github/coffeescript
1
1
Fork 0
mirror of https://github.com/jashkenas/coffeescript.git synced 2026-02-19 03:44:23 -05:00
Code Issues Packages Projects Releases Wiki Activity

disabled interpolations in normal regexes

Browse Source
This commit is contained in:
satyr
2010-10-04 21:50:50 +09:00
parent 493fa7d8fe
commit cdd033ffb0
10 changed files with 194 additions and 243 deletions
Download Patch File Download Diff File Expand all files Collapse all files

116
lib/lexer.js
View File

@@ -1,5 +1,5 @@
(function() {
var ASSIGNED, CALLABLE, CODE, COFFEE_ALIASES, COFFEE_KEYWORDS, COMMENT, COMPARE, COMPOUND_ASSIGN, CONVERSIONS, HEREDOC, HEREDOC_INDENT, HEREGEX, HEREGEX_OMIT, IDENTIFIER, JSTOKEN, JS_FORBIDDEN, JS_KEYWORDS, LEADING_SPACES, LINE_BREAK, LOGIC, Lexer, MATH, MULTILINER, MULTI_DENT, NEXT_CHARACTER, NOT_REGEX, NO_NEWLINE, NUMBER, OPERATOR, REGEX_END, REGEX_ESCAPE, REGEX_START, RESERVED, Rewriter, SHIFT, SIMPLESTR, TRAILING_SPACES, UNARY, WHITESPACE, _ref, compact, count, include, last, starts;
var ASSIGNED, CALLABLE, CODE, COFFEE_ALIASES, COFFEE_KEYWORDS, COMMENT, COMPARE, COMPOUND_ASSIGN, CONVERSIONS, HEREDOC, HEREDOC_INDENT, HEREGEX, HEREGEX_OMIT, IDENTIFIER, JSTOKEN, JS_FORBIDDEN, JS_KEYWORDS, LEADING_SPACES, LINE_BREAK, LOGIC, Lexer, MATH, MULTILINER, MULTI_DENT, NEXT_CHARACTER, NOT_REGEX, NO_NEWLINE, NUMBER, OPERATOR, REGEX, RESERVED, Rewriter, SHIFT, SIMPLESTR, TRAILING_SPACES, UNARY, WHITESPACE, _ref, compact, count, include, last, starts;
Rewriter = require('./rewriter').Rewriter;
_ref = require('./helpers'), include = _ref.include, count = _ref.count, starts = _ref.starts, compact = _ref.compact, last = _ref.last;
exports.Lexer = (function() {
@@ -49,7 +49,7 @@
if (include(JS_FORBIDDEN, id)) {
if (forcedIdentifier) {
tag = 'STRING';
id = ("\"" + (id) + "\"");
id = ("\"" + id + "\"");
if (forcedIdentifier === 'accessor') {
closeIndex = true;
if (this.tag() !== '@') {
@@ -165,60 +165,55 @@
return true;
};
Lexer.prototype.regexToken = function() {
var _ref2, end, first, flags, match, regex, str;
var match;
if (this.chunk.charAt(0) !== '/') {
return false;
}
if (match = HEREGEX.exec(this.chunk)) {
return this.heregexToken(match);
}
if (!(first = REGEX_START.exec(this.chunk))) {
return false;
}
if (first[1] === ' ' && !('CALL_START' === (_ref2 = this.tag()) || '=' === _ref2)) {
return false;
}
if (include(NOT_REGEX, this.tag())) {
return false;
}
if (!(regex = this.balancedString(this.chunk, [['/', '/']]))) {
if (!(match = REGEX.exec(this.chunk))) {
return false;
}
if (!(end = this.chunk.slice(regex.length).match(REGEX_END))) {
return false;
}
flags = end[0];
if (~regex.indexOf('#{')) {
str = regex.slice(1, -1);
this.tokens.push(['IDENTIFIER', 'RegExp'], ['CALL_START', '(']);
this.interpolateString("\"" + (str) + "\"", {
regex: true
});
if (flags) {
this.tokens.push([',', ','], ['STRING', ("\"" + (flags) + "\"")]);
