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

com.sindicetech.siren.analysis.ExtendedJsonScanner Maven / Gradle / Ivy

The newest version!
/* The following code was generated by JFlex 1.4.3 on 11/17/14 12:41 PM */

/**
 * Copyright (c) 2014, Sindice Limited. All Rights Reserved.
 *
 * This file is part of the SIREn project.
 *
 * SIREn is a free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as
 * published by the Free Software Foundation, either version 3 of
 * the License, or (at your option) any later version.
 *
 * SIREn is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 * GNU Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public
 * License along with this program. If not, see .
 */

package com.sindicetech.siren.analysis;

import static com.sindicetech.siren.analysis.ExtendedJsonTokenizer.*;

import java.util.Stack;
import java.util.Arrays;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.util.IntsRef;
import com.sindicetech.siren.util.ArrayUtils;
import com.sindicetech.siren.util.XSDDatatype;
import com.sindicetech.siren.util.JSONDatatype;

/**
 * A scanner for JSON document that maps a JSON tree to a node-based tree model using a depth-first traversal approach.
 * 

* This scanner creates one token per attribute, value and object. Nested arrays are not flattened and will be mapped * to an empty node. */ public final class ExtendedJsonScanner { /** This character denotes the end of file */ public static final int YYEOF = -1; /** initial size of the lookahead buffer */ private static final int ZZ_BUFFERSIZE = 16384; /** lexical states */ public static final int sDATATYPE_STRING_VALUE = 14; public static final int sARRAY_COMMA = 12; public static final int sARRAY_OBJECT = 18; public static final int sOBJECT = 4; public static final int sARRAY = 10; public static final int sFIELD_STRING = 8; public static final int YYINITIAL = 0; public static final int sSTRING = 2; public static final int sFIELD = 6; public static final int sDATATYPE_LABEL = 16; /** * ZZ_LEXSTATE[l] is the state in the DFA for the lexical state l * ZZ_LEXSTATE[l+1] is the state in the DFA for the lexical state l * at the beginning of a line * l is of the form l = 2*k, k a non negative integer */ private static final int ZZ_LEXSTATE[] = { 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9 }; /** * Translates characters to character classes */ private static final String ZZ_CMAP_PACKED = "\11\0\1\22\1\21\1\0\1\22\1\20\22\0\1\22\1\0\1\26"+ "\10\0\1\15\1\27\1\11\1\13\1\0\12\12\1\34\6\0\4\40"+ "\1\14\1\40\24\0\1\25\1\37\1\36\1\0\1\30\1\0\1\6"+ "\2\40\1\31\1\4\1\5\5\0\1\7\1\0\1\17\1\0\1\33"+ "\1\0\1\2\1\10\1\1\1\3\1\35\2\0\1\32\1\0\1\23"+ "\1\16\1\24\uff82\0"; /** * Translates characters to character classes */ private static final char [] ZZ_CMAP = zzUnpackCMap(ZZ_CMAP_PACKED); /** * Translates DFA states to action switch labels. */ private static final int [] ZZ_ACTION = zzUnpackAction(); private static final String ZZ_ACTION_PACKED_0 = "\12\0\1\1\2\2\1\3\1\4\1\5\1\0\4\6"+ "\1\7\1\6\1\10\1\11\1\12\1\13\1\14\1\15"+ "\1\16\1\0\4\17\1\20\1\17\1\21\1\22\1\23"+ "\1\24\1\25\1\26\2\2\1\27\1\30\2\2\1\31"+ "\1\0\2\4\1\32\6\0\1\33\5\0\2\30\1\34"+ "\4\0\1\7\1\35\6\0\1\20\1\36\3\0\1\37"+ "\2\0\1\40\2\0\1\41\2\0\1\42\2\0\1\43"+ "\1\0\1\35\2\0\1\44\1\0\1\36\1\0\1\45"+ "\2\0\1\46\11\0\1\47\2\0\1\50"; private static int [] zzUnpackAction() { int [] result = new int[124]; int offset = 0; offset = zzUnpackAction(ZZ_ACTION_PACKED_0, offset, result); return result; } private static int zzUnpackAction(String packed, int offset, int [] result) { int i = 0; /* index in packed string */ int j = offset; /* index in unpacked array */ int l = packed.length(); while (i < l) { int count = packed.charAt(i++); int value = packed.charAt(i++); do