[GitHub] [lucene] dweiss commented on a diff in pull request #11734: Fix repeating token sentence boundary bug

[GitBox <gi...@apache.org>]

dweiss commented on code in PR #11734:
URL: https://github.com/apache/lucene/pull/11734#discussion_r975127196


##########
lucene/analysis/opennlp/src/test/org/apache/lucene/analysis/opennlp/TestOpenNLPLemmatizerFilterFactory.java:
##########
@@ -290,4 +299,61 @@ public void testKeywordAttributeAwarenessDictionaryAndMaxEnt() throws Exception
         null,
         true);
   }
+
+  public void testNoBreakWithRepeatKeywordFilter() throws Exception {
+    CustomAnalyzer analyzer =
+        CustomAnalyzer.builder(new ClasspathResourceLoader(getClass()))
+            .withTokenizer(
+                "opennlp", "tokenizerModel", tokenizerModelFile, "sentenceModel", sentenceModelFile)
+            .addTokenFilter("opennlpPOS", "posTaggerModel", "en-test-pos-maxent.bin")
+            .addTokenFilter(KeywordRepeatFilterFactory.class)
+            .addTokenFilter("opennlplemmatizer", "dictionary", "en-test-lemmas.dict")
+            .build();
+    assertAnalyzesTo(
+        analyzer,
+        NO_BREAK_SINGLE_TOKEN_REPEAT_KEYWORD,
+        NO_BREAK_SINGLE_TOKEN_REPEAT_KEYWORD_terms,
+        null,
+        null,
+        null,
+        null,
+        null,
+        true);
+  }
+
+  public void testPreventEarlyExit() throws IOException {
+    ClasspathResourceLoader loader = new ClasspathResourceLoader(getClass());
+    InputStream earlyExitInput = loader.openResource("data/early-exit-bug-input.txt");

Review Comment:
   Can we add a try-with-finally around those opened resource streams? 



##########
lucene/analysis/opennlp/src/java/org/apache/lucene/analysis/opennlp/SentenceAttributeExtractor.java:
##########
@@ -0,0 +1,75 @@
+/*
+ * 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.lucene.analysis.opennlp;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.tokenattributes.SentenceAttribute;
+import org.apache.lucene.util.AttributeSource;
+
+/**
+ * Iterate through sentence tokens and cache their attributes. Could consider moving this to a more
+ * central location to be used by other sentence-aware components.
+ */
+public class SentenceAttributeExtractor {
+
+  private final TokenStream input;
+  private final SentenceAttribute sentenceAtt;
+  private final List<AttributeSource> sentenceTokenAttrs = new ArrayList<>();
+  private AttributeSource prevAttributeSource;
+  private int currSentence = 0;
+  private boolean hasNextToken = true;
+
+  public SentenceAttributeExtractor(TokenStream input, SentenceAttribute sentenceAtt) {
+    this.input = input;
+    this.sentenceAtt = sentenceAtt;
+  }
+
+  public List<AttributeSource> extractSentenceAttributes() throws IOException {
+    sentenceTokenAttrs.clear();
+    boolean hasNext;
+    do {
+      hasNextToken = input.incrementToken();
+      int currSentenceTmp = sentenceAtt.getSentenceIndex();
+      hasNext = currSentence == currSentenceTmp && hasNextToken;

Review Comment:
   ```suggestion
         hasNext = (currSentence == currSentenceTmp && hasNextToken);
   ```
   Makes it clearer to read.



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: issues-unsubscribe@lucene.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@lucene.apache.org
For additional commands, e-mail: issues-help@lucene.apache.org