weka.core.json.Scanner Maven / Gradle / Ivy
Show all versions of weka-dev Show documentation
// DO NOT EDIT
// Generated by JFlex 1.8.2 http://jflex.de/
// source: src/main/java/weka/core/json/Scanner.jflex
/*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see .
*/
/*
* Scanner.java
* Copyright (C) 2009-2012 University of Waikato, Hamilton, New Zealand
*/
package weka.core.json;
import java_cup.runtime.SymbolFactory;
import java.io.*;
/**
* A scanner for JSON data files.
*
* @author FracPete (fracpete at waikato dot ac dot nz)
* @version $Revision: 15625 $
*/
// See https://github.com/jflex-de/jflex/issues/222
@SuppressWarnings("FallThrough")
public class Scanner implements java_cup.runtime.Scanner {
/** 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 YYINITIAL = 0;
public static final int STRING = 2;
/**
* 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
};
/**
* Top-level table for translating characters to character classes
*/
private static final int [] ZZ_CMAP_TOP = zzUnpackcmap_top();
private static final String ZZ_CMAP_TOP_PACKED_0 =
"\1\0\327\u0100\10\u0200\u1020\u0100";
private static int [] zzUnpackcmap_top() {
int [] result = new int[4352];
int offset = 0;
offset = zzUnpackcmap_top(ZZ_CMAP_TOP_PACKED_0, offset, result);
return result;
}
private static int zzUnpackcmap_top(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;
}
/**
* Second-level tables for translating characters to character classes
*/
private static final int [] ZZ_CMAP_BLOCKS = zzUnpackcmap_blocks();
private static final String ZZ_CMAP_BLOCKS_PACKED_0 =
"\11\0\1\1\1\2\1\0\1\1\1\3\22\0\1\1"+
"\1\0\1\4\11\0\1\5\1\6\1\7\1\0\12\10"+
"\1\11\40\0\1\12\1\13\1\14\3\0\1\15\1\16"+
"\2\0\1\17\1\20\5\0\1\21\1\0\1\22\3\0"+
"\1\23\1\24\1\25\1\26\5\0\1\27\1\0\1\30"+
"\u0182\0\u0100\31";
private static int [] zzUnpackcmap_blocks() {
int [] result = new int[768];
int offset = 0;
offset = zzUnpackcmap_blocks(ZZ_CMAP_BLOCKS_PACKED_0, offset, result);
return result;
}
private static int zzUnpackcmap_blocks(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 DFA states to action switch labels.
*/
private static final int [] ZZ_ACTION = zzUnpackAction();
private static final String ZZ_ACTION_PACKED_0 =
"\2\0\1\1\1\2\1\3\1\4\1\1\1\5\1\6"+
"\1\7\1\10\3\1\1\11\1\12\1\13\1\14\1\15"+
"\2\16\3\0\1\17\1\20\1\21\1\22\1\23\1\24"+
"\3\0\1\25\1\26";
private static int [] zzUnpackAction() {
int [] result = new int[35];
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\32\0\64\0\64\0\64\0\64\0\116\0\150"+
"\0\64\0\64\0\64\0\202\0\234\0\266\0\64\0\64"+
"\0\320\0\64\0\352\0\u0104\0\u011e\0\u0138\0\u0152\0\u016c"+
"\0\64\0\64\0\64\0\64\0\64\0\64\0\u0186\0\u01a0"+
"\0\u01ba\0\64\0\64";
private static int [] zzUnpackRowMap() {
int [] result = new int[35];
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 =
"\1\3\3\4\1\5\1\6\1\7\1\3\1\10\1\11"+
"\1\12\1\3\1\13\3\3\1\14\1\3\1\15\2\3"+
"\1\16\1\3\1\17\1\20\1\0\2\21\1\0\1\3"+
"\1\22\6\21\1\23\16\21\42\0\1\24\30\0\1\25"+
"\1\10\36\0\1\26\42\0\1\27\26\0\1\30\6\0"+
"\2\21\3\0\6\21\1\0\16\21\4\0\1\31\11\0"+
"\1\32\1\0\1\33\1\0\1\34\1\35\1\0\1\36"+
"\13\0\1\25\1\24\31\0\1\25\42\0\1\37\31\0"+
"\1\40\36\0\1\41\27\0\1\41\26\0\1\42\27\0"+
"\1\43\12\0";
private static int [] zzUnpackTrans() {
int [] result = new int[468];
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 code for "Unknown internal scanner error". */
private static final int ZZ_UNKNOWN_ERROR = 0;
/** Error code for "could not match input". */
private static final int ZZ_NO_MATCH = 1;
/** Error code for "pushback value was too large". */
private static final int ZZ_PUSHBACK_2BIG = 2;
/**
* Error messages for {@link #ZZ_UNKNOWN_ERROR}, {@link #ZZ_NO_MATCH}, and
* {@link #ZZ_PUSHBACK_2BIG} respectively.
