update to 8.4.1

Update log4j

.github/FUNDING.yml

@@ -0,0 +1,2 @@
+patreon: medcl
+custom: ["https://www.buymeacoffee.com/medcl"]

.travis.yml

@@ -1,11 +1,9 @@
+sudo: required
+jdk:
+  - oraclejdk8
+install: true
+script:
+  - sudo apt-get update && sudo apt-get install oracle-java8-installer
+  - java -version
 language: java
 script: mvn clean package
-deploy:
-  provider: releases
-  api_key:
-    secure: llxJZlRYBIWINl5XI42RpEe+jTxlmSP6MX+oTNZa4oFjEeN9Kdd1G8+S3HSIhCc31RoF/2zeNsM9OehRi1O6bweNSQ9vjlKZQPD8FYcHaHpYW0U7h/OMbEeC794fAghm9ZsmOTNymdvbAXL14nJTrwOW9W8VqoZT9Jx7Ejad63Y=
-  file: target/releases/elasticsearch-analysis-ik-*.zip
-  file_glob: true
-  on:
-    repo: medcl/elasticsearch-analysis-ik
-    tags: true

README.md

@@ -10,43 +10,41 @@ Versions
 
 IK version | ES version
 -----------|-----------
-master | 2.2.1 -> master
+master | 7.x -> master
+6.x| 6.x
+5.x| 5.x
+1.10.6 | 2.4.6
+1.9.5 | 2.3.5
 1.8.1 | 2.2.1
-1.8.0 | 2.2.0
 1.7.0 | 2.1.1
-1.6.1 | 2.1.0
 1.5.0 | 2.0.0
-1.4.1 | 1.7.2
-1.4.0 | 1.6.0
-1.3.0 | 1.5.0
-1.2.9 | 1.4.0
-1.2.8 | 1.3.2
-1.2.7 | 1.2.1
 1.2.6 | 1.0.0
 1.2.5 | 0.90.x
 1.1.3 | 0.20.x
-1.1.2 | 0.19.x
 1.0.0 | 0.16.2 -> 0.19.0
 
 Install
 -------
 
-1.compile
+1.download or compile
 
-`mvn package`
+* optional 1 - download pre-build package from here: https://github.com/medcl/elasticsearch-analysis-ik/releases
 
-copy and unzip `target/releases/elasticsearch-analysis-ik-{version}.zip` to `your-es-root/plugins/ik`
+    create plugin folder `cd your-es-root/plugins/ && mkdir ik`
     
+    unzip plugin to folder `your-es-root/plugins/ik`
+
+* optional 2 - use elasticsearch-plugin to install ( supported from version v5.5.1 ):
+
+    ```
+    ./bin/elasticsearch-plugin install https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v6.3.0/elasticsearch-analysis-ik-6.3.0.zip
+    ```
+
+   NOTE: replace `6.3.0` to your own elasticsearch version
 
 2.restart elasticsearch
 
 
-Tips:
-
-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”。
-
 
 #### Quick Example
 
@@ -59,52 +57,41 @@ curl -XPUT http://localhost:9200/index
 2.create a mapping
 
 ```bash
-curl -XPOST http://localhost:9200/index/fulltext/_mapping -d'
+curl -XPOST http://localhost:9200/index/_mapping -H 'Content-Type:application/json' -d'
 {
-    "fulltext": {
-             "_all": {
-            "analyzer": "ik_max_word",
-            "search_analyzer": "ik_max_word",
-            "term_vector": "no",
-            "store": "false"
-        },
         "properties": {
             "content": {
-                "type": "string",
+                "type": "text",
-                "store": "no",
-                "term_vector": "with_positions_offsets",
                 "analyzer": "ik_max_word",
-                "search_analyzer": "ik_max_word",
+                "search_analyzer": "ik_smart"
-                "include_in_all": "true",
-                "boost": 8
-            }
             }
         }
+
 }'
 ```
 
 3.index some docs
 
 ```bash
-curl -XPOST http://localhost:9200/index/fulltext/1 -d'
+curl -XPOST http://localhost:9200/index/_create/1 -H 'Content-Type:application/json' -d'
 {"content":"美国留给伊拉克的是个烂摊子吗"}
 '
 ```
 
 ```bash
-curl -XPOST http://localhost:9200/index/fulltext/2 -d'
+curl -XPOST http://localhost:9200/index/_create/2 -H 'Content-Type:application/json' -d'
 {"content":"公安部：各地校车将享最高路权"}
 '
 ```
 
 ```bash
-curl -XPOST http://localhost:9200/index/fulltext/3 -d'
+curl -XPOST http://localhost:9200/index/_create/3 -H 'Content-Type:application/json' -d'
 {"content":"中韩渔警冲突调查：韩警平均每天扣1艘中国渔船"}
 '
 ```
 
 ```bash
-curl -XPOST http://localhost:9200/index/fulltext/4 -d'
+curl -XPOST http://localhost:9200/index/_create/4 -H 'Content-Type:application/json' -d'
 {"content":"中国驻洛杉矶领事馆遭亚裔男子枪击 嫌犯已自首"}
 '
 ```
@@ -112,9 +99,9 @@ curl -XPOST http://localhost:9200/index/fulltext/4 -d'
 4.query with highlighting
 
 ```bash
-curl -XPOST http://localhost:9200/index/fulltext/_search  -d'
+curl -XPOST http://localhost:9200/index/_search  -H 'Content-Type:application/json' -d'
 {
-    "query" : { "term" : { "content" : "中国" }},
+    "query" : { "match" : { "content" : "中国" }},
     "highlight" : {
         "pre_tags" : ["<tag1>", "<tag2>"],
         "post_tags" : ["</tag1>", "</tag2>"],
@@ -176,7 +163,8 @@ Result
 
 ### Dictionary Configuration
 
-#### `plugins/elasticsearch-analysis-ik-*/config/ik/IKAnalyzer.cfg.xml`
+`IKAnalyzer.cfg.xml` can be located at `{conf}/analysis-ik/config/IKAnalyzer.cfg.xml`
+or `{plugins}/elasticsearch-analysis-ik-*/config/IKAnalyzer.cfg.xml`
 
 ```xml
 <?xml version="1.0" encoding="UTF-8"?>
@@ -230,12 +218,38 @@ have fun.
 ```bash
 git clone https://github.com/medcl/elasticsearch-analysis-ik
 cd elasticsearch-analysis-ik
+git checkout tags/{version}
 mvn clean
 mvn compile
 mvn package
 ```
 
-copy & unzip file  #{project_path}/elasticsearch-analysis-ik/target/releases/elasticsearch-analysis-ik-*.zip to your elasticsearch's folder: plugins/ik
+拷贝和解压release下的文件: #{project_path}/elasticsearch-analysis-ik/target/releases/elasticsearch-analysis-ik-*.zip 到你的 elasticsearch 插件目录, 如: plugins/ik
+重启elasticsearch
+
+3.分词测试失败
+请在某个索引下调用analyze接口测试,而不是直接调用analyze接口
+如:
+```bash
+curl -XGET "http://localhost:9200/your_index/_analyze" -H 'Content-Type: application/json' -d'
+{
+   "text":"中华人民共和国MN","tokenizer": "my_ik"
+}'
+```
+
+
+4. ik_max_word 和 ik_smart 什么区别?
+
+
+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，适合 Term Query；
+
+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”，适合 Phrase 查询。
+
+Changes
+------
+*自 v5.0.0 起*
+
+- 移除名为 `ik` 的analyzer和tokenizer,请分别使用 `ik_smart` 和 `ik_max_word`
 
 
 Thanks

config/IKAnalyzer.cfg.xml

@@ -3,9 +3,9 @@
 <properties>
 	<comment>IK Analyzer 扩展配置</comment>
 	<!--用户可以在这里配置自己的扩展字典 -->
-	<entry key="ext_dict">custom/mydict.dic;custom/single_word_low_freq.dic</entry> 	
+	<entry key="ext_dict"></entry>
 	 <!--用户可以在这里配置自己的扩展停止词字典-->
-	<entry key="ext_stopwords">custom/ext_stopword.dic</entry>
+	<entry key="ext_stopwords"></entry>
 	<!--用户可以在这里配置远程扩展字典 -->
 	<!-- <entry key="remote_ext_dict">words_location</entry> -->
 	<!--用户可以在这里配置远程扩展停止词字典-->

config/ik/custom/mydict.dic

@@ -1,14 +0,0 @@
-medcl
-elastic
-elasticsearch
-kogstash
-kibana
-marvel
-shield
-watcher
-beats
-packetbeat
-filebeat
-topbeat
-metrixbeat
-kimchy

licenses/lucene-LICENSE.txt

@@ -0,0 +1,475 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed 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.
+
+
+
+Some code in core/src/java/org/apache/lucene/util/UnicodeUtil.java was
+derived from unicode conversion examples available at
+http://www.unicode.org/Public/PROGRAMS/CVTUTF.  Here is the copyright
+from those sources:
+
+/*
+ * Copyright 2001-2004 Unicode, Inc.
+ * 
+ * Disclaimer
+ * 
+ * This source code is provided as is by Unicode, Inc. No claims are
+ * made as to fitness for any particular purpose. No warranties of any
+ * kind are expressed or implied. The recipient agrees to determine
+ * applicability of information provided. If this file has been
+ * purchased on magnetic or optical media from Unicode, Inc., the
+ * sole remedy for any claim will be exchange of defective media
+ * within 90 days of receipt.
+ * 
+ * Limitations on Rights to Redistribute This Code
+ * 
+ * Unicode, Inc. hereby grants the right to freely use the information
+ * supplied in this file in the creation of products supporting the
+ * Unicode Standard, and to make copies of this file in any form
+ * for internal or external distribution as long as this notice
+ * remains attached.
+ */
+
+
+Some code in core/src/java/org/apache/lucene/util/ArrayUtil.java was
+derived from Python 2.4.2 sources available at
+http://www.python.org. Full license is here:
+
+  http://www.python.org/download/releases/2.4.2/license/
+
+Some code in core/src/java/org/apache/lucene/util/UnicodeUtil.java was
+derived from Python 3.1.2 sources available at
+http://www.python.org. Full license is here:
+
+  http://www.python.org/download/releases/3.1.2/license/
+
+Some code in core/src/java/org/apache/lucene/util/automaton was
+derived from Brics automaton sources available at
+www.brics.dk/automaton/. Here is the copyright from those sources:
+
+/*
+ * Copyright (c) 2001-2009 Anders Moeller
+ * All rights reserved.
+ * 
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. The name of the author may not be used to endorse or promote products
+ *    derived from this software without specific prior written permission.
+ * 
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+ * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
+ * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
+ * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+ 
+The levenshtein automata tables in core/src/java/org/apache/lucene/util/automaton 
+were automatically generated with the moman/finenight FSA package.
+Here is the copyright for those sources:
+
+# Copyright (c) 2010, Jean-Philippe Barrette-LaPierre, <jpb@rrette.com>
+#
+# Permission is hereby granted, free of charge, to any person
+# obtaining a copy of this software and associated documentation
+# files (the "Software"), to deal in the Software without
+# restriction, including without limitation the rights to use,
+# copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following
+# conditions:
+#
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+# OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+# HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+# WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+
+Some code in core/src/java/org/apache/lucene/util/UnicodeUtil.java was
+derived from ICU (http://www.icu-project.org)
+The full license is available here: 
+  http://source.icu-project.org/repos/icu/icu/trunk/license.html
+
+/*
+ * Copyright (C) 1999-2010, International Business Machines
+ * Corporation and others.  All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy 
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights 
+ * to use, copy, modify, merge, publish, distribute, and/or sell copies of the 
+ * Software, and to permit persons to whom the Software is furnished to do so, 
+ * provided that the above copyright notice(s) and this permission notice appear 
+ * in all copies of the Software and that both the above copyright notice(s) and
+ * this permission notice appear in supporting documentation.
+ * 
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. 
+ * IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE BE 
+ * LIABLE FOR ANY CLAIM, OR 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 TORTIOUS ACTION, ARISING OUT 
+ * OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ *
+ * Except as contained in this notice, the name of a copyright holder shall not 
+ * be used in advertising or otherwise to promote the sale, use or other 
+ * dealings in this Software without prior written authorization of the 
+ * copyright holder.
+ */
+ 
+The following license applies to the Snowball stemmers:
+
+Copyright (c) 2001, Dr Martin Porter
+Copyright (c) 2002, Richard Boulton
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice,
+    * this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+    * notice, this list of conditions and the following disclaimer in the
+    * documentation and/or other materials provided with the distribution.
+    * Neither the name of the copyright holders nor the names of its contributors
+    * may be used to endorse or promote products derived from this software
+    * without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+The following license applies to the KStemmer:
+
+Copyright © 2003,
+Center for Intelligent Information Retrieval,
+University of Massachusetts, Amherst.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification,
+are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+this list of conditions and the following disclaimer in the documentation
+and/or other materials provided with the distribution.
+
+3. The names "Center for Intelligent Information Retrieval" and
+"University of Massachusetts" must not be used to endorse or promote products
+derived from this software without prior written permission. To obtain
+permission, contact info@ciir.cs.umass.edu.
+
+THIS SOFTWARE IS PROVIDED BY UNIVERSITY OF MASSACHUSETTS AND OTHER CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
+GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGE.
+
+The following license applies to the Morfologik project:
+
+Copyright (c) 2006 Dawid Weiss
+Copyright (c) 2007-2011 Dawid Weiss, Marcin Miłkowski
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification, 
+are permitted provided that the following conditions are met:
+
+    * Redistributions of source code must retain the above copyright notice, 
+    this list of conditions and the following disclaimer.
+    
+    * Redistributions in binary form must reproduce the above copyright notice, 
+    this list of conditions and the following disclaimer in the documentation 
+    and/or other materials provided with the distribution.
+    
+    * Neither the name of Morfologik nor the names of its contributors 
+    may be used to endorse or promote products derived from this software 
+    without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND 
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED 
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE 
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR 
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES 
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON 
+ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+---
+
+The dictionary comes from Morfologik project. Morfologik uses data from 
+Polish ispell/myspell dictionary hosted at http://www.sjp.pl/slownik/en/ and 
+is licenced on the terms of (inter alia) LGPL and Creative Commons 
+ShareAlike. The part-of-speech tags were added in Morfologik project and
+are not found in the data from sjp.pl. The tagset is similar to IPI PAN
+tagset.
+
+---
+
+The following license applies to the Morfeusz project,
+used by org.apache.lucene.analysis.morfologik.
+
+BSD-licensed dictionary of Polish (SGJP)
+http://sgjp.pl/morfeusz/
+
+Copyright © 2011 Zygmunt Saloni, Włodzimierz Gruszczyński, 
+             Marcin Woliński, Robert Wołosz
+
+All rights reserved.
+
+Redistribution and  use in  source and binary  forms, with  or without
+modification, are permitted provided that the following conditions are
+met:
+
+1. Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the
+   distribution.
+
+THIS SOFTWARE IS PROVIDED BY COPYRIGHT HOLDERS “AS IS” AND ANY EXPRESS
+OR  IMPLIED WARRANTIES,  INCLUDING, BUT  NOT LIMITED  TO,  THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED.  IN NO EVENT  SHALL COPYRIGHT  HOLDERS OR  CONTRIBUTORS BE
+LIABLE FOR  ANY DIRECT,  INDIRECT, INCIDENTAL, SPECIAL,  EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES  (INCLUDING, BUT NOT LIMITED  TO, PROCUREMENT OF
+SUBSTITUTE  GOODS OR  SERVICES;  LOSS  OF USE,  DATA,  OR PROFITS;  OR
+BUSINESS INTERRUPTION) HOWEVER CAUSED  AND ON ANY THEORY OF LIABILITY,
+WHETHER IN  CONTRACT, STRICT LIABILITY, OR  TORT (INCLUDING NEGLIGENCE
+OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

licenses/lucene-NOTICE.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.

