From ecf1830f21634f2b711b4fd840789ec8ddf01649 Mon Sep 17 00:00:00 2001 From: ntdaley Date: Tue, 14 Oct 2014 21:27:16 +0100 Subject: [PATCH 1/2] Fix string escapes. (issue #37) Previously the different escape characters were being applied one after the other, so that "\\n" in the json will get turned into a new-line instead of "\n". Previously unicode escapes were not being converted resulting in stringifying the parse result turning "\u20AC" getting turned into "\\u20AC". Previously "\/" was not being converted resulting in stringifying the parse result turning it into "\\/" Note: I removed handling of '\v' because this would not be accepted by the lexer anyway, and is not part of the json standard. Note: Because unicode escapes are converted, strings in the input like "\u20AC" will become their unicode equivalent after parsing (e.g. in this case the euro character). Also changed the command line use of JSON.stringify to further process the result to convert non-ASCII printable characters to unicode escapes. While not strictly necessary according to the JSON standard, ascii output is safer for some parsers, and now that the parser processes unicode escapes there is more chance of having non-ASCII characters in the parser output. I would suggest that it would be better to always use formatter.js instead of JSON.stringify, because that way the choice between unicode escaped values and unicode characters would always be the same for input and output. Similar formatting changes should probably be made in the web version. --- lib/cli.js | 4 +- lib/jsonlint.js | 753 ++++++++++++++++++++++++++++++---------------- src/jsonlint.y | 20 +- test/all-tests.js | 10 + web/jsonlint.js | 2 +- 5 files changed, 526 insertions(+), 263 deletions(-) diff --git a/lib/cli.js b/lib/cli.js index 981c15f..38ed9bd 100755 --- a/lib/cli.js +++ b/lib/cli.js @@ -90,7 +90,9 @@ function parse (source) { } } - return JSON.stringify(parsed, null, options.indent); + return JSON.stringify(parsed, null, options.indent).replace(/[^\x20-\x7e]/g, function(char) { + return '\\u' + ('0000' + Number(char.charCodeAt(0)).toString(16)).match(/....$/)[0]; + }); } catch (e) { if (options.forcePrettyPrint) { /* From https://github.com/umbrae/jsonlintdotcom: diff --git a/lib/jsonlint.js b/lib/jsonlint.js index 598c18c..c4a8ff7 100644 --- a/lib/jsonlint.js +++ b/lib/jsonlint.js @@ -1,377 +1,619 @@ -/* Jison generated parser */ -var jsonlint = (function(){ +/* parser generated by jison 0.4.15 */ +/* + Returns a Parser object of the following structure: + + Parser: { + yy: {} + } + + Parser.prototype: { + yy: {}, + trace: function(), + symbols_: {associative list: name ==> number}, + terminals_: {associative list: number ==> name}, + productions_: [...], + performAction: function anonymous(yytext, yyleng, yylineno, yy, yystate, $$, _$), + table: [...], + defaultActions: {...}, + parseError: function(str, hash), + parse: function(input), + + lexer: { + EOF: 1, + parseError: function(str, hash), + setInput: function(input), + input: function(), + unput: function(str), + more: function(), + less: function(n), + pastInput: function(), + upcomingInput: function(), + showPosition: function(), + test_match: function(regex_match_array, rule_index), + next: function(), + lex: function(), + begin: function(condition), + popState: function(), + _currentRules: function(), + topState: function(), + pushState: function(condition), + + options: { + ranges: boolean (optional: true ==> token location info will include a .range[] member) + flex: boolean (optional: true ==> flex-like lexing behaviour where the rules are tested exhaustively to find the longest match) + backtrack_lexer: boolean (optional: true ==> lexer regexes are tested in order and for each matching regex the action code is invoked; the lexer terminates the scan when a token is returned by the action code) + }, + + performAction: function(yy, yy_, $avoiding_name_collisions, YY_START), + rules: [...], + conditions: {associative list: name ==> set}, + } + } + + + token location info (@$, _$, etc.): { + first_line: n, + last_line: n, + first_column: n, + last_column: n, + range: [start_number, end_number] (where the numbers are indexes into the input string, regular zero-based) + } + + + the parseError function receives a 'hash' object with these members for lexer and parser errors: { + text: (matched text) + token: (the produced terminal token, if any) + line: (yylineno) + } + while parser (grammar) errors will also provide these members, i.e. parser errors deliver a superset of attributes: { + loc: (yylloc) + expected: (string describing the set of expected tokens) + recoverable: (boolean: TRUE when the parser has a error recovery rule available for this particular error) + } +*/ +var parser = (function(){ +var o=function(k,v,o,l){for(o=o||{},l=k.length;l--;o[k[l]]=v);return o},$V0=[1,12],$V1=[1,13],$V2=[1,9],$V3=[1,10],$V4=[1,11],$V5=[1,14],$V6=[1,15],$V7=[14,18,22,24],$V8=[18,22],$V9=[22,24]; var parser = {trace: function trace() { }, yy: {}, symbols_: {"error":2,"JSONString":3,"STRING":4,"JSONNumber":5,"NUMBER":6,"JSONNullLiteral":7,"NULL":8,"JSONBooleanLiteral":9,"TRUE":10,"FALSE":11,"JSONText":12,"JSONValue":13,"EOF":14,"JSONObject":15,"JSONArray":16,"{":17,"}":18,"JSONMemberList":19,"JSONMember":20,":":21,",":22,"[":23,"]":24,"JSONElementList":25,"$accept":0,"$end":1}, terminals_: {2:"error",4:"STRING",6:"NUMBER",8:"NULL",10:"TRUE",11:"FALSE",14:"EOF",17:"{",18:"}",21:":",22:",",23:"[",24:"]"}, productions_: [0,[3,1],[5,1],[7,1],[9,1],[9,1],[12,2],[13,1],[13,1],[13,1],[13,1],[13,1],[13,1],[15,2],[15,3],[20,3],[19,1],[19,3],[16,2],[16,3],[25,1],[25,3]], -performAction: function anonymous(yytext,yyleng,yylineno,yy,yystate,$$,_$) { +performAction: function anonymous(yytext, yyleng, yylineno, yy, yystate /* action[1] */, $$ /* vstack */, _$ /* lstack */) { +/* this == yyval */ var $0 = $$.length - 1; switch (yystate) { -case 1: // replace escaped characters with actual character - this.$ = yytext.replace(/\\(\\|")/g, "$"+"1") - .replace(/\\n/g,'\n') - .replace(/\\r/g,'\r') - .replace(/\\t/g,'\t') - .replace(/\\v/g,'\v') - .replace(/\\f/g,'\f') - .replace(/\\b/g,'\b'); +case 1: + // replace escaped characters with actual character + this.$ = yytext.replace(/\\([\"\\\/bfnrt]|u[0-9a-fA-f]{4})/g, function(match, part) { + if(part.charAt(0) === 'u') { + return String.fromCharCode(parseInt(part.substr(1),16)); + } + switch(part) { + case 'b':return '\b'; + case 'f':return '\f'; + case 'n':return '\n'; + case 'r':return '\r'; + case 't':return '\t'; + case '"':case '\\':case '/':return part; + } + }); break; -case 2:this.$ = Number(yytext); +case 2: +this.$ = Number(yytext); break; -case 3:this.$ = null; +case 3: +this.$ = null; break; -case 4:this.$ = true; +case 4: +this.$ = true; break; -case 5:this.$ = false; +case 5: +this.$ = false; break; -case 6:return this.$ = $$[$0-1]; +case 6: +return this.$ = $$[$0-1]; break; -case 13:this.