1 |
|
2 | (function() {
|
3 | var BOM, BOOL, CALLABLE, CODE, COFFEE_ALIASES, COFFEE_ALIAS_MAP, COFFEE_KEYWORDS, COMMENT, COMPARE, COMPOUND_ASSIGN, HEREDOC, HEREDOC_ILLEGAL, HEREDOC_INDENT, HEREGEX, HEREGEX_OMIT, IDENTIFIER, INDEXABLE, INVERSES, JSTOKEN, JS_FORBIDDEN, JS_KEYWORDS, LINE_BREAK, LINE_CONTINUER, LITERATE, LOGIC, Lexer, MATH, MULTILINER, MULTI_DENT, NOT_REGEX, NOT_SPACED_REGEX, NUMBER, OPERATOR, REGEX, RELATION, RESERVED, Rewriter, SHIFT, SIMPLESTR, STRICT_PROSCRIBED, TRAILING_SPACES, UNARY, WHITESPACE, compact, count, key, last, locationDataToString, starts, _ref, _ref1,
|
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, last = _ref1.last, locationDataToString = _ref1.locationDataToString;
|
9 |
|
10 | exports.Lexer = Lexer = (function() {
|
11 |
|
12 | function Lexer() {}
|
13 |
|
14 | Lexer.prototype.tokenize = function(code, opts) {
|
15 | var consumed, i, tag, _ref2;
|
16 | if (opts == null) {
|
17 | opts = {};
|
18 | }
|
19 | this.literate = opts.literate;
|
20 | this.indent = 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.heredocToken() || 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 | }
|
35 | this.closeIndentation();
|
36 | if (tag = this.ends.pop()) {
|
37 | this.error("missing " + tag);
|
38 | }
|
39 | if (opts.rewrite === false) {
|
40 | return this.tokens;
|
41 | }
|
42 | return (new Rewriter).rewrite(this.tokens);
|
43 | };
|
44 |
|
45 | Lexer.prototype.clean = function(code) {
|
46 | var line, lines, match;
|
47 | if (code.charCodeAt(0) === BOM) {
|
48 | code = code.slice(1);
|
49 | }
|
50 | code = code.replace(/\r/g, '').replace(TRAILING_SPACES, '');
|
51 | if (WHITESPACE.test(code)) {
|
52 | code = "\n" + code;
|
53 | this.chunkLine--;
|
54 | }
|
55 | if (this.literate) {
|
56 | lines = (function() {
|
57 | var _i, _len, _ref2, _results;
|
58 | _ref2 = code.split('\n');
|
59 | _results = [];
|
60 | for (_i = 0, _len = _ref2.length; _i < _len; _i++) {
|
61 | line = _ref2[_i];
|
62 | if (match = LITERATE.exec(line)) {
|
63 | _results.push(line.slice(match[0].length));
|
64 | } else {
|
65 | _results.push('# ' + line);
|
66 | }
|
67 | }
|
68 | return _results;
|
69 | })();
|
70 | code = lines.join('\n');
|
71 | }
|
72 | return code;
|
73 | };
|
74 |
|
75 | Lexer.prototype.identifierToken = function() {
|
76 | var colon, colonOffset, forcedIdentifier, id, idLength, input, match, poppedToken, prev, tag, tagToken, _ref2, _ref3, _ref4;
|
77 | if (!(match = IDENTIFIER.exec(this.chunk))) {
|
78 | return 0;
|
79 | }
|
80 | input = match[0], id = match[1], colon = match[2];
|
81 | idLength = id.length;
|
82 | poppedToken = void 0;
|
83 | if (id === 'own' && this.tag() === 'FOR') {
|
84 | this.token('OWN', id);
|
85 | return id.length;
|
86 | }
|
87 | forcedIdentifier = colon || (prev = last(this.tokens)) && (((_ref2 = prev[0]) === '.' || _ref2 === '?.' || _ref2 === '::' || _ref2 === '?::') || !prev.spaced && prev[0] === '@');
|
88 | tag = 'IDENTIFIER';
|
89 | if (!forcedIdentifier && (__indexOf.call(JS_KEYWORDS, id) >= 0 || __indexOf.call(COFFEE_KEYWORDS, id) >= 0)) {
|
90 | tag = id.toUpperCase();
|
91 | if (tag === 'WHEN' && (_ref3 = this.tag(), __indexOf.call(LINE_BREAK, _ref3) >= 0)) {
|
92 | tag = 'LEADING_WHEN';
|
93 | } else if (tag === 'FOR') {
|
94 | this.seenFor = true;
|
95 | } else if (tag === 'UNLESS') {
|
96 | tag = 'IF';
|
97 | } else if (__indexOf.call(UNARY, tag) >= 0) {
|
98 | tag = 'UNARY';
|
99 | } else if (__indexOf.call(RELATION, tag) >= 0) {
|
100 | if (tag !== 'INSTANCEOF' && this.seenFor) {
|
101 | tag = 'FOR' + tag;
|
102 | this.seenFor = false;
|
103 | } else {
|
104 | tag = 'RELATION';
|
105 | if (this.value() === '!') {
|
106 | poppedToken = this.tokens.pop();
|
107 | id = '!' + id;
|
108 | }
|
109 | }
|
110 | }
|
111 | }
|
112 | if (__indexOf.call(JS_FORBIDDEN, id) >= 0) {
|
113 | if (forcedIdentifier) {
