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
//! Utility module for lexer implementations, //! providing types to help manage states and tokens. use std::str::Chars; use super::token::Token; use super::token::Category; /// A recursive function type used by lexers to manage their state. /// Based on Rob Pike's "Lexical Scanning in Go" talk, these functions are /// invoked in a call/return loop (letting the current function determine /// the next) until a `None` value is returned, after which lexing is complete. /// /// See the `lexers` module for examples. pub struct StateFunction(pub fn(&mut Tokenizer) -> Option<StateFunction>); /// The Tokenizer type is used to produce and store tokens for lexers. pub struct Tokenizer<'a> { data: Chars<'a>, current_token: String, tokens: Vec<Token>, pub states: Vec<StateFunction>, } impl<'a> Tokenizer<'a> { /// Initializes a new tokenizer with the given data. /// /// # Examples /// /// ``` /// let tokenizer = luthor::Tokenizer::new("luthor"); /// ``` pub fn new(data: &str) -> Tokenizer { Tokenizer{ data: data.chars(), current_token: String::new(), tokens: vec![], states: vec![] } } /// Returns a copy of the tokens processed to date, in addition to any /// in-progress or remaining data appended as a text-category token. /// As a result, the returned tokens always produce the original dataset /// when their lexemes are concatenated. /// /// # Examples /// /// ``` /// use luthor::token::{Category, Token}; /// /// // Set up a new tokenizer. /// let mut tokenizer = luthor::Tokenizer::new("luthor"); /// tokenizer.tokenize_next(2, Category::Keyword); /// /// assert_eq!( /// tokenizer.tokens(), /// vec![ /// Token{ lexeme: "lu".to_string(), category: Category::Keyword }, /// Token{ lexeme: "thor".to_string(), category: Category::Text } /// ] /// ); /// /// ``` pub fn tokens(&self) -> Vec<Token> { let mut tokens = self.tokens.clone(); // Duplicate the tokenizer's character iterator so that we can // advance it to check for equality without affecting the original. let data_iter = self.data.clone(); // Append any remaining data to the in-progress token. let mut remaining_data = self.current_token.clone(); for c in data_iter { remaining_data.push(c); } // If there was any remaining or in-progress data, add it as a text token. if !remaining_data.is_empty() { tokens.push(Token{ lexeme: remaining_data, category: Category::Text}); } tokens } /// Moves to the next character in the data. /// Does nothing if there is no more data to process. /// /// # Examples /// /// ``` /// // Set up a new tokenizer. /// let mut tokenizer = luthor::Tokenizer::new("luthor"); /// /// // Ensure that we're at the first character. /// assert_eq!(tokenizer.current_char().unwrap(), 'l'); /// /// // Consume the first character. /// tokenizer.advance(); /// /// // Ensure that we're at the next character. /// assert_eq!(tokenizer.current_char().unwrap(), 'u'); /// ``` pub fn advance(&mut self) { match self.data.next() { Some(c) => self.current_token.push(c), None => () } } /// Returns the character at the current position, /// unless all of the data has been processed. /// /// # Examples /// /// ``` /// // Set up a new tokenizer. /// let mut tokenizer = luthor::Tokenizer::new("l"); /// /// // Ensure that the current character is correct. /// assert_eq!(tokenizer.current_char().unwrap(), 'l'); /// /// // Consume the last bit of data. /// tokenizer.advance(); /// /// // Ensure that there is no current character. /// assert_eq!(tokenizer.current_char(), None); /// ``` pub fn current_char(&self) -> Option<char> { match self.data.clone().peekable().peek() { Some(c) => Some(c.clone()), None => None } } /// Returns the next non-whitespace character, without advancing the cursor. /// /// # Examples /// /// ``` /// // Set up a new tokenizer. /// let mut tokenizer = luthor::Tokenizer::new(" b"); /// /// // Ask for the next non-whitespace character. /// assert_eq!(tokenizer.next_non_whitespace_char().unwrap(), 'b'); /// /// // Advance past the "b" character and ask again. /// for _ in 0..3 { tokenizer.advance(); } /// assert!