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
#![doc(html_root_url = "https://docs.rs/mo/0.1.0")] //! # Usage //! //! mo come in two flavors: binary or crate (library) //! //! For a basic/medium/advanced usage of the binary/library, please see the [Readme](https://github.com/yuulive/mo). //! //! ## Frequently Asked Questions? (FAQ) //! //! See the [Readme](https://github.com/yuulive/mo). //! //! ## I just want to see how this code works //! //! Please see first the Readme. Well if you really want to see the code, go ahead //! use aho_corasick::AhoCorasick; use indicatif::{ProgressBar, ProgressStyle}; use pest::error::{Error, ErrorVariant, InputLocation}; use pest_meta::ast::Rule as AstRule; use pest_meta::parser::{self, Rule}; use pest_meta::{optimizer, validator}; use pest_vm::Vm; use rayon::prelude::*; use std::collections::HashMap; use std::fs::File; use std::io::Write; use std::path::Path; pub mod config; mod generator; // Re-exports pub use pest; pub use pest_meta; use crate::config::*; use crate::generator::*; /// Compile a grammar string and creates a `HashMap` with rules found as keys and their components (AST) as entries /// /// In this step, the grammar is validated with the pest reference grammar, and the built-in rules are replaced for /// their equivalents /// ``` /// use mo::compile_grammar; /// /// // Grammar string /// let mut grammar = r#" /// language = {"Rust" | "Python" | "Go" | "Java" | "PHP" | "Haskell"} /// one = {"1"} /// daysNumber = {one ~ " day" | !one ~ ASCII_NONZERO_DIGIT ~ " days"} /// sentence = {"I have been programming in " ~ language ~ " for " ~ daysNumber ~ "."} /// "#; /// /// // Generate the ast /// let grammar_ast = compile_grammar(grammar.to_string()); /// /// println!("{:?}", grammar_ast); /// ``` pub fn compile_grammar(grammar: String) -> Result<Grammar, Vec<HashMap<String, String>>> { // Replace builtin pest rules for their equivalents let grammar = replace_builtin_rules(&grammar).unwrap(); // Print grammar after replaces builtin rules // println!("{}", grammar.clone()); let result = parser::parse(Rule::grammar_rules, &grammar).map_err(|error| { error.renamed_rules(|rule| match *rule { Rule::grammar_rule => "rule".to_owned(), Rule::_push => "push".to_owned(), Rule::assignment_operator => "`=`".to_owned(), Rule::silent_modifier => "`_`".to_owned(), Rule::atomic_modifier => "`@`".to_owned(), Rule::compound_atomic_modifier => "`$`".to_owned(), Rule::non_atomic_modifier => "`!`".to_owned(), Rule::opening_brace => "`{`".to_owned(), Rule::closing_brace => "`}`".to_owned(), Rule::opening_paren => "`(`".to_owned(), Rule::positive_predicate_operator => "`&`".to_owned(), Rule::negative_predicate_operator => "`!`".to_owned(), Rule::sequence_operator => "`&`".to_owned(), Rule::choice_operator => "`|`".to_owned(), Rule::optional_operator => "`?`".to_owned(), Rule::repeat_operator => "`*`".to_owned(), Rule::repeat_once_operator => "`+`".to_owned(), Rule::comma => "`,`".to_owned(), Rule::closing_paren => "`)`".to_owned(), Rule::quote => "`\"`".to_owned(), Rule::insensitive_string => "`^`".to_owned(), Rule::range_operator => "`..`".to_owned(), Rule::single_quote => "`'`".to_owned(), other_rule => format!("{:?