mirror of
https://github.com/jashkenas/coffeescript.git
synced 2026-05-03 03:00:14 -04:00
8fd6258a46
A regex may not follow a specific set of tokens. These were already known before in the `NOT_REGEX` and `NOT_SPACED_REGEX` arrays. (However, I've refactored them to be more correct and to add a few missing tokens). In all other cases (except after a spaced callable) a slash is the start of a regex, and may now start with a space or an equals sign. It’s really that simple! A slash after a spaced callable is the only ambigous case. We cannot know if that's division or function application with a regex as the argument. The spacing determines which is which: Space on both sides: - `a / b/i` -> `a / b / i` - `a /= b/i` -> `a /= b / i` No spaces: - `a/b/i` -> `a / b / i` - `a/=b/i` -> `a /= b / i` Space on the right side: - `a/ b/i` -> `a / b / i` - `a/= b/i` -> `a /= b / i` Space on the left side: - `a /b/i` -> `a(/b/i)` - `a /=b/i` -> `a(/=b/i)` The last case used to compile to `a /= b / i`, but that has been changed to be consistent with the `/` operator. The last case really looks like a regex, so it should be parsed as one. Moreover, you may now also space the `/` and `/=` operators with other whitespace characters than a space (such as tabs and non-breaking spaces) for consistency. Lastly, unclosed regexes are now reported as such, instead of generating some other confusing error message. It should perhaps also be noted that apart from escaping (such as `a /\ b/`) you may now also use parentheses to disambiguate division and regex: `a (/ b/)`. See https://github.com/jashkenas/coffeescript/issues/3182#issuecomment-26688427.
914 lines
30 KiB
JavaScript
914 lines
30 KiB
JavaScript
// Generated by CoffeeScript 1.8.0
|
|
(function() {
|
|
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, INVERSES, JSTOKEN, JS_FORBIDDEN, JS_KEYWORDS, LEADING_BLANK_LINE, LINE_BREAK, LINE_CONTINUER, LOGIC, Lexer, MATH, MULTILINER, MULTI_DENT, NOT_REGEX, NUMBER, OCTAL_ESCAPE, OPERATOR, POSSIBLY_DIVISION, REGEX, REGEX_FLAGS, REGEX_ILLEGAL, RELATION, RESERVED, Rewriter, SHIFT, 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, last, locationDataToString, repeat, starts, throwSyntaxError, _ref, _ref1,
|
|
__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; };
|
|
|
|
_ref = require('./rewriter'), Rewriter = _ref.Rewriter, INVERSES = _ref.INVERSES;
|
|
|
|
_ref1 = require('./helpers'), count = _ref1.count, starts = _ref1.starts, compact = _ref1.compact, last = _ref1.last, repeat = _ref1.repeat, invertLiterate = _ref1.invertLiterate, locationDataToString = _ref1.locationDataToString, throwSyntaxError = _ref1.throwSyntaxError;
|
|
|
|
exports.Lexer = Lexer = (function() {
|
|
function Lexer() {}
|
|
|
|
Lexer.prototype.tokenize = function(code, opts) {
|
|
var consumed, end, i, _ref2;
|
|
if (opts == null) {
|
|
opts = {};
|
|
}
|
|
this.literate = opts.literate;
|
|
this.indent = 0;
|
|
this.baseIndent = 0;
|
|
this.indebt = 0;
|
|
this.outdebt = 0;
|
|
this.indents = [];
|
|
this.ends = [];
|
|
this.tokens = [];
|
|
this.chunkLine = opts.line || 0;
|
|
this.chunkColumn = opts.column || 0;
|
|
code = this.clean(code);
|
|
i = 0;
|
|
while (this.chunk = code.slice(i)) {
|
|
consumed = this.identifierToken() || this.commentToken() || this.whitespaceToken() || this.lineToken() || this.stringToken() || this.numberToken() || this.regexToken() || this.jsToken() || this.literalToken();
|
|
_ref2 = this.getLineAndColumnFromChunk(consumed), this.chunkLine = _ref2[0], this.chunkColumn = _ref2[1];
|
|
i += consumed;
|
|
if (opts.untilBalanced && this.ends.length === 0) {
|
|
return {
|
|
