Docjar: A Java Source and Docuemnt Enginecom.*    java.*    javax.*    org.*    all    new    plug-in

Quick Search    Search Deep

org.apache.lenya.lucene.html
Class HTMLParser  view HTMLParser download HTMLParser.java

java.lang.Object
  extended byorg.apache.lenya.lucene.html.HTMLParser
All Implemented Interfaces:
HTMLParserConstants

public class HTMLParser
extends java.lang.Object
implements HTMLParserConstants

HTML Parser


Nested Class Summary
(package private) static class HTMLParser.JJCalls
           
 
Field Summary
(package private)  boolean afterSpace
           
(package private)  boolean afterTag
           
(package private)  java.lang.String eol
           
(package private)  boolean inScript
           
(package private)  boolean inTitle
           
private  HTMLParser.JJCalls[] jj_2_rtns
           
private  int jj_endpos
           
private  java.util.Vector jj_expentries
           
private  int[] jj_expentry
           
private  int jj_gc
           
private  int jj_gen
           
(package private)  SimpleCharStream jj_input_stream
           
private  int jj_kind
           
private  int jj_la
           
private  int[] jj_la1
           
private  int[] jj_la1_0
           
private  Token jj_lastpos
           
private  int[] jj_lasttokens
           
 Token jj_nt
           
private  int jj_ntk
           
private  boolean jj_rescan
           
private  Token jj_scanpos
           
(package private)  int length
           
 boolean lookingAhead
           
(package private)  int MAX_WAIT
           
(package private)  java.io.PipedReader pipeIn
           
(package private)  java.io.PipedWriter pipeOut
           
(package private)  java.lang.StringBuffer summary
           
static int SUMMARY_LENGTH
           
(package private)  java.lang.StringBuffer title
           
(package private)  boolean titleComplete
           
 Token token
           
 HTMLParserTokenManager token_source
           
 
Fields inherited from interface org.apache.lenya.lucene.html.HTMLParserConstants
AfterEquals, ArgEquals, ArgName, ArgQuote1, ArgQuote2, ArgValue, CloseQuote1, CloseQuote2, Comment1, Comment2, CommentEnd1, CommentEnd2, CommentText1, CommentText2, DeclName, DEFAULT, Entity, EOF, LET, NUM, Punct, Quote1Text, Quote2Text, SP, Space, TagEnd, TagName, tokenImage, WithinComment1, WithinComment2, WithinQuote1, WithinQuote2, WithinTag, Word
 
Constructor Summary
HTMLParser(java.io.File file)
          Creates a new HTMLParser object.
HTMLParser(HTMLParserTokenManager tm)
          Creates a new HTMLParser object.
HTMLParser(java.io.InputStream stream)
          Creates a new HTMLParser object.
HTMLParser(java.io.Reader stream)
          Creates a new HTMLParser object.
 
Method Summary
(package private)  void addSpace()
           
(package private)  void addText(java.lang.String text)
           
(package private)  void addToSummary(java.lang.String text)
           
(package private)  void addToTitle(java.lang.String text)
           
 Token ArgValue()
          DOCUMENT ME!
 void CommentTag()
          DOCUMENT ME!
 Token Decl()
          DOCUMENT ME!
 void disable_tracing()
          DOCUMENT ME!
 void enable_tracing()
          DOCUMENT ME!
 ParseException generateParseException()
          DOCUMENT ME!
 java.lang.String getKeywords()
          Get keywords
 Token getNextToken()
          DOCUMENT ME!
 java.io.Reader getReader()
          DOCUMENT ME!
 java.lang.String getSummary()
          DOCUMENT ME!
 java.lang.String getTitle()
          DOCUMENT ME!
 Token getToken(int index)
          DOCUMENT ME!
 void HTMLDocument()
          DOCUMENT ME!
private  boolean jj_2_1(int xla)
           
private  boolean jj_2_2(int xla)
           
private  boolean jj_3_1()
           
private  boolean jj_3_2()
           
private  void jj_add_error_token(int kind, int pos)
           
private  Token jj_consume_token(int kind)
           
private  int jj_ntk()
           
private  void jj_rescan_token()
           
private  void jj_save(int index, int xla)
           
private  boolean jj_scan_token(int kind)
           
 void ReInit(HTMLParserTokenManager tm)
          DOCUMENT ME!
 void ReInit(java.io.InputStream stream)
          DOCUMENT ME!
 void ReInit(java.io.Reader stream)
          DOCUMENT ME!
 void Tag()
          DOCUMENT ME!
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