}", other_rule), }) }); let pairs = match result { Ok(pairs) => pairs, Err(error) => { // add_rules_to_select(vec![]); return Err(vec![convert_error(error, &grammar)]); } }; if let Err(errors) = validator::validate_pairs(pairs.clone()) { // add_rules_to_select(vec![]); return Err(errors .into_iter() .map(|e| convert_error(e, &grammar)) .collect()); } let ast = match parser::consume_rules(pairs) { Ok(ast) => ast, Err(errors) => { // add_rules_to_select(vec![]); return Err(errors .into_iter() .map(|e| convert_error(e, &grammar)) .collect()); } }; let hashmap_ast_rules: HashMap<String, AstRule> = ast .iter() .map(|rule| (rule.name.to_string(), rule.clone())) .collect(); Ok(Grammar { rules: hashmap_ast_rules, }) } /// Generate a number of examples with the grammar,start rule and config provided /// /// ``` /// use mo::config::GeneratorConfig; /// use mo::parallel_generate_examples; /// /// // Default configuration for the generator /// let mut config: GeneratorConfig = Default::default(); /// /// // Grammar string /// let mut grammar = r#" /// language = {"Rust" | "Python" | "Go" | "Java" | "PHP" | "Haskell"} /// one = {"1"} /// daysNumber = {one ~ " day" | !one ~ ASCII_NONZERO_DIGIT ~ " days"} /// sentence = {"I have been programming in " ~ language ~ " for " ~ daysNumber ~ "."} /// "#; /// /// // Generate the examples /// let results = parallel_generate_examples( /// grammar.to_string(), // The grammar /// 5, // Quantity of examples /// "sentence".to_string(), // Start rule /// &config, // Config of the generator /// false, // Print progress /// false, // Print in stdout, false return a vector with the examples /// ); /// /// println!("{:?}", results); /// ``` /// pub fn parallel_generate_examples( grammar_string: String, quantity: u32, start: String, config: &GeneratorConfig, print_progress: bool, print_stdout: bool, ) -> Vec<Result<String, String>> { let input_data = InputData::new(grammar_string); let mut vec = vec![]; // This mode is for avoid printing the examples, nothing special // Nobody wants to generate examples and then discard all of them... right? if config.benchmark_mode { // Print examples as they are generated (1..quantity + 1).into_par_iter().for_each(|_| { // This isn't optimized by the compiler... right? let _r = generator::generate_example(input_data.clone(), start.clone(), config); }); } else if print_stdout { // Print examples as they are generated (1..quantity + 1).into_par_iter().for_each(|i| { let r = generator::generate_example(input_data.clone(), start.clone(), config); if print_progress { println!("Example #{} generated:\r\n{}", i, r.unwrap()); } else { println!("{}", r.unwrap()); } }); } else { vec = Vec::with_capacity(quantity as usize); vec.par_extend((1..quantity + 1).into_par_iter().map(|i| { let r = generator::generate_example(input_data.clone(), start.clone(), config); if print_progress { println!("Example #{} generated", i); } r })); } vec } // pub fn gen_random_html_and_save(examples: u32,) // where> // S: AsRef<Path>, // Creación de ejemplos recibiendo una gramática, numero de ejemplos, regla de inicio, path de guardado, nombre de archivos en formato "example-{}.ext" /// Generate and save a number of examples with the grammar,start rule and config provided /// /// ```ignore /// # // This doc_test is ignored because have side effects (the files) /// use std::path::Path; /// use mo::config::GeneratorConfig; /// use mo::parallel_generate_save_examples; /// /// // Default configuration for the generator /// let mut config: GeneratorConfig = Default::default(); /// /// // Grammar string /// let mut grammar = r#" /// language = {"Rust" | "Python" | "Go" | "Java" | "PHP" | "Haskell"} /// one = {"1"} /// daysNumber = {one ~ " day" | !one ~ ASCII_NONZERO_DIGIT ~ " days"} /// sentence = {"I have been programming in " ~ language ~ " for " ~ daysNumber ~ "."