1 |
|
2 | (function() {
|
3 | var BOM, BOOL, CALLABLE, CODE, COFFEE_ALIASES, COFFEE_ALIAS_MAP, COFFEE_KEYWORDS, COMMENT, COMPARE, COMPOUND_ASSIGN, HERECOMMENT_ILLEGAL, HEREDOC_DOUBLE, HEREDOC_INDENT, HEREDOC_SINGLE, HEREGEX, HEREGEX_OMIT, IDENTIFIER, INDENTABLE_CLOSERS, INDEXABLE, INVALID_ESCAPE, INVERSES, JSTOKEN, JS_FORBIDDEN, JS_KEYWORDS, LEADING_BLANK_LINE, LINE_BREAK, LINE_CONTINUER, LOGIC, Lexer, MATH, MULTI_DENT, NOT_REGEX, NUMBER, OPERATOR, POSSIBLY_DIVISION, REGEX, REGEX_FLAGS, REGEX_ILLEGAL, RELATION, RESERVED, Rewriter, SHIFT, SIMPLE_STRING_OMIT, STRICT_PROSCRIBED, STRING_DOUBLE, STRING_OMIT, STRING_SINGLE, STRING_START, TRAILING_BLANK_LINE, TRAILING_SPACES, UNARY, UNARY_MATH, VALID_FLAGS, WHITESPACE, compact, count, invertLiterate, key, locationDataToString, ref, ref1, repeat, starts, throwSyntaxError,
|
4 | indexOf = [].indexOf || function(item) { for (var i = 0, l = this.length; i < l; i++) { if (i in this && this[i] === item) return i; } return -1; };
|
5 |
|
6 | ref = require('./rewriter'), Rewriter = ref.Rewriter, INVERSES = ref.INVERSES;
|
7 |
|
8 | ref1 = require('./helpers'), count = ref1.count, starts = ref1.starts, compact = ref1.compact, repeat = ref1.repeat, invertLiterate = ref1.invertLiterate, locationDataToString = ref1.locationDataToString, throwSyntaxError = ref1.throwSyntaxError;
|
9 |
|
10 | exports.Lexer = Lexer = (function() {
|
11 | function Lexer() {}
|
12 |
|
13 | Lexer.prototype.tokenize = function(code, opts) {
|
14 | var consumed, end, i, ref2;
|
15 | if (opts == null) {
|
16 | opts = {};
|
17 | }
|
18 | this.literate = opts.literate;
|
19 | this.indent = 0;
|
20 | this.baseIndent = 0;
|
21 | this.indebt = 0;
|
22 | this.outdebt = 0;
|
23 | this.indents = [];
|
24 | this.ends = [];
|
25 | this.tokens = [];
|
26 | this.chunkLine = opts.line || 0;
|
27 | this.chunkColumn = opts.column || 0;
|
28 | code = this.clean(code);
|
29 | i = 0;
|
30 | while (this.chunk = code.slice(i)) {
|
31 | consumed = this.identifierToken() || this.commentToken() || this.whitespaceToken() || this.lineToken() || this.stringToken() || this.numberToken() || this.regexToken() || this.jsToken() || this.literalToken();
|
32 | ref2 = this.getLineAndColumnFromChunk(consumed), this.chunkLine = ref2[0], this.chunkColumn = ref2[1];
|
33 | i += consumed;
|
34 | if (opts.untilBalanced && this.ends.length === 0) {
|
35 | return {
|
36 | tokens: this.tokens,
|
37 | index: i
|
38 | };
|
39 | }
|
40 | }
|
41 | this.closeIndentation();
|
42 | if (end = this.ends.pop()) {
|
43 | this.error("missing " + end.tag, end.origin[2]);
|
44 | }
|
45 | if (opts.rewrite === false) {
|
46 | return this.tokens;
|
47 | }
|
48 | return (new Rewriter).rewrite(this.tokens);
|
49 | };
|
50 |
|
51 | Lexer.prototype.clean = function(code) {
|
52 | if (code.charCodeAt(0) === BOM) {
|
53 | code = code.slice(1);
|
54 | }
|
55 | code = code.replace(/\r/g, '').replace(TRAILING_SPACES, '');
|
56 | if (WHITESPACE.test(code)) {
|
57 | code = "\n" + code;
|
58 | this.chunkLine--;
|
59 | }
|
60 | if (this.literate) {
|
61 | code = invertLiterate(code);
|
62 | }
|
63 | return code;
|
64 | };
|
65 |
|
66 | Lexer.prototype.identifierToken = function() {
|
67 | var alias, colon, colonOffset, forcedIdentifier, id, idLength, input, match, poppedToken, prev, ref2, ref3, ref4, ref5, tag, tagToken;
|
68 | if (!(match = IDENTIFIER.exec(this.chunk))) {
|
69 | return 0;
|
70 | }
|
71 | input = match[0], id = match[1], colon = match[2];
|
72 | idLength = id.length;
|
73 | poppedToken = void 0;
|
74 | if (id === 'own' && this.tag() === 'FOR') {
|
75 | this.token('OWN', id);
|
76 | return id.length;
|
77 | }
|
78 | if (id === 'from' && this.tag() === 'YIELD') {
|
79 | this.token('FROM', id);
|
80 | return id.length;
|
81 | }
|
82 | ref2 = this.tokens, prev = ref2[ref2.length - 1];
|
83 | forcedIdentifier = colon || (prev != null) && (((ref3 = prev[0]) === '.' || ref3 === '?.' || ref3 === '::' || ref3 === '?::') || !prev.spaced && prev[0] === '@');
|
84 | tag = 'IDENTIFIER';
|
85 | if (!forcedIdentifier && (indexOf.call(JS_KEYWORDS, id) >= 0 || indexOf.call(COFFEE_KEYWORDS, id) >= 0)) {
|
86 | tag = id.toUpperCase();
|
87 | if (tag === 'WHEN' && (ref4 = this.tag(), indexOf.call(LINE_BREAK, ref4) >= 0)) {
|
88 | tag = 'LEADING_WHEN';
|
89 | } else if (tag === 'FOR') {
|
90 | this.seenFor = true;
|
91 | } else if (tag === 'UNLESS') {
|
92 | tag = 'IF';
|
