mirror of https://github.com/apache/lucene.git
small javadoc fixes
git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@178832 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
parent
f4e819c006
commit
816f370c0e
|
@ -19,7 +19,8 @@ package org.apache.lucene.analysis;
|
||||||
import java.io.Reader;
|
import java.io.Reader;
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* "Tokenizes" the entire stream as a single token.
|
* "Tokenizes" the entire stream as a single token. This is useful
|
||||||
|
* for data like zip codes, ids, and some product names.
|
||||||
*/
|
*/
|
||||||
public class KeywordAnalyzer extends Analyzer {
|
public class KeywordAnalyzer extends Analyzer {
|
||||||
public TokenStream tokenStream(String fieldName,
|
public TokenStream tokenStream(String fieldName,
|
||||||
|
|
|
@ -31,16 +31,16 @@ import java.util.HashSet;
|
||||||
import java.util.Set;
|
import java.util.Set;
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Analyzer for brazilian language. Supports an external list of stopwords (words that
|
* Analyzer for Brazilian language. Supports an external list of stopwords (words that
|
||||||
* will not be indexed at all) and an external list of exclusions (word that will
|
* will not be indexed at all) and an external list of exclusions (word that will
|
||||||
* not be stemmed, but indexed).
|
* not be stemmed, but indexed).
|
||||||
*
|
*
|
||||||
* @author Jo<EFBFBD>o Kramer
|
* @author João Kramer
|
||||||
*/
|
*/
|
||||||
public final class BrazilianAnalyzer extends Analyzer {
|
public final class BrazilianAnalyzer extends Analyzer {
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* List of typical german stopwords.
|
* List of typical Brazilian stopwords.
|
||||||
*/
|
*/
|
||||||
public final static String[] BRAZILIAN_STOP_WORDS = {
|
public final static String[] BRAZILIAN_STOP_WORDS = {
|
||||||
"a","ainda","alem","ambas","ambos","antes",
|
"a","ainda","alem","ambas","ambos","antes",
|
||||||
|
@ -68,6 +68,7 @@ public final class BrazilianAnalyzer extends Analyzer {
|
||||||
* Contains the stopwords used with the StopFilter.
|
* Contains the stopwords used with the StopFilter.
|
||||||
*/
|
*/
|
||||||
private Set stoptable = new HashSet();
|
private Set stoptable = new HashSet();
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Contains words that should be indexed but not stemmed.
|
* Contains words that should be indexed but not stemmed.
|
||||||
*/
|
*/
|
||||||
|
|
|
@ -105,7 +105,7 @@ public final class CzechAnalyzer extends Analyzer {
|
||||||
/**
|
/**
|
||||||
* Loads stopwords hash from resource stream (file, database...).
|
* Loads stopwords hash from resource stream (file, database...).
|
||||||
* @param wordfile File containing the wordlist
|
* @param wordfile File containing the wordlist
|
||||||
* @param encoding Encoding used (win-1250, iso-8859-2, ...}, null for default system encoding
|
* @param encoding Encoding used (win-1250, iso-8859-2, ...), null for default system encoding
|
||||||
*/
|
*/
|
||||||
public void loadStopWords( InputStream wordfile, String encoding ) {
|
public void loadStopWords( InputStream wordfile, String encoding ) {
|
||||||
if ( wordfile == null ) {
|
if ( wordfile == null ) {
|
||||||
|
@ -122,7 +122,6 @@ public final class CzechAnalyzer extends Analyzer {
|
||||||
else
|
else
|
||||||
isr = new InputStreamReader(wordfile, encoding);
|
isr = new InputStreamReader(wordfile, encoding);
|
||||||
|
|
||||||
|
|
||||||
LineNumberReader lnr = new LineNumberReader(isr);
|
LineNumberReader lnr = new LineNumberReader(isr);
|
||||||
String word;
|
String word;
|
||||||
while ( ( word = lnr.readLine() ) != null ) {
|
while ( ( word = lnr.readLine() ) != null ) {
|
||||||
|
@ -138,7 +137,7 @@ public final class CzechAnalyzer extends Analyzer {
|
||||||
* Creates a TokenStream which tokenizes all the text in the provided Reader.
|
* Creates a TokenStream which tokenizes all the text in the provided Reader.
|
||||||
*
|
*
|
||||||
* @return A TokenStream build from a StandardTokenizer filtered with
|
* @return A TokenStream build from a StandardTokenizer filtered with
|
||||||
* StandardFilter, StopFilter, GermanStemFilter and LowerCaseFilter
|
* StandardFilter, LowerCaseFilter, and StopFilter
|
||||||
*/
|
*/
|
||||||
public final TokenStream tokenStream( String fieldName, Reader reader ) {
|
public final TokenStream tokenStream( String fieldName, Reader reader ) {
|
||||||
TokenStream result = new StandardTokenizer( reader );
|
TokenStream result = new StandardTokenizer( reader );
|
||||||
|
|
|
@ -32,19 +32,19 @@ import java.util.Hashtable;
|
||||||
import java.util.Set;
|
import java.util.Set;
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Analyzer for french language. Supports an external list of stopwords (words that
|
* Analyzer for French language. Supports an external list of stopwords (words that
|
||||||
* will not be indexed at all) and an external list of exclusions (word that will
|
* will not be indexed at all) and an external list of exclusions (word that will
|
||||||
* not be stemmed, but indexed).
|
* not be stemmed, but indexed).
|
||||||
* A default set of stopwords is used unless an other list is specified, the
|
* A default set of stopwords is used unless an alternative list is specified, the
|
||||||
* exclusionlist is empty by default.
|
* exclusion list is empty by default.
|
||||||
*
|
*
|
||||||
* @author Patrick Talbot (based on Gerhard Schwarz work for German)
|
* @author Patrick Talbot (based on Gerhard Schwarz's work for German)
|
||||||
* @version $Id$
|
* @version $Id$
|
||||||
*/
|
*/
|
||||||
public final class FrenchAnalyzer extends Analyzer {
|
public final class FrenchAnalyzer extends Analyzer {
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Extended list of typical french stopwords.
|
* Extended list of typical French stopwords.
|
||||||
*/
|
*/
|
||||||
public final static String[] FRENCH_STOP_WORDS = {
|
public final static String[] FRENCH_STOP_WORDS = {
|
||||||
"a", "afin", "ai", "ainsi", "après", "attendu", "au", "aujourd", "auquel", "aussi",
|
"a", "afin", "ai", "ainsi", "après", "attendu", "au", "aujourd", "auquel", "aussi",
|
||||||
|
@ -142,7 +142,7 @@ public final class FrenchAnalyzer extends Analyzer {
|
||||||
public final TokenStream tokenStream(String fieldName, Reader reader) {
|
public final TokenStream tokenStream(String fieldName, Reader reader) {
|
||||||
|
|
||||||
if (fieldName == null) throw new IllegalArgumentException("fieldName must not be null");
|
if (fieldName == null) throw new IllegalArgumentException("fieldName must not be null");
|
||||||
if (reader == null) throw new IllegalArgumentException("readermust not be null");
|
if (reader == null) throw new IllegalArgumentException("reader must not be null");
|
||||||
|
|
||||||
TokenStream result = new StandardTokenizer(reader);
|
TokenStream result = new StandardTokenizer(reader);
|
||||||
result = new StandardFilter(result);
|
result = new StandardFilter(result);
|
||||||
|
|
Loading…
Reference in New Issue