xml格式文件（大概有50G）转换为json格式 上传到mongodb数据库中

XML 前端之家
前端之家收集整理的这篇文章主要介绍了xml格式文件（大概有50G）转换为json格式 上传到mongodb数据库中，前端之家小编觉得挺不错的，现在分享给大家，也给大家做个参考。
  1. 偏小数据的就不做多描述，网上有很多资料，在此有大概50G的xml格式的地理数据转换为json格式的数据，之后上传到mongodb数据库中，有什么好的建议，欢迎指正
  1. 解析xml数据
  1. import java.util.ArrayList;
  2. import java.util.List;
  3.  
  4. import org.xml.sax.Attributes;
  5. import org.xml.sax.ContentHandler;
  6. import org.xml.sax