$ = {}; +case 13: +this.$ = {}; break; -case 14:this.$ = $$[$0-1]; +case 14: case 19: +this.$ = $$[$0-1]; break; -case 15:this.$ = [$$[$0-2], $$[$0]]; +case 15: +this.$ = [$$[$0-2], $$[$0]]; break; -case 16:this.$ = {}; this.$[$$[$0][0]] = $$[$0][1]; +case 16: +this.$ = {}; this.$[$$[$0][0]] = $$[$0][1]; break; -case 17:this.$ = $$[$0-2]; $$[$0-2][$$[$0][0]] = $$[$0][1]; +case 17: +this.$ = $$[$0-2]; $$[$0-2][$$[$0][0]] = $$[$0][1]; break; -case 18:this.$ = []; +case 18: +this.$ = []; break; -case 19:this.$ = $$[$0-1]; +case 20: +this.$ = [$$[$0]]; break; -case 20:this.$ = [$$[$0]]; -break; -case 21:this.$ = $$[$0-2]; $$[$0-2].push($$[$0]); +case 21: +this.$ = $$[$0-2]; $$[$0-2].push($$[$0]); break; } }, -table: [{3:5,4:[1,12],5:6,6:[1,13],7:3,8:[1,9],9:4,10:[1,10],11:[1,11],12:1,13:2,15:7,16:8,17:[1,14],23:[1,15]},{1:[3]},{14:[1,16]},{14:[2,7],18:[2,7],22:[2,7],24:[2,7]},{14:[2,8],18:[2,8],22:[2,8],24:[2,8]},{14:[2,9],18:[2,9],22:[2,9],24:[2,9]},{14:[2,10],18:[2,10],22:[2,10],24:[2,10]},{14:[2,11],18:[2,11],22:[2,11],24:[2,11]},{14:[2,12],18:[2,12],22:[2,12],24:[2,12]},{14:[2,3],18:[2,3],22:[2,3],24:[2,3]},{14:[2,4],18:[2,4],22:[2,4],24:[2,4]},{14:[2,5],18:[2,5],22:[2,5],24:[2,5]},{14:[2,1],18:[2,1],21:[2,1],22:[2,1],24:[2,1]},{14:[2,2],18:[2,2],22:[2,2],24:[2,2]},{3:20,4:[1,12],18:[1,17],19:18,20:19},{3:5,4:[1,12],5:6,6:[1,13],7:3,8:[1,9],9:4,10:[1,10],11:[1,11],13:23,15:7,16:8,17:[1,14],23:[1,15],24:[1,21],25:22},{1:[2,6]},{14:[2,13],18:[2,13],22:[2,13],24:[2,13]},{18:[1,24],22:[1,25]},{18:[2,16],22:[2,16]},{21:[1,26]},{14:[2,18],18:[2,18],22:[2,18],24:[2,18]},{22:[1,28],24:[1,27]},{22:[2,20],24:[2,20]},{14:[2,14],18:[2,14],22:[2,14],24:[2,14]},{3:20,4:[1,12],20:29},{3:5,4:[1,12],5:6,6:[1,13],7:3,8:[1,9],9:4,10:[1,10],11:[1,11],13:30,15:7,16:8,17:[1,14],23:[1,15]},{14:[2,19],18:[2,19],22:[2,19],24:[2,19]},{3:5,4:[1,12],5:6,6:[1,13],7:3,8:[1,9],9:4,10:[1,10],11:[1,11],13:31,15:7,16:8,17:[1,14],23:[1,15]},{18:[2,17],22:[2,17]},{18:[2,15],22:[2,15]},{22:[2,21],24:[2,21]}], +table: [{3:5,4:$V0,5:6,6:$V1,7:3,8:$V2,9:4,10:$V3,11:$V4,12:1,13:2,15:7,16:8,17:$V5,23:$V6},{1:[3]},{14:[1,16]},o($V7,[2,7]),o($V7,[2,8]),o($V7,[2,9]),o($V7,[2,10]),o($V7,[2,11]),o($V7,[2,12]),o($V7,[2,3]),o($V7,[2,4]),o($V7,[2,5]),o([14,18,21,22,24],[2,1]),o($V7,[2,2]),{3:20,4:$V0,18:[1,17],19:18,20:19},{3:5,4:$V0,5:6,6:$V1,7:3,8:$V2,9:4,10:$V3,11:$V4,13:23,15:7,16:8,17:$V5,23:$V6,24:[1,21],25:22},{1:[2,6]},o($V7,[2,13]),{18:[1,24],22:[1,25]},o($V8,[2,16]),{21:[1,26]},o($V7,[2,18]),{22:[1,28],24:[1,27]},o($V9,[2,20]),o($V7,[2,14]),{3:20,4:$V0,20:29},{3:5,4:$V0,5:6,6:$V1,7:3,8:$V2,9:4,10:$V3,11:$V4,13:30,15:7,16:8,17:$V5,23:$V6},o($V7,[2,19]),{3:5,4:$V0,5:6,6:$V1,7:3,8:$V2,9:4,10:$V3,11:$V4,13:31,15:7,16:8,17:$V5,23:$V6},o($V8,[2,17]),o($V8,[2,15]),o($V9,[2,21])], defaultActions: {16:[2,6]}, parseError: function parseError(str, hash) { - throw new Error(str); + if (hash.recoverable) { + this.trace(str); + } else { + throw new Error(str); + } }, parse: function parse(input) { - var self = this, - stack = [0], - vstack = [null], // semantic value stack - lstack = [], // location stack - table = this.table, - yytext = '', - yylineno = 0, - yyleng = 0, - recovering = 0, - TERROR = 2, - EOF = 1; - - //this.reductionCount = this.shiftCount = 0; - - this.lexer.setInput(input); - this.lexer.yy = this.yy; - this.yy.lexer = this.lexer; - if (typeof this.lexer.yylloc == 'undefined') - this.lexer.yylloc = {}; - var yyloc = this.lexer.yylloc; + var self = this, stack = [0], tstack = [], vstack = [null], lstack = [], table = this.table, yytext = '', yylineno = 0, yyleng = 0, recovering = 0, TERROR = 2, EOF = 1; + var args = lstack.slice.call(arguments, 1); + var lexer = Object.create(this.lexer); + var sharedState = { yy: {} }; + for (var k in this.yy) { + if (Object.prototype.hasOwnProperty.call(this.yy, k)) { + sharedState.yy[k] = this.yy[k]; + } + } + lexer.setInput(input, sharedState.yy); + sharedState.yy.lexer = lexer; + sharedState.yy.parser = this; + if (typeof lexer.yylloc == 'undefined') { + lexer.yylloc = {}; + } + var yyloc = lexer.yylloc; lstack.push(yyloc); - - if (typeof this.yy.parseError === 'function') - this.parseError = this.yy.parseError; - - function popStack (n) { - stack.length = stack.length - 2*n; + var ranges = lexer.options && lexer.options.ranges; + if (typeof sharedState.yy.parseError === 'function') { + this.parseError = sharedState.yy.parseError; + } else { + this.parseError = Object.getPrototypeOf(this).parseError; + } + function popStack(n) { + stack.length = stack.length - 2 * n; vstack.length = vstack.length - n; lstack.length = lstack.length - n; } - - function lex() { - var token; - token = self.lexer.lex() || 1; // $end = 1 - // if token isn't its numeric value, convert - if (typeof token !== 'number') { - token = self.symbols_[token] || token; + _token_stack: + function lex() { + var token; + token = lexer.lex() || EOF; + if (typeof token !== 'number') { + token = self.symbols_[token] || token; + } + return token; } - return token; - } - - var symbol, preErrorSymbol, state, action, a, r, yyval={},p,len,newState, expected; + var symbol, preErrorSymbol, state, action, a, r, yyval = {}, p, len, newState, expected; while (true) { - // retreive state number from top of stack - state = stack[stack.length-1]; - - // use default actions if available + state = stack[stack.length - 1]; if (this.defaultActions[state]) { action = this.defaultActions[state]; } else { - if (symbol == null) + if (symbol === null || typeof symbol == 'undefined') { symbol = lex(); - // read action for current state and first input + } action = table[state] && table[state][symbol]; } - - // handle parse error - _handle_error: - if (typeof action === 'undefined' || !action.length || !action[0]) { - - if (!recovering) { - // Report error + if (typeof action === 'undefined' || !action.length || !action[0]) { + var errStr = ''; expected = []; - for (p in table[state]) if (this.terminals_[p] && p > 2) { - expected.push("'"+this.terminals_[p]+"'"); + for (p in table[state]) { + if (this.terminals_[p] && p > TERROR) { + expected.push('\'' + this.terminals_[p] + '\''); + } } - var errStr = ''; - if (this.lexer.showPosition) { - errStr = 'Parse error on line '+(yylineno+1)+":\n"+this.lexer.showPosition()+"\nExpecting "+expected.join(', ') + ", got '" + this.terminals_[symbol]+ "'"; + if (lexer.showPosition) { + errStr = 'Parse error on line ' + (yylineno + 1) + ':\n' + lexer.showPosition() + '\nExpecting ' + expected.join(', ') + ', got \'' + (this.terminals_[symbol] || symbol) + '\''; } else { - errStr = 'Parse error on line '+(yylineno+1)+": Unexpected " + - (symbol == 1 /*EOF*/ ? "end of input" : - ("'"+(this.terminals_[symbol] || symbol)+"'")); + errStr = 'Parse error on line ' + (yylineno + 1) + ': Unexpected ' + (symbol == EOF ? 