*/
private static final String ZZ_ERROR_MSG[] = {
"Unknown internal scanner error",
"Error: could not match input",
"Error: pushback value was too large"
};
/**
* ZZ_ATTRIBUTE[aState] contains the attributes of state {@code aState}
*/
private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute();
private static final String ZZ_ATTRIBUTE_PACKED_0 =
"\2\0\4\11\2\1\3\11\3\1\2\11\1\1\1\11"+
"\3\1\3\0\6\11\3\0\2\11";
private static int [] zzUnpackAttribute() {
int [] result = new int[35];
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;
}
/** Input device. */
private java.io.Reader zzReader;
/** Current state of the DFA. */
private int zzState;
/** Current lexical state. */
private int zzLexicalState = YYINITIAL;
/**
* This buffer contains the current text to be matched and is the source of the {@link #yytext()}
* string.
*/
private char zzBuffer[] = new char[ZZ_BUFFERSIZE];
/** Text position at the last accepting state. */
private int zzMarkedPos;
/** Current text position in the buffer. */
private int zzCurrentPos;
/** Marks the beginning of the {@link #yytext()} string in the buffer. */
private int zzStartRead;
/** Marks the last character in the buffer, that has been read from input. */
private int zzEndRead;
/**
* Whether the scanner is at the end of file.
* @see #yyatEOF
*/
private boolean zzAtEOF;
/**
* The number of occupied positions in {@link #zzBuffer} beyond {@link #zzEndRead}.
*
* When a lead/high surrogate has been read from the input stream into the final
* {@link #zzBuffer} position, this will have a value of 1; otherwise, it will have a value of 0.
*/
private int zzFinalHighSurrogate = 0;
/** Number of newlines encountered up to the start of the matched text. */
@SuppressWarnings("unused")
private int yyline;
/** Number of characters from the last newline up to the start of the matched text. */
@SuppressWarnings("unused")
private int yycolumn;
/** Number of characters up to the start of the matched text. */
@SuppressWarnings("unused")
private long yychar;
/** Whether the scanner is currently at the beginning of a line. */
@SuppressWarnings("unused")
private boolean zzAtBOL = true;
/** Whether the user-EOF-code has already been executed. */
@SuppressWarnings("unused")
private boolean zzEOFDone;
/* user code: */
// Author: FracPete (fracpete at waikato dot ac dot nz)
// Version: $Revision: 15625 $
protected SymbolFactory m_SF;
protected StringBuffer m_String = new StringBuffer();
public Scanner(InputStream r, SymbolFactory sf) {
this(new InputStreamReader(r));
m_SF = sf;
}
public Scanner(Reader r, SymbolFactory sf) {
this(r);
m_SF = sf;
}
/**
* Creates a new scanner
*
* @param in the java.io.Reader to read input from.
