All Downloads are FREE. Search and download functionalities are using the official Maven repository.

javacc-7.0.3.grammars.JSONParser.jjt Maven / Gradle / Ivy

There is a newer version: 7.0.13
Show newest version
/*
 * This software is licensed under the terms of the ISC License.
 * (ISCL http://www.opensource.org/licenses/isc-license.txt
 * It is functionally equivalent to the 2-clause BSD licence,
 * with language "made unnecessary by the Berne convention" removed).
 *
 * Copyright (c) 2011-2013 Mike Norman
 *
 * Permission to use, copy, modify, and/or distribute this software for any
 * purpose with or without fee is hereby granted, provided that the above
 * copyright notice and this permission notice appear in all copies.
 *
 * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
 * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
 * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
 * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER
 * RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
 * NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE
 * USE OR PERFORMANCE OF THIS SOFTWARE.
 *
 ******************************************************************************/
options {
      STATIC = false;
      SUPPORT_CLASS_VISIBILITY_PUBLIC = true;
      ERROR_REPORTING = false;
      JAVA_UNICODE_ESCAPE = true;
      UNICODE_INPUT = true;
      NODE_USES_PARSER = false;
      VISITOR = false;
}

PARSER_BEGIN(JSONParser)
/*
 * This software is licensed under the terms of the ISC License.
 * (ISCL http://www.opensource.org/licenses/isc-license.txt
 * It is functionally equivalent to the 2-clause BSD licence,
 * with language "made unnecessary by the Berne convention" removed).
 *
 * Copyright (c) 2011-2013 Mike Norman
 *
 * Permission to use, copy, modify, and/or distribute this software for any
 * purpose with or without fee is hereby granted, provided that the above
 * copyright notice and this permission notice appear in all copies.
 *
 * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
 * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
 * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
 * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER
 * RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
 * NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE
 * USE OR PERFORMANCE OF THIS SOFTWARE.
 *
 ******************************************************************************/
package org.mwnorman.json;

//javase imports
import java.math.BigDecimal;
import java.math.BigInteger;
import java.util.ArrayList;
import java.util.Collections;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;

public class JSONParser {

    static protected String stripOffQuotes(String quotedString) {
        return quotedString.substring(1, quotedString.length() - 1);
    }
    public static String TRUE_ATOM = stripOffQuotes(tokenImage[K_TRUE]);
    public static String FALSE_ATOM = stripOffQuotes(tokenImage[K_FALSE]);

    public JSONParser() {
        super();
    }

    //cheat to sorta get generics on productions
    public  List array() throws ParseException {
        return _array();
    }
    public  Map object() throws ParseException {
        return _object();
    }
}

PARSER_END(JSONParser)

TOKEN_MGR_DECLS :
{
    static int commentNesting = 0;
}

// Pls see http://www.ietf.org/rfc/rfc4627.txt for JSON spec details

// white space
SKIP: {
        " "
    |   "\t"
    |   "\n"
    |   "\r"
    |   "\f"
}

// comments: not really part of JSON spec, but parser shouldn't blow-up if present
SKIP: {
        //single-line 'C'-style comments
        < "//" (~["\n","\r"])* ("\n" | "\r" | "\r\n")>
        //single-line Bash-style comments
    |   < "#" (~["\n","\r"])* ("\n"|"\r"|"\r\n")>
        //multi-line 'C'-style comments with counter for nesting
    |   "/*" { commentNesting++; } : WithinMLC
        //multi-line HTML comments (no nesting)
    |   "" : DEFAULT
}
 MORE :
{
        <~[]>
}