'end of input' : '\'' + (this.terminals_[symbol] || symbol) + '\''); } - this.parseError(errStr, - {text: this.lexer.match, token: this.terminals_[symbol] || symbol, line: this.lexer.yylineno, loc: yyloc, expected: expected}); + this.parseError(errStr, { + text: lexer.match, + token: this.terminals_[symbol] || symbol, + line: lexer.yylineno, + loc: yyloc, + expected: expected + }); } - - // just recovered from another error - if (recovering == 3) { - if (symbol == EOF) { - throw new Error(errStr || 'Parsing halted.'); - } - - // discard current lookahead and grab another - yyleng = this.lexer.yyleng; - yytext = this.lexer.yytext; - yylineno = this.lexer.yylineno; - yyloc = this.lexer.yylloc; - symbol = lex(); - } - - // try to recover from error - while (1) { - // check for error recovery rule in this state - if ((TERROR.toString()) in table[state]) { - break; - } - if (state == 0) { - throw new Error(errStr || 'Parsing halted.'); - } - popStack(1); - state = stack[stack.length-1]; - } - - preErrorSymbol = symbol; // save the lookahead token - symbol = TERROR; // insert generic error symbol as new lookahead - state = stack[stack.length-1]; - action = table[state] && table[state][TERROR]; - recovering = 3; // allow 3 real symbols to be shifted before reporting a new error - } - - // this shouldn't happen, unless resolve defaults are off if (action[0] instanceof Array && action.length > 1) { - throw new Error('Parse Error: multiple actions possible at state: '+state+', token: '+symbol); + throw new Error('Parse Error: multiple actions possible at state: ' + state + ', token: ' + symbol); } - switch (action[0]) { - - case 1: // shift - //this.shiftCount++; - - stack.push(symbol); - vstack.push(this.lexer.yytext); - lstack.push(this.lexer.yylloc); - stack.push(action[1]); // push state - symbol = null; - if (!preErrorSymbol) { // normal execution/no error - yyleng = this.lexer.yyleng; - yytext = this.lexer.yytext; - yylineno = this.lexer.yylineno; - yyloc = this.lexer.yylloc; - if (recovering > 0) - recovering--; - } else { // error just occurred, resume old lookahead f/ before error - symbol = preErrorSymbol; - preErrorSymbol = null; - } - break; - - case 2: // reduce - //this.reductionCount++; - - len = this.productions_[action[1]][1]; - - // perform semantic action - yyval.$ = vstack[vstack.length-len]; // default to $$ = $1 - // default location, uses first token for firsts, last for lasts - yyval._$ = { - first_line: lstack[lstack.length-(len||1)].first_line, - last_line: lstack[lstack.length-1].last_line, - first_column: lstack[lstack.length-(len||1)].first_column, - last_column: lstack[lstack.length-1].last_column - }; - r = this.performAction.call(yyval, yytext, yyleng, yylineno, this.yy, action[1], vstack, lstack); - - if (typeof r !== 'undefined') { - return r; - } - - // pop off stack - if (len) { - stack = stack.slice(0,-1*len*2); - vstack = vstack.slice(0, -1*len); - lstack = lstack.slice(0, -1*len); + case 1: + stack.push(symbol); + vstack.push(lexer.yytext); + lstack.push(lexer.yylloc); + stack.push(action[1]); + symbol = null; + if (!preErrorSymbol) { + yyleng = lexer.yyleng; + yytext = lexer.yytext; + yylineno = lexer.yylineno; + yyloc = lexer.yylloc; + if (recovering > 0) { + recovering--; } - - stack.push(this.productions_[action[1]][0]); // push nonterminal (reduce) - vstack.push(yyval.$); - lstack.push(yyval._$); - // goto new state = table[STATE][NONTERMINAL] - newState = table[stack[stack.length-2]][stack[stack.length-1]]; - stack.push(newState); - break; - - case 3: // accept - return true; + } else { + symbol = preErrorSymbol; + preErrorSymbol = null; + } + break; + case 2: + len = this.productions_[action[1]][1]; + yyval.$ = vstack[vstack.length - len]; + yyval._$ = { + first_line: lstack[lstack.length - (len || 1)].first_line, + last_line: lstack[lstack.length - 1].last_line, + first_column: lstack[lstack.length - (len || 1)].first_column, + last_column: lstack[lstack.length - 1].last_column + }; + if (ranges) { + yyval._$.range = [ + lstack[lstack.length - (len || 1)].range[0], + lstack[lstack.length - 1].range[1] + ]; + } + r = this.performAction.apply(yyval, [ + yytext, + yyleng, + yylineno, + sharedState.yy, + action[1], + vstack, + lstack + ].concat(args)); + if (typeof r !== 'undefined') { + return r; + } + if (len) { + stack = stack.slice(0, -1 * len * 2); + vstack = vstack.slice(0, -1 * len); + lstack = lstack.slice(0, -1 * len); + } + stack.push(this.productions_[action[1]][0]); + vstack.push(yyval.$); + lstack.push(yyval._$); + newState = table[stack[stack.length - 2]][stack[stack.length - 1]]; + stack.push(newState); + break; + case 3: + return true; } - } - return true; }}; -/* Jison generated lexer */ +/* generated by jison-lex 0.3.4 */ var lexer = (function(){ -var lexer = ({EOF:1, +var lexer = ({ + +EOF:1, + parseError:function parseError(str, hash) { - if (this.yy.parseError) { - this.yy.parseError(str, hash); + if (this.yy.parser) { + this.yy.parser.parseError(str, hash); } else { throw new Error(str); } }, -setInput:function (input) { + +// resets the lexer, sets new input +setInput:function (input, yy) { + this.yy = yy || this.yy || {}; this._input = input; - this._more = this._less = this.done = false; + this._more = this._backtrack = this.done = false; this.yylineno = this.yyleng = 0; this.yytext = this.matched = this.match = ''; this.conditionStack = ['INITIAL']; - this.yylloc = {first_line:1,first_column:0,last_line:1,last_column:0}; + this.yylloc = { + first_line: 1, + first_column: 0, + last_line: 1, + last_column: 0 + }; + if (this.options.ranges) { + this.yylloc.range = [0,0]; + } + this.offset = 0; return this; }, + +// consumes and returns one char from the input input:function () { var ch = this._input[0]; - this.yytext+=ch; + this.yytext += ch; this.yyleng++; - this.match+=ch; - this.matched+=ch; - var lines = ch.match(/\n/); - if (lines) this.yylineno++; + this.offset++; + this.match += ch; + this.matched += ch; + var lines = ch.match(/(?:\r\n?|\n).*/g); + if (lines) { + this.yylineno++; + this.yylloc.last_line++; + } else { + this.yylloc.last_column++; + } + if (this.options.ranges) { + this.yylloc.range[1]++; + } + this._input = this._input.slice(1); return ch; }, + +// unshifts one char (or a string) into the input unput:function (ch) { + var len = ch.length; + var lines = ch.split(/(?:\r\n?|\n)/g); + this._input = ch + this._input; + this.yytext = this.yytext.substr(0, this.yytext.length - len); + //this.yyleng -= len; + this.offset -= len; + var oldLines = this.match.split(/(?:\r\n?