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
use logos::Logos;
use crate::lexer::LexIt;
use crate::error::ParseError;
use crate::step::Step;
use crate::step::Step::{Error, Fail, Success};
/// The base structure of the parser combinator that providers a set of methods to construct a gramma
///
/// To construct the parser it takes a token set from `Logos` typically as an Enum
///
/// ```
/// use logos::Logos;
/// use crate::parsit::parser::Parsit;
/// #[derive(Logos,PartialEq)]
/// pub enum TFQ {
/// #[token("true")]
/// True,
/// #[token("false")]
/// False,
///
/// #[token("?")]
/// Question,
/// }
/// let p:Parsit<TFQ> = Parsit::new("true?").unwrap();
/// ```
/// Note: The parser works only with string input
///
pub struct Parsit<'a, T> where T: Logos<'a, Source=str>, {
lexer: LexIt<'a, T>,
}
impl<'a, Token> Parsit<'a, Token>
where Token: Logos<'a, Source=str> + PartialEq,
{
/// Creates a parser with aset of tokens from the source
/// Raises an error if lexer raises an error
pub fn new(src: &'a str) -> Result<Self, ParseError<'a>>
where Token::Extras: Default
{
Ok(Parsit {
lexer: LexIt::new(src)?,
})
}
/// obtain a token from the parsing output according to the position number
///
/// # Arguments
/// * `pos` position number
///
/// # Examples
/// typically used in the token! macros:
/// ```ignore
/// let p:Parsit<_> = Parsit::new(...)?;
/// token!(p.token(0) => ...)
/// ```
pub fn token(&self, pos: usize) -> Result<(&Token, usize), ParseError<'a>> {
self.lexer.token(pos)
}
/// executes some rule one or more times shifting the cursor farther.
/// The operator expects at least one occurance of the given function
/// # Arguments
/// * `pos` - starting postion to parse
/// * `then` - parsing function
///
/// # Examples
/// ```
/// use logos::Logos;
/// use crate::parsit::parser::Parsit;
/// use crate::parsit::token;
/// use crate::parsit::step::Step;
/// #[derive(Logos,PartialEq)]
/// pub enum TFQ {
/// #[token("true")]
/// True,
/// #[token("false")]
/// False,
///
/// #[token("?")]
/// Question,
/// }
/// let parser:Parsit<TFQ> = Parsit::new("true?false").unwrap();
/// let parser_fn = |p|{ token!( parser.token(p) =>
/// TFQ::True => Some(true),
/// TFQ::False => Some(false),
/// TFQ::Question => None
/// )};
///
/// if let Some(res) = parser.one_or_more(0, parser_fn).ok() {
/// assert_eq!(res, vec![Some(true), None, Some(false)]);
/// } else { assert!(false) };
/// ```
pub fn one_or_more<T, Then>(&self, pos: usize, then: Then) -> Step<'a, Vec<T>>
where
Then: FnOnce(usize) -> Step<'a, T> + Copy,
{
match self.zero_or_more(pos, then) {
Success(vals, _) if vals.is_empty() => Fail(pos),
other => other,
}
}
/// executes some rule one or more times shifting the cursor farther.
/// The operator expects zero or more occurances of the given function
/// # Arguments
/// * `pos` - starting postion to parse
/// * `then` - parsing function
///
/// # Examples
/// ```
/// use logos::Logos;
/// use crate::parsit::parser::Parsit;
/// use crate::parsit::token;
/// use crate::parsit::step::Step;
/// #[derive(Logos,PartialEq)]
/// pub enum TFQ {
/// #[token("true")]
/// True,
/// #[token("false")]
/// False,
///
/// #[token("?")]
