支持elasticsearch-5.4.3

DejianYang · Oct 25, 2017 · cca78c7 · cca78c7
1 parent 66647fd
commit cca78c7
Show file tree

Hide file tree

Showing 10 changed files with 70 additions and 285 deletions.
diff --git a/pom.xml b/pom.xml
@@ -126,7 +126,7 @@
         <slf4j-api.version>1.6.4</slf4j-api.version>
         <logback-classic.version>0.9.28</logback-classic.version>
         <lucene.version>5.4.0</lucene.version>
-        <elasticsearch.version>2.1.1</elasticsearch.version>
+        <elasticsearch.version>5.4.3</elasticsearch.version>
         <jedis.version>2.5.1</jedis.version>
         <pinyin4j.version>2.5.0</pinyin4j.version>
   </properties>
@@ -241,44 +241,6 @@
             </exclusion>
         </exclusions>
     </dependency>
-    <!-- elasticsearch测试依赖 -->
-    <dependency>
-        <groupId>org.elasticsearch</groupId>
-        <artifactId>elasticsearch</artifactId>
-        <version>${elasticsearch.version}</version>
-        <type>test-jar</type>
-        <scope>test</scope>
-        <exclusions>
-            <exclusion>
-                <groupId>org.apache.lucene</groupId>
-                <artifactId>lucene-memory</artifactId>
-            </exclusion>
-            <exclusion>
-                <groupId>org.apache.lucene</groupId>
-                <artifactId>lucene-highlighter</artifactId>
-            </exclusion>
-            <exclusion>
-                <groupId>org.apache.lucene</groupId>
-                <artifactId>lucene-suggest</artifactId>
-            </exclusion>
-            <exclusion>
-                <groupId>org.apache.lucene</groupId>
-                <artifactId>lucene-misc</artifactId>
-            </exclusion>
-            <exclusion>
-                <groupId>org.apache.lucene</groupId>
-                <artifactId>lucene-join</artifactId>
-            </exclusion>
-            <exclusion>
-                <groupId>org.apache.lucene</groupId>
-                <artifactId>lucene-grouping</artifactId>
-            </exclusion>
-            <exclusion>
-                <groupId>org.apache.lucene</groupId>
-                <artifactId>lucene-spatial</artifactId>
-            </exclusion>
-        </exclusions>
-    </dependency>
     <!-- redis客户端库 -->
     <dependency>
         <groupId>redis.clients</groupId>

diff --git a/src/main/java/org/apdplat/word/elasticsearch/ChineseWordAnalysisBinderProcessor.java b/src/main/java/org/apdplat/word/elasticsearch/ChineseWordAnalysisBinderProcessor.java
diff --git a/src/main/java/org/apdplat/word/elasticsearch/ChineseWordAnalyzerProvider.java b/src/main/java/org/apdplat/word/elasticsearch/ChineseWordAnalyzerProvider.java
@@ -1,59 +1,39 @@
-/**
- * 
- * APDPlat - Application Product Development Platform
- * Copyright (c) 2013, 杨尚川, [email protected]
- * 
- * This program is free software: you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- * 
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- * 
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- * 
- */
-
 package org.apdplat.word.elasticsearch;
 
 import org.apdplat.word.lucene.ChineseWordAnalyzer;
 import org.apdplat.word.segmentation.Segmentation;
 import org.apdplat.word.segmentation.SegmentationAlgorithm;
 import org.apdplat.word.segmentation.SegmentationFactory;
-import org.elasticsearch.common.inject.Inject;
-import org.elasticsearch.common.inject.assistedinject.Assisted;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
-import org.elasticsearch.index.Index;
+import org.elasticsearch.index.IndexSettings;
 import org.elasticsearch.index.analysis.AbstractIndexAnalyzerProvider;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
 /**
- * 中文分析器工厂
- * @author 杨尚川
+ * Created by ysc on 25/10/2017.
  */
 public class ChineseWordAnalyzerProvider extends AbstractIndexAnalyzerProvider<ChineseWordAnalyzer> {
     private static final Logger LOGGER = LoggerFactory.getLogger(ChineseWordAnalyzerProvider.class);
+
     private final ChineseWordAnalyzer analyzer;
-    @Inject
-    public ChineseWordAnalyzerProvider(Index index, Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
-        super(index, indexSettings, name, settings);
+    private final Segmentation segmentation;
+
+    public ChineseWordAnalyzerProvider(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
+        super(indexSettings, name, settings);
         String segAlgorithm = settings.get("segAlgorithm");
         if(segAlgorithm != null){
-            LOGGER.info("analyzer使用指定分词算法："+segAlgorithm);
-            Segmentation segmentation = SegmentationFactory.getSegmentation(SegmentationAlgorithm.valueOf(segAlgorithm));
-            analyzer = new ChineseWordAnalyzer(segmentation);
+            LOGGER.info("tokenizer使用指定分词算法："+segAlgorithm);
+            segmentation = SegmentationFactory.getSegmentation(SegmentationAlgorithm.valueOf(segAlgorithm));
         }else{
-            LOGGER.info("没有为word analyzer指定segAlgorithm参数");
-            LOGGER.info("analyzer使用默认分词算法："+SegmentationAlgorithm.BidirectionalMaximumMatching);
-            analyzer = new ChineseWordAnalyzer();
+            LOGGER.info("没有为word tokenizer指定segAlgorithm参数");
+            LOGGER.info("tokenizer使用默认分词算法："+SegmentationAlgorithm.MaxNgramScore);
+            segmentation = SegmentationFactory.getSegmentation(SegmentationAlgorithm.MaxNgramScore);
         }
+        analyzer = new ChineseWordAnalyzer(segmentation);
     }
+
     @Override
     public ChineseWordAnalyzer get() {
         return this.analyzer;

diff --git a/src/main/java/org/apdplat/word/elasticsearch/ChineseWordIndicesAnalysis.java b/src/main/java/org/apdplat/word/elasticsearch/ChineseWordIndicesAnalysis.java
diff --git a/src/main/java/org/apdplat/word/elasticsearch/ChineseWordIndicesAnalysisModule.java b/src/main/java/org/apdplat/word/elasticsearch/ChineseWordIndicesAnalysisModule.java
diff --git a/src/main/java/org/apdplat/word/elasticsearch/ChineseWordNoOpTokenFilterFactory.java b/src/main/java/org/apdplat/word/elasticsearch/ChineseWordNoOpTokenFilterFactory.java
@@ -0,0 +1,22 @@
+package org.apdplat.word.elasticsearch;
+
+import org.apache.lucene.analysis.TokenStream;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.env.Environment;
+import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;
+
+/**
+ * Created by ysc on 25/10/2017.
+ */
+public class ChineseWordNoOpTokenFilterFactory extends AbstractTokenFilterFactory {
+
+    public ChineseWordNoOpTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
+        super(indexSettings, name, settings);
+    }
+
+    @Override
+    public TokenStream create(TokenStream tokenStream) {
+        return tokenStream;
+    }
+}