result[j++] = value; while (--count > 0); } return j; } /** * Translates a state to a row index in the transition table */ private static final int [] ZZ_ROWMAP = zzUnpackRowMap(); private static final String ZZ_ROWMAP_PACKED_0 = "\0\0\0\41\0\102\0\143\0\204\0\245\0\306\0\347"+ "\0\u0108\0\u0129\0\u0129\0\u014a\0\u0129\0\u0129\0\u016b\0\u0129"+ "\0\u018c\0\u0129\0\u01ad\0\u01ce\0\u01ef\0\u0210\0\u0231\0\u0129"+ "\0\u0129\0\u0129\0\u0129\0\u0129\0\u0129\0\u0252\0\u0273\0\u0129"+ "\0\u0294\0\u02b5\0\u02d6\0\u02f7\0\u0318\0\u0129\0\u0129\0\u0129"+ "\0\u0129\0\u0129\0\u0129\0\u0339\0\u016b\0\u0129\0\u035a\0\u037b"+ "\0\u035a\0\u0129\0\u039c\0\u0129\0\u03bd\0\u0129\0\u03de\0\u03ff"+ "\0\u0420\0\u0441\0\u0462\0\u0483\0\u0129\0\u04a4\0\u04c5\0\u04e6"+ "\0\u0507\0\u0528\0\u0129\0\u0549\0\u0129\0\u056a\0\u058b\0\u05ac"+ "\0\u05cd\0\u05cd\0\u05ee\0\u060f\0\u0630\0\u0651\0\u0672\0\u0693"+ "\0\u06b4\0\u06b4\0\u06d5\0\u06f6\0\u0717\0\u0738\0\u0129\0\u0759"+ "\0\u077a\0\u0129\0\u079b\0\u07bc\0\u0129\0\u07dd\0\u07fe\0\u0129"+ "\0\u081f\0\u0840\0\u0129\0\u0861\0\u0861\0\u0882\0\u08a3\0\u0129"+ "\0\u08c4\0\u08c4\0\u08e5\0\u0129\0\u0906\0\u0927\0\u0129\0\u0948"+ "\0\u0969\0\u098a\0\u09ab\0\u09cc\0\u09ed\0\u0a0e\0\u0a2f\0\u0a50"+ "\0\u0129\0\u0a71\0\u0a92\0\u0129"; private static int [] zzUnpackRowMap() { int [] result = new int[124]; int offset = 0; offset = zzUnpackRowMap(ZZ_ROWMAP_PACKED_0, offset, result); return result; } private static int zzUnpackRowMap(String packed, int offset, int [] result) { int i = 0; /* index in packed string */ int j = offset; /* index in unpacked array */ int l = packed.length(); while (i < l) { int high = packed.charAt(i++) << 16; result[j++] = high | packed.charAt(i++); } return j; } /** * The transition table of the DFA */ private static final int [] ZZ_TRANS = zzUnpackTrans(); private static final String ZZ_TRANS_PACKED_0 = "\20\13\1\14\2\15\1\16\15\13\26\17\1\20\10\17"+ "\1\21\1\17\1\22\1\23\3\22\1\24\3\22\1\25"+ "\1\26\4\22\1\27\1\14\2\15\1\30\1\31\1\32"+ "\1\33\1\34\11\22\20\35\1\14\2\15\1\35\1\31"+ "\1\35\1\36\12\35\26\17\1\37\10\17\1\21\1\17"+ "\1\40\1\41\3\40\1\42\3\40\1\43\1\44\4\40"+ "\1\45\1\14\2\15\1\46\1\40\1\47\1\50\7\40"+ "\1\51\2\40\20\52\1\14\2\15\4\52\1\53\6\52"+ "\1\51\2\52\20\17\1\54\2\55\3\17\1\56\10\17"+ "\1\21\1\17\20\57\1\60\2\61\3\57\1\62\10\57"+ "\1\63\1\57\62\0\1\15\17\0\26\17\1\0\10\17"+ "\1\0\1\17\3\64\1\65\15\64\1\0\4\64\1\66"+ "\12\64\2\0\1\67\44\0\1\70\44\0\1\26\32\0"+ "\1\71\5\0\1\26\1\72\1\71\1\0\1\71\25\0"+ "\1\73\65\0\1\74\30\0\3\37\11\0\1\75\6\0"+ "\1\76\44\0\1\77\44\0\1\44\32\0\1\100\5\0"+ "\1\44\1\101\1\100\1\0\1\100\25\0\1\102\35\0"+ "\21\17\1\55\4\17\1\0\10\17\1\0\1\17\26\57"+ "\1\0\10\57\1\0\22\57\1\61\4\57\1\0\10\57"+ "\1\0\1\57\3\103\1\104\15\103\1\0\4\103\1\105"+ "\12\103\4\0\3\106\3\0\1\106\1\0\1\106\14\0"+ "\1\106\6\0\1\106\3\0\1\107\44\0\1\110\42\0"+ "\1\111\1\112\2\0\2\111\34\0\1\113\35\0\1\114"+ "\62\0\1\115\3\0\1\116\6\0\1\117\44\0\1\120"+ "\42\0\1\121\1\122\2\0\2\121\34\0\1\123\35\0"+ "\1\124\35\0\3\125\3\0\1\125\1\0\1\125\14\0"+ "\1\125\6\0\1\125\4\0\3\126\3\0\1\126\1\0"+ "\1\126\14\0\1\126\6\0\1\126\4\0\1\127\44\0"+ "\1\130\42\0\1\112\32\0\1\131\5\0\1\113\1\0"+ "\1\131\1\0\1\131\31\0\1\132\37\0\1\133\40\0"+ "\1\134\36\0\1\135\44\0\1\136\42\0\1\122\32\0"+ "\1\137\5\0\1\123\1\0\1\137\1\0\1\137\31\0"+ "\1\140\35\0\3\141\3\0\1\141\1\0\1\141\14\0"+ "\1\141\6\0\1\141\4\0\3\142\3\0\1\142\1\0"+ "\1\142\14\0\1\142\6\0\1\142\4\0\1\143\45\0"+ "\1\144\1\145\2\0\2\144\23\0\1\146\46\0\1\147"+ "\35\0\1\150\45\0\1\151\1\152\2\0\2\151\26\0"+ "\3\153\3\0\1\153\1\0\1\153\14\0\1\153\6\0"+ "\1\153\4\0\3\154\3\0\1\154\1\0\1\154\14\0"+ "\1\154\6\0\1\154\12\0\1\145\34\0\1\155\35\0"+ "\1\156\47\0\1\152\32\0\3\157\3\0\1\157\1\0"+ "\1\157\14\0\1\157\6\0\1\157\1\0\1\160\43\0"+ "\1\161\66\0\1\162\36\0\1\163\43\0\1\164\33\0"+ "\1\165\16\0\1\166\54\0\3\165\11\0\1\167\34\0"+ "\1\170\30\0\3\167\3\0\1\171\40\0\1\172\32\0"+ "\3\172\11\0\1\173\24\0\3\173\3\0\1\174\12\0"; private static int [] zzUnpackTrans() { int [] result = new int[2739]; int offset = 0; offset = zzUnpackTrans(ZZ_TRANS_PACKED_0, offset, result); return result; } private static int zzUnpackTrans(String packed, int offset, int [] result) { int i = 0; /* index in packed string */ int j = offset; /* index in unpacked array */ int l = packed.length(); while (i < l) { int count = packed.charAt(i++); int value = packed.charAt(i++); value--; do result[j++] = value; while (--count > 0); } return j; } /* error codes */ private static final int ZZ_UNKNOWN_ERROR = 0; private static final int ZZ_NO_MATCH = 1; private static final int ZZ_PUSHBACK_2BIG = 2; /* error messages for the codes above */ private static final String ZZ_ERROR_MSG[] = { "Unkown internal scanner error", "Error: could not match input", "Error: pushback value was too large" }; /** * ZZ_ATTRIBUTE[aState] contains the attributes of state aState */ private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute(); private static final String ZZ_ATTRIBUTE_PACKED_0 = "\11\0\1\10\1\11\1\1\2\11\1\1\1\11\1\0"+ "\1\11\5\1\6\11\1\1\1\0\1\11\5\1\6\11"+ "\2\1\1\11\3\1\1\11\1\0\1\11\1\1\1\11"+ "\6\0\1\11\5\0\1\11\1\1\1\11\4\0\2\1"+ "\6\0\2\1\3\0\1\11\2\0\1\11\2\0\1\11"+ "\2\0\1\11\2\0\1\11\1\0\1\1\2\0\1\11"+ "\1\0\1\1\1\0\1\11\2\0\1\11\11\0\1\11"+ "\2\0\1\11"; private static int [] zzUnpackAttribute() { int [] result = new int[124]; int offset = 0; offset = zzUnpackAttribute(ZZ_ATTRIBUTE_PACKED_0, offset, result); return result; } private static int zzUnpackAttribute(String packed, int offset, int [] result) { int i = 0; /* index in packed string */ int j = offset; /* index in unpacked array */ int l = packed.length(); while (i < l) { int count = packed.charAt(i++); int value = packed.charAt(i++); do result[j++] = value; while (--count > 0); } return j; } /** the input device */ private java.io.Reader zzReader; /** the current state of the DFA */ private int zzState; /** the current lexical state */ private int zzLexicalState = YYINITIAL; /** this buffer contains the current text to be matched and is the source of the yytext() string */ private char zzBuffer[] = new char[ZZ_BUFFERSIZE]; /** the textposition at the last accepting state */ private int zzMarkedPos; /** the current text position in the buffer */ private int zzCurrentPos; /** startRead marks the beginning of the yytext() string in the buffer */ private int zzStartRead; /** endRead marks the last character in the buffer, that has been read from input */ private int zzEndRead; /** number of newlines encountered up to the start of the matched text */ private int yyline; /** the number of characters up to the start of the matched text */ private int yychar; /** * the number of characters from the last newline up to the start of the * matched text */ private int yycolumn; /** * zzAtBOL == true <=> the scanner is currently at the beginning of a line */ private boolean zzAtBOL = true; /** zzAtEOF == true <=> the scanner is at the EOF */ private boolean zzAtEOF; /** denotes if the user-EOF-code has already been executed */ private boolean zzEOFDone; /* user code: */ /** * Buffer containing literal or number value */ protected final StringBuilder buffer = new StringBuilder(); // NODE IDENTIFIERS /** * The size of the path buffer */ protected final static int BUFFER_SIZE = 1024; /** * The path to a node */ protected final IntsRef nodePath = new IntsRef(BUFFER_SIZE); /** * Stack of lexical states */ protected final Stack states = new Stack(); /** * Indicates if a leaf node, i.e., a literal, a number, null, or a boolean, * was encountered, in which