|
| 1 | +mod parser_impl; |
| 2 | +mod reader; |
| 3 | +mod span_factory; |
| 4 | +mod state; |
| 5 | +mod unicode; |
| 6 | +mod unicode_property; |
| 7 | + |
| 8 | +pub use parser_impl::Parser; |
| 9 | + |
| 10 | +#[cfg(test)] |
| 11 | +mod test { |
| 12 | + use crate::{Parser, ParserOptions}; |
| 13 | + use oxc_allocator::Allocator; |
| 14 | + |
| 15 | + fn default() -> ParserOptions { |
| 16 | + ParserOptions::default() |
| 17 | + } |
| 18 | + fn with_unicode_mode() -> ParserOptions { |
| 19 | + ParserOptions { unicode_mode: true, ..Default::default() } |
| 20 | + } |
| 21 | + fn with_unicode_sets_mode() -> ParserOptions { |
| 22 | + ParserOptions { unicode_mode: true, unicode_sets_mode: true, ..Default::default() } |
| 23 | + } |
| 24 | + |
| 25 | + #[test] |
| 26 | + fn should_pass() { |
| 27 | + let allocator = Allocator::default(); |
| 28 | + |
| 29 | + for (source_text, options) in &[ |
| 30 | + ("", default()), |
| 31 | + ("a", default()), |
| 32 | + ("a+", default()), |
| 33 | + ("a*", default()), |
| 34 | + ("a?", default()), |
| 35 | + ("^$^$^$", default()), |
| 36 | + ("(?=a){1}", default()), |
| 37 | + ("(?!a){1}", default()), |
| 38 | + ("a{1}", default()), |
| 39 | + ("a{1", default()), |
| 40 | + ("a|{", default()), |
| 41 | + ("a{", default()), |
| 42 | + ("a{,", default()), |
| 43 | + ("a{1,", default()), |
| 44 | + ("a{1,}", default()), |
| 45 | + ("a{1,2}", default()), |
| 46 | + ("x{9007199254740991}", default()), |
| 47 | + ("x{9007199254740991,9007199254740991}", default()), |
| 48 | + ("a|b", default()), |
| 49 | + ("a|b|c", default()), |
| 50 | + ("a|b+?|c", default()), |
| 51 | + ("a+b*?c{1}d{2,}e{3,4}?", default()), |
| 52 | + (r"^(?=ab)\b(?!cd)(?<=ef)\B(?<!gh)$", default()), |
| 53 | + ("a.b..", default()), |
| 54 | + (r"\d\D\s\S\w\W", default()), |
| 55 | + (r"\x", default()), |
| 56 | + (r"\p{Emoji_Presentation}\P{Script_Extensions=Latin}\p{Sc}|\p{Basic_Emoji}", default()), |
| 57 | + (r"\p{Emoji_Presentation}\P{Script_Extensions=Latin}\p{Sc}|\p{P}", with_unicode_mode()), |
| 58 | + (r"^\p{General_Category=cntrl}+$", with_unicode_mode()), |
| 59 | + (r"\p{Basic_Emoji}", with_unicode_sets_mode()), |
| 60 | + (r"\n\cM\0\x41\u1f60\.\/", default()), |
| 61 | + (r"\c0", default()), |
| 62 | + (r"\0", default()), |
| 63 | + (r"\0", with_unicode_mode()), |
| 64 | + (r"\u", default()), |
| 65 | + (r"\u{", default()), |
| 66 | + (r"\u{}", default()), |
| 67 | + (r"\u{0}", default()), |
| 68 | + (r"\u{1f600}", default()), |
| 69 | + (r"\u{1f600}", with_unicode_mode()), |