|\n)/g); + this.match = this.match.substr(0, this.match.length - 1); + this.matched = this.matched.substr(0, this.matched.length - 1); + + if (lines.length - 1) { + this.yylineno -= lines.length - 1; + } + var r = this.yylloc.range; + + this.yylloc = { + first_line: this.yylloc.first_line, + last_line: this.yylineno + 1, + first_column: this.yylloc.first_column, + last_column: lines ? + (lines.length === oldLines.length ? this.yylloc.first_column : 0) + + oldLines[oldLines.length - lines.length].length - lines[0].length : + this.yylloc.first_column - len + }; + + if (this.options.ranges) { + this.yylloc.range = [r[0], r[0] + this.yyleng - len]; + } + this.yyleng = this.yytext.length; return this; }, + +// When called from action, caches matched text and appends it on next action more:function () { this._more = true; return this; }, + +// When called from action, signals the lexer that this rule fails to match the input, so the next matching rule (regex) should be tested instead. +reject:function () { + if (this.options.backtrack_lexer) { + this._backtrack = true; + } else { + return this.parseError('Lexical error on line ' + (this.yylineno + 1) + '. You can only invoke reject() in the lexer when the lexer is of the backtracking persuasion (options.backtrack_lexer = true).\n' + this.showPosition(), { + text: "", + token: null, + line: this.yylineno + }); + + } + return this; + }, + +// retain first n characters of the match less:function (n) { - this._input = this.match.slice(n) + this._input; + this.unput(this.match.slice(n)); }, + +// displays already matched input, i.e. for error messages pastInput:function () { var past = this.matched.substr(0, this.matched.length - this.match.length); return (past.length > 20 ? '...':'') + past.substr(-20).replace(/\n/g, ""); }, + +// displays upcoming input, i.e. for error messages upcomingInput:function () { var next = this.match; if (next.length < 20) { next += this._input.substr(0, 20-next.length); } - return (next.substr(0,20)+(next.length > 20 ? '...':'')).replace(/\n/g, ""); + return (next.substr(0,20) + (next.length > 20 ? '...' : '')).replace(/\n/g, ""); }, + +// displays the character position where the lexing error occurred, i.e. for error messages showPosition:function () { var pre = this.pastInput(); var c = new Array(pre.length + 1).join("-"); - return pre + this.upcomingInput() + "\n" + c+"^"; + return pre + this.upcomingInput() + "\n" + c + "^"; + }, + +// test the lexed token: return FALSE when not a match, otherwise return token +test_match:function (match, indexed_rule) { + var token, + lines, + backup; + + if (this.options.backtrack_lexer) { + // save context + backup = { + yylineno: this.yylineno, + yylloc: { + first_line: this.yylloc.first_line, + last_line: this.last_line, + first_column: this.yylloc.first_column, + last_column: this.yylloc.last_column + }, + yytext: this.yytext, + match: this.match, + matches: this.matches, + matched: this.matched, + yyleng: this.yyleng, + offset: this.offset, + _more: this._more, + _input: this._input, + yy: this.yy, + conditionStack: this.conditionStack.slice(0), + done: this.done + }; + if (this.options.ranges) { + backup.yylloc.range = this.yylloc.range.slice(0); + } + } + + lines = match[0].match(/(?:\r\n?|\n).*/g); + if (lines) { + this.yylineno += lines.length; + } + this.yylloc = { + first_line: this.yylloc.last_line, + last_line: this.yylineno + 1, + first_column: this.yylloc.last_column, + last_column: lines ? + lines[lines.length - 1].length - lines[lines.length - 1].match(/\r?\n?/)[0].length : + this.yylloc.last_column + match[0].length + }; + this.yytext += match[0]; + this.match += match[0]; + this.matches = match; + this.yyleng = this.yytext.length; + if (this.options.ranges) { + this.yylloc.range = [this.offset, this.offset += this.yyleng]; + } + this._more = false; + this._backtrack = false; + this._input = this._input.slice(match[0].length); + this.matched += match[0]; + token = this.performAction.call(this, this.yy, this, indexed_rule, this.conditionStack[this.conditionStack.length - 1]); + if (this.done && this._input) { + this.done = false; + } + if (token) { + return token; + } else if (this._backtrack) { + // recover context + for (var k in backup) { + this[k] = backup[k]; + } + return false; // rule action called reject() implying the next rule should be tested instead. + } + return false; }, + +// return next match in input next:function () { if (this.done) { return this.EOF; } - if (!this._input) this.done = true; + if (!this._input) { + this.done = true; + } var token, match, tempMatch, - index, - col, - lines; + index; if (!this._more) { this.yytext = ''; this.match = ''; } var rules = this._currentRules(); - for (var i=0;i < rules.length; i++) { + for (var i = 0; i < rules.length; i++) { tempMatch = this._input.match(this.rules[rules[i]]); if (tempMatch && (!match || tempMatch[0].length > match[0].length)) { match = tempMatch; index = i; - if (!this.options.flex) break; + if (this.options.backtrack_lexer) { + token = this.test_match(tempMatch, rules[i]); + if (token !== false) { + return token; + } else if (this._backtrack) { + match = false; + continue; // rule action called reject() implying a rule MISmatch. + } else { + // else: this is a lexer rule which consumes input without producing a token (e.g. whitespace) + return false; + } + } else if (!this.options.flex) { + break; + } } } if (match) { - lines = match[0].match(/\n.*/g); - if (lines) this.yylineno += lines.length; - this.yylloc = {first_line: this.yylloc.last_line, - last_line: this.yylineno+1, - first_column: this.yylloc.last_column, - last_column: lines ? lines[lines.length-1].length-1 : this.yylloc.last_column + match[0].length} - this.yytext += match[0]; - this.match += match[0]; - this.yyleng = this.yytext.length; - this._more = false; - this._input = this._input.slice(match[0].length); - this.matched += match[0]; - token = this.performAction.call(this, this.yy, this, rules[index],this.conditionStack[this.conditionStack.length-1]); - if (this.done && this._input) this.done = false; - if (token) return token; - else return; + token = this.test_match(match, rules[index]); + if (token !== false) { + return token; + } + // else: this is a lexer rule which consumes input without producing a token (e.g. whitespace) + return false; } if (this._input === "") { return this.EOF; } else { - this.parseError('Lexical error on line '+(this.yylineno+1)+'. Unrecognized text.\n'+this.showPosition(), - {text: "", token: null, line: this.yylineno}); + return this.parseError('Lexical error on line ' + (this.yylineno + 1) + '. Unrecognized text.\n' + this.showPosition(), { + text: "", + token: null, + line: this.yylineno + }); } }, + +// return next match that has a token lex:function lex() { var r = this.next(); - if (typeof r !