edu.stanford.nlp.process.WhitespaceLexer Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of stanford-parser Show documentation
Show all versions of stanford-parser Show documentation
Stanford Parser processes raw text in English, Chinese, German, Arabic, and French, and extracts constituency parse trees.
/* The following code was generated by JFlex 1.6.1 */
package edu.stanford.nlp.process;
import java.io.Reader;
/** Provides a Unicode-aware plain whitespace tokenizer. This tokenizer separates words
* based on whitespace, including Unicode spaces such as the CJK ideographic space as well
* as traditional Unix whitespace characters. It can optionally separate out and return
* newline characters, again recognizing all Unicode newline sequences.
* Designed to be called by WhitespaceTokenizer.
*
* @author Roger Levy
* @author Christopher Manning
*/
class WhitespaceLexer {
/** 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;
/**
* 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
};
/**
* Translates characters to character classes
*/
private static final String ZZ_CMAP_PACKED =
"\11\0\1\4\1\2\2\3\1\1\20\0\2\3\1\4\144\0\1\3"+
"\u15fa\0\1\4\u097f\0\7\4\1\0\3\4\35\0\1\3\1\3\65\0"+
"\1\4\u0fa0\0\1\4\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\uffff\0\ud00f\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 =
"\1\0\1\1\2\2\1\3";
private static int [] zzUnpackAction() {
int [] result = new int[5];
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\5\0\12\0\17\0\24";
private static int [] zzUnpackRowMap() {
int [] result = new int[5];
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\2\1\3\2\4\1\5\1\2\6\0\1\4\13\0"+
"\1\5";
private static int [] zzUnpackTrans() {
int [] result = new int[25];
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[] = {
"Unknown 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 =
"\1\0\2\1\1\11\1\1";
private static int [] zzUnpackAttribute() {
int [] result = new int[5];
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;
/**
* The number of occupied positions in zzBuffer beyond zzEndRead.
* When a lead/high surrogate has been read from the input stream
* into the final zzBuffer position, this will have a value of 1;
* otherwise, it will have a value of 0.
*/
private int zzFinalHighSurrogate = 0;
/* user code: */
/**
* See: http://www.w3.org/TR/newline on Web newline chars: NEL, LS, PS.
See: http://unicode.org/reports/tr13/tr13-9.html and
http://www.unicode.org/unicode/reports/tr18/#Line_Boundaries
for Unicode conventions,
including other separators (vertical tab and form feed).
We do not interpret the zero width joiner/non-joiner (U+200C,
U+200D) as white spaces.
No longer %standalone. See WhitespaceTokenizer for a main method.
*/
public WhitespaceLexer(Reader r, LexedTokenFactory tf) {
this(r);
this.tokenFactory = tf;
}
private LexedTokenFactory tokenFactory;
static final String NEWLINE = "\n";
/**
* Creates a new scanner
*
* @param in the java.io.Reader to read input from.
*/
WhitespaceLexer(java.io.Reader in) {
this.zzReader = 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[0x110000];
int i = 0; /* index in packed string */
int j = 0; /* index in unpacked array */
while (i < 80) {
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) {
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 for workaround.");
}
if (numRead > 0) {
zzEndRead += numRead;
/* If numRead == requested, we might have requested to few chars to
encode a full Unicode character. We assume that a Reader would
otherwise never return half characters. */
if (numRead == requested) {
if (Character.isHighSurrogate(zzBuffer[zzEndRead - 1])) {
--zzEndRead;
zzFinalHighSurrogate = 1;
}
}
/* potentially more input available */
return false;
}
/* numRead < 0 ==> end of stream */
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.
*
* 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;
zzFinalHighSurrogate = 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 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 Object next() 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];
// 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] + 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;
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
zzAtEOF = true;
{
return null;
}
}
else {
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
case 1:
{ return tokenFactory.makeToken(yytext(), yychar, yylength());
}
case 4: break;
case 2:
{ return tokenFactory.makeToken(NEWLINE, yychar, yylength());
}
case 5: break;
case 3:
{
}
case 6: break;
default:
zzScanError(ZZ_NO_MATCH);
}
}
}
}
}