| Leo Repp | 58b9f11 | 2021-11-22 11:57:47 +0100 | [diff] [blame^] | 1 | var types = require('./types'); |
| 2 | var sets = require('./sets'); |
| 3 | |
| 4 | |
| 5 | // All of these are private and only used by randexp. |
| 6 | // It's assumed that they will always be called with the correct input. |
| 7 | |
| 8 | var CTRL = '@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^ ?'; |
| 9 | var SLSH = { '0': 0, 't': 9, 'n': 10, 'v': 11, 'f': 12, 'r': 13 }; |
| 10 | |
| 11 | /** |
| 12 | * Finds character representations in str and convert all to |
| 13 | * their respective characters |
| 14 | * |
| 15 | * @param {String} str |
| 16 | * @return {String} |
| 17 | */ |
| 18 | exports.strToChars = function(str) { |
| 19 | /* jshint maxlen: false */ |
| 20 | var chars_regex = /(\[\\b\])|(\\)?\\(?:u([A-F0-9]{4})|x([A-F0-9]{2})|(0?[0-7]{2})|c([@A-Z\[\\\]\^?])|([0tnvfr]))/g; |
| 21 | str = str.replace(chars_regex, function(s, b, lbs, a16, b16, c8, dctrl, eslsh) { |
| 22 | if (lbs) { |
| 23 | return s; |
| 24 | } |
| 25 | |
| 26 | var code = b ? 8 : |
| 27 | a16 ? parseInt(a16, 16) : |
| 28 | b16 ? parseInt(b16, 16) : |
| 29 | c8 ? parseInt(c8, 8) : |
| 30 | dctrl ? CTRL.indexOf(dctrl) : |
| 31 | SLSH[eslsh]; |
| 32 | |
| 33 | var c = String.fromCharCode(code); |
| 34 | |
| 35 | // Escape special regex characters. |
| 36 | if (/[\[\]{}\^$.|?*+()]/.test(c)) { |
| 37 | c = '\\' + c; |
| 38 | } |
| 39 | |
| 40 | return c; |
| 41 | }); |
| 42 | |
| 43 | return str; |
| 44 | }; |
| 45 | |
| 46 | |
| 47 | /** |
| 48 | * turns class into tokens |
| 49 | * reads str until it encounters a ] not preceeded by a \ |
| 50 | * |
| 51 | * @param {String} str |
| 52 | * @param {String} regexpStr |
| 53 | * @return {Array.<Array.<Object>, Number>} |
| 54 | */ |
| 55 | exports.tokenizeClass = function(str, regexpStr) { |
| 56 | /* jshint maxlen: false */ |
| 57 | var tokens = []; |
| 58 | var regexp = /\\(?:(w)|(d)|(s)|(W)|(D)|(S))|((?:(?:\\)(.)|([^\]\\]))-(?:\\)?([^\]]))|(\])|(?:\\)?(.)/g; |
| 59 | var rs, c; |
| 60 | |
| 61 | |
| 62 | while ((rs = regexp.exec(str)) != null) { |
| 63 | if (rs[1]) { |
| 64 | tokens.push(sets.words()); |
| 65 | |
| 66 | } else if (rs[2]) { |
| 67 | tokens.push(sets.ints()); |
| 68 | |
| 69 | } else if (rs[3]) { |
| 70 | tokens.push(sets.whitespace()); |
| 71 | |
| 72 | } else if (rs[4]) { |
| 73 | tokens.push(sets.notWords()); |
| 74 | |
| 75 | } else if (rs[5]) { |
| 76 | tokens.push(sets.notInts()); |
| 77 | |
| 78 | } else if (rs[6]) { |
| 79 | tokens.push(sets.notWhitespace()); |
| 80 | |
| 81 | } else if (rs[7]) { |
| 82 | tokens.push({ |
| 83 | type: types.RANGE, |
| 84 | from: (rs[8] || rs[9]).charCodeAt(0), |
| 85 | to: rs[10].charCodeAt(0), |
| 86 | }); |
| 87 | |
| 88 | } else if (c = rs[12]) { |
| 89 | tokens.push({ |
| 90 | type: types.CHAR, |
| 91 | value: c.charCodeAt(0), |
| 92 | }); |
| 93 | |
| 94 | } else { |
| 95 | return [tokens, regexp.lastIndex]; |
| 96 | } |
| 97 | } |
| 98 | |
| 99 | exports.error(regexpStr, 'Unterminated character class'); |
| 100 | }; |
| 101 | |
| 102 | |
| 103 | /** |
| 104 | * Shortcut to throw errors. |
| 105 | * |
| 106 | * @param {String} regexp |
| 107 | * @param {String} msg |
| 108 | */ |
| 109 | exports.error = function(regexp, msg) { |
| 110 | throw new SyntaxError('Invalid regular expression: /' + regexp + '/: ' + msg); |
| 111 | }; |