tokens: this.tokens,
|
|
index: i
|
|
};
|
|
}
|
|
}
|
|
this.closeIndentation();
|
|
if (end = this.ends.pop()) {
|
|
throwSyntaxError("missing " + end.tag, end.origin[2]);
|
|
}
|
|
if (opts.rewrite === false) {
|
|
return this.tokens;
|
|
}
|
|
return (new Rewriter).rewrite(this.tokens);
|
|
};
|
|
|
|
Lexer.prototype.clean = function(code) {
|
|
if (code.charCodeAt(0) === BOM) {
|
|
code = code.slice(1);
|
|
}
|
|
code = code.replace(/\r/g, '').replace(TRAILING_SPACES, '');
|
|
if (WHITESPACE.test(code)) {
|
|
code = "\n" + code;
|
|
this.chunkLine--;
|
|
}
|
|
if (this.literate) {
|
|
code = invertLiterate(code);
|
|
}
|
|
return code;
|
|
};
|
|
|
|
Lexer.prototype.identifierToken = function() {
|
|
var colon, colonOffset, forcedIdentifier, id, idLength, input, match, poppedToken, prev, tag, tagToken, _ref2, _ref3, _ref4;
|
|
if (!(match = IDENTIFIER.exec(this.chunk))) {
|
|
return 0;
|
|
}
|
|
input = match[0], id = match[1], colon = match[2];
|
|
idLength = id.length;
|
|
poppedToken = void 0;
|
|
if (id === 'own' && this.tag() === 'FOR') {
|
|
this.token('OWN', id);
|
|
return id.length;
|
|
}
|
|
if (id === 'from' && this.tag() === 'YIELD') {
|
|
this.token('FROM', id);
|
|
return id.length;
|
|
}
|
|
forcedIdentifier = colon || (prev = last(this.tokens)) && (((_ref2 = prev[0]) === '.' || _ref2 === '?.' || _ref2 === '::' || _ref2 === '?::') || !prev.spaced && prev[0] === '@');
|
|
tag = 'IDENTIFIER';
|
|
if (!forcedIdentifier && (__indexOf.call(JS_KEYWORDS, id) >= 0 || __indexOf.call(COFFEE_KEYWORDS, id) >= 0)) {
|
|
tag = id.toUpperCase();
|
|
if (tag === 'WHEN' && (_ref3 = this.tag(), __indexOf.call(LINE_BREAK, _ref3) >= 0)) {
|
|
tag = 'LEADING_WHEN';
|
|
} else if (tag === 'FOR') {
|
|
this.seenFor = true;
|
|
} else if (tag === 'UNLESS') {
|
|
tag = 'IF';
|
|
} else if (__indexOf.call(UNARY, tag) >= 0) {
|
|
tag = 'UNARY';
|
|
} else if (__indexOf.call(RELATION, tag) >= 0) {
|
|
if (tag !== 'INSTANCEOF' && this.seenFor) {
|
|
tag = 'FOR' + tag;
|
|
this.seenFor = false;
|
|
} else {
|
|
tag = 'RELATION';
|
|
if (this.value() === '!') {
|
|
poppedToken = this.tokens.pop();
|
|
id = '!' + id;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
if (__indexOf.call(JS_FORBIDDEN, id) >= 0) {
|
|
if (forcedIdentifier) {
|
|
tag = 'IDENTIFIER';
|
|
id = new String(id);
|
|
id.reserved = true;
|
|
} else if (__indexOf.call(RESERVED, id) >= 0) {
|
|
this.error("reserved word \"" + id + "\"");
|
|
}
|
|
}
|
|
if (!forcedIdentifier) {
|
|
if (__indexOf.call(COFFEE_ALIASES, id) >= 0) {
|
|
id = COFFEE_ALIAS_MAP[id];
|
|
}
|
|
tag = (function() {
|
|
switch (id) {
|
|
case '!':
|
|
return 'UNARY';
|
|
case '==':
|
|
case '!=':
|
|
return 'COMPARE';
|
|
case '&&':
|
|
case '||':
|
|
return 'LOGIC';
|
|
case 'true':
|
|
case 'false':
|
|
return 'BOOL';
|
|
case 'break':
|
|
case 'continue':
|
|
return 'STATEMENT';
|
|
default:
|
|
return tag;
|
|
}
|
|
})();
|
|
}
|
|
tagToken = this.token(tag, id, 0, idLength);
|
|
if (poppedToken) {
|
|
_ref4 = [poppedToken[2].first_line, poppedToken[2].first_column], tagToken[2].first_line = _ref4[0], tagToken[2].first_column = _ref4[1];
|
|
}
|
|
if (colon) {
|
|
colonOffset = input.lastIndexOf(':');
|
|
this.token(':', ':', colonOffset, colon.length);
|
|
}
|
|
return input.length;
|
|
};
|
|
|
|
Lexer.prototype.numberToken = function() {
|
|
var binaryLiteral, lexedLength, match, number, octalLiteral;
|
|
if (!(match = NUMBER.exec(this.chunk))) {
|
|
return 0;
|
|
}
|
|
number = match[0];
|
|
if (/^0[BOX]/.test(number)) {
|
|
this.error("radix prefix '" + number + "' must be lowercase");
|
|
} else if (/E/.test(number) && !/^0x/.test(number)) {