pom.xml

@@ -6,20 +6,22 @@
     <modelVersion>4.0.0</modelVersion>
     <groupId>org.elasticsearch</groupId>
     <artifactId>elasticsearch-analysis-ik</artifactId>
-    <version>1.8.1</version>
+    <version>${elasticsearch.version}</version>
     <packaging>jar</packaging>
     <description>IK Analyzer for Elasticsearch</description>
     <inceptionYear>2011</inceptionYear>
 
     <properties>
-        <elasticsearch.version>2.2.1</elasticsearch.version>
+        <elasticsearch.version>8.4.1</elasticsearch.version>
-        <maven.compiler.target>1.7</maven.compiler.target>
+        <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>
         <elasticsearch.plugin.jvm>true</elasticsearch.plugin.jvm>
         <tests.rest.load_packaged>false</tests.rest.load_packaged>
         <skip.unit.tests>true</skip.unit.tests>
+        <gpg.keyname>4E899B30</gpg.keyname>
+        <gpg.useagent>true</gpg.useagent>
     </properties>
 
     <licenses>
@@ -30,6 +32,15 @@
         </license>
     </licenses>
 
+    <developers>
+        <developer>
+            <name>INFINI Labs</name>
+            <email>hello@infini.ltd</email>
+            <organization>INFINI Labs</organization>
+            <organizationUrl>https://infinilabs.com</organizationUrl>
+        </developer>
+    </developers>
+
     <scm>
         <connection>scm:git:git@github.com:medcl/elasticsearch-analysis-ik.git</connection>
         <developerConnection>scm:git:git@github.com:medcl/elasticsearch-analysis-ik.git
@@ -40,16 +51,27 @@
     <parent>
         <groupId>org.sonatype.oss</groupId>
         <artifactId>oss-parent</artifactId>
-        <version>7</version>
+        <version>9</version>
     </parent>
 
+    <distributionManagement>
+        <snapshotRepository>
+            <id>oss.sonatype.org</id>
+            <url>https://oss.sonatype.org/content/repositories/snapshots</url>
+        </snapshotRepository>
+        <repository>
+            <id>oss.sonatype.org</id>
+            <url>https://oss.sonatype.org/service/local/staging/deploy/maven2/</url>
+        </repository>
+    </distributionManagement>
+
     <repositories>
         <repository>
             <id>oss.sonatype.org</id>
             <name>OSS Sonatype</name>
             <releases><enabled>true</enabled></releases>
             <snapshots><enabled>true</enabled></snapshots>
-            <url>http://oss.sonatype.org/content/repositories/releases/</url>
+            <url>https://oss.sonatype.org/content/repositories/releases/</url>
         </repository>
     </repositories>
 
@@ -61,36 +83,36 @@
             <scope>compile</scope>
         </dependency>
 
+
         <dependency>
             <groupId>org.apache.httpcomponents</groupId>
             <artifactId>httpclient</artifactId>
-	     <version>4.4.1</version>
+            <version>4.5.2</version>
         </dependency>
 
         <dependency>
-            <groupId>log4j</groupId>
+            <groupId>org.apache.logging.log4j</groupId>
-            <artifactId>log4j</artifactId>
+            <artifactId>log4j-api</artifactId>
-            <version>1.2.16</version>
+            <version>2.18.0</version>
-            <scope>runtime</scope>
         </dependency>
 
         <dependency>
             <groupId>org.hamcrest</groupId>
             <artifactId>hamcrest-core</artifactId>
-            <version>1.3.RC2</version>
+            <version>1.3</version>
             <scope>test</scope>
         </dependency>
 
         <dependency>
             <groupId>org.hamcrest</groupId>
             <artifactId>hamcrest-library</artifactId>
-            <version>1.3.RC2</version>
+            <version>1.3</version>
             <scope>test</scope>
         </dependency>
         <dependency>
             <groupId>junit</groupId>
             <artifactId>junit</artifactId>
-            <version>4.10</version>
+            <version>4.12</version>
             <scope>test</scope>
         </dependency>
     </dependencies>
@@ -100,10 +122,10 @@
             <plugin>
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-compiler-plugin</artifactId>
-                <version>2.3.2</version>
+                <version>3.5.1</version>
                 <configuration>
-                    <source>1.6</source>
+                    <source>${maven.compiler.target}</source>
-                    <target>1.6</target>
+                    <target>${maven.compiler.target}</target>
                 </configuration>
             </plugin>
             <plugin>
@@ -131,7 +153,9 @@
             </plugin>
             <plugin>
                 <artifactId>maven-assembly-plugin</artifactId>
+
                 <configuration>
+                    <appendAssemblyId>false</appendAssemblyId>
                     <outputDirectory>${project.build.directory}/releases/</outputDirectory>
                     <descriptors>
                         <descriptor>${basedir}/src/main/assemblies/plugin.xml</descriptor>
@@ -153,4 +177,93 @@
             </plugin>
         </plugins>
     </build>
+    <profiles>
+        <profile>
+            <id>disable-java8-doclint</id>
+            <activation>
+                <jdk>[1.8,)</jdk>
+            </activation>
+            <properties>
+                <additionalparam>-Xdoclint:none</additionalparam>
+            </properties>
+        </profile>
+            <profile>
+                <id>release</id>
+                <build>
+                    <plugins>
+                        <plugin>
+                            <groupId>org.sonatype.plugins</groupId>
+                            <artifactId>nexus-staging-maven-plugin</artifactId>
+                            <version>1.6.3</version>
+                            <extensions>true</extensions>
+                            <configuration>
+                                <serverId>oss</serverId>
+                                <nexusUrl>https://oss.sonatype.org/</nexusUrl>
+                                <autoReleaseAfterClose>true</autoReleaseAfterClose>
+                            </configuration>
+                        </plugin>
+                        <plugin>
+                            <groupId>org.apache.maven.plugins</groupId>
+                            <artifactId>maven-release-plugin</artifactId>
+                            <version>2.1</version>
+                            <configuration>
+                                <autoVersionSubmodules>true</autoVersionSubmodules>
+                                <useReleaseProfile>false</useReleaseProfile>
+                                <releaseProfiles>release</releaseProfiles>
+                                <goals>deploy</goals>
+                            </configuration>
+                        </plugin>
+                        <plugin>
+                            <groupId>org.apache.maven.plugins</groupId>
+                            <artifactId>maven-compiler-plugin</artifactId>
+                            <version>3.5.1</version>
+                            <configuration>
+                                <source>${maven.compiler.target}</source>
+                                <target>${maven.compiler.target}</target>
+                            </configuration>
+                        </plugin>
+                        <plugin>
+                            <groupId>org.apache.maven.plugins</groupId>
+                            <artifactId>maven-gpg-plugin</artifactId>
+                            <version>1.5</version>
+                            <executions>
+                                <execution>
+                                    <id>sign-artifacts</id>
+                                    <phase>verify</phase>
+                                    <goals>
+                                        <goal>sign</goal>
+                                    </goals>
+                                </execution>
+                            </executions>
+                        </plugin>
+                        <plugin>
+                            <groupId>org.apache.maven.plugins</groupId>
+                            <artifactId>maven-source-plugin</artifactId>
+                            <version>2.2.1</version>
+                            <executions>
+                                <execution>
+                                    <id>attach-sources</id>
+                                    <goals>
+                                        <goal>jar-no-fork</goal>
+                                    </goals>
+                                </execution>
+                            </executions>
+                        </plugin>
+                        <plugin>
+                            <groupId>org.apache.maven.plugins</groupId>
+                            <artifactId>maven-javadoc-plugin</artifactId>
+                            <version>2.9</version>
+                            <executions>
+                                <execution>
+                                    <id>attach-javadocs</id>
+                                    <goals>
+                                        <goal>jar</goal>
+                                    </goals>
+                                </execution>
+                            </executions>
+                        </plugin>
+                    </plugins>
+                </build>
+            </profile>
+    </profiles>
 </project>

src/main/assemblies/plugin.xml

@@ -1,5 +1,6 @@
 <?xml version="1.0"?>
 <assembly>
+    <id>analysis-ik-release</id>
     <formats>
         <format>zip</format>
     </formats>
@@ -7,20 +8,25 @@
     <fileSets>
         <fileSet>
         <directory>${project.basedir}/config</directory>
-            <outputDirectory>/config</outputDirectory>
+            <outputDirectory>config</outputDirectory>
         </fileSet>
     </fileSets>
 
     <files>
         <file>
             <source>${project.basedir}/src/main/resources/plugin-descriptor.properties</source>
-            <outputDirectory></outputDirectory>
+            <outputDirectory/>
+            <filtered>true</filtered>
+        </file>
+        <file>
+            <source>${project.basedir}/src/main/resources/plugin-security.policy</source>
+            <outputDirectory/>
             <filtered>true</filtered>
         </file>
     </files>
     <dependencySets>
         <dependencySet>
-            <outputDirectory>/</outputDirectory>
+            <outputDirectory/>
             <useProjectArtifact>true</useProjectArtifact>
             <useTransitiveFiltering>true</useTransitiveFiltering>
             <excludes>
@@ -28,7 +34,7 @@
             </excludes>
         </dependencySet>
         <dependencySet>
-            <outputDirectory>/</outputDirectory>
+            <outputDirectory/>
             <useProjectArtifact>true</useProjectArtifact>
             <useTransitiveFiltering>true</useTransitiveFiltering>
             <includes>

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

@@ -1,24 +0,0 @@
-package org.elasticsearch.index.analysis;
-
-
-@Deprecated
-public class IkAnalysisBinderProcessor extends AnalysisModule.AnalysisBinderProcessor {
-
-
-    @Override
-    public void processTokenFilters(TokenFiltersBindings tokenFiltersBindings) {
-
-    }
-
-
-    @Override
-    public void processAnalyzers(AnalyzersBindings analyzersBindings) {
-        analyzersBindings.processAnalyzer("ik", IkAnalyzerProvider.class);
-    }
-
-
-    @Override
-    public void processTokenizers(TokenizersBindings tokenizersBindings) {
-        tokenizersBindings.processTokenizer("ik", IkTokenizerFactory.class);
-    }
-}

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

@@ -1,26 +1,28 @@
 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.IndexSettings;
-import org.elasticsearch.index.settings.IndexSettingsService;
 import org.wltea.analyzer.cfg.Configuration;
-import org.wltea.analyzer.dic.Dictionary;
 import org.wltea.analyzer.lucene.IKAnalyzer;
 
-@Deprecated
 public class IkAnalyzerProvider extends AbstractIndexAnalyzerProvider<IKAnalyzer> {
     private final IKAnalyzer analyzer;
-    private boolean useSmart=false;
 
-    @Inject
+    public IkAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings,boolean useSmart) {
-    public IkAnalyzerProvider(Index index, IndexSettingsService indexSettingsService, Environment env, @Assisted String name, @Assisted Settings settings) {
+        super(name, settings);
-        super(index, indexSettingsService.getSettings(), name, settings);
+
-        Dictionary.initial(new Configuration(env));
+        Configuration configuration=new Configuration(env,settings).setUseSmart(useSmart);
-        useSmart = settings.get("use_smart", "false").equals("true");
+
-        analyzer=new IKAnalyzer(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() {

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

@@ -1,32 +1,34 @@
 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.IndexSettings;
-import org.elasticsearch.index.settings.IndexSettingsService;
 import org.wltea.analyzer.cfg.Configuration;
-import org.wltea.analyzer.dic.Dictionary;
 import org.wltea.analyzer.lucene.IKTokenizer;
 
-@Deprecated
 public class IkTokenizerFactory extends AbstractTokenizerFactory {
-  private final Settings settings;
+  private Configuration configuration;
-  private boolean useSmart=false;
 
-  @Inject
+  public IkTokenizerFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
-  public IkTokenizerFactory(Index index, IndexSettingsService indexSettingsService,Environment env, @Assisted String name, @Assisted Settings settings) {
+      super(indexSettings, settings,name);
-	  super(index, indexSettingsService.getSettings(), name, settings);
+	  configuration=new Configuration(env,settings);
-      this.settings=settings;
-	  Dictionary.initial(new Configuration(env));
   }
 
+  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() {
-    this.useSmart = settings.get("use_smart", "false").equals("true");
+      return new IKTokenizer(configuration);  }
-
-    return new IKTokenizer(useSmart);  }
 }

src/main/java/org/elasticsearch/indices/analysis/IKIndicesAnalysis.java

@@ -1,84 +0,0 @@
-package org.elasticsearch.indices.analysis;
-
-import org.apache.lucene.analysis.Tokenizer;
-import org.elasticsearch.common.component.AbstractComponent;
-import org.elasticsearch.common.inject.Inject;
-import org.elasticsearch.common.settings.Settings;
-import org.elasticsearch.env.Environment;
-import org.elasticsearch.index.analysis.AnalyzerScope;
-import org.elasticsearch.index.analysis.PreBuiltAnalyzerProviderFactory;
-import org.elasticsearch.index.analysis.PreBuiltTokenizerFactoryFactory;
-import org.elasticsearch.index.analysis.TokenizerFactory;
-import org.wltea.analyzer.cfg.Configuration;
-import org.wltea.analyzer.dic.Dictionary;
-import org.wltea.analyzer.lucene.IKAnalyzer;
-import org.wltea.analyzer.lucene.IKTokenizer;
-
-/**
- * Registers indices level analysis components so, if not explicitly configured,
- * will be shared among all indices.
- */
-public class IKIndicesAnalysis extends AbstractComponent {
-
-    private boolean useSmart=false;
-
-    @Inject
-    public IKIndicesAnalysis(final Settings settings,
-                                   IndicesAnalysisService indicesAnalysisService,Environment env) {
-        super(settings);
-        Dictionary.initial(new Configuration(env));
-
-        this.useSmart = settings.get("use_smart", "false").equals("true");
-
-        indicesAnalysisService.analyzerProviderFactories().put("ik",
-                new PreBuiltAnalyzerProviderFactory("ik", AnalyzerScope.GLOBAL,
-                        new IKAnalyzer(useSmart)));
-
-        indicesAnalysisService.analyzerProviderFactories().put("ik_smart",
-                new PreBuiltAnalyzerProviderFactory("ik_smart", AnalyzerScope.GLOBAL,
-                        new IKAnalyzer(true)));
-
-        indicesAnalysisService.analyzerProviderFactories().put("ik_max_word",
-                new PreBuiltAnalyzerProviderFactory("ik_max_word", AnalyzerScope.GLOBAL,
-                        new IKAnalyzer(false)));
-
-        indicesAnalysisService.tokenizerFactories().put("ik",
-                new PreBuiltTokenizerFactoryFactory(new TokenizerFactory() {
-                    @Override
-                    public String name() {
-                        return "ik";
-                    }
-
-                    @Override
-                    public Tokenizer create() {
-                        return new IKTokenizer(false);
-                    }
-                }));
-
-        indicesAnalysisService.tokenizerFactories().put("ik_smart",
-                new PreBuiltTokenizerFactoryFactory(new TokenizerFactory() {
-                    @Override
-                    public String name() {
-                        return "ik_smart";
-                    }
-
-                    @Override
-                    public Tokenizer create() {
-                        return new IKTokenizer(true);
-                    }
-                }));
-
-        indicesAnalysisService.tokenizerFactories().put("ik_max_word",
-                new PreBuiltTokenizerFactoryFactory(new TokenizerFactory() {
-                    @Override
-                    public String name() {
-                        return "ik_max_word";
-                    }
-
-                    @Override
-                    public Tokenizer create() {
-                        return new IKTokenizer(false);
-                    }
-                }));
-    }
-}

src/main/java/org/elasticsearch/indices/analysis/IKIndicesAnalysisModule.java

@@ -1,32 +0,0 @@
-/*
- * Licensed to Elasticsearch under one or more contributor
- * license agreements. See the NOTICE file distributed with
- * this work for additional information regarding copyright
- * ownership. Elasticsearch 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.elasticsearch.indices.analysis;
-
-import org.elasticsearch.common.inject.AbstractModule;
-
-/**
- */
-public class IKIndicesAnalysisModule extends AbstractModule {
-
-    @Override
-    protected void configure() {
-        bind(IKIndicesAnalysis.class).asEagerSingleton();
-    }
-}

src/main/java/org/elasticsearch/plugin/analysis/ik/AnalysisIkPlugin.java

@@ -1,44 +1,41 @@
 package org.elasticsearch.plugin.analysis.ik;
 