|
114 | tag = 'IDENTIFIER';
|
115 | id = new String(id);
|
116 | id.reserved = true;
|
117 | } else if (__indexOf.call(RESERVED, id) >= 0) {
|
118 | this.error("reserved word \"" + id + "\"");
|
119 | }
|
120 | }
|
121 | if (!forcedIdentifier) {
|
122 | if (__indexOf.call(COFFEE_ALIASES, id) >= 0) {
|
123 | id = COFFEE_ALIAS_MAP[id];
|
124 | }
|
125 | tag = (function() {
|
126 | switch (id) {
|
127 | case '!':
|
128 | return 'UNARY';
|
129 | case '==':
|
130 | case '!=':
|
131 | return 'COMPARE';
|
132 | case '&&':
|
133 | case '||':
|
134 | return 'LOGIC';
|
135 | case 'true':
|
136 | case 'false':
|
137 | return 'BOOL';
|
138 | case 'break':
|
139 | case 'continue':
|
140 | return 'STATEMENT';
|
141 | default:
|
142 | return tag;
|
143 | }
|
144 | })();
|
145 | }
|
146 | tagToken = this.token(tag, id, 0, idLength);
|
147 | if (poppedToken) {
|
148 | _ref4 = [poppedToken[2].first_line, poppedToken[2].first_column], tagToken[2].first_line = _ref4[0], tagToken[2].first_column = _ref4[1];
|
149 | }
|
150 | if (colon) {
|
151 | colonOffset = input.lastIndexOf(':');
|
152 | this.token(':', ':', colonOffset, colon.length);
|
153 | }
|
154 | return input.length;
|
155 | };
|
156 |
|
157 | Lexer.prototype.numberToken = function() {
|
158 | var binaryLiteral, lexedLength, match, number, octalLiteral;
|
159 | if (!(match = NUMBER.exec(this.chunk))) {
|
160 | return 0;
|
161 | }
|
162 | number = match[0];
|
163 | if (/^0[BOX]/.test(number)) {
|
164 | this.error("radix prefix '" + number + "' must be lowercase");
|
165 | } else if (/E/.test(number) && !/^0x/.test(number)) {
|
166 | this.error("exponential notation '" + number + "' must be indicated with a lowercase 'e'");
|
167 | } else if (/^0\d*[89]/.test(number)) {
|
168 | this.error("decimal literal '" + number + "' must not be prefixed with '0'");
|
169 | } else if (/^0\d+/.test(number)) {
|
170 | this.error("octal literal '" + number + "' must be prefixed with '0o'");
|
171 | }
|
172 | lexedLength = number.length;
|
173 | if (octalLiteral = /^0o([0-7]+)/.exec(number)) {
|
174 | number = '0x' + (parseInt(octalLiteral[1], 8)).toString(16);
|
175 | }
|
176 | if (binaryLiteral = /^0b([01]+)/.exec(number)) {
|
177 | number = '0x' + (parseInt(binaryLiteral[1], 2)).toString(16);
|
178 | }
|
179 | this.token('NUMBER', number, 0, lexedLength);
|
180 | return lexedLength;
|
181 | };
|
182 |
|
183 | Lexer.prototype.stringToken = function() {
|
184 | var match, octalEsc, string;
|
185 | switch (this.chunk.charAt(0)) {
|
186 | case "'":
|
187 | if (!(match = SIMPLESTR.exec(this.chunk))) {
|
188 | return 0;
|
189 | }
|
190 | string = match[0];
|
191 | this.token('STRING', string.replace(MULTILINER, '\\\n'), 0, string.length);
|
192 | break;
|
193 | case '"':
|
194 | if (!(string = this.balancedString(this.chunk, '"'))) {
|
195 | return 0;
|
196 | }
|
197 | if (0 < string.indexOf('#{', 1)) {
|
198 | this.interpolateString(string.slice(1, -1), {
|
199 | strOffset: 1,
|
200 | lexedLength: string.length
|
201 | });
|
202 | } else {
|
203 | this.token('STRING', this.escapeLines(string, 0, string.length));
|
204 | }
|
205 | break;
|
206 | default:
|
207 | return 0;
|
208 | }
|
209 | if (octalEsc = /^(?:\\.|[^\\])*\\(?:0[0-7]|[1-7])/.test(string)) {
|
210 | this.error("octal escape sequences " + string + " are not allowed");
|
211 | }
|
212 | return string.length;
|
213 | };
|
214 |
|
215 | Lexer.prototype.heredocToken = function() {
|
216 | var doc, heredoc, match, quote;
|
217 | if (!(match = HEREDOC.exec(this.chunk))) {
|
218 | return 0;
|
219 | }
|
220 | heredoc = match[0];
|
221 | quote = heredoc.charAt(0);
|
222 | doc = this.sanitizeHeredoc(match[2], {
|
223 | quote: quote,
|
224 | indent: null
|
225 | });
|
226 | if (quote === '"' && 0 <= doc.indexOf('#{')) {
|
227 | this.interpolateString(doc, {
|
228 | heredoc: true,
|
229 | strOffset: 3,
|