| 70 | + ("(?:abc)", default()), |
| 71 | + (r"(?<\u{1d49c}>.)\x1f", default()), |
| 72 | + ("a]", default()), |
| 73 | + ("a}", default()), |
| 74 | + ("]", default()), |
| 75 | + ("[]", default()), |
| 76 | + ("[a]", default()), |
| 77 | + ("[ab]", default()), |
| 78 | + ("[a-b]", default()), |
| 79 | + ("[-]", default()), |
| 80 | + ("[a-]", default()), |
| 81 | + ("[-a]", default()), |
| 82 | + ("[-a-]", default()), |
| 83 | + (r"[a\-b]", default()), |
| 84 | + (r"[-a-b]", default()), |
| 85 | + (r"[a-b-]", default()), |
| 86 | + (r"[a\-b-]", default()), |
| 87 | + (r"[\[\]\-]", default()), |
| 88 | + ("[a-z0-9]", default()), |
| 89 | + ("[a-a]", default()), |
| 90 | + (r"[\d-\D]", default()), |
| 91 | + (r"^([\ud801[\udc28-\udc4f])$", default()), |
| 92 | + (r"[a-c]]", default()), |
| 93 | + ( |
| 94 | + r"[ϗϙϛϝϟϡϣϥϧϩϫϭϯ-ϳϵϸϻ-ϼа-џѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿҁҋҍҏґғҕҗҙқҝҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎ-ӏӑӓӕӗәӛӝӟӡӣӥӧөӫӭӯӱӳӵӷӹӻӽӿԁԃԅԇԉԋԍԏԑԓԕԗԙԛԝԟԡԣա-ևᴀ-ᴫᵢ-ᵷᵹ-ᶚḁḃḅḇḉḋḍḏḑḓḕḗḙḛḝḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿṁṃṅṇṉṋṍṏṑṓṕṗṙṛṝṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿẁẃẅẇẉẋẍẏẑẓẕ-ẝẟạảấầẩẫậắằẳẵặẹẻẽếềểễệỉịọỏốồổỗộớờởỡợụủứừửữựỳỵỷỹỻỽỿ-ἇἐ-ἕἠ-ἧἰ-ἷὀ-ὅὐ-ὗὠ-ὧὰ]", |
| 95 | + default(), |
| 96 | + ), |
| 97 | + (r"[a-z0-9[.\\]]", with_unicode_sets_mode()), |
| 98 | + (r"[a&&b&&c]", with_unicode_sets_mode()), |
| 99 | + (r"[a--b--c]", with_unicode_sets_mode()), |
| 100 | + (r"[[a-z]--b--c]", with_unicode_sets_mode()), |
| 101 | + (r"[[[[[[[[[[[[[[[[[[[[[[[[a]]]]]]]]]]]]]]]]]]]]]]]]", with_unicode_sets_mode()), |
| 102 | + (r"[\q{}\q{a}\q{bc}\q{d|e|f}\q{|||}]", with_unicode_sets_mode()), |
| 103 | + (r"(?<foo>A)\k<foo>", default()), |
| 104 | + (r"(?<!a>)\k<a>", default()), |
| 105 | + (r"\k", default()), |
| 106 | + (r"\k<4>", default()), |
| 107 | + (r"\k<a>", default()), |
| 108 | + (r"(?<a>)\k<a>", default()), |
| 109 | + (r"(?<a>)\k<a>", with_unicode_mode()), |
| 110 | + (r"\1", default()), |
| 111 | + (r"\1()", default()), |
| 112 | + (r"\1()", with_unicode_mode()), |
| 113 | + (r"(?<n1>..)(?<n2>..)", default()), |
| 114 | + // TODO: ES2025 Duplicate named capturing groups |
| 115 | + // (r"(?<n1>..)|(?<n1>..)", default()), |
| 116 | + // (r"(?<year>[0-9]{4})-[0-9]{2}|[0-9]{2}-(?<year>[0-9]{4})", default()), |
| 117 | + // (r"(?:(?<a>x)|(?<a>y))\k<a>", default()), |
| 118 | + ] { |
| 119 | + let res = Parser::new(&allocator, source_text, *options).parse(); |
| 120 | + if let Err(err) = res { |