case it needs to be closed, either in the COMMA * state, or in the closing curly bracket. */ protected boolean openLeafNode = false; /** * Indicates how many nested objects there are. * A nested object implies a blank node. */ protected int nestedObjects = 0; // DATATYPES /** * Datatype representing xsd:string */ protected static final char[] XSD_STRING = XSDDatatype.XSD_STRING.toCharArray(); /** * Datatype representing json:field */ protected static final char[] JSON_FIELD = JSONDatatype.JSON_FIELD.toCharArray(); /** * Datatype representing xsd:double */ protected static final char[] XSD_DOUBLE = XSDDatatype.XSD_DOUBLE.toCharArray(); /** * Datatype representing xsd:long */ protected static final char[] XSD_LONG = XSDDatatype.XSD_LONG.toCharArray(); /** * Datatype representing xsd:boolean */ protected static final char[] XSD_BOOLEAN = XSDDatatype.XSD_BOOLEAN.toCharArray(); /** * Buffer containing the datatype label */ protected final StringBuilder dtLabel = new StringBuilder(); /** * A reference to the current datatype URI */ protected char[] datatype; // lexical states for datatypes protected final static int DATATYPE_OBJ_OFF = 0; protected final static int DATATYPE_OBJ_ON = 1; protected final static int DATATYPE_OBJ_JUNK = 2; protected final static int DATATYPE_OBJ_ERROR = 3; protected final static int DATATYPE_OBJ_LABEL = 4; protected final static int DATATYPE_OBJ_VALUE = 8; protected final static int DATATYPE_OBJ_OK = 13; /** * The current lexical state for a datatype object */ protected int datatypeObject = DATATYPE_OBJ_OFF; /** * Return the datatype URI. */ public final char[] getDatatypeURI() { return datatype; } public final int yychar() { return yychar; } /** * Fills Lucene TermAttribute with the current string buffer. */ public final void getLiteralText(CharTermAttribute t) { char[] chars = new char[buffer.length()]; buffer.getChars(0, buffer.length(), chars, 0); t.copyBuffer(chars, 0, chars.length); } /** * Returns the node path of the token */ public final IntsRef getNodePath() { return nodePath; } /** * Initialise inner variables */ private void reset() { states.clear(); Arrays.fill(nodePath.ints, -1); nodePath.offset = 0; nodePath.length = 1; openLeafNode = false; datatype = null; nestedObjects = 0; datatypeObject = DATATYPE_OBJ_OFF; } /** * Add an object to the current node path */ private void incrNodeObjectPath() { ArrayUtils.growAndCopy(nodePath, nodePath.length + 1); nodePath.length++; // Initialise node setLastNode(-1); } private void initDatatypeObject() { // Initialise the datatype data, this is possibly a Datatype object datatype = null; datatypeObject = DATATYPE_OBJ_OFF; buffer.setLength(0); } /** * Decrement the tree level of 1. */ private void decrNodeObjectPath() { nodePath.length--; } /** Update the path of the current values of the current object node */ private void setLastNode(int val) { nodePath.ints[nodePath.length - 1] = val; } /** Update the path of the current values of the current object node */ private void addToLastNode(int val) { nodePath.ints[nodePath.length - 1] += val; } /** * Return the {@link #NUMBER} token type. */ private int processNumber() { buffer.setLength(0); buffer.append(yytext()); return NUMBER; } /** * Helper method to print an error while scanning a JSON * document with line and column information. */ private String errorMessage(String msg) { return "Error parsing JSON document at [line=" + yyline + ", column=" + yycolumn + "]: " + msg; } /** * Close the JSON object: * - decrement the tree level of 1; * - decrement the tree level of 1 one more time if the last value was a leaf; * - decrement the tree level of 1 one more time if the object was nested into another one (i.e., the blank node), * but exclude nested objects in arrays; and * - remove {@link #sOBJECT} from