json5/json5.js

// json5.js
// Modern JSON. See README.md for details.
//
// This file is modeled directly off of Douglas Crockford's json_parse.js:
// https://github.com/douglascrockford/JSON-js/blob/master/json_parse.js

var JSON5 = (typeof exports === 'object' ? exports : {});

JSON5.parse = (function () {
    "use strict";

// This is a function that can parse a JSON5 text, producing a JavaScript
// data structure. It is a simple, recursive descent parser. It does not use
// eval or regular expressions, so it can be used as a model for implementing
// a JSON5 parser in other languages.

// We are defining the function inside of another function to avoid creating
// global variables.

    var at,     // The index of the current character
        ch,     // The current character
        escapee = {
            "'":  "'",
            '"':  '"',
            '\\': '\\',
            '/':  '/',
            '\n': '',       // Replace newlines in strings w/ empty string
            b:    '\b',
            f:    '\f',
            n:    '\n',
            r:    '\r',
            t:    '\t'
        },
        text,

        error = function (m) {

// Call error when something is wrong.

            throw {
                name:    'SyntaxError',
                message: m,
                at:      at,
                text:    text
            };
        },

        next = function (c) {

// If a c parameter is provided, verify that it matches the current character.

            if (c && c !== ch) {
                error("Expected '" + c + "' instead of '" + ch + "'");
            }

// Get the next character. When there are no more characters,
// return the empty string.

            ch = text.charAt(at);
            at += 1;
            return ch;
        },

        identifier = function () {

// Parse an identifier. Normally, reserved words are disallowed here, but we
// only use this for unquoted object keys, where reserved words are allowed,
// so we don't check for those here. References:
// - http://es5.github.com/#x7.6
// - https://developer.mozilla.org/en/Core_JavaScript_1.5_Guide/Core_Language_Features#Variables
// - http://docstore.mik.ua/orelly/webprog/jscript/ch02_07.htm
// TODO Identifiers can have Unicode "letters" in them; add support for those.

            var key = ch;

            // Identifiers must start with a letter, _ or $.
            if (!ch.match(/^[a-zA-Z_$]$/)) {
                error("Bad identifier");
            }

            // Subsequent characters can contain digits.
            while (next() && ch.match(/^[\w$]$/)) {
                key += ch;
            }

            return key;
        },

        number = function () {

// Parse a number value.

            var number,
                string = '';

            if (ch === '-') {
                string = '-';
                next('-');
            }
            while (ch >= '0' && ch <= '9') {
                string += ch;
                next();
            }
            if (ch === '.') {
                string += '.';
                while (next() && ch >= '0' && ch <= '9') {
                    string += ch;
                }
            }
            if (ch === 'e' || ch === 'E') {
                string += ch;
                next();
                if (ch === '-' || ch === '+') {
                    string += ch;
                    next();
                }
                while (ch >= '0' && ch <= '9') {
                    string += ch;
                    next();
                }
            }
            number = +string;
            if (!isFinite(number)) {
                error("Bad number");
            } else {
                return number;
            }
        },

        string = function () {

// Parse a string value.

            var hex,
                i,
                string = '',
                delim,      // double quote or single quote
                uffff;

// When parsing for string values, we must look for " and \ characters.

            if (ch === '"' || ch === "'") {
                delim = ch;
                while (next()) {
                    if (ch === delim) {
                        next();
                        return string;
                    } else if (ch === '\\') {
                        next();
                        if (ch === 'u') {
                            uffff = 0;
                            for (i = 0; i < 4; i += 1) {
                                hex = parseInt(next(), 16);
                                if (!isFinite(hex)) {
                                    break;
                                }
                                uffff = uffff * 16 + hex;
                            }
                            string += String.fromCharCode(uffff);
                        } else if (typeof escapee[ch] === 'string') {
                            string += escapee[ch];
                        } else {
                            break;
                        }
                    } else {
                        string += ch;
                    }
                }
            }
            error("Bad string");
        },

        inlineComment = function () {

// Skip inline comments, assuming this is one. The current character should be
// the second / character in the // pair that begins this inline comment.
// When parsing inline comments, we look for a newline or the end of the text.

            if (ch !== '/') {
                error("Not an inline comment");
            }

            do {
                next();
                if (ch === '\n') {
                    next('\n');
                    return;
                }
            } while (ch);
        },

        blockComment = function () {

// Skip block comments, assuming this is one. The current character should be
// the * character in the /* pair that begins this block comment.
// When parsing block comments, we look for an ending */ pair of characters,
// but we also watch for the end of text before the comment is terminated.

