com.sindicetech.siren.analysis.ConciseJsonScanner Maven / Gradle / Ivy
/* 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
* A concise tree model creates one token per attribute-object and attribute-value pair. A token represents the content
* of a node. The attribute-object token has an empty content. To be able to distinguish between multiple objects, it
* duplicates the attribute-object token for each attribute-object pair and increments its node identifiers.
* Nested arrays are not flattened and will be mapped to an empty node.
*/
public final class ConciseJsonScanner {
/** 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 = 12;
public static final int sOBJECT = 2;
public static final int sARRAY = 10;
public static final int YYINITIAL = 0;
public static final int sSTRING = 8;
public static final int sFIELD = 4;
public static final int sVALUE = 6;
public static final int sDATATYPE_LABEL = 16;
public static final int sDATATYPE_FIELD = 14;
public static final int sDATATYPE_VALUE = 18;
/**
* 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\31"+
"\10\0\1\15\1\33\1\11\1\13\1\0\12\12\1\34\6\0\4\36"+
"\1\14\1\36\24\0\1\37\1\35\1\40\1\0\1\23\1\0\1\6"+
"\2\36\1\24\1\4\1\5\5\0\1\7\1\0\1\17\1\0\1\26"+
"\1\0\1\2\1\10\1\1\1\3\1\27\2\0\1\25\1\0\1\30"+
"\1\16\1\32\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\6\1\7"+
"\1\10\1\11\2\12\3\0\1\13\1\0\1\14\1\15"+
"\1\16\1\17\1\20\1\21\1\22\1\23\1\24\1\25"+
"\1\26\1\27\1\30\1\31\1\26\1\32\1\33\1\34"+
"\1\35\1\36\2\0\1\37\2\11\1\40\7\0\2\20"+
"\1\41\1\0\2\32\1\42\6\0\1\13\1\43\11\0"+
"\1\44\2\0\1\45\11\0\1\46\1\0\1\43\10\0"+
"\1\47\2\0\1\50\2\0\1\51\7\0\1\52\10\0"+
"\1\53\3\0\1\54\2\0\1\55";
private static int [] zzUnpackAction() {
int [] result = new int[139];
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\u014a\0\u016b\0\u014a\0\u014a\0\u014a\0\u014a"+
"\0\u018c\0\u014a\0\u014a\0\u01ad\0\u01ce\0\u01ef\0\u0210\0\u0231"+
"\0\u0252\0\u0273\0\u0294\0\u02b5\0\u014a\0\u014a\0\u014a\0\u02d6"+
"\0\u014a\0\u02f7\0\u014a\0\u014a\0\u014a\0\u014a\0\u014a\0\u014a"+
"\0\u014a\0\u0318\0\u0339\0\u014a\0\u035a\0\u014a\0\u02f7\0\u037b"+
"\0\u01ce\0\u014a\0\u014a\0\u039c\0\u014a\0\u03bd\0\u03de\0\u03ff"+
"\0\u0420\0\u0441\0\u02b5\0\u0462\0\u014a\0\u0483\0\u014a\0\u04a4"+
"\0\u014a\0\u04c5\0\u014a\0\u04e6\0\u0507\0\u0528\0\u0549\0\u056a"+
"\0\u058b\0\u058b\0\u05ac\0\u05cd\0\u05ee\0\u060f\0\u0630\0\u0651"+
"\0\u0672\0\u0693\0\u06b4\0\u06d5\0\u014a\0\u06f6\0\u0717\0\u014a"+
"\0\u0738\0\u0759\0\u077a\0\u079b\0\u07bc\0\u07dd\0\u07fe\0\u081f"+
"\0\u0840\0\u014a\0\u0861\0\u0861\0\u0882\0\u08a3\0\u08c4\0\u08e5"+
"\0\u0906\0\u0927\0\u0948\0\u0969\0\u014a\0\u098a\0\u09ab\0\u014a"+
"\0\u09cc\0\u09ed\0\u014a\0\u0a0e\0\u0a2f\0\u0a50\0\u0a71\0\u0a92"+
