dnaber 2004/08/10 12:02:47
Modified: src/java/org/apache/lucene/analysis/de GermanStemmer.java
Log:
Bernhard's fix for 'ß' not being replaced at the end of a word + plus a small code
simplification by me
PR: 29931
Submitted by: Bernhard Messer
Revision Changes Path
1.12 +8 -6
jakarta-lucene/src/java/org/apache/lucene/analysis/de/GermanStemmer.java
Index: GermanStemmer.java
===================================================================
RCS file:
/home/cvs/jakarta-lucene/src/java/org/apache/lucene/analysis/de/GermanStemmer.java,v
retrieving revision 1.11
retrieving revision 1.12
diff -u -r1.11 -r1.12
--- GermanStemmer.java 30 May 2004 20:24:20 -0000 1.11
+++ GermanStemmer.java 10 Aug 2004 19:02:47 -0000 1.12
@@ -178,15 +178,16 @@
else if ( buffer.charAt( c ) == 'ü' ) {
buffer.setCharAt( c, 'u' );
}
- // Take care that at least one character is left left side from the current
one
- if ( c < buffer.length() - 1 ) {
- if ( buffer.charAt( c ) == 'ß' ) {
+ // Fix bug so that 'ß' at the end of a word is replaced.
+ else if ( buffer.charAt( c ) == 'ß' ) {
buffer.setCharAt( c, 's' );
buffer.insert( c + 1, 's' );
substCount++;
- }
+ }
+ // Take care that at least one character is left left side from the current
one
+ if ( c < buffer.length() - 1 ) {
// Masking several common character combinations with an token
- else if ( ( c < buffer.length() - 2 ) && buffer.charAt( c ) == 's' &&
+ if ( ( c < buffer.length() - 2 ) && buffer.charAt( c ) == 's' &&
buffer.charAt( c + 1 ) == 'c' && buffer.charAt( c + 2 ) == 'h' )
{
buffer.setCharAt( c, '$' );
@@ -260,4 +261,5 @@
}
}
}
+
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