93 | } else if (indexOf.call(UNARY, tag) >= 0) {
|
94 | tag = 'UNARY';
|
95 | } else if (indexOf.call(RELATION, tag) >= 0) {
|
96 | if (tag !== 'INSTANCEOF' && this.seenFor) {
|
97 | tag = 'FOR' + tag;
|
98 | this.seenFor = false;
|
99 | } else {
|
100 | tag = 'RELATION';
|
101 | if (this.value() === '!') {
|
102 | poppedToken = this.tokens.pop();
|
103 | id = '!' + id;
|
104 | }
|
105 | }
|
106 | }
|
107 | }
|
108 | if (indexOf.call(JS_FORBIDDEN, id) >= 0) {
|
109 | if (forcedIdentifier) {
|
110 | tag = 'IDENTIFIER';
|
111 | id = new String(id);
|
112 | id.reserved = true;
|
113 | } else if (indexOf.call(RESERVED, id) >= 0) {
|
114 | this.error("reserved word '" + id + "'", {
|
115 | length: id.length
|
116 | });
|
117 | }
|
118 | }
|
119 | if (!forcedIdentifier) {
|
120 | if (indexOf.call(COFFEE_ALIASES, id) >= 0) {
|
121 | alias = id;
|
122 | id = COFFEE_ALIAS_MAP[id];
|
123 | }
|
124 | tag = (function() {
|
125 | switch (id) {
|
126 | case '!':
|
127 | return 'UNARY';
|
128 | case '==':
|
129 | case '!=':
|
130 | return 'COMPARE';
|
131 | case '&&':
|
132 | case '||':
|
133 | return 'LOGIC';
|
134 | case 'true':
|
135 | case 'false':
|
136 | return 'BOOL';
|
137 | case 'break':
|
138 | case 'continue':
|
139 | return 'STATEMENT';
|
140 | default:
|
141 | return tag;
|
142 | }
|
143 | })();
|
144 | }
|
145 | tagToken = this.token(tag, id, 0, idLength);
|
146 | if (alias) {
|
147 | tagToken.origin = [tag, alias, tagToken[2]];
|
148 | }
|
149 | tagToken.variable = !forcedIdentifier;
|
150 | if (poppedToken) {
|
151 | ref5 = [poppedToken[2].first_line, poppedToken[2].first_column], tagToken[2].first_line = ref5[0], tagToken[2].first_column = ref5[1];
|
152 | }
|
153 | if (colon) {
|
154 | colonOffset = input.lastIndexOf(':');
|
155 | this.token(':', ':', colonOffset, colon.length);
|
156 | }
|
157 | return input.length;
|
158 | };
|
159 |
|
160 | Lexer.prototype.numberToken = function() {
|
161 | var binaryLiteral, lexedLength, match, number, octalLiteral;
|
162 | if (!(match = NUMBER.exec(this.chunk))) {
|
163 | return 0;
|
164 | }
|
165 | number = match[0];
|
166 | lexedLength = number.length;
|
167 | if (/^0[BOX]/.test(number)) {
|
168 | this.error("radix prefix in '" + number + "' must be lowercase", {
|
169 | offset: 1
|
170 | });
|
171 | } else if (/E/.test(number) && !/^0x/.test(number)) {
|
172 | this.error("exponential notation in '" + number + "' must be indicated with a lowercase 'e'", {
|
173 | offset: number.indexOf('E')
|
174 | });
|
175 | } else if (/^0\d*[89]/.test(number)) {
|
176 | this.error("decimal literal '" + number + "' must not be prefixed with '0'", {
|
177 | length: lexedLength
|
178 | });
|
179 | } else if (/^0\d+/.test(number)) {
|
180 | this.error("octal literal '" + number + "' must be prefixed with '0o'", {
|
181 | length: lexedLength
|
182 | });
|
183 | }
|
184 | if (octalLiteral = /^0o([0-7]+)/.exec(number)) {
|
185 | number = '0x' + parseInt(octalLiteral[1], 8).toString(16);
|
186 | }
|
187 | if (binaryLiteral = /^0b([01]+)/.exec(number)) {
|
188 | number = '0x' + parseInt(binaryLiteral[1], 2).toString(16);
|
189 | }
|
190 | this.token('NUMBER', number, 0, lexedLength);
|
191 | return lexedLength;
|
192 | };
|
193 |
|
194 | Lexer.prototype.stringToken = function() {
|
195 | var $, attempt, delimiter, doc, end, heredoc, i, indent, indentRegex, match, quote, ref2, ref3, regex, token, tokens;
|
196 | quote = (STRING_START.exec(this.chunk) || [])[0];
|
197 | if (!quote) {
|
198 | return 0;
|
199 | }
|
200 | regex = (function() {
|
201 | switch (quote) {
|
202 | case "'":
|
203 | return STRING_SINGLE;
|
204 | case '"':
|
205 | return STRING_DOUBLE;
|
206 | case "'''":
|
207 | return HEREDOC_SINGLE;
|
208 | case '"""':
|
209 | return HEREDOC_DOUBLE;
|
210 | }
|
211 | })();
|
212 | heredoc = quote.length === 3;
|
213 | ref2 = this.matchWithInterpolations(regex, quote), tokens = ref2.tokens, end = ref2.index;
|
214 | $ = tokens.length - 1;
|
215 | delimiter = quote.charAt(0);
|
216 | if (heredoc) {
|
217 | indent = null;
|
218 | doc = ((function() {
|
219 | var j, len, results;
|
220 | results = [];
|
221 | for (i = j = 0, len = tokens.length; j < len; i = ++j) {
|
222 | token = tokens[i];
|
223 | if (token[0] === 'NEOSTRING') {
|
224 | results.push(token[1]);
|
225 | }
|
226 | }
|
227 | return results;
|
228 | })()).join('#{}');
|
229 | while (match = HEREDOC_INDENT.exec(doc)) {
|
230 | attempt = match[1];