// JSON reserved keywords (prefix with K_ to avoid naming conflicts): only lower case allowed!
TOKEN: {
        
    |   
    |   
}

// JSON operators (prefix with O_ to avoid naming conflicts)
TOKEN: {
        
    |   
    |   
    |   
    |   
    |   
    |   
    |   
    |   
}

// numeric literals
TOKEN: {
        <#DIGIT: [
            //Unicode "DIGIT" characters - more inclusive than Character.isDigit
            "\u0030"-"\u0039", //DIGIT ZERO - DIGIT NINE
            "\u0660"-"\u0669", //ARABIC-INDIC DIGIT ZERO -ARABIC-INDIC DIGIT NINE
            "\u06f0"-"\u06f9", //EXTENDED ARABIC-INDIC DIGIT ZERO - EXTENDED ARABIC-INDIC DIGIT NINE
            "\u07c0"-"\u07c9", //NKO DIGIT ZERO - NKO DIGIT NINE
            "\u0966"-"\u096f", //DEVANAGARI DIGIT ZERO - DEVANAGARI DIGIT NINE
            "\u09e6"-"\u09ef", //BENGALI DIGIT ZERO - BENGALI DIGIT NINE
            "\u0a66"-"\u0a6f", //GURMUKHI DIGIT ZERO - GURMUKHI DIGIT NINE
            "\u0ae6"-"\u0aef", //GUJARATI DIGIT ZERO - GUJARATI DIGIT NINE
            "\u0b66"-"\u0b6f", //ORIYA DIGIT ZERO - ORIYA DIGIT NINE
            "\u0be6"-"\u0bef", //TAMIL DIGIT ZERO - TAMIL DIGIT NINE
            "\u0c66"-"\u0c6f", //TELUGU DIGIT ZERO - TELUGU DIGIT NINE
            "\u0ce6"-"\u0cef", //KANNADA DIGIT ZERO - KANNADA DIGIT NINE
            "\u0d66"-"\u0d6f", //MALAYALAM DIGIT ZERO - MALAYALAM DIGIT NINE
            "\u0e50"-"\u0e59", //THAI DIGIT ZERO - THAI DIGIT NINE
            "\u0ed0"-"\u0ed9", //LAO DIGIT ZERO - LAO DIGIT NINE
            "\u0f20"-"\u0f29", //TIBETAN DIGIT ZERO - TIBETAN DIGIT NINE
            "\u1040"-"\u1049", //MYANMAR DIGIT ZERO - MYANMAR DIGIT NINE
            "\u1090"-"\u1099", //MYANMAR SHAN DIGIT ZERO - MYANMAR SHAN DIGIT NINE
            "\u1369"-"\u1371", //ETHIOPIC DIGIT ZERO - ETHIOPIC DIGIT NINE  
            "\u17e0"-"\u17e9", //KHMER DIGIT ZERO - KHMER DIGIT NINE
            "\u1810"-"\u1819", //MONGOLIAN DIGIT ZERO - MONGOLIAN DIGIT NINE
            "\u1946"-"\u194f", //LIMBU DIGIT ZERO - LIMBU DIGIT NINE
            "\u19d0"-"\u19d9", //NEW TAI LUE DIGIT ZERO - NEW TAI LUE DIGIT NINE
            "\u1a80"-"\u1a89", //TAI THAM HORA DIGIT ZERO - TAI THAM HORA DIGIT NINE
            "\u1a90"-"\u1a99", //TAI THAM THAM DIGIT ZERO - TAI THAM THAM DIGIT NINE
            "\u1b50"-"\u1b59", //BALINESE DIGIT ZERO - BALINESE DIGIT NINE
            "\u1bb0"-"\u1bb9", //SUNDANESE DIGIT ZERO - SUNDANESE DIGIT NINE
            "\u1c40"-"\u1c49", //LEPCHA DIGIT ZERO - LEPCHA DIGIT NINE
            "\u1c50"-"\u1c59", //OL CHIKI DIGIT ZERO - OL CHIKI DIGIT NINE
            "\ua620"-"\ua629", //VAI DIGIT ZERO - VAI DIGIT NINE
            "\ua8d0"-"\ua8d9", //SAURASHTRA DIGIT ZERO - SAURASHTRA DIGIT NINE
            "\ua8e0"-"\ua8e9", //COMBINING DEVANAGARI DIGIT ZERO - COMBINING DEVANAGARI DIGIT NINE
            "\ua900"-"\ua909", //KAYAH LI DIGIT ZERO - KAYAH LI DIGIT NINE
            "\ua9d0"-"\ua9d9", //JAVANESE DIGIT ZERO - JAVANESE DIGIT NINE
            "\uaa50"-"\uaa59", //CHAM DIGIT ZERO - CHAM DIGIT NINE
            "\uabf0"-"\uabf9", //MEETEI MAYEK DIGIT ZERO - MEETEI MAYEK DIGIT NINE
            "\uff10"-"\uff19"  //FULLWIDTH DIGIT ZERO -FULLWIDTH DIGIT NINE
        ] >
    |   <#EXP: ["e", "E"] (  |  )? >
}
// JSON numbers do not support octal or hexadecimal formats
TOKEN: {
         |   |   |    >
    |   )? (  ) > //support leading zeros
    |     >
    |     >
    |    )+ >
}