|
|
this.error("exponential notation '" + number + "' must be indicated with a lowercase 'e'");
|
|
} else if (/^0\d*[89]/.test(number)) {
|
|
this.error("decimal literal '" + number + "' must not be prefixed with '0'");
|
|
} else if (/^0\d+/.test(number)) {
|
|
this.error("octal literal '" + number + "' must be prefixed with '0o'");
|
|
}
|
|
lexedLength = number.length;
|
|
if (octalLiteral = /^0o([0-7]+)/.exec(number)) {
|
|
number = '0x' + parseInt(octalLiteral[1], 8).toString(16);
|
|
}
|
|
if (binaryLiteral = /^0b([01]+)/.exec(number)) {
|
|
number = '0x' + parseInt(binaryLiteral[1], 2).toString(16);
|
|
}
|
|
this.token('NUMBER', number, 0, lexedLength);
|
|
return lexedLength;
|
|
};
|
|
|
|
Lexer.prototype.stringToken = function() {
|
|
var $, attempt, doc, end, heredoc, i, indent, indentRegex, match, quote, regex, start, token, tokens, _ref2, _ref3;
|
|
quote = (STRING_START.exec(this.chunk) || [])[0];
|
|
if (!quote) {
|
|
return 0;
|
|
}
|
|
regex = (function() {
|
|
switch (quote) {
|
|
case "'":
|
|
return STRING_SINGLE;
|
|
case '"':
|
|
return STRING_DOUBLE;
|
|
case "'''":
|
|
return HEREDOC_SINGLE;
|
|
case '"""':
|
|
return HEREDOC_DOUBLE;
|
|
}
|
|
})();
|
|
heredoc = quote.length === 3;
|
|
start = quote.length;
|
|
_ref2 = this.matchWithInterpolations(this.chunk.slice(start), regex, quote, start), tokens = _ref2.tokens, end = _ref2.index;
|
|
$ = tokens.length - 1;
|
|
if (heredoc) {
|
|
indent = null;
|
|
doc = ((function() {
|
|
var _i, _len, _results;
|
|
_results = [];
|
|
for (i = _i = 0, _len = tokens.length; _i < _len; i = ++_i) {
|
|
token = tokens[i];
|
|
if (token[0] === 'NEOSTRING') {
|
|
_results.push(token[1]);
|
|
}
|
|
}
|
|
return _results;
|
|
})()).join('#{}');
|
|
while (match = HEREDOC_INDENT.exec(doc)) {
|
|
attempt = match[1];
|
|
if (indent === null || (0 < (_ref3 = attempt.length) && _ref3 < indent.length)) {
|
|
indent = attempt;
|
|
}
|
|
}
|
|
if (indent) {
|
|
indentRegex = RegExp("^" + indent, "gm");
|
|
}
|
|
this.mergeInterpolationTokens(tokens, {
|
|
quote: quote[0],
|
|
start: start,
|
|
end: end
|
|
}, (function(_this) {
|
|
return function(value, i) {
|
|
value = _this.formatString(value);
|
|
if (i === 0) {
|
|
value = value.replace(LEADING_BLANK_LINE, '');
|
|
}
|
|
if (i === $) {
|
|
value = value.replace(TRAILING_BLANK_LINE, '');
|
|
}
|
|
value = value.replace(indentRegex, '');
|
|
value = value.replace(MULTILINER, '\\n');
|
|
return value;
|
|
};
|
|
})(this));
|
|
} else {
|
|
this.mergeInterpolationTokens(tokens, {
|
|
quote: quote,
|
|
start: start,
|
|
end: end
|
|
}, (function(_this) {
|
|
return function(value, i) {
|
|
value = _this.formatString(value);
|
|
value = value.replace(STRING_OMIT, function(match, offset) {
|
|
if ((i === 0 && offset === 0) || (i === $ && offset + match.length === value.length)) {
|
|
return '';
|
|
} else {
|
|
return ' ';
|
|
}
|
|
});
|
|
return value;
|
|
};
|
|
})(this));
|
|
}
|
|
return end;
|
|
};
|
|
|
|
Lexer.prototype.commentToken = function() {
|
|
var comment, here, match;
|
|
if (!(match = this.chunk.match(COMMENT))) {
|
|
return 0;
|
|
}
|
|
comment = match[0], here = match[1];
|
|
if (here) {
|
|
if (match = HERECOMMENT_ILLEGAL.exec(comment)) {
|
|
this.error("block comments cannot contain " + match[0], match.index);
|
|
}
|
|
if (here.indexOf('\n') >= 0) {
|
|
here = here.replace(RegExp("\\n" + (repeat(' ', this.indent)), "g"), '\n');
|
|
}
|
|
this.token('HERECOMMENT', here, 0, comment.length);
|
|
}
|
|
return comment.length;
|
|
};
|
|
|
|
Lexer.prototype.jsToken = function() {
|
|
var match, script;
|
|
