hadoop源码解析—— conf包中Configuration.java解析（一）

地方

package org.apache.hadoop.conf;

import java.io.BufferedInputStream;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.Reader;
import java.io.Writer;
import java.net.URL;
import java.util.ArrayList;
import java.util.Collection;
import java.util.Enumeration;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.List;
import java.util.ListIterator;
import java.util.Map;
import java.util.Properties;
import java.util.Set;
import java.util.StringTokenizer;
import java.util.WeakHashMap;
import java.util.concurrent.CopyOnWriteArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
//引入了IO的流类
//引入了网络编程类，用来封装或获取网络资源
//引入了工具包中的集合类。其中StringTokenier在hadoop中用的非常多，特别是在mapreduce编程中，经常需要这个工具类来处理数据。
//它起着分词器的作用。
//关于CopyOnWriteArrayList，之前没接触过，具体推荐 http://blog.csdn.net/imzoer/article/details/9751591，就是实现了线程安全
//关于regex.Matcher和regex.Pattern，看regex可知就是正则类，具体用法不太一样 http://ningtukun.blog.163.com/blog/static/186541445201292984311656/
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableUtils;
import org.apache.hadoop.util.StringUtils;
import org.codehaus.jackson.JsonFactory;
import org.codehaus.jackson.JsonGenerator;
import org.w3c.dom.DOMException;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.w3c.dom.Text;
import org.xml.sax.SAXException;

/** 
 * Provides access to configuration parameters.
 *
 * 
Resources
 *
 * 
Configurations are specified by resources. A resource contains a set of
 * name/value pairs as XML data. Each resource is named by either a 
 * String or by a {@link Path}. If named by a String, 
 * then the classpath is examined for a file with that name.  If named by a 
 * Path, then the local filesystem is examined directly, without 
 * referring to the classpath.
 *
 * 
Unless explicitly turned off, Hadoop by default specifies two 
 * resources, loaded in-order from the classpath: 

 * 
core-default.xml
 * : Read-only defaults for hadoop.
 * 
core-site.xml: Site-specific configuration for a given hadoop
 * installation.
 * 
 * Applications may add additional resources, which are loaded
 * subsequent to these resources in the order they are added.
 * 
 * 
Final Parameters
 *
 * 
Configuration parameters may be declared final. 
 * Once a resource declares a value final, no subsequently-loaded 
 * resource can alter that value.  
 * For example, one might define a final parameter with:
 * 
 *  
 *    dfs.client.buffer.dir
 *    /tmp/hadoop/dfs/client
 *    true
 *  
 *
 * Administrators typically define parameters as final in 
 * core-site.xml for values that user applications may not alter.
 *
 * 
Variable Expansion
 *
 * 
Value strings are first processed for variable expansion. The
 * available properties are:

 * 
Other properties defined in this Configuration; and, if a name is
 * undefined here,
 * 
Properties in {@link System#getProperties()}.
 * 
 *
 * 
For example, if a configuration resource contains the following property
 * definitions: 
 * 
 *  
 *    basedir
 *    /user/${user.name}
 *  
 *  
 *  
 *    tempdir
 *    ${basedir}/tmp
 *  
 *
 * When conf.get("tempdir") is called, then ${basedir}
 * will be resolved to another property in this Configuration, while
 * ${user.name} would then ordinarily be resolved to the value
 * of the System property with that name.
 */
 //一大段注释。第一句说这个类是用来提供访问配置中属性的渠道
 //第二段话说配置文件的构造，XML文件中键值对。
 //第三段话说除非主动关闭，否则hadoop会默认加载一些默认的配置文件。并且可以“重载”
 //第四段说了配置文件中属性标记为final会怎么样
 //第五段说配置文件中的属性可以用变量来表示，可以不是具体的实值。还举了个例子。
public class Configuration implements Iterable>,
                                      Writable {
//实现了Iterable和Writable接口。
//实现Iterable接口，可以调用Iterator()方法进行迭代
//关于Map.Entry类，之前不了解。就是map的一种方便的遍历工具类
//实现了Writable接口。hadoop没有采用Java的序列化（具体原因不解释），而是引入了自己的序列化系统，所有的
//序列化对象都要实现writable接口。以后会遇到。                                  
  private static final Log LOG =
    LogFactory.getLog(Configuration.class);
  //创建了一个日志类。并做了初始化
  private boolean quietmode = true;
  //布尔变量quietmode，“安静模式”，用来确定加载配置的时候日志的某些动作，
  //当为true的时候则在加载解析配置文件的过程中不输出日志信息，反之......
  /**
   * List of configuration resources.
   */
  private ArrayList