230 | lexedLength: heredoc.length
|
231 | });
|
232 | } else {
|
233 | this.token('STRING', this.makeString(doc, quote, true), 0, heredoc.length);
|
234 | }
|
235 | return heredoc.length;
|
236 | };
|
237 |
|
238 | Lexer.prototype.commentToken = function() {
|
239 | var comment, here, match;
|
240 | if (!(match = this.chunk.match(COMMENT))) {
|
241 | return 0;
|
242 | }
|
243 | comment = match[0], here = match[1];
|
244 | if (here) {
|
245 | this.token('HERECOMMENT', this.sanitizeHeredoc(here, {
|
246 | herecomment: true,
|
247 | indent: Array(this.indent + 1).join(' ')
|
248 | }), 0, comment.length);
|
249 | }
|
250 | return comment.length;
|
251 | };
|
252 |
|
253 | Lexer.prototype.jsToken = function() {
|
254 | var match, script;
|
255 | if (!(this.chunk.charAt(0) === '`' && (match = JSTOKEN.exec(this.chunk)))) {
|
256 | return 0;
|
257 | }
|
258 | this.token('JS', (script = match[0]).slice(1, -1), 0, script.length);
|
259 | return script.length;
|
260 | };
|
261 |
|
262 | Lexer.prototype.regexToken = function() {
|
263 | var flags, length, match, prev, regex, _ref2, _ref3;
|
264 | if (this.chunk.charAt(0) !== '/') {
|
265 | return 0;
|
266 | }
|
267 | if (match = HEREGEX.exec(this.chunk)) {
|
268 | length = this.heregexToken(match);
|
269 | return length;
|
270 | }
|
271 | prev = last(this.tokens);
|
272 | if (prev && (_ref2 = prev[0], __indexOf.call((prev.spaced ? NOT_REGEX : NOT_SPACED_REGEX), _ref2) >= 0)) {
|
273 | return 0;
|
274 | }
|
275 | if (!(match = REGEX.exec(this.chunk))) {
|
276 | return 0;
|
277 | }
|
278 | _ref3 = match, match = _ref3[0], regex = _ref3[1], flags = _ref3[2];
|
279 | if (regex.slice(0, 2) === '/*') {
|
280 | this.error('regular expressions cannot begin with `*`');
|
281 | }
|
282 | if (regex === '//') {
|
283 | regex = '/(?:)/';
|
284 | }
|
285 | this.token('REGEX', "" + regex + flags, 0, match.length);
|
286 | return match.length;
|
287 | };
|
288 |
|
289 | Lexer.prototype.heregexToken = function(match) {
|
290 | var body, flags, flagsOffset, heregex, plusToken, prev, re, tag, token, tokens, value, _i, _len, _ref2, _ref3, _ref4;
|
291 | heregex = match[0], body = match[1], flags = match[2];
|
292 | if (0 > body.indexOf('#{')) {
|
293 | re = body.replace(HEREGEX_OMIT, '').replace(/\//g, '\\/');
|
294 | if (re.match(/^\*/)) {
|
295 | this.error('regular expressions cannot begin with `*`');
|
296 | }
|
297 | this.token('REGEX', "/" + (re || '(?:)') + "/" + flags, 0, heregex.length);
|
298 | return heregex.length;
|
299 | }
|
300 | this.token('IDENTIFIER', 'RegExp', 0, 0);
|
301 | this.token('CALL_START', '(', 0, 0);
|
302 | tokens = [];
|
303 | _ref2 = this.interpolateString(body, {
|
304 | regex: true
|
305 | });
|
306 | for (_i = 0, _len = _ref2.length; _i < _len; _i++) {
|
307 | token = _ref2[_i];
|
308 | tag = token[0], value = token[1];
|
309 | if (tag === 'TOKENS') {
|
310 | tokens.push.apply(tokens, value);
|
311 | } else if (tag === 'NEOSTRING') {
|
312 | if (!(value = value.replace(HEREGEX_OMIT, ''))) {
|
313 | continue;
|
314 | }
|
315 | value = value.replace(/\\/g, '\\\\');
|
316 | token[0] = 'STRING';
|
317 | token[1] = this.makeString(value, '"', true);
|
318 | tokens.push(token);
|
319 | } else {
|
320 | this.error("Unexpected " + tag);
|
321 | }
|
322 | prev = last(this.tokens);
|
323 | plusToken = ['+', '+'];
|
324 | plusToken[2] = prev[2];
|
325 | tokens.push(plusToken);
|
326 | }
|
327 | tokens.pop();
|
328 | if (((_ref3 = tokens[0]) != null ? _ref3[0] : void 0) !== 'STRING') {
|
329 | this.token('STRING', '""', 0, 0);
|
330 | this.token('+', '+', 0, 0);
|
331 | }
|
332 | (_ref4 = this.tokens).push.apply(_ref4, tokens);
|
333 | if (flags) {
|
334 | flagsOffset = heregex.lastIndexOf(flags);
|
335 | this.token(',', ',', flagsOffset, 0);
|
336 | this.token('STRING', '"' + flags + '"', flagsOffset, flags.length);
|
337 | }
|
