support es 5.0.0-alpha5

Author: medcl

licenses/lucene-LICENSE.txt

@@ -0,0 +1,191 @@
+Apache Lucene
+Copyright 2014 The Apache Software Foundation
+
+This product includes software developed at
+The Apache Software Foundation (http://www.apache.org/).
+
+Includes software from other Apache Software Foundation projects,
+including, but not limited to:
+ - Apache Ant
+ - Apache Jakarta Regexp
+ - Apache Commons
+ - Apache Xerces
+
+ICU4J, (under analysis/icu) is licensed under an MIT styles license
+and Copyright (c) 1995-2008 International Business Machines Corporation and others
+
+Some data files (under analysis/icu/src/data) are derived from Unicode data such
+as the Unicode Character Database. See http://unicode.org/copyright.html for more
+details.
+
+Brics Automaton (under core/src/java/org/apache/lucene/util/automaton) is 
+BSD-licensed, created by Anders Møller. See http://www.brics.dk/automaton/
+
+The levenshtein automata tables (under core/src/java/org/apache/lucene/util/automaton) were
+automatically generated with the moman/finenight FSA library, created by
+Jean-Philippe Barrette-LaPierre. This library is available under an MIT license,
+see http://sites.google.com/site/rrettesite/moman and 
+http://bitbucket.org/jpbarrette/moman/overview/
+
+The class org.apache.lucene.util.WeakIdentityMap was derived from
+the Apache CXF project and is Apache License 2.0.
+
+The Google Code Prettify is Apache License 2.0.
+See http://code.google.com/p/google-code-prettify/
+
+JUnit (junit-4.10) is licensed under the Common Public License v. 1.0
+See http://junit.sourceforge.net/cpl-v10.html
+
+This product includes code (JaspellTernarySearchTrie) from Java Spelling Checkin
+g Package (jaspell): http://jaspell.sourceforge.net/
+License: The BSD License (http://www.opensource.org/licenses/bsd-license.php)
+
+The snowball stemmers in
+  analysis/common/src/java/net/sf/snowball
+were developed by Martin Porter and Richard Boulton.
+The snowball stopword lists in
+  analysis/common/src/resources/org/apache/lucene/analysis/snowball
+were developed by Martin Porter and Richard Boulton.
+The full snowball package is available from
+  http://snowball.tartarus.org/
+
+The KStem stemmer in
+  analysis/common/src/org/apache/lucene/analysis/en
+was developed by Bob Krovetz and Sergio Guzman-Lara (CIIR-UMass Amherst)
+under the BSD-license.
+
+The Arabic,Persian,Romanian,Bulgarian, and Hindi analyzers (common) come with a default
+stopword list that is BSD-licensed created by Jacques Savoy.  These files reside in:
+analysis/common/src/resources/org/apache/lucene/analysis/ar/stopwords.txt,
+analysis/common/src/resources/org/apache/lucene/analysis/fa/stopwords.txt,
+analysis/common/src/resources/org/apache/lucene/analysis/ro/stopwords.txt,
+analysis/common/src/resources/org/apache/lucene/analysis/bg/stopwords.txt,
+analysis/common/src/resources/org/apache/lucene/analysis/hi/stopwords.txt
+See http://members.unine.ch/jacques.savoy/clef/index.html.
+
+The German,Spanish,Finnish,French,Hungarian,Italian,Portuguese,Russian and Swedish light stemmers
+(common) are based on BSD-licensed reference implementations created by Jacques Savoy and
+Ljiljana Dolamic. These files reside in:
+analysis/common/src/java/org/apache/lucene/analysis/de/GermanLightStemmer.java
+analysis/common/src/java/org/apache/lucene/analysis/de/GermanMinimalStemmer.java
+analysis/common/src/java/org/apache/lucene/analysis/es/SpanishLightStemmer.java
+analysis/common/src/java/org/apache/lucene/analysis/fi/FinnishLightStemmer.java
+analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchLightStemmer.java
+analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchMinimalStemmer.java
+analysis/common/src/java/org/apache/lucene/analysis/hu/HungarianLightStemmer.java
+analysis/common/src/java/org/apache/lucene/analysis/it/ItalianLightStemmer.java
+analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseLightStemmer.java
+analysis/common/src/java/org/apache/lucene/analysis/ru/RussianLightStemmer.java
+analysis/common/src/java/org/apache/lucene/analysis/sv/SwedishLightStemmer.java
+
+The Stempel analyzer (stempel) includes BSD-licensed software developed 
+by the Egothor project http://egothor.sf.net/, created by Leo Galambos, Martin Kvapil,
+and Edmond Nolan.
+
+The Polish analyzer (stempel) comes with a default
+stopword list that is BSD-licensed created by the Carrot2 project. The file resides
+in stempel/src/resources/org/apache/lucene/analysis/pl/stopwords.txt.
+See http://project.carrot2.org/license.html.
+
+The SmartChineseAnalyzer source code (smartcn) was
+provided by Xiaoping Gao and copyright 2009 by www.imdict.net.
+
+WordBreakTestUnicode_*.java (under modules/analysis/common/src/test/) 
+is derived from Unicode data such as the Unicode Character Database. 
+See http://unicode.org/copyright.html for more details.
+
+The Morfologik analyzer (morfologik) includes BSD-licensed software
+developed by Dawid Weiss and Marcin Miłkowski (http://morfologik.blogspot.com/).
+
+Morfologik uses data from Polish ispell/myspell dictionary
+(http://www.sjp.pl/slownik/en/) licenced on the terms of (inter alia)
+LGPL and Creative Commons ShareAlike.
+
+Morfologic includes data from BSD-licensed dictionary of Polish (SGJP)
+(http://sgjp.pl/morfeusz/)
+
+Servlet-api.jar and javax.servlet-*.jar are under the CDDL license, the original
+source code for this can be found at http://www.eclipse.org/jetty/downloads.php
+
+===========================================================================
+Kuromoji Japanese Morphological Analyzer - Apache Lucene Integration
+===========================================================================
+
+This software includes a binary and/or source version of data from
+
+  mecab-ipadic-2.7.0-20070801
+
+which can be obtained from
+
+  http://atilika.com/releases/mecab-ipadic/mecab-ipadic-2.7.0-20070801.tar.gz
+
+or
+
+  http://jaist.dl.sourceforge.net/project/mecab/mecab-ipadic/2.7.0-20070801/mecab-ipadic-2.7.0-20070801.tar.gz
+
+===========================================================================
+mecab-ipadic-2.7.0-20070801 Notice
+===========================================================================
+
+Nara Institute of Science and Technology (NAIST),
+the copyright holders, disclaims all warranties with regard to this
+software, including all implied warranties of merchantability and
+fitness, in no event shall NAIST be liable for
+any special, indirect or consequential damages or any damages
+whatsoever resulting from loss of use, data or profits, whether in an
+action of contract, negligence or other tortuous action, arising out
+of or in connection with the use or performance of this software.
+
+A large portion of the dictionary entries
+originate from ICOT Free Software.  The following conditions for ICOT
+Free Software applies to the current dictionary as well.
+
+Each User may also freely distribute the Program, whether in its
+original form or modified, to any third party or parties, PROVIDED
+that the provisions of Section 3 ("NO WARRANTY") will ALWAYS appear
+on, or be attached to, the Program, which is distributed substantially
+in the same form as set out herein and that such intended
+distribution, if actually made, will neither violate or otherwise
+contravene any of the laws and regulations of the countries having
+jurisdiction over the User or the intended distribution itself.
+
+NO WARRANTY
+
+The program was produced on an experimental basis in the course of the
+research and development conducted during the project and is provided
+to users as so produced on an experimental basis.  Accordingly, the
+program is provided without any warranty whatsoever, whether express,
+implied, statutory or otherwise.  The term "warranty" used herein
+includes, but is not limited to, any warranty of the quality,
+performance, merchantability and fitness for a particular purpose of
+the program and the nonexistence of any infringement or violation of
+any right of any third party.
+
+Each user of the program will agree and understand, and be deemed to
+have agreed and understood, that there is no warranty whatsoever for
+the program and, accordingly, the entire risk arising from or
+otherwise connected with the program is assumed by the user.
+
+Therefore, neither ICOT, the copyright holder, or any other
+organization that participated in or was otherwise related to the
+development of the program and their respective officials, directors,
+officers and other employees shall be held liable for any and all
+damages, including, without limitation, general, special, incidental
+and consequential damages, arising out of or otherwise in connection
+with the use or inability to use the program or any product, material
+or result produced or otherwise obtained by using the program,
+regardless of whether they have been advised of, or otherwise had
+knowledge of, the possibility of such damages at any time during the
+project or thereafter.  Each user will be deemed to have agreed to the
+foregoing by his or her commencement of use of the program.  The term
+"use" as used herein includes, but is not limited to, the use,
+modification, copying and distribution of the program and the
+production of secondary products from the program.
+
+In the case where the program, whether in its original form or
+modified, was distributed or delivered to or received by a user from
+any person, organization or entity other than ICOT, unless it makes or
+grants independently of ICOT any specific warranty to the user in
+writing, such person, organization or entity, will also be exempted
+from and not be held liable to the user for any such damages as noted
+above as far as the program is concerned.