the stack of states. */ private void closeObject() { final int state = states.pop(); if (state != sOBJECT && state != sARRAY_OBJECT) { throw new IllegalStateException(errorMessage("Expected '}', got " + yychar())); } decrNodeObjectPath(); if (openLeafNode) { // unclosed entry to a leaf node decrNodeObjectPath(); openLeafNode = false; } // this curly bracket closes a nested object // this requires an additional call to decrNodeObjectPath() // since nested objects have implicitly a blank node. // This excludes the nested objects in array (i.e., sARRAY_OBJECT) if (state == sOBJECT && nestedObjects > 0) { nestedObjects--; decrNodeObjectPath(); } } /** * Closes the JSON object and further checks if the node path should be updated. * It returns a {@link #LITERAL}, which is the value associated to the field "_value_" * with the datatype equal to the value associated to the field "_datatype_". */ private int closeDatatypeObject() { closeObject(); // when the states stack is empty, I am the root of the JSON tree if (states.empty()) { throw new IllegalStateException(errorMessage("A datatype object at the" + " root of the JSON document is not possible.")); } if (states.peek() == sOBJECT) { incrNodeObjectPath(); setLastNode(0); } return LITERAL; } /** * Returns the current state. If the state of the top of the stack is a {@link #sARRAY_OBJECT}, * it returns a {@link #sOBJECT} instead. */ private int getCurrentState() { int state = states.peek(); return state == sARRAY_OBJECT ? sOBJECT : state; } /** * Creates a new scanner * There is also a java.io.InputStream version of this constructor. * * @param in the java.io.Reader to read input from. */ public ExtendedJsonScanner(java.io.Reader in) { this.zzReader = in; } /** * Creates a new scanner. * There is also java.io.Reader version of this constructor. * * @param in the java.io.Inputstream to read input from. */ public ExtendedJsonScanner(java.io.InputStream in) { this(new java.io.InputStreamReader(in)); } /** * Unpacks the compressed character translation table. * * @param packed the packed character translation table * @return the unpacked character translation table */ private static char [] zzUnpackCMap(String packed) { char [] map = new char[0x10000]; int i = 0; /* index in packed string */ int j = 0; /* index in unpacked array */ while (i < 106) { int count = packed.charAt(i++); char value = packed.charAt(i++); do map[j++] = value; while (--count > 0); } return map; } /** * Refills the input buffer. * * @return false, iff there was new input. * * @exception java.io.IOException if any I/O-Error occurs */ private boolean zzRefill() throws java.io.IOException { /* first: make room (if you can) */ if (zzStartRead > 0) { System.arraycopy(zzBuffer, zzStartRead, zzBuffer, 0, zzEndRead-zzStartRead); /* translate stored positions */ zzEndRead-= zzStartRead; zzCurrentPos-= zzStartRead; zzMarkedPos-= zzStartRead; zzStartRead = 0; } /* is the buffer big enough? */ if (zzCurrentPos >= zzBuffer.length) { /* if not: blow it up */ char newBuffer[] = new char[zzCurrentPos*2]; System.arraycopy(zzBuffer, 0, newBuffer, 0, zzBuffer.length); zzBuffer = newBuffer; } /* finally: fill the buffer with new input */ int numRead = zzReader.read(zzBuffer, zzEndRead, zzBuffer.length-zzEndRead); if (numRead > 0) { zzEndRead+= numRead; return false; } // unlikely but not impossible: read 0 characters, but not at end of stream if (numRead == 0) { int c = zzReader.read(); if (c == -1) { return true; } else { zzBuffer[zzEndRead++] = (char) c; return false; } } // numRead < 0 return true; } /** * Closes the input stream. */ public final void yyclose() throws java.io.IOException { zzAtEOF = true; /* indicate end of file */ zzEndRead = zzStartRead; /* invalidate buffer */ if (zzReader != null) zzReader.close(); } /** * Resets