== 'undefined') { + if (r) { return r; } else { return this.lex(); } }, + +// activates a new lexer condition state (pushes the new lexer condition state onto the condition stack) begin:function begin(condition) { this.conditionStack.push(condition); }, + +// pop the previously active lexer condition state off the condition stack popState:function popState() { - return this.conditionStack.pop(); + var n = this.conditionStack.length - 1; + if (n > 0) { + return this.conditionStack.pop(); + } else { + return this.conditionStack[0]; + } }, + +// produce the lexer rule set which is active for the currently active lexer condition state _currentRules:function _currentRules() { - return this.conditions[this.conditionStack[this.conditionStack.length-1]].rules; + if (this.conditionStack.length && this.conditionStack[this.conditionStack.length - 1]) { + return this.conditions[this.conditionStack[this.conditionStack.length - 1]].rules; + } else { + return this.conditions["INITIAL"].rules; + } }, -topState:function () { - return this.conditionStack[this.conditionStack.length-2]; + +// return the currently active lexer condition state; when an index argument is provided it produces the N-th previous condition state, if available +topState:function topState(n) { + n = this.conditionStack.length - 1 - Math.abs(n || 0); + if (n >= 0) { + return this.conditionStack[n]; + } else { + return "INITIAL"; + } }, -pushState:function begin(condition) { + +// alias for begin(condition) +pushState:function pushState(condition) { this.begin(condition); - }}); -lexer.options = {}; -lexer.performAction = function anonymous(yy,yy_,$avoiding_name_collisions,YY_START) { + }, -var YYSTATE=YY_START +// return the number of states currently on the stack +stateStackSize:function stateStackSize() { + return this.conditionStack.length; + }, +options: {}, +performAction: function anonymous(yy,yy_,$avoiding_name_collisions,YY_START) { +var YYSTATE=YY_START; switch($avoiding_name_collisions) { case 0:/* skip whitespace */ break; @@ -402,31 +644,34 @@ break; case 13:return 'INVALID' break; } -}; -lexer.rules = [/^(?:\s+)/,/^(?:(-?([0-9]|[1-9][0-9]+))(\.[0-9]+)?([eE][-+]?[0-9]+)?\b)/,/^(?:"(?:\\[\\"bfnrt/]|\\u[a-fA-F0-9]{4}|[^\\\0-\x09\x0a-\x1f"])*")/,/^(?:\{)/,/^(?:\})/,/^(?:\[)/,/^(?:\])/,/^(?:,)/,/^(?::)/,/^(?:true\b)/,/^(?:false\b)/,/^(?:null\b)/,/^(?:$)/,/^(?:.)/]; -lexer.conditions = {"INITIAL":{"rules":[0,1,2,3,4,5,6,7,8,9,10,11,12,13],"inclusive":true}}; - - -; -return lexer;})() +}, +rules: [/^(?:\s+)/,/^(?:(-?([0-9]|[1-9][0-9]+))(\.[0-9]+)?([eE][-+]?[0-9]+)?\b)/,/^(?:"(?:\\[\\"bfnrt/]|\\u[a-fA-F0-9]{4}|[^\\\0-\x09\x0a-\x1f"])*")/,/^(?:\{)/,/^(?:\})/,/^(?:\[)/,/^(?:\])/,/^(?:,)/,/^(?::)/,/^(?:true\b)/,/^(?:false\b)/,/^(?:null\b)/,/^(?:$)/,/^(?:.)/], +conditions: {"INITIAL":{"rules":[0,1,2,3,4,5,6,7,8,9,10,11,12,13],"inclusive":true}} +}); +return lexer; +})(); parser.lexer = lexer; -return parser; +function Parser () { + this.yy = {}; +} +Parser.prototype = parser;parser.Parser = Parser; +return new Parser; })(); + + if (typeof require !== 'undefined' && typeof exports !== 'undefined') { -exports.parser = jsonlint; -exports.parse = function () { return jsonlint.parse.apply(jsonlint, arguments); } +exports.parser = parser; +exports.Parser = parser.Parser; +exports.parse = function () { return parser.parse.apply(parser, arguments); }; exports.main = function commonjsMain(args) { - if (!args[1]) - throw new Error('Usage: '+args[0]+' FILE'); - if (typeof process !== 'undefined') { - var source = require('fs').readFileSync(require('path').join(process.cwd(), args[1]), "utf8"); - } else { - var cwd = require("file").path(require("file").cwd()); - var source = cwd.join(args[1]).read({charset: "utf-8"}); + if (!args[1]) { + console.log('Usage: '+args[0]+' FILE'); + process.exit(1); } + var source = require('fs').readFileSync(require('path').normalize(args[1]), "utf8"); return exports.parser.parse(source); -} +}; if (typeof module !== 'undefined' && require.main === module) { - exports.main(typeof process !== 'undefined' ? process.argv.slice(1) : require("system").args); + exports.main(process.argv.slice(1)); } } \ No newline at end of file diff --git a/src/jsonlint.y b/src/jsonlint.y index a4d6d29..b6aac7e 100644 --- a/src/jsonlint.y +++ b/src/jsonlint.y @@ -10,13 +10,19 @@ JSONString : STRING { // replace escaped characters with actual character - $$ = yytext.replace(/\\(\\|")/g, "$"+"1") - .replace(/\\n/g,'\n') - .replace(/\\r/g,'\r') - .replace(/\\t/g,'\t') - .replace(/\\v/g,'\v') - .replace(/\\f/g,'\f') - .replace(/\\b/g,'\b'); + $$ = yytext.replace(/\\([\"\\\/bfnrt]|u[0-9a-fA-f]{4})/g, function(match, part) { + if(part.charAt(0) === 'u') { + return String.fromCharCode(parseInt(part.substr(1),16)); + } + switch(part) { + case 'b':return '\b'; + case 'f':return '\f'; + case 'n':return '\n'; + case 'r':return '\r'; + case 't':return '\t'; + case '"':case '\\':case '/':return part; + } + }); } ; diff --git a/test/all-tests.js b/test/all-tests.js index 8a2fede..d502747 100644 --- a/test/all-tests.js +++ b/test/all-tests.js @@ -17,11 +17,21 @@ exports["test escaped chars"] = function () { assert.deepEqual(parser.parse(json), {"foo": '\\\"'}); }; +exports["test all escaped characters"] = function () { + var json = '["\\u20AC","\\/","\\\\","\\b","\\f","\\n","\\r","\\t","\\\""]'; + assert.deepEqual(parser.parse(json), ['\u20AC','\/','\\','\b','\f','\n','\r','\t','\"']); +}; + exports["test escaped \\n"] = function () { var json = '{"foo": "\\\\\\n"}'; assert.deepEqual(parser.parse(json), {"foo": '\\\n'}); }; +exports["test escaped backslash does not get used to escape"] = function () { + var json = '{"foo": "\\\\n"}'; + assert.deepEqual(parser.parse(json), {"foo": '\\n'}); +}; + exports["test string with escaped line break"] = function () { var json = '{"foo": "bar\\nbar"}'; assert.deepEqual(parser.parse(json), {"foo": "bar\nbar"}); diff --git a/web/jsonlint.js b/web/jsonlint.js index f34759e..89547fd 100644 --- a/web/jsonlint.js +++ b/web/jsonlint.js @@ -1 +1 @@ -var jsonlint=function(){var a=!0,b=!1,c={},d=function(){var a={trace:function(){},yy:{},symbols_:{error:2,JSONString:3,STRING:4,JSONNumber:5,NUMBER:6,JSONNullLiteral:7,NULL:8,JSONBooleanLiteral:9,TRUE:10,FALSE:11,JSONText:12,JSONValue:13,EOF:14,JSONObject:15,JSONArray:16,"{":17,"}":18,JSONMemberList:19,JSONMember:20,":":21,",":22,"[":23,"]":24,JSONElementList:25,$accept:0,$end:1},terminals_:{2:"error",4:"STRING",6:"NUMBER",8:"NULL",10:"TRUE",11:"FALSE",14:"EOF",17:"{",18:"}",21:":",22:",",23:"[",24:"]"},productions_:[0,[3,1],[5,1],[7,1],[9,1],[9,1],[12,2],[13,1],[13,1],[13,1],[13,1],[13,1],[13,1],[15,2],[15,3],[20,3],[19,1],[19,3],[16,2],[16,3],[25,1],[25,3]],performAction:function(b,c,d,e,f,g,h){var i=g.length-1;switch(f){case 1:this.$=b.replace(/\\(\\|")/g,"$1").replace(/\\n/g,"\n").replace(/\\r/g,"\r").replace(/\\t/g," ").replace(/\\v/g," ").replace(/\\f/g,"\f").replace(/\\b/g,"\b");break;case 2:this.$=Number(b);break;case 3:this.$=null;break;case 4:this.$=!0;break;case 5:this.$=!1;break;case 6:return this.$=g[i-1];case 13:this.$={};break;case 14:this.$=g[i-1];break;case 15:this.$=[g[i-2],g[i]];break;case 16:this.$={},this.$[g[i][0]]=g[i][1];break;case 17:this.$=g[i-2],g[i-2][g[i][0]]=g[i][1];break;case 18:this.$=[];break;case 19:this.$=g[i-1];break;case 20:this.$=[g[i]];break;case 21:this.