if (!(this.chunk.charAt(0) === '`' && (match = JSTOKEN.exec(this.chunk)))) {
|
|
return 0;
|
|
}
|
|
this.token('JS', (script = match[0]).slice(1, -1), 0, script.length);
|
|
return script.length;
|
|
};
|
|
|
|
Lexer.prototype.regexToken = function() {
|
|
var closed, end, flags, index, match, prev, re, regex, tokens, _ref2, _ref3, _ref4;
|
|
switch (false) {
|
|
case !(match = REGEX_ILLEGAL.exec(this.chunk)):
|
|
this.error("regular expressions cannot begin with " + match[2], match.index + match[1].length);
|
|
break;
|
|
case this.chunk.slice(0, 3) !== '///':
|
|
_ref2 = this.matchWithInterpolations(this.chunk.slice(3), HEREGEX, '///', 3), tokens = _ref2.tokens, index = _ref2.index;
|
|
break;
|
|
case !(match = REGEX.exec(this.chunk)):
|
|
regex = match[0], closed = match[1];
|
|
index = regex.length;
|
|
prev = last(this.tokens);
|
|
if (prev) {
|
|
if (prev.spaced && (_ref3 = prev[0], __indexOf.call(CALLABLE, _ref3) >= 0)) {
|
|
if (!closed || POSSIBLY_DIVISION.test(regex)) {
|
|
return 0;
|
|
}
|
|
} else if (_ref4 = prev[0], __indexOf.call(NOT_REGEX, _ref4) >= 0) {
|
|
return 0;
|
|
}
|
|
}
|
|
if (!closed) {
|
|
this.error('missing / (unclosed regex)');
|
|
}
|
|
break;
|
|
default:
|
|
return 0;
|
|
}
|
|
flags = REGEX_FLAGS.exec(this.chunk.slice(index))[0];
|
|
end = index + flags.length;
|
|
switch (false) {
|
|
case !!VALID_FLAGS.test(flags):
|
|
this.error("invalid regular expression flags " + flags, index);
|
|
break;
|
|
case !regex:
|
|
this.token('REGEX', "" + regex + flags);
|
|
break;
|
|
case tokens.length !== 1:
|
|
re = this.formatHeregex(tokens[0][1]).replace(/\//g, '\\/');
|
|
this.token('REGEX', "/" + (re || '(?:)') + "/" + flags);
|
|
break;
|
|
default:
|
|
this.token('IDENTIFIER', 'RegExp', 0, 0);
|
|
this.token('CALL_START', '(', 0, 0);
|
|
this.mergeInterpolationTokens(tokens, {
|
|
quote: '"',
|
|
start: 3,
|
|
end: end
|
|
}, (function(_this) {
|
|
return function(value) {
|
|
return _this.formatHeregex(value).replace(/\\/g, '\\\\');
|
|
};
|
|
})(this));
|
|
if (flags) {
|
|
this.token(',', ',', index, 0);
|
|
this.token('STRING', '"' + flags + '"', index, flags.length);
|
|
}
|
|
this.token(')', ')', end, 0);
|
|
}
|
|
return end;
|
|
};
|
|
|
|
Lexer.prototype.lineToken = function() {
|
|
var diff, indent, match, noNewlines, size;
|
|
if (!(match = MULTI_DENT.exec(this.chunk))) {
|
|
return 0;
|
|
}
|
|
indent = match[0];
|
|
this.seenFor = false;
|
|
size = indent.length - 1 - indent.lastIndexOf('\n');
|
|
noNewlines = this.unfinished();
|
|
if (size - this.indebt === this.indent) {
|
|
if (noNewlines) {
|
|
this.suppressNewlines();
|
|
} else {
|
|
this.newlineToken(0);
|
|
}
|
|
return indent.length;
|
|
}
|
|
if (size > this.indent) {
|
|
if (noNewlines) {
|
|
this.indebt = size - this.indent;
|
|
this.suppressNewlines();
|
|
return indent.length;
|
|
}
|
|
if (!this.tokens.length) {
|
|
this.baseIndent = this.indent = size;
|
|
return indent.length;
|
|
}
|
|
diff = size - this.indent + this.outdebt;
|
|
this.token('INDENT', diff, indent.length - size, size);
|
|
this.indents.push(diff);
|
|
this.ends.push({
|
|
tag: 'OUTDENT'
|
|
});
|
|
this.outdebt = this.indebt = 0;
|
|
this.indent = size;
|
|
} else if (size < this.baseIndent) {
|
|
this.error('missing indentation', indent.length);
|
|
} else {
|
|
this.indebt = 0;
|
|
this.outdentToken(this.indent - size, noNewlines, indent.length);
|
|
}
|
|
return indent.length;
|
|
};
|
|
|
|
Lexer.prototype.outdentToken = function(moveOut, noNewlines, outdentLength) {
|
|
var decreasedIndent, dent, lastIndent, _ref2;
|
|
decreasedIndent = this.indent - moveOut;
|
|
while (moveOut > 0) {
|
