: &str) -> IResult<&str, &str> {
//!   tag("abcd")(i) // will consume bytes if the input begins with "abcd"
//! }
//!
//! fn take_10(i: &[u8]) -> IResult<&[u8], &[u8]> {
//!   take(10u8)(i) // will consume and return 10 bytes of input
//! }
//! ```
//!
//! ## Combining parsers
//!
//! There are higher level patterns, like the **`alt`** combinator, which
//! provides a choice between multiple parsers. If one branch fails, it tries
//! the next, and returns the result of the first parser that succeeds:
//!
//! ```rust
//! use nom::IResult;
//! use nom::branch::alt;
//! use nom::bytes::complete::tag;
//!
//! let alt_tags = alt((tag("abcd"), tag("efgh")));
//!
//! assert_eq!(alt_tags(&b"abcdxxx"[..]), Ok((&b"xxx"[..], &b"abcd"[..])));
//! assert_eq!(alt_tags(&b"efghxxx"[..]), Ok((&b"xxx"[..], &b"efgh"[..])));
//! assert_eq!(alt_tags(&b"ijklxxx"[..]), Err(nom::Err::Error((&b"ijklxxx"[..], nom::error::ErrorKind::Tag))));
//! ```
//!
//! The **`opt`** combinator makes a parser optional. If the child parser returns
//! an error, **`opt`** will still succeed and return None:
//!
//! ```rust
//! use nom::{IResult, combinator::opt, bytes::complete::tag};
//! fn abcd_opt(i: &[u8]) -> IResult<&[u8], Option<&[u8]>> {
//!   opt(tag("abcd"))(i)
//! }
//!
//! assert_eq!(abcd_opt(&b"abcdxxx"[..]), Ok((&b"xxx"[..], Some(&b"abcd"[..]))));
//! assert_eq!(abcd_opt(&b"efghxxx"[..]), Ok((&b"efghxxx"[..], None)));
//! ```
//!
//! **`many0`** applies a parser 0 or more times, and returns a vector of the aggregated results:
//!
//! ```rust
//! # #[macro_use] extern crate nom;
//! # #[cfg(feature = "alloc")]
//! # fn main() {
//! use nom::{IResult, multi::many0, bytes::complete::tag};
//! use std::str;
//!
//! fn multi(i: &str) -> IResult<&str, Vec<&str>> {
//!   many0(tag("abcd"))(i)
//! }
//!
//! let a = "abcdef";
//! let b = "abcdabcdef";
//! let c = "azerty";
//! assert_eq!(multi(a), Ok(("ef",     vec!["abcd"])));
//! assert_eq!(multi(b), Ok(("ef",     vec!["abcd", "abcd"])));
//! assert_eq!(multi(c), Ok(("azerty", Vec::new())));
//! # }
//! # #[cfg(not(feature = "alloc"))]
//! # fn main() {}
//! ```
//!
//! Here are some basic combining macros available:
//!
//! - **`opt`**: will make the parser optional (if it returns the `O` type, the new parser returns `Option<O>`)
//! - **`many0`**: will apply the parser 0 or more times (if it returns the `O` type, the new parser returns `Vec<O>`)
//! - **`many1`**: will apply the parser 1 or more times
//!
//! There are more complex (and more useful) parsers like `tuple!`, which is
//! used to apply a series of parsers then assemble their results.
//!
//! Example with `tuple`:
//!
//! ```rust
//! # #[macro_use] extern crate nom;
//! # fn main() {
//! use nom::{error::ErrorKind, Needed,
//! number::streaming::be_u16,
//! bytes::streaming::{tag, take},
//! sequence::tuple};
//!
//! let tpl = tuple((be_u16, take(3u8), tag("fg")));
//!
//! assert_eq!(
//!   tpl(&b"abcdefgh"[..]),
//!   Ok((
//!     &b"h"[..],
//!     (0x6162u16, &b"cde"[..], &b"fg"[..])
//!   ))
//! );
//! assert_eq!(tpl(&b"abcde"[..]), Err(nom::Err::Incomplete(Needed::Size(2))));
//! let input = &b"abcdejk"[..];
//! assert_eq!(tpl(input), Err(nom::Err::Error((&input[5..], ErrorKind::Tag))));
//! # }
//! ```
//!
//! But you can also use a sequence of combinators written in imperative style,
//! thanks to the `?` operator:
//!
//! ```rust
//! # #[macro_use] extern crate nom;
//! # fn main() {
//! use nom::{IResult, bytes::complete::tag};
//!
//! #[derive(Debug, PartialEq)]
//! struct A {
//!   a: u8,
//!   b: u8
//! }
//!
//! fn ret_int1(i:&[u8]) -> IResult<&[u8], u8> { Ok((i,1)) }
//! fn ret_int2(i:&[u8]) -> IResult<&[u8], u8> { Ok((i,2)) }
//!
//! fn f(i: &[u8]) -> IResult<&[u8], A> {
//!   // if successful, the parser returns `Ok((remaining_input, output_value))` that we can destructure
//!   let (i, _) = tag("abcd")(i)?;
//!   let (i, a) = ret_int1(i)?;
//!   let (i, _) = tag("efgh")(i)?;
//!   let (i, b) = ret_int2(i)?;
//!
//!   Ok((i, A { a, b }))
//! }
//!
//! let r = f(b"abcdefghX");
//! assert_eq!(r, Ok((&b"X"[..], A{a: 1, b: 2})));
//! # }
//! ```
//!
//! ## Streaming / Complete
//!
//! Some of nom's modules have `streaming` or `complete` submodules. They hold
//! different variants of the same combinators.
//!
//! A streaming parser assumes that we might not have all of the input data.
//! This can happen with some network protocol or large file parsers, where the
//! input buffer can be full and need to be resized or refilled.
//!
//! A complete parser assumes that we already have all of the input data.
//! This will be the common case with small files that can be read entirely to
//! memory.
//!
//! Here is how it works in practice:
//!
//! ```rust
//! use nom::{IResult, Err, Needed, error::ErrorKind, bytes, character};
//!
//! fn take_streaming(i: &[u8]) -> IResult<&[u8], &[u8]> {
//!   bytes::streaming::take(4u8)(i)
//! }
//!
//! fn take_complete(i: &[u8]) -> IResult<&[u8], &[u8]> {
//!   bytes::complete::take(4u8)(i)
//! }
//!
//! // both parsers will take 4 bytes as expected
//! assert_eq!(take_streaming(&b"abcde"[..]), Ok((&b"e"[..], &b"abcd"[..])));
//! assert_eq!(take_complete(&b"abcde"[..]), Ok((&b"e"[..], &b"abcd"[..])));
//!
//! // if the input is smaller than 4 bytes, the streaming parser
//! // will return `Incomplete` to indicate that we need more data
//! assert_eq!(take_streaming(&b"abc"[..]), Err(Err::Incomplete(Needed::Size(4))));
//!
//! // but the complete parser will return an error
//! assert_eq!(take_complete(&b"abc"[..]), Err(Err::Error((&b"abc"[..], ErrorKind::Eof))));
//!
//! // the alpha0 function recognizes 0 or more alphabetic characters
//! fn alpha0_streaming(i: &str) -> IResult<&str, &str> {
//!   character::streaming::alpha0(i)
//! }
//!
//! fn alpha0_complete(i: &str) -> IResult<&str, &str> {
//!   character::complete::alpha0(i)
//! }
//!
//! // if there's a clear limit to the recognized characters, both parsers work the same way
//! assert_eq!(alpha0_streaming("abcd;"), Ok((";", "abcd")));
//! assert_eq!(alpha0_complete("abcd;"), Ok((";", "abcd")));
//!
//! // but when there's no limit, the streaming version returns `Incomplete`, because it cannot
//! // know if more input data should be recognized. The whole input could be "abcd;", or
//! // "abcde;"
//! assert_eq!(alpha0_streaming("abcd"), Err(Err::Incomplete(Needed::Size(1))));
//!
//! // while the complete version knows that all of the data is there
//! assert_eq!(alpha0_complete("abcd"), Ok(("", "abcd")));
//! ```
//! **Going further:** read the [guides](https://github.com/Geal/nom/tree/master/doc)!
#![cfg_attr(all(not(feature = "std"), feature = "alloc"), feature(alloc))]
#![cfg_attr(not(feature = "std"), no_std)]
#![cfg_attr(feature = "cargo-clippy", allow(doc_markdown))]
#![cfg_attr(nightly, feature(test))]
#![deny(missing_docs)]
#![warn(missing_doc_code_examples)]