-import org.elasticsearch.common.inject.AbstractModule;
+import org.apache.lucene.analysis.Analyzer;
-import org.elasticsearch.common.inject.Inject;
+import org.elasticsearch.index.analysis.AnalyzerProvider;
-import org.elasticsearch.common.inject.Module;
+import org.elasticsearch.index.analysis.IkAnalyzerProvider;
-import org.elasticsearch.common.logging.ESLogger;
+import org.elasticsearch.index.analysis.IkTokenizerFactory;
-import org.elasticsearch.common.logging.ESLoggerFactory;
+import org.elasticsearch.index.analysis.TokenizerFactory;
-import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.indices.analysis.AnalysisModule;
-import org.elasticsearch.env.Environment;
+import org.elasticsearch.plugins.AnalysisPlugin;
-import org.elasticsearch.index.analysis.AnalysisModule;
-import org.elasticsearch.index.analysis.IkAnalysisBinderProcessor;
-import org.elasticsearch.indices.analysis.IKIndicesAnalysisModule;
 import org.elasticsearch.plugins.Plugin;
-import org.wltea.analyzer.cfg.Configuration;
-import org.wltea.analyzer.dic.Dictionary;
 
-import java.nio.file.Path;
+import java.util.HashMap;
-import java.util.Collection;
+import java.util.Map;
-import java.util.Collections;
-import java.util.logging.Logger;
-
-import static java.rmi.Naming.bind;
 
 
-public class AnalysisIkPlugin extends Plugin {
+public class AnalysisIkPlugin extends Plugin implements AnalysisPlugin {
 
-    @Override public String name() {
+	public static String PLUGIN_NAME = "analysis-ik";
-        return "analysis-ik";
+
-    }
+    @Override
+    public Map<String, AnalysisModule.AnalysisProvider<TokenizerFactory>> getTokenizers() {
+        Map<String, AnalysisModule.AnalysisProvider<TokenizerFactory>> extra = new HashMap<>();
 
 
-    @Override public String description() {
+        extra.put("ik_smart", IkTokenizerFactory::getIkSmartTokenizerFactory);
-        return "ik analysis";
+        extra.put("ik_max_word", IkTokenizerFactory::getIkTokenizerFactory);
+
+        return extra;
     }
 
     @Override
-    public Collection<Module> nodeModules() {
+    public Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> getAnalyzers() {
-        return Collections.<Module>singletonList(new IKIndicesAnalysisModule());
+        Map<String, AnalysisModule.AnalysisProvider<AnalyzerProvider<? extends Analyzer>>> extra = new HashMap<>();
-    }
+
-    public void onModule(AnalysisModule module) {
+        extra.put("ik_smart", IkAnalyzerProvider::getIkSmartAnalyzerProvider);
-        module.addProcessor(new IkAnalysisBinderProcessor());
+        extra.put("ik_max_word", IkAnalyzerProvider::getIkAnalyzerProvider);
+
+        return extra;
     }
 
 }

src/main/java/org/wltea/analyzer/cfg/Configuration.java

@@ -4,134 +4,72 @@
 package org.wltea.analyzer.cfg;
 
 import org.elasticsearch.common.inject.Inject;
-import org.elasticsearch.common.io.PathUtils;
+import org.elasticsearch.core.PathUtils;
-import org.elasticsearch.common.logging.ESLogger;
+import org.elasticsearch.common.settings.Settings;
-import org.elasticsearch.common.logging.Loggers;
 import org.elasticsearch.env.Environment;
 import org.elasticsearch.plugin.analysis.ik.AnalysisIkPlugin;
+import org.wltea.analyzer.dic.Dictionary;
 
-import java.io.*;
+import java.io.File;
-import java.net.URL;
 import java.nio.file.Path;
-import java.util.ArrayList;
-import java.util.InvalidPropertiesFormatException;
-import java.util.List;
-import java.util.Properties;
 
 public class Configuration {
 
-	private static String FILE_NAME = "ik/IKAnalyzer.cfg.xml";
-	private static final String EXT_DICT = "ext_dict";
-	private static final String REMOTE_EXT_DICT = "remote_ext_dict";
-	private static final String EXT_STOP = "ext_stopwords";
-	private static final String REMOTE_EXT_STOP = "remote_ext_stopwords";
-    private static ESLogger logger = Loggers.getLogger("ik-analyzer");
-	private Properties props;
 	private Environment environment;
+	private Settings settings;
+
+	//是否启用智能分词
+	private  boolean useSmart;
+
+	//是否启用远程词典加载
+	private boolean enableRemoteDict=false;
+
+	//是否启用小写处理
+	private boolean enableLowercase=true;
+
 
 	@Inject
-    public  Configuration(Environment env){
+	public Configuration(Environment env,Settings settings) {
-		props = new Properties();
+		this.environment = env;
-        environment = env;
+		this.settings=settings;
 
+		this.useSmart = settings.get("use_smart", "false").equals("true");
+		this.enableLowercase = settings.get("enable_lowercase", "true").equals("true");
+		this.enableRemoteDict = settings.get("enable_remote_dict", "true").equals("true");
 
-		Path fileConfig = PathUtils.get(getDictRoot(), FILE_NAME);
+		Dictionary.initial(this);
-
-
-        InputStream input = null;
-        try {
-            input = new FileInputStream(fileConfig.toFile());
-        } catch (FileNotFoundException e) {
-            logger.error("ik-analyzer",e);
-        }
-        if(input != null){
-			try {
-				props.loadFromXML(input);
-			} catch (InvalidPropertiesFormatException e) {
-				logger.error("ik-analyzer", e);
-			} catch (IOException e) {
-				logger.error("ik-analyzer",e);
-			}
-		}
-	}
-
-    public  List<String> getExtDictionarys(){
-		List<String> extDictFiles = new ArrayList<String>(2);
-		String extDictCfg = props.getProperty(EXT_DICT);
-		if(extDictCfg != null){
-
-			String[] filePaths = extDictCfg.split(";");
-			if(filePaths != null){
-				for(String filePath : filePaths){
-					if(filePath != null && !"".equals(filePath.trim())){
-						Path file = PathUtils.get("ik", filePath.trim());
-						extDictFiles.add(file.toString());
 
 	}
-				}
+
-			}
+	public Path getConfigInPluginDir() {
-		}		
+		return PathUtils
-		return extDictFiles;		
+				.get(new File(AnalysisIkPlugin.class.getProtectionDomain().getCodeSource().getLocation().getPath())
+						.getParent(), "config")
+				.toAbsolutePath();
 	}
 
-    public  List<String> getRemoteExtDictionarys(){
+	public boolean isUseSmart() {
-		List<String> remoteExtDictFiles = new ArrayList<String>(2);
+		return useSmart;
-		String remoteExtDictCfg = props.getProperty(REMOTE_EXT_DICT);
-		if(remoteExtDictCfg != null){
-
-			String[] filePaths = remoteExtDictCfg.split(";");
-			if(filePaths != null){
-				for(String filePath : filePaths){
-					if(filePath != null && !"".equals(filePath.trim())){
-						remoteExtDictFiles.add(filePath);
-
-					}
-				}
-			}
-		}		
-		return remoteExtDictFiles;		
 	}
 
-	public List<String> getExtStopWordDictionarys(){
+	public Configuration setUseSmart(boolean useSmart) {
-		List<String> extStopWordDictFiles = new ArrayList<String>(2);
+		this.useSmart = useSmart;
-		String extStopWordDictCfg = props.getProperty(EXT_STOP);
+		return this;
-		if(extStopWordDictCfg != null){
-			
-			String[] filePaths = extStopWordDictCfg.split(";");
-			if(filePaths != null){
-				for(String filePath : filePaths){
-					if(filePath != null && !"".equals(filePath.trim())){
-						Path file = PathUtils.get("ik", filePath.trim());
-						extStopWordDictFiles.add(file.toString());
-
-					}
-				}
-			}
-		}		
-		return extStopWordDictFiles;		
 	}
 
-	public  List<String> getRemoteExtStopWordDictionarys(){
+	public Environment getEnvironment() {
-		List<String> remoteExtStopWordDictFiles = new ArrayList<String>(2);
+		return environment;
-		String remoteExtStopWordDictCfg = props.getProperty(REMOTE_EXT_STOP);
-		if(remoteExtStopWordDictCfg != null){
-
-			String[] filePaths = remoteExtStopWordDictCfg.split(";");
-			if(filePaths != null){
-				for(String filePath : filePaths){
-					if(filePath != null && !"".equals(filePath.trim())){
-						remoteExtStopWordDictFiles.add(filePath);
-
-					}
-				}
-			}
-		}
-		return remoteExtStopWordDictFiles;		
 	}
 
-    public String getDictRoot() {
+	public Settings getSettings() {
-		return PathUtils.get(
+		return settings;
-				new File(AnalysisIkPlugin.class.getProtectionDomain().getCodeSource().getLocation().getPath()).getParent(),"config")
+	}
-				.toAbsolutePath().toString();
+
+	public boolean isEnableRemoteDict() {
+		return enableRemoteDict;
+	}
+
+	public boolean isEnableLowercase() {
+		return enableLowercase;
 	}
 }

src/main/java/org/wltea/analyzer/core/AnalyzeContext.java

@@ -32,6 +32,7 @@ import java.util.LinkedList;
 import java.util.Map;
 import java.util.Set;
 
+import org.wltea.analyzer.cfg.Configuration;
 import org.wltea.analyzer.dic.Dictionary;
 
 /**
@@ -47,7 +48,7 @@ class AnalyzeContext {
 	private static final int BUFF_EXHAUST_CRITICAL = 100;	
 	
  
-	//字符窜读取缓冲
+	//字符串读取缓冲
     private char[] segmentBuff;
     //字符类型数组
     private int[] charTypes;
@@ -72,12 +73,11 @@ class AnalyzeContext {
     private Map<Integer , LexemePath> pathMap;    
     //最终分词结果集
     private LinkedList<Lexeme> results;
-    private boolean useSmart;
 	//分词器配置项
-//	private Configuration cfg;
+	private Configuration cfg;
 
-    public AnalyzeContext(boolean useSmart){
+    public AnalyzeContext(Configuration configuration){
-        this.useSmart = useSmart;
+        this.cfg = configuration;
     	this.segmentBuff = new char[BUFF_SIZE];
     	this.charTypes = new int[BUFF_SIZE];
     	this.buffLocker = new HashSet<String>();
@@ -139,7 +139,7 @@ class AnalyzeContext {
      */
     void initCursor(){
     	this.cursor = 0;
-    	this.segmentBuff[this.cursor] = CharacterUtil.regularize(this.segmentBuff[this.cursor]);
+    	this.segmentBuff[this.cursor] = CharacterUtil.regularize(this.segmentBuff[this.cursor],cfg.isEnableLowercase());
     	this.charTypes[this.cursor] = CharacterUtil.identifyCharType(this.segmentBuff[this.cursor]);
     }
     
@@ -151,7 +151,7 @@ class AnalyzeContext {
     boolean moveCursor(){
     	if(this.cursor < this.available - 1){
     		this.cursor++;
-        	this.segmentBuff[this.cursor] = CharacterUtil.regularize(this.segmentBuff[this.cursor]);
+        	this.segmentBuff[this.cursor] = CharacterUtil.regularize(this.segmentBuff[this.cursor],cfg.isEnableLowercase());
         	this.charTypes[this.cursor] = CharacterUtil.identifyCharType(this.segmentBuff[this.cursor]);
     		return true;
     	}else{
@@ -267,6 +267,15 @@ class AnalyzeContext {
 				Lexeme l = path.pollFirst();
 				while(l != null){
 					this.results.add(l);
+					//字典中无单字，但是词元冲突了，切分出相交词元的前一个词元中的单字
+					/*int innerIndex = index + 1;
+					for (; innerIndex < index + l.getLength(); innerIndex++) {
+						Lexeme innerL = path.peekFirst();
+						if (innerL != null && innerIndex == innerL.getBegin()) {
+							this.outputSingleCJK(innerIndex - 1);
+						}
+					}*/
+					
 					//将index移至lexeme后
 					index = l.getBegin() + l.getLength();					
 					l = path.pollFirst();
@@ -345,7 +354,7 @@ class AnalyzeContext {
 	 */
 	private void compound(Lexeme result){
 
-		if(!this.useSmart){
+		if(!this.cfg.isUseSmart()){
 			return ;
 		}
    		//数量词合并处理

src/main/java/org/wltea/analyzer/core/CharacterUtil.java

@@ -86,14 +86,14 @@ class CharacterUtil {
 	 * @param input
 	 * @return char
 	 */
-	static char regularize(char input){
+	static char regularize(char input,boolean lowercase){
         if (input == 12288) {
             input = (char) 32;
             
         }else if (input > 65280 && input < 65375) {
             input = (char) (input - 65248);
             
-        }else if (input >= 'A' && input <= 'Z') {
+        }else if (input >= 'A' && input <= 'Z' && lowercase) {
         	input += 32;
 		}
         

src/main/java/org/wltea/analyzer/core/IKSegmenter.java

@@ -23,10 +23,7 @@
  */
 package org.wltea.analyzer.core;
 
-import org.elasticsearch.common.settings.Settings;
-import org.elasticsearch.env.Environment;
 import org.wltea.analyzer.cfg.Configuration;
-import org.wltea.analyzer.dic.Dictionary;
 
 import java.io.IOException;
 import java.io.Reader;
@@ -47,16 +44,16 @@ public final class IKSegmenter {
 	private List<ISegmenter> segmenters;
 	//分词歧义裁决器
 	private IKArbitrator arbitrator;
-    private  boolean useSmart = false;
+    private  Configuration configuration;
 	
 
 	/**
 	 * IK分词器构造函数
 	 * @param input
      */
-	public IKSegmenter(Reader input ,boolean useSmart){
+	public IKSegmenter(Reader input ,Configuration configuration){
 		this.input = input;
-        this.useSmart = useSmart;
+        this.configuration = configuration;
         this.init();
 	}
 
@@ -66,7 +63,7 @@ public final class IKSegmenter {
 	 */
 	private void init(){
 		//初始化分词上下文
-		this.context = new AnalyzeContext(useSmart);
+		this.context = new AnalyzeContext(configuration);
 		//加载子分词器
 		this.segmenters = this.loadSegmenters();
 		//加载歧义裁决器
@@ -127,7 +124,7 @@ public final class IKSegmenter {
 				}
 			}
 			//对分词进行歧义处理
-			this.arbitrator.process(context, useSmart);
+			this.arbitrator.process(context, configuration.isUseSmart());
 			//将分词结果输出到结果集，并处理未切分的单个CJK字符
 			context.outputToResult();
 			//记录本次分词的缓冲区位移

src/main/java/org/wltea/analyzer/dic/DictSegment.java

@@ -57,7 +57,7 @@ class DictSegment implements Comparable<DictSegment>{
 	
 	DictSegment(Character nodeChar){
 		if(nodeChar == null){
-			throw new IllegalArgumentException("参数为空异常，字符不能为空");
+			throw new IllegalArgumentException("node char cannot be empty");
 		}
 		this.nodeChar = nodeChar;
 	}

src/main/java/org/wltea/analyzer/dic/Dictionary.java

@@ -26,37 +26,44 @@
 package org.wltea.analyzer.dic;
 
 import java.io.BufferedReader;
-import java.io.File;
 import java.io.FileInputStream;
 import java.io.FileNotFoundException;
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.InputStreamReader;
+import java.nio.file.attribute.BasicFileAttributes;
+import java.nio.file.Files;
+import java.nio.file.FileVisitResult;
 import java.nio.file.Path;
-import java.util.ArrayList;
+import java.nio.file.SimpleFileVisitor;
-import java.util.Collection;
+import java.security.AccessController;
-import java.util.List;
+import java.security.PrivilegedAction;
+import java.util.*;
 import java.util.concurrent.Executors;
 import java.util.concurrent.ScheduledExecutorService;
 import java.util.concurrent.TimeUnit;
 