"\0\u0ab3\0\u0ad4\0\u014a\0\u0af5\0\u0b16\0\u0b37\0\u0b58\0\u0b79"+
"\0\u0b9a\0\u0bbb\0\u0bdc\0\u014a\0\u0bfd\0\u0c1e\0\u0c3f\0\u014a"+
"\0\u0c60\0\u0c81\0\u014a";
private static int [] zzUnpackRowMap() {
int [] result = new int[139];
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\5\13\1\16\10\13\20\17\1\14"+
"\2\15\5\17\1\20\1\21\1\22\1\23\5\17\31\24"+
"\1\25\3\24\1\26\3\24\1\0\1\27\3\0\1\30"+
"\3\0\1\31\1\32\4\0\1\33\1\14\2\15\5\0"+
"\1\34\1\35\5\0\1\36\1\37\31\40\1\41\3\40"+
"\1\42\3\40\20\43\1\14\2\15\10\43\1\44\3\43"+
"\1\45\1\37\20\46\1\14\2\15\5\46\1\47\1\46"+
"\1\50\1\51\25\46\1\14\2\15\6\46\1\52\7\46"+
"\31\53\1\54\3\53\1\55\3\53\31\40\1\56\3\40"+
"\1\57\3\40\62\0\1\15\42\0\1\60\15\0\31\24"+
"\1\0\3\24\1\0\3\24\20\0\3\61\11\0\1\62"+
"\4\0\3\63\1\64\15\63\1\0\7\63\1\65\7\63"+
"\2\0\1\66\44\0\1\67\44\0\1\32\32\0\1\70"+
"\5\0\1\32\1\71\1\70\1\0\1\70\25\0\1\72"+
"\55\0\3\73\6\0\1\74\7\0\31\40\1\0\3\40"+
"\1\0\3\40\3\75\1\76\15\75\1\0\7\75\1\77"+
"\7\75\23\0\1\100\15\0\31\53\1\0\3\53\1\0"+
"\3\53\3\101\1\102\15\101\1\0\7\101\1\103\7\101"+
"\24\0\1\104\2\0\1\105\15\0\3\106\3\0\1\106"+
"\1\0\1\106\7\0\1\106\11\0\1\106\5\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\54\0\1\115\21\0\3\116\3\0"+
"\1\116\1\0\1\116\7\0\1\116\11\0\1\116\26\0"+
"\1\117\2\0\1\120\15\0\3\121\3\0\1\121\1\0"+
"\1\121\7\0\1\121\11\0\1\121\10\0\1\122\40\0"+
"\1\123\36\0\3\124\3\0\1\124\1\0\1\124\7\0"+
"\1\124\11\0\1\124\6\0\1\125\44\0\1\126\42\0"+
"\1\112\32\0\1\127\5\0\1\113\1\0\1\127\1\0"+
"\1\127\31\0\1\130\55\0\1\131\2\0\1\132\15\0"+
"\3\133\3\0\1\133\1\0\1\133\7\0\1\133\11\0"+
"\1\133\10\0\1\134\40\0\1\135\36\0\3\136\3\0"+
"\1\136\1\0\1\136\7\0\1\136\11\0\1\136\3\0"+
"\1\137\46\0\1\140\35\0\3\141\3\0\1\141\1\0"+
"\1\141\7\0\1\141\11\0\1\141\6\0\1\142\45\0"+
"\1\143\1\144\2\0\2\143\30\0\1\145\40\0\1\146"+
"\36\0\3\147\3\0\1\147\1\0\1\147\7\0\1\147"+
"\11\0\1\147\3\0\1\150\46\0\1\151\35\0\3\152"+
"\3\0\1\152\1\0\1\152\7\0\1\152\11\0\1\152"+
"\10\0\1\153\35\0\1\154\41\0\3\155\3\0\1\155"+
"\1\0\1\155\7\0\1\155\11\0\1\155\14\0\1\144"+
"\27\0\1\156\46\0\1\157\35\0\3\160\3\0\1\160"+
"\1\0\1\160\7\0\1\160\11\0\1\160\10\0\1\161"+
"\35\0\1\162\41\0\3\163\3\0\1\163\1\0\1\163"+
"\7\0\1\163\11\0\1\163\3\0\1\164\43\0\1\165"+
"\42\0\1\166\35\0\1\167\36\0\1\170\43\0\1\171"+
"\61\0\1\172\36\0\1\173\16\0\1\174\43\0\1\175"+
"\61\0\1\176\36\0\1\177\43\0\1\154\37\0\1\200"+
"\36\0\1\201\43\0\1\202\43\0\1\203\35\0\1\167"+
"\43\0\1\204\13\0\1\205\54\0\3\203\11\0\1\206"+
"\27\0\1\207\35\0\3\206\6\0\1\210\40\0\1\211"+
"\27\0\3\211\11\0\1\212\24\0\3\212\6\0\1\213"+
"\7\0";
private static int [] zzUnpackTrans() {
int [] result = new int[3234];
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 =
"\12\0\1\11\1\1\4\11\1\1\2\11\3\1\3\0"+
"\1\1\1\0\1\1\3\11\1\1\1\11\1\1\7\11"+