#[cfg(all(not(feature = "std"), feature = "alloc"))]
#[macro_use]
extern crate alloc;
#[cfg(feature = "regexp_macros")]
#[macro_use]
extern crate lazy_static;
extern crate memchr;
#[cfg(feature = "regexp")]
pub extern crate regex;
#[cfg(feature = "lexical")]
extern crate lexical_core;
#[cfg(nightly)]
extern crate test;
#[cfg(test)]
extern crate doc_comment;

//FIXME: reactivate doctest once https://github.com/rust-lang/rust/issues/62210 is done
//#[cfg(doctest)]
//doc_comment::doctest!("../README.md");

/// Lib module to re-export everything needed from `std` or `core`/`alloc`. This is how `serde` does
/// it, albeit there it is not public.
pub mod lib {
  /// `std` facade allowing `std`/`core` to be interchangeable. Reexports `alloc` crate optionally,
  /// as well as `core` or `std`
  #[cfg(not(feature = "std"))]
  /// internal std exports for no_std compatibility
  pub mod std {
    #[cfg(feature = "alloc")]
    #[cfg_attr(feature = "alloc", macro_use)]
    pub use alloc::{boxed, string, vec};

    pub use core::{cmp, convert, fmt, iter, mem, ops, option, result, slice, str, borrow};

    /// internal reproduction of std prelude
    pub mod prelude {
      pub use core::prelude as v1;
    }
  }

  #[cfg(feature = "std")]
  /// internal std exports for no_std compatibility
  pub mod std {
    pub use std::{alloc, boxed, cmp, collections, convert, fmt, hash, iter, mem, ops, option, result, slice, str, string, vec, borrow};

    /// internal reproduction of std prelude
    pub mod prelude {
      pub use std::prelude as v1;
    }
  }

  #[cfg(feature = "regexp")]
  pub use regex;
}

pub use self::traits::*;
pub use self::util::*;
pub use self::internal::*;
pub use self::methods::*;
pub use self::bits::*;
pub use self::whitespace::*;

#[cfg(feature = "regexp")]
pub use self::regexp::*;
pub use self::str::*;

#[macro_use]
mod util;

#[macro_use]
pub mod error;

#[macro_use]
mod internal;
mod traits;
#[macro_use]
pub mod combinator;
#[macro_use]
pub mod branch;
#[macro_use]
pub mod sequence;
#[macro_use]
pub mod multi;
#[macro_use]
pub mod methods;

#[macro_use]
pub mod bytes;
#[macro_use]
pub mod bits;

#[macro_use]
pub mod character;

#[macro_use]
pub mod whitespace;

#[cfg(feature = "regexp")]
#[macro_use]
mod regexp;

mod str;

#[macro_use]
pub mod number;