|
lastIndent = this.indents[this.indents.length - 1];
|
|
if (!lastIndent) {
|
|
moveOut = 0;
|
|
} else if (lastIndent === this.outdebt) {
|
|
moveOut -= this.outdebt;
|
|
this.outdebt = 0;
|
|
} else if (lastIndent < this.outdebt) {
|
|
this.outdebt -= lastIndent;
|
|
moveOut -= lastIndent;
|
|
} else {
|
|
dent = this.indents.pop() + this.outdebt;
|
|
if (outdentLength && (_ref2 = this.chunk[outdentLength], __indexOf.call(INDENTABLE_CLOSERS, _ref2) >= 0)) {
|
|
decreasedIndent -= dent - moveOut;
|
|
moveOut = dent;
|
|
}
|
|
this.outdebt = 0;
|
|
this.pair('OUTDENT');
|
|
this.token('OUTDENT', moveOut, 0, outdentLength);
|
|
moveOut -= dent;
|
|
}
|
|
}
|
|
if (dent) {
|
|
this.outdebt -= moveOut;
|
|
}
|
|
while (this.value() === ';') {
|
|
this.tokens.pop();
|
|
}
|
|
if (!(this.tag() === 'TERMINATOR' || noNewlines)) {
|
|
this.token('TERMINATOR', '\n', outdentLength, 0);
|
|
}
|
|
this.indent = decreasedIndent;
|
|
return this;
|
|
};
|
|
|
|
Lexer.prototype.whitespaceToken = function() {
|
|
var match, nline, prev;
|
|
if (!((match = WHITESPACE.exec(this.chunk)) || (nline = this.chunk.charAt(0) === '\n'))) {
|
|
return 0;
|
|
}
|
|
prev = last(this.tokens);
|
|
if (prev) {
|
|
prev[match ? 'spaced' : 'newLine'] = true;
|
|
}
|
|
if (match) {
|
|
return match[0].length;
|
|
} else {
|
|
return 0;
|
|
}
|
|
};
|
|
|
|
Lexer.prototype.newlineToken = function(offset) {
|
|
while (this.value() === ';') {
|
|
this.tokens.pop();
|
|
}
|
|
if (this.tag() !== 'TERMINATOR') {
|
|
this.token('TERMINATOR', '\n', offset, 0);
|
|
}
|
|
return this;
|
|
};
|
|
|
|
Lexer.prototype.suppressNewlines = function() {
|
|
if (this.value() === '\\') {
|
|
this.tokens.pop();
|
|
}
|
|
return this;
|
|
};
|
|
|
|
Lexer.prototype.literalToken = function() {
|
|
var match, prev, tag, token, value, _ref2, _ref3, _ref4, _ref5;
|
|
if (match = OPERATOR.exec(this.chunk)) {
|
|
value = match[0];
|
|
if (CODE.test(value)) {
|
|
this.tagParameters();
|
|
}
|
|
} else {
|
|
value = this.chunk.charAt(0);
|
|
}
|
|
tag = value;
|
|
prev = last(this.tokens);
|
|
if (value === '=' && prev) {
|
|
if (!prev[1].reserved && (_ref2 = prev[1], __indexOf.call(JS_FORBIDDEN, _ref2) >= 0)) {
|
|
this.error("reserved word \"" + (this.value()) + "\" can't be assigned");
|
|
}
|
|
if ((_ref3 = prev[1]) === '||' || _ref3 === '&&') {
|
|
prev[0] = 'COMPOUND_ASSIGN';
|
|
prev[1] += '=';
|
|
return value.length;
|
|
}
|
|
}
|
|
if (value === ';') {
|
|
this.seenFor = false;
|
|
tag = 'TERMINATOR';
|
|
} else if (__indexOf.call(MATH, value) >= 0) {
|
|
tag = 'MATH';
|
|
} else if (__indexOf.call(COMPARE, value) >= 0) {
|
|
tag = 'COMPARE';
|
|
} else if (__indexOf.call(COMPOUND_ASSIGN, value) >= 0) {
|
|
tag = 'COMPOUND_ASSIGN';
|
|
} else if (__indexOf.call(UNARY, value) >= 0) {
|
|
tag = 'UNARY';
|
|
} else if (__indexOf.call(UNARY_MATH, value) >= 0) {
|
|
tag = 'UNARY_MATH';
|
|
} else if (__indexOf.call(SHIFT, value) >= 0) {
|
|
tag = 'SHIFT';
|
|
} else if (__indexOf.call(LOGIC, value) >= 0 || value === '?' && (prev != null ? prev.spaced : void 0)) {
|
|
tag = 'LOGIC';
|
|
} else if (prev && !prev.spaced) {
|
|
if (value === '(' && (_ref4 = prev[0], __indexOf.call(CALLABLE, _ref4) >= 0)) {
|
|
if (prev[0] === '?') {
|
|
prev[0] = 'FUNC_EXIST';
|
|
}
|
|
tag = 'CALL_START';
|
|
} else if (value === '[' && (_ref5 = prev[0], __indexOf.call(INDEXABLE, _ref5) >= 0)) {
|
|
tag = 'INDEX_START';
|
|
switch (prev[0]) {
|
|
case '?':
|
|
prev[0] = 'INDEX_SOAK';
|
|
}
|
|
}
|
|
}
|
|
token = this.makeToken(tag, value);
|
|
switch (value) {
|
|
case '(':
|
|
case '{':
|
|
case '[':
|
|
this.ends.push({
|
|