the scanner to read from a new input stream. * Does not close the old reader. * * All internal variables are reset, the old input stream * cannot be reused (internal buffer is discarded and lost). * Lexical state is set to ZZ_INITIAL. * * @param reader the new input stream */ public final void yyreset(java.io.Reader reader) { zzReader = reader; zzAtBOL = true; zzAtEOF = false; zzEOFDone = false; zzEndRead = zzStartRead = 0; zzCurrentPos = zzMarkedPos = 0; yyline = yychar = yycolumn = 0; zzLexicalState = YYINITIAL; } /** * Returns the current lexical state. */ public final int yystate() { return zzLexicalState; } /** * Enters a new lexical state * * @param newState the new lexical state */ public final void yybegin(int newState) { zzLexicalState = newState; } /** * Returns the text matched by the current regular expression. */ public final String yytext() { return new String( zzBuffer, zzStartRead, zzMarkedPos-zzStartRead ); } /** * Returns the character at position pos from the * matched text. * * It is equivalent to yytext().charAt(pos), but faster * * @param pos the position of the character to fetch. * A value from 0 to yylength()-1. * * @return the character at position pos */ public final char yycharat(int pos) { return zzBuffer[zzStartRead+pos]; } /** * Returns the length of the matched text region. */ public final int yylength() { return zzMarkedPos-zzStartRead; } /** * Reports an error that occured while scanning. * * In a wellformed scanner (no or only correct usage of * yypushback(int) and a match-all fallback rule) this method * will only be called with things that "Can't Possibly Happen". * If this method is called, something is seriously wrong * (e.g. a JFlex bug producing a faulty scanner etc.). * * Usual syntax/scanner level error handling should be done * in error fallback rules. * * @param errorCode the code of the errormessage to display */ private void zzScanError(int errorCode) { String message; try { message = ZZ_ERROR_MSG[errorCode]; } catch (ArrayIndexOutOfBoundsException e) { message = ZZ_ERROR_MSG[ZZ_UNKNOWN_ERROR]; } throw new Error(message); } /** * Pushes the specified amount of characters back into the input stream. * * They will be read again by then next call of the scanning method * * @param number the number of characters to be read again. * This number must not be greater than yylength()! */ public void yypushback(int number) { if ( number > yylength() ) zzScanError(ZZ_PUSHBACK_2BIG); zzMarkedPos -= number; } /** * Resumes scanning until the next regular expression is matched, * the end of input is encountered or an I/O-Error occurs. * * @return the next token * @exception java.io.IOException if any I/O-Error occurs */ public int getNextToken() throws java.io.IOException, java.lang.IllegalStateException { int zzInput; int zzAction; // cached fields: int zzCurrentPosL; int zzMarkedPosL; int zzEndReadL = zzEndRead; char [] zzBufferL = zzBuffer; char [] zzCMapL = ZZ_CMAP; int [] zzTransL = ZZ_TRANS; int [] zzRowMapL = ZZ_ROWMAP; int [] zzAttrL = ZZ_ATTRIBUTE; while (true) { zzMarkedPosL = zzMarkedPos; yychar+= zzMarkedPosL-zzStartRead; zzAction = -1; zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL; zzState = ZZ_LEXSTATE[zzLexicalState]; zzForAction: { while (true) { if (zzCurrentPosL < zzEndReadL) zzInput = zzBufferL[zzCurrentPosL++]; else if (zzAtEOF) { zzInput = YYEOF; break zzForAction; } else { // store back cached positions zzCurrentPos = zzCurrentPosL; zzMarkedPos = zzMarkedPosL; boolean eof = zzRefill(); // get translated positions and possibly new buffer zzCurrentPosL = zzCurrentPos; zzMarkedPosL = zzMarkedPos; zzBufferL = zzBuffer; zzEndReadL = zzEndRead; if (eof) { zzInput = YYEOF; break zzForAction; } else { zzInput = zzBufferL[zzCurrentPosL++]; } } int