You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@jena.apache.org by ki...@apache.org on 2018/04/21 22:50:06 UTC
jena git commit: JENA-1488: add a selective folding analyzer
Repository: jena
Updated Branches:
refs/heads/master be6edc53d -> a56f7710d
JENA-1488: add a selective folding analyzer
Project: http://git-wip-us.apache.org/repos/asf/jena/repo
Commit: http://git-wip-us.apache.org/repos/asf/jena/commit/a56f7710
Tree: http://git-wip-us.apache.org/repos/asf/jena/tree/a56f7710
Diff: http://git-wip-us.apache.org/repos/asf/jena/diff/a56f7710
Branch: refs/heads/master
Commit: a56f7710d88e368824042863e1ebef9afc7fd5f3
Parents: be6edc5
Author: Bruno P. Kinoshita <ki...@users.noreply.github.com>
Authored: Mon Apr 9 21:38:14 2018 +1200
Committer: Bruno P. Kinoshita <ki...@users.noreply.github.com>
Committed: Sun Apr 22 10:42:21 2018 +1200
----------------------------------------------------------------------
.../text/filter/SelectiveFoldingFilter.java | 92 +++++++++++++
.../text/filter/TestSelectiveFoldingFilter.java | 134 +++++++++++++++++++
2 files changed, 226 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/jena/blob/a56f7710/jena-text/src/main/java/org/apache/jena/query/text/filter/SelectiveFoldingFilter.java
----------------------------------------------------------------------
diff --git a/jena-text/src/main/java/org/apache/jena/query/text/filter/SelectiveFoldingFilter.java b/jena-text/src/main/java/org/apache/jena/query/text/filter/SelectiveFoldingFilter.java
new file mode 100644
index 0000000..7483a06
--- /dev/null
+++ b/jena-text/src/main/java/org/apache/jena/query/text/filter/SelectiveFoldingFilter.java
@@ -0,0 +1,92 @@
+/**
+ * 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.
+ */
+
+package org.apache.jena.query.text.filter;
+
+import java.io.IOException;
+import java.util.Objects;
+
+import org.apache.lucene.analysis.CharArraySet;
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.util.ArrayUtil;
+
+/**
+ * A Lucene filter based on ASCIIFoldingFilter, but that allows the
+ * caller to provide a white list for selective folding filter. Entries in the
+ * white list are ignored during the filtering. This is useful for languages
+ * that require certain characters to be ignored.
+ *
+ * @link ASCIIFoldingFilter
+ */
+
+public final class SelectiveFoldingFilter extends TokenFilter {
+ /*
+ * text:defineFilter :selectiveFoldingFilter ;
+ * text:filter [
+ * a text:GenericFilter ;
+ * text:class "org.apache.jena.query.text.filter.SelectiveFoldingFilter" ;
+ * text:params (
+ * [
+ * text:paramName "whitelisted" ;
+ * text:paramType text:TypeSet ;
+ * text:paramValue ("ç" "á")
+ * ]
+ * )
+ * ]
+ */
+
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+
+ /**
+ * List of whitelisted characters.
+ */
+ private CharArraySet whitelisted;
+
+ public SelectiveFoldingFilter(TokenStream input, CharArraySet whitelisted) {
+ super(input);
+ Objects.requireNonNull(whitelisted, "You must provide the list of whiltelisted characters.");
+ this.whitelisted = CharArraySet.unmodifiableSet(CharArraySet.copy(whitelisted));
+ }
+
+ @Override
+ public boolean incrementToken() throws IOException {
+ if (input.incrementToken()) {
+ final char[] buffer = termAtt.buffer();
+ final int length = termAtt.length();
+ // prepare the output char array, adapted from ASCIIFoldingFilter
+ final int maxSizeNeeded = 4 * length;
+ char[] output = new char[ArrayUtil.oversize(maxSizeNeeded, Character.BYTES)];
+ for (int i = 0; i < length; ++i) {
+ final char c = buffer[i];
+ if (c >= '\u0080' && !whitelisted.contains(c)) {
+ // here we are using the method that will iterate always over a list with a
+ // single char
+ ASCIIFoldingFilter.foldToASCII(buffer, i, output, i, 1);
+ } else {
+ output[i] = c;
+ }
+ }
+ termAtt.copyBuffer(output, 0, length);
+ return true;
+ }
+ return false;
+ }
+}
http://git-wip-us.apache.org/repos/asf/jena/blob/a56f7710/jena-text/src/test/java/org/apache/jena/query/text/filter/TestSelectiveFoldingFilter.java
----------------------------------------------------------------------
diff --git a/jena-text/src/test/java/org/apache/jena/query/text/filter/TestSelectiveFoldingFilter.java b/jena-text/src/test/java/org/apache/jena/query/text/filter/TestSelectiveFoldingFilter.java
new file mode 100644
index 0000000..7d4a7ae
--- /dev/null
+++ b/jena-text/src/test/java/org/apache/jena/query/text/filter/TestSelectiveFoldingFilter.java
@@ -0,0 +1,134 @@
+/**
+ * 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.
+ */
+
+package org.apache.jena.query.text.filter;
+
+import static org.junit.Assert.assertTrue;
+
+import java.io.IOException;
+import java.io.StringReader;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.List;
+
+import org.apache.lucene.analysis.CharArraySet;
+import org.apache.lucene.analysis.standard.StandardTokenizer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.junit.Before;
+import org.junit.Test;
+
+/**
+ * Test {@link SelectiveFoldingFilter}.
+ */
+
+public class TestSelectiveFoldingFilter {
+
+ private StringReader inputText;
+ private CharArraySet whitelisted;
+
+ @Before
+ public void setUp() {
+ inputText = new StringReader("Señora Siobhán, look at that façade");
+ }
+
+ /**
+ * An empty white list means that the default behaviour of the Lucene's ASCIIFoldingFilter applies.
+ * @throws IOException from Lucene API
+ */
+ @Test
+ public void testEmptyWhiteListIsOkay() throws IOException {
+ whitelisted = new CharArraySet(Collections.emptyList(), false);
+ List<String> tokens = collectTokens(inputText, whitelisted);
+ List<String> expected = Arrays.asList("Senora", "Siobhan", "look", "at", "that", "facade");
+ assertTrue(tokens.equals(expected));
+ }
+
+ @Test
+ public void testSingleCharacterWhiteListed() throws IOException {
+ whitelisted = new CharArraySet(Arrays.asList("ç"), false);
+ List<String> tokens = collectTokens(inputText, whitelisted);
+ List<String> expected = Arrays.asList("Senora", "Siobhan", "look", "at", "that", "façade");
+ assertTrue(tokens.equals(expected));
+ }
+
+ @Test
+ public void testCompleteWhiteListed() throws IOException {
+ whitelisted = new CharArraySet(Arrays.asList("ñ", "á", "ç"), false);
+ List<String> tokens = collectTokens(inputText, whitelisted);
+ // here we should have the complete input
+ List<String> expected = Arrays.asList("Señora", "Siobhán", "look", "at", "that", "façade");
+ assertTrue(tokens.equals(expected));
+ }
+
+ @Test
+ public void testCaseMatters() throws IOException {
+ // note the first capital letter
+ whitelisted = new CharArraySet(Arrays.asList("Ñ", "á", "ç"), false);
+ List<String> tokens = collectTokens(inputText, whitelisted);
+ List<String> expected = Arrays.asList("Senora", "Siobhán", "look", "at", "that", "façade");
+ assertTrue(tokens.equals(expected));
+ }
+
+ @Test
+ public void testMismatchWhiteList() throws IOException {
+ whitelisted = new CharArraySet(Arrays.asList("ú", "ć", "ž"), false);
+ List<String> tokens = collectTokens(inputText, whitelisted);
+ List<String> expected = Arrays.asList("Senora", "Siobhan", "look", "at", "that", "facade");
+ assertTrue(tokens.equals(expected));
+ }
+
+ @Test(expected = NullPointerException.class)
+ public void testNullWhiteListThrowsError() throws IOException {
+ collectTokens(inputText, null);
+ }
+
+ @Test
+ public void testEmptyInput() throws IOException {
+ whitelisted = new CharArraySet(Arrays.asList("ç"), false);
+ inputText = new StringReader("");
+ List<String> tokens = collectTokens(inputText, whitelisted);
+ List<String> expected = Collections.emptyList();
+ assertTrue(tokens.equals(expected));
+ }
+
+ /**
+ * Return the list of CharTermAttribute converted to a list of String's.
+ *
+ * @param whitelisted white-list
+ * @return list of CharTermAttribute converted to a list of String's
+ * @throws IOException from Lucene API
+ */
+ private List<String> collectTokens(StringReader inputText, CharArraySet whitelisted) throws IOException {
+ StandardTokenizer tokenizer = new StandardTokenizer();
+ tokenizer.setReader(inputText);
+
+ SelectiveFoldingFilter selectiveFoldingFilter = new SelectiveFoldingFilter(tokenizer, whitelisted);
+
+ CharTermAttribute termAttrib = (CharTermAttribute) selectiveFoldingFilter.getAttribute(CharTermAttribute.class);
+
+ selectiveFoldingFilter.reset();
+ List<String> tokens = new ArrayList<>();
+ while (selectiveFoldingFilter.incrementToken()) {
+ tokens.add(termAttrib.toString());
+ }
+ selectiveFoldingFilter.end();
+ selectiveFoldingFilter.close();
+ return tokens;
+ }
+}