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

LUCENE-3400: Removed DutchAnalyzer.setStemDictionary 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1161484 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Christopher John Male 2011-08-25 10:32:21 +00:00
parent a05f774573
commit 1057d24e7f
3 changed files with 4 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modules/analysis/CHANGES.txt
View File

@ -31,6 +31,8 @@ API Changes
* LUCENE-2514, LUCENE-2551: JDK and ICU CollationKeyAnalyzers were changed to
use pure byte keys when Version >= 4.0. This cuts sort key size approximately
in half. (Robert Muir)
* LUCENE-3400: Removed DutchAnalyzer.setStemDictionary (Chris Male)
New Features

20
modules/analysis/common/src/java/org/apache/lucene/analysis/nl/DutchAnalyzer.java
View File

@ -105,7 +105,7 @@ public final class DutchAnalyzer extends ReusableAnalyzerBase {
*/
private Set<?> excltable = Collections.emptySet();
private Map<String, String> stemdict = new HashMap<String, String>();
private final Map<String, String> stemdict = new HashMap<String, String>();
private final Version matchVersion;
/**
@ -130,23 +130,7 @@ public final class DutchAnalyzer extends ReusableAnalyzerBase {
excltable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionTable));
this.matchVersion = matchVersion;
}
/**
* Reads a stemdictionary file , that overrules the stemming algorithm
* This is a textfile that contains per line
* <tt>word<b>\t</b>stem</tt>, i.e: two tab seperated words
*/
public void setStemDictionary(File stemdictFile) {
try {
stemdict = WordlistLoader.getStemDict(stemdictFile);
setPreviousTokenStream(null); // force a new stemmer to be created
} catch (IOException e) {
// TODO: throw IOException
throw new RuntimeException(e);
}
}
/**
* Returns a (possibly reused) {@link TokenStream} which tokenizes all the
* text in the provided {@link Reader}.

12
modules/analysis/common/src/test/org/apache/lucene/analysis/nl/TestDutchStemmer.java
View File

@ -150,18 +150,6 @@ public class TestDutchStemmer extends BaseTokenStreamTestCase {
}
/*
* Test that changes to the dictionary stemming table are applied immediately
* when using reusable token streams.
*/
public void testStemDictionaryReuse() throws Exception {
DutchAnalyzer a = new DutchAnalyzer(TEST_VERSION_CURRENT);
checkOneTermReuse(a, "lichamelijk", "licham");
File customDictFile = getDataFile("customStemDict.txt");
a.setStemDictionary(customDictFile);
checkOneTermReuse(a, "lichamelijk", "somethingentirelydifferent");
}
/**
* Prior to 3.1, this analyzer had no lowercase filter.
* stopwords were case sensitive. Preserve this for back compat.