/* The following code was generated by JFlex 1.5.0-SNAPSHOT */
package edu.stanford.nlp.trees.international.negra;
import edu.stanford.nlp.util.logging.Redwood;
import edu.stanford.nlp.io.Lexer;
/** A lexer for the Penn Treebank-style context-free version of the
* NEGRA corpus. Inherits ACCEPT and IGNORE fields from
* edu.stanford.nlp.trees.international.<code>Lexer</code>.
*
* @author Roger Levy
*/
public class NegraPennLexer implements Lexer {
/** A logger for this class */
private static Redwood.RedwoodChannels log = Redwood.channels(NegraPennLexer.class);
/** 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 SENTENCE = 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
};
/**
* Translates characters to character classes
*/
private static final String ZZ_CMAP_PACKED =
"\11\0\1\11\1\13\1\11\1\11\1\12\22\0\1\2\4\14\1\1"+
"\2\14\2\10\6\14\12\7\31\14\1\3\12\14\1\0\6\14\1\4"+
"\10\14\1\5\5\14\1\6\6\14\12\0\1\11\41\0\1\14\17\0"+
"\1\14\10\0\100\14\u1f28\0\1\11\1\11\udfd6\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 =
"\2\0\1\1\1\2\1\3\2\2\1\3\1\4\1\2"+
"\6\0\1\3";
private static int [] zzUnpackAction() {
int [] result = new int[17];
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\15\0\32\0\47\0\32\0\64\0\32\0\101"+
"\0\32\0\116\0\133\0\150\0\165\0\202\0\217\0\234"+
"\0\234";
private static int [] zzUnpackRowMap() {
int [] result = new int[17];
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\1\4\1\5\5\6\1\7\1\5\1\10\1\5"+
"\1\6\15\11\16\0\1\12\1\0\5\6\4\0\1\6"+
"\1\0\1\6\1\0\5\6\4\0\1\6\13\0\1\5"+
"\2\0\1\6\1\13\5\6\4\0\1\6\3\0\1\14"+
"\15\0\1\15\15\0\1\16\15\0\1\17\10\0\1\20"+
"\21\0\1\21\5\0";
private static int [] zzUnpackTrans() {
int [] result = new int[169];
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 <code>aState</code>
*/
private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute();
private static final String ZZ_ATTRIBUTE_PACKED_0 =
"\2\0\1\11\1\1\1\11\1\1\1\11\1\1\1\11"+
"\1\1\6\0\1\1";
private static int [] zzUnpackAttribute() {
int [] result = new int[17];
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 void pushBack(int n) {
yypushback(n);
}
public int getYYEOF() {
return YYEOF;
}
/**
* 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.
*/
NegraPennLexer(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.
*/
NegraPennLexer(java.io.InputStream in) {
this(new java.io.InputStreamReader
(in, java.nio.charset.Charset.forName("UTF-8")));
}
/**
* 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 <code>false</code>, 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
* <b>cannot</b> be reused (internal buffer is discarded and lost).
* Lexical state is set to <tt>ZZ_INITIAL</tt>.
*
* 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;
zzAtBOL = true;
zzAtEOF = false;
zzEOFDone = false;
zzEndRead = zzStartRead = 0;
zzCurrentPos = zzMarkedPos = 0;
yyline = yychar = yycolumn = 0;
zzLexicalState = YYINITIAL;
if (zzBuffer.length > ZZ_BUFFERSIZE)
zzBuffer = new char[ZZ_BUFFERSIZE];
}
/**
* 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 <tt>pos</tt> 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 yylex() 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;
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 = 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;
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 1:
{ log.info("Error: " + yytext());
return IGNORE;
}
case 5: break;
case 2:
{ return ACCEPT;
}
case 6: break;
case 3:
{ return IGNORE;
}
case 7: break;
case 4:
{ System.out.print(yytext());
}
case 8: break;
default:
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
zzAtEOF = true;
return YYEOF;
}
else {
zzScanError(ZZ_NO_MATCH);
}
}
}
}
/**
* Runs the scanner on input files.
*
* This is a standalone scanner, it will print any unmatched
* text to System.out unchanged.
*
* @param argv the command line, contains the filenames to run
* the scanner on.
*/
public static void main(String argv[]) {
if (argv.length == 0) {
System.out.println("Usage : java NegraPennLexer [ --encoding <name> ] <inputfile(s)>");
}
else {
int firstFilePos = 0;
String encodingName = "UTF-8";
if (argv[0].equals("--encoding")) {
firstFilePos = 2;
encodingName = argv[1];
try {
java.nio.charset.Charset.forName(encodingName); // Side-effect: is encodingName valid?
} catch (Exception e) {
System.out.println("Invalid encoding '" + encodingName + "'");
return;
}
}
for (int i = firstFilePos; i < argv.length; i++) {
NegraPennLexer scanner = null;
try {
java.io.FileInputStream stream = new java.io.FileInputStream(argv[i]);
java.io.Reader reader = new java.io.InputStreamReader(stream, encodingName);
scanner = new NegraPennLexer(reader);
while ( !scanner.zzAtEOF ) scanner.yylex();
}
catch (java.io.FileNotFoundException e) {
System.out.println("File not found : \""+argv[i]+"\"");
}
catch (java.io.IOException e) {
System.out.println("IO error scanning file \""+argv[i]+"\"");
System.out.println(e);
}
catch (Exception e) {
System.out.println("Unexpected exception:");
e.printStackTrace();
}
}
}
}
}