            if (ch !== '*') {
                error("Not a block comment");
            }

            do {
                next();
                while (ch === '*') {
                    next('*');
                    if (ch === '/') {
                        next('/');
                        return;
                    }
                }
            } while (ch);

            error("Unterminated block comment");
        },

        comment = function () {

// Skip comments, both inline and block-level, assuming this is one. Comments
// always begin with a / character.

            if (ch !== '/') {
                error("Not a comment");
            }

            next('/');

            if (ch === '/') {
                inlineComment();
            } else if (ch === '*') {
                blockComment();
            } else {
                error("Unrecognized comment");
            }
        },

        white = function () {

// Skip whitespace and comments.
// Note that we're detecting comments by only a single / character.
// This works since regular expressions are not valid JSON(5), but this will
// break if there are other valid values that begin with a / character!

            while (ch) {
                if (ch === '/') {
                    comment();
                } else if (ch <= ' ') {
                    next();
                } else {
                    return;
                }
            }
        },

        word = function () {

// true, false, or null.

            switch (ch) {
            case 't':
                next('t');
                next('r');
                next('u');
                next('e');
                return true;
            case 'f':
                next('f');
                next('a');
                next('l');
                next('s');
                next('e');
                return false;
            case 'n':
                next('n');
                next('u');
                next('l');
                next('l');
                return null;
            }
            error("Unexpected '" + ch + "'");
        },

        value,  // Place holder for the value function.

        array = function () {

// Parse an array value.

            var array = [];

            if (ch === '[') {
                next('[');
                white();
                while (ch) {
                    if (ch === ']') {
                        next(']');
                        return array;   // Potentially empty array
                    }
                    // Omitted values are allowed and detected by the presence
                    // of a trailing comma. Whether the value was omitted or
                    // not, the current character after this block should be
                    // the character after the value.
                    if (ch === ',') {
                        // Pushing an undefined value isn't quite equivalent
                        // to what ES5 does in practice, but we can emulate it
                        // by incrementing the array's length.
                        array.length += 1;
                        // Don't go next; the comma is the character after the
                        // omitted (undefined) value.
                    } else {
                        array.push(value());
                        // The various value methods call next(); the current
                        // character here is now the one after the value.
                    }
                    white();
                    // If there's no comma after this value, this needs to
                    // be the end of the array.
                    if (ch !== ',') {
                        next(']');
                        return array;
                    }
                    next(',');
                    white();
                }
            }
            error("Bad array");
        },

        object = function () {

// Parse an object value.
// TODO Update to support unquoted keys.

            var key,
                object = {};

            if (ch === '{') {
                next('{');
                white();
                while (ch) {
                    if (ch === '}') {
                        next('}');
                        return object;   // Potentially empty object
                    }

                    // Keys can be unquoted. If they are, they need to be
                    // valid JS identifiers.
                    if (ch === '"' || ch === "'") {
                        key = string();
                    } else {
                        key = identifier();
                    }

                    white();
                    next(':');
                    if (Object.hasOwnProperty.call(object, key)) {
                        error('Duplicate key "' + key + '"');
                    }
                    object[key] = value();
                    white();
                    // If there's no comma after this pair, this needs to be
                    // the end of the object.
                    if (ch !== ',') {
                        next('}');
                        return object;
                    }
                    next(',');
                    white();
                }
            }
            error("Bad object");
        };

    value = function () {

// Parse a JSON value. It could be an object, an array, a string, a number,
// or a word.

        white();
        switch (ch) {
        case '{':
            return object();
        case '[':
            return array();
        case '"':
        case "'":
            return string();
        case '-':
            return number();
        default:
            return ch >= '0' && ch <= '9' ? number() : word();
        }
    };

// Return the json_parse function. It will have access to all of the above
// functions and variables.

    return function (source, reviver) {
        var result;

        text = source;
        at = 0;
        ch = ' ';
        result = value();
        white();
        if (ch) {
            error("Syntax error");
        }

// If there is a reviver function, we recursively walk the new structure,
// passing each name/value pair to the reviver function for possible
// transformation, starting with a temporary root object that holds the result
// in an empty key. If there is not a reviver function, we simply return the
// result.

        return typeof reviver === 'function' ? (function walk(holder, key) {
            var k, v, value = holder[key];
            if (value && typeof value === 'object') {
                for (k in value) {
                    if (Object.prototype.hasOwnProperty.call(value, k)) {
                        v = walk(value, k);
                        if (v !== undefined) {
                            value[k] = v;
                        } else {
                            delete value[k];
                        }
                    }
                }
            }
            return reviver.call(holder, key, value);
        }({'': result}, '')) : result;
    };
}());

JSON5.stringify = function (obj, replacer, space) {
    // Since regular JSON is a strict subset of JSON5, we'll always output as
    // regular JSON to foster better interoperability. TODO Should we not?
    return JSON.stringify.apply(JSON, arguments);
};