You are viewing a plain text version of this content. The canonical link for it is here.
Posted to java-commits@lucene.apache.org by dn...@apache.org on 2005/05/28 01:00:50 UTC
svn commit: r178832 - in
/lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis:
KeywordAnalyzer.java br/BrazilianAnalyzer.java cz/CzechAnalyzer.java
fr/FrenchAnalyzer.java
Author: dnaber
Date: Fri May 27 16:00:49 2005
New Revision: 178832
URL: http://svn.apache.org/viewcvs?rev=178832&view=rev
Log:
small javadoc fixes
Modified:
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/KeywordAnalyzer.java
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java
Modified: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/KeywordAnalyzer.java
URL: http://svn.apache.org/viewcvs/lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/KeywordAnalyzer.java?rev=178832&r1=178831&r2=178832&view=diff
==============================================================================
--- lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/KeywordAnalyzer.java (original)
+++ lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/KeywordAnalyzer.java Fri May 27 16:00:49 2005
@@ -19,7 +19,8 @@
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 TokenStream tokenStream(String fieldName,
Modified: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java
URL: http://svn.apache.org/viewcvs/lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java?rev=178832&r1=178831&r2=178832&view=diff
==============================================================================
--- lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java (original)
+++ lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java Fri May 27 16:00:49 2005
@@ -31,16 +31,16 @@
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
* not be stemmed, but indexed).
*
- * @author Jo�o Kramer
+ * @author João Kramer
*/
public final class BrazilianAnalyzer extends Analyzer {
/**
- * List of typical german stopwords.
+ * List of typical Brazilian stopwords.
*/
public final static String[] BRAZILIAN_STOP_WORDS = {
"a","ainda","alem","ambas","ambos","antes",
@@ -68,6 +68,7 @@
* Contains the stopwords used with the StopFilter.
*/
private Set stoptable = new HashSet();
+
/**
* Contains words that should be indexed but not stemmed.
*/
Modified: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java
URL: http://svn.apache.org/viewcvs/lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java?rev=178832&r1=178831&r2=178832&view=diff
==============================================================================
--- lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java (original)
+++ lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java Fri May 27 16:00:49 2005
@@ -105,7 +105,7 @@
/**
* Loads stopwords hash from resource stream (file, database...).
* @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 ) {
if ( wordfile == null ) {
@@ -122,7 +122,6 @@
else
isr = new InputStreamReader(wordfile, encoding);
-
LineNumberReader lnr = new LineNumberReader(isr);
String word;
while ( ( word = lnr.readLine() ) != null ) {
@@ -138,7 +137,7 @@
* Creates a TokenStream which tokenizes all the text in the provided Reader.
*
* @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 ) {
TokenStream result = new StandardTokenizer( reader );
Modified: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java
URL: http://svn.apache.org/viewcvs/lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java?rev=178832&r1=178831&r2=178832&view=diff
==============================================================================
--- lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java (original)
+++ lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java Fri May 27 16:00:49 2005
@@ -32,19 +32,19 @@
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
* not be stemmed, but indexed).
- * A default set of stopwords is used unless an other list is specified, the
- * exclusionlist is empty by default.
+ * A default set of stopwords is used unless an alternative list is specified, the
+ * 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 $Id$
*/
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 = {
"a", "afin", "ai", "ainsi", "après", "attendu", "au", "aujourd", "auquel", "aussi",
@@ -142,7 +142,7 @@
public final TokenStream tokenStream(String fieldName, Reader reader) {
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);
result = new StandardFilter(result);