SUMMARY_LENGTH

public static int SUMMARY_LENGTH

title

java.lang.StringBuffer title

summary

java.lang.StringBuffer summary

length

int length

titleComplete

boolean titleComplete

inTitle

boolean inTitle

inScript

boolean inScript

afterTag

boolean afterTag

afterSpace

boolean afterSpace

eol

java.lang.String eol

pipeIn

java.io.PipedReader pipeIn

pipeOut

java.io.PipedWriter pipeOut

MAX_WAIT

int MAX_WAIT

token_source

public HTMLParserTokenManager token_source

jj_input_stream

SimpleCharStream jj_input_stream

token

public Token token

jj_nt

public Token jj_nt

jj_ntk

private int jj_ntk

jj_scanpos

private Token jj_scanpos

jj_lastpos

private Token jj_lastpos

jj_la

private int jj_la

lookingAhead

public boolean lookingAhead

jj_gen

private int jj_gen

jj_la1

private final int[] jj_la1

jj_la1_0

private final int[] jj_la1_0

jj_2_rtns

private final HTMLParser.JJCalls[] jj_2_rtns

jj_rescan

private boolean jj_rescan

jj_gc

private int jj_gc

jj_expentries

private java.util.Vector jj_expentries

jj_expentry

private int[] jj_expentry

jj_kind

private int jj_kind

jj_lasttokens

private int[] jj_lasttokens

jj_endpos

private int jj_endpos
Constructor Detail

HTMLParser

public HTMLParser(java.io.File file)
           throws java.io.FileNotFoundException
Creates a new HTMLParser object.


HTMLParser

public HTMLParser(java.io.InputStream stream)
Creates a new HTMLParser object.


HTMLParser

public HTMLParser(java.io.Reader stream)
Creates a new HTMLParser object.


HTMLParser

public HTMLParser(HTMLParserTokenManager tm)
Creates a new HTMLParser object.

Method Detail

getTitle

public java.lang.String getTitle()
                          throws java.io.IOException,
                                 java.lang.InterruptedException
DOCUMENT ME!


getKeywords

public java.lang.String getKeywords()
                             throws java.io.IOException,
                                    java.lang.InterruptedException
Get keywords


getSummary

public java.lang.String getSummary()
                            throws java.io.IOException,
                                   java.lang.InterruptedException
DOCUMENT ME!


getReader

public java.io.Reader getReader()
                         throws java.io.IOException
DOCUMENT ME!


addToSummary

void addToSummary(java.lang.String text)

addToTitle

void addToTitle(java.lang.String text)

addText

void addText(java.lang.String text)
       throws java.io.IOException

addSpace

void addSpace()
        throws java.io.IOException

HTMLDocument

public final void HTMLDocument()
                        throws ParseException,
                               java.io.IOException
DOCUMENT ME!


Tag

public final void Tag()
               throws ParseException,
                      java.io.IOException
DOCUMENT ME!


ArgValue

public final Token ArgValue()
                     throws ParseException
DOCUMENT ME!


Decl

public final Token Decl()
                 throws ParseException
DOCUMENT ME!


CommentTag

public final void CommentTag()
                      throws ParseException
DOCUMENT ME!


jj_2_1

private final boolean jj_2_1(int xla)

jj_2_2

private final boolean jj_2_2(int xla)

jj_3_1

private final boolean jj_3_1()

jj_3_2

private final boolean jj_3_2()

ReInit

public void ReInit(java.io.InputStream stream)
DOCUMENT ME!


ReInit

public void ReInit(java.io.Reader stream)
DOCUMENT ME!


ReInit

public void ReInit(HTMLParserTokenManager tm)
DOCUMENT ME!


jj_consume_token

private final Token jj_consume_token(int kind)
                              throws ParseException

jj_scan_token

private final boolean jj_scan_token(int kind)

getNextToken

public final Token getNextToken()
DOCUMENT ME!


getToken

public final Token getToken(int index)
DOCUMENT ME!


jj_ntk

private final int jj_ntk()

jj_add_error_token

private void jj_add_error_token(int kind,
                                int pos)

generateParseException

public final ParseException generateParseException()
DOCUMENT ME!


enable_tracing

public final void enable_tracing()
DOCUMENT ME!


disable_tracing

public final void disable_tracing()
DOCUMENT ME!


jj_rescan_token

private final void jj_rescan_token()

jj_save

private final void jj_save(int index,
                           int xla)