$=g[i-2],g[i-2].push(g[i])}},table:[{3:5,4:[1,12],5:6,6:[1,13],7:3,8:[1,9],9:4,10:[1,10],11:[1,11],12:1,13:2,15:7,16:8,17:[1,14],23:[1,15]},{1:[3]},{14:[1,16]},{14:[2,7],18:[2,7],22:[2,7],24:[2,7]},{14:[2,8],18:[2,8],22:[2,8],24:[2,8]},{14:[2,9],18:[2,9],22:[2,9],24:[2,9]},{14:[2,10],18:[2,10],22:[2,10],24:[2,10]},{14:[2,11],18:[2,11],22:[2,11],24:[2,11]},{14:[2,12],18:[2,12],22:[2,12],24:[2,12]},{14:[2,3],18:[2,3],22:[2,3],24:[2,3]},{14:[2,4],18:[2,4],22:[2,4],24:[2,4]},{14:[2,5],18:[2,5],22:[2,5],24:[2,5]},{14:[2,1],18:[2,1],21:[2,1],22:[2,1],24:[2,1]},{14:[2,2],18:[2,2],22:[2,2],24:[2,2]},{3:20,4:[1,12],18:[1,17],19:18,20:19},{3:5,4:[1,12],5:6,6:[1,13],7:3,8:[1,9],9:4,10:[1,10],11:[1,11],13:23,15:7,16:8,17:[1,14],23:[1,15],24:[1,21],25:22},{1:[2,6]},{14:[2,13],18:[2,13],22:[2,13],24:[2,13]},{18:[1,24],22:[1,25]},{18:[2,16],22:[2,16]},{21:[1,26]},{14:[2,18],18:[2,18],22:[2,18],24:[2,18]},{22:[1,28],24:[1,27]},{22:[2,20],24:[2,20]},{14:[2,14],18:[2,14],22:[2,14],24:[2,14]},{3:20,4:[1,12],20:29},{3:5,4:[1,12],5:6,6:[1,13],7:3,8:[1,9],9:4,10:[1,10],11:[1,11],13:30,15:7,16:8,17:[1,14],23:[1,15]},{14:[2,19],18:[2,19],22:[2,19],24:[2,19]},{3:5,4:[1,12],5:6,6:[1,13],7:3,8:[1,9],9:4,10:[1,10],11:[1,11],13:31,15:7,16:8,17:[1,14],23:[1,15]},{18:[2,17],22:[2,17]},{18:[2,15],22:[2,15]},{22:[2,21],24:[2,21]}],defaultActions:{16:[2,6]},parseError:function(b,c){throw new Error(b)},parse:function(b){function o(a){d.length=d.length-2*a,e.length=e.length-a,f.length=f.length-a}function p(){var a;return a=c.lexer.lex()||1,typeof a!="number"&&(a=c.symbols_[a]||a),a}var c=this,d=[0],e=[null],f=[],g=this.table,h="",i=0,j=0,k=0,l=2,m=1;this.lexer.setInput(b),this.lexer.yy=this.yy,this.yy.lexer=this.lexer,typeof this.lexer.yylloc=="undefined"&&(this.lexer.yylloc={});var n=this.lexer.yylloc;f.push(n),typeof this.yy.parseError=="function"&&(this.parseError=this.yy.parseError);var q,r,s,t,u,v,w={},x,y,z,A;for(;;){s=d[d.length-1],this.defaultActions[s]?t=this.defaultActions[s]:(q==null&&(q=p()),t=g[s]&&g[s][q]);if(typeof t=="undefined"||!t.length||!t[0]){if(!k){A=[];for(x in g[s])this.terminals_[x]&&x>2&&A.push("'"+this.terminals_[x]+"'");var B="";this.lexer.showPosition?B="Parse error on line "+(i+1)+":\n"+this.lexer.showPosition()+"\nExpecting "+A.join(", ")+", got '"+this.terminals_[q]+"'":B="Parse error on line "+(i+1)+": Unexpected "+(q==1?"end of input":"'"+(this.terminals_[q]||q)+"'"),this.parseError(B,{text:this.lexer.match,token:this.terminals_[q]||q,line:this.lexer.yylineno,loc:n,expected:A})}if(k==3){if(q==m)throw new Error(B||"Parsing halted.");j=this.lexer.yyleng,h=this.lexer.yytext,i=this.lexer.yylineno,n=this.lexer.yylloc,q=p()}for(;;){if(l.toString()in g[s])break;if(s==0)throw new Error(B||"Parsing halted.");o(1),s=d[d.length-1]}r=q,q=l,s=d[d.length-1],t=g[s]&&g[s][l],k=3}if(t[0]instanceof Array&&t.length>1)throw new Error("Parse Error: multiple actions possible at state: "+s+", token: "+q);switch(t[0]){case 1:d.push(q),e.push(this.lexer.yytext),f.push(this.lexer.yylloc),d.push(t[1]),q=null,r?(q=r,r=null):(j=this.lexer.yyleng,h=this.lexer.yytext,i=this.lexer.yylineno,n=this.lexer.yylloc,k>0&&k--);break;case 2:y=this.productions_[t[1]][1],w.$=e[e.length-y],w._$={first_line:f[f.length-(y||1)].first_line,last_line:f[f.length-1].last_line,first_column:f[f.length-(y||1)].first_column,last_column:f[f.length-1].last_column},v=this.performAction.call(w,h,j,i,this.yy,t[1],e,f);if(typeof v!="undefined")return v;y&&(d=d.slice(0,-1*y*2),e=e.slice(0,-1*y),f=f.slice(0,-1*y)),d.push(this.productions_[t[1]][0]),e.push(w.$),f.push(w._$),z=g[d[d.length-2]][d[d.length-1]],d.push(z);break;case 3:return!0}}return!0}},b=function(){var a={EOF:1,parseError:function(b,c){if(!this.yy.parseError)throw new Error(b);this.yy.parseError(b,c)},setInput:function(a){return this._input=a,this._more=this._less=this.done=!1,this.yylineno=this.yyleng=0,this.yytext=this.matched=this.match="",this.conditionStack=["INITIAL"],this.yylloc={first_line:1,first_column:0,last_line:1,last_column:0},this},input:function(){var a=this._input[0];this.yytext+=a,this.yyleng++,this.match+=a,this.matched+=a;var b=a.match(/\n/);return b&&this.yylineno++,this._input=this._input.slice(1),a},unput:function(a){return this._input=a+this._input,this},more:function(){return this._more=!0,this},less:function(a){this._input=this.match.slice(a)+this._input},pastInput:function(){var a=this.matched.substr(0,this.matched.length-this.match.length);return(a.length>20?"...":"")+a.substr(-20).replace(/\n/g,"")},upcomingInput:function(){var a=this.match;return a.length<20&&(a+=this._input.substr(0,20-a.length)),(a.substr(0,20)+(a.length>20?"...":"")).replace(/\n/g,"")},showPosition:function(){var a=this.pastInput(),b=(new Array(a.length+1)).join("-");return a+this.upcomingInput()+"\n"+b+"^"},next:function(){if(this.done)return this.EOF;this._input||(this.done=!0);var a,b,c,d,e,f;this._more||(this.yytext="",this.match="");var g=this._currentRules();for(var h=0;hb[0].length)){b=c,d=h;if(!this.options.flex)break}}if(b){f=b[0].match(/\n.*/g),f&&(this.yylineno+=f.length),this.yylloc={first_line:this.yylloc.last_line,last_line:this.yylineno+1,first_column:this.yylloc.last_column,last_column:f?f[f.length-1].length-1:this.yylloc.last_column+b[0].length},this.yytext+=b[0],this.match+=b[0],this.yyleng=this.yytext.length,this._more=!1,this._input=this._input.slice(b[0].length),this.matched+=b[0],a=this.performAction.call(this,this.yy,this,g[d],this.conditionStack[this.conditionStack.length-1]),this.done&&this._input&&(this.done=!1);if(a)return a;return}if(this._input==="")return this.EOF;this.parseError("Lexical error on line "+(this.yylineno+1)+". Unrecognized text.\n"+this.showPosition(),{text:"",token:null,line:this.yylineno})},lex:function(){var b=this.next();return typeof b!="undefined"?b:this.lex()},begin:function(b){this.conditionStack.push(b)},popState:function(){return this.conditionStack.pop()},_currentRules:function(){return this.conditions[this.conditionStack[this.conditionStack.length-1]].rules},topState:function(){return this.conditionStack[this.conditionStack.length-2]},pushState:function(b){this.begin(b)}};return a.options={},a.performAction=function(b,c,d,e){var f=e;switch(d){case 0:break;case 1:return 6;case 2:return c.yytext=c.yytext.substr(1,c.yyleng-2),4;case 3:return 17;case 4:return 18;case 5:return 23;case 6:return 24;case 7:return 22;case 8:return 21;case 9:return 10;case 10:return 11;case 11:return 8;case 12:return 14;case 13:return"INVALID"}},a.rules=[/^(?:\s+)/,/^(?:(-?([0-9]|[1-9][0-9]+))(\.[0-9]+)?([eE][-+]?[0-9]+)?\b)/,/^(?:"(?:\\[\\"bfnrt/]|\\u[a-fA-F0-9]{4}|[^\\\0-\x09\x0a-\x1f"])*")/,/^(?:\{)/,/^(?:\})/,/^(?:\[)/,/^(?:\])/,/^(?:,)/,/^(?::)/,/^(?:true\b)/,/^(?:false\b)/,/^(?:null\b)/,/^(?:$)/,/^(?:.)/],a.conditions={INITIAL:{rules:[0,1,2,3,4,5,6,7,8,9,10,11,12,13],inclusive:!0}},a}();return a.lexer=b,a}();return typeof a!="undefined"&&typeof c!="undefined"&&(c.parser=d,c.parse=function(){return d.parse.apply(d,arguments)},c.main=function(d){if(!d[1])throw new Error("Usage: "+d[0]+" FILE");if(typeof process!="undefined")var e=a("fs").readFileSync(a("path").join(process.cwd(),d[1]),"utf8");else var f=a("file").path(a("file").cwd()),e=f.join(d[1]).read({charset:"utf-8"});return c.parser.parse(e)},typeof b!