338 | this.token(')', ')', heregex.length - 1, 0);
|
339 | return heregex.length;
|
340 | };
|
341 |
|
342 | Lexer.prototype.lineToken = function() {
|
343 | var diff, indent, match, noNewlines, size;
|
344 | if (!(match = MULTI_DENT.exec(this.chunk))) {
|
345 | return 0;
|
346 | }
|
347 | indent = match[0];
|
348 | this.seenFor = false;
|
349 | size = indent.length - 1 - indent.lastIndexOf('\n');
|
350 | noNewlines = this.unfinished();
|
351 | if (size - this.indebt === this.indent) {
|
352 | if (noNewlines) {
|
353 | this.suppressNewlines();
|
354 | } else {
|
355 | this.newlineToken(0);
|
356 | }
|
357 | return indent.length;
|
358 | }
|
359 | if (size > this.indent) {
|
360 | if (noNewlines) {
|
361 | this.indebt = size - this.indent;
|
362 | this.suppressNewlines();
|
363 | return indent.length;
|
364 | }
|
365 | diff = size - this.indent + this.outdebt;
|
366 | this.token('INDENT', diff, 0, indent.length);
|
367 | this.indents.push(diff);
|
368 | this.ends.push('OUTDENT');
|
369 | this.outdebt = this.indebt = 0;
|
370 | } else {
|
371 | this.indebt = 0;
|
372 | this.outdentToken(this.indent - size, noNewlines, indent.length);
|
373 | }
|
374 | this.indent = size;
|
375 | return indent.length;
|
376 | };
|
377 |
|
378 | Lexer.prototype.outdentToken = function(moveOut, noNewlines, outdentLength) {
|
379 | var dent, len;
|
380 | while (moveOut > 0) {
|
381 | len = this.indents.length - 1;
|
382 | if (this.indents[len] === void 0) {
|
383 | moveOut = 0;
|
384 | } else if (this.indents[len] === this.outdebt) {
|
385 | moveOut -= this.outdebt;
|
386 | this.outdebt = 0;
|
387 | } else if (this.indents[len] < this.outdebt) {
|
388 | this.outdebt -= this.indents[len];
|
389 | moveOut -= this.indents[len];
|
390 | } else {
|
391 | dent = this.indents.pop() + this.outdebt;
|
392 | moveOut -= dent;
|
393 | this.outdebt = 0;
|
394 | this.pair('OUTDENT');
|
395 | this.token('OUTDENT', dent, 0, outdentLength);
|
396 | }
|
397 | }
|
398 | if (dent) {
|
399 | this.outdebt -= moveOut;
|
400 | }
|
401 | while (this.value() === ';') {
|
402 | this.tokens.pop();
|
403 | }
|
404 | if (!(this.tag() === 'TERMINATOR' || noNewlines)) {
|
405 | this.token('TERMINATOR', '\n', outdentLength, 0);
|
406 | }
|
407 | return this;
|
408 | };
|
409 |
|
410 | Lexer.prototype.whitespaceToken = function() {
|
411 | var match, nline, prev;
|
412 | if (!((match = WHITESPACE.exec(this.chunk)) || (nline = this.chunk.charAt(0) === '\n'))) {
|
413 | return 0;
|
414 | }
|
415 | prev = last(this.tokens);
|
416 | if (prev) {
|
417 | prev[match ? 'spaced' : 'newLine'] = true;
|
418 | }
|
419 | if (match) {
|
420 | return match[0].length;
|
421 | } else {
|
422 | return 0;
|
423 | }
|
424 | };
|
425 |
|
426 | Lexer.prototype.newlineToken = function(offset) {
|
427 | while (this.value() === ';') {
|
428 | this.tokens.pop();
|
429 | }
|
430 | if (this.tag() !== 'TERMINATOR') {
|
431 | this.token('TERMINATOR', '\n', offset, 0);
|
432 | }
|
433 | return this;
|
434 | };
|
435 |
|
436 | Lexer.prototype.suppressNewlines = function() {
|
437 | if (this.value() === '\\') {
|
438 | this.tokens.pop();
|
439 | }
|
440 | return this;
|
441 | };
|
442 |
|
443 | Lexer.prototype.literalToken = function() {
|
444 | var match, prev, tag, value, _ref2, _ref3, _ref4, _ref5;
|
445 | if (match = OPERATOR.exec(this.chunk)) {
|
446 | value = match[0];
|
447 | if (CODE.test(value)) {
|
448 | this.tagParameters();
|
449 | }
|
450 | } else {
|
451 | value = this.chunk.charAt(0);
|
452 | }
|
453 | tag = value;
|
454 | prev = last(this.tokens);
|
455 | if (value === '=' && prev) {
|
456 | if (!prev[1].reserved && (_ref2 = prev[1], __indexOf.call(JS_FORBIDDEN, _ref2) >= 0)) {
|
457 | this.error("reserved word \"" + (this.value()) + "\" can't be assigned");
|
458 | }
|
459 | if ((_ref3 = prev[1]) === '||' || _ref3 === '&&') {
|
460 | prev[0] = 'COMPOUND_ASSIGN';