(tokenizer.next_non_whitespace_char().is_none()); /// /// ``` pub fn next_non_whitespace_char(&self) -> Option<char> { // Duplicate the tokenizer's character iterator so that we can // advance it to check for equality without affecting the original. let mut data_iter = self.data.clone(); data_iter.find(|&c| c != ' ' && c != '\n') } /// Whether or not the remaining data starts with the specified prefix. /// /// # Examples /// /// ``` /// // Set up a new tokenizer. /// let tokenizer = luthor::Tokenizer::new("lex"); /// /// assert!(tokenizer.has_prefix("le")); /// ``` pub fn has_prefix(&self, prefix: &str) -> bool { // Duplicate the tokenizer's character iterator so that we can // advance it to check for equality without affecting the original. let mut data_iter = self.data.clone(); // Check that the subject is a prefix, character by character. // This is much faster than building a string of equal length from // self.data and deferring to a straight string comparison using ==. prefix.chars().all(|c| { match data_iter.next() { Some(d) => c == d, None => false } }) } /// Whether or not the remaining data starts with the specified lexeme. /// Ensures that the specified lexeme is not just a prefix by checking that /// the data that follows it is a newline, space, comma, or nothing at all. /// /// # Examples /// /// ``` /// use luthor::token::Category; /// /// // Set up a new tokenizer. /// let mut tokenizer = luthor::Tokenizer::new("lex\nluthor lib,rary"); /// /// // Prefixes don't count. /// assert!(!tokenizer.starts_with_lexeme("le")); /// /// // Newlines delineate lexemes. /// assert!(tokenizer.starts_with_lexeme("lex")); /// /// // Consume 4 characters, advancing to the next lexeme. /// tokenizer.tokenize_next(4, Category::Text); /// /// // Spaces delineate lexemes. /// assert!(tokenizer.starts_with_lexeme("luthor")); /// /// // Consume 7 characters, advancing to the next lexeme. /// tokenizer.tokenize_next(7, Category::Text); /// /// // Commas delineate lexemes. /// assert!(tokenizer.starts_with_lexeme("lib")); /// /// // Consume 4 characters, advancing to the next lexeme. /// tokenizer.tokenize_next(4, Category::Text); /// /// // End of string delineates lexemes. /// assert!(tokenizer.starts_with_lexeme("rary")); /// ``` pub fn starts_with_lexeme(&self, lexeme: &str) -> bool { // Duplicate the tokenizer's character iterator so that we can // advance it to check for equality without affecting the original. let data_iter = self.data.clone(); self.has_prefix(lexeme) && match data_iter.skip(lexeme.len()).next() { Some(' ') | Some('\n') | Some(',') => true, None => true, _ => false } } /// Creates and stores a token with the given category containing any /// data processed using `advance` since the last call to this method. /// /// # Examples /// /// ``` /// use luthor::token::Category; /// /// // Set up a new tokenizer. /// let mut tokenizer = luthor::Tokenizer::new("luthor"); /// /// // Consume two characters and then tokenize them. /// tokenizer.advance(); /// tokenizer.advance(); /// tokenizer.tokenize(Category::Text); /// /// // Ensure that we have a correctly-categorized token. /// assert_eq!(tokenizer.tokens()[0].lexeme, "lu"); /// ``` pub fn tokenize(&mut self, category: Category) { if !self.current_token.is_empty() { let token = Token{ lexeme: self.current_token.clone(), category: category, }; self.tokens.push(token); self.current_token = String::new(); } } /// Creates and stores a token with the given category and the /// next `amount` characters of the data. Before doing this, it /// tokenizes any previously processed characters with the generic /// `Category::Text` category. /// /// # Examples /// /// ``` /// use luthor::token::Category; /// use luthor::token::Token; /// /// // Set up a new tokenizer. /// let mut tokenizer = luthor::Tokenizer::new("luthor"); /// /// // Consume one character, and then tokenize the next 5. /// tokenizer.advance(); /// tokenizer.tokenize_next(5, Category::Keyword); /// /// // Ensure that we have two properly-categorized tokens. /// assert_eq!( /// tokenizer.tokens()[0], /// Token{ lexeme: "l".to_string(), category: Category::Text } /// ); /// assert_eq!