="undefined"&&a.main===b&&c.main(typeof process!="undefined"?process.argv.slice(1):a("system").args)),c}(); \ No newline at end of file +var jsonlint=function(){var require=true,module=false;var exports={};var parser=function(){var o=function(k,v,o,l){for(o=o||{},l=k.length;l--;o[k[l]]=v);return o},$V0=[1,12],$V1=[1,13],$V2=[1,9],$V3=[1,10],$V4=[1,11],$V5=[1,14],$V6=[1,15],$V7=[14,18,22,24],$V8=[18,22],$V9=[22,24];var parser={trace:function trace(){},yy:{},symbols_:{error:2,JSONString:3,STRING:4,JSONNumber:5,NUMBER:6,JSONNullLiteral:7,NULL:8,JSONBooleanLiteral:9,TRUE:10,FALSE:11,JSONText:12,JSONValue:13,EOF:14,JSONObject:15,JSONArray:16,"{":17,"}":18,JSONMemberList:19,JSONMember:20,":":21,",":22,"[":23,"]":24,JSONElementList:25,$accept:0,$end:1},terminals_:{2:"error",4:"STRING",6:"NUMBER",8:"NULL",10:"TRUE",11:"FALSE",14:"EOF",17:"{",18:"}",21:":",22:",",23:"[",24:"]"},productions_:[0,[3,1],[5,1],[7,1],[9,1],[9,1],[12,2],[13,1],[13,1],[13,1],[13,1],[13,1],[13,1],[15,2],[15,3],[20,3],[19,1],[19,3],[16,2],[16,3],[25,1],[25,3]],performAction:function anonymous(yytext,yyleng,yylineno,yy,yystate,$$,_$){var $0=$$.length-1;switch(yystate){case 1:this.$=yytext.replace(/\\([\"\\\/bfnrt]|u[0-9a-fA-f]{4})/g,function(match,part){if(part.charAt(0)==="u"){return String.fromCharCode(parseInt(part.substr(1),16))}switch(part){case"b":return"\b";case"f":return"\f";case"n":return"\n";case"r":return"\r";case"t":return" ";case'"':case"\\":case"/":return part}});break;case 2:this.$=Number(yytext);break;case 3:this.$=null;break;case 4:this.$=true;break;case 5:this.$=false;break;case 6:return this.$=$$[$0-1];break;case 13:this.$={};break;case 14:case 19:this.$=$$[$0-1];break;case 15:this.$=[$$[$0-2],$$[$0]];break;case 16:this.$={};this.$[$$[$0][0]]=$$[$0][1];break;case 17:this.$=$$[$0-2];$$[$0-2][$$[$0][0]]=$$[$0][1];break;case 18:this.$=[];break;case 20:this.$=[$$[$0]];break;case 21:this.$=$$[$0-2];$$[$0-2].push($$[$0]);break}},table:[{3:5,4:$V0,5:6,6:$V1,7:3,8:$V2,9:4,10:$V3,11:$V4,12:1,13:2,15:7,16:8,17:$V5,23:$V6},{1:[3]},{14:[1,16]},o($V7,[2,7]),o($V7,[2,8]),o($V7,[2,9]),o($V7,[2,10]),o($V7,[2,11]),o($V7,[2,12]),o($V7,[2,3]),o($V7,[2,4]),o($V7,[2,5]),o([14,18,21,22,24],[2,1]),o($V7,[2,2]),{3:20,4:$V0,18:[1,17],19:18,20:19},{3:5,4:$V0,5:6,6:$V1,7:3,8:$V2,9:4,10:$V3,11:$V4,13:23,15:7,16:8,17:$V5,23:$V6,24:[1,21],25:22},{1:[2,6]},o($V7,[2,13]),{18:[1,24],22:[1,25]},o($V8,[2,16]),{21:[1,26]},o($V7,[2,18]),{22:[1,28],24:[1,27]},o($V9,[2,20]),o($V7,[2,14]),{3:20,4:$V0,20:29},{3:5,4:$V0,5:6,6:$V1,7:3,8:$V2,9:4,10:$V3,11:$V4,13:30,15:7,16:8,17:$V5,23:$V6},o($V7,[2,19]),{3:5,4:$V0,5:6,6:$V1,7:3,8:$V2,9:4,10:$V3,11:$V4,13:31,15:7,16:8,17:$V5,23:$V6},o($V8,[2,17]),o($V8,[2,15]),o($V9,[2,21])],defaultActions:{16:[2,6]},parseError:function parseError(str,hash){if(hash.recoverable){this.trace(str)}else{throw new Error(str)}},parse:function parse(input){var self=this,stack=[0],tstack=[],vstack=[null],lstack=[],table=this.table,yytext="",yylineno=0,yyleng=0,recovering=0,TERROR=2,EOF=1;var args=lstack.slice.call(arguments,1);var lexer=Object.create(this.lexer);var sharedState={yy:{}};for(var k in this.yy){if(Object.prototype.hasOwnProperty.call(this.yy,k)){sharedState.yy[k]=this.yy[k]}}lexer.setInput(input,sharedState.yy);sharedState.yy.lexer=lexer;sharedState.yy.parser=this;if(typeof lexer.yylloc=="undefined"){lexer.yylloc={}}var yyloc=lexer.yylloc;lstack.push(yyloc);var ranges=lexer.options&&lexer.options.ranges;if(typeof sharedState.yy.parseError==="function"){this.parseError=sharedState.yy.parseError}else{this.parseError=Object.getPrototypeOf(this).parseError}function popStack(n){stack.length=stack.length-2*n;vstack.length=vstack.length-n;lstack.length=lstack.length-n}_token_stack:function lex(){var token;token=lexer.lex()||EOF;if(typeof token!=="number"){token=self.symbols_[token]||token}return token}var symbol,preErrorSymbol,state,action,a,r,yyval={},p,len,newState,expected;while(true){state=stack[stack.length-1];if(this.defaultActions[state]){action=this.defaultActions[state]}else{if(symbol===null||typeof symbol=="undefined"){symbol=lex()}action=table[state]&&table[state][symbol]}if(typeof action==="undefined"||!action.length||!action[0]){var errStr="";expected=[];for(p in table[state]){if(this.terminals_[p]&&p>TERROR){expected.push("'"+this.terminals_[p]+"'")}}if(lexer.showPosition){errStr="Parse error on line "+(yylineno+1)+":\n"+lexer.showPosition()+"\nExpecting "+expected.join(", ")+", got '"+(this.terminals_[symbol]||symbol)+"'"}else{errStr="Parse error on line "+(yylineno+1)+": Unexpected "+(symbol==EOF?"end of input":"'"+(this.terminals_[symbol]||symbol)+"'")}this.parseError(errStr,{text:lexer.match,token:this.terminals_[symbol]||symbol,line:lexer.yylineno,loc:yyloc,expected:expected})}if(action[0]instanceof Array&&action.length>1){throw new Error("Parse Error: multiple actions possible at state: "+state+", token: "+symbol)}switch(action[0]){case 1:stack.push(symbol);vstack.push(lexer.yytext);lstack.push(lexer.yylloc);stack.push(action[1]);symbol=null;if(!preErrorSymbol){yyleng=lexer.yyleng;yytext=lexer.yytext;yylineno=lexer.yylineno;yyloc=lexer.yylloc;if(recovering>0){recovering--}}else{symbol=preErrorSymbol;preErrorSymbol=null}break;case 2:len=this.productions_[action[1]][1];yyval.$=vstack[vstack.length-len];yyval._$={first_line:lstack[lstack.length-(len||1)].first_line,last_line:lstack[lstack.length-1].last_line,first_column:lstack[lstack.length-(len||1)].first_column,last_column:lstack[lstack.length-1].last_column};if(ranges){yyval._$.range=[lstack[lstack.length-(len||1)].range[0],lstack[lstack.length-1].range[1]]}r=this.performAction.apply(yyval,[yytext,yyleng,yylineno,sharedState.yy,action[1],vstack,lstack].concat(args));if(typeof r!=="undefined"){return r}if(len){stack=stack.slice(0,-1*len*2);vstack=vstack.slice(0,-1*len);lstack=lstack.slice(0,-1*len)}stack.push(this.productions_[action[1]][0]);vstack.push(yyval.$);lstack.push(yyval._$);newState=table[stack[stack.length-2]][stack[stack.length-1]];stack.push(newState);break;case 3:return true}}return true}};var lexer=function(){var lexer={EOF:1,parseError:function parseError(str,hash){if(this.yy.parser){this.yy.parser.parseError(str,hash)}else{throw new Error(str)}},setInput:function(input,yy){this.yy=yy||this.yy||{};this._input=input;this._more=this._backtrack=this.done=false;this.yylineno=this.yyleng=0;this.yytext=this.matched=this.match="";this.conditionStack=["INITIAL"];this.yylloc={first_line:1,first_column:0,last_line:1,last_column:0};if(this.options.ranges){this.yylloc.range=[0,0]}this.offset=0;return this},input:function(){var ch=this._input[0];this.yytext+=ch;this.yyleng++;this.offset++;this.match+=ch;this.matched+=ch;var lines=ch.match(/(?:\r\n?|\n).*/g);if(lines){this.yylineno++;this.yylloc.last_line++}else{this.yylloc.last_column++}if(this.options.ranges){this.yylloc.range[1]++}this._input=this._input.slice(1);return ch},unput:function(ch){var len=ch.length;var lines=ch.split(/(?:\r\n?