upgrade es to 6.2.4,hanlp to 1.6.4

Signed-off-by: Ranger Tsao <[email protected]>
shikeio · Jun 20, 2018 · 6e611e5 · 6e611e5
1 parent 364a68b
commit 6e611e5
Show file tree

Hide file tree

Showing 5 changed files with 16 additions and 6 deletions.
diff --git a/build.gradle b/build.gradle
@@ -1,11 +1,12 @@
 buildscript {
     ext {
-        elasticserachVersion = '6.2.3'
-        hanlpVersion = '1.5.3'
+        elasticserachVersion = '6.2.4'
+        hanlpVersion = '1.6.4'
     }
 
     repositories {
         mavenLocal()
+        maven { url = 'http://maven.aliyun.com/nexus/content/groups/public/' }
         mavenCentral()
         jcenter()
     }
@@ -16,7 +17,7 @@ buildscript {
 }
 
 group = 'io.shike'
-version = '6.2.3'
+version = '6.2.4'
 
 repositories {
     mavenLocal()
@@ -61,7 +62,7 @@ bundlePlugin {
 
 task mvn(type: Exec) {
     workingDir 'libs'
-    commandLine 'mvn', 'install:install-file', '-Dfile=hanlp-$hanlpVersion.jar', '-DgroupId=com.hankcs', '-DartifactId=hanlp','-Dversion=1.5.3', '-Dpackaging=jar'
+    commandLine 'mvn', 'install:install-file', '-Dfile=hanlp-1.6.4.jar', '-DgroupId=com.hankcs', '-DartifactId=hanlp','-Dversion=1.6.4', '-Dpackaging=jar'
     doLast {
         println('Installed hanlp')
     }

diff --git a/config/hanlp.properties b/config/hanlp.properties
@@ -1,6 +1,6 @@
 #本配置文件中的路径的根目录，根目录+其他路径=完整路径（支持相对路径，请参考：https://github.com/hankcs/HanLP/pull/254）
 #Windows用户请注意，路径分隔符统一使用/
-root                                = /${data.root}
+root                                = ${data root}
 #核心词典路径
 CoreDictionaryPath                  = data/dictionary/CoreNatureDictionary.txt
 #2元语法词典路径
@@ -27,3 +27,12 @@ ShowTermNature                      = true
 #IO适配器，实现com.hankcs.hanlp.corpus.io.IIOAdapter接口以在不同的平台（Hadoop、Redis等）上运行HanLP
 #默认的IO适配器如下，该适配器是基于普通文件系统的。
 #IOAdapter=com.hankcs.hanlp.corpus.io.FileIOAdapter
+#感知机词法分析器
+PerceptronCWSModelPath              = data/model/perceptron/pku199801/cws.bin
+PerceptronPOSModelPath              = data/model/perceptron/pku199801/pos.bin
+PerceptronNERModelPath              = data/model/perceptron/pku199801/ner.bin
+#CRF词法分析器
+CRFCWSModelPath                     = data/model/crf/pku199801/cws.bin
+CRFPOSModelPath                     = data/model/crf/pku199801/pos.bin
+CRFNERModelPath                     = data/model/crf/pku199801/ner.bin
+#更多配置项请参考 https://github.com/hankcs/HanLP/blob/master/src/main/java/com/hankcs/hanlp/HanLP.java#L59 自行添加
diff --git a/libs/hanlp-1.5.3-sources.jar → libs/hanlp-1.6.4-sources.jar b/libs/hanlp-1.5.3-sources.jar → libs/hanlp-1.6.4-sources.jar
diff --git a/libs/hanlp-1.5.3.jar → libs/hanlp-1.6.4.jar b/libs/hanlp-1.5.3.jar → libs/hanlp-1.6.4.jar
diff --git a/src/main/java/org/elasticsearch/index/analysis/HanLPTokenizerFactory.java b/src/main/java/org/elasticsearch/index/analysis/HanLPTokenizerFactory.java
@@ -39,7 +39,7 @@ public static HanLPTokenizerFactory createNLP(IndexSettings indexSettings, Envir
         return new HanLPTokenizerFactory(indexSettings, environment, name, settings) {
             @Override
             public Tokenizer create() {
-                return new HanLPTokenizer(NLPTokenizer.SEGMENT, defaultStopWordDictionary, enablePorterStemming);
+                return new HanLPTokenizer(NLPTokenizer.ANALYZER, defaultStopWordDictionary, enablePorterStemming);
             }
         };
     }