| 121 | + panic!("Failed to parse {source_text} with {options:?}\n💥 {err}"); |
| 122 | + } |
| 123 | + } |
| 124 | + } |
| 125 | + |
| 126 | + #[test] |
| 127 | + fn should_fail() { |
| 128 | + let allocator = Allocator::default(); |
| 129 | + |
| 130 | + for (source_text, options) in &[ |
| 131 | + ("a)", default()), |
| 132 | + (r"a\", default()), |
| 133 | + ("a]", with_unicode_mode()), |
| 134 | + ("a}", with_unicode_mode()), |
| 135 | + ("a|+", default()), |
| 136 | + ("a|{", with_unicode_mode()), |
| 137 | + ("a{", with_unicode_mode()), |
| 138 | + ("a{1", with_unicode_mode()), |
| 139 | + ("a{1,", with_unicode_mode()), |
| 140 | + ("a{,", with_unicode_mode()), |
| 141 | + ("x{9007199254740992}", default()), |
| 142 | + ("x{9007199254740991,9007199254740992}", default()), |
| 143 | + ("x{99999999999999999999999999999999999999999999999999}", default()), |
| 144 | + (r"\99999999999999999999999999999999999999999999999999", default()), |
| 145 | + (r"\u{FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF}", with_unicode_mode()), |
| 146 | + ("(?=a", default()), |
| 147 | + ("(?<!a", default()), |
| 148 | + (r"\c0", with_unicode_mode()), |
| 149 | + (r"\xa", with_unicode_mode()), |
| 150 | + (r"a\u", with_unicode_mode()), |
| 151 | + (r"\p{Emoji_Presentation", with_unicode_mode()), |
| 152 | + (r"\p{Script=", with_unicode_mode()), |
| 153 | + (r"\ka", with_unicode_mode()), |
| 154 | + (r"\k", with_unicode_mode()), |
| 155 | + (r"\k<", with_unicode_mode()), |
| 156 | + (r"\k<>", with_unicode_mode()), |
| 157 | + (r"\k<4>", with_unicode_mode()), |
| 158 | + (r"\k<a", with_unicode_mode()), |
| 159 | + (r"\1", with_unicode_mode()), |
| 160 | + (r"\k<a>", with_unicode_mode()), |
| 161 | + ("a(?:", default()), |
| 162 | + ("(a", default()), |
| 163 | + ("(?<a>", default()), |
| 164 | + (r"(?<a\>.)", default()), |
| 165 | + (r"(?<a\>.)", with_unicode_mode()), |
| 166 | + (r"(?<\>.)", default()), |
| 167 | + (r"(?<\>.)", with_unicode_mode()), |
| 168 | + ("(?)", default()), |
| 169 | + ("(?=a){1}", with_unicode_mode()), |
| 170 | + ("(?!a){1}", with_unicode_mode()), |
| 171 | + (r"[\d-\D]", with_unicode_mode()), |
| 172 | + ("[", default()), |
| 173 | + ("[", with_unicode_sets_mode()), |
| 174 | + ("[[", with_unicode_sets_mode()), |
| 175 | + ("[[]", with_unicode_sets_mode()), |
| 176 | + ("[z-a]", default()), |
| 177 | + (r"[a-c]]", with_unicode_mode()), |
| 178 | + ( |