|\n)/g);this._input=ch+this._input;this.yytext=this.yytext.substr(0,this.yytext.length-len);this.offset-=len;var oldLines=this.match.split(/(?:\r\n?|\n)/g);this.match=this.match.substr(0,this.match.length-1);this.matched=this.matched.substr(0,this.matched.length-1);if(lines.length-1){this.yylineno-=lines.length-1}var r=this.yylloc.range;this.yylloc={first_line:this.yylloc.first_line,last_line:this.yylineno+1,first_column:this.yylloc.first_column,last_column:lines?(lines.length===oldLines.length?this.yylloc.first_column:0)+oldLines[oldLines.length-lines.length].length-lines[0].length:this.yylloc.first_column-len};if(this.options.ranges){this.yylloc.range=[r[0],r[0]+this.yyleng-len]}this.yyleng=this.yytext.length;return this},more:function(){this._more=true;return this},reject:function(){if(this.options.backtrack_lexer){this._backtrack=true}else{return this.parseError("Lexical error on line "+(this.yylineno+1)+". You can only invoke reject() in the lexer when the lexer is of the backtracking persuasion (options.backtrack_lexer = true).\n"+this.showPosition(),{text:"",token:null,line:this.yylineno})}return this},less:function(n){this.unput(this.match.slice(n))},pastInput:function(){var past=this.matched.substr(0,this.matched.length-this.match.length);return(past.length>20?"...":"")+past.substr(-20).replace(/\n/g,"")},upcomingInput:function(){var next=this.match;if(next.length<20){next+=this._input.substr(0,20-next.length)}return(next.substr(0,20)+(next.length>20?"...":"")).replace(/\n/g,"")},showPosition:function(){var pre=this.pastInput();var c=new Array(pre.length+1).join("-");return pre+this.upcomingInput()+"\n"+c+"^"},test_match:function(match,indexed_rule){var token,lines,backup;if(this.options.backtrack_lexer){backup={yylineno:this.yylineno,yylloc:{first_line:this.yylloc.first_line,last_line:this.last_line,first_column:this.yylloc.first_column,last_column:this.yylloc.last_column},yytext:this.yytext,match:this.match,matches:this.matches,matched:this.matched,yyleng:this.yyleng,offset:this.offset,_more:this._more,_input:this._input,yy:this.yy,conditionStack:this.conditionStack.slice(0),done:this.done};if(this.options.ranges){backup.yylloc.range=this.yylloc.range.slice(0)}}lines=match[0].match(/(?:\r\n?|\n).*/g);if(lines){this.yylineno+=lines.length}this.yylloc={first_line:this.yylloc.last_line,last_line:this.yylineno+1,first_column:this.yylloc.last_column,last_column:lines?lines[lines.length-1].length-lines[lines.length-1].match(/\r?\n?/)[0].length:this.yylloc.last_column+match[0].length};this.yytext+=match[0];this.match+=match[0];this.matches=match;this.yyleng=this.yytext.length;if(this.options.ranges){this.yylloc.range=[this.offset,this.offset+=this.yyleng]}this._more=false;this._backtrack=false;this._input=this._input.slice(match[0].length);this.matched+=match[0];token=this.performAction.call(this,this.yy,this,indexed_rule,this.conditionStack[this.conditionStack.length-1]);if(this.done&&this._input){this.done=false}if(token){return token}else if(this._backtrack){for(var k in backup){this[k]=backup[k]}return false}return false},next:function(){if(this.done){return this.EOF}if(!this._input){this.done=true}var token,match,tempMatch,index;if(!this._more){this.yytext="";this.match=""}var rules=this._currentRules();for(var i=0;imatch[0].length)){match=tempMatch;index=i;if(this.options.backtrack_lexer){token=this.test_match(tempMatch,rules[i]);if(token!==false){return token}else if(this._backtrack){match=false;continue}else{return false}}else if(!this.options.flex){break}}}if(match){token=this.test_match(match,rules[index]);if(token!==false){return token}return false}if(this._input===""){return this.EOF}else{return this.parseError("Lexical error on line "+(this.yylineno+1)+". Unrecognized text.\n"+this.showPosition(),{text:"",token:null,line:this.yylineno})}},lex:function lex(){var r=this.next();if(r){return r}else{return this.lex()}},begin:function begin(condition){this.conditionStack.push(condition)},popState:function popState(){var n=this.conditionStack.length-1;if(n>0){return this.conditionStack.pop()}else{return this.conditionStack[0]}},_currentRules:function _currentRules(){if(this.conditionStack.length&&this.conditionStack[this.conditionStack.length-1]){return this.conditions[this.conditionStack[this.conditionStack.length-1]].rules}else{return this.conditions["INITIAL"].rules}},topState:function topState(n){n=this.conditionStack.length-1-Math.abs(n||0);if(n>=0){return this.conditionStack[n]}else{return"INITIAL"}},pushState:function pushState(condition){this.begin(condition)},stateStackSize:function stateStackSize(){return this.conditionStack.length},options:{},performAction:function anonymous(yy,yy_,$avoiding_name_collisions,YY_START){var YYSTATE=YY_START;switch($avoiding_name_collisions){case 0:break;case 1:return 6;break;case 2:yy_.yytext=yy_.yytext.substr(1,yy_.yyleng-2);return 4;break;case 3:return 17;break;case 4:return 18;break;case 5:return 23;break;case 6:return 24;break;case 7:return 22;break;case 8:return 21;break;case 9:return 10;break;case 10:return 11;break;case 11:return 8;break;case 12:return 14;break;case 13:return"INVALID";break}},rules:[/^(?:\s+)/,/^(?:(-?([0-9]|[1-9][0-9]+))(\.[0-9]+)?([eE][-+]?[0-9]+)?\b)/,/^(?:"(?:\\[\\"bfnrt/]|\\u[a-fA-F0-9]{4}|[^\\\0-\x09\x0a-\x1f"])*")/,/^(?:\{)/,/^(?:\})/,/^(?:\[)/,/^(?:\])/,/^(?:,)/,/^(?::)/,/^(?:true\b)/,/^(?:false\b)/,/^(?:null\b)/,/^(?:$)/,/^(?:.)/],conditions:{INITIAL:{rules:[0,1,2,3,4,5,6,7,8,9,10,11,12,13],inclusive:true}}};return lexer}();parser.lexer=lexer;function Parser(){this.yy={}}Parser.prototype=parser;parser.Parser=Parser;return new Parser}();if(typeof require!=="undefined"&&typeof exports!=="undefined"){exports.parser=parser;exports.Parser=parser.Parser;exports.parse=function(){return parser.parse.apply(parser,arguments)};exports.main=function commonjsMain(args){if(!args[1]){console.log("Usage: "+args[0]+" FILE");process.exit(1)}var source=require("fs").readFileSync(require("path").normalize(args[1]),"utf8");return exports.parser.parse(source)};if(typeof module!=="undefined"&&require.main===module){exports.main(process.argv.slice(1))}}return exports}(); \ No newline at end of file From aaf81b140f12cfa20ba9411770fa26f665ba6010 Mon Sep 17 00:00:00 2001 From: ntdaley Date: Wed, 15 Oct 2014 00:12:40 +0100 Subject: [PATCH 2/2] Don't escape regular whitespace characters. --- lib/cli.js | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/cli.js b/lib/cli.js index 38ed9bd..de385a0 100755 --- a/lib/cli.js +++ b/lib/cli.js @@ -90,7 +90,7 @@ function parse (source) { } } - return JSON.stringify(parsed, null, options.indent).replace(/[^\x20-\x7e]/g, function(char) { + return JSON.stringify(parsed, null, options.indent).replace(/[^\n\r\ \x20-\x7e]/g, function(char) { return '\\u' + ('0000' + Number(char.charCodeAt(0)).toString(16)).match(/....$/)[0]; }); } catch (e) {