|
461 | prev[1] += '=';
|
462 | return value.length;
|
463 | }
|
464 | }
|
465 | if (value === ';') {
|
466 | this.seenFor = false;
|
467 | tag = 'TERMINATOR';
|
468 | } else if (__indexOf.call(MATH, value) >= 0) {
|
469 | tag = 'MATH';
|
470 | } else if (__indexOf.call(COMPARE, value) >= 0) {
|
471 | tag = 'COMPARE';
|
472 | } else if (__indexOf.call(COMPOUND_ASSIGN, value) >= 0) {
|
473 | tag = 'COMPOUND_ASSIGN';
|
474 | } else if (__indexOf.call(UNARY, value) >= 0) {
|
475 | tag = 'UNARY';
|
476 | } else if (__indexOf.call(SHIFT, value) >= 0) {
|
477 | tag = 'SHIFT';
|
478 | } else if (__indexOf.call(LOGIC, value) >= 0 || value === '?' && (prev != null ? prev.spaced : void 0)) {
|
479 | tag = 'LOGIC';
|
480 | } else if (prev && !prev.spaced) {
|
481 | if (value === '(' && (_ref4 = prev[0], __indexOf.call(CALLABLE, _ref4) >= 0)) {
|
482 | if (prev[0] === '?') {
|
483 | prev[0] = 'FUNC_EXIST';
|
484 | }
|
485 | tag = 'CALL_START';
|
486 | } else if (value === '[' && (_ref5 = prev[0], __indexOf.call(INDEXABLE, _ref5) >= 0)) {
|
487 | tag = 'INDEX_START';
|
488 | switch (prev[0]) {
|
489 | case '?':
|
490 | prev[0] = 'INDEX_SOAK';
|
491 | }
|
492 | }
|
493 | }
|
494 | switch (value) {
|
495 | case '(':
|
496 | case '{':
|
497 | case '[':
|
498 | this.ends.push(INVERSES[value]);
|
499 | break;
|
500 | case ')':
|
501 | case '}':
|
502 | case ']':
|
503 | this.pair(value);
|
504 | }
|
505 | this.token(tag, value);
|
506 | return value.length;
|
507 | };
|
508 |
|
509 | Lexer.prototype.sanitizeHeredoc = function(doc, options) {
|
510 | var attempt, herecomment, indent, match, _ref2;
|
511 | indent = options.indent, herecomment = options.herecomment;
|
512 | if (herecomment) {
|
513 | if (HEREDOC_ILLEGAL.test(doc)) {
|
514 | this.error("block comment cannot contain \"*/\", starting");
|
515 | }
|
516 | if (doc.indexOf('\n') < 0) {
|
517 | return doc;
|
518 | }
|
519 | } else {
|
520 | while (match = HEREDOC_INDENT.exec(doc)) {
|
521 | attempt = match[1];
|
522 | if (indent === null || (0 < (_ref2 = attempt.length) && _ref2 < indent.length)) {
|
523 | indent = attempt;
|
524 | }
|
525 | }
|
526 | }
|
527 | if (indent) {
|
528 | doc = doc.replace(RegExp("\\n" + indent, "g"), '\n');
|
529 | }
|
530 | if (this.literate) {
|
531 | doc = doc.replace(/\n# \n/g, '\n\n');
|
532 | }
|
533 | if (!herecomment) {
|
534 | doc = doc.replace(/^\n/, '');
|
535 | }
|
536 | return doc;
|
537 | };
|
538 |
|
539 | Lexer.prototype.tagParameters = function() {
|
540 | var i, stack, tok, tokens;
|
541 | if (this.tag() !== ')') {
|
542 | return this;
|
543 | }
|
544 | stack = [];
|
545 | tokens = this.tokens;
|
546 | i = tokens.length;
|
547 | tokens[--i][0] = 'PARAM_END';
|
548 | while (tok = tokens[--i]) {
|
549 | switch (tok[0]) {
|
550 | case ')':
|
551 | stack.push(tok);
|
552 | break;
|
553 | case '(':
|
554 | case 'CALL_START':
|
555 | if (stack.length) {
|
556 | stack.pop();
|
557 | } else if (tok[0] === '(') {
|
558 | tok[0] = 'PARAM_START';
|
559 | return this;
|
560 | } else {
|
561 | return this;
|
562 | }
|
563 | }
|
564 | }
|
565 | return this;
|
566 | };
|
567 |
|
568 | Lexer.prototype.closeIndentation = function() {
|
569 | return this.outdentToken(this.indent);
|
570 | };
|
571 |
|
572 | Lexer.prototype.balancedString = function(str, end) {
|
573 | var continueCount, i, letter, match, prev, stack, _i, _ref2;
|
574 | continueCount = 0;
|
575 | stack = [end];
|
576 | for (i = _i = 1, _ref2 = str.length; 1 <= _ref2 ? _i < _ref2 : _i > _ref2; i = 1 <= _ref2 ? ++_i : --_i) {
|
577 | if (continueCount) {
|
578 | --continueCount;
|
579 | continue;
|
580 | }
|
581 | switch (letter = str.charAt(i)) {
|
582 | case '\\':
|
583 | ++continueCount;
|
584 | continue;
|
585 | case end:
|
586 | stack.pop();
|
587 | if (!stack.length) {
|
588 | return str.slice(0, +i + 1 || 9e9);
|
589 | }
|
590 | end = stack[stack.length - 1];
|
591 | continue;
|
592 | }
|
593 | if (end === '}' && (letter === '"' || letter === "'")) {
|
594 | stack.push(end = letter);
|
595 | } else if (end === '}' && letter === '/' && (match = HEREGEX.exec(str.slice(i)) || REGEX.exec(str.slice(i)))) {
|
596 | continueCount += match[0].length - 1;
|
597 | } else if (end === '}' && letter === '{') {
|
598 | stack.push(end = '}');
|
599 | } else if (end === '"' && prev === '#' && letter === '{') {
|
600 | stack.push(end = '}');
|
601 | }
|
602 | prev = letter;
|
603 | }
|
604 | return this.error("missing " + (stack.pop()) + ", starting");
|
605 | };
|
606 |
|
607 | Lexer.prototype.interpolateString = function(str, options) {
|
608 | var column, expr, heredoc, i, inner, interpolated, len, letter, lexedLength, line, locationToken, nested, offsetInChunk, pi, plusToken, popped, regex, strOffset, tag, token, tokens, value, _i, _len, _ref2, _ref3, _ref4;
|
609 | if (options == null) {
|
610 | options = {};
|
611 | }
|
612 | heredoc = options.heredoc, regex = options.regex, offsetInChunk = options.offsetInChunk, strOffset = options.strOffset, lexedLength = options.lexedLength;
|
613 | offsetInChunk = offsetInChunk || 0;
|
614 | strOffset = strOffset || 0;
|
615 | lexedLength = lexedLength || str.length;
|
616 | if (heredoc && str.length > 0 && str[0] === '\n') {
|
617 | str = str.slice(1);
|
618 | strOffset++;
|
619 | }
|
620 | tokens = [];
|
621 | pi = 0;
|
622 | i = -1;
|
623 | while (letter = str.charAt(i += 1)) {
|
624 | if (letter === '\\') {
|
625 | i += 1;
|
626 | continue;
|
627 | }
|
628 | if (!(letter === '#' && str.charAt(i + 1) === '{' && (expr = this.balancedString(str.slice(i + 1), '}')))) {
|
629 | continue;
|
630 | }
|
631 | if (pi < i) {
|
632 | tokens.push(this.makeToken('NEOSTRING', str.slice(pi, i), strOffset + pi));
|
633 | }
|
634 | inner = expr.slice(1, -1);
|
635 | if (inner.length) {
|
636 | _ref2 = this.getLineAndColumnFromChunk(strOffset + i + 1), line = _ref2[0], column = _ref2[1];
|
637 | nested = new Lexer().tokenize(inner, {
|
638 | line: line,
|
639 | column: column,
|
640 | rewrite: false
|
641 | });
|
642 | popped = nested.pop();
|
643 | if (((_ref3 = nested[0]) != null ? _ref3[0] : void 0) === 'TERMINATOR') {
|
644 | popped = nested.shift();
|
645 | }
|
646 | if (len = nested.length) {
|
647 | if (len > 1) {
|
648 | nested.unshift(this.makeToken('(', '(', strOffset + i + 1, 0));
|
649 | nested.push(this.makeToken(')', ')', strOffset + i + 1 + inner.length, 0));
|
650 | }
|
651 | tokens.push(['TOKENS', nested]);
|
652 | }
|
653 | }
|
654 | i += expr.length;
|
655 | pi = i + 1;
|
656 | }
|
657 | if ((i > pi && pi < str.length)) {
|
658 | tokens.push(this.makeToken('NEOSTRING', str.slice(pi), strOffset + pi));
|
659 | }
|
660 | if (regex) {
|
661 | return tokens;
|
662 | }
|
663 | if (!tokens.length) {
|
664 | return this.token('STRING', '""', offsetInChunk, lexedLength);
|
665 | }
|
666 | if (tokens[0][0] !== 'NEOSTRING') {
|
667 | tokens.unshift(this.makeToken('NEOSTRING', '', offsetInChunk));
|
668 | }
|
669 | if (interpolated = tokens.length > 1) {
|
670 | this.token('(', '(', offsetInChunk, 0);
|
671 | }
|
672 | for (i = _i = 0, _len = tokens.length; _i < _len; i = ++_i) {
|
673 | token = tokens[i];
|
674 | tag = token[0], value = token[1];
|
675 | if (i) {
|
676 | if (i) {
|
677 | plusToken = this.token('+', '+');
|
678 | }
|
679 | locationToken = tag === 'TOKENS' ? value[0] : token;
|
680 | plusToken[2] = {
|
681 | first_line: locationToken[2].first_line,
|
682 | first_column: locationToken[2].first_column,
|
683 | last_line: locationToken[2].first_line,
|
684 | last_column: locationToken[2].first_column
|
685 | };
|
686 | }
|
687 | if (tag === 'TOKENS') {
|
688 | (_ref4 = this.tokens).push.apply(_ref4, value);
|
689 | } else if (tag === 'NEOSTRING') {
|