|
231 | if (indent === null || (0 < (ref3 = attempt.length) && ref3 < indent.length)) {
|
232 | indent = attempt;
|
233 | }
|
234 | }
|
235 | if (indent) {
|
236 | indentRegex = RegExp("^" + indent, "gm");
|
237 | }
|
238 | this.mergeInterpolationTokens(tokens, {
|
239 | delimiter: delimiter
|
240 | }, (function(_this) {
|
241 | return function(value, i) {
|
242 | value = _this.formatString(value);
|
243 | if (i === 0) {
|
244 | value = value.replace(LEADING_BLANK_LINE, '');
|
245 | }
|
246 | if (i === $) {
|
247 | value = value.replace(TRAILING_BLANK_LINE, '');
|
248 | }
|
249 | if (indentRegex) {
|
250 | value = value.replace(indentRegex, '');
|
251 | }
|
252 | return value;
|
253 | };
|
254 | })(this));
|
255 | } else {
|
256 | this.mergeInterpolationTokens(tokens, {
|
257 | delimiter: delimiter
|
258 | }, (function(_this) {
|
259 | return function(value, i) {
|
260 | value = _this.formatString(value);
|
261 | value = value.replace(SIMPLE_STRING_OMIT, function(match, offset) {
|
262 | if ((i === 0 && offset === 0) || (i === $ && offset + match.length === value.length)) {
|
263 | return '';
|
264 | } else {
|
265 | return ' ';
|
266 | }
|
267 | });
|
268 | return value;
|
269 | };
|
270 | })(this));
|
271 | }
|
272 | return end;
|
273 | };
|
274 |
|
275 | Lexer.prototype.commentToken = function() {
|
276 | var comment, here, match;
|
277 | if (!(match = this.chunk.match(COMMENT))) {
|
278 | return 0;
|
279 | }
|
280 | comment = match[0], here = match[1];
|
281 | if (here) {
|
282 | if (match = HERECOMMENT_ILLEGAL.exec(comment)) {
|
283 | this.error("block comments cannot contain " + match[0], {
|
284 | offset: match.index,
|
285 | length: match[0].length
|
286 | });
|
287 | }
|
288 | if (here.indexOf('\n') >= 0) {
|
289 | here = here.replace(RegExp("\\n" + (repeat(' ', this.indent)), "g"), '\n');
|
290 | }
|
291 | this.token('HERECOMMENT', here, 0, comment.length);
|
292 | }
|
293 | return comment.length;
|
294 | };
|
295 |
|
296 | Lexer.prototype.jsToken = function() {
|
297 | var match, script;
|
298 | if (!(this.chunk.charAt(0) === '`' && (match = JSTOKEN.exec(this.chunk)))) {
|
299 | return 0;
|
300 | }
|
301 | this.token('JS', (script = match[0]).slice(1, -1), 0, script.length);
|
302 | return script.length;
|
303 | };
|
304 |
|
305 | Lexer.prototype.regexToken = function() {
|
306 | var body, closed, end, flags, index, match, origin, prev, ref2, ref3, ref4, regex, tokens;
|
307 | switch (false) {
|
308 | case !(match = REGEX_ILLEGAL.exec(this.chunk)):
|
309 | this.error("regular expressions cannot begin with " + match[2], {
|
310 | offset: match.index + match[1].length
|
311 | });
|
312 | break;
|
313 | case !(match = this.matchWithInterpolations(HEREGEX, '///')):
|
314 | tokens = match.tokens, index = match.index;
|
315 | break;
|
316 | case !(match = REGEX.exec(this.chunk)):
|
317 | regex = match[0], body = match[1], closed = match[2];
|
318 | this.validateEscapes(body, {
|
319 | isRegex: true,
|
320 | offsetInChunk: 1
|
321 | });
|
322 | index = regex.length;
|
323 | ref2 = this.tokens, prev = ref2[ref2.length - 1];
|
324 | if (prev) {
|
325 | if (prev.spaced && (ref3 = prev[0], indexOf.call(CALLABLE, ref3) >= 0)) {
|
326 | if (!closed || POSSIBLY_DIVISION.test(regex)) {
|
327 | return 0;
|
328 | }
|
329 | } else if (ref4 = prev[0], indexOf.call(NOT_REGEX, ref4) >= 0) {
|
330 | return 0;
|
331 | }
|
332 | }
|
333 | if (!closed) {
|
334 | this.error('missing / (unclosed regex)');
|
335 | }
|
336 | break;
|
337 | default:
|
338 | return 0;
|
339 | }
|
340 | flags = REGEX_FLAGS.exec(this.chunk.slice(index))[0];
|
341 | end = index + flags.length;
|
342 | origin = this.makeToken('REGEX', null, 0, end);
|
343 | switch (false) {
|
344 | case !!VALID_FLAGS.test(flags):
|
345 | this.error("invalid regular expression flags " + flags, {
|
346 | offset: index,
|
347 | length: flags.length
|
348 | });
|
349 | break;
|
350 | case !(regex || tokens.length === 1):
|
351 | if (body == null) {
|
352 | body = this.formatHeregex(tokens[0][1]);
|
353 | }
|
354 | this.token('REGEX', "" + (this.makeDelimitedLiteral(body, {
|
355 | delimiter: '/'
|
356 | })) + flags, 0, end, origin);
|
357 | break;
|
358 | default:
|
359 | this.token('REGEX_START', '(', 0, 0, origin);
|
360 | this.token('IDENTIFIER', 'RegExp', 0, 0);
|
361 | this.token('CALL_START', '(', 0, 0);
|
362 | this.mergeInterpolationTokens(tokens, {
|
363 | delimiter: '"',
