[GitHub] [lucene-solr] dweiss commented on a change in pull request #2217: LUCENE-9676: Hunspell: improve stemming of all-caps words

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

dweiss commented on a change in pull request #2217:
URL: https://github.com/apache/lucene-solr/pull/2217#discussion_r559806181



##########
File path: lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/Dictionary.java
##########
@@ -74,6 +74,8 @@
 
   static final char[] NOFLAGS = new char[0];
 
+  private static final char HIDDEN_FLAG = (char) 65511; // called 'ONLYUPCASEFLAG' in Hunspell

Review comment:
       I think you could use an explicit char here? '\uFFE7'? Not sure though because this isn't valid unicode so some validation tools may complain later on... Let's leave it.

##########
File path: lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/WordCase.java
##########
@@ -0,0 +1,59 @@
+/*
+ * 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.hunspell;
+
+enum WordCase {
+  UPPER,
+  TITLE,
+  LOWER,
+  MIXED;
+
+  static WordCase caseOf(char[] word, int length) {
+    boolean capitalized = Character.isUpperCase(word[0]);
+
+    boolean seenUpper = false;
+    boolean seenLower = false;
+    for (int i = 1; i < length; i++) {
+      char ch = word[i];
+      seenUpper = seenUpper || Character.isUpperCase(ch);
+      seenLower = seenLower || Character.isLowerCase(ch);
+    }
+
+    return get(capitalized, seenUpper, seenLower);
+  }
+
+  static WordCase caseOf(CharSequence word, int length) {
+    boolean capitalized = Character.isUpperCase(word.charAt(0));
+
+    boolean seenUpper = false;
+    boolean seenLower = false;
+    for (int i = 1; i < length; i++) {

Review comment:
       don't know if this makes much sense to optimize but you could break the loop too if (seenLower || seenUpper) as checking further on doesn't make sense.




----------------------------------------------------------------
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.

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