// string literals
TOKEN: {
        
    |   
}
TOKEN: {
         ( |  | "_")* >
    |   <#LETTER: [
            //Unicode "LETTER" characters - as of Javase 6, Unicode 4 is supported
            //http://www.unicode.org/Public/4.1.0/ucd/NamesList.txt
            //more inclusive than Character.isLetter
           "\u0024",          //DOLLAR SIGN: milreis, escudo
           "\u0041"-"\u005a", //LATIN CAPITAL LETTER A - LATIN CAPITAL LETTER Z
           "\u005f",          //LOW LINE: spacing underscore
           "\u0061"-"\u007a", //LATIN SMALL LETTER A - LATIN SMALL LETTER Z
           "\u00aa"-"\u00ad", //  00AA FEMININE ORDINAL INDICATOR: spanish
                              //  00AB LEFT-POINTING DOUBLE ANGLE QUOTATION MARK: left guillemet
                              //  00AC NOT SIGN: angled dash
                              //  00AD SOFT HYPHEN: discretionary hyphen
           "\u00b5"-"\u00b6", //  00B5 MICRO SIGN: greek small letter mu
                              //  00B6 PILCROW SIGN: paragraph sign
           "\u00ba"-"\u00bb", //  00BA MASCULINE ORDINAL INDICATOR: spanish
                              //  00BB RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK : right guillemet        
           "\u00c0"-"\u00d6", //LATIN CAPITAL LETTER A WITH GRAVE - LATIN CAPITAL LETTER O WITH DIAERESIS
           "\u00d8"-"\u00f6", //LATIN CAPITAL LETTER O WITH STROKE - LATIN SMALL LETTER O WITH DIAERESIS
           "\u00f8"-"\u00ff", //LATIN SMALL LETTER O WITH STROKE - LATIN SMALL LETTER Y WITH DIAERESIS
           "\u0100"-"\u1fff", //LATIN CAPITAL LETTER A WITH MACRON - GREEK DASIA:reversed comma
           "\u3040"-"\u318f", //Hiragana - Hangul
           "\u3300"-"\u337f", //Squared Katakana
           "\u3400"-"\u3d2d", //CJK Unified Ideographs Extension A
           "\u4e00"-"\u9fff", //CJK Unified Ideographs
           "\uf900"-"\ufaff", //CJK Compatibility Ideographs
           "\ufb00"-"\ufb06", //LATIN SMALL LIGATURE FF -LATIN SMALL LIGATURE ST
           "\ufb13"-"\ufb17", //ARMENIAN SMALL LIGATURE MEN NOW - ARMENIAN SMALL LIGATURE MEN XEH
           "\ufb1f"-"\ufb28", //HEBREW LIGATURE YIDDISH YOD YOD PATAH -HEBREW LETTER WIDE TAV
           "\ufb2a"-"\ufb36", //HEBREW LETTER SHIN WITH SHIN DOT - HEBREW LETTER ZAYIN WITH DAGESH
           "\ufb38"-"\ufb3e", //HEBREW LETTER TET WITH DAGESH - HEBREW LETTER MEM WITH DAGESH
           "\ufb40"-"\ufb41", //HEBREW LETTER NUN WITH DAGESH - HEBREW LETTER SAMEKH WITH DAGESH
           "\ufb43"-"\ufb44", //HEBREW LETTER FINAL PE WITH DAGESH - HEBREW LETTER PE WITH DAGESH
           "\ufb46"-"\ufb4f", //HEBREW LETTER TSADI WITH DAGESH - HEBREW LIGATURE ALEF LAMED
           "\ufb50"-"\ufdd7", //Arabic Presentation Forms(A) - ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
           "\ufdf0"-"\ufdfd", //ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM -ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
           "\ufe70"-"\ufefc", //Arabic Presentation Forms(B) - ARABIC LIGATURE LAM WITH ALEF FINAL FORM
           "\uff1f"-"\uff3a", //FULLWIDTH QUESTION MARK - FULLWIDTH LATIN CAPITAL LETTER Z
           "\uff3f"-"\uff5e", //FULLWIDTH LOW LINE - FULLWIDTH TILDE
           "\uff61"-"\uffbe", //Halfwidth CJK punctuation:HALFWIDTH IDEOGRAPHIC FULL STOP - HALFWIDTH HANGUL LETTER HIEUH
           "\uffc2"-"\uffc7", //HALFWIDTH HANGUL LETTER A - HALFWIDTH HANGUL LETTER E
           "\uffca"-"\uffcf", //HALFWIDTH HANGUL LETTER YEO - HALFWIDTH HANGUL LETTER OE
           "\uffd2"-"\uffd7", //HALFWIDTH HANGUL LETTER YO - HALFWIDTH HANGUL LETTER YU
           "\uffda"-"\uffdc"  //HALFWIDTH HANGUL LETTER EU - HALFWIDTH HANGUL LETTER I
      ]
  >
}