tag: INVERSES[value],
|
|
origin: token
|
|
});
|
|
break;
|
|
case ')':
|
|
case '}':
|
|
case ']':
|
|
this.pair(value);
|
|
}
|
|
this.tokens.push(token);
|
|
return value.length;
|
|
};
|
|
|
|
Lexer.prototype.tagParameters = function() {
|
|
var i, stack, tok, tokens;
|
|
if (this.tag() !== ')') {
|
|
return this;
|
|
}
|
|
stack = [];
|
|
tokens = this.tokens;
|
|
i = tokens.length;
|
|
tokens[--i][0] = 'PARAM_END';
|
|
while (tok = tokens[--i]) {
|
|
switch (tok[0]) {
|
|
case ')':
|
|
stack.push(tok);
|
|
break;
|
|
case '(':
|
|
case 'CALL_START':
|
|
if (stack.length) {
|
|
stack.pop();
|
|
} else if (tok[0] === '(') {
|
|
tok[0] = 'PARAM_START';
|
|
return this;
|
|
} else {
|
|
return this;
|
|
}
|
|
}
|
|
}
|
|
return this;
|
|
};
|
|
|
|
Lexer.prototype.closeIndentation = function() {
|
|
return this.outdentToken(this.indent);
|
|
};
|
|
|
|
Lexer.prototype.matchWithInterpolations = function(str, regex, end, offsetInChunk) {
|
|
var column, index, line, nested, strPart, tokens, _ref2, _ref3, _ref4;
|
|
tokens = [];
|
|
while (true) {
|
|
strPart = regex.exec(str)[0];
|
|
tokens.push(this.makeToken('NEOSTRING', strPart, offsetInChunk));
|
|
str = str.slice(strPart.length);
|
|
offsetInChunk += strPart.length;
|
|
if (str.slice(0, 2) !== '#{') {
|
|
break;
|
|
}
|
|
_ref2 = this.getLineAndColumnFromChunk(offsetInChunk + 1), line = _ref2[0], column = _ref2[1];
|
|
_ref3 = new Lexer().tokenize(str.slice(1), {
|
|
line: line,
|
|
column: column,
|
|
untilBalanced: true
|
|
}), nested = _ref3.tokens, index = _ref3.index;
|
|
index += 1;
|
|
nested.shift();
|
|
nested.pop();
|
|
if (((_ref4 = nested[0]) != null ? _ref4[0] : void 0) === 'TERMINATOR') {
|
|
nested.shift();
|
|
}
|
|
if (nested.length > 1) {
|
|
nested.unshift(this.makeToken('(', '(', offsetInChunk + 1, 0));
|
|
nested.push(this.makeToken(')', ')', offsetInChunk + 1 + index, 0));
|
|
}
|
|
tokens.push(['TOKENS', nested]);
|
|
str = str.slice(index);
|
|
offsetInChunk += index;
|
|
}
|
|
if (str.slice(0, end.length) !== end) {
|
|
this.error("missing " + end);
|
|
}
|
|
return {
|
|
tokens: tokens,
|
|
index: offsetInChunk + end.length
|
|
};
|
|
};
|
|
|
|
Lexer.prototype.mergeInterpolationTokens = function(tokens, _arg, fn) {
|
|
var converted, end, errorToken, firstEmptyStringIndex, firstIndex, i, interpolated, locationToken, plusToken, quote, rparen, start, tag, token, tokensToPush, value, _i, _len, _ref2;
|
|
quote = _arg.quote, start = _arg.start, end = _arg.end;
|
|
if (interpolated = tokens.length > 1) {
|
|
errorToken = this.makeToken('', 'interpolation', start + tokens[0][1].length, 2);
|
|
this.token('(', '(', 0, 0, errorToken);
|
|
}
|
|
firstIndex = this.tokens.length;
|
|
for (i = _i = 0, _len = tokens.length; _i < _len; i = ++_i) {
|
|
token = tokens[i];
|
|
tag = token[0], value = token[1];
|
|
switch (tag) {
|
|
case 'TOKENS':
|
|
if (value.length === 0) {
|
|
continue;
|
|
}
|
|
locationToken = value[0];
|
|
tokensToPush = value;
|
|
break;
|
|
case 'NEOSTRING':
|
|
converted = fn(token[1], i);
|
|
if (converted.length === 0) {
|
|
if (i === 0) {
|
|
firstEmptyStringIndex = this.tokens.length;
|
|
} else {
|
|
continue;
|
|
}
|
|
}
|
|
if (i === 2 && (firstEmptyStringIndex != null)) {
|
|
this.tokens.splice(firstEmptyStringIndex, 2);
|
|
}
|
|
token[0] = 'STRING';
|
|
token[1] = this.makeString(converted, quote);
|
|
locationToken = token;
|
|
tokensToPush = [token];
|
|
}
|
|
if (this.tokens.length > firstIndex) {
|
|
plusToken = this.token('+', '+');
|
|
plusToken[2] = {
|
|
first_line: locationToken[2].first_line,
|
|
first_column: locationToken[2].first_column,
|
|