/// Question,
/// }
/// let parser:Parsit<TFQ> = Parsit::new("").unwrap();
/// let parser_fn = |p|{ token!( parser.token(p) =>
/// TFQ::True => Some(true),
/// TFQ::False => Some(false),
/// TFQ::Question => None
/// )};
///
/// if let Some(res) = parser.zero_or_more(0, parser_fn).ok() {
/// assert_eq!(res, vec![]);
/// } else { assert!(false) };
/// ```
pub fn zero_or_more<T, Then>(&self, pos: usize, then: Then) -> Step<'a, Vec<T>>
where
Then: FnOnce(usize) -> Step<'a, T> + Copy,
{
match then(pos).then_multi_zip(then).merge() {
Fail(_) => Success(vec![], pos),
Error(ParseError::ReachedEOF(_)) => Success(vec![], pos),
success => success,
}
}
/// Validates if the parsing process reaches the end of the input.
/// If so transforms the result to the error UnreachedEOF
///
/// It can be used in the end of the parsing
pub fn validate_eof<T>(&self, res: Step<'a, T>) -> Step<'a, T> {
match res {
Success(_, pos) if self.lexer.len() != pos => Error(ParseError::UnreachedEOF(pos)),
other => other,
}
}
/// Prints a position and env from the source text.
/// It has a radius of 2 tokens so thus it prints
/// -3-2-10+1+2+3
pub fn env<T>(&self, step: &Step<'a, T>) -> String {
match step {
Success(_, p) => self.lexer.env(*p),
Fail(p) => self.lexer.env(*p),
Error(ParseError::ExternalError(_,p)) => self.lexer.env(*p),
Error(ParseError::FailedOnValidation(_,p)) => self.lexer.env(*p),
Error(ParseError::ReachedEOF(p)) => self.lexer.env(*p),
Error(ParseError::UnreachedEOF(p)) => self.lexer.env(*p),
Error(e) => format!("{:?}", e)
}
}
}
/// The token is used as a stub for the parsing operations when we need just a notion
/// that the token is parsed correctly but we don't need to process any values.
#[derive(Debug, Copy, Clone, PartialEq)]
pub struct EmptyToken {}
/// Helps to parse a token on the lexer level
/// - Typically, it takes a token from the parser(defined in the structure of Logos)
/// - The structure should implement `PartialEq`
///
/// # Examples
/// - create a pattern matching for the given tokens
/// ```
/// use logos::Logos;
/// use crate::parsit::parser::Parsit;
/// use crate::parsit::token;
/// use crate::parsit::step::Step;
/// use crate::parsit::parser::EmptyToken;
/// #[derive(Logos,PartialEq)]
/// pub enum TFQ {
/// #[token("true")]
/// True,
/// #[token("false")]
/// False,
///
/// #[token("?")]
/// Question,
/// }
///
/// let p:Parsit<TFQ> = Parsit::new("true?").unwrap();
/// // create a pattern matching for the given tokens
/// token!(
/// p.token(0) =>
/// TFQ::True => true,
/// TFQ::False => false
/// );
/// // create a matching for only one token without a result
/// // it is used oftenly with then().
/// // The EmptyToken will be return
/// token!(p.token(1) => TFQ::Question);
///
/// ```
///
#[macro_export]
macro_rules! token {
($obj:expr => $($matcher:pat $(if $pred:expr)* => $result:expr),*) => {
match $obj {
Ok((t,p)) => match t {
$($matcher $(if $pred)* => Step::Success($result, p + 1)),*,
_ => Step::Fail(p)
}
Err(e) => Step::Error(e)
}
};
($obj:expr => $($matcher:pat $(if $pred:expr)*),*) => {
match $obj {
Ok((t,p)) => match t {
$($matcher $(if $pred)* => Step::Success(EmptyToken{}, p + 1)),*,
_ => Step::Fail(p)
}
Err(e) => Step::Error(e)
}
}
}
/// Helps to parse a wrapper
/// ```ebnf
/// <rule> ::= '(' "value" ')'
/// ```
///
/// # Examples
/// ```
/// use logos::Logos;
/// use crate::parsit::parser::Parsit;