|
364 | double: true
|
365 | }, this.formatHeregex);
|
366 | if (flags) {
|
367 | this.token(',', ',', index, 0);
|
368 | this.token('STRING', '"' + flags + '"', index, flags.length);
|
369 | }
|
370 | this.token(')', ')', end, 0);
|
371 | this.token('REGEX_END', ')', end, 0);
|
372 | }
|
373 | return end;
|
374 | };
|
375 |
|
376 | Lexer.prototype.lineToken = function() {
|
377 | var diff, indent, match, noNewlines, size;
|
378 | if (!(match = MULTI_DENT.exec(this.chunk))) {
|
379 | return 0;
|
380 | }
|
381 | indent = match[0];
|
382 | this.seenFor = false;
|
383 | size = indent.length - 1 - indent.lastIndexOf('\n');
|
384 | noNewlines = this.unfinished();
|
385 | if (size - this.indebt === this.indent) {
|
386 | if (noNewlines) {
|
387 | this.suppressNewlines();
|
388 | } else {
|
389 | this.newlineToken(0);
|
390 | }
|
391 | return indent.length;
|
392 | }
|
393 | if (size > this.indent) {
|
394 | if (noNewlines) {
|
395 | this.indebt = size - this.indent;
|
396 | this.suppressNewlines();
|
397 | return indent.length;
|
398 | }
|
399 | if (!this.tokens.length) {
|
400 | this.baseIndent = this.indent = size;
|
401 | return indent.length;
|
402 | }
|
403 | diff = size - this.indent + this.outdebt;
|
404 | this.token('INDENT', diff, indent.length - size, size);
|
405 | this.indents.push(diff);
|
406 | this.ends.push({
|
407 | tag: 'OUTDENT'
|
408 | });
|
409 | this.outdebt = this.indebt = 0;
|
410 | this.indent = size;
|
411 | } else if (size < this.baseIndent) {
|
412 | this.error('missing indentation', {
|
413 | offset: indent.length
|
414 | });
|
415 | } else {
|
416 | this.indebt = 0;
|
417 | this.outdentToken(this.indent - size, noNewlines, indent.length);
|
418 | }
|
419 | return indent.length;
|
420 | };
|
421 |
|
422 | Lexer.prototype.outdentToken = function(moveOut, noNewlines, outdentLength) {
|
423 | var decreasedIndent, dent, lastIndent, ref2;
|
424 | decreasedIndent = this.indent - moveOut;
|
425 | while (moveOut > 0) {
|
426 | lastIndent = this.indents[this.indents.length - 1];
|
427 | if (!lastIndent) {
|
428 | moveOut = 0;
|
429 | } else if (lastIndent === this.outdebt) {
|
430 | moveOut -= this.outdebt;
|
431 | this.outdebt = 0;
|
432 | } else if (lastIndent < this.outdebt) {
|
433 | this.outdebt -= lastIndent;
|
434 | moveOut -= lastIndent;
|
435 | } else {
|
436 | dent = this.indents.pop() + this.outdebt;
|
437 | if (outdentLength && (ref2 = this.chunk[outdentLength], indexOf.call(INDENTABLE_CLOSERS, ref2) >= 0)) {
|
438 | decreasedIndent -= dent - moveOut;
|
439 | moveOut = dent;
|
440 | }
|
441 | this.outdebt = 0;
|
442 | this.pair('OUTDENT');
|
443 | this.token('OUTDENT', moveOut, 0, outdentLength);
|
444 | moveOut -= dent;
|
445 | }
|
446 | }
|
447 | if (dent) {
|
448 | this.outdebt -= moveOut;
|
449 | }
|
450 | while (this.value() === ';') {
|
451 | this.tokens.pop();
|
452 | }
|
453 | if (!(this.tag() === 'TERMINATOR' || noNewlines)) {
|
454 | this.token('TERMINATOR', '\n', outdentLength, 0);
|
455 | }
|
456 | this.indent = decreasedIndent;
|
457 | return this;
|
458 | };
|
459 |
|
460 | Lexer.prototype.whitespaceToken = function() {
|
461 | var match, nline, prev, ref2;
|
462 | if (!((match = WHITESPACE.exec(this.chunk)) || (nline = this.chunk.charAt(0) === '\n'))) {
|
463 | return 0;
|
464 | }
|
465 | ref2 = this.tokens, prev = ref2[ref2.length - 1];
|
466 | if (prev) {
|
467 | prev[match ? 'spaced' : 'newLine'] = true;
|
468 | }
|
469 | if (match) {
|
470 | return match[0].length;
|
471 | } else {
|
472 | return 0;
|
473 | }
|
474 | };
|
475 |
|
476 | Lexer.prototype.newlineToken = function(offset) {
|
477 | while (this.value() === ';') {
|
478 | this.tokens.pop();
|
479 | }
|
480 | if (this.tag() !== 'TERMINATOR') {
|
481 | this.token('TERMINATOR', '\n', offset, 0);
|
482 | }
|
483 | return this;
|
484 | };
|
485 |
|
486 | Lexer.prototype.suppressNewlines = function() {
|
487 | if (this.value() === '\\') {
|
488 | this.tokens.pop();
|
489 | }
|
490 | return this;
|
491 | };
|
492 |
|
493 | Lexer.prototype.literalToken = function() {
|
494 | var match, prev, ref2, ref3, ref4, ref5, ref6, tag, token, value;
|
495 | if (match = OPERATOR.exec(this.chunk)) {
|
496 | value = match[0];
|
497 | if (CODE.test(value)) {
|
498 | this.tagParameters();
|
499 | }
|
500 | } else {
|
501 | value = this.chunk.charAt(0);
|
502 | }
|
503 | tag = value;
|
504 | ref2 = this.tokens, prev = ref2[ref2.length - 1];