"\2\1\1\11\1\1\1\11\1\1\2\0\2\11\1\1"+
"\1\11\7\0\1\11\1\1\1\11\1\0\1\11\1\1"+
"\1\11\6\0\2\1\11\0\1\11\2\0\1\11\11\0"+
"\1\11\1\0\1\1\10\0\1\11\2\0\1\11\2\0"+
"\1\11\7\0\1\11\10\0\1\11\3\0\1\11\2\0"+
"\1\11";
private static int [] zzUnpackAttribute() {
int [] result = new int[139];
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
*/
private final StringBuilder buffer = new StringBuilder();
// OBJECT
/**
* Flag to indicate if the current object is empty, i.e., if it does not contain at least one field
*/
private boolean isObjectEmpty = true;
// NODE IDENTIFIERS
/**
* The size of the path buffer
*/
private final static int BUFFER_SIZE = 1024;
/**
* The path to a node
*/
private final IntsRef nodePath = new IntsRef(BUFFER_SIZE);
/**
* Stack of lexical states.
*
* It is used to (1) verify that objects and arrays are correctly closed, and (2) to be able to resume the previous
* state during the traversal of the tree.
*/
private final Deque states = new ArrayDeque();
// DATATYPES
/**
* Datatype representing xsd:string
*/
private static final char[] XSD_STRING = XSDDatatype.XSD_STRING.toCharArray();
/**
* Datatype representing json:field
*/
private static final char[] JSON_FIELD = JSONDatatype.JSON_FIELD.toCharArray();
/**
* Datatype representing xsd:double
*/
private static final char[] XSD_DOUBLE = XSDDatatype.XSD_DOUBLE.toCharArray();
/**
* Datatype representing xsd:long
*/
private static final char[] XSD_LONG = XSDDatatype.XSD_LONG.toCharArray();
/**
* Datatype representing xsd:boolean
*/
private static final char[] XSD_BOOLEAN = XSDDatatype.XSD_BOOLEAN.toCharArray();
/**
* Buffer used to build the datatype label
*/
private final StringBuilder dtLabel = new StringBuilder();
/**
* A reference to the current datatype URI
*/
private char[] datatype;
/**
* Flags to indicate if the datatype object has a datatype label and value.
*/
private boolean hasLabel, hasValue;
// FIELDS
/**
* Buffer used to build the field label
*/
private final StringBuilder fieldLabel = new StringBuilder();
/**
* Queue of field labels
*/
private final Deque paths = new ArrayDeque();
// ARRAY
private boolean mustFlattenNestedArray = false;
/**
* If set to true, the nested arrays will be flattened.
*/
public void setMustFlattenNestedArray(boolean mustFlattenNestedArray) {
this.mustFlattenNestedArray = mustFlattenNestedArray;
}
/**
* Return a copy of the current path.
*/
public final String[] getPath() {
return paths.toArray(new String[paths.size()]);
}
/**
* 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 = 0;
datatype = null;
}
/**
* 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;
}
/**
* Called when entering into a new object. Adds a {@link #sOBJECT} state to the stack. Set the flag for empty object
* to true.