| 179 | + r"^([a-zªµºß-öø-ÿāăąćĉċčďđēĕėęěĝğġģĥħĩīĭįıijĵķ-ĸĺļľŀłńņň-ʼnŋōŏőœŕŗřśŝşšţťŧũūŭůűųŵŷźżž-ƀƃƅƈƌ-ƍƒƕƙ-ƛƞơƣƥƨƪ-ƫƭưƴƶƹ-ƺƽ-ƿdžljnjǎǐǒǔǖǘǚǜ-ǝǟǡǣǥǧǩǫǭǯ-ǰdzǵǹǻǽǿȁȃȅȇȉȋȍȏȑȓȕȗșțȝȟȡȣȥȧȩȫȭȯȱȳ-ȹȼȿ-ɀɂɇɉɋɍɏ-ʓʕ-ʯͱͳͷͻ-ͽΐά-ώϐ-ϑϕ-ϗϙϛϝϟϡϣϥϧϩϫϭϯ-ϳϵϸϻ-ϼа-џѡѣѥѧѩѫѭѯѱѳѵѷѹѻѽѿҁҋҍҏґғҕҗҙқҝҟҡңҥҧҩҫҭүұҳҵҷҹһҽҿӂӄӆӈӊӌӎ-ӏӑӓӕӗәӛӝӟӡӣӥӧөӫӭӯӱӳӵӷӹӻӽӿԁԃԅԇԉԋԍԏԑԓԕԗԙԛԝԟԡԣա-ևᴀ-ᴫᵢ-ᵷᵹ-ᶚḁḃḅḇḉḋḍḏḑḓḕḗḙḛḝḟḡḣḥḧḩḫḭḯḱḳḵḷḹḻḽḿṁṃṅṇṉṋṍṏṑṓṕṗṙṛṝṟṡṣṥṧṩṫṭṯṱṳṵṷṹṻṽṿẁẃẅẇẉẋẍẏẑẓẕ-ẝẟạảấầẩẫậắằẳẵặẹẻẽếềểễệỉịọỏốồổỗộớờởỡợụủứừửữựỳỵỷỹỻỽỿ-ἇἐ-ἕἠ-ἧἰ-ἷὀ-ὅὐ-ὗὠ-ὧὰ-ώᾀ-ᾇᾐ-ᾗᾠ-ᾧᾰ-ᾴᾶ-ᾷιῂ-ῄῆ-ῇῐ-ΐῖ-ῗῠ-ῧῲ-ῴῶ-ῷⁱⁿℊℎ-ℏℓℯℴℹℼ-ℽⅆ-ⅉⅎↄⰰ-ⱞⱡⱥ-ⱦⱨⱪⱬⱱⱳ-ⱴⱶ-ⱼⲁⲃⲅⲇⲉⲋⲍⲏⲑⲓⲕⲗⲙⲛⲝⲟⲡⲣⲥⲧⲩⲫⲭⲯⲱⲳⲵⲷⲹⲻⲽⲿⳁⳃⳅⳇⳉⳋⳍⳏⳑⳓⳕⳗⳙⳛⳝⳟⳡⳣ-ⳤⴀ-ⴥꙁꙃꙅꙇꙉꙋꙍꙏꙑꙓꙕꙗꙙꙛꙝꙟꙣꙥꙧꙩꙫꙭꚁꚃꚅꚇꚉꚋꚍꚏꚑꚓꚕꚗꜣꜥꜧꜩꜫꜭꜯ-ꜱꜳꜵꜷꜹꜻꜽꜿꝁꝃꝅꝇꝉꝋꝍꝏꝑꝓꝕꝗꝙꝛꝝꝟꝡꝣꝥꝧꝩꝫꝭꝯꝱ-ꝸꝺꝼꝿꞁꞃꞅꞇꞌff-stﬓ-ﬗａ-ｚ]|\ud801[\udc28-\udc4f]|\ud835[\udc1a-\udc33\udc4e-\udc54\udc56-\udc67\udc82-\udc9b\udcb6-\udcb9\udcbb\udcbd-\udcc3\udcc5-\udccf\udcea-\udd03\udd1e-\udd37\udd52-\udd6b\udd86-\udd9f\uddba-\uddd3\uddee-\ude07\ude22-\ude3b\ude56-\ude6f\ude8a-\udea5\udec2-\udeda\udedc-\udee1\udefc-\udf14\udf16-\udf1b\udf36-\udf4e\udf50-\udf55\udf70-\udf88\udf8a-\udf8f\udfaa-\udfc2\udfc4-\udfc9\udfcb])$", |
| 180 | + default(), |
| 181 | + ), |
| 182 | + (r"[[\d-\D]]", with_unicode_sets_mode()), |
| 183 | + (r"[a&&b--c]", with_unicode_sets_mode()), |
| 184 | + (r"[a--b&&c]", with_unicode_sets_mode()), |
| 185 | + (r"[\q{]", with_unicode_sets_mode()), |
| 186 | + (r"[\q{\a}]", with_unicode_sets_mode()), |
| 187 | + // TODO: ES2025 Duplicate named capturing groups |
| 188 | + (r"(?<n>..)|(?<n>..)", default()), // This will be valid |
| 189 | + // (r"(?<a>|(?<a>))", default()), // Nested, still invalid |
| 190 | + ] { |
| 191 | + assert!( |
| 192 | + Parser::new(&allocator, source_text, *options).parse().is_err(), |
| 193 | + "{source_text} should fail to parse with {options:?}!" |
| 194 | + ); |
| 195 | + } |
| 196 | + } |
| 197 | + |
| 198 | + #[test] |
| 199 | + fn should_fail_early_errors() { |
| 200 | + let allocator = Allocator::default(); |
| 201 | + |
| 202 | + for (source_text, options, is_err) in &[ |
| 203 | + // No tests for 4,294,967,295 left parens |
| 204 | + (r"(?<n>..)(?<n>..)", default(), true), |
| 205 | + (r"a{2,1}", default(), true), |
| 206 | + (r"(?<a>)\k<n>", default(), true), |
| 207 | + (r"()\2", with_unicode_mode(), true), |
| 208 | + (r"[a-\d]", with_unicode_mode(), true), |
| 209 | + (r"[\d-z]", with_unicode_mode(), true), |
| 210 | + (r"[\d-\d]", with_unicode_mode(), true), |
| 211 | + (r"[z-a]", default(), true), |
| 212 | + (r"\u{110000}", with_unicode_mode(), true), |
| 213 | + (r"(?<\uD800\uDBFF>)", default(), true), |
| 214 | + (r"\u{0}\u{110000}", with_unicode_mode(), true), |
| 215 | + (r"(?<a\uD800\uDBFF>)", default(), true), |