|
505 | if (value === '=' && prev) {
|
506 | if (!prev[1].reserved && (ref3 = prev[1], indexOf.call(JS_FORBIDDEN, ref3) >= 0)) {
|
507 | if (prev.origin) {
|
508 | prev = prev.origin;
|
509 | }
|
510 | this.error("reserved word '" + prev[1] + "' can't be assigned", prev[2]);
|
511 | }
|
512 | if ((ref4 = prev[1]) === '||' || ref4 === '&&') {
|
513 | prev[0] = 'COMPOUND_ASSIGN';
|
514 | prev[1] += '=';
|
515 | return value.length;
|
516 | }
|
517 | }
|
518 | if (value === ';') {
|
519 | this.seenFor = false;
|
520 | tag = 'TERMINATOR';
|
521 | } else if (indexOf.call(MATH, value) >= 0) {
|
522 | tag = 'MATH';
|
523 | } else if (indexOf.call(COMPARE, value) >= 0) {
|
524 | tag = 'COMPARE';
|
525 | } else if (indexOf.call(COMPOUND_ASSIGN, value) >= 0) {
|
526 | tag = 'COMPOUND_ASSIGN';
|
527 | } else if (indexOf.call(UNARY, value) >= 0) {
|
528 | tag = 'UNARY';
|
529 | } else if (indexOf.call(UNARY_MATH, value) >= 0) {
|
530 | tag = 'UNARY_MATH';
|
531 | } else if (indexOf.call(SHIFT, value) >= 0) {
|
532 | tag = 'SHIFT';
|
533 | } else if (indexOf.call(LOGIC, value) >= 0 || value === '?' && (prev != null ? prev.spaced : void 0)) {
|
534 | tag = 'LOGIC';
|
535 | } else if (prev && !prev.spaced) {
|
536 | if (value === '(' && (ref5 = prev[0], indexOf.call(CALLABLE, ref5) >= 0)) {
|
537 | if (prev[0] === '?') {
|
538 | prev[0] = 'FUNC_EXIST';
|
539 | }
|
540 | tag = 'CALL_START';
|
541 | } else if (value === '[' && (ref6 = prev[0], indexOf.call(INDEXABLE, ref6) >= 0)) {
|
542 | tag = 'INDEX_START';
|
543 | switch (prev[0]) {
|
544 | case '?':
|
545 | prev[0] = 'INDEX_SOAK';
|
546 | }
|
547 | }
|
548 | }
|
549 | token = this.makeToken(tag, value);
|
550 | switch (value) {
|
551 | case '(':
|
552 | case '{':
|
553 | case '[':
|
554 | this.ends.push({
|
555 | tag: INVERSES[value],
|
556 | origin: token
|
557 | });
|
558 | break;
|
559 | case ')':
|
560 | case '}':
|
561 | case ']':
|
562 | this.pair(value);
|
563 | }
|
564 | this.tokens.push(token);
|
565 | return value.length;
|
566 | };
|
567 |
|
568 | Lexer.prototype.tagParameters = function() {
|
569 | var i, stack, tok, tokens;
|
570 | if (this.tag() !== ')') {
|
571 | return this;
|
572 | }
|
573 | stack = [];
|
574 | tokens = this.tokens;
|
575 | i = tokens.length;
|
576 | tokens[--i][0] = 'PARAM_END';
|
577 | while (tok = tokens[--i]) {
|
578 | switch (tok[0]) {
|
579 | case ')':
|
580 | stack.push(tok);
|
581 | break;
|
582 | case '(':
|
583 | case 'CALL_START':
|
584 | if (stack.length) {
|
585 | stack.pop();
|
586 | } else if (tok[0] === '(') {
|
587 | tok[0] = 'PARAM_START';
|
588 | return this;
|
589 | } else {
|
590 | return this;
|
591 | }
|
592 | }
|
593 | }
|
594 | return this;
|
595 | };
|
596 |
|
597 | Lexer.prototype.closeIndentation = function() {
|
598 | return this.outdentToken(this.indent);
|
599 | };
|
600 |
|
601 | Lexer.prototype.matchWithInterpolations = function(regex, delimiter) {
|
602 | var close, column, firstToken, index, lastToken, line, nested, offsetInChunk, open, ref2, ref3, ref4, str, strPart, tokens;
|
603 | tokens = [];
|
604 | offsetInChunk = delimiter.length;
|
605 | if (this.chunk.slice(0, offsetInChunk) !== delimiter) {
|
606 | return null;
|
607 | }
|
608 | str = this.chunk.slice(offsetInChunk);
|
609 | while (true) {
|
610 | strPart = regex.exec(str)[0];
|
611 | this.validateEscapes(strPart, {
|
612 | isRegex: delimiter.charAt(0) === '/',
|
613 | offsetInChunk: offsetInChunk
|
614 | });
|
615 | tokens.push(this.makeToken('NEOSTRING', strPart, offsetInChunk));
|
616 | str = str.slice(strPart.length);
|
617 | offsetInChunk += strPart.length;
|
618 | if (str.slice(0, 2) !== '#{') {
|
619 | break;
|
620 | }
|
621 | ref2 = this.getLineAndColumnFromChunk(offsetInChunk + 1), line = ref2[0], column = ref2[1];
|
622 | ref3 = new Lexer().tokenize(str.slice(1), {
|
623 | line: line,
|
624 | column: column,
|
625 | untilBalanced: true
|
626 | }), nested = ref3.tokens, index = ref3.index;
|
627 | index += 1;
|
628 | open = nested[0], close = nested[nested.length - 1];
|
629 | open[0] = open[1] = '(';
|
630 | close[0] = close[1] = ')';
|
631 | close.origin = ['', 'end of interpolation', close[2]];
|
632 | if (((ref4 = nested[1]) != null ? ref4[0] : void 0) === 'TERMINATOR') {
|
633 | nested.splice(1, 1);
|
634 | }
|
635 | tokens.push(['TOKENS', nested]);
|
636 | str = str.slice(index);
|
637 | offsetInChunk += index;
|
638 | }
|