+import org.apache.http.Header;
+import org.apache.http.HttpEntity;
 import org.apache.http.client.ClientProtocolException;
 import org.apache.http.client.config.RequestConfig;
 import org.apache.http.client.methods.CloseableHttpResponse;
 import org.apache.http.client.methods.HttpGet;
 import org.apache.http.impl.client.CloseableHttpClient;
 import org.apache.http.impl.client.HttpClients;
-import org.elasticsearch.common.io.PathUtils;
+import org.elasticsearch.SpecialPermission;
-import org.elasticsearch.common.logging.ESLogger;
+import org.elasticsearch.core.PathUtils;
-import org.elasticsearch.common.logging.Loggers;
+import org.elasticsearch.plugin.analysis.ik.AnalysisIkPlugin;
 import org.wltea.analyzer.cfg.Configuration;
+import org.apache.logging.log4j.Logger;
+import org.wltea.analyzer.help.ESPluginLoggerFactory;
+
 
 /**
  * 词典管理类,单子模式
  */
 public class Dictionary {
 
-
 	/*
 	 * 词典单子实例
 	 */
@@ -64,50 +71,83 @@ public class Dictionary {
 
 	private DictSegment _MainDict;
 
-    private DictSegment _SurnameDict;
-
 	private DictSegment _QuantifierDict;
 
-    private DictSegment _SuffixDict;
-
-    private DictSegment _PrepDict;
-
 	private DictSegment _StopWords;
 
-	
 	/**
 	 * 配置对象
 	 */
 	private Configuration configuration;
-    public static final ESLogger logger=Loggers.getLogger("ik-analyzer");
+
+	private static final Logger logger = ESPluginLoggerFactory.getLogger(Dictionary.class.getName());
 
 	private static ScheduledExecutorService pool = Executors.newScheduledThreadPool(1);
 
-    public static final String PATH_DIC_MAIN = "ik/main.dic";
+	private static final String PATH_DIC_MAIN = "main.dic";
-    public static final String PATH_DIC_SURNAME = "ik/surname.dic";
+	private static final String PATH_DIC_SURNAME = "surname.dic";
-    public static final String PATH_DIC_QUANTIFIER = "ik/quantifier.dic";
+	private static final String PATH_DIC_QUANTIFIER = "quantifier.dic";
-    public static final String PATH_DIC_SUFFIX = "ik/suffix.dic";
+	private static final String PATH_DIC_SUFFIX = "suffix.dic";
-    public static final String PATH_DIC_PREP = "ik/preposition.dic";
+	private static final String PATH_DIC_PREP = "preposition.dic";
-    public static final String PATH_DIC_STOP = "ik/stopword.dic";
+	private static final String PATH_DIC_STOP = "stopword.dic";
 
-    private Dictionary(){
+	private final static  String FILE_NAME = "IKAnalyzer.cfg.xml";
+	private final static  String EXT_DICT = "ext_dict";
+	private final static  String REMOTE_EXT_DICT = "remote_ext_dict";
+	private final static  String EXT_STOP = "ext_stopwords";
+	private final static  String REMOTE_EXT_STOP = "remote_ext_stopwords";
 
+	private Path conf_dir;
+	private Properties props;
+
+	private Dictionary(Configuration cfg) {
+		this.configuration = cfg;
+		this.props = new Properties();
+		this.conf_dir = cfg.getEnvironment().configFile().resolve(AnalysisIkPlugin.PLUGIN_NAME);
+		Path configFile = conf_dir.resolve(FILE_NAME);
+
+		InputStream input = null;
+		try {
+			logger.info("try load config from {}", configFile);
+			input = new FileInputStream(configFile.toFile());
+		} catch (FileNotFoundException e) {
+			conf_dir = cfg.getConfigInPluginDir();
+			configFile = conf_dir.resolve(FILE_NAME);
+			try {
+				logger.info("try load config from {}", configFile);
+				input = new FileInputStream(configFile.toFile());
+			} catch (FileNotFoundException ex) {
+				// We should report origin exception
+				logger.error("ik-analyzer", e);
+			}
+		}
+		if (input != null) {
+			try {
+				props.loadFromXML(input);
+			} catch (IOException e) {
+				logger.error("ik-analyzer", e);
+			}
+		}
 	}
 
+	private String getProperty(String key){
+		if(props!=null){
+			return props.getProperty(key);
+		}
+		return null;
+	}
 	/**
-	 * 词典初始化
+	 * 词典初始化 由于IK Analyzer的词典采用Dictionary类的静态方法进行词典初始化
-	 * 由于IK Analyzer的词典采用Dictionary类的静态方法进行词典初始化
+	 * 只有当Dictionary类被实际调用时，才会开始载入词典， 这将延长首次分词操作的时间 该方法提供了一个在应用加载阶段就初始化字典的手段
-	 * 只有当Dictionary类被实际调用时，才会开始载入词典，
+	 * 
-	 * 这将延长首次分词操作的时间
-	 * 该方法提供了一个在应用加载阶段就初始化字典的手段
 	 * @return Dictionary
 	 */
-	public static synchronized Dictionary initial(Configuration cfg){
+	public static synchronized void initial(Configuration cfg) {
-		
+		if (singleton == null) {
 			synchronized (Dictionary.class) {
 				if (singleton == null) {
-				singleton = new Dictionary();
+
-				singleton.configuration=cfg;
+					singleton = new Dictionary(cfg);
 					singleton.loadMainDict();
 					singleton.loadSurnameDict();
 					singleton.loadQuantifierDict();
@@ -115,35 +155,156 @@ public class Dictionary {
 					singleton.loadPrepDict();
 					singleton.loadStopWordDict();
 
+					if(cfg.isEnableRemoteDict()){
 						// 建立监控线程
-				for(String location:cfg.getRemoteExtDictionarys()){
+						for (String location : singleton.getRemoteExtDictionarys()) {
 							// 10 秒是初始延迟可以修改的 60是间隔时间 单位秒
 							pool.scheduleAtFixedRate(new Monitor(location), 10, 60, TimeUnit.SECONDS);
 						}
-				for(String location:cfg.getRemoteExtStopWordDictionarys()){
+						for (String location : singleton.getRemoteExtStopWordDictionarys()) {
 							pool.scheduleAtFixedRate(new Monitor(location), 10, 60, TimeUnit.SECONDS);
 						}
+					}
 
-				return singleton;
 				}
 			}
-		return singleton;
 		}
+	}
+
+	private void walkFileTree(List<String> files, Path path) {
+		if (Files.isRegularFile(path)) {
+			files.add(path.toString());
+		} else if (Files.isDirectory(path)) try {
+			Files.walkFileTree(path, new SimpleFileVisitor<Path>() {
+				@Override
+				public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) {
+					files.add(file.toString());
+					return FileVisitResult.CONTINUE;
+				}
+				@Override
+				public FileVisitResult visitFileFailed(Path file, IOException e) {
+					logger.error("[Ext Loading] listing files", e);
+					return FileVisitResult.CONTINUE;
+				}
+			});
+		} catch (IOException e) {
+			logger.error("[Ext Loading] listing files", e);
+		} else {
+			logger.warn("[Ext Loading] file not found: " + path);
+		}
+	}
+
+	private void loadDictFile(DictSegment dict, Path file, boolean critical, String name) {
+		try (InputStream is = new FileInputStream(file.toFile())) {
+			BufferedReader br = new BufferedReader(
+					new InputStreamReader(is, "UTF-8"), 512);
+			String word = br.readLine();
+			if (word != null) {
+				if (word.startsWith("\uFEFF"))
+					word = word.substring(1);
+				for (; word != null; word = br.readLine()) {
+					word = word.trim();
+					if (word.isEmpty()) continue;
+					dict.fillSegment(word.toCharArray());
+				}
+			}
+		} catch (FileNotFoundException e) {
+			logger.error("ik-analyzer: " + name + " not found", e);
+			if (critical) throw new RuntimeException("ik-analyzer: " + name + " not found!!!", e);
+		} catch (IOException e) {
+			logger.error("ik-analyzer: " + name + " loading failed", e);
+		}
+	}
+
+	private List<String> getExtDictionarys() {
+		List<String> extDictFiles = new ArrayList<String>(2);
+		String extDictCfg = getProperty(EXT_DICT);
+		if (extDictCfg != null) {
+
+			String[] filePaths = extDictCfg.split(";");
+			for (String filePath : filePaths) {
+				if (filePath != null && !"".equals(filePath.trim())) {
+					Path file = PathUtils.get(getDictRoot(), filePath.trim());
+					walkFileTree(extDictFiles, file);
+
+				}
+			}
+		}
+		return extDictFiles;
+	}
+
+	private List<String> getRemoteExtDictionarys() {
+		List<String> remoteExtDictFiles = new ArrayList<String>(2);
+		String remoteExtDictCfg = getProperty(REMOTE_EXT_DICT);
+		if (remoteExtDictCfg != null) {
+
+			String[] filePaths = remoteExtDictCfg.split(";");
+			for (String filePath : filePaths) {
+				if (filePath != null && !"".equals(filePath.trim())) {
+					remoteExtDictFiles.add(filePath);
+
+				}
+			}
+		}
+		return remoteExtDictFiles;
+	}
+
+	private List<String> getExtStopWordDictionarys() {
+		List<String> extStopWordDictFiles = new ArrayList<String>(2);
+		String extStopWordDictCfg = getProperty(EXT_STOP);
+		if (extStopWordDictCfg != null) {
+
+			String[] filePaths = extStopWordDictCfg.split(";");
+			for (String filePath : filePaths) {
+				if (filePath != null && !"".equals(filePath.trim())) {
+					Path file = PathUtils.get(getDictRoot(), filePath.trim());
+					walkFileTree(extStopWordDictFiles, file);
+
+				}
+			}
+		}
+		return extStopWordDictFiles;
+	}
+
+	private List<String> getRemoteExtStopWordDictionarys() {
+		List<String> remoteExtStopWordDictFiles = new ArrayList<String>(2);
+		String remoteExtStopWordDictCfg = getProperty(REMOTE_EXT_STOP);
+		if (remoteExtStopWordDictCfg != null) {
+
+			String[] filePaths = remoteExtStopWordDictCfg.split(";");
+			for (String filePath : filePaths) {
+				if (filePath != null && !"".equals(filePath.trim())) {
+					remoteExtStopWordDictFiles.add(filePath);
+
+				}
+			}
+		}
+		return remoteExtStopWordDictFiles;
+	}
+
+	private String getDictRoot() {
+		return conf_dir.toAbsolutePath().toString();
+	}
+
 
 	/**
 	 * 获取词典单子实例
+	 * 
 	 * @return Dictionary 单例对象
 	 */
 	public static Dictionary getSingleton() {
 		if (singleton == null) {
-			throw new IllegalStateException("词典尚未初始化，请先调用initial方法");
+			throw new IllegalStateException("ik dict has not been initialized yet, please call initial method first.");
 		}
 		return singleton;
 	}
 
+
 	/**
 	 * 批量加载新词条
-	 * @param words Collection<String>词条列表
+	 * 
+	 * @param words
+	 *            Collection<String>词条列表
 	 */
 	public void addWords(Collection<String> words) {
 		if (words != null) {
@@ -172,6 +333,7 @@ public class Dictionary {
 
 	/**
 	 * 检索匹配主词典
+	 * 
 	 * @return Hit 匹配结果描述
 	 */
 	public Hit matchInMainDict(char[] charArray) {
@@ -180,6 +342,7 @@ public class Dictionary {
 
 	/**
 	 * 检索匹配主词典
+	 * 
 	 * @return Hit 匹配结果描述
 	 */
 	public Hit matchInMainDict(char[] charArray, int begin, int length) {
@@ -188,15 +351,16 @@ public class Dictionary {
 
 	/**
 	 * 检索匹配量词词典
+	 * 
 	 * @return Hit 匹配结果描述
 	 */
 	public Hit matchInQuantifierDict(char[] charArray, int begin, int length) {
 		return singleton._QuantifierDict.match(charArray, begin, length);
 	}
 
-	
 	/**
 	 * 从已匹配的Hit中直接取出DictSegment，继续向下匹配
+	 * 
 	 * @return Hit
 	 */
 	public Hit matchWithHit(char[] charArray, int currentIndex, Hit matchedHit) {
@@ -204,9 +368,9 @@ public class Dictionary {
 		return ds.match(charArray, currentIndex, 1, matchedHit);
 	}
 
-	
 	/**
 	 * 判断是否是停止词
+	 * 
 	 * @return boolean
 	 */
 	public boolean isStopWord(char[] charArray, int begin, int length) {
@@ -221,38 +385,8 @@ public class Dictionary {
 		_MainDict = new DictSegment((char) 0);
 
 		// 读取主词典文件
-		Path file = PathUtils.get(configuration.getDictRoot(), Dictionary.PATH_DIC_MAIN);
+		Path file = PathUtils.get(getDictRoot(), Dictionary.PATH_DIC_MAIN);
-
+		loadDictFile(_MainDict, file, false, "Main Dict");
-        InputStream is = null;
-        try {
-            is = new FileInputStream(file.toFile());
-        } catch (FileNotFoundException e) {
-            e.printStackTrace();
-        }
-        
-		try {
-			BufferedReader br = new BufferedReader(new InputStreamReader(is , "UTF-8"), 512);
-			String theWord = null;
-			do {
-				theWord = br.readLine();
-				if (theWord != null && !"".equals(theWord.trim())) {
-					_MainDict.fillSegment(theWord.trim().toCharArray());
-				}
-			} while (theWord != null);
-			
-		} catch (IOException e) {
-            logger.error("ik-analyzer",e);
-
-        }finally{
-			try {
-				if(is != null){
-                    is.close();
-                    is = null;
-				}
-			} catch (IOException e) {
-                logger.error("ik-analyzer",e);
-			}
-		}
 		// 加载扩展词典
 		this.loadExtDict();
 		// 加载远程自定义词库
@@ -264,65 +398,30 @@ public class Dictionary {
 	 */
 	private void loadExtDict() {
 		// 加载扩展词典配置
-		List<String> extDictFiles  = configuration.getExtDictionarys();
+		List<String> extDictFiles = getExtDictionarys();
 		if (extDictFiles != null) {
-			InputStream is = null;
 			for (String extDictName : extDictFiles) {
 				// 读取扩展词典文件
 				logger.info("[Dict Loading] " + extDictName);
-				Path file = PathUtils.get(configuration.getDictRoot(), extDictName);
+				Path file = PathUtils.get(extDictName);
-                try {
+				loadDictFile(_MainDict, file, false, "Extra Dict");
-                    is = new FileInputStream(file.toFile());
-                } catch (FileNotFoundException e) {
-                    logger.error("ik-analyzer",e);
-                }
-
-				//如果找不到扩展的字典，则忽略
-				if(is == null){
-					continue;
-				}
-				try {
-					BufferedReader br = new BufferedReader(new InputStreamReader(is , "UTF-8"), 512);
-					String theWord = null;
-					do {
-						theWord = br.readLine();
-                        if (theWord != null && !"".equals(theWord.trim())) {
-							//加载扩展词典数据到主内存词典中
-							_MainDict.fillSegment(theWord.trim().toCharArray());
-						}
-					} while (theWord != null);
-					
-				} catch (IOException e) {
-                    logger.error("ik-analyzer",e);
-                }finally{
-					try {
-						is.close();
-						is = null;
-					} catch (IOException e) {
-                        logger.error("ik-analyzer",e);
 			}
 		}
 	}
-		}		
-	}
-	
 
 	/**
 	 * 加载远程扩展词典到主词库表
 	 */
 	private void loadRemoteExtDict() {
-		List<String> remoteExtDictFiles  = configuration.getRemoteExtDictionarys();
+		List<String> remoteExtDictFiles = getRemoteExtDictionarys();
 		for (String location : remoteExtDictFiles) {
 			logger.info("[Dict Loading] " + location);
 			List<String> lists = getRemoteWords(location);
-			
-			/** Redundant Nullcheck as the list is initialized in the getRemoteWords method
 			// 如果找不到扩展的字典，则忽略
 			if (lists == null) {
-				logger.error("[Dict Loading] "+location+"加载失败");
+				logger.error("[Dict Loading] " + location + " load failed");
 				continue;
-			}*/
+			}
-			
 			for (String theWord : lists) {
 				if (theWord != null && !"".equals(theWord.trim())) {
 					// 加载扩展词典数据到主内存词典中
@@ -334,14 +433,21 @@ public class Dictionary {
 
 	}
 
+	private static List<String> getRemoteWords(String location) {
+		SpecialPermission.check();
+		return AccessController.doPrivileged((PrivilegedAction<List<String>>) () -> {
+			return getRemoteWordsUnprivileged(location);
+		});
+	}
+
 	/**
 	 * 从远程服务器上下载自定义词条
 	 */
-	private static List<String> getRemoteWords(String location){
+	private static List<String> getRemoteWordsUnprivileged(String location) {
 
 		List<String> buffer = new ArrayList<String>();
-		RequestConfig rc = RequestConfig.custom().setConnectionRequestTimeout(10*1000)
+		RequestConfig rc = RequestConfig.custom().setConnectionRequestTimeout(10 * 1000).setConnectTimeout(10 * 1000)
-				.setConnectTimeout(10*1000).setSocketTimeout(60*1000).build();
+				.setSocketTimeout(60 * 1000).build();
 		CloseableHttpClient httpclient = HttpClients.createDefault();
 		CloseableHttpResponse response;
 		BufferedReader in;
@@ -353,11 +459,18 @@ public class Dictionary {
 
 				String charset = "UTF-8";
 				// 获取编码，默认为utf-8
-				if(response.getEntity().getContentType().getValue().contains("charset=")){
+				HttpEntity entity = response.getEntity();
-					String contentType=response.getEntity().getContentType().getValue();
+				if(entity!=null){
-					charset=contentType.substring(contentType.lastIndexOf("=")+1);
+					Header contentType = entity.getContentType();
+					if(contentType!=null&&contentType.getValue()!=null){
+						String typeValue = contentType.getValue();
+						if(typeValue!=null&&typeValue.contains("charset=")){
+							charset = typeValue.substring(typeValue.lastIndexOf("=") + 1);
 						}
-				in = new BufferedReader(new InputStreamReader(response.getEntity().getContent(),charset));
+					}
+
+					if (entity.getContentLength() > 0 || entity.isChunked()) {
+						in = new BufferedReader(new InputStreamReader(entity.getContent(), charset));
 						String line;
 						while ((line = in.readLine()) != null) {
 							buffer.add(line);
@@ -366,19 +479,15 @@ public class Dictionary {
 						response.close();
 						return buffer;
 					}
+			}
+			}
 			response.close();
-		} catch (ClientProtocolException e) {
+		} catch (IllegalStateException | IOException e) {
-			logger.error( "getRemoteWords {} error" , e , location);
-		} catch (IllegalStateException e) {
-			logger.error( "getRemoteWords {} error" , e , location );
-		} catch (IOException e) {
 			logger.error("getRemoteWords {} error", e, location);
 		}
 		return buffer;
 	}
 
-	
-	
 	/**
 	 * 加载用户扩展的停止词词典
 	 */
@@ -387,96 +496,31 @@ public class Dictionary {
 		_StopWords = new DictSegment((char) 0);
 
 		// 读取主词典文件
-		Path file = PathUtils.get(configuration.getDictRoot(), Dictionary.PATH_DIC_STOP);
+		Path file = PathUtils.get(getDictRoot(), Dictionary.PATH_DIC_STOP);
-
+		loadDictFile(_StopWords, file, false, "Main Stopwords");
-        InputStream is = null;
-        try {
-            is = new FileInputStream(file.toFile());
-        } catch (FileNotFoundException e) {
-            e.printStackTrace();
-        }
-
-        try {
-            BufferedReader br = new BufferedReader(new InputStreamReader(is , "UTF-8"), 512);
-            String theWord = null;
-            do {
-                theWord = br.readLine();
-                if (theWord != null && !"".equals(theWord.trim())) {
-                    _StopWords.fillSegment(theWord.trim().toCharArray());
-                }
-            } while (theWord != null);
-
-        } catch (IOException e) {
-            logger.error("ik-analyzer",e);
-
-        }finally{
-            try {
-                if(is != null){
-                    is.close();
-                    is = null;
-                }
-            } catch (IOException e) {
-                logger.error("ik-analyzer",e);
-            }
-        }
-
 
 		// 加载扩展停止词典
-		List<String> extStopWordDictFiles  = configuration.getExtStopWordDictionarys();
+		List<String> extStopWordDictFiles = getExtStopWordDictionarys();
 		if (extStopWordDictFiles != null) {
-			is = null;
 			for (String extStopWordDictName : extStopWordDictFiles) {
 				logger.info("[Dict Loading] " + extStopWordDictName);
 
 				// 读取扩展词典文件
-                file=PathUtils.get(configuration.getDictRoot(), extStopWordDictName);
+				file = PathUtils.get(extStopWordDictName);
-                try {
+				loadDictFile(_StopWords, file, false, "Extra Stopwords");
-                    is = new FileInputStream(file.toFile());
-                } catch (FileNotFoundException e) {
-                    logger.error("ik-analyzer",e);
-                }
-				//如果找不到扩展的字典，则忽略
-				if(is == null){
-					continue;
-				}
-				try {
-					BufferedReader br = new BufferedReader(new InputStreamReader(is , "UTF-8"), 512);
-					String theWord = null;
-					do {
-						theWord = br.readLine();
-						if (theWord != null && !"".equals(theWord.trim())) {
-							//加载扩展停止词典数据到内存中
-                            _StopWords.fillSegment(theWord.trim().toCharArray());
-						}
-					} while (theWord != null);
-					
-				} catch (IOException e) {
-                    logger.error("ik-analyzer",e);
-					
-				}finally{
-					try {
-						is.close();
-						is = null;
-					} catch (IOException e) {
-                        logger.error("ik-analyzer",e);
-					}
-				}
 			}
 		}
 
 		// 加载远程停用词典
-		List<String> remoteExtStopWordDictFiles  = configuration.getRemoteExtStopWordDictionarys();
+		List<String> remoteExtStopWordDictFiles = getRemoteExtStopWordDictionarys();
 		for (String location : remoteExtStopWordDictFiles) {
 			logger.info("[Dict Loading] " + location);
 			List<String> lists = getRemoteWords(location);
-			
-			/** Redundant Nullcheck as the list is initialized in the getRemoteWords method
 			// 如果找不到扩展的字典，则忽略
 			if (lists == null) {
-				logger.error("[Dict Loading] "+location+"加载失败");
+				logger.error("[Dict Loading] " + location + " load failed");
 				continue;
-			}*/
+			}
-			
 			for (String theWord : lists) {
 				if (theWord != null && !"".equals(theWord.trim())) {
 					// 加载远程词典数据到主内存中
@@ -486,7 +530,6 @@ public class Dictionary {
 			}
 		}
 
-		
 	}
 
 	/**
@@ -496,156 +539,38 @@ public class Dictionary {
 		// 建立一个量词典实例
 		_QuantifierDict = new DictSegment((char) 0);
 		// 读取量词词典文件
-		Path file = PathUtils.get(configuration.getDictRoot(), Dictionary.PATH_DIC_QUANTIFIER);
+		Path file = PathUtils.get(getDictRoot(), Dictionary.PATH_DIC_QUANTIFIER);
-        InputStream is = null;
+		loadDictFile(_QuantifierDict, file, false, "Quantifier");
-        try {
-            is = new FileInputStream(file.toFile());
-        } catch (FileNotFoundException e) {
-            logger.error("ik-analyzer",e);
 	}
-		try {
-			BufferedReader br = new BufferedReader(new InputStreamReader(is , "UTF-8"), 512);
-			String theWord = null;
-			do {
-				theWord = br.readLine();
-				if (theWord != null && !"".equals(theWord.trim())) {
-					_QuantifierDict.fillSegment(theWord.trim().toCharArray());
-				}
-			} while (theWord != null);
-			
-		} catch (IOException ioe) {
-			logger.error("Quantifier Dictionary loading exception.");
-			
-		}finally{
-			try {
-				if(is != null){
-                    is.close();
-                    is = null;
-				}
-			} catch (IOException e) {
-                logger.error("ik-analyzer",e);
-			}
-		}
-	}
-
 
 	private void loadSurnameDict() {
-
+		DictSegment _SurnameDict = new DictSegment((char) 0);
-        _SurnameDict = new DictSegment((char)0);
+		Path file = PathUtils.get(getDictRoot(), Dictionary.PATH_DIC_SURNAME);
-		Path file = PathUtils.get(configuration.getDictRoot(), Dictionary.PATH_DIC_SURNAME);
+		loadDictFile(_SurnameDict, file, true, "Surname");
-        InputStream is = null;
-        try {
-            is = new FileInputStream(file.toFile());
-        } catch (FileNotFoundException e) {
-            logger.error("ik-analyzer",e);
 	}
-        if(is == null){
-            throw new RuntimeException("Surname Dictionary not found!!!");
-        }
-        try {
-            BufferedReader br = new BufferedReader(new InputStreamReader(is , "UTF-8"), 512);
-            String theWord;
-            do {
-                theWord = br.readLine();
-                if (theWord != null && !"".equals(theWord.trim())) {
-                    _SurnameDict.fillSegment(theWord.trim().toCharArray());
-                }
-            } while (theWord != null);
-        } catch (IOException e) {
-            logger.error("ik-analyzer",e);
-        }finally{
-            try {
-				is.close();
-				is = null;
-            } catch (IOException e) {
-                logger.error("ik-analyzer",e);
-            }
-        }
-    }
-
 
 	private void loadSuffixDict() {
-
+		DictSegment _SuffixDict = new DictSegment((char) 0);
-        _SuffixDict = new DictSegment((char)0);
+		Path file = PathUtils.get(getDictRoot(), Dictionary.PATH_DIC_SUFFIX);
-		Path file = PathUtils.get(configuration.getDictRoot(), Dictionary.PATH_DIC_SUFFIX);
+		loadDictFile(_SuffixDict, file, true, "Suffix");
-        InputStream is = null;
-        try {
-            is = new FileInputStream(file.toFile());
-        } catch (FileNotFoundException e) {
-            logger.error("ik-analyzer",e);
 	}
-        if(is == null){
-            throw new RuntimeException("Suffix Dictionary not found!!!");
-        }
-        try {
-
-            BufferedReader br = new BufferedReader(new InputStreamReader(is , "UTF-8"), 512);
-            String theWord;
-            do {
-                theWord = br.readLine();
-                if (theWord != null && !"".equals(theWord.trim())) {
-                    _SuffixDict.fillSegment(theWord.trim().toCharArray());
-                }
-            } while (theWord != null);
-        } catch (IOException e) {
-            logger.error("ik-analyzer",e);
-        }finally{
-            try {
-                is.close();
-                is = null;
-            } catch (IOException e) {
-                logger.error("ik-analyzer",e);
-            }
-        }
-    }
-
 
 	private void loadPrepDict() {
-
+		DictSegment _PrepDict = new DictSegment((char) 0);
-        _PrepDict = new DictSegment((char)0);
+		Path file = PathUtils.get(getDictRoot(), Dictionary.PATH_DIC_PREP);
-		Path file = PathUtils.get(configuration.getDictRoot(), Dictionary.PATH_DIC_PREP);
+		loadDictFile(_PrepDict, file, true, "Preposition");
-        InputStream is = null;
-        try {
-            is = new FileInputStream(file.toFile());
-        } catch (FileNotFoundException e) {
-            logger.error("ik-analyzer",e);
-        }
-        if(is == null){
-            throw new RuntimeException("Preposition Dictionary not found!!!");
-        }
-        try {
-
-            BufferedReader br = new BufferedReader(new InputStreamReader(is , "UTF-8"), 512);
-            String theWord;
-            do {
-                theWord = br.readLine();
-                if (theWord != null && !"".equals(theWord.trim())) {
-
-                    _PrepDict.fillSegment(theWord.trim().toCharArray());
-                }
-            } while (theWord != null);
-        } catch (IOException e) {
-            logger.error("ik-analyzer",e);
-        }finally{
-            try {
-                is.close();
-                is = null;
-            } catch (IOException e) {
-                logger.error("ik-analyzer",e);
-            }
-        }
 	}
 
-    public void reLoadMainDict(){
+	void reLoadMainDict() {
-    	logger.info("重新加载词典...");
+		logger.info("start to reload ik dict.");
 		// 新开一个实例加载词典，减少加载过程对当前词典使用的影响
-		Dictionary tmpDict = new Dictionary();
+		Dictionary tmpDict = new Dictionary(configuration);
 		tmpDict.configuration = getSingleton().configuration;
 		tmpDict.loadMainDict();
 		tmpDict.loadStopWordDict();
 		_MainDict = tmpDict._MainDict;
 		_StopWords = tmpDict._StopWords;
-		logger.info("重新加载词典完毕...");
+		logger.info("reload ik dict finished.");
 	}
 
 }

src/main/java/org/wltea/analyzer/dic/Monitor.java

@@ -1,15 +1,22 @@
 package org.wltea.analyzer.dic;
 
 import java.io.IOException;
+import java.security.AccessController;
+import java.security.PrivilegedAction;
 
 import org.apache.http.client.config.RequestConfig;
 import org.apache.http.client.methods.CloseableHttpResponse;
 import org.apache.http.client.methods.HttpHead;
 import org.apache.http.impl.client.CloseableHttpClient;
 import org.apache.http.impl.client.HttpClients;
+import org.apache.logging.log4j.Logger;
+import org.elasticsearch.SpecialPermission;
+import org.wltea.analyzer.help.ESPluginLoggerFactory;
 
 public class Monitor implements Runnable {
 
+	private static final Logger logger = ESPluginLoggerFactory.getLogger(Monitor.class.getName());
+
 	private static CloseableHttpClient httpclient = HttpClients.createDefault();
 	/*
 	 * 上次更改时间
@@ -30,6 +37,15 @@ public class Monitor implements Runnable {
 		this.last_modified = null;
 		this.eTags = null;
 	}
+
+	public void run() {
+		SpecialPermission.check();
+		AccessController.doPrivileged((PrivilegedAction<Void>) () -> {
+			this.runUnprivileged();
+			return null;
+		});
+	}
+
 	/**
 	 * 监控流程：
 	 *  ①向词库服务器发送Head请求
@@ -39,7 +55,7 @@ public class Monitor implements Runnable {
 	 *  ⑤休眠1min，返回第①步
 	 */
 
