org.apache.lucene.wikipedia.analysis
Class WikipediaTokenizer

java.lang.Object
  extended by org.apache.lucene.analysis.TokenStream
      extended by org.apache.lucene.analysis.Tokenizer
          extended by org.apache.lucene.wikipedia.analysis.WikipediaTokenizer

public class WikipediaTokenizer
extends Tokenizer

Extension of StandardTokenizer that is aware of Wikipedia syntax. It is based off of the Wikipedia tutorial available at http://en.wikipedia.org/wiki/Wikipedia:Tutorial, but it may not be complete.

EXPERIMENTAL !!!!!!!!! NOTE: This Tokenizer is considered experimental and the grammar is subject to change in the trunk and in follow up releases.


Field Summary
static int ACRONYM_ID
           
static int ALPHANUM_ID
           
static int APOSTROPHE_ID
           
static String BOLD
           
static int BOLD_ID
           
static String BOLD_ITALICS
           
static int BOLD_ITALICS_ID
           
static int BOTH
           
static String CATEGORY
           
static int CATEGORY_ID
           
static String CITATION
           
static int CITATION_ID
           
static int CJ_ID
           
static int COMPANY_ID
           
static int EMAIL_ID
           
static String EXTERNAL_LINK
           
static int EXTERNAL_LINK_ID
           
static String EXTERNAL_LINK_URL
           
static int EXTERNAL_LINK_URL_ID
           
static String HEADING
           
static int HEADING_ID
           
static int HOST_ID
           
static String INTERNAL_LINK
           
static int INTERNAL_LINK_ID
           
static String ITALICS
           
static int ITALICS_ID
           
static int NUM_ID
           
static String SUB_HEADING
           
static int SUB_HEADING_ID
           
static String[] TOKEN_TYPES
          String token types that correspond to token type int constants
static String[] tokenImage
          Deprecated. Please use TOKEN_TYPES instead
static int TOKENS_ONLY
           
static int UNTOKENIZED_ONLY
           
 
Fields inherited from class org.apache.lucene.analysis.Tokenizer
input
 
Constructor Summary
WikipediaTokenizer(Reader input)
          Creates a new instance of the WikipediaTokenizer.
 
Method Summary
 Token next(Token result)
           
 void reset()
           
 void reset(Reader reader)
           
 
Methods inherited from class org.apache.lucene.analysis.Tokenizer
close
 
Methods inherited from class org.apache.lucene.analysis.TokenStream
next
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

INTERNAL_LINK

public static final String INTERNAL_LINK
See Also:
Constant Field Values

EXTERNAL_LINK

public static final String EXTERNAL_LINK
See Also:
Constant Field Values

EXTERNAL_LINK_URL

public static final String EXTERNAL_LINK_URL
See Also:
Constant Field Values

CITATION

public static final String CITATION
See Also:
Constant Field Values

CATEGORY

public static final String CATEGORY
See Also:
Constant Field Values

BOLD

public static final String BOLD
See Also:
Constant Field Values

ITALICS

public static final String ITALICS
See Also:
Constant Field Values

BOLD_ITALICS

public static final String BOLD_ITALICS
See Also:
Constant Field Values

HEADING

public static final String HEADING
See Also:
Constant Field Values

SUB_HEADING

public static final String SUB_HEADING
See Also:
Constant Field Values

ALPHANUM_ID

public static final int ALPHANUM_ID
See Also:
Constant Field Values

APOSTROPHE_ID

public static final int APOSTROPHE_ID
See Also:
Constant Field Values

ACRONYM_ID

public static final int ACRONYM_ID
See Also:
Constant Field Values

COMPANY_ID

public static final int COMPANY_ID
See Also:
Constant Field Values

EMAIL_ID

public static final int EMAIL_ID
See Also:
Constant Field Values

HOST_ID

public static final int HOST_ID
See Also:
Constant Field Values

NUM_ID

public static final int NUM_ID
See Also:
Constant Field Values

CJ_ID

public static final int CJ_ID
See Also:
Constant Field Values

INTERNAL_LINK_ID

public static final int INTERNAL_LINK_ID
See Also:
Constant Field Values

EXTERNAL_LINK_ID

public static final int EXTERNAL_LINK_ID
See Also:
Constant Field Values

CITATION_ID

public static final int CITATION_ID
See Also:
Constant Field Values

CATEGORY_ID

public static final int CATEGORY_ID
See Also:
Constant Field Values

BOLD_ID

public static final int BOLD_ID
See Also:
Constant Field Values

ITALICS_ID

public static final int ITALICS_ID
See Also:
Constant Field Values

BOLD_ITALICS_ID

public static final int BOLD_ITALICS_ID
See Also:
Constant Field Values

HEADING_ID

public static final int HEADING_ID
See Also:
Constant Field Values

SUB_HEADING_ID

public static final int SUB_HEADING_ID
See Also:
Constant Field Values

EXTERNAL_LINK_URL_ID

public static final int EXTERNAL_LINK_URL_ID
See Also:
Constant Field Values

TOKEN_TYPES

public static final String[] TOKEN_TYPES
String token types that correspond to token type int constants


tokenImage

public static final String[] tokenImage
Deprecated. Please use TOKEN_TYPES instead

TOKENS_ONLY

public static final int TOKENS_ONLY
See Also:
Constant Field Values

UNTOKENIZED_ONLY

public static final int UNTOKENIZED_ONLY
See Also:
Constant Field Values

BOTH

public static final int BOTH
See Also:
Constant Field Values
Constructor Detail

WikipediaTokenizer

public WikipediaTokenizer(Reader input)
Creates a new instance of the WikipediaTokenizer. Attaches the input to a newly created JFlex scanner.

Parameters:
input - The Input Reader
Method Detail

next

public Token next(Token result)
           throws IOException
Overrides:
next in class TokenStream
Throws:
IOException

reset

public void reset()
           throws IOException
Overrides:
reset in class TokenStream
Throws:
IOException

reset

public void reset(Reader reader)
           throws IOException
Overrides:
reset in class Tokenizer
Throws:
IOException


Copyright © 2000-2008 Apache Software Foundation. All Rights Reserved.