639 | if (str.slice(0, delimiter.length) !== delimiter) {
|
640 | this.error("missing " + delimiter, {
|
641 | length: delimiter.length
|
642 | });
|
643 | }
|
644 | firstToken = tokens[0], lastToken = tokens[tokens.length - 1];
|
645 | firstToken[2].first_column -= delimiter.length;
|
646 | lastToken[2].last_column += delimiter.length;
|
647 | if (lastToken[1].length === 0) {
|
648 | lastToken[2].last_column -= 1;
|
649 | }
|
650 | return {
|
651 | tokens: tokens,
|
652 | index: offsetInChunk + delimiter.length
|
653 | };
|
654 | };
|
655 |
|
656 | Lexer.prototype.mergeInterpolationTokens = function(tokens, options, fn) {
|
657 | var converted, firstEmptyStringIndex, firstIndex, i, j, lastToken, len, locationToken, lparen, plusToken, ref2, rparen, tag, token, tokensToPush, value;
|
658 | if (tokens.length > 1) {
|
659 | lparen = this.token('STRING_START', '(', 0, 0);
|
660 | }
|
661 | firstIndex = this.tokens.length;
|
662 | for (i = j = 0, len = tokens.length; j < len; i = ++j) {
|
663 | token = tokens[i];
|
664 | tag = token[0], value = token[1];
|
665 | switch (tag) {
|
666 | case 'TOKENS':
|
667 | if (value.length === 2) {
|
668 | continue;
|
669 | }
|
670 | locationToken = value[0];
|
671 | tokensToPush = value;
|
672 | break;
|
673 | case 'NEOSTRING':
|
674 | converted = fn(token[1], i);
|
675 | if (converted.length === 0) {
|
676 | if (i === 0) {
|
677 | firstEmptyStringIndex = this.tokens.length;
|
678 | } else {
|
679 | continue;
|
680 | }
|
681 | }
|
682 | if (i === 2 && (firstEmptyStringIndex != null)) {
|
683 | this.tokens.splice(firstEmptyStringIndex, 2);
|
684 | }
|
685 | token[0] = 'STRING';
|
686 | token[1] = this.makeDelimitedLiteral(converted, options);
|
687 | locationToken = token;
|
688 | tokensToPush = [token];
|
689 | }
|
690 | if (this.tokens.length > firstIndex) {
|
691 | plusToken = this.token('+', '+');
|
692 | plusToken[2] = {
|
693 | first_line: locationToken[2].first_line,
|
694 | first_column: locationToken[2].first_column,
|
695 | last_line: locationToken[2].first_line,
|
696 | last_column: locationToken[2].first_column
|
697 | };
|
698 | }
|
699 | (ref2 = this.tokens).push.apply(ref2, tokensToPush);
|
700 | }
|
701 | if (lparen) {
|
702 | lastToken = tokens[tokens.length - 1];
|
703 | lparen.origin = [
|
704 | 'STRING', null, {
|
705 | first_line: lparen[2].first_line,
|
706 | first_column: lparen[2].first_column,
|
707 | last_line: lastToken[2].last_line,
|
708 | last_column: lastToken[2].last_column
|
709 | }
|
710 | ];
|
711 | rparen = this.token('STRING_END', ')');
|
712 | return rparen[2] = {
|
713 | first_line: lastToken[2].last_line,
|
714 | first_column: lastToken[2].last_column,
|
715 | last_line: lastToken[2].last_line,
|
716 | last_column: lastToken[2].last_column
|
717 | };
|
718 | }
|
719 | };
|
720 |
|
721 | Lexer.prototype.pair = function(tag) {
|
722 | var lastIndent, prev, ref2, ref3, wanted;
|
723 | ref2 = this.ends, prev = ref2[ref2.length - 1];
|
724 | if (tag !== (wanted = prev != null ? prev.tag : void 0)) {
|
725 | if ('OUTDENT' !== wanted) {
|
726 | this.error("unmatched " + tag);
|
727 | }
|
728 | ref3 = this.indents, lastIndent = ref3[ref3.length - 1];
|
729 | this.outdentToken(lastIndent, true);
|
730 | return this.pair(tag);
|
731 | }
|
732 | return this.ends.pop();
|
733 | };
|
734 |
|
735 | Lexer.prototype.getLineAndColumnFromChunk = function(offset) {
|
736 | var column, lastLine, lineCount, ref2, string;
|
737 | if (offset === 0) {
|
738 | return [this.chunkLine, this.chunkColumn];
|
739 | }
|
740 | if (offset >= this.chunk.length) {
|
741 | string = this.chunk;
|
742 | } else {
|
743 | string = this.chunk.slice(0, +(offset - 1) + 1 || 9e9);
|
744 | }
|
745 | lineCount = count(string, '\n');
|
746 | column = this.chunkColumn;
|
747 | if (lineCount > 0) {
|
748 | ref2 = string.split('\n'), lastLine = ref2[ref2.length - 1];
|
749 | column = lastLine.length;
|
750 | } else {
|
751 | column += string.length;
|
752 | }
|
753 | return [this.chunkLine + lineCount, column];
|
754 | };
|
755 |
|
756 | Lexer.prototype.makeToken = function(tag, value, offsetInChunk, length) {
|
757 | var lastCharacter, locationData, ref2, ref3, token;
|
758 | if (offsetInChunk == null) {
|
759 | offsetInChunk = 0;
|
760 | }
|
761 | if (length == null) {
|
762 | length = value.length;
|
763 | }
|
764 | locationData = {};
|
