You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@lucene.apache.org by eh...@apache.org on 2004/03/12 10:45:17 UTC
cvs commit: jakarta-lucene/src/java/org/apache/lucene/analysis/de GermanAnalyzer.java
ehatcher 2004/03/12 01:45:17
Modified: src/java/org/apache/lucene/analysis/de GermanAnalyzer.java
Log:
format clean-up
Revision Changes Path
1.9 +96 -104 jakarta-lucene/src/java/org/apache/lucene/analysis/de/GermanAnalyzer.java
Index: GermanAnalyzer.java
===================================================================
RCS file: /home/cvs/jakarta-lucene/src/java/org/apache/lucene/analysis/de/GermanAnalyzer.java,v
retrieving revision 1.8
retrieving revision 1.9
diff -u -r1.8 -r1.9
--- GermanAnalyzer.java 12 Mar 2004 09:43:48 -0000 1.8
+++ GermanAnalyzer.java 12 Mar 2004 09:45:17 -0000 1.9
@@ -59,11 +59,12 @@
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
+
import java.io.File;
import java.io.Reader;
+import java.util.HashSet;
import java.util.Hashtable;
import java.util.Set;
-import java.util.HashSet;
/**
* Analyzer for German language. Supports an external list of stopwords (words that
@@ -72,108 +73,99 @@
* A default set of stopwords is used unless an alternative list is specified, the
* exclusion list is empty by default.
*
- * @author Gerhard Schwarz
- * @version $Id$
+ * @author Gerhard Schwarz
+ * @version $Id$
*/
-public class GermanAnalyzer extends Analyzer
-{
- /**
- * List of typical german stopwords.
- */
- private String[] GERMAN_STOP_WORDS = {
- "einer", "eine", "eines", "einem", "einen",
- "der", "die", "das", "dass", "da�",
- "du", "er", "sie", "es",
- "was", "wer", "wie", "wir",
- "und", "oder", "ohne", "mit",
- "am", "im", "in", "aus", "auf",
- "ist", "sein", "war", "wird",
- "ihr", "ihre", "ihres",
- "als", "f�r", "von", "mit",
- "dich", "dir", "mich", "mir",
- "mein", "sein", "kein",
- "durch", "wegen", "wird"
- };
-
- /**
- * Contains the stopwords used with the StopFilter.
- */
- private Set stopSet = new HashSet();
-
- /**
- * Contains words that should be indexed but not stemmed.
- */
- private Set exclusionSet = new HashSet();
-
- /**
- * Builds an analyzer.
- */
- public GermanAnalyzer()
- {
- stopSet = StopFilter.makeStopSet( GERMAN_STOP_WORDS );
- }
-
- /**
- * Builds an analyzer with the given stop words.
- */
- public GermanAnalyzer( String[] stopwords )
- {
- stopSet = StopFilter.makeStopSet( stopwords );
- }
-
- /**
- * Builds an analyzer with the given stop words.
- */
- public GermanAnalyzer( Hashtable stopwords )
- {
- stopSet = new HashSet(stopwords.keySet());
- }
-
- /**
- * Builds an analyzer with the given stop words.
- */
- public GermanAnalyzer( File stopwords )
- {
- stopSet = new HashSet(WordlistLoader.getWordtable( stopwords ).keySet());
- }
-
- /**
- * Builds an exclusionlist from an array of Strings.
- */
- public void setStemExclusionTable( String[] exclusionlist )
- {
- exclusionSet = StopFilter.makeStopSet( exclusionlist );
- }
-
- /**
- * Builds an exclusionlist from a Hashtable.
- */
- public void setStemExclusionTable( Hashtable exclusionlist )
- {
- exclusionSet = new HashSet(exclusionlist.keySet());
- }
-
- /**
- * Builds an exclusionlist from the words contained in the given file.