last_line: locationToken[2].first_line,
|
|
last_column: locationToken[2].first_column
|
|
};
|
|
}
|
|
(_ref2 = this.tokens).push.apply(_ref2, tokensToPush);
|
|
}
|
|
if (interpolated) {
|
|
rparen = this.token(')', ')', end, 0);
|
|
return rparen.stringEnd = true;
|
|
}
|
|
};
|
|
|
|
Lexer.prototype.pair = function(tag) {
|
|
var wanted, _ref2;
|
|
if (tag !== (wanted = (_ref2 = last(this.ends)) != null ? _ref2.tag : void 0)) {
|
|
if ('OUTDENT' !== wanted) {
|
|
this.error("unmatched " + tag);
|
|
}
|
|
this.outdentToken(last(this.indents), true);
|
|
return this.pair(tag);
|
|
}
|
|
return this.ends.pop();
|
|
};
|
|
|
|
Lexer.prototype.getLineAndColumnFromChunk = function(offset) {
|
|
var column, lineCount, lines, string;
|
|
if (offset === 0) {
|
|
return [this.chunkLine, this.chunkColumn];
|
|
}
|
|
if (offset >= this.chunk.length) {
|
|
string = this.chunk;
|
|
} else {
|
|
string = this.chunk.slice(0, +(offset - 1) + 1 || 9e9);
|
|
}
|
|
lineCount = count(string, '\n');
|
|
column = this.chunkColumn;
|
|
if (lineCount > 0) {
|
|
lines = string.split('\n');
|
|
column = last(lines).length;
|
|
} else {
|
|
column += string.length;
|
|
}
|
|
return [this.chunkLine + lineCount, column];
|
|
};
|
|
|
|
Lexer.prototype.makeToken = function(tag, value, offsetInChunk, length) {
|
|
var lastCharacter, locationData, token, _ref2, _ref3;
|
|
if (offsetInChunk == null) {
|
|
offsetInChunk = 0;
|
|
}
|
|
if (length == null) {
|
|
length = value.length;
|
|
}
|
|
locationData = {};
|
|
_ref2 = this.getLineAndColumnFromChunk(offsetInChunk), locationData.first_line = _ref2[0], locationData.first_column = _ref2[1];
|
|
lastCharacter = Math.max(0, length - 1);
|
|
_ref3 = this.getLineAndColumnFromChunk(offsetInChunk + lastCharacter), locationData.last_line = _ref3[0], locationData.last_column = _ref3[1];
|
|
token = [tag, value, locationData];
|
|
return token;
|
|
};
|
|
|
|
Lexer.prototype.token = function(tag, value, offsetInChunk, length, origin) {
|
|
var token;
|
|
token = this.makeToken(tag, value, offsetInChunk, length);
|
|
if (origin) {
|
|
token.origin = origin;
|
|
}
|
|
this.tokens.push(token);
|
|
return token;
|
|
};
|
|
|
|
Lexer.prototype.tag = function(index, tag) {
|
|
var tok;
|
|
return (tok = last(this.tokens, index)) && (tag ? tok[0] = tag : tok[0]);
|
|
};
|
|
|
|
Lexer.prototype.value = function(index, val) {
|
|
var tok;
|
|
return (tok = last(this.tokens, index)) && (val ? tok[1] = val : tok[1]);
|
|
};
|
|
|
|
Lexer.prototype.unfinished = function() {
|
|
var _ref2;
|
|
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');
|
|
};
|
|
|
|
Lexer.prototype.formatString = function(str) {
|
|
return str.replace(/\\[^\S\n]*(\n|\\)\s*/g, function(escaped, character) {
|
|
if (character === '\n') {
|
|
return '';
|
|
} else {
|
|
return escaped;
|
|
}
|
|
});
|
|
};
|
|
|
|
Lexer.prototype.formatHeregex = function(str) {
|
|
return str.replace(HEREGEX_OMIT, '$1$2').replace(MULTILINER, '\\n');
|
|
};
|
|
|
|
Lexer.prototype.makeString = function(body, quote) {
|
|
var match;
|
|
if (!body) {
|
|
return quote + quote;
|
|
}
|
|
body = body.replace(RegExp("\\\\(" + quote + "|\\\\)", "g"), function(match, contents) {
|
|
if (contents === quote) {
|
|
return contents;
|
|
} else {
|
|
return match;
|
|
}
|
|
});
|
|
body = body.replace(RegExp("" + quote, "g"), '\\$&');
|
|
if (match = OCTAL_ESCAPE.exec(body)) {
|
|
this.error("octal escape sequences are not allowed " + match[2], match.index + match[1].length + 1);
|
|
}
|
|
return quote + body + quote;
|
|
};
|
|
|
|
Lexer.prototype.error = function(message, offset) {
|
|
var first_column, first_line, _ref2;
