📄 nutchanalyzer.java
字号:
/** * Copyright 2005 The Apache Software Foundation * * 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. */package org.apache.nutch.analysis;// JDK importsimport java.io.Reader;// Lucene importsimport org.apache.lucene.analysis.Analyzer;import org.apache.lucene.analysis.TokenStream;// Hadoop importsimport org.apache.hadoop.conf.Configurable;import org.apache.hadoop.conf.Configuration;// Nutch importsimport org.apache.nutch.plugin.Pluggable;/** * Extension point for analysis. * All plugins found which implement this extension point are run * sequentially on the parse. * * @author Jérôme Charron */public abstract class NutchAnalyzer extends Analyzer implements Configurable, Pluggable { /** The name of the extension point. */ final static String X_POINT_ID = NutchAnalyzer.class.getName(); /** The current Configuration */ protected Configuration conf = null; /** * Creates a TokenStream which tokenizes all the text in the provided Reader. */ public abstract TokenStream tokenStream(String fieldName, Reader reader); /* ----------------------------- * * <implementation:Configurable> * * ----------------------------- */ // Inherited Javadoc public void setConf(Configuration conf) { this.conf = conf; } // Inherited Javadoc public Configuration getConf() { return this.conf; } /* ------------------------------ * * </implementation:Configurable> * * ------------------------------ */}
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -