update to support es 2.0

Author: medcl

README.md

@@ -3,16 +3,15 @@ IK Analysis for ElasticSearch
 
 The IK Analysis plugin integrates Lucene IK analyzer into elasticsearch, support customized dictionary.
 
-Tokenizer: `ik`
-
-更新：对于使用 ES 集群，用 IK 作为分词插件，经常会修改自定义词典的使用者，可以透过远程加载的方式，每次更新都会重新加载词典，不必重启 ES 服务。
+Analyzer: `ik_smart` , `ik_max_word` , Tokenizer: `ik_smart` , `ik_max_word` 
 
 Versions
 --------
 
 IK version | ES version
 -----------|-----------
-master | 1.5.0 -> master
+master | 2.0.0 -> master
+1.5.0 | 2.0.0
 1.4.1 | 1.7.2
 1.4.0 | 1.6.0
 1.3.0 | 1.5.0
@@ -30,108 +29,42 @@ master | 1.5.0 -> master
 Install
 -------
 
-you can download this plugin from RTF project(https://github.com/medcl/elasticsearch-rtf)
-https://github.com/medcl/elasticsearch-rtf/tree/master/plugins/analysis-ik
-https://github.com/medcl/elasticsearch-rtf/tree/master/config/ik
-
-<del>also remember to download the dict files,unzip these dict file into your elasticsearch's config folder,such as: your-es-root/config/ik</del>
-
-you need a service restart after that!
-
-Configuration
--------------
-
-### Analysis Configuration
-
-#### `elasticsearch.yml`
-
-```yaml
-index:
-  analysis:
-    analyzer:
-      ik:
-          alias: [ik_analyzer]
-          type: org.elasticsearch.index.analysis.IkAnalyzerProvider
-      ik_max_word:
-          type: ik
-          use_smart: false
-      ik_smart:
-          type: ik
-          use_smart: true
-```
-
-Or
-
-```yaml
-index.analysis.analyzer.ik.type : "ik"
-```
-
-#### 以上两种配置方式的区别：
+1.compile
 
-1、第二种方式，只定义了一个名为 ik 的 analyzer，其 use_smart 采用默认值 false
+`mvn package`
 
-2、第一种方式，定义了三个 analyzer，分别为：ik、ik_max_word、ik_smart，其中 ik_max_word 和 ik_smart 是基于 ik 这个 analyzer 定义的，并各自明确设置了 use_smart 的不同值。
+copy and unzip `target/release/ik**.zip` to `your-es-root/plugins/ik`
 
-3、其实，ik_max_word 等同于 ik。ik_max_word 会将文本做最细粒度的拆分，比如会将“中华人民共和国国歌”拆分为“中华人民共和国,中华人民,中华,华人,人民共和国,人民,人,民,共和国,共和,和,国国,国歌”，会穷尽各种可能的组合；而 ik_smart 会做最粗粒度的拆分，比如会将“中华人民共和国国歌”拆分为“中华人民共和国,国歌”。
+2.config files:
 
-因此，建议，在设置 mapping 时，用 ik 这个 analyzer，以尽可能地被搜索条件匹配到。
+download the dict files,unzip these dict file into your elasticsearch's config folder,such as: `your-es-root/config/ik`
 
-不过，如果你想将 /index_name/_analyze 这个 RESTful API 做为分词器用，用来提取某段文字中的主题词，则建议使用 ik_smart 这个 analyzer：
+3.restart elasticsearch
 
-```
-POST /hailiang/_analyze?analyzer=ik_smart HTTP/1.1
-Host: localhost:9200
-Cache-Control: no-cache
-
-中华人民共和国国歌
-```
-
-返回值：
-
-```json
-{
-  "tokens" : [ {
-    "token" : "中华人民共和国",
-    "start_offset" : 0,
-    "end_offset" : 7,
-    "type" : "CN_WORD",
-    "position" : 1
-  }, {
-    "token" : "国歌",
-    "start_offset" : 7,
-    "end_offset" : 9,
-    "type" : "CN_WORD",
-    "position" : 2
-  } ]
-}
-```
+Tips:
 
-另外，可以在 elasticsearch.yml 里加上如下一行，设置默认的 analyzer 为 ik：
-
-```yaml
-index.analysis.analyzer.default.type : "ik"
-```
+ik_max_word: 会将文本做最细粒度的拆分，比如会将“中华人民共和国国歌”拆分为“中华人民共和国,中华人民,中华,华人,人民共和国,人民,人,民,共和国,共和,和,国国,国歌”，会穷尽各种可能的组合；
 
+ik_smart: 会做最粗粒度的拆分，比如会将“中华人民共和国国歌”拆分为“中华人民共和国,国歌”。
 
-### Mapping Configuration
 
 #### Quick Example
 
-1. create a index
+1.create a index
 
 ```bash
 curl -XPUT http://localhost:9200/index
 ```
 
-2. create a mapping
+2.create a mapping
 
 ```bash
 curl -XPOST http://localhost:9200/index/fulltext/_mapping -d'
 {
     "fulltext": {
              "_all": {
-            "indexAnalyzer": "ik",
-            "searchAnalyzer": "ik",
+            "indexAnalyzer": "ik_max_word",
+            "searchAnalyzer": "ik_max_word",
             "term_vector": "no",
             "store": "false"
         },
@@ -140,8 +73,8 @@ curl -XPOST http://localhost:9200/index/fulltext/_mapping -d'
                 "type": "string",
                 "store": "no",
                 "term_vector": "with_positions_offsets",
-                "indexAnalyzer": "ik",
-                "searchAnalyzer": "ik",
+                "indexAnalyzer": "ik_max_word",
+                "searchAnalyzer": "ik_max_word",
                 "include_in_all": "true",
                 "boost": 8
             }
@@ -150,7 +83,7 @@ curl -XPOST http://localhost:9200/index/fulltext/_mapping -d'
 }'
 ```
 
-3. index some docs
+3.index some docs
 
 ```bash
 curl -XPOST http://localhost:9200/index/fulltext/1 -d'
@@ -176,7 +109,7 @@ curl -XPOST http://localhost:9200/index/fulltext/4 -d'
 '
 ```
 
-4. query with highlighting
+4.query with highlighting
 
 ```bash
 curl -XPOST http://localhost:9200/index/fulltext/_search  -d'
@@ -193,7 +126,7 @@ curl -XPOST http://localhost:9200/index/fulltext/_search  -d'
 '
 ```
 
-#### Result
+Result
 
 ```json
 {
@@ -257,7 +190,7 @@ curl -XPOST http://localhost:9200/index/fulltext/_search  -d'
  	<!--用户可以在这里配置远程扩展字典 -->
 	<entry key="remote_ext_dict">location</entry>
  	<!--用户可以在这里配置远程扩展停止词字典-->
-	<entry key="remote_ext_stopwords">location</entry>
+	<entry key="remote_ext_stopwords">http://xxx.com/xxx.dic</entry>
 </properties>
 ```
 

pom.xml

@@ -6,17 +6,29 @@
     <modelVersion>4.0.0</modelVersion>
     <groupId>org.elasticsearch</groupId>
     <artifactId>elasticsearch-analysis-ik</artifactId>
-    <version>1.4.1</version>
+    <version>1.5.0</version>
     <packaging>jar</packaging>
     <description>IK Analyzer for ElasticSearch</description>
     <inceptionYear>2009</inceptionYear>
+
+    <properties>
+        <elasticsearch.version>2.0.0</elasticsearch.version>
+
+        <elasticsearch.assembly.descriptor>${project.basedir}/src/main/assemblies/plugin.xml</elasticsearch.assembly.descriptor>
+        <elasticsearch.plugin.classname>org.elasticsearch.plugin.analysis.ik.AnalysisIkPlugin</elasticsearch.plugin.classname>
+        <elasticsearch.plugin.jvm>true</elasticsearch.plugin.jvm>
+        <tests.rest.load_packaged>false</tests.rest.load_packaged>
+        <skip.unit.tests>true</skip.unit.tests>
+    </properties>
+
     <licenses>
         <license>
             <name>The Apache Software License, Version 2.0</name>
             <url>http://www.apache.org/licenses/LICENSE-2.0.txt</url>
             <distribution>repo</distribution>
         </license>
     </licenses>
+
     <scm>
         <connection>scm:git:[email protected]:medcl/elasticsearch-analysis-ik.git</connection>
         <developerConnection>scm:git:[email protected]:medcl/elasticsearch-analysis-ik.git
@@ -30,10 +42,6 @@
         <version>7</version>
     </parent>
 
-    <properties>
-        <elasticsearch.version>1.7.2</elasticsearch.version>
-    </properties>
-
   <repositories>
         <repository>
             <id>oss.sonatype.org</id>
@@ -84,11 +92,6 @@
             <version>4.10</version>
             <scope>test</scope>
         </dependency>
-        <dependency>
-            <groupId>org.apache.lucene</groupId>
-            <artifactId>lucene-core</artifactId>
-            <version>4.10.4</version>
-        </dependency>
     </dependencies>
 
     <build>
@@ -137,9 +140,6 @@
                             <mainClass>fully.qualified.MainClass</mainClass>
                         </manifest>
                     </archive>
-                    <descriptorRefs>
-                        <descriptorRef>jar-with-dependencies</descriptorRef>
-                    </descriptorRefs>
                 </configuration>
                 <executions>
                     <execution>

src/main/assemblies/plugin.xml

@@ -5,6 +5,13 @@
         <format>zip</format>
     </formats>
     <includeBaseDirectory>false</includeBaseDirectory>
+    <files>
+        <file>
+            <source>${project.basedir}/src/main/resources/plugin-descriptor.properties</source>
+            <outputDirectory></outputDirectory>
+            <filtered>true</filtered>
+        </file>
+    </files>
     <dependencySets>
         <dependencySet>
             <outputDirectory>/</outputDirectory>

src/main/config/ik.yaml

@@ -3,20 +3,21 @@
 
 public class IkAnalysisBinderProcessor extends AnalysisModule.AnalysisBinderProcessor {
 
-    @Override public void processTokenFilters(TokenFiltersBindings tokenFiltersBindings) {
+
+    @Override
+    public void processTokenFilters(TokenFiltersBindings tokenFiltersBindings) {
 
     }
 
 
-    @Override public void processAnalyzers(AnalyzersBindings analyzersBindings) {
+    @Override
+    public void processAnalyzers(AnalyzersBindings analyzersBindings) {
         analyzersBindings.processAnalyzer("ik", IkAnalyzerProvider.class);
-        super.processAnalyzers(analyzersBindings);
     }
 
 
     @Override
     public void processTokenizers(TokenizersBindings tokenizersBindings) {
-      tokenizersBindings.processTokenizer("ik", IkTokenizerFactory.class);
-      super.processTokenizers(tokenizersBindings);
+        tokenizersBindings.processTokenizer("ik_tokenizer", IkTokenizerFactory.class);
     }
 }

src/main/java/org/elasticsearch/index/analysis/IkAnalysisBinderProcessor.java

@@ -1,7 +1,6 @@
 package org.elasticsearch.index.analysis;
 
 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;
@@ -12,12 +11,14 @@
 
 public class IkAnalyzerProvider extends AbstractIndexAnalyzerProvider<IKAnalyzer> {
     private final IKAnalyzer analyzer;
+    private boolean useSmart=false;
 
     @Inject
-    public IkAnalyzerProvider(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
+    public IkAnalyzerProvider(Index index, @IndexSettings Settings indexSettings,Environment env, String name, Settings settings) {
         super(index, indexSettings, name, settings);
         Dictionary.initial(new Configuration(env));
-        analyzer=new IKAnalyzer(indexSettings, settings, env);
+        useSmart = settings.get("use_smart", "false").equals("true");
+        analyzer=new IKAnalyzer(useSmart);
     }
 
     @Override public IKAnalyzer get() {

src/main/java/org/elasticsearch/index/analysis/IkAnalyzerProvider.java

@@ -11,23 +11,21 @@
 import org.wltea.analyzer.dic.Dictionary;
 import org.wltea.analyzer.lucene.IKTokenizer;
 
-import java.io.Reader;
-
 public class IkTokenizerFactory extends AbstractTokenizerFactory {
-  private Environment environment;
-  private Settings settings;
+  private final Settings settings;
+  private boolean useSmart=false;
 
   @Inject
   public IkTokenizerFactory(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
 	  super(index, indexSettings, name, settings);
-	  this.environment = env;
-	  this.settings = settings;
+      this.settings=settings;
 	  Dictionary.initial(new Configuration(env));
   }
 
+
   @Override
-  public Tokenizer create(Reader reader) {
-	  return new IKTokenizer(reader, settings, environment);
-  }
+  public Tokenizer create() {
+    this.useSmart = settings.get("use_smart", "false").equals("true");
 
+    return new IKTokenizer(useSmart);  }
 }