| 216 | + (r"\p{Foo=Bar}", with_unicode_mode(), true), |
| 217 | + (r"\p{Foo}", with_unicode_mode(), true), |
| 218 | + (r"\p{Basic_Emoji}", with_unicode_mode(), true), |
| 219 | + (r"\P{Basic_Emoji}", with_unicode_sets_mode(), true), |
| 220 | + (r"[^\p{Basic_Emoji}]", with_unicode_sets_mode(), true), |
| 221 | + (r"[[^\p{Basic_Emoji}]]", with_unicode_sets_mode(), true), |
| 222 | + (r"[^\q{}]", with_unicode_sets_mode(), true), |
| 223 | + (r"[[^\q{}]]", with_unicode_sets_mode(), true), |
| 224 | + (r"[[^\q{ng}]]", with_unicode_sets_mode(), true), |
| 225 | + (r"[[^\q{a|}]]", with_unicode_sets_mode(), true), |
| 226 | + (r"[[^\q{ng}\q{o|k}]]", with_unicode_sets_mode(), true), |
| 227 | + (r"[[^\q{o|k}\q{ng}\q{o|k}]]", with_unicode_sets_mode(), true), |
| 228 | + (r"[[^\q{o|k}\q{o|k}\q{ng}]]", with_unicode_sets_mode(), true), |
| 229 | + (r"[[^\q{}&&\q{ng}]]", with_unicode_sets_mode(), true), |
| 230 | + (r"[[^\q{ng}&&\q{o|k}]]", with_unicode_sets_mode(), false), |
| 231 | + (r"[[^\q{ng}&&\q{o|k}&&\q{ng}]]", with_unicode_sets_mode(), false), |
| 232 | + (r"[[^\q{ng}--\q{o|k}]]", with_unicode_sets_mode(), true), |
| 233 | + (r"[[^\q{o|k}--\q{ng}]]", with_unicode_sets_mode(), false), |
| 234 | + (r"[[z-a]]", with_unicode_sets_mode(), true), |
| 235 | + (r"[[[[[^[[[[\q{ng}]]]]]]]]]", with_unicode_sets_mode(), true), |
| 236 | + (r"[^[[[[[[[[[[[[[[[[\q{ng}]]]]]]]]]]]]]]]]]", with_unicode_sets_mode(), true), |
| 237 | + ] { |
| 238 | + assert_eq!( |
| 239 | + Parser::new(&allocator, source_text, *options).parse().is_err(), |
| 240 | + *is_err, |
| 241 | + "{source_text} should early error with {options:?}!" |
| 242 | + ); |
| 243 | + } |
| 244 | + } |
| 245 | + |
| 246 | + #[test] |
| 247 | + fn should_handle_empty() { |
| 248 | + let allocator = Allocator::default(); |
| 249 | + let pattern = Parser::new(&allocator, "", default()).parse().unwrap(); |
| 250 | + |
| 251 | + assert_eq!(pattern.body.body[0].body.len(), 1); |
| 252 | + } |
| 253 | + |
| 254 | + #[test] |
| 255 | + fn should_handle_unicode() { |
| 256 | + let allocator = Allocator::default(); |
| 257 | + let source_text = "このEmoji🥹の数が変わる"; |
| 258 | + |
| 259 | + for (options, expected) in |
| 260 | + &[(default(), 15), (with_unicode_mode(), 14), (with_unicode_sets_mode(), 14)] |
| 261 | + { |
| 262 | + let pattern = Parser::new(&allocator, source_text, *options).parse().unwrap(); |
| 263 | + assert_eq!(pattern.body.body[0].body.len(), *expected); |
| 264 | + } |
| 265 | + } |
| 266 | +} |
0 commit comments