Created
March 28, 2010 04:40
-
-
Save Constellation/346579 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
function trimComment(str){ | |
var lines = str.split(/\n|\r\n/); | |
var end = lines.length-1; | |
var current = 0; | |
var buffer = lines[current]; | |
var exps = []; | |
// 現在primary expressionの立ち居地にあるのかどうかをtestする | |
// 直前のものしか調べてないから, 正確性に欠けるかも... | |
function isPrimary(exps){ | |
var len = exps.length; | |
if(len === 0){ | |
return true; | |
} | |
// len !== 0 | |
if(exps[len-1].type === 'IDENT'){ | |
var val = exps[len-1].val; | |
return val === 'new' || val === 'typeof' || val === 'void' || val === 'delete' || val === 'instanceof' || val === 'in' || val === 'case' || 'throw' || val === 'do' || val === 'else' || val === 'return'; | |
} | |
if(exps[len-1].type === 'OP'){ | |
var val = exps[len-1].val; | |
return val === '+' || | |
val === '-' || | |
val === '!' || | |
val === '*' || | |
val === '/' || | |
val === '%' || | |
val === '~' || | |
val === '>>' || | |
val === '<<' || | |
val === '>>>'|| | |
val === '>' || | |
val === '<' || | |
val === '<=' || | |
val === '>=' || | |
val === '==' || | |
val === '!=' || | |
val === '==='|| | |
val === '!=='|| | |
val === '&' || | |
val === '^' || | |
val === '|' || | |
val === '&&' || | |
val === '||' || | |
val === ':' || | |
val === '?' || | |
val === ',' || | |
val === '=' || | |
val === '*=' || | |
val === '/=' || | |
val === '%=' || | |
val === '+=' || | |
val === '-=' || | |
val === '>>=' || | |
val === '<<=' || | |
val === '>>>=' || | |
val === '&=' || | |
val === '^=' || | |
val === '|=' || | |
val === '[' || | |
val === '}' || | |
val === ';' || | |
val === ')' || | |
val === '('; | |
} | |
return false; | |
} | |
var comment = false; | |
var single_comment = false; | |
var invalid = false; | |
var result = []; | |
var match = null; | |
while(true){ | |
if(!buffer){ | |
if(current === end){ | |
break; | |
} | |
current+=1; | |
buffer = lines[current]; | |
if(!comment && !single_comment) | |
result.push("\n"); | |
} else if(comment){ | |
if(/\*\//.test(buffer)){ | |
buffer = RegExp.rightContext; | |
comment = false; | |
} else { | |
buffer = null; | |
} | |
} else { | |
if(/^[ \t\r\n]+/.test(buffer)){ | |
result.push(RegExp.lastMatch); | |
buffer = RegExp.rightContext; | |
} else if(/^\//.test(buffer)){ | |
// 正規表現は/や*から始まらない RegularExpressionFirstChar | |
// よって即座に判断可能 | |
if(/^\/\//.test(buffer)){ | |
buffer = null; | |
} else if(/^\/\*/.test(buffer)){ | |
buffer = RegExp.rightContext; | |
comment = true; | |
} else { | |
// 正規表現の可能性がある | |
// 現在PrimaryExpressionがこれるかどうか | |
if(isPrimary(exps)){ | |
if(/^\/(?:[^\/\\]|\\.)?(?:\[.*\]|[^\/\\]|\\.)*\/[igIG]*/.test(buffer)){ | |
result.push(RegExp.lastMatch); | |
buffer = RegExp.rightContext; | |
exps.push({ | |
type: "REGEXP", | |
val : RegExp.lastMatch | |
}); | |
} else { | |
invalid = true; | |
break; | |
} | |
} else if(/^\/=|^\//.test(buffer)){ | |
result.push(RegExp.lastMatch); | |
buffer = RegExp.rightContext; | |
exps.push({ | |
type: "OP", | |
val : RegExp.lastMatch | |
}); | |
} | |
} | |
} else if(/^"(?:[^"\\]|\\.)*"|^'(?:[^'\\]|\\.)*'/.test(buffer)){ | |
result.push(RegExp.lastMatch); | |
buffer = RegExp.rightContext; | |
exps.push({ | |
type: "STRING", | |
val : RegExp.lastMatch | |
}); | |
} else if(/^0x[0-9A-Fa-f]+|^[0-9]*\.[0-9]+(?:e|E)(?:\-|\+|)[0-9]+|^[0-9]+(?:e|E)(?:\-|\+|)[0-9]+|^[0-9]*\.[0-9]+|^[0-9]+/.test(buffer)){ | |
result.push(RegExp.lastMatch); | |
buffer = RegExp.rightContext; | |
exps.push({ | |
type: "NUMBER", | |
val : RegExp.lastMatch | |
}); | |
} else if(/^[_\$A-Za-z][_\$0-9A-Za-z]*/.test(buffer)){ | |
result.push(RegExp.lastMatch); | |
buffer = RegExp.rightContext; | |
exps.push({ | |
type: "IDENT", | |
val : RegExp.lastMatch | |
}); | |
} else if(/^===|^!==|^>>>=|^>>>|^>>=|^<<=|^\-\-|^\+\+|^>>|^\|\||^\|=|^\^=|^>=|^==|^<=|^&=|^&&|^!=|^\+=|^\/=|^\-=|^\*=|^%=|^<<|^\}|^\||^\{|^\^|^\[|^\?|^=|^;|^:|^,|^\(|^&|^!|^~|^\+|^>|^<|^\]|^\/|^.|^\*|^\)|^%/.test(buffer)){ | |
result.push(RegExp.lastMatch); | |
buffer = RegExp.rightContext; | |
exps.push({ | |
type: "OP", | |
val : RegExp.lastMatch | |
}); | |
} else { | |
invalid = true; | |
break; | |
} | |
} | |
} | |
return (invalid)? "invalid result" : result.join(""); | |
} | |
var val = <><![CDATA[ | |
function ok(){ | |
// single line comment | |
var comment = "これは//こめんとじゃないよ!" | |
/* multiple comment */ | |
/* | |
* | |
* | |
*/ | |
var i = /.\/*/;// 正規表現... | |
print(i); | |
} | |
]]></>.trim(); | |
print("===============ORIGINAL================="); | |
print(val); | |
print("================TRIMED=================="); | |
print(trimComment(val)); | |
print(trimComment('hel/*as/[/*]/df*/lo /\\/*hello[*/]///asdf')); | |
print("var i = ~~/0[/*]/; // asa"); | |
print(trimComment("var i = +/0[/*]/; // asa")); | |
print(trimComment("var i = 10;if(true){ i *= /0[/*]/;}; i = 0 * /0[/*]/;// asa")); | |
print("ORIGINAL"); | |
print("var i = 100 / 10 / [1,2,3][~~/[/*]/] // hogeeee"); | |
print("TRIMED"); | |
print(trimComment("var i = 100 / 10 / [1,2,3][~~/[/*]/] // hogeeee")); | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment