X-Git-Url: https://git.mdrn.pl/pylucene.git/blobdiff_plain/a2e61f0c04805cfcb8706176758d1283c7e3a55c..aaeed5504b982cf3545252ab528713250aa33eed:/lucene-java-3.5.0/lucene/src/java/org/apache/lucene/analysis/StopFilter.java diff --git a/lucene-java-3.5.0/lucene/src/java/org/apache/lucene/analysis/StopFilter.java b/lucene-java-3.5.0/lucene/src/java/org/apache/lucene/analysis/StopFilter.java new file mode 100644 index 0000000..bc19ac2 --- /dev/null +++ b/lucene-java-3.5.0/lucene/src/java/org/apache/lucene/analysis/StopFilter.java @@ -0,0 +1,265 @@ +package org.apache.lucene.analysis; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.IOException; +import java.util.Arrays; +import java.util.Set; +import java.util.List; + +import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; +import org.apache.lucene.queryParser.QueryParser; // for javadoc +import org.apache.lucene.util.Version; + +/** + * Removes stop words from a token stream. + * + * + *
You must specify the required {@link Version} + * compatibility when creating StopFilter: + *
stopWords
is an instance of {@link CharArraySet} (true if
+ * makeStopSet()
was used to construct the set) it will be directly used
+ * and ignoreCase
will be ignored since CharArraySet
+ * directly controls case sensitivity.
+ *
+ * If stopWords
is not an instance of {@link CharArraySet},
+ * a new CharArraySet will be constructed and ignoreCase
will be
+ * used to specify the case sensitivity of that set.
+ *
+ * @param enablePositionIncrements true if token positions should record the removed stop words
+ * @param input Input TokenStream
+ * @param stopWords A Set of Strings or char[] or any other toString()-able set representing the stopwords
+ * @param ignoreCase if true, all words are lower cased first
+ * @deprecated use {@link #StopFilter(Version, TokenStream, Set, boolean)} instead
+ */
+ @Deprecated
+ public StopFilter(boolean enablePositionIncrements, TokenStream input, Set> stopWords, boolean ignoreCase)
+ {
+ this(Version.LUCENE_30, enablePositionIncrements, input, stopWords, ignoreCase);
+ }
+
+ /**
+ * Construct a token stream filtering the given input. If
+ * stopWords
is an instance of {@link CharArraySet} (true if
+ * makeStopSet()
was used to construct the set) it will be
+ * directly used and ignoreCase
will be ignored since
+ * CharArraySet
directly controls case sensitivity.
+ *
+ * If stopWords
is not an instance of {@link CharArraySet}, a new
+ * CharArraySet will be constructed and ignoreCase
will be used
+ * to specify the case sensitivity of that set.
+ *
+ * @param matchVersion
+ * Lucene version to enable correct Unicode 4.0 behavior in the stop
+ * set if Version > 3.0. See above for details.
+ * @param input
+ * Input TokenStream
+ * @param stopWords
+ * A Set of Strings or char[] or any other toString()-able set
+ * representing the stopwords
+ * @param ignoreCase
+ * if true, all words are lower cased first
+ */
+ public StopFilter(Version matchVersion, TokenStream input, Set> stopWords, boolean ignoreCase)
+ {
+ this(matchVersion, matchVersion.onOrAfter(Version.LUCENE_29), input, stopWords, ignoreCase);
+ }
+
+ /*
+ * convenience ctor to enable deprecated ctors to set posInc explicitly
+ */
+ private StopFilter(Version matchVersion, boolean enablePositionIncrements, TokenStream input, Set> stopWords, boolean ignoreCase){
+ super(enablePositionIncrements, input);
+ this.stopWords = stopWords instanceof CharArraySet ? (CharArraySet)stopWords : new CharArraySet(matchVersion, stopWords, ignoreCase);
+ }
+
+ /**
+ * Constructs a filter which removes words from the input
+ * TokenStream that are named in the Set.
+ *
+ * @param enablePositionIncrements true if token positions should record the removed stop words
+ * @param in Input stream
+ * @param stopWords A Set of Strings or char[] or any other toString()-able set representing the stopwords
+ * @see #makeStopSet(Version, java.lang.String[])
+ * @deprecated use {@link #StopFilter(Version, TokenStream, Set)} instead
+ */
+ @Deprecated
+ public StopFilter(boolean enablePositionIncrements, TokenStream in, Set> stopWords) {
+ this(Version.LUCENE_30, enablePositionIncrements, in, stopWords, false);
+ }
+
+ /**
+ * Constructs a filter which removes words from the input TokenStream that are
+ * named in the Set.
+ *
+ * @param matchVersion
+ * Lucene version to enable correct Unicode 4.0 behavior in the stop
+ * set if Version > 3.0. See above for details.
+ * @param in
+ * Input stream
+ * @param stopWords
+ * A Set of Strings or char[] or any other toString()-able set
+ * representing the stopwords
+ * @see #makeStopSet(Version, java.lang.String[])
+ */
+ public StopFilter(Version matchVersion, TokenStream in, Set> stopWords) {
+ this(matchVersion, in, stopWords, false);
+ }
+
+ /**
+ * Builds a Set from an array of stop words,
+ * appropriate for passing into the StopFilter constructor.
+ * This permits this stopWords construction to be cached once when
+ * an Analyzer is constructed.
+ *
+ * @see #makeStopSet(Version, java.lang.String[], boolean) passing false to ignoreCase
+ * @deprecated use {@link #makeStopSet(Version, String...)} instead
+ */
+ @Deprecated
+ public static final Set