public class JapaneseTokenizerFactory extends BaseTokenizerFactory implements ResourceLoaderAware
JapaneseTokenizer
.
<fieldType name="text_ja" class="solr.TextField"> <analyzer> <tokenizer class="solr.JapaneseTokenizerFactory" mode=NORMAL userDictionary=user.txt userDictionaryEncoding=UTF-8 /> <filter class="solr.JapaneseBaseFormFilterFactory"/> </analyzer> </fieldType>
Modifier and Type | Field and Description |
---|---|
private org.apache.lucene.analysis.ja.JapaneseTokenizer.Mode |
mode |
private static java.lang.String |
MODE |
private static java.lang.String |
USER_DICT_ENCODING |
private static java.lang.String |
USER_DICT_PATH |
private org.apache.lucene.analysis.ja.dict.UserDictionary |
userDictionary |
log
args, luceneMatchVersion
Constructor and Description |
---|
JapaneseTokenizerFactory() |
Modifier and Type | Method and Description |
---|---|
org.apache.lucene.analysis.Tokenizer |
create(java.io.Reader input)
Creates a TokenStream of the specified input
|
private org.apache.lucene.analysis.ja.JapaneseTokenizer.Mode |
getMode(java.util.Map<java.lang.String,java.lang.String> args) |
void |
inform(ResourceLoader loader) |
assureMatchVersion, getArgs, getBoolean, getBoolean, getInt, getInt, getInt, getSnowballWordSet, getWordSet, init, warnDeprecated
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
getArgs, init
private static final java.lang.String MODE
private static final java.lang.String USER_DICT_PATH
private static final java.lang.String USER_DICT_ENCODING
private org.apache.lucene.analysis.ja.dict.UserDictionary userDictionary
private org.apache.lucene.analysis.ja.JapaneseTokenizer.Mode mode
public void inform(ResourceLoader loader)
inform
in interface ResourceLoaderAware
public org.apache.lucene.analysis.Tokenizer create(java.io.Reader input)
TokenizerFactory
create
in interface TokenizerFactory
private org.apache.lucene.analysis.ja.JapaneseTokenizer.Mode getMode(java.util.Map<java.lang.String,java.lang.String> args)