765 | ref2 = this.getLineAndColumnFromChunk(offsetInChunk), locationData.first_line = ref2[0], locationData.first_column = ref2[1];
|
766 | lastCharacter = Math.max(0, length - 1);
|
767 | ref3 = this.getLineAndColumnFromChunk(offsetInChunk + lastCharacter), locationData.last_line = ref3[0], locationData.last_column = ref3[1];
|
768 | token = [tag, value, locationData];
|
769 | return token;
|
770 | };
|
771 |
|
772 | Lexer.prototype.token = function(tag, value, offsetInChunk, length, origin) {
|
773 | var token;
|
774 | token = this.makeToken(tag, value, offsetInChunk, length);
|
775 | if (origin) {
|
776 | token.origin = origin;
|
777 | }
|
778 | this.tokens.push(token);
|
779 | return token;
|
780 | };
|
781 |
|
782 | Lexer.prototype.tag = function() {
|
783 | var ref2, token;
|
784 | ref2 = this.tokens, token = ref2[ref2.length - 1];
|
785 | return token != null ? token[0] : void 0;
|
786 | };
|
787 |
|
788 | Lexer.prototype.value = function() {
|
789 | var ref2, token;
|
790 | ref2 = this.tokens, token = ref2[ref2.length - 1];
|
791 | return token != null ? token[1] : void 0;
|
792 | };
|
793 |
|
794 | Lexer.prototype.unfinished = function() {
|
795 | var ref2;
|
796 | return LINE_CONTINUER.test(this.chunk) || ((ref2 = this.tag()) === '\\' || ref2 === '.' || ref2 === '?.' || ref2 === '?::' || ref2 === 'UNARY' || ref2 === 'MATH' || ref2 === 'UNARY_MATH' || ref2 === '+' || ref2 === '-' || ref2 === 'YIELD' || ref2 === '**' || ref2 === 'SHIFT' || ref2 === 'RELATION' || ref2 === 'COMPARE' || ref2 === 'LOGIC' || ref2 === 'THROW' || ref2 === 'EXTENDS');
|
797 | };
|
798 |
|
799 | Lexer.prototype.formatString = function(str) {
|
800 | return str.replace(STRING_OMIT, '$1');
|
801 | };
|
802 |
|
803 | Lexer.prototype.formatHeregex = function(str) {
|
804 | return str.replace(HEREGEX_OMIT, '$1$2');
|
805 | };
|
806 |
|
807 | Lexer.prototype.validateEscapes = function(str, options) {
|
808 | var before, hex, invalidEscape, match, message, octal, ref2, unicode;
|
809 | if (options == null) {
|
810 | options = {};
|
811 | }
|
812 | match = INVALID_ESCAPE.exec(str);
|
813 | if (!match) {
|
814 | return;
|
815 | }
|
816 | match[0], before = match[1], octal = match[2], hex = match[3], unicode = match[4];
|
817 | if (options.isRegex && octal && octal.charAt(0) !== '0') {
|
818 | return;
|
819 | }
|
820 | message = octal ? "octal escape sequences are not allowed" : "invalid escape sequence";
|
821 | invalidEscape = "\\" + (octal || hex || unicode);
|
822 | return this.error(message + " " + invalidEscape, {
|
823 | offset: ((ref2 = options.offsetInChunk) != null ? ref2 : 0) + match.index + before.length,
|
824 | length: invalidEscape.length
|
825 | });
|
826 | };
|
827 |
|
828 | Lexer.prototype.makeDelimitedLiteral = function(body, options) {
|
829 | var regex;
|
830 | if (options == null) {
|
831 | options = {};
|
832 | }
|
833 | if (body === '' && options.delimiter === '/') {
|
834 | body = '(?:)';
|
835 | }
|
836 | regex = RegExp("(\\\\\\\\)|(\\\\0(?=[1-7]))|\\\\?(" + options.delimiter + ")|\\\\?(?:(\\n)|(\\r)|(\\u2028)|(\\u2029))|(\\\\.)", "g");
|
837 | body = body.replace(regex, function(match, backslash, nul, delimiter, lf, cr, ls, ps, other) {
|
838 | switch (false) {
|
839 | case !backslash:
|
840 | if (options.double) {
|
841 | return backslash + backslash;
|
842 | } else {
|
843 | return backslash;
|
844 | }
|
845 | case !nul:
|
846 | return '\\x00';
|
847 | case !delimiter:
|
848 | return "\\" + delimiter;
|
849 | case !lf:
|
850 | return '\\n';
|
851 | case !cr:
|
852 | return '\\r';
|
853 | case !ls:
|
854 | return '\\u2028';
|
855 | case !ps:
|
856 | return '\\u2029';
|
857 | case !other:
|
858 | if (options.double) {
|
859 | return "\\" + other;
|
860 | } else {
|
861 | return other;
|
862 | }
|
863 | }
|
864 | });
|
865 | return "" + options.delimiter + body + options.delimiter;
|
866 | };
|
867 |
|
868 | Lexer.prototype.error = function(message, options) {
|
869 | var first_column, first_line, location, ref2, ref3, ref4;
|
870 | if (options == null) {
|
871 | options = {};
|
872 | }
|
873 | location = 'first_line' in options ? options : ((ref3 = this.getLineAndColumnFromChunk((ref2 = options.offset) != null ? ref2 : 0), first_line = ref3[0], first_column = ref3[1], ref3), {
|
874 | first_line: first_line,
|
875 | first_column: first_column,
|
876 | last_column: first_column + ((ref4 = options.length) != null ? ref4 : 1) - 1
|
877 | });
|
878 | return throwSyntaxError(message, location);