zzNext = zzTransL[ zzRowMapL[zzState] + zzCMapL[zzInput] ]; if (zzNext == -1) break zzForAction; zzState = zzNext; int zzAttributes = zzAttrL[zzState]; if ( (zzAttributes & 1) == 1 ) { zzAction = zzState; zzMarkedPosL = zzCurrentPosL; if ( (zzAttributes & 8) == 8 ) break zzForAction; } } } // store back cached position zzMarkedPos = zzMarkedPosL; switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) { case 37: { buffer.append(Character.toChars(Integer.parseInt(new String(zzBufferL, zzStartRead+2, zzMarkedPos - zzStartRead - 2 ), 16))); } case 41: break; case 13: { throw new IllegalStateException(errorMessage("Found bad character while scanning an object: [" + yytext() + "]")); } case 42: break; case 36: { datatype = XSD_BOOLEAN; yybegin(sARRAY_COMMA); return FALSE; } case 43: break; case 21: { throw new IllegalStateException(errorMessage("Found bad character while scanning an array: [" + yytext() + "]. Expecting either ',' or ']'.")); } case 44: break; case 6: { throw new IllegalStateException(errorMessage("Found invalid character while scanning an object: [" + yytext() + "]")); } case 45: break; case 24: { dtLabel.append(yytext()); } case 46: break; case 29: { openLeafNode = true; incrNodeObjectPath(); datatype = XSD_DOUBLE; setLastNode(0); return processNumber(); } case 47: break; case 31: { openLeafNode = true; incrNodeObjectPath(); datatype = XSD_BOOLEAN; setLastNode(0); return TRUE; } case 48: break; case 18: { incrNodeObjectPath(); states.push(sARRAY_COMMA); setLastNode(0); // initialise the first element of the array } case 49: break; case 17: { initDatatypeObject(); incrNodeObjectPath(); states.push(sARRAY_OBJECT); yybegin(sFIELD); } case 50: break; case 30: { datatype = XSD_DOUBLE; yybegin(sARRAY_COMMA); return processNumber(); } case 51: break; case 2: { /* ignore white space. */ } case 52: break; case 39: { datatypeObject |= DATATYPE_OBJ_ON; if ((datatypeObject & DATATYPE_OBJ_VALUE) == DATATYPE_OBJ_VALUE) { throw new IllegalStateException(errorMessage("Wrong Datatype schema. The field _value_ appears several times.")); } datatypeObject |= DATATYPE_OBJ_VALUE; if ((datatypeObject & DATATYPE_OBJ_ERROR) == DATATYPE_OBJ_ERROR) { throw new IllegalStateException(errorMessage("Wrong Datatype schema. Got unexpected elements in the datatype object.")); } buffer.setLength(0); yybegin(sDATATYPE_STRING_VALUE); } case 53: break; case 3: { reset(); states.push(sOBJECT); yybegin(sFIELD); } case 54: break; case 19: { datatype = XSD_STRING; buffer.setLength(0); yybegin(sSTRING); } case 55: break; case 26: { buffer.append('\"'); } case 56: break; case 10: { incrNodeObjectPath(); yybegin(sARRAY); states.push(sARRAY_COMMA); setLastNode(0); // initialise the first element of the array } case 57: break; case 34: { datatype = XSD_STRING; yybegin(sARRAY_COMMA); return NULL; } case 58: break; case 14: { datatypeObject |= DATATYPE_OBJ_JUNK; if ((datatypeObject & DATATYPE_OBJ_ERROR) == DATATYPE_OBJ_ERROR) { throw new IllegalStateException(errorMessage("Wrong Datatype schema. Got unexpected text: " + yytext())); } datatype = JSON_FIELD; addToLastNode(1); buffer.setLength(0); yybegin(sFIELD_STRING); } case 59: break; case 7: { openLeafNode = true; incrNodeObjectPath(); datatype = XSD_LONG; setLastNode(0); return processNumber(); } case 60: break; case 16: { datatype = XSD_LONG; yybegin(sARRAY_COMMA); return processNumber(); } case 61: break; case 8: { initDatatypeObject(); // Two incrementations, because the object introduce a "blank" node nestedObjects++; incrNodeObjectPath(); setLastNode(0); incrNodeObjectPath(); states.push(sOBJECT); yybegin(sFIELD); } case 62: break; case 40: { datatypeObject |= DATATYPE_OBJ_ON; if ((datatypeObject & DATATYPE_OBJ_LABEL) == DATATYPE_OBJ_LABEL) { throw new IllegalStateException(errorMessage("Wrong