Object parse():
{
Object o = null;
}
{
    ( o=_object() | o=_array() )
    {
        return o;
    }
}

protected Map _object():
{
Map m = new LinkedHashMap();
}
{
     ( members(m) )? 
    {
        return m;
    }
}

protected void members(Map m):
{
}
{
    pair(m) [  members(m) ]
}

protected void pair(Map m):
{
Token t = null;
Object o;
String fieldName = null;
}
{
    fieldName=fieldName()  o=value()
    {
        m.put(fieldName, o);
    }
}

protected String fieldName():
{
String fieldName = null;
}
{
    (
      
        {
          fieldName = stripOffQuotes(token.image);
        }
      |
      
        {
          fieldName = stripOffQuotes(token.image);
        }
      |
      //some JSON systems now accept 'naked' JSON Objects
      
        {
          fieldName = token.image;
        }
    )
    {
      return fieldName;
    }
}

protected List _array():
{
List a=new ArrayList();
}
{
     ( elements(a) )? 
    {
        Collections.reverse(a);
        return a;
    }
}

protected void elements(List a):
{
Object o = null;
}
{
    o=value() [  elements(a) ]
    {
        a.add(o);
    }
}

protected Object value():
{
Token t = null;
Object o = null;
}
{
    (   o=_object()
    |   o=_array()
    |   t= {o = t.image;} //'naked' values, too
    |   t= {o = stripOffQuotes(t.image);}
    |   t= {o = stripOffQuotes(t.image);}
    |   t=
        {
            try {
              o = Integer.valueOf(t.image);
            }
            catch (NumberFormatException nfe1) {
                try {
                     o = new BigInteger(t.image);
                }
                catch  (NumberFormatException nfe2) {
                    try {
                         o = new BigDecimal(t.image);
                    }
                    catch  (NumberFormatException nfe3) {
                         o = Double.NaN;
                    }
                }
            }
        }
    |    {o = Boolean.TRUE;}
    |    {o = Boolean.FALSE;}
    |    )
    {
        return o;
    }
}




© 2015 - 2024 Weber Informatics LLC | Privacy Policy