-	public void run() {
+	public void runUnprivileged() {
 
 		//超时设置
 		RequestConfig rc = RequestConfig.custom().setConnectionRequestTimeout(10*1000)
@@ -64,8 +80,8 @@ public class Monitor implements Runnable {
 			//返回200 才做操作
 			if(response.getStatusLine().getStatusCode()==200){
 
-				if (!response.getLastHeader("Last-Modified").getValue().equalsIgnoreCase(last_modified)
+				if (((response.getLastHeader("Last-Modified")!=null) && !response.getLastHeader("Last-Modified").getValue().equalsIgnoreCase(last_modified))
-					||!response.getLastHeader("ETag").getValue().equalsIgnoreCase(eTags)) {
+						||((response.getLastHeader("ETag")!=null) && !response.getLastHeader("ETag").getValue().equalsIgnoreCase(eTags))) {
 
 					// 远程词库有更新,需要重新加载词典，并修改last_modified,eTags
 					Dictionary.getSingleton().reLoadMainDict();
@@ -76,18 +92,18 @@ public class Monitor implements Runnable {
 				//没有修改，不做操作
 				//noop
 			}else{
-				Dictionary.logger.info("remote_ext_dict {} return bad code {}" , location , response.getStatusLine().getStatusCode() );
+				logger.info("remote_ext_dict {} return bad code {}" , location , response.getStatusLine().getStatusCode() );
 			}
 
 		} catch (Exception e) {
-			Dictionary.logger.error("remote_ext_dict {} error!",e , location);
+			logger.error("remote_ext_dict {} error!",e , location);
 		}finally{
 			try {
 				if (response != null) {
 					response.close();
 				}
 			} catch (IOException e) {
-				e.printStackTrace();
+				logger.error(e.getMessage(), e);
 			}
 		}
 	}

src/main/java/org/wltea/analyzer/help/ESPluginLoggerFactory.java

@@ -0,0 +1,27 @@
+package org.wltea.analyzer.help;
+
+import org.apache.logging.log4j.LogManager;
+import org.apache.logging.log4j.Logger;
+import org.apache.logging.log4j.spi.ExtendedLogger;
+
+public class ESPluginLoggerFactory {
+
+    private ESPluginLoggerFactory() {
+    }
+
+    static public Logger getLogger(String name) {
+        return getLogger("", LogManager.getLogger(name));
+    }
+
+    static public Logger getLogger(String prefix, String name) {
+        return getLogger(prefix, LogManager.getLogger(name));
+    }
+
+    static public Logger getLogger(String prefix, Class<?> clazz) {
+        return getLogger(prefix, LogManager.getLogger(clazz.getName()));
+    }
+
+    static public Logger getLogger(String prefix, Logger logger) {
+        return (Logger)(prefix != null && prefix.length() != 0 ? new PrefixPluginLogger((ExtendedLogger)logger, logger.getName(), prefix) : logger);
+    }
+}

src/main/java/org/wltea/analyzer/help/PrefixPluginLogger.java

@@ -0,0 +1,48 @@
+package org.wltea.analyzer.help;
+
+import org.apache.logging.log4j.Level;
+import org.apache.logging.log4j.Marker;
+import org.apache.logging.log4j.MarkerManager;
+import org.apache.logging.log4j.message.Message;
+import org.apache.logging.log4j.message.MessageFactory;
+import org.apache.logging.log4j.spi.ExtendedLogger;
+import org.apache.logging.log4j.spi.ExtendedLoggerWrapper;
+
+import java.util.WeakHashMap;
+
+public class PrefixPluginLogger extends ExtendedLoggerWrapper {
+    private static final WeakHashMap<String, Marker> markers = new WeakHashMap();
+    private final Marker marker;
+
+    static int markersSize() {
+        return markers.size();
+    }
+
+    public String prefix() {
+        return this.marker.getName();
+    }
+
+    PrefixPluginLogger(ExtendedLogger logger, String name, String prefix) {
+        super(logger, name, (MessageFactory) null);
+        String actualPrefix = prefix == null ? "" : prefix;
+        WeakHashMap var6 = markers;
+        MarkerManager.Log4jMarker actualMarker;
+        synchronized (markers) {
+            MarkerManager.Log4jMarker maybeMarker = (MarkerManager.Log4jMarker) markers.get(actualPrefix);
+            if (maybeMarker == null) {
+                actualMarker = new MarkerManager.Log4jMarker(actualPrefix);
+                markers.put(new String(actualPrefix), actualMarker);
+            } else {
+                actualMarker = maybeMarker;
+            }
+        }
+
+        this.marker = (Marker) actualMarker;
+    }
+
+    public void logMessage(String fqcn, Level level, Marker marker, Message message, Throwable t) {
+        assert marker == null;
+
+        super.logMessage(fqcn, level, this.marker, message, t);
+    }
+}

src/main/java/org/wltea/analyzer/help/Sleep.java

@@ -1,13 +1,15 @@
 package org.wltea.analyzer.help;
 
-import org.elasticsearch.common.logging.ESLogger;
+import org.apache.logging.log4j.Logger;
-import org.elasticsearch.common.logging.Loggers;
 
 public class Sleep {
 
-    public static final ESLogger logger= Loggers.getLogger("ik-analyzer");
+    private static final Logger logger = ESPluginLoggerFactory.getLogger(Sleep.class.getName());
+
+    public enum Type {MSEC, SEC, MIN, HOUR}
+
+    ;
 
-	public enum Type{MSEC,SEC,MIN,HOUR};
     public static void sleep(Type type, int num) {
         try {
             switch (type) {
@@ -15,20 +17,20 @@ public class Sleep {
                     Thread.sleep(num);
                     return;
                 case SEC:
-					Thread.sleep(num*1000L);
+                    Thread.sleep(num * 1000);
                     return;
                 case MIN:
-					Thread.sleep(num*60*1000L);
+                    Thread.sleep(num * 60 * 1000);
                     return;
                 case HOUR:
-					Thread.sleep(num*60*60*1000L);
+                    Thread.sleep(num * 60 * 60 * 1000);
                     return;
                 default:
-                    logger.error("输入类型错误，应为MSEC,SEC,MIN,HOUR之一");
+                    System.err.println("输入类型错误，应为MSEC,SEC,MIN,HOUR之一");
                     return;
             }
         } catch (InterruptedException e) {
-			e.printStackTrace();
+            logger.error(e.getMessage(), e);
         }
     }
 

src/main/java/org/wltea/analyzer/lucene/IKAnalyzer.java

@@ -26,6 +26,7 @@ package org.wltea.analyzer.lucene;
 
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.Tokenizer;
+import org.wltea.analyzer.cfg.Configuration;
 
 /**
  * IK分词器，Lucene Analyzer接口实现
@@ -33,15 +34,7 @@ import org.apache.lucene.analysis.Tokenizer;
  */
 public final class IKAnalyzer extends Analyzer{
 	
-	private boolean useSmart;
+	private Configuration configuration;
-
-    public boolean useSmart() {
-		return useSmart;
-	}
-
-	public void setUseSmart(boolean useSmart) {
-		this.useSmart = useSmart;
-	}
 
 	/**
 	 * IK分词器Lucene  Analyzer接口实现类
@@ -54,11 +47,11 @@ public final class IKAnalyzer extends Analyzer{
     /**
 	 * IK分词器Lucene Analyzer接口实现类
 	 * 
-	 * @param useSmart 当为true时，分词器进行智能切分
+	 * @param configuration IK配置
 	 */
-	public IKAnalyzer(boolean useSmart){
+	public IKAnalyzer(Configuration configuration){
 		super();
-        this.useSmart = useSmart;
+        this.configuration = configuration;
 	}
 
 
@@ -67,7 +60,7 @@ public final class IKAnalyzer extends Analyzer{
 	 */
 	@Override
 	protected TokenStreamComponents createComponents(String fieldName) {
-        Tokenizer _IKTokenizer = new IKTokenizer(useSmart);
+        Tokenizer _IKTokenizer = new IKTokenizer(configuration);
 		return new TokenStreamComponents(_IKTokenizer);
     }
 

src/main/java/org/wltea/analyzer/lucene/IKTokenizer.java

@@ -32,6 +32,7 @@ import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
 import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.env.Environment;
+import org.wltea.analyzer.cfg.Configuration;
 import org.wltea.analyzer.core.IKSegmenter;
 import org.wltea.analyzer.core.Lexeme;
 
@@ -64,16 +65,15 @@ public final class IKTokenizer extends Tokenizer {
 
     /**
 	 * Lucene 4.0 Tokenizer适配器类构造函数
-	 * @param in
      */
-	public IKTokenizer(boolean useSmart){
+	public IKTokenizer(Configuration configuration){
 	    super();
 	    offsetAtt = addAttribute(OffsetAttribute.class);
 	    termAtt = addAttribute(CharTermAttribute.class);
 	    typeAtt = addAttribute(TypeAttribute.class);
         posIncrAtt = addAttribute(PositionIncrementAttribute.class);
 
-        _IKImplement = new IKSegmenter(input,useSmart);
+        _IKImplement = new IKSegmenter(input,configuration);
 	}
 
 	/* (non-Javadoc)