}
this.tokens.push(['CALL_END', ')']);
} else {
this.token('REGEX', regex + flags);
}
this.i += regex.length + flags.length;
this.token('REGEX', match[0]);
this.i += match[0].length;
return true;
};
Lexer.prototype.heregexToken = function(match) {
var _ref2, body, flags, heregex, re;
var _i, _len, _ref2, _ref3, _this, body, flags, heregex, re, tag, tokens, value;
_ref2 = match, heregex = _ref2[0], body = _ref2[1], flags = _ref2[2];
this.i += heregex.length;
if (!(~body.indexOf('#{'))) {
re = body.replace(HEREGEX_OMIT, '').replace(/\//g, '\\/');
this.token('REGEX', "/" + (re || '(?:)') + "/" + (flags));
this.token('REGEX', "/" + (re || '(?:)') + "/" + flags);
return true;
}
this.token('IDENTIFIER', 'RegExp');
this.tokens.push(['CALL_START', '(']);
this.interpolateString("\"" + (body) + "\"", {
regex: true,
heregex: true
tokens = [];
_ref2 = this.interpolateString('"' + body + '"', {
regex: true
});
for (_i = 0, _len = _ref2.length; _i < _len; _i++) {
_ref3 = _ref2[_i], tag = _ref3[0], value = _ref3[1];
if (tag === 'TOKENS') {
tokens.push.apply(tokens, value);
} else {
if (!(value = value.slice(1, -1).replace(HEREGEX_OMIT, ''))) {
continue;
}
tokens.push(['STRING', '"' + value.replace(/[\\\"]/g, '\\$&') + '"']);
}
tokens.push(['+', '+']);
}
tokens.pop();
if ((((_ref2 = tokens[0]) != null) ? _ref2[0] !== 'STRING' : undefined)) {
this.tokens.push(['STRING', '""'], ['+', '+']);
}
(_this = this.tokens).push.apply(_this, tokens);
if (flags) {
this.tokens.push([',', ','], ['STRING', '"' + flags + '"']);
}
@@ -404,7 +399,7 @@
}
}
if (indent) {
doc = doc.replace(RegExp("\\n" + (indent), "g"), '\n');
doc = doc.replace(RegExp("\\n" + indent, "g"), '\n');
}
if (herecomment) {
return doc;
@@ -414,7 +409,7 @@
doc = doc.replace(/\\([\s\S])/g, function(m, c) {
return ('\n' === c || quote === c) ? c : m;
});
doc = doc.replace(RegExp("" + (quote), "g"), '\\$&');
doc = doc.replace(RegExp("" + quote, "g"), '\\$&');
if (quote === "'") {
doc = this.escapeLines(doc, true);
}
@@ -448,15 +443,14 @@
return this.outdentToken(this.indent);
};
Lexer.prototype.identifierError = function(word) {
throw new Error("SyntaxError: Reserved word \"" + (word) + "\" on line " + (this.line + 1));
throw new Error("SyntaxError: Reserved word \"" + word + "\" on line " + (this.line + 1));
};
Lexer.prototype.assignmentError = function() {
throw new Error("SyntaxError: Reserved word \"" + (this.value()) + "\" on line " + (this.line + 1) + " can't be assigned");
};
Lexer.prototype.balancedString = function(str, delimited, options) {
var _i, _len, _ref2, close, i, levels, open, pair, slash, slen;
var _i, _len, _ref2, close, i, levels, open, pair, slen;
options || (options = {});
slash = delimited[0][0] === '/';
levels = [];
i = 0;
slen = str.length;
@@ -482,21 +476,18 @@
}
}
}
if (!levels.length || slash && str.charAt(i) === '\n') {