licenses/lucene-NOTICE.txt

@@ -6,14 +6,14 @@
     <modelVersion>4.0.0</modelVersion>
     <groupId>org.elasticsearch</groupId>
     <artifactId>elasticsearch-analysis-ik</artifactId>
-    <version>1.9.5</version>
+    <version>${elasticsearch.version}</version>
     <packaging>jar</packaging>
     <description>IK Analyzer for Elasticsearch</description>
     <inceptionYear>2011</inceptionYear>
 
     <properties>
-        <elasticsearch.version>2.3.5</elasticsearch.version>
-        <maven.compiler.target>1.7</maven.compiler.target>
+        <elasticsearch.version>5.0.0-alpha5</elasticsearch.version>
+        <maven.compiler.target>1.8</maven.compiler.target>
         <elasticsearch.assembly.descriptor>${project.basedir}/src/main/assemblies/plugin.xml</elasticsearch.assembly.descriptor>
         <elasticsearch.plugin.name>analysis-ik</elasticsearch.plugin.name>
         <elasticsearch.plugin.classname>org.elasticsearch.plugin.analysis.ik.AnalysisIkPlugin</elasticsearch.plugin.classname>
@@ -113,8 +113,8 @@
                 <artifactId>maven-compiler-plugin</artifactId>
                 <version>3.5.1</version>
                 <configuration>
-                    <source>1.7</source>
-                    <target>1.7</target>
+                    <source>1.8</source>
+                    <target>1.8</target>
                 </configuration>
             </plugin>
             <plugin>

pom.xml

@@ -1,27 +1,30 @@
 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;
-import org.elasticsearch.index.settings.IndexSettingsService;
+import org.elasticsearch.index.IndexSettings;
 import org.wltea.analyzer.cfg.Configuration;
-import org.wltea.analyzer.dic.Dictionary;
 import org.wltea.analyzer.lucene.IKAnalyzer;
 
 public class IkAnalyzerProvider extends AbstractIndexAnalyzerProvider<IKAnalyzer> {
     private final IKAnalyzer analyzer;
 
-    @Inject
-    public IkAnalyzerProvider(Index index, IndexSettingsService indexSettingsService, Environment env, @Assisted String name, @Assisted Settings settings) {
-        super(index, indexSettingsService.getSettings(), name, settings);
+    public IkAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings,boolean useSmart) {
+        super(indexSettings, name, settings);
 
-        Configuration configuration=new Configuration(env,settings);
+        Configuration configuration=new Configuration(env,settings).setUseSmart(useSmart);
 
         analyzer=new IKAnalyzer(configuration);
     }
 
+    public static IkAnalyzerProvider getIkSmartAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
+        return new IkAnalyzerProvider(indexSettings,env,name,settings,true);
+    }
+
+    public static IkAnalyzerProvider getIkAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
+        return new IkAnalyzerProvider(indexSettings,env,name,settings,false);
+    }
+
     @Override public IKAnalyzer get() {
         return this.analyzer;
     }

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

@@ -1,24 +1,33 @@
 package org.elasticsearch.index.analysis;
 
 import org.apache.lucene.analysis.Tokenizer;
-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.settings.IndexSettingsService;
+import org.elasticsearch.index.IndexSettings;
 import org.wltea.analyzer.cfg.Configuration;
 import org.wltea.analyzer.lucene.IKTokenizer;
 
 public class IkTokenizerFactory extends AbstractTokenizerFactory {
   private Configuration configuration;
 
-  @Inject
-  public IkTokenizerFactory(Index index, IndexSettingsService indexSettingsService,Environment env, @Assisted String name, @Assisted Settings settings) {
-	  super(index, indexSettingsService.getSettings(), name, settings);
+  public IkTokenizerFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
+      super(indexSettings, name, settings);
 	  configuration=new Configuration(env,settings);
   }
 
+  public static IkTokenizerFactory getIkTokenizerFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
+      return new IkTokenizerFactory(indexSettings,env, name, settings).setSmart(false);
+  }
+
+  public static IkTokenizerFactory getIkSmartTokenizerFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
+      return new IkTokenizerFactory(indexSettings,env, name, settings).setSmart(true);
+  }
+
+  public IkTokenizerFactory setSmart(boolean smart){
+        this.configuration.setUseSmart(smart);
+        return this;
+  }
+
   @Override
   public Tokenizer create() {
       return new IKTokenizer(configuration);  }