*/
private void newObject() {
states.push(sOBJECT);
this.incrNodeObjectPath();
this.isObjectEmpty = true;
}
/**
* Add an object to the current node path
*/
private void incrNodeObjectPath() {
ArrayUtils.growAndCopy(nodePath, nodePath.length + 1);
nodePath.length++;
// Initialise node
setLastNode(-1);
}
/**
* Update the path of the current values of the current object node
*/
private void setLastNode(int val) {
nodePath.ints[nodePath.length - 1] = val;
}
/**
* Called when leaving an object:
*
* - decrement the tree level of 1; and
*
- remove {@link #sOBJECT} from the stack of states.
*
*/
private void closeObject() {
final int state = states.pop();
if (state != sOBJECT) {
throw new IllegalStateException(errorMessage("Object is not properly closed"));
}
decrNodeObjectPath();
}
/**
* Decrement the tree level of 1.
*/
private void decrNodeObjectPath() {
nodePath.length--;
}
/**
* Called for each new number value. Return the {@link #NUMBER} token type.
*/
private int newNumber(char[] datatype) {
this.datatype = datatype;
buffer.setLength(0);
buffer.append(yytext());
return NUMBER;
}
/**
* Called for each new boolean value. Return the {@link #NUMBER} token type.
*/
private int newBoolean(boolean b) {
this.datatype = XSD_BOOLEAN;
return b ? TRUE : FALSE;
}
/**
* Update the path of the current values of the current object node
*/
private void addToLastNode(int val) {
nodePath.ints[nodePath.length - 1] += val;
}
/**
* 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 ConciseJsonScanner(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 ConciseJsonScanner(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 40:
{ buffer.append(Character.toChars(Integer.parseInt(new String(zzBufferL, zzStartRead+2, zzMarkedPos - zzStartRead - 2 ), 16)));
}
case 46: break;
case 7:
{ if (!isObjectEmpty) {
paths.removeLast();
}
this.closeObject();
// while stack of states is non empty, unroll states
if (!states.isEmpty()) {
yybegin(states.peek());
}
}
case 47: break;
case 8:
{ if (!isObjectEmpty) {
paths.removeLast();
}
}
case 48: break;
case 11:
{ addToLastNode(1);
yybegin(states.peek());
return newNumber(XSD_LONG);
}
case 49: break;
case 4:
{ throw new IllegalStateException(errorMessage("Found invalid character while scanning an object: [" + yytext() + "]"));
}
case 50: break;
case 26:
{ dtLabel.append(yytext());
}
case 51: break;
case 27:
{ datatype = new char[dtLabel.length()];
dtLabel.getChars(0, dtLabel.length(), datatype, 0);
yybegin(sDATATYPE);
}
case 52: break;
case 3:
{ reset();
yypushback(1);
yybegin(sOBJECT);
}
case 53: break;
case 44:
{ hasValue = true;
buffer.setLength(0);
yybegin(sDATATYPE_VALUE);
}
case 54: break;
case 36:
{ addToLastNode(1);
yybegin(states.peek());
return newBoolean(true);
}
case 55: break;
case 24:
{ if (!hasLabel) {
throw new IllegalStateException(errorMessage("Invalid datatype object: no _datatype_ attribute."));
}
if (!hasValue) {
throw new IllegalStateException(errorMessage("Invalid datatype object: no _value_ attribute."));
}
int state = states.pop();
if (state != sDATATYPE) {
throw new IllegalStateException(errorMessage("Datatype object is not properly closed"));
}
yybegin(states.peek());
return LITERAL;
}
case 56: break;
case 2:
{ /* ignore white space. */
}
case 57: break;
case 21:
{ // if the previous state is an array, this is a nested array,
// we need to increase the node identifier
if (!mustFlattenNestedArray && states.peek() == sARRAY) {
addToLastNode(1);
this.incrNodeObjectPath();
}
states.push(sARRAY);
yybegin(sVALUE);
}
case 58: break;
case 13:
{ datatype = XSD_STRING;
addToLastNode(1);
buffer.setLength(0);
yybegin(sSTRING);
}
case 59: break;
case 19:
{ throw new IllegalStateException(errorMessage("Found invalid character while scanning an array: [" + yytext() + "]"));