|
879 | };
|
880 |
|
881 | return Lexer;
|
882 |
|
883 | })();
|
884 |
|
885 | JS_KEYWORDS = ['true', 'false', 'null', 'this', 'new', 'delete', 'typeof', 'in', 'instanceof', 'return', 'throw', 'break', 'continue', 'debugger', 'yield', 'if', 'else', 'switch', 'for', 'while', 'do', 'try', 'catch', 'finally', 'class', 'extends', 'super'];
|
886 |
|
887 | COFFEE_KEYWORDS = ['undefined', 'then', 'unless', 'until', 'loop', 'of', 'by', 'when'];
|
888 |
|
889 | COFFEE_ALIAS_MAP = {
|
890 | and: '&&',
|
891 | or: '||',
|
892 | is: '==',
|
893 | isnt: '!=',
|
894 | not: '!',
|
895 | yes: 'true',
|
896 | no: 'false',
|
897 | on: 'true',
|
898 | off: 'false'
|
899 | };
|
900 |
|
901 | COFFEE_ALIASES = (function() {
|
902 | var results;
|
903 | results = [];
|
904 | for (key in COFFEE_ALIAS_MAP) {
|
905 | results.push(key);
|
906 | }
|
907 | return results;
|
908 | })();
|
909 |
|
910 | COFFEE_KEYWORDS = COFFEE_KEYWORDS.concat(COFFEE_ALIASES);
|
911 |
|
912 | RESERVED = ['case', 'default', 'function', 'var', 'void', 'with', 'const', 'let', 'enum', 'export', 'import', 'native', 'implements', 'interface', 'package', 'private', 'protected', 'public', 'static'];
|
913 |
|
914 | STRICT_PROSCRIBED = ['arguments', 'eval', 'yield*'];
|
915 |
|
916 | JS_FORBIDDEN = JS_KEYWORDS.concat(RESERVED).concat(STRICT_PROSCRIBED);
|
917 |
|
918 | exports.RESERVED = RESERVED.concat(JS_KEYWORDS).concat(COFFEE_KEYWORDS).concat(STRICT_PROSCRIBED);
|
919 |
|
920 | exports.STRICT_PROSCRIBED = STRICT_PROSCRIBED;
|
921 |
|
922 | BOM = 65279;
|
923 |
|
924 | IDENTIFIER = /^(?!\d)((?:(?!\s)[$\w\x7f-\uffff])+)([^\n\S]*:(?!:))?/;
|
925 |
|
926 | NUMBER = /^0b[01]+|^0o[0-7]+|^0x[\da-f]+|^\d*\.?\d+(?:e[+-]?\d+)?/i;
|
927 |
|
928 | OPERATOR = /^(?:[-=]>|[-+*\/%<>&|^!?=]=|>>>=?|([-+:])\1|([&|<>*\/%])\2=?|\?(\.|::)|\.{2,3})/;
|
929 |
|
930 | WHITESPACE = /^[^\n\S]+/;
|
931 |
|
932 | COMMENT = /^###([^#][\s\S]*?)(?:###[^\n\S]*|###$)|^(?:\s*#(?!##[^#]).*)+/;
|
933 |
|
934 | CODE = /^[-=]>/;
|
935 |
|
936 | MULTI_DENT = /^(?:\n[^\n\S]*)+/;
|
937 |
|
938 | JSTOKEN = /^`[^\\`]*(?:\\.[^\\`]*)*`/;
|
939 |
|
940 | STRING_START = /^(?:'''|"""|'|")/;
|
941 |
|
942 | STRING_SINGLE = /^(?:[^\\']|\\[\s\S])*/;
|
943 |
|
944 | STRING_DOUBLE = /^(?:[^\\"#]|\\[\s\S]|\#(?!\{))*/;
|
945 |
|
946 | HEREDOC_SINGLE = /^(?:[^\\']|\\[\s\S]|'(?!''))*/;
|
947 |
|
948 | HEREDOC_DOUBLE = /^(?:[^\\"#]|\\[\s\S]|"(?!"")|\#(?!\{))*/;
|
949 |
|
950 | STRING_OMIT = /((?:\\\\)+)|\\[^\S\n]*\n\s*/g;
|
951 |
|
952 | SIMPLE_STRING_OMIT = /\s*\n\s*/g;
|
953 |
|
954 | HEREDOC_INDENT = /\n+([^\n\S]*)(?=\S)/g;
|
955 |
|
956 | REGEX = /^\/(?!\/)((?:[^[\/\n\\]|\\[^\n]|\[(?:\\[^\n]|[^\]\n\\])*\])*)(\/)?/;
|
957 |
|
958 | REGEX_FLAGS = /^\w*/;
|
959 |
|
960 | VALID_FLAGS = /^(?!.*(.).*\1)[imgy]*$/;
|
961 |
|
962 | HEREGEX = /^(?:[^\\\/#]|\\[\s\S]|\/(?!\/\/)|\#(?!\{))*/;
|
963 |
|
964 | HEREGEX_OMIT = /((?:\\\\)+)|\\(\s)|\s+(?:#.*)?/g;
|
965 |
|
966 | REGEX_ILLEGAL = /^(\/|\/{3}\s*)(\*)/;
|
967 |
|
968 | POSSIBLY_DIVISION = /^\/=?\s/;
|
969 |
|
970 | HERECOMMENT_ILLEGAL = /\*\//;
|
971 |
|
972 | LINE_CONTINUER = /^\s*(?:,|\??\.(?![.\d])|::)/;
|
973 |
|
974 | INVALID_ESCAPE = /((?:^|[^\\])(?:\\\\)*)\\(?:(0[0-7]|[1-7])|(x(?![\da-fA-F]{2}).{0,2})|(u(?![\da-fA-F]{4}).{0,4}))/;
|
975 |
|
976 | LEADING_BLANK_LINE = /^[^\n\S]*\n/;
|
977 |
|
978 | TRAILING_BLANK_LINE = /\n[^\n\S]*$/;
|
979 |
|
980 | TRAILING_SPACES = /\s+$/;
|
981 |
|
982 | COMPOUND_ASSIGN = ['-=', '+=', '/=', '*=', '%=', '||=', '&&=', '?=', '<<=', '>>=', '>>>=', '&=', '^=', '|=', '**=', '//=', '%%='];
|
983 |
|
984 | UNARY = ['NEW', 'TYPEOF', 'DELETE', 'DO'];
|
985 |
|
986 | UNARY_MATH = ['!', '~'];
|
987 |
|
988 | LOGIC = ['&&', '||', '&', '|', '^'];
|
989 |
|
990 | SHIFT = ['<<', '>>', '>>>'];
|
991 |
|
992 | COMPARE = ['==', '!=', '<', '>', '<=', '>='];
|
993 |
|
994 | MATH = ['*', '/', '%', '//', '%%'];
|
995 |
|
996 | RELATION = ['IN', 'OF', 'INSTANCEOF'];
|
997 |
|
998 | BOOL = ['TRUE', 'FALSE'];
|
999 |
|
1000 | CALLABLE = ['IDENTIFIER', ')', ']', '?', '@', 'THIS', 'SUPER'];
|
1001 |
|
1002 | INDEXABLE = CALLABLE.concat(['NUMBER', 'STRING', 'STRING_END', 'REGEX', 'REGEX_END', 'BOOL', 'NULL', 'UNDEFINED', '}', '::']);
|
1003 |
|
1004 | NOT_REGEX = INDEXABLE.concat(['++', '--']);
|
1005 |
|
1006 | LINE_BREAK = ['INDENT', 'OUTDENT', 'TERMINATOR'];
|
1007 |
|
1008 | INDENTABLE_CLOSERS = [')', '}', ']'];
|
1009 |
|
1010 | }).call(this);
|