690 | token[0] = 'STRING';
|
691 | token[1] = this.makeString(value, '"', heredoc);
|
692 | this.tokens.push(token);
|
693 | } else {
|
694 | this.error("Unexpected " + tag);
|
695 | }
|
696 | }
|
697 | if (interpolated) {
|
698 | this.token(')', ')', offsetInChunk + lexedLength, 0);
|
699 | }
|
700 | return tokens;
|
701 | };
|
702 |
|
703 | Lexer.prototype.pair = function(tag) {
|
704 | var size, wanted;
|
705 | if (tag !== (wanted = last(this.ends))) {
|
706 | if ('OUTDENT' !== wanted) {
|
707 | this.error("unmatched " + tag);
|
708 | }
|
709 | this.indent -= size = last(this.indents);
|
710 | this.outdentToken(size, true);
|
711 | return this.pair(tag);
|
712 | }
|
713 | return this.ends.pop();
|
714 | };
|
715 |
|
716 | Lexer.prototype.getLineAndColumnFromChunk = function(offset) {
|
717 | var column, lineCount, lines, string;
|
718 | if (offset === 0) {
|
719 | return [this.chunkLine, this.chunkColumn];
|
720 | }
|
721 | if (offset >= this.chunk.length) {
|
722 | string = this.chunk;
|
723 | } else {
|
724 | string = this.chunk.slice(0, +(offset - 1) + 1 || 9e9);
|
725 | }
|
726 | lineCount = count(string, '\n');
|
727 | column = this.chunkColumn;
|
728 | if (lineCount > 0) {
|
729 | lines = string.split('\n');
|
730 | column = (last(lines)).length;
|
731 | } else {
|
732 | column += string.length;
|
733 | }
|
734 | return [this.chunkLine + lineCount, column];
|
735 | };
|
736 |
|
737 | Lexer.prototype.makeToken = function(tag, value, offsetInChunk, length) {
|
738 | var lastCharacter, locationData, token, _ref2, _ref3;
|
739 | if (offsetInChunk == null) {
|
740 | offsetInChunk = 0;
|
741 | }
|
742 | if (length == null) {
|
743 | length = value.length;
|
744 | }
|
745 | locationData = {};
|
746 | _ref2 = this.getLineAndColumnFromChunk(offsetInChunk), locationData.first_line = _ref2[0], locationData.first_column = _ref2[1];
|
747 | lastCharacter = Math.max(0, length - 1);
|
748 | _ref3 = this.getLineAndColumnFromChunk(offsetInChunk + (length - 1)), locationData.last_line = _ref3[0], locationData.last_column = _ref3[1];
|
749 | token = [tag, value, locationData];
|
750 | return token;
|
751 | };
|
752 |
|
753 | Lexer.prototype.token = function(tag, value, offsetInChunk, length) {
|
754 | var token;
|
755 | token = this.makeToken(tag, value, offsetInChunk, length);
|
756 | this.tokens.push(token);
|
757 | return token;
|
758 | };
|
759 |
|
760 | Lexer.prototype.tag = function(index, tag) {
|
761 | var tok;
|
762 | return (tok = last(this.tokens, index)) && (tag ? tok[0] = tag : tok[0]);
|
763 | };
|
764 |
|
765 | Lexer.prototype.value = function(index, val) {
|
766 | var tok;
|
767 | return (tok = last(this.tokens, index)) && (val ? tok[1] = val : tok[1]);
|
768 | };
|
769 |
|
770 | Lexer.prototype.unfinished = function() {
|
771 | var _ref2;
|
772 | return LINE_CONTINUER.test(this.chunk) || ((_ref2 = this.tag()) === '\\' || _ref2 === '.' || _ref2 === '?.' || _ref2 === '?::' || _ref2 === 'UNARY' || _ref2 === 'MATH' || _ref2 === '+' || _ref2 === '-' || _ref2 === 'SHIFT' || _ref2 === 'RELATION' || _ref2 === 'COMPARE' || _ref2 === 'LOGIC' || _ref2 === 'THROW' || _ref2 === 'EXTENDS');
|
773 | };
|
774 |
|
775 | Lexer.prototype.escapeLines = function(str, heredoc) {
|
776 | return str.replace(MULTILINER, heredoc ? '\\n' : '');
|
777 | };
|
778 |
|
779 | Lexer.prototype.makeString = function(body, quote, heredoc) {
|
780 | if (!body) {
|
781 | return quote + quote;
|
782 | }
|
783 | body = body.replace(/\\([\s\S])/g, function(match, contents) {
|
784 | if (contents === '\n' || contents === quote) {
|
785 | return contents;
|
786 | } else {
|
787 | return match;
|
788 | }
|
789 | });
|
790 | body = body.replace(RegExp("" + quote, "g"), '\\$&');
|
791 | return quote + this.escapeLines(body, heredoc) + quote;
|
792 | };
|
793 |
|
794 | Lexer.prototype.error = function(message) {
|
