From 14af0cb0f3640ac5773b5533f36d2cb0b76c9c8c Mon Sep 17 00:00:00 2001
From: Areek Zillur <areek.zillur@elasticsearch.com>
Date: Tue, 8 Jul 2014 11:36:58 -0400
Subject: [PATCH] Remove Lucene's deprecated PatternTokenizer

Instead of using the PatternTokenizer, the functionality was replicated by using Lucene's StopFilter, PatterTokenizer and LowerCaseFilter

Closes #6717
---
 .../analysis/PatternAnalyzerProvider.java     | 34 +++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

diff --git a/src/main/java/org/elasticsearch/index/analysis/PatternAnalyzerProvider.java b/src/main/java/org/elasticsearch/index/analysis/PatternAnalyzerProvider.java
index af053b3d47f..5acd1f23fa7 100644
--- a/src/main/java/org/elasticsearch/index/analysis/PatternAnalyzerProvider.java
+++ b/src/main/java/org/elasticsearch/index/analysis/PatternAnalyzerProvider.java
@@ -19,8 +19,12 @@
 
 package org.elasticsearch.index.analysis;
 
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.core.LowerCaseFilter;
 import org.apache.lucene.analysis.core.StopAnalyzer;
-import org.apache.lucene.analysis.miscellaneous.PatternAnalyzer;
+import org.apache.lucene.analysis.core.StopFilter;
+import org.apache.lucene.analysis.pattern.PatternTokenizer;
 import org.apache.lucene.analysis.util.CharArraySet;
 import org.elasticsearch.ElasticsearchIllegalArgumentException;
 import org.elasticsearch.Version;
@@ -33,15 +37,41 @@ import org.elasticsearch.env.Environment;
 import org.elasticsearch.index.Index;
 import org.elasticsearch.index.settings.IndexSettings;
 
+import java.io.Reader;
 import java.util.regex.Pattern;
 
 /**
  *
  */
-public class PatternAnalyzerProvider extends AbstractIndexAnalyzerProvider<PatternAnalyzer> {
+public class PatternAnalyzerProvider extends AbstractIndexAnalyzerProvider<Analyzer> {
 
     private final PatternAnalyzer analyzer;
 
+    private static final class PatternAnalyzer extends Analyzer {
+        private final org.apache.lucene.util.Version version;
+        private final Pattern pattern;
+        private final boolean lowercase;
+        private final CharArraySet stopWords;
+
+        PatternAnalyzer(org.apache.lucene.util.Version version, Pattern pattern, boolean lowercase, CharArraySet stopWords) {
+            this.version = version;
+            this.pattern = pattern;
+            this.lowercase = lowercase;
+            this.stopWords = stopWords;
+        }
+
+        @Override
+        protected TokenStreamComponents createComponents(String s, Reader reader) {
+            final TokenStreamComponents source = new TokenStreamComponents(new PatternTokenizer(reader, pattern, -1));
+            TokenStream result = null;
+            if (lowercase) {
+                 result = new LowerCaseFilter(version, source.getTokenStream());
+            }
+            result = new StopFilter(version, (result == null) ? source.getTokenStream() : result, stopWords);
+            return new TokenStreamComponents(source.getTokenizer(), result);
+        }
+    }
+
     @Inject
     public PatternAnalyzerProvider(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
         super(index, indexSettings, name, settings);