src/main/java/org/wltea/analyzer/query/IKQueryExpressionParser.java

@@ -1,716 +0,0 @@
-/**
- * IK 中文分词  版本 5.0
- * IK Analyzer release 5.0
- * 
- * 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.
- *
- * 源代码由林良益(linliangyi2005@gmail.com)提供
- * 版权声明 2012，乌龙茶工作室
- * provided by Linliangyi and copyright 2012 by Oolong studio
- * 
- */
-package org.wltea.analyzer.query;
-
-import org.apache.lucene.index.Term;
-import org.apache.lucene.search.*;
-import org.apache.lucene.search.BooleanClause.Occur;
-import org.apache.lucene.util.BytesRef;
-import org.elasticsearch.common.logging.ESLogger;
-import org.elasticsearch.common.logging.Loggers;
-
-import java.util.ArrayList;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.Stack;
-
-/**
- * IK简易查询表达式解析 
- * 结合SWMCQuery算法
- * 
- * 表达式例子 ：
- * (id='1231231' && title:'monkey') || (content:'你好吗'  || ulr='www.ik.com') - name:'helloword'
- * @author linliangyi
- *
- */
-public class IKQueryExpressionParser {
-
-    public static final ESLogger logger= Loggers.getLogger("ik-analyzer");
-    
-	//public static final String LUCENE_SPECIAL_CHAR = "&&||-()':={}[],";
-	
-	private List<Element> elements = new ArrayList<Element>();
-	
-	private Stack<Query> querys =  new Stack<Query>();
-	
-	private Stack<Element> operates = new Stack<Element>();
-	
-	/**
-	 * 解析查询表达式，生成Lucene Query对象
-	 * 
-	 * @param expression
-	 * @param quickMode 
-	 * @return Lucene query
-	 */
-	public Query parseExp(String expression , boolean quickMode){
-		Query lucenceQuery = null;
-		if(expression != null && !"".equals(expression)){
-			try{
-				//文法解析
-				this.splitElements(expression);
-				//语法解析
-				this.parseSyntax(quickMode);
-				if(this.querys.size() == 1){
-					lucenceQuery = this.querys.pop();
-				}else{
-					throw new IllegalStateException("表达式异常： 缺少逻辑操作符 或 括号缺失");
-				}
-			}finally{
-				elements.clear();
-				querys.clear();
-				operates.clear();
-			}
-		}
-		return lucenceQuery;
-	}	
-	
-	/**
-	 * 表达式文法解析
-	 * @param expression
-	 */
-	private void splitElements(String expression){
- 		
-		if(expression == null){
-			return;
-		}
-		Element curretElement = null;
-		
-		char[] expChars = expression.toCharArray();
-		for(int i = 0 ; i < expChars.length ; i++){
-			switch(expChars[i]){
-			case '&' :
-				if(curretElement == null){
-					curretElement = new Element();
-					curretElement.type = '&';
-					curretElement.append(expChars[i]);
-				}else if(curretElement.type == '&'){
-					curretElement.append(expChars[i]);
-					this.elements.add(curretElement);
-					curretElement = null;
-				}else if(curretElement.type == '\''){
-					curretElement.append(expChars[i]);
-				}else {
-					this.elements.add(curretElement);
-					curretElement = new Element();
-					curretElement.type = '&';
-					curretElement.append(expChars[i]);
-				}
-				break;
-				
-			case '|' :
-				if(curretElement == null){
-					curretElement = new Element();
-					curretElement.type = '|';
-					curretElement.append(expChars[i]);
-				}else if(curretElement.type == '|'){
-					curretElement.append(expChars[i]);
-					this.elements.add(curretElement);
-					curretElement = null;
-				}else if(curretElement.type == '\''){
-					curretElement.append(expChars[i]);
-				}else {
-					this.elements.add(curretElement);
-					curretElement = new Element();
-					curretElement.type = '|';
-					curretElement.append(expChars[i]);
-				}				
-				break;
-				
-			case '-' :
-				if(curretElement != null){
-					if(curretElement.type == '\''){
-						curretElement.append(expChars[i]);
-						continue;
-					}else{
-						this.elements.add(curretElement);
-					}
-				}
-				curretElement = new Element();
-				curretElement.type = '-';
-				curretElement.append(expChars[i]);
-				this.elements.add(curretElement);
-				curretElement = null;			
-				break;
-
-			case '(' :
-				if(curretElement != null){
-					if(curretElement.type == '\''){
-						curretElement.append(expChars[i]);
-						continue;
-					}else{
-						this.elements.add(curretElement);
-					}
-				}
-				curretElement = new Element();
-				curretElement.type = '(';
-				curretElement.append(expChars[i]);
-				this.elements.add(curretElement);
-				curretElement = null;			
-				break;				
-
-			case ')' :
-				if(curretElement != null){
-					if(curretElement.type == '\''){
-						curretElement.append(expChars[i]);
-						continue;
-					}else{
-						this.elements.add(curretElement);
-					}
-				}
-				curretElement = new Element();
-				curretElement.type = ')';
-				curretElement.append(expChars[i]);
-				this.elements.add(curretElement);
-				curretElement = null;			
-				break;					
-
-			case ':' :
-				if(curretElement != null){
-					if(curretElement.type == '\''){
-						curretElement.append(expChars[i]);
-						continue;
-					}else{
-						this.elements.add(curretElement);
-					}
-				}
-				curretElement = new Element();
-				curretElement.type = ':';
-				curretElement.append(expChars[i]);
-				this.elements.add(curretElement);
-				curretElement = null;			
-				break;	
-			
-			case '=' :
-				if(curretElement != null){
-					if(curretElement.type == '\''){
-						curretElement.append(expChars[i]);
-						continue;
-					}else{
-						this.elements.add(curretElement);
-					}
-				}
-				curretElement = new Element();
-				curretElement.type = '=';
-				curretElement.append(expChars[i]);
-				this.elements.add(curretElement);
-				curretElement = null;			
-				break;					
-
-			case ' ' :
-				if(curretElement != null){
-					if(curretElement.type == '\''){
-						curretElement.append(expChars[i]);
-					}else{
-						this.elements.add(curretElement);
-						curretElement = null;
-					}
-				}
-				
-				break;
-			
-			case '\'' :
-				if(curretElement == null){
-					curretElement = new Element();
-					curretElement.type = '\'';
-					
-				}else if(curretElement.type == '\''){
-					this.elements.add(curretElement);
-					curretElement = null;
-					
-				}else{
-					this.elements.add(curretElement);
-					curretElement = new Element();
-					curretElement.type = '\'';
-					
-				}
-				break;
-				
-			case '[':
-				if(curretElement != null){
-					if(curretElement.type == '\''){
-						curretElement.append(expChars[i]);
-						continue;
-					}else{
-						this.elements.add(curretElement);
-					}
-				}
-				curretElement = new Element();
-				curretElement.type = '[';
-				curretElement.append(expChars[i]);
-				this.elements.add(curretElement);
-				curretElement = null;					
-				break;
-				
-			case ']':
-				if(curretElement != null){
-					if(curretElement.type == '\''){
-						curretElement.append(expChars[i]);
-						continue;
-					}else{
-						this.elements.add(curretElement);
-					}
-				}
-				curretElement = new Element();
-				curretElement.type = ']';
-				curretElement.append(expChars[i]);
-				this.elements.add(curretElement);
-				curretElement = null;
-				
-				break;
-				
-			case '{':
-				if(curretElement != null){
-					if(curretElement.type == '\''){
-						curretElement.append(expChars[i]);
-						continue;
-					}else{
-						this.elements.add(curretElement);
-					}
-				}
-				curretElement = new Element();
-				curretElement.type = '{';
-				curretElement.append(expChars[i]);
-				this.elements.add(curretElement);
-				curretElement = null;					
-				break;
-				
-			case '}':
-				if(curretElement != null){
-					if(curretElement.type == '\''){
-						curretElement.append(expChars[i]);
-						continue;
-					}else{
-						this.elements.add(curretElement);
-					}
-				}
-				curretElement = new Element();
-				curretElement.type = '}';
-				curretElement.append(expChars[i]);
-				this.elements.add(curretElement);
-				curretElement = null;
-				
-				break;
-			case ',':
-				if(curretElement != null){
-					if(curretElement.type == '\''){
-						curretElement.append(expChars[i]);
-						continue;
-					}else{
-						this.elements.add(curretElement);
-					}
-				}
-				curretElement = new Element();
-				curretElement.type = ',';
-				curretElement.append(expChars[i]);
-				this.elements.add(curretElement);
-				curretElement = null;
-				
-				break;
-				
-			default :
-				if(curretElement == null){
-					curretElement = new Element();
-					curretElement.type = 'F';
-					curretElement.append(expChars[i]);
-					
-				}else if(curretElement.type == 'F'){
-					curretElement.append(expChars[i]);
-					
-				}else if(curretElement.type == '\''){
-					curretElement.append(expChars[i]);
-
-				}else{
-					this.elements.add(curretElement);
-					curretElement = new Element();
-					curretElement.type = 'F';
-					curretElement.append(expChars[i]);
-				}			
-			}
-		}
-		
-		if(curretElement != null){
-			this.elements.add(curretElement);
-			curretElement = null;
-		}
-	}
-		
-	/**
-	 * 语法解析
-	 * 
-	 */
-	private void parseSyntax(boolean quickMode){
-		for(int i = 0 ; i < this.elements.size() ; i++){
-			Element e = this.elements.get(i);
-			if('F' == e.type){
-				Element e2 = this.elements.get(i + 1);
-				if('=' != e2.type && ':' != e2.type){
-					throw new IllegalStateException("表达式异常： = 或 ： 号丢失");
-				}
-				Element e3 = this.elements.get(i + 2);
-				//处理 = 和 ： 运算
-				if('\'' == e3.type){
-					i+=2;
-					if('=' == e2.type){
-						TermQuery tQuery = new TermQuery(new Term(e.toString() , e3.toString()));
-						this.querys.push(tQuery);
-					}else if(':' == e2.type){
-						String keyword = e3.toString();
-						//SWMCQuery Here
-						Query _SWMCQuery =  SWMCQueryBuilder.create(e.toString(), keyword , quickMode);
-						this.querys.push(_SWMCQuery);
-					}
-					
-				}else if('[' == e3.type || '{' == e3.type){
-					i+=2;
-					//处理 [] 和 {}
-					LinkedList<Element> eQueue = new LinkedList<Element>();
-					eQueue.add(e3);
-					for( i++ ; i < this.elements.size() ; i++){							
-						Element eN = this.elements.get(i);
-						eQueue.add(eN);
-						if(']' == eN.type || '}' == eN.type){
-							break;
-						}
-					}
-					//翻译RangeQuery
-					Query rangeQuery = this.toTermRangeQuery(e , eQueue);
-					this.querys.push(rangeQuery);
-				}else{
-					throw new IllegalStateException("表达式异常：匹配值丢失");
-				}
-				
-			}else if('(' == e.type){
-				this.operates.push(e);
-				
-			}else if(')' == e.type){
-				boolean doPop = true;
-				while(doPop && !this.operates.empty()){
-					Element op = this.operates.pop();
-					if('(' == op.type){
-						doPop = false;
-					}else {
-						Query q = toBooleanQuery(op);
-						this.querys.push(q);
-					}
-					
-				}
-			}else{ 
-				
-				if(this.operates.isEmpty()){
-					this.operates.push(e);
-				}else{
-					boolean doPeek = true;
-					while(doPeek && !this.operates.isEmpty()){
-						Element eleOnTop = this.operates.peek();
-						if('(' == eleOnTop.type){
-							doPeek = false;
-							this.operates.push(e);
-						}else if(compare(e , eleOnTop) == 1){
-							this.operates.push(e);
-							doPeek = false;
-						}else if(compare(e , eleOnTop) == 0){
-							Query q = toBooleanQuery(eleOnTop);
-							this.operates.pop();
-							this.querys.push(q);
-						}else{
-							Query q = toBooleanQuery(eleOnTop);
-							this.operates.pop();
-							this.querys.push(q);
-						}
-					}
-					
-					if(doPeek && this.operates.empty()){
-						this.operates.push(e);
-					}
-				}
-			}			
-		}
-		
-		while(!this.operates.isEmpty()){
-			Element eleOnTop = this.operates.pop();
-			Query q = toBooleanQuery(eleOnTop);
-			this.querys.push(q);			
-		}		
-	}
-
-	/**
-	 * 根据逻辑操作符，生成BooleanQuery
-	 * @param op
-	 * @return
-	 */
-	private Query toBooleanQuery(Element op){
-		if(this.querys.size() == 0){
-			return null;
-		}
-		
-		BooleanQuery resultQuery = new BooleanQuery();
-
-		if(this.querys.size() == 1){
-			return this.querys.get(0);
-		}
-		
-		Query q2 = this.querys.pop();
-		Query q1 = this.querys.pop();
-		if('&' == op.type){
-			if(q1 != null){
-				if(q1 instanceof BooleanQuery){
-					BooleanClause[] clauses = ((BooleanQuery)q1).getClauses();
-					if(clauses.length > 0 
-							&& clauses[0].getOccur() == Occur.MUST){
-						for(BooleanClause c : clauses){
-							resultQuery.add(c);
-						}					
-					}else{
-						resultQuery.add(q1,Occur.MUST);
-					}
-
-				}else{
-					//q1 instanceof TermQuery 
-					//q1 instanceof TermRangeQuery 
-					//q1 instanceof PhraseQuery
-					//others
-					resultQuery.add(q1,Occur.MUST);
-				}
-			}
-			
-			if(q2 != null){
-				if(q2 instanceof BooleanQuery){
-					BooleanClause[] clauses = ((BooleanQuery)q2).getClauses();
-					if(clauses.length > 0 
-							&& clauses[0].getOccur() == Occur.MUST){
-						for(BooleanClause c : clauses){
-							resultQuery.add(c);
-						}					
-					}else{
-						resultQuery.add(q2,Occur.MUST);
-					}
-					
-				}else{
-					//q1 instanceof TermQuery 
-					//q1 instanceof TermRangeQuery 
-					//q1 instanceof PhraseQuery
-					//others
-					resultQuery.add(q2,Occur.MUST);
-				}
-			}
-			
-		}else if('|' == op.type){
-			if(q1 != null){
-				if(q1 instanceof BooleanQuery){
-					BooleanClause[] clauses = ((BooleanQuery)q1).getClauses();
-					if(clauses.length > 0 
-							&& clauses[0].getOccur() == Occur.SHOULD){
-						for(BooleanClause c : clauses){
-							resultQuery.add(c);
-						}					
-					}else{
-						resultQuery.add(q1,Occur.SHOULD);
-					}
-					
-				}else{
-					//q1 instanceof TermQuery 
-					//q1 instanceof TermRangeQuery 
-					//q1 instanceof PhraseQuery
-					//others
-					resultQuery.add(q1,Occur.SHOULD);
-				}
-			}
-			
-			if(q2 != null){
-				if(q2 instanceof BooleanQuery){
-					BooleanClause[] clauses = ((BooleanQuery)q2).getClauses();
-					if(clauses.length > 0 
-							&& clauses[0].getOccur() == Occur.SHOULD){
-						for(BooleanClause c : clauses){
-							resultQuery.add(c);
-						}					
-					}else{
-						resultQuery.add(q2,Occur.SHOULD);
-					}
-				}else{
-					//q2 instanceof TermQuery 
-					//q2 instanceof TermRangeQuery 
-					//q2 instanceof PhraseQuery
-					//others
-					resultQuery.add(q2,Occur.SHOULD);
-					
-				}
-			}
-			
-		}else if('-' == op.type){
-			if(q1 == null || q2 == null){
-				throw new IllegalStateException("表达式异常：SubQuery 个数不匹配");
-			}
-			
-			if(q1 instanceof BooleanQuery){
-				BooleanClause[] clauses = ((BooleanQuery)q1).getClauses();
-				if(clauses.length > 0){
-					for(BooleanClause c : clauses){
-						resultQuery.add(c);
-					}					
-				}else{
-					resultQuery.add(q1,Occur.MUST);
-				}
-
-			}else{
-				//q1 instanceof TermQuery 
-				//q1 instanceof TermRangeQuery 
-				//q1 instanceof PhraseQuery
-				//others
-				resultQuery.add(q1,Occur.MUST);
-			}				
-			
-			resultQuery.add(q2,Occur.MUST_NOT);
-		}
-		return resultQuery;
-	}	
-	
-	/**
-	 * 组装TermRangeQuery
-	 * @param elements
-	 * @return
-	 */
-	private TermRangeQuery toTermRangeQuery(Element fieldNameEle , LinkedList<Element> elements){
-
-		boolean includeFirst = false;
-		boolean includeLast = false;
-		String firstValue = null;
-		String lastValue = null;
-		//检查第一个元素是否是[或者{
-		Element first = elements.getFirst();
-		if('[' == first.type){
-			includeFirst = true;
-		}else if('{' == first.type){
-			includeFirst = false;
-		}else {
-			throw new IllegalStateException("表达式异常");
-		}
-		//检查最后一个元素是否是]或者}
-		Element last = elements.getLast();
-		if(']' == last.type){
-			includeLast = true;
-		}else if('}' == last.type){
-			includeLast = false;
-		}else {
-			throw new IllegalStateException("表达式异常, RangeQuery缺少结束括号");
-		}
-		if(elements.size() < 4 || elements.size() > 5){
-			throw new IllegalStateException("表达式异常, RangeQuery 错误");
-		}			
-		//读出中间部分
-		Element e2 = elements.get(1);
-		if('\'' == e2.type){
-			firstValue = e2.toString();
-			//
-			Element e3 = elements.get(2);
-			if(',' != e3.type){
-				throw new IllegalStateException("表达式异常, RangeQuery缺少逗号分隔");
-			}
-			//
-			Element e4 = elements.get(3);
-			if('\'' == e4.type){
-				lastValue = e4.toString();
-			}else if(e4 != last){
-				throw new IllegalStateException("表达式异常，RangeQuery格式错误");
-			}				
-		}else if(',' == e2.type){
-			firstValue = null;
-			//
-			Element e3 = elements.get(2);
-			if('\'' == e3.type){
-				lastValue = e3.toString();
-			}else{
-				throw new IllegalStateException("表达式异常，RangeQuery格式错误");
-			}
-			
-		}else {
-			throw new IllegalStateException("表达式异常, RangeQuery格式错误");
-		}
-		
-		return new TermRangeQuery(fieldNameEle.toString() , new BytesRef(firstValue) , new BytesRef(lastValue) , includeFirst , includeLast);
-	}	
-	
-	/**
-	 * 比较操作符优先级
-	 * @param e1
-	 * @param e2
-	 * @return
-	 */
-	private int compare(Element e1 , Element e2){
-		if('&' == e1.type){
-			if('&' == e2.type){
-				return 0;
-			}else {
-				return 1;
-			}
-		}else if('|' == e1.type){
-			if('&' == e2.type){
-				return -1;
-			}else if('|' == e2.type){
-				return 0;
-			}else{
-				return 1;
-			}
-		}else{
-			if('-' == e2.type){
-				return 0;
-			}else{
-				return -1;
-			}
-		}
-	}
-	
-	/**
-	 * 表达式元素（操作符、FieldName、FieldValue）
-	 * @author linliangyi
-	 * May 20, 2010
-	 */
-	private class Element{
-		char type = 0;
-		StringBuffer eleTextBuff;
-
-		public Element(){
-			eleTextBuff = new StringBuffer();
-		}
-		
-		public void append(char c){
-			this.eleTextBuff.append(c);
-		}
-	
-		public String toString(){
-			return this.eleTextBuff.toString();
-		}
-	}	
-
-	public static void main(String[] args){
-		IKQueryExpressionParser parser = new IKQueryExpressionParser();
-		//String ikQueryExp = "newsTitle:'的两款《魔兽世界》插件Bigfoot和月光宝盒'";
-		String ikQueryExp = "(id='ABcdRf' && date:{'20010101','20110101'} && keyword:'魔兽中国') || (content:'KSHT-KSH-A001-18'  || ulr='www.ik.com') - name:'林良益'";
-		Query result = parser.parseExp(ikQueryExp , true);
-        logger.info(result.toString());
-
-	}	
-	
-}