795 | throw SyntaxError("" + message + " on line " + (this.chunkLine + 1));
|
796 | };
|
797 |
|
798 | return Lexer;
|
799 |
|
800 | })();
|
801 |
|
802 | JS_KEYWORDS = ['true', 'false', 'null', 'this', 'new', 'delete', 'typeof', 'in', 'instanceof', 'return', 'throw', 'break', 'continue', 'debugger', 'if', 'else', 'switch', 'for', 'while', 'do', 'try', 'catch', 'finally', 'class', 'extends', 'super'];
|
803 |
|
804 | COFFEE_KEYWORDS = ['undefined', 'then', 'unless', 'until', 'loop', 'of', 'by', 'when'];
|
805 |
|
806 | COFFEE_ALIAS_MAP = {
|
807 | and: '&&',
|
808 | or: '||',
|
809 | is: '==',
|
810 | isnt: '!=',
|
811 | not: '!',
|
812 | yes: 'true',
|
813 | no: 'false',
|
814 | on: 'true',
|
815 | off: 'false'
|
816 | };
|
817 |
|
818 | COFFEE_ALIASES = (function() {
|
819 | var _results;
|
820 | _results = [];
|
821 | for (key in COFFEE_ALIAS_MAP) {
|
822 | _results.push(key);
|
823 | }
|
824 | return _results;
|
825 | })();
|
826 |
|
827 | COFFEE_KEYWORDS = COFFEE_KEYWORDS.concat(COFFEE_ALIASES);
|
828 |
|
829 | RESERVED = ['case', 'default', 'function', 'var', 'void', 'with', 'const', 'let', 'enum', 'export', 'import', 'native', '__hasProp', '__extends', '__slice', '__bind', '__indexOf', 'implements', 'interface', 'package', 'private', 'protected', 'public', 'static', 'yield'];
|
830 |
|
831 | STRICT_PROSCRIBED = ['arguments', 'eval'];
|
832 |
|
833 | JS_FORBIDDEN = JS_KEYWORDS.concat(RESERVED).concat(STRICT_PROSCRIBED);
|
834 |
|
835 | exports.RESERVED = RESERVED.concat(JS_KEYWORDS).concat(COFFEE_KEYWORDS).concat(STRICT_PROSCRIBED);
|
836 |
|
837 | exports.STRICT_PROSCRIBED = STRICT_PROSCRIBED;
|
838 |
|
839 | BOM = 65279;
|
840 |
|
841 | IDENTIFIER = /^([$A-Za-z_\x7f-\uffff][$\w\x7f-\uffff]*)([^\n\S]*:(?!:))?/;
|
842 |
|
843 | NUMBER = /^0b[01]+|^0o[0-7]+|^0x[\da-f]+|^\d*\.?\d+(?:e[+-]?\d+)?/i;
|
844 |
|
845 | HEREDOC = /^("""|''')([\s\S]*?)(?:\n[^\n\S]*)?\1/;
|
846 |
|
847 | OPERATOR = /^(?:[-=]>|[-+*\/%<>&|^!?=]=|>>>=?|([-+:])\1|([&|<>])\2=?|\?(\.|::)|\.{2,3})/;
|
848 |
|
849 | WHITESPACE = /^[^\n\S]+/;
|
850 |
|
851 | COMMENT = /^###([^#][\s\S]*?)(?:###[^\n\S]*|(?:###)$)|^(?:\s*#(?!##[^#]).*)+/;
|
852 |
|
853 | LITERATE = /^([ ]{4}|\t)/;
|
854 |
|
855 | CODE = /^[-=]>/;
|
856 |
|
857 | MULTI_DENT = /^(?:\n[^\n\S]*)+/;
|
858 |
|
859 | SIMPLESTR = /^'[^\\']*(?:\\.[^\\']*)*'/;
|
860 |
|
861 | JSTOKEN = /^`[^\\`]*(?:\\.[^\\`]*)*`/;
|
862 |
|
863 | REGEX = /^(\/(?![\s=])[^[\/\n\\]*(?:(?:\\[\s\S]|\[[^\]\n\\]*(?:\\[\s\S][^\]\n\\]*)*])[^[\/\n\\]*)*\/)([imgy]{0,4})(?!\w)/;
|
864 |
|
865 | HEREGEX = /^\/{3}([\s\S]+?)\/{3}([imgy]{0,4})(?!\w)/;
|
866 |
|
867 | HEREGEX_OMIT = /\s+(?:#.*)?/g;
|
868 |
|
869 | MULTILINER = /\n/g;
|
870 |
|
871 | HEREDOC_INDENT = /\n+([^\n\S]*)/g;
|
872 |
|
873 | HEREDOC_ILLEGAL = /\*\//;
|
874 |
|
875 | LINE_CONTINUER = /^\s*(?:,|\??\.(?![.\d])|::)/;
|
876 |
|
877 | TRAILING_SPACES = /\s+$/;
|
878 |
|
879 | COMPOUND_ASSIGN = ['-=', '+=', '/=', '*=', '%=', '||=', '&&=', '?=', '<<=', '>>=', '>>>=', '&=', '^=', '|='];
|
880 |
|
881 | UNARY = ['!', '~', 'NEW', 'TYPEOF', 'DELETE', 'DO'];
|
882 |
|
883 | LOGIC = ['&&', '||', '&', '|', '^'];
|
884 |
|
885 | SHIFT = ['<<', '>>', '>>>'];
|
886 |
|
887 | COMPARE = ['==', '!=', '<', '>', '<=', '>='];
|
888 |
|
889 | MATH = ['*', '/', '%'];
|
890 |
|
891 | RELATION = ['IN', 'OF', 'INSTANCEOF'];
|
892 |
|
893 | BOOL = ['TRUE', 'FALSE'];
|
894 |
|
895 | NOT_REGEX = ['NUMBER', 'REGEX', 'BOOL', 'NULL', 'UNDEFINED', '++', '--', ']'];
|
896 |
|
897 | NOT_SPACED_REGEX = NOT_REGEX.concat(')', '}', 'THIS', 'IDENTIFIER', 'STRING');
|
898 |
|
899 | CALLABLE = ['IDENTIFIER', 'STRING', 'REGEX', ')', ']', '}', '?', '::', '@', 'THIS', 'SUPER'];
|
900 |
|
901 | INDEXABLE = CALLABLE.concat('NUMBER', 'BOOL', 'NULL', 'UNDEFINED');
|
902 |
|
903 | LINE_BREAK = ['INDENT', 'OUTDENT', 'TERMINATOR'];
|
904 |
|
905 | }).call(this);
|