} /// "#; /// /// // Folder to save the examples /// let path = Path::new("./my-examples/"); /// /// let template_name = "relevant-example-{}.txt".to_string(); /// /// // Generate and save the examples /// let results = parallel_generate_save_examples( /// grammar.to_string(), // The grammar /// 5, // Quantity of examples /// "sentence".to_string(), // Start rule /// path, // The folder to save the examples /// template_name, // The name of the files saved /// &config, // Config of the generator /// ); /// /// ``` pub fn parallel_generate_save_examples<S>( grammar_string: String, quantity: u32, start: String, path: S, name_format: String, config: &GeneratorConfig, ) where S: AsRef<Path>, { // use env_logger; // env_logger::init(); let path_cloned = path.as_ref(); // Creación de la barra de progreso let progress_bar = ProgressBar::new(quantity.into()); progress_bar.set_style( ProgressStyle::default_bar() .template( "[{elapsed_precise}] {wide_bar} {pos:>3}/{len:3} {msg} {percent}% {eta_precise}", ) .progress_chars("██░"), ); // Forzar el pintado inicial de la barra progress_bar.tick(); let input_data = InputData::new(grammar_string); (0..quantity).into_par_iter().for_each(|i| { // Generar el ejemplo let r = generator::generate_example(input_data.clone(), start.clone(), config); match r { Ok(example) => { let new_path = path_cloned.join(name_format.replace("{}", &i.to_string())); // println!("for {:?}", new_path); // Guardar el archivo let mut f = File::create(new_path).expect("Unable to create file"); f.write_all(example.as_bytes()) .expect("Unable to write data"); // Modificando la barra de progreso progress_bar.inc(1); // println!( // "HTML {} completado y guardado, total esperado {}", // i, examples // ); } Err(error) => { println!("{}", error); } } }); // Terminando la barra de progreso progress_bar.finish(); } // Parsea `input` usando la gramática `grammar`, iniciando el parseo desde `rule` // retorna Ok si es exitoso el parseo, Err si no es posible parsear // Es usado en términos generales como shorcut en los tests para validar si una cadena generada, puede ser parseada por la misma gramatica que la genero /// Parse input with the provided grammar and start rule returns `Ok` if the parse is sucessfull, `Err` otherwise /// /// It's used for validate the examples generated with the original grammar /// /// ``` /// use mo::config::GeneratorConfig; /// use mo::{compile_grammar, parse_input, parallel_generate_examples}; /// /// // Default configuration for the generator /// let mut config: GeneratorConfig = Default::default(); /// /// // Grammar string /// let mut grammar = r#" /// language = {"Rust" | "Python" | "Go" | "Java" | "PHP" | "Haskell"} /// one = {"1"} /// daysNumber = {one ~ " day" | !one ~ ASCII_NONZERO_DIGIT ~ " days"} /// sentence = {"I have been programming in " ~ language ~ " for " ~ daysNumber ~ "."} /// "#; /// /// // Generate the ast /// let grammar_ast = compile_grammar(grammar.to_string()); /// /// // Generate the examples /// let results = parallel_generate_examples( /// grammar.to_string(), // The grammar /// 1, // Quantity of examples /// "sentences".to_string(), // Start rule /// &config, // Config of the generator /// false, // Print progress /// false, // Print in stdout, false return a vector with the examples /// ); /// /// let one_example = results[0].as_ref().unwrap(); /// /// // Validate the generated example with the grammar /// let validate = parse_input(grammar_ast.unwrap(), "sentence".to_string(), one_example.to_string()); /// /// println!("{:?