*/
public Scanner(java.io.Reader in) {
this.zzReader = in;
}
/**
* Translates raw input code points to DFA table row
*/
private static int zzCMap(int input) {
int offset = input & 255;
return offset == input ? ZZ_CMAP_BLOCKS[offset] : ZZ_CMAP_BLOCKS[ZZ_CMAP_TOP[input >> 8] | offset];
}
/**
* Refills the input buffer.
*
* @return {@code 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) {
zzEndRead += zzFinalHighSurrogate;
zzFinalHighSurrogate = 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 - zzFinalHighSurrogate) {
/* if not: blow it up */
char newBuffer[] = new char[zzBuffer.length * 2];
System.arraycopy(zzBuffer, 0, newBuffer, 0, zzBuffer.length);
zzBuffer = newBuffer;
zzEndRead += zzFinalHighSurrogate;
zzFinalHighSurrogate = 0;
}
/* fill the buffer with new input */
int requested = zzBuffer.length - zzEndRead;
int numRead = zzReader.read(zzBuffer, zzEndRead, requested);
/* not supposed to occur according to specification of java.io.Reader */
if (numRead == 0) {
throw new java.io.IOException(
"Reader returned 0 characters. See JFlex examples/zero-reader for a workaround.");
}
if (numRead > 0) {
zzEndRead += numRead;
if (Character.isHighSurrogate(zzBuffer[zzEndRead - 1])) {
if (numRead == requested) { // We requested too few chars to encode a full Unicode character
--zzEndRead;
zzFinalHighSurrogate = 1;
} else { // There is room in the buffer for at least one more char
int c = zzReader.read(); // Expecting to read a paired low surrogate char
if (c == -1) {
return true;
} else {
zzBuffer[zzEndRead++] = (char)c;
}
}
}
/* potentially more input available */
return false;
}
/* numRead < 0 ==> end of stream */
return true;
}
/**
* Closes the input reader.
*
* @throws java.io.IOException if the reader could not be closed.
*/
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 {@code ZZ_INITIAL}.
*
*
Internal scan buffer is resized down to its initial length, if it has grown.
*
* @param reader The new input stream.
*/
public final void yyreset(java.io.Reader reader) {
zzReader = reader;
zzEOFDone = false;
yyResetPosition();
zzLexicalState = YYINITIAL;
if (zzBuffer.length > ZZ_BUFFERSIZE) {
zzBuffer = new char[ZZ_BUFFERSIZE];
}
}
/**
* Resets the input position.
*/
private final void yyResetPosition() {
zzAtBOL = true;
zzAtEOF = false;
zzCurrentPos = 0;
zzMarkedPos = 0;
zzStartRead = 0;
zzEndRead = 0;
zzFinalHighSurrogate = 0;
yyline = 0;
yycolumn = 0;
yychar = 0L;
}
/**
* Returns whether the scanner has reached the end of the reader it reads from.
*
* @return whether the scanner has reached EOF.
*/
public final boolean yyatEOF() {
return zzAtEOF;
}
/**
* Returns the current lexical state.
*
* @return 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.
*
* @return the matched text.
*/
public final String yytext() {
return new String(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
}
/**
* Returns the character at the given position from the matched text.
*
*
It is equivalent to {@code yytext().charAt(pos)}, but faster.
*
* @param position the position of the character to fetch. A value from 0 to {@code yylength()-1}.
*
* @return the character at {@code position}.
*/
public final char yycharat(int position) {
return zzBuffer[zzStartRead + position];
}
/**
* How many characters were matched.
*
* @return the length of the matched text region.
*/
public final int yylength() {
return zzMarkedPos-zzStartRead;
}
/**
* Reports an error that occurred while scanning.
*
*
In a well-formed scanner (no or only correct usage of {@code 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 error message to display.
*/
private static 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
* {@link #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.