|
|
if (offset == null) {
|
|
offset = 0;
|
|
}
|
|
_ref2 = this.getLineAndColumnFromChunk(offset), first_line = _ref2[0], first_column = _ref2[1];
|
|
return throwSyntaxError(message, {
|
|
first_line: first_line,
|
|
first_column: first_column
|
|
});
|
|
};
|
|
|
|
return Lexer;
|
|
|
|
})();
|
|
|
|
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'];
|
|
|
|
COFFEE_KEYWORDS = ['undefined', 'then', 'unless', 'until', 'loop', 'of', 'by', 'when'];
|
|
|
|
COFFEE_ALIAS_MAP = {
|
|
and: '&&',
|
|
or: '||',
|
|
is: '==',
|
|
isnt: '!=',
|
|
not: '!',
|
|
yes: 'true',
|
|
no: 'false',
|
|
on: 'true',
|
|
off: 'false'
|
|
};
|
|
|
|
COFFEE_ALIASES = (function() {
|
|
var _results;
|
|
_results = [];
|
|
for (key in COFFEE_ALIAS_MAP) {
|
|
_results.push(key);
|
|
}
|
|
return _results;
|
|
})();
|
|
|
|
COFFEE_KEYWORDS = COFFEE_KEYWORDS.concat(COFFEE_ALIASES);
|
|
|
|
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'];
|
|
|
|
STRICT_PROSCRIBED = ['arguments', 'eval', 'yield*'];
|
|
|
|
JS_FORBIDDEN = JS_KEYWORDS.concat(RESERVED).concat(STRICT_PROSCRIBED);
|
|
|
|
exports.RESERVED = RESERVED.concat(JS_KEYWORDS).concat(COFFEE_KEYWORDS).concat(STRICT_PROSCRIBED);
|
|
|
|
exports.STRICT_PROSCRIBED = STRICT_PROSCRIBED;
|
|
|
|
BOM = 65279;
|
|
|
|
IDENTIFIER = /^(?!\d)((?:(?!\s)[$\w\x7f-\uffff])+)([^\n\S]*:(?!:))?/;
|
|
|
|
NUMBER = /^0b[01]+|^0o[0-7]+|^0x[\da-f]+|^\d*\.?\d+(?:e[+-]?\d+)?/i;
|
|
|
|
OPERATOR = /^(?:[-=]>|[-+*\/%<>&|^!?=]=|>>>=?|([-+:])\1|([&|<>*\/%])\2=?|\?(\.|::)|\.{2,3})/;
|
|
|
|
WHITESPACE = /^[^\n\S]+/;
|
|
|
|
COMMENT = /^###([^#][\s\S]*?)(?:###[^\n\S]*|###$)|^(?:\s*#(?!##[^#]).*)+/;
|
|
|
|
CODE = /^[-=]>/;
|
|
|
|
MULTI_DENT = /^(?:\n[^\n\S]*)+/;
|
|
|
|
JSTOKEN = /^`[^\\`]*(?:\\.[^\\`]*)*`/;
|
|
|
|
STRING_START = /^(?:'''|"""|'|")/;
|
|
|
|
STRING_SINGLE = /^(?:[^\\']|\\[\s\S])*/;
|
|
|
|
STRING_DOUBLE = /^(?:[^\\"#]|\\[\s\S]|\#(?!\{))*/;
|
|
|
|
HEREDOC_SINGLE = /^(?:[^\\']|\\[\s\S]|'(?!''))*/;
|
|
|
|
HEREDOC_DOUBLE = /^(?:[^\\"#]|\\[\s\S]|"(?!"")|\#(?!\{))*/;
|
|
|
|
STRING_OMIT = /\s*\n\s*/g;
|
|
|
|
HEREDOC_INDENT = /\n+([^\n\S]*)(?=\S)/g;
|
|
|
|
REGEX = /^\/(?!\/)(?:[^[\/\n\\]|\\.|\[(?:\\.|[^\]\n\\])*])*(\/)?/;
|
|
|
|
REGEX_FLAGS = /^\w*/;
|
|
|
|
VALID_FLAGS = /^(?!.*(.).*\1)[imgy]*$/;
|
|
|
|
HEREGEX = /^(?:[^\\\/#]|\\[\s\S]|\/(?!\/\/)|\#(?!\{))*/;
|
|
|
|
HEREGEX_OMIT = /((?:\\\\)+)|\\(\s|\/)|\s+(?:#.*)?/g;
|
|
|
|
REGEX_ILLEGAL = /^(\/|\/{3}\s*)(\*)/;
|
|
|
|
POSSIBLY_DIVISION = /^\/=?\s/;
|
|
|
|
MULTILINER = /\n/g;
|
|
|
|
HERECOMMENT_ILLEGAL = /\*\//;
|
|
|
|
LINE_CONTINUER = /^\s*(?:,|\??\.(?![.\d])|::)/;
|
|
|
|
OCTAL_ESCAPE = /^((?:\\.|[^\\])*)(\\(?:0[0-7]|[1-7]))/;
|
|
|
|
LEADING_BLANK_LINE = /^[^\n\S]*\n/;
|
|
|
|
TRAILING_BLANK_LINE = /\n[^\n\S]*$/;
|
|
|
|
TRAILING_SPACES = /\s+$/;
|
|
|
|
COMPOUND_ASSIGN = ['-=', '+=', '/=', '*=', '%=', '||=', '&&=', '?=', '<<=', '>>=', '>>>=', '&=', '^=', '|=', '**=', '//=', '%%='];
|
|
|
|
UNARY = ['NEW', 'TYPEOF', 'DELETE', 'DO'];
|
|
|
|
UNARY_MATH = ['!', '~'];
|
|
|
|
LOGIC = ['&&', '||', '&', '|', '^'];
|
|
|
|
SHIFT = ['<<', '>>', '>>>'];
|
|
|
|
COMPARE = ['==', '!=', '<', '>', '<=', '>='];
|
|
|
|
MATH = ['*', '/', '%', '//', '%%'];
|
|
|
|
RELATION = ['IN', 'OF', 'INSTANCEOF'];
|
|
|
|
BOOL = ['TRUE', 'FALSE'];
|
|
|
|
CALLABLE = ['IDENTIFIER', ')', ']', '?', '@', 'THIS', 'SUPER'];
|
|
|
|
INDEXABLE = CALLABLE.concat(['NUMBER', 'STRING', 'REGEX', 'BOOL', 'NULL', 'UNDEFINED', '}', '::']);
|
|
|
|
NOT_REGEX = INDEXABLE.concat(['++', '--']);
|
|
|
|
LINE_BREAK = ['INDENT', 'OUTDENT', 'TERMINATOR'];
|
|
|
|
INDENTABLE_CLOSERS = [')', '}', ']'];
|
|
|
|
}).call(this);
|