Datatype schema. The field _datatype_ appears several times.")); } datatypeObject |= DATATYPE_OBJ_LABEL; if ((datatypeObject & DATATYPE_OBJ_ERROR) == DATATYPE_OBJ_ERROR) { throw new IllegalStateException(errorMessage("Wrong Datatype schema. Got unexpected elements in the datatype object.")); } dtLabel.setLength(0); yybegin(sDATATYPE_LABEL); } case 63: break; case 4: { buffer.append(yytext()); } case 64: break; case 9: { // A datatype object is already closed before, // in the state sDATATYPE_LABEL or sDATATYPE_STRING_VALUE if ((datatypeObject & DATATYPE_OBJ_ON) == DATATYPE_OBJ_ON && datatypeObject != DATATYPE_OBJ_OK) { if ((datatypeObject & DATATYPE_OBJ_LABEL) == DATATYPE_OBJ_LABEL) { throw new IllegalStateException(errorMessage("Uncomplete datatype object, missing _value_ field.")); } else { throw new IllegalStateException(errorMessage("Uncomplete datatype object, missing _datatype_ field.")); } } else if ((datatypeObject & DATATYPE_OBJ_ON) == DATATYPE_OBJ_OFF) { closeObject(); } else if (datatypeObject == DATATYPE_OBJ_OK && states.peek() == sOBJECT) { // Decrement the node created in the state // sDATATYPE_LABEL or sDATATYPE_STRING_VALUE. // This only happens when in state sOBJECT, since it explicitly // adds a blank node (i.e., nestedObjects variable). // In the state sARRAY, the blank node is implicit. decrNodeObjectPath(); } // when the states stack is empty, I am the root of the JSON tree yybegin(states.empty() ? YYINITIAL : this.getCurrentState()); // Switch off the datatype object datatypeObject = DATATYPE_OBJ_OFF; } case 65: break; case 1: { throw new IllegalStateException(errorMessage("Found bad character: [" + yytext() + "]")); } case 66: break; case 12: { if (openLeafNode) { openLeafNode = false; decrNodeObjectPath(); } yybegin(sFIELD); } case 67: break; case 22: { addToLastNode(1); yybegin(sARRAY); } case 68: break; case 32: { openLeafNode = true; incrNodeObjectPath(); datatype = XSD_STRING; setLastNode(0); return NULL; } case 69: break; case 28: { dtLabel.append('\"'); } case 70: break; case 27: { yybegin(sOBJECT); return LITERAL; } case 71: break; case 5: { yybegin(this.getCurrentState()); return LITERAL; } case 72: break; case 25: { yybegin(sOBJECT); datatype = new char[dtLabel.length()]; dtLabel.getChars(0, dtLabel.length(), datatype, 0); // the datatype value is here already if (datatypeObject == DATATYPE_OBJ_OK) { return closeDatatypeObject(); } } case 73: break; case 23: { yybegin(sOBJECT); // the datatype label is here already if (datatypeObject == DATATYPE_OBJ_OK) { return closeDatatypeObject(); } } case 74: break; case 35: { openLeafNode = true; incrNodeObjectPath(); datatype = XSD_BOOLEAN; setLastNode(0); return FALSE; } case 75: break; case 20: { decrNodeObjectPath(); int state = states.pop(); if (state != sARRAY_COMMA) { throw new IllegalStateException(errorMessage("Expected ']', got " + yychar())); } yybegin(this.getCurrentState()); } case 76: break; case 15: { throw new IllegalStateException(errorMessage("Found bad character while scanning an array: [" + yytext() + "]")); } case 77: break; case 11: { openLeafNode = true; incrNodeObjectPath(); datatype = XSD_STRING; setLastNode(0); buffer.setLength(0); yybegin(sSTRING); } case 78: break; case 33: { datatype = XSD_BOOLEAN; yybegin(sARRAY_COMMA); return TRUE; } case 79: break; case 38: { dtLabel.append(Character.toChars(Integer.parseInt(new String(zzBufferL, zzStartRead+2, zzMarkedPos - zzStartRead - 2 ), 16))); } case 80: break; default: if (zzInput == YYEOF && zzStartRead == zzCurrentPos) { zzAtEOF = true; { if (!states.empty()) { throw new IllegalStateException(errorMessage("Check that all arrays/objects/strings are closed")); } return YYEOF; } } else { zzScanError(ZZ_NO_MATCH); } } } } }





© 2015 - 2025 Weber Informatics LLC | Privacy Policy