src/main/java/org/wltea/analyzer/query/SWMCQueryBuilder.java

@@ -1,154 +0,0 @@
-/**
- * IK 中文分词  版本 5.0
- * IK Analyzer release 5.0
- * 
- * 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.
- *
- * 源代码由林良益(linliangyi2005@gmail.com)提供
- * 版权声明 2012，乌龙茶工作室
- * provided by Linliangyi and copyright 2012 by Oolong studio
- * 
- */
-package org.wltea.analyzer.query;
-
-import java.io.IOException;
-import java.io.StringReader;
-import java.util.ArrayList;
-import java.util.List;
-
-import org.apache.lucene.analysis.standard.StandardAnalyzer;
-import org.apache.lucene.queryparser.classic.ParseException;
-import org.apache.lucene.queryparser.classic.QueryParser;
-import org.apache.lucene.search.Query;
-import org.apache.lucene.util.Version;
-import org.wltea.analyzer.core.IKSegmenter;
-import org.wltea.analyzer.core.Lexeme;
-
-/**
- * Single Word Multi Char Query Builder
- * IK分词算法专用
- * @author linliangyi
- *
- */
-public class SWMCQueryBuilder {
-
-	/**
-	 * 生成SWMCQuery
-	 * @param fieldName
-	 * @param keywords
-	 * @param quickMode
-	 * @return Lucene Query
-	 */
-	public static Query create(String fieldName ,String keywords , boolean quickMode){
-		if(fieldName == null || keywords == null){
-			throw new IllegalArgumentException("参数 fieldName 、 keywords 不能为null.");
-		}
-		//1.对keywords进行分词处理
-		List<Lexeme> lexemes = doAnalyze(keywords);
-		//2.根据分词结果，生成SWMCQuery
-		Query _SWMCQuery = getSWMCQuery(fieldName , lexemes , quickMode);
-		return _SWMCQuery;
-	}
-	
-	/**
-	 * 分词切分，并返回结链表
-	 * @param keywords
-	 * @return
-	 */
-	private static List<Lexeme> doAnalyze(String keywords){
-		List<Lexeme> lexemes = new ArrayList<Lexeme>();
-
-		IKSegmenter ikSeg = new IKSegmenter(new StringReader(keywords),true);
-		try{
-			Lexeme l = null;
-			while( (l = ikSeg.next()) != null){
-				lexemes.add(l);
-			}
-		}catch(IOException e){
-			e.printStackTrace();
-		}
-		return lexemes;
-	}
-	
-	
-	/**
-	 * 根据分词结果生成SWMC搜索
-	 * @param fieldName
-//	 * @param pathOption
-	 * @param quickMode
-	 * @return
-	 */
-	private static Query getSWMCQuery(String fieldName , List<Lexeme> lexemes , boolean quickMode){
-		//构造SWMC的查询表达式
-		StringBuffer keywordBuffer = new StringBuffer();
-		//精简的SWMC的查询表达式
-		StringBuffer keywordBuffer_Short = new StringBuffer();
-		//记录最后词元长度
-		int lastLexemeLength = 0;
-		//记录最后词元结束位置
-		int lastLexemeEnd = -1;
-		
-		int shortCount = 0;
-		int totalCount = 0;
-		for(Lexeme l : lexemes){
-			totalCount += l.getLength();
-			//精简表达式
-			if(l.getLength() > 1){
-				keywordBuffer_Short.append(' ').append(l.getLexemeText());
-				shortCount += l.getLength();
-			}
-			
-			if(lastLexemeLength == 0){
-				keywordBuffer.append(l.getLexemeText());				
-			}else if(lastLexemeLength == 1 && l.getLength() == 1
-					&& lastLexemeEnd == l.getBeginPosition()){//单字位置相邻，长度为一，合并)
-				keywordBuffer.append(l.getLexemeText());
-			}else{
-				keywordBuffer.append(' ').append(l.getLexemeText());
-				
-			}
-			lastLexemeLength = l.getLength();
-			lastLexemeEnd = l.getEndPosition();
-		}
-
-		//借助lucene queryparser 生成SWMC Query
-		QueryParser qp = new QueryParser(fieldName, new StandardAnalyzer());
-		qp.setDefaultOperator(QueryParser.AND_OPERATOR);
-		qp.setAutoGeneratePhraseQueries(true);
-		
-		if(quickMode && (shortCount * 1.0f / totalCount) > 0.5f){
-			try {
-				//System.out.println(keywordBuffer.toString());
-				Query q = qp.parse(keywordBuffer_Short.toString());
-				return q;
-			} catch (ParseException e) {
-				e.printStackTrace();
-			}
-			
-		}else{
-			if(keywordBuffer.length() > 0){
-				try {
-					//System.out.println(keywordBuffer.toString());
-					Query q = qp.parse(keywordBuffer.toString());
-					return q;
-				} catch (ParseException e) {
-					e.printStackTrace();
-				}
-			}
-		}
-		return null;
-	}
-}

src/main/java/org/wltea/analyzer/sample/IKAnalzyerDemo.java

@@ -1,90 +0,0 @@
-/**
- * IK 中文分词  版本 5.0.1
- * IK Analyzer release 5.0.1
- * 
- * 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.
- *
- * 源代码由林良益(linliangyi2005@gmail.com)提供
- * 版权声明 2012，乌龙茶工作室
- * provided by Linliangyi and copyright 2012 by Oolong studio
- * 
- * 
- */
-package org.wltea.analyzer.sample;
-
-import java.io.IOException;
-import java.io.StringReader;
-
-import org.apache.lucene.analysis.Analyzer;
-import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
-import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
-import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
-import org.elasticsearch.common.logging.ESLogger;
-import org.elasticsearch.common.logging.Loggers;
-import org.wltea.analyzer.lucene.IKAnalyzer;
-
-/**
- * 使用IKAnalyzer进行分词的演示
- * 2012-10-22
- *
- */
-public class IKAnalzyerDemo {
-
-    public static final ESLogger logger= Loggers.getLogger("ik-analyzer");
-    
-	public static void main(String[] args){
-		//构建IK分词器，使用smart分词模式
-		Analyzer analyzer = new IKAnalyzer(true);
-		
-		//获取Lucene的TokenStream对象
-	    TokenStream ts = null;
-		try {
-			ts = analyzer.tokenStream("myfield", new StringReader("WORLD ,.. html DATA</html>HELLO"));
-//			ts = analyzer.tokenStream("myfield", new StringReader("这是一个中文分词的例子，你可以直接运行它！IKAnalyer can analysis english text too"));
-			//获取词元位置属性
-		    OffsetAttribute  offset = ts.addAttribute(OffsetAttribute.class); 
-		    //获取词元文本属性
-		    CharTermAttribute term = ts.addAttribute(CharTermAttribute.class);
-		    //获取词元文本属性
-		    TypeAttribute type = ts.addAttribute(TypeAttribute.class);
-		    
-		    
-		    //重置TokenStream（重置StringReader）
-			ts.reset(); 
-			//迭代获取分词结果
-			while (ts.incrementToken()) {
-			  logger.info(offset.startOffset() + " - " + offset.endOffset() + " : " + term.toString() + " | " + type.type());
-			}
-			//关闭TokenStream（关闭StringReader）
-			ts.end();   // Perform end-of-stream operations, e.g. set the final offset.
-
-		} catch (IOException e) {
-			e.printStackTrace();
-		} finally {
-			//释放TokenStream的所有资源
-			if(ts != null){
-		      try {
-				ts.close();
-		      } catch (IOException e) {
-				e.printStackTrace();
-		      }
-			}
-	    }
-		
-	}
-
-}

src/main/java/org/wltea/analyzer/sample/LuceneIndexAndSearchDemo.java

@@ -1,150 +0,0 @@
-/**
- * IK 中文分词  版本 5.0
- * IK Analyzer release 5.0
- * 
- * 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.
- *
- * 源代码由林良益(linliangyi2005@gmail.com)提供
- * 版权声明 2012，乌龙茶工作室
- * provided by Linliangyi and copyright 2012 by Oolong studio
- * 
- * 
- */
-package org.wltea.analyzer.sample;
-
-import java.io.IOException;
-
-import org.apache.lucene.analysis.Analyzer;
-import org.apache.lucene.document.Document;
-import org.apache.lucene.document.Field;
-import org.apache.lucene.document.StringField;
-import org.apache.lucene.document.TextField;
-import org.apache.lucene.index.CorruptIndexException;
-import org.apache.lucene.index.DirectoryReader;
-import org.apache.lucene.index.IndexReader;
-import org.apache.lucene.index.IndexWriter;
-import org.apache.lucene.index.IndexWriterConfig;
-import org.apache.lucene.index.IndexWriterConfig.OpenMode;
-import org.apache.lucene.queryparser.classic.ParseException;
-import org.apache.lucene.queryparser.classic.QueryParser;
-import org.apache.lucene.search.IndexSearcher;
-import org.apache.lucene.search.Query;
-import org.apache.lucene.search.ScoreDoc;
-import org.apache.lucene.search.TopDocs;
-import org.apache.lucene.store.Directory;
-import org.apache.lucene.store.LockObtainFailedException;
-import org.apache.lucene.store.RAMDirectory;
-import org.apache.lucene.util.Version;
-import org.elasticsearch.common.logging.ESLogger;
-import org.elasticsearch.common.logging.Loggers;
-import org.wltea.analyzer.lucene.IKAnalyzer;
-
-
-
-
-/**
- * 使用IKAnalyzer进行Lucene索引和查询的演示
- * 2012-3-2
- * 
- * 以下是结合Lucene4.0 API的写法
- *
- */
-public class LuceneIndexAndSearchDemo {
-
-    public static final ESLogger logger= Loggers.getLogger("ik-analyzer");
-	
-	/**
-	 * 模拟：
-	 * 创建一个单条记录的索引，并对其进行搜索
-	 * @param args
-	 */
-	public static void main(String[] args){
-		//Lucene Document的域名
-		String fieldName = "text";
-		 //检索内容
-		String text = "IK Analyzer是一个结合词典分词和文法分词的中文分词开源工具包。它使用了全新的正向迭代最细粒度切分算法。";
-		
-		//实例化IKAnalyzer分词器
-		Analyzer analyzer = new IKAnalyzer(true);
-		
-		Directory directory = null;
-		IndexWriter iwriter = null;
-		IndexReader ireader = null;
-		IndexSearcher isearcher = null;
-		try {
-			//建立内存索引对象
-			directory = new RAMDirectory();	 
-			
-			//配置IndexWriterConfig
-			IndexWriterConfig iwConfig = new IndexWriterConfig(analyzer);
-			iwConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
-			iwriter = new IndexWriter(directory , iwConfig);
-			//写入索引
-			Document doc = new Document();
-			doc.add(new StringField("ID", "10000", Field.Store.YES));
-			doc.add(new TextField(fieldName, text, Field.Store.YES));
-			iwriter.addDocument(doc);
-			iwriter.close();
-			
-			
-			//搜索过程**********************************
-		    //实例化搜索器   
-			ireader = DirectoryReader.open(directory);
-			isearcher = new IndexSearcher(ireader);			
-			
-			String keyword = "中文分词工具包";			
-			//使用QueryParser查询分析器构造Query对象
-			QueryParser qp = new QueryParser(fieldName,  analyzer);
-			qp.setDefaultOperator(QueryParser.AND_OPERATOR);
-			Query query = qp.parse(keyword);
-			logger.info("Query = " + query);
-			
-			//搜索相似度最高的5条记录
-			TopDocs topDocs = isearcher.search(query , 5);
-            logger.info("命中：" + topDocs.totalHits);
-			//输出结果
-			ScoreDoc[] scoreDocs = topDocs.scoreDocs;
-			for (int i = 0; i < topDocs.totalHits; i++){
-				Document targetDoc = isearcher.doc(scoreDocs[i].doc);
-                logger.info("内容：" + targetDoc.toString());
-			}			
-			
-		} catch (CorruptIndexException e) {
-			e.printStackTrace();
-		} catch (LockObtainFailedException e) {
-			e.printStackTrace();
-		} catch (IOException e) {
-			e.printStackTrace();
-		} catch (ParseException e) {
-			e.printStackTrace();
-		} finally{
-			if(ireader != null){
-				try {
-					ireader.close();
-				} catch (IOException e) {
-					e.printStackTrace();
-				}
-			}
-			if(directory != null){
-				try {
-					directory.close();
-				} catch (IOException e) {
-					e.printStackTrace();
-				}
-			}
-		}
-	}
-}

src/main/resources/plugin-descriptor.properties

@@ -38,21 +38,6 @@ version=${project.version}
 #
 # 'name': the plugin name
 name=${elasticsearch.plugin.name}
-
-### mandatory elements for site plugins:
-#
-# 'site': set to true to indicate contents of the _site/
-#  directory in the root of the plugin should be served.
-site=${elasticsearch.plugin.site}
-#
-### mandatory elements for jvm plugins :
-#
-# 'jvm': true if the 'classname' class should be loaded
-#  from jar files in the root directory of the plugin.
-#  Note that only jar files in the root directory are
-#  added to the classpath for the plugin! If you need
-#  other resources, package them into a resources jar.
-jvm=${elasticsearch.plugin.jvm}
 #
 # 'classname': the name of the class to load, fully-qualified.
 classname=${elasticsearch.plugin.classname}
@@ -69,12 +54,3 @@ java.version=${maven.compiler.target}
 # is loaded so Elasticsearch will refuse to start in the presence of
 # plugins with the incorrect elasticsearch.version.
 elasticsearch.version=${elasticsearch.version}
-#
-### deprecated elements for jvm plugins :
-#
-# 'isolated': true if the plugin should have its own classloader.
-# passing false is deprecated, and only intended to support plugins
-# that have hard dependencies against each other. If this is
-# not specified, then the plugin is isolated by default.
-isolated=${elasticsearch.plugin.isolated}
-#

src/main/resources/plugin-security.policy

@@ -0,0 +1,4 @@
+grant {
+  // needed because of the hot reload functionality
+  permission java.net.SocketPermission "*", "connect,resolve";
+};

src/main/uml/IKAnalysisBinderProcessor.uml

@@ -1,83 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<Diagram>
-  <ID>JAVA</ID>
-  <OriginalElement>org.elasticsearch.index.analysis.IKAnalysisBinderProcessor</OriginalElement>
-  <nodes>
-    <node x="1244.0" y="553.0">org.elasticsearch.index.analysis.IKAnalysisBinderProcessor</node>
-    <node x="2212.0" y="489.0">org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.AnalyzersBindings</node>
-    <node x="1316.0" y="0.0">java.lang.Object</node>
-    <node x="1244.0" y="329.0">org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor</node>
-    <node x="616.0" y="510.0">org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.TokenFiltersBindings</node>
-    <node x="0.0" y="510.0">org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.CharFiltersBindings</node>
-    <node x="1608.0" y="510.0">org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.TokenizersBindings</node>
-  </nodes>
-  <notes />
-  <edges>
-    <edge source="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.TokenFiltersBindings" target="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor">
-      <point x="152.0" y="-77.0" />
-      <point x="1072.0" y="469.0" />
-      <point x="1347.2" y="469.0" />
-      <point x="-68.79999999999995" y="55.0" />
-    </edge>
-    <edge source="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.CharFiltersBindings" target="java.lang.Object">
-      <point x="-149.0" y="-77.0" />
-      <point x="149.0" y="299.0" />
-      <point x="1336.0" y="299.0" />
-      <point x="-80.0" y="139.5" />
-    </edge>
-    <edge source="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor" target="java.lang.Object">
-      <point x="0.0" y="-55.0" />
-      <point x="0.0" y="139.5" />
-    </edge>
-    <edge source="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.AnalyzersBindings" target="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor">
-      <point x="-180.5" y="-98.0" />
-      <point x="2392.5" y="459.0" />
-      <point x="1553.6" y="459.0" />
-      <point x="137.5999999999999" y="55.0" />
-    </edge>
-    <edge source="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.CharFiltersBindings" target="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor">
-      <point x="149.0" y="-77.0" />
-      <point x="447.0" y="459.0" />
-      <point x="1278.4" y="459.0" />
-      <point x="-137.5999999999999" y="55.0" />
-    </edge>
-    <edge source="org.elasticsearch.index.analysis.IKAnalysisBinderProcessor" target="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor">
-      <point x="0.0" y="-34.0" />
-      <point x="0.0" y="55.0" />
-    </edge>
-    <edge source="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.TokenFiltersBindings" target="java.lang.Object">
-      <point x="-152.0" y="-77.0" />
-      <point x="768.0" y="309.0" />
-      <point x="1376.0" y="309.0" />
-      <point x="-40.0" y="139.5" />
-    </edge>
-    <edge source="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.AnalyzersBindings" target="java.lang.Object">
-      <point x="180.5" y="-98.0" />
-      <point x="2753.5" y="299.0" />
-      <point x="1496.0" y="299.0" />
-      <point x="80.0" y="139.5" />
-    </edge>
-    <edge source="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.TokenizersBindings" target="java.lang.Object">
-      <point x="146.0" y="-77.0" />
-      <point x="2046.0" y="309.0" />
-      <point x="1456.0" y="309.0" />
-      <point x="40.0" y="139.5" />
-    </edge>
-    <edge source="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor.TokenizersBindings" target="org.elasticsearch.index.analysis.AnalysisModule.AnalysisBinderProcessor">
-      <point x="-146.0" y="-77.0" />
-      <point x="1754.0" y="469.0" />
-      <point x="1484.8" y="469.0" />
-      <point x="68.79999999999995" y="55.0" />
-    </edge>
-  </edges>
-  <settings layout="Hierarchic Group" zoom="1.0" x="110.5" y="89.0" />
-  <SelectedNodes />
-  <Categories>
-    <Category>Fields</Category>
-    <Category>Methods</Category>
-    <Category>Constructors</Category>
-    <Category>Inner Classes</Category>
-    <Category>Properties</Category>
-  </Categories>
-</Diagram>
-