( /// tokenizer.tokens()[1], /// Token{ lexeme: "uthor".to_string(), category: Category::Keyword } /// ); /// ``` pub fn tokenize_next(&mut self, amount: usize, category: Category) { // If there's any data that has yet // to be tokenized, take care of that. self.tokenize(Category::Text); // Mark the next series of characters. for _ in 0..amount { self.advance(); } // Tokenize the marked characters. self.tokenize(category); } /// Consumes consecutive whitespace characters as a single token. /// /// # Examples /// /// ``` /// use luthor::token::Category; /// use luthor::token::Token; /// /// let mut tokenizer = luthor::Tokenizer::new(" \nluthor"); /// tokenizer.consume_whitespace(); /// /// assert_eq!( /// tokenizer.tokens()[0], /// Token{ lexeme: " \n".to_string(), category: Category::Whitespace } /// ); /// ``` pub fn consume_whitespace(&mut self) { let mut found_whitespace = false; loop { match self.current_char() { Some(' ') | Some('\n') => { if !found_whitespace { self.tokenize(Category::Text); found_whitespace = true; } self.advance(); }, _ => { if found_whitespace { self.tokenize(Category::Whitespace); } return } } } } } #[cfg(test)] mod tests { use tokenizer::Tokenizer; use token::{Category, Token}; #[test] fn current_char_returns_the_char_at_head() { let data = "él"; let tokenizer = Tokenizer::new(data); assert_eq!(tokenizer.current_char().unwrap(), 'é'); } #[test] fn current_char_returns_none_if_at_the_end() { let data = "él"; let mut tokenizer = Tokenizer::new(data); tokenizer.advance(); tokenizer.advance(); assert_eq!(tokenizer.current_char(), None); } #[test] fn tokenize_creates_the_correct_token() { let data = "élégant"; let mut tokenizer = Tokenizer::new(data); tokenizer.advance(); tokenizer.advance(); tokenizer.tokenize(Category::Text); let token = tokenizer.tokens.pop().unwrap(); let expected_token = Token{ lexeme: "él".to_string(), category: Category::Text}; assert_eq!(token, expected_token); } #[test] fn tokenize_does_nothing_if_range_is_empty() { let data = "élégant"; let mut tokenizer = Tokenizer::new(data); tokenizer.tokenize(Category::Text); assert_eq!(tokenizer.tokens.len(), 0); } #[test] fn tokenize_next_tokenizes_previous_data_as_text() { let data = "élégant"; let mut tokenizer = Tokenizer::new(data); tokenizer.advance(); tokenizer.advance(); tokenizer.tokenize_next(1, Category::Keyword); let token = tokenizer.tokens.remove(0); let expected_token = Token{ lexeme: "él".to_string(), category: Category::Text}; assert_eq!(token, expected_token); } #[test] fn tokenize_next_tokenizes_next_x_chars() { let data = "élégant"; let mut tokenizer = Tokenizer::new(data); tokenizer.advance(); tokenizer.advance(); tokenizer.tokenize_next(5, Category::Keyword); let token = tokenizer.tokens.pop().unwrap(); let expected_token = Token{ lexeme: "égant".to_string(), category: Category::Keyword}; assert_eq!(token, expected_token); } #[test] fn tokenize_next_takes_at_most_what_is_left() { let data = "élégant"; let mut tokenizer = Tokenizer::new(data); tokenizer.advance(); tokenizer.advance(); tokenizer.tokenize_next(15, Category::Keyword); let token = tokenizer.tokens.pop().unwrap(); let expected_token = Token{ lexeme: "égant".to_string(), category: Category::Keyword}; assert_eq!(token, expected_token); } #[test] fn consume_whitespace_handles_preexisting_noncategorized_chars() { let data = "e "; let mut tokenizer = Tokenizer::new(data); tokenizer.advance(); tokenizer.consume_whitespace(); assert_eq!( tokenizer.tokens()[0], Token{ lexeme: "e".to_string(), category: Category::Text } ); assert_eq!( tokenizer.tokens()[1], Token{ lexeme: " ".to_string(), category: Category::Whitespace } ); } #[test] fn tokens_returns_unprocessed_data_as_text_token() { let tokenizer = Tokenizer::new("luthor"); assert_eq!( tokenizer.tokens()[0], Token{ lexeme: "luthor".to_string(), category: Category::Text } ); } #[test] fn tokens_joins_advanced_data_with_unprocessed_data_as_text_token() { let mut tokenizer = Tokenizer::new("luthor"); tokenizer.advance(); assert_eq!( tokenizer.tokens()[0], Token{ lexeme: "luthor".to_string(), category: Category::Text } ); } }