Merge pull request #56 from rockybean/master

optimize Dictionary reload process

README.textile

@@ -223,6 +223,25 @@ here is the query result
 
 have fun.
 
+热更新IK分词使用方法
+----------
+目前该插件支持热更新IK分词，通过上文在ik配置文件中提到的如下配置
+
+<pre>
+ 	<!--用户可以在这里配置远程扩展字典 -->
+	<entry key="remote_ext_dict">location</entry>
+ 	<!--用户可以在这里配置远程扩展停止词字典-->
+	<entry key="remote_ext_stopwords">location</entry>
+</pre>
+
+其中`location`是指一个url，比如`http://yoursite.com/getCustomDict`，该请求只需满足一下两点即可完成分词热更新。
+
+1. 该http请求需要返回两个头部，一个是`Last-Modified`，一个是`ETags`，这两者都是字符串类型，只要有一个发生变化，该插件就会去抓取新的分词进而更新词库。
+
+2. 该http请求返回的内容格式是一行一个分词，换行符用`\n`即可。
+
+满足上面两点要求就可以实现热更新分词了，不需要重启es实例。
+
 
 常见问题：
 -------------

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

@@ -77,7 +77,7 @@ public class Dictionary {
 	 * 配置对象
 	 */
 	private Configuration configuration;
-    private ESLogger logger=null;
+    public static ESLogger logger=Loggers.getLogger("ik-analyzer");
     
     private static ScheduledExecutorService pool = Executors.newScheduledThreadPool(1);
     
@@ -89,8 +89,7 @@ public class Dictionary {
     public static final String PATH_DIC_STOP = "ik/stopword.dic";
     
     private Dictionary(){
-    	
+
-        logger = Loggers.getLogger("ik-analyzer");
     }
 
 	/**
@@ -367,11 +366,11 @@ public class Dictionary {
 			}
 			response.close();
 		} catch (ClientProtocolException e) {
-			e.printStackTrace();
+			logger.error( "getRemoteWords {} error" , e , location);
 		} catch (IllegalStateException e) {
-			e.printStackTrace();
+			logger.error( "getRemoteWords {} error" , e , location );
 		} catch (IOException e) {
-			e.printStackTrace();
+			logger.error( "getRemoteWords {} error" , e , location );
 		}
 		return buffer;
 	}
@@ -638,8 +637,14 @@ public class Dictionary {
     
     public void reLoadMainDict(){
     	logger.info("重新加载词典...");
-	loadMainDict();
+		// 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
-	loadStopWordDict();
+		Dictionary tmpDict = new Dictionary();
+		tmpDict.configuration = getSingleton().configuration;
+		tmpDict.loadMainDict();
+		tmpDict.loadStopWordDict();
+		_MainDict = tmpDict._MainDict;
+		_StopWords = tmpDict._StopWords;
+		logger.info("重新加载词典完毕...");
     }
     
 }

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

@@ -9,7 +9,7 @@ import org.apache.http.impl.client.CloseableHttpClient;
 import org.apache.http.impl.client.HttpClients;
 
 public class Monitor implements Runnable {
-	
+
 	private static CloseableHttpClient httpclient = HttpClients.createDefault();
 	/*
 	 * 上次更改时间
@@ -40,7 +40,7 @@ public class Monitor implements Runnable {
 	 */
 	
 	public void run() {
-		
+
 		//超时设置
 		RequestConfig rc = RequestConfig.custom().setConnectionRequestTimeout(10*1000)
 				.setConnectTimeout(10*1000).setSocketTimeout(15*1000).build();
@@ -72,13 +72,17 @@ public class Monitor implements Runnable {
 					last_modified = response.getLastHeader("Last-Modified")==null?null:response.getLastHeader("Last-Modified").getValue();
 					eTags = response.getLastHeader("ETags")==null?null:response.getLastHeader("ETags").getValue();
 				}
+			}else{
+				Dictionary.logger.info("remote_ext_dict {} return bad code {}" , location , response.getStatusLine().getStatusCode() );
 			}
-			
+
 		} catch (Exception e) {
-			e.printStackTrace();
+			Dictionary.logger.error("remote_ext_dict {} error!",e , location);
 		}finally{
 			try {
-				response.close();
+				if (response != null) {
+					response.close();
+				}
 			} catch (IOException e) {
 				e.printStackTrace();
 			}