if (!levels.length) {
break;
}
i += 1;
}
if (levels.length) {
if (slash) {
return false;
}
throw new Error("SyntaxError: Unterminated " + (levels.pop()[0]) + " starting on line " + (this.line + 1));
}
return !i ? false : str.slice(0, i);
};
Lexer.prototype.interpolateString = function(str, options) {
var _i, _len, _ref2, char, expr, heredoc, i, inner, interpolated, lexer, nested, pi, push, regex, s, tag, tok, tokens, value;
var _i, _len, _ref2, _this, char, expr, heredoc, i, inner, interpolated, lexer, nested, pi, regex, tag, tok, tokens, value;
if (str.length < 5) {
return this.token('STRING', this.escapeLines(str, heredoc));
}
@@ -514,14 +505,14 @@
continue;
}
if (pi < i) {
tokens.push(['STRING', '"' + this.escapeLines(str.slice(pi, i), heredoc) + '"']);
tokens.push(['STRING', '"' + str.slice(pi, i) + '"']);
}
inner = expr.slice(1, -1).replace(LEADING_SPACES, '').replace(TRAILING_SPACES, '');
if (inner.length) {
if (heredoc) {
inner = inner.replace(/\\\"/g, '"');
}
nested = lexer.tokenize("(" + (inner) + ")", {
nested = lexer.tokenize("(" + inner + "\n)", {
line: this.line
});
for (_i = 0, _len = nested.length; _i < _len; _i++) {
@@ -531,43 +522,38 @@
}
}
nested.pop();
if (nested.length < 5) {
nested.pop();
nested.shift();
}
tokens.push(['TOKENS', nested]);
} else {
tokens.push(['STRING', '""']);
}
i += expr.length;
pi = i + 1;
}
if ((i > pi) && (pi < str.length - 1)) {
s = this.escapeLines(str.slice(pi, -1), heredoc);
tokens.push(['STRING', '"' + s + '"']);
tokens.push(['STRING', '"' + str.slice(pi)]);
}
if (tokens[0][0] !== 'STRING') {
if (regex) {
return tokens;
}
interpolated = tokens.length > 1;
if ((((_ref2 = tokens[0]) != null) ? _ref2[0] !== 'STRING' : undefined)) {
tokens.unshift(['STRING', '""']);
}
interpolated = !regex && tokens.length > 1;
if (interpolated) {
this.token('(', '(');
}
push = tokens.push;
for (i = 0, _len = tokens.length; i < _len; i++) {
_ref2 = tokens[i], tag = _ref2[0], value = _ref2[1];
if (i) {
this.token('+', '+');
}
if (tag === 'TOKENS') {
push.apply(this.tokens, value);
continue;
(_this = this.tokens).push.apply(_this, value);
} else {
this.token(tag, this.escapeLines(value, heredoc));
}
if (regex) {
value = value.slice(1, -1);
value = value.replace(/[\\\"]/g, '\\$&');
if (options.heregex) {
value = value.replace(HEREGEX_OMIT, '');
}
value = '"' + value + '"';
}
this.token(tag, value);
}
if (interpolated) {
this.token(')', ')');
@@ -615,9 +601,7 @@
MULTI_DENT = /^(?:\n[ \t]*)+/;
SIMPLESTR = /^'[^\\']*(?:\\.[^\\']*)*'/;
JSTOKEN = /^`[^\\`]*(?:\\.[^\\`]*)*`/;
REGEX_START = /^\/([^\/])/;
REGEX_END = /^[imgy]{0,4}(?![a-zA-Z])/;
REGEX_ESCAPE = /\\[^#]/g;
REGEX = /^\/(?!\s)(?:[^[\/\n\\]+|\\.|\[([^\\\]]+|\\.)*])+\/[imgy]{0,4}(?![A-Za-z])/;
HEREGEX = /^\/{3}([\s\S]+?)\/{3}([imgy]{0,4})(?![A-Za-z])/;
HEREGEX_OMIT = /\s+(?:#.*)?/g;
MULTILINER = /\n/g;