}", validate); /// ``` /// pub fn parse_input<'a>(grammar: Grammar, rule: String, input: String) -> Result<(), String> { // Es necesario entregar una copia entera de las reglas al vm let vm = Vm::new(optimizer::optimize( grammar.rules.values().map(|r| r.clone()).collect(), )); parse_input_with_vm(vm, rule, input) } /// Parsea `input` usando la máquina `Vm`, iniciando el parseo desde `rule` /// retorna Ok si es exitoso el parseo, Err si no es posible parsear fn parse_input_with_vm<'a>(vm: Vm, rule: String, input: String) -> Result<(), String> { match vm.parse(&rule, &input) { Ok(_pairs) => { // let lines: Vec<_> = pairs.map(|pair| format_pair(pair, 0, true)).collect(); // let lines = lines.join("\n"); // output.set_value(&format!("{}", lines)); Ok(()) } Err(error) => { // output.set_value(&format!("{}", error.renamed_rules(|r| r.to_string()))) // FIXME: Eliminar el string para usar un tipo de error más "Rustacean" Err(format!("{}", error.renamed_rules(|r| r.to_string()))) } } // } } fn convert_error(error: Error<Rule>, grammar: &str) -> HashMap<String, String> { let message = match error.variant { ErrorVariant::CustomError { message } => message, _ => unreachable!(), }; match error.location { InputLocation::Pos(pos) => { let mut map = HashMap::new(); map.insert("from".to_owned(), line_col(pos, grammar)); map.insert("to".to_owned(), line_col(pos, grammar)); map.insert("message".to_owned(), format!("{}", message)); map } InputLocation::Span((start, end)) => { let mut map = HashMap::new(); map.insert("from".to_owned(), line_col(start, grammar)); map.insert("to".to_owned(), line_col(end, grammar)); map.insert("message".to_owned(), format!("{}", message)); map } } } fn line_col(pos: usize, input: &str) -> String { let (line, col) = { let mut pos = pos; // Position's pos is always a UTF-8 border. let slice = &input[..pos]; let mut chars = slice.chars().peekable(); let mut line_col = (1, 1); while pos != 0 { match chars.next() { Some('\r') => { if let Some(&'\n') = chars.peek() { chars.next(); if pos == 1 { pos -= 1; } else { pos -= 2; } line_col = (line_col.0 + 1, 1); } else { pos -= 1; line_col = (line_col.0, line_col.1 + 1); } } Some('\n') => { pos -= 1; line_col = (line_col.0 + 1, 1); } Some(c) => { pos -= c.len_utf8(); line_col = (line_col.0, line_col.1 + 1); } None => unreachable!(), } } line_col }; format!("({}, {})", line - 1, col - 1) } /// Replace builtin pest rules for their equivalents /// /// For example in a grammar like this: /// ```text /// small_number = ASCII_DIGIT{3} /// ``` /// /// the replaced equivalent will be this: /// ASCII_DIGIT /// ```text /// small_number = ('0'..'9'){3} /// ``` /// /// **Note:** currently only the ASCII rules are replaced /// /// For the list of equivalent rules see https://pest.rs/book/grammars/built-ins.html fn replace_builtin_rules(grammar: &String) -> Result<String, std::io::Error> { //TODO: Add the Unicode rules from https://pest.rs/book/grammars/built-ins.html let patterns = &[ "ANY", "ASCII_DIGIT", "ASCII_NONZERO_DIGIT", "ASCII_BIN_DIGIT", "ASCII_OCT_DIGIT", "ASCII_HEX_DIGIT", "ASCII_ALPHA_LOWER", "ASCII_ALPHA_UPPER", "ASCII_ALPHANUMERIC", "NEWLINE", ]; // Parentheses are kept to facilitate things like ASCII_ALPHA{1,5} let replace_with = &[ "('\u{00}'..'\u{10FFFF}')", "('0'..'9')", "('1'..'9')", "('0'..'1')", "('0'..'7')", "('0'..'9' | 'a'..'f' | 'A'..'F')", "('a'..'z')", "('A'..'Z')", "('0'..'9' | 'a'..'z' | 'A'..'Z')", r#"("\n" | "\r\n" | "\r")"#, ]; // Replace all strings in a single pass let mut wtr = vec![]; let ac = AhoCorasick::new(patterns); ac.stream_replace_all(grammar.as_bytes(), &mut wtr, replace_with)?; // println!("{:?}", wtr); let mut s = match String::from_utf8(wtr) { Ok(v) => v, Err(e) => panic!("Invalid UTF-8 sequence: {}", e), }; // ASCII_ALPHA it is replaced last because it has conflict with ASCII_ALPHA_LOWER y ASCII_ALPHA_UPPER // because the word "ASCII_ALPHA" is shorter s = s.replace("ASCII_ALPHA", "('a'..'z' | 'A'..'Z')"); // println!("result: {}", s); Ok(s) }