- */
- public void setStemExclusionTable( File exclusionlist )
- {
- exclusionSet = new HashSet(WordlistLoader.getWordtable( exclusionlist ).keySet());
- }
-
- /**
- * Creates a TokenStream which tokenizes all the text in the provided Reader.
- *
- * @return A TokenStream build from a StandardTokenizer filtered with
- * StandardFilter, StopFilter, GermanStemFilter
- */
- public TokenStream tokenStream( String fieldName, Reader reader )
- {
- TokenStream result = new StandardTokenizer( reader );
- result = new StandardFilter( result );
- // shouldn't there be a lowercaser before stop word filtering?
- result = new StopFilter( result, stopSet );
- result = new GermanStemFilter( result, exclusionSet );
- return result;
- }
+public class GermanAnalyzer extends Analyzer {
+ /**
+ * List of typical german stopwords.
+ */
+ private String[] GERMAN_STOP_WORDS = {
+ "einer", "eine", "eines", "einem", "einen",
+ "der", "die", "das", "dass", "da�",
+ "du", "er", "sie", "es",
+ "was", "wer", "wie", "wir",
+ "und", "oder", "ohne", "mit",
+ "am", "im", "in", "aus", "auf",
+ "ist", "sein", "war", "wird",
+ "ihr", "ihre", "ihres",
+ "als", "f�r", "von", "mit",
+ "dich", "dir", "mich", "mir",
+ "mein", "sein", "kein",
+ "durch", "wegen", "wird"
+ };
+
+ /**
+ * Contains the stopwords used with the StopFilter.
+ */
+ private Set stopSet = new HashSet();
+
+ /**
+ * Contains words that should be indexed but not stemmed.
+ */
+ private Set exclusionSet = new HashSet();
+
+ /**
+ * Builds an analyzer.
+ */
+ public GermanAnalyzer() {
+ stopSet = StopFilter.makeStopSet(GERMAN_STOP_WORDS);
+ }
+
+ /**
+ * Builds an analyzer with the given stop words.
+ */
+ public GermanAnalyzer(String[] stopwords) {
+ stopSet = StopFilter.makeStopSet(stopwords);
+ }
+
+ /**
+ * Builds an analyzer with the given stop words.
+ */
+ public GermanAnalyzer(Hashtable stopwords) {
+ stopSet = new HashSet(stopwords.keySet());
+ }
+
+ /**
+ * Builds an analyzer with the given stop words.
+ */
+ public GermanAnalyzer(File stopwords) {
+ stopSet = new HashSet(WordlistLoader.getWordtable(stopwords).keySet());
+ }
+
+ /**
+ * Builds an exclusionlist from an array of Strings.
+ */
+ public void setStemExclusionTable(String[] exclusionlist) {
+ exclusionSet = StopFilter.makeStopSet(exclusionlist);
+ }
+
+ /**
+ * Builds an exclusionlist from a Hashtable.
+ */
+ public void setStemExclusionTable(Hashtable exclusionlist) {
+ exclusionSet = new HashSet(exclusionlist.keySet());
+ }
+
+ /**
+ * Builds an exclusionlist from the words contained in the given file.
+ */
+ public void setStemExclusionTable(File exclusionlist) {
+ exclusionSet = new HashSet(WordlistLoader.getWordtable(exclusionlist).keySet());
+ }
+
+ /**
+ * Creates a TokenStream which tokenizes all the text in the provided Reader.
+ *
+ * @return A TokenStream build from a StandardTokenizer filtered with
+ * StandardFilter, StopFilter, GermanStemFilter
+ */
+ public TokenStream tokenStream(String fieldName, Reader reader) {
+ TokenStream result = new StandardTokenizer(reader);
+ result = new StandardFilter(result);
+// shouldn't there be a lowercaser before stop word filtering?
+ result = new StopFilter(result, stopSet);
+ result = new GermanStemFilter(result, exclusionSet);
+ return result;
+ }
}
---------------------------------------------------------------------
To unsubscribe, e-mail: lucene-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: lucene-dev-help@jakarta.apache.org