/// use crate::parsit::wrap;
/// use crate::parsit::token;
/// use crate::parsit::step::Step;
/// use crate::parsit::parser::EmptyToken;
/// #[derive(Logos,PartialEq)]
/// pub enum TFQ {
/// #[token("(")]
/// L,
/// #[token(")")]
/// R,
///
/// #[token("word")]
/// Word,
/// #[token("none")]
/// None,
/// }
///
/// let p:Parsit<TFQ> = Parsit::new("(word)").unwrap();
/// let left = |pos:usize|{token!(p.token(pos) => TFQ::L)};
/// let right = |pos:usize|{token!(p.token(pos) => TFQ::R)};
/// let word = |pos:usize|{token!(p.token(pos) => TFQ::Word)};
/// let pos = 0;
/// wrap!(pos => left ; word; right );
///
/// let p:Parsit<TFQ> = Parsit::new("()").unwrap();
/// let word = |pos:usize|{token!(p.token(pos) => TFQ::Word).or_none()};
/// wrap!(0 => left ; word ?; right );
///
/// let p:Parsit<TFQ> = Parsit::new("()").unwrap();
/// let word = |pos:usize|{token!(p.token(pos) => TFQ::Word => 1)};
/// wrap!(0 => left ; word or 0; right ).print();
/// ```
///
#[macro_export]
macro_rules! wrap {
($pos:literal => $left:ident; $internal:ident; $right:ident ) => {
$left($pos).then($internal).then_zip($right).take_left()
} ;
($pos:literal => $left:ident; $internal:ident ?; $right:ident ) => {
$left($pos).then_or_none($internal).then_zip($right).take_left()
};
($pos:literal => $left:ident; $internal:ident or $default:ident; $right:ident ) => {
$left($pos).then_or_val($internal,$default).then_zip($right).take_left()
};
($pos:literal => $left:ident; $internal:ident or $default:literal; $right:ident ) => {
$left($pos).then_or_val($internal,$default).then_zip($right).take_left()
};
($pos:ident => $left:ident; $internal:ident; $right:ident ) => {
$left($pos).then($internal).then_zip($right).take_left()
} ;
($pos:ident => $left:ident; $internal:ident ?; $right:ident ) => {
$left($pos).then_or_none($internal).then_zip($right).take_left()
};
($pos:ident => $left:ident; $internal:ident or $default:ident; $right:ident ) => {
$left($pos).then_or_val($internal,$default).then_zip($right).take_left()
};
($pos:ident => $left:ident; $internal:ident or $default:literal; $right:ident ) => {
$left($pos).then_or_val($internal,$default).then_zip($right).take_left()
}
}
/// Helps to parse a sequence
/// ```ebnf
/// <rule> ::= el {delim el}
/// ```
///
/// # Examples
/// ```
/// use logos::Logos;
/// use crate::parsit::parser::Parsit;
/// use crate::parsit::wrap;
/// use crate::parsit::seq;
/// use crate::parsit::token;
/// use crate::parsit::step::Step;
/// use crate::parsit::parser::EmptyToken;
/// #[derive(Logos,PartialEq)]
/// pub enum TFQ {
/// #[token("(")]
/// L,
/// #[token(")")]
/// R,
/// #[token(",")]
/// C,
///
/// #[token("word")]
/// Word,
/// #[token("none")]
/// None,
/// }
///
/// let p:Parsit<TFQ> = Parsit::new("word,word,word").unwrap();
/// let comma = |pos:usize|{token!(p.token(pos) => TFQ::C)};
/// let word = |pos:usize|{token!(p.token(pos) => TFQ::Word)};
/// let pos = 0;
/// seq!(pos => word, comma );
/// let p:Parsit<TFQ> = Parsit::new("word,word,word,").unwrap();
/// seq!(pos => word, comma ,);
/// ```
///
#[macro_export]
macro_rules! seq {
($pos:ident => $elem:ident, $sep:ident ) => {
$elem($pos)
.then_multi_zip(|p| $sep(p).then($elem))
.merge()
};
($pos:ident => $elem:ident,$sep:ident, ) => {
$elem($pos)
.then_multi_zip(|p| {$sep(p).then($elem)})
.then_or_none_zip(|p| $sep(p).or_none())
.take_left()
.merge()
};
}