Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

convert to utf-8 

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@151009 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Daniel Naber 2004-08-18 14:30:48 +00:00
parent e7ae41ce23
commit 5ae03e4587
2 changed files with 21 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
sandbox/contributions/analyzers/src/java/org/apache/lucene/analysis/br/BrazilianStemFilter.java
View File

@ -66,7 +66,7 @@ import java.util.Set;
/**
* Based on (copied) the GermanStemFilter
*
* @author João Kramer
* @author João Kramer
* <p/>
* <p/>
* A filter that stemms german words. It supports a table of words that should

40
sandbox/contributions/analyzers/src/java/org/apache/lucene/analysis/br/BrazilianStemmer.java
View File

@ -56,7 +56,7 @@ package org.apache.lucene.analysis.br;
/**
* A stemmer for brazilian words. The algorithm is based on the report
* "A Fast and Simple Stemming Algorithm for German Words" by Jörg
* "A Fast and Simple Stemming Algorithm for German Words" by Jörg
* Caumanns (joerg.caumanns@isst.fhg.de).
*
* @author Gerhard Schwarz
@ -282,8 +282,8 @@ public class BrazilianStemmer {
/**
* 1) Turn to lowercase
* 2) Remove accents
* 3) ã -> a ; õ -> o
* 4) ç -> c
* 3) ã -> a ; õ -> o
* 4) ç -> c
*
* @return null or a string transformed
*/
@ -299,31 +299,31 @@ public class BrazilianStemmer {
value = value.toLowerCase() ;
for (j=0 ; j < value.length() ; j++) {
if ((value.charAt(j) == 'á') ||
(value.charAt(j) == 'â') ||
(value.charAt(j) == 'ã')) {
if ((value.charAt(j) == 'á') ||
(value.charAt(j) == 'â') ||
(value.charAt(j) == 'ã')) {
r= r + "a" ; continue ;
}
if ((value.charAt(j) == 'é') ||
(value.charAt(j) == 'ê')) {
if ((value.charAt(j) == 'é') ||
(value.charAt(j) == 'ê')) {
r= r + "e" ; continue ;
}
if (value.charAt(j) == 'í') {
if (value.charAt(j) == 'í') {
r= r + "i" ; continue ;
}
if ((value.charAt(j) == 'ó') ||
(value.charAt(j) == 'ô') ||
(value.charAt(j) == 'õ')) {
if ((value.charAt(j) == 'ó') ||
(value.charAt(j) == 'ô') ||
(value.charAt(j) == 'õ')) {
r= r + "o" ; continue ;
}
if ((value.charAt(j) == 'ú') ||
(value.charAt(j) == 'ü')) {
if ((value.charAt(j) == 'ú') ||
(value.charAt(j) == 'ü')) {
r= r + "u" ; continue ;
}
if (value.charAt(j) == 'ç') {
if (value.charAt(j) == 'ç') {
r= r + "c" ; continue ;
}
if (value.charAt(j) == 'ñ') {
if (value.charAt(j) == 'ñ') {
r= r + "n" ; continue ;
}
@ -410,7 +410,7 @@ public class BrazilianStemmer {
}
/**
* Creates CT (changed term) , substituting * 'ã' and 'õ' for 'a~' and 'o~'.
* Creates CT (changed term) , substituting * 'ã' and 'õ' for 'a~' and 'o~'.
*/
private void createCT( String term ) {
CT = changeTerm(term) ;
@ -1008,7 +1008,7 @@ public class BrazilianStemmer {
/**
* Residual suffix
*
* If the word ends with one of the suffixes (os a i o á í ó)
* If the word ends with one of the suffixes (os a i o á í ó)
* in RV, delete it
*
*/
@ -1031,11 +1031,11 @@ public class BrazilianStemmer {
}
/**
* If the word ends with one of ( e é ê) in RV,delete it,
* If the word ends with one of ( e é ê) in RV,delete it,
* and if preceded by 'gu' (or 'ci') with the 'u' (or 'i') in RV,
* delete the 'u' (or 'i')
*
* Or if the word ends ç remove the cedilha
* Or if the word ends ç remove the cedilha
*
*/
private void step5() {