*/
@Override public java_cup.runtime.Symbol next_token() throws java.io.IOException {
int zzInput;
int zzAction;
// cached fields:
int zzCurrentPosL;
int zzMarkedPosL;
int zzEndReadL = zzEndRead;
char[] zzBufferL = zzBuffer;
int [] zzTransL = ZZ_TRANS;
int [] zzRowMapL = ZZ_ROWMAP;
int [] zzAttrL = ZZ_ATTRIBUTE;
while (true) {
zzMarkedPosL = zzMarkedPos;
zzAction = -1;
zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL;
zzState = ZZ_LEXSTATE[zzLexicalState];
// set up zzAction for empty match case:
int zzAttributes = zzAttrL[zzState];
if ( (zzAttributes & 1) == 1 ) {
zzAction = zzState;
}
zzForAction: {
while (true) {
if (zzCurrentPosL < zzEndReadL) {
zzInput = Character.codePointAt(zzBufferL, zzCurrentPosL, zzEndReadL);
zzCurrentPosL += Character.charCount(zzInput);
}
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 = Character.codePointAt(zzBufferL, zzCurrentPosL, zzEndReadL);
zzCurrentPosL += Character.charCount(zzInput);
}
}
int zzNext = zzTransL[ zzRowMapL[zzState] + zzCMap(zzInput) ];
if (zzNext == -1) break zzForAction;
zzState = zzNext;
zzAttributes = zzAttrL[zzState];
if ( (zzAttributes & 1) == 1 ) {
zzAction = zzState;
zzMarkedPosL = zzCurrentPosL;
if ( (zzAttributes & 8) == 8 ) break zzForAction;
}
}
}
// store back cached position
zzMarkedPos = zzMarkedPosL;
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
zzAtEOF = true;
{ return m_SF.newSymbol("EOF", sym.EOF);
}
}
else {
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
case 1:
{ System.err.println("Illegal character: " + yytext());
}
// fall through
case 23: break;
case 2:
{ /* ignore white space. */
}
// fall through
case 24: break;
case 3:
{ m_String.setLength(0); yybegin(STRING);
}
// fall through
case 25: break;
case 4:
{ return m_SF.newSymbol("Comma", sym.COMMA);
}
// fall through
case 26: break;
case 5:
{ return m_SF.newSymbol("Integer", sym.INTEGER, new Integer(yytext()));
}
// fall through
case 27: break;
case 6:
{ return m_SF.newSymbol("Colon", sym.COLON);
}
// fall through
case 28: break;
case 7:
{ return m_SF.newSymbol("Left square bracket", sym.LSQUARE);
}
// fall through
case 29: break;
case 8:
{ return m_SF.newSymbol("Right square bracket", sym.RSQUARE);
}
// fall through
case 30: break;
case 9:
{ return m_SF.newSymbol("Left curly bracket", sym.LCURLY);
}
// fall through
case 31: break;
case 10:
{ return m_SF.newSymbol("Right curly bracket", sym.RCURLY);
}
// fall through
case 32: break;
case 11:
{ m_String.append(yytext());
}
// fall through
case 33: break;
case 12:
{ yybegin(YYINITIAL); return m_SF.newSymbol("String", sym.STRING, m_String.toString());
}
// fall through
case 34: break;
case 13:
{ m_String.append('\\');
}
// fall through
case 35: break;
case 14:
{ return m_SF.newSymbol("Double", sym.DOUBLE, new Double(yytext()));
}
// fall through
case 36: break;
case 15:
{ m_String.append('\"');
}
// fall through
case 37: break;
case 16:
{ m_String.append('\b');
}
// fall through
case 38: break;
case 17:
{ m_String.append('\f');
}
// fall through
case 39: break;
case 18:
{ m_String.append('\n');
}
// fall through
case 40: break;
case 19:
{ m_String.append('\r');
}
// fall through
case 41: break;
case 20:
{ m_String.append('\t');
}
// fall through
case 42: break;
case 21:
{ return m_SF.newSymbol("Null", sym.NULL);
}
// fall through
case 43: break;
case 22:
{ return m_SF.newSymbol("Boolean", sym.BOOLEAN, new Boolean(yytext()));
}
// fall through
case 44: break;
default:
zzScanError(ZZ_NO_MATCH);
}
}
}
}
}