}
case 60: break;
case 12:
{ addToLastNode(1);
yypushback(1);
yybegin(sOBJECT);
// return an empty token for the field
datatype = XSD_STRING;
buffer.setLength(0);
return LITERAL;
}
case 61: break;
case 30:
{ throw new IllegalStateException(errorMessage("Found invalid character while scanning a datatype string: [" + yytext() + "]"));
}
case 62: break;
case 25:
{ yybegin(sDATATYPE_FIELD);
}
case 63: break;
case 43:
// lookahead expression with fixed base length
zzMarkedPos = zzStartRead + 1;
{ addToLastNode(1);
yypushback(1);
yybegin(sDATATYPE);
}
case 64: break;
case 33:
{ buffer.append('\"');
}
case 65: break;
case 5:
{ this.newObject();
}
case 66: break;
case 10:
{ throw new IllegalStateException(errorMessage("Found invalid character while scanning a field: [" + yytext() + "]"));
}
case 67: break;
case 22:
{ throw new IllegalStateException(errorMessage("Found invalid character while scanning a datatype: [" + yytext() + "]"));
}
case 68: break;
case 31:
{ paths.addLast(fieldLabel.toString());
yybegin(sVALUE);
}
case 69: break;
case 39:
{ fieldLabel.append(Character.toChars(Integer.parseInt(new String(zzBufferL, zzStartRead+2, zzMarkedPos - zzStartRead - 2 ), 16)));
}
case 70: break;
case 23:
{ hasLabel = hasValue = false;
states.push(sDATATYPE);
yybegin(sDATATYPE_FIELD);
}
case 71: break;
case 9:
{ fieldLabel.append(yytext());
}
case 72: break;
case 16:
{ buffer.append(yytext());
}
case 73: break;
case 17:
{ yybegin(states.peek());
return LITERAL;
}
case 74: break;
case 18:
{ throw new IllegalStateException(errorMessage("Found invalid character while scanning a string: [" + yytext() + "]"));
}
case 75: break;
case 20:
{ yybegin(sVALUE);
}
case 76: break;
case 1:
{ throw new IllegalStateException(errorMessage("Found invalid character while scanning start of the json input: [" + yytext() + "]"));
}
case 77: break;
case 14:
{ yypushback(1);
yybegin(sARRAY);
}
case 78: break;
case 35:
{ addToLastNode(1);
yybegin(states.peek());
return newNumber(XSD_DOUBLE);
}
case 79: break;
case 42:
{ // Throws exception if object uses restricted field names
throw new IllegalStateException(errorMessage("Restricted field name found while scanning an object: [" + yytext() + "]"));
}
case 80: break;
case 37:
{ datatype = XSD_STRING;
addToLastNode(1);
yybegin(states.peek());
return NULL;
}
case 81: break;
case 34:
{ dtLabel.append('\"');
}
case 82: break;
case 6:
{ this.isObjectEmpty = false;
fieldLabel.setLength(0);
yybegin(sFIELD);
}
case 83: break;
case 45:
{ hasLabel = true;
dtLabel.setLength(0);
yybegin(sDATATYPE_LABEL);
}
case 84: break;
case 28:
{ throw new IllegalStateException(errorMessage("Found invalid character while scanning a datatype label: [" + yytext() + "]"));
}
case 85: break;
case 38:
{ addToLastNode(1);
yybegin(states.peek());
return newBoolean(false);
}
case 86: break;
case 32:
{ fieldLabel.append('\"');
}
case 87: break;
case 29:
{ yybegin(sDATATYPE);
}
case 88: break;
case 15:
{ int state = states.pop();
if (state != sARRAY) {
throw new IllegalStateException(errorMessage("Array is not properly closed"));
}
state = states.peek();
if (!mustFlattenNestedArray && state == sARRAY) { // we were in a nested array, decrease the node identifier
this.decrNodeObjectPath();
}
yybegin(state);
}
case 89: break;
case 41:
{ dtLabel.append(Character.toChars(Integer.parseInt(new String(zzBufferL, zzStartRead+2, zzMarkedPos - zzStartRead - 2 ), 16)));
}
case 90: break;
default:
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
zzAtEOF = true;
{
if (!states.isEmpty()) {
throw new IllegalStateException(errorMessage("Arrays/objects/strings are not properly closed"));
}
return YYEOF;
}
}
else {
zzScanError(ZZ_NO_MATCH);
}
}
}
}
}