com.sindicetech.siren.analysis.TupleTokenizerImpl 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 aState
*/
private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute();
private static final String ZZ_ATTRIBUTE_PACKED_0 =
"\2\0\1\11\3\1\2\11\3\1\4\0\1\11\2\1"+
"\1\11\1\0\1\1\7\0\1\11\1\0\1\11\1\1";
private static int [] zzUnpackAttribute() {
int [] result = new int[32];
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: */
public static final String[] TOKEN_TYPES = getTokenTypes();
StringBuffer buffer = new StringBuffer();
StringBuffer metadataBuffer = new StringBuffer();
/** Datatype representing xsd:anyURI */
private static final char[] XSD_ANY_URI = XSDDatatype.XSD_ANY_URI.toCharArray();
/** Datatype representing xsd:string */
private static final char[] XSD_STRING = XSDDatatype.XSD_STRING.toCharArray();
public final int yychar() {
return yychar;
}
/**
* Fills Lucene TermAttribute with the current token text.
*/
public final void getText(CharTermAttribute t) {
t.copyBuffer(zzBuffer, zzStartRead, zzMarkedPos - zzStartRead);
}
/**
* Fills Lucene TermAttribute with the current token text, removing the two first
* characters.
*/
public final void getBNodeText(CharTermAttribute t) {
t.copyBuffer(zzBuffer, zzStartRead + 2, zzMarkedPos - zzStartRead - 2);
}
/**
* Fills Lucene TermAttribute with the current token text, removing the first and
* last characters.
*/
public final void getURIText(CharTermAttribute t) {
t.copyBuffer(zzBuffer, zzStartRead + 1, zzMarkedPos - zzStartRead - 2);
}
/**
* 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);
}
/**
* Return the current string buffer.
*/
public final char[] getLiteralText() {
char[] chars = new char[buffer.length()];
buffer.getChars(0, buffer.length(), chars, 0);
return chars;
}
/**
* Return the language tag.
*
* Return empty char array if no language tag has been defined
*/
public final char[] getLanguageTag() {
char[] chars = new char[metadataBuffer.length()];
metadataBuffer.getChars(0, metadataBuffer.length(), chars, 0);
return chars;
}
/**
* Return the datatype URI.
*
*
Return the datatype xsd:string by default.
*/
public final char[] getDatatypeURI() {
// If not datatype, returns by default datatype xsd:string
if (metadataBuffer.length() == 0) {
return XSD_STRING;
}
char[] chars = new char[metadataBuffer.length()];
metadataBuffer.getChars(0, metadataBuffer.length(), chars, 0);
return chars;
}
/**
* 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.
*/
TupleTokenizerImpl(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.
*/
TupleTokenizerImpl(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 < 74) {
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 {
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 2:
{ buffer.setLength(0);
metadataBuffer.setLength(0);
yybegin(STRING);
}
case 11: break;
case 3:
{ return DOT;
}
case 12: break;
case 1:
{ /* ignore */
}
case 13: break;
case 4:
{ buffer.append(yytext());
}
case 14: break;
case 9:
{ yybegin(YYINITIAL);
// remove the first four and the last characters.
metadataBuffer.append(zzBuffer, zzStartRead + 4, zzMarkedPos - zzStartRead - 5);
return LITERAL;
}
case 15: break;
case 7:
{ // Assign the xsd:anyURI
metadataBuffer.setLength(0);
metadataBuffer.append(XSD_ANY_URI);
return URI;
}
case 16: break;
case 6:
{ return BNODE;
}
case 17: break;
case 5:
{ yybegin(YYINITIAL);
return LITERAL;
}
case 18: break;
case 8:
{ yybegin(YYINITIAL);
// remove the first two characters.
metadataBuffer.append(zzBuffer, zzStartRead + 2, zzMarkedPos - zzStartRead - 2);
return LITERAL;
}
case 19: break;
case 10:
{ buffer.append(Character.toChars(Integer.parseInt(new String(zzBufferL, zzStartRead+2, zzMarkedPos - zzStartRead - 2 ), 16)));
}
case 20: break;
default:
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
zzAtEOF = true;
return YYEOF;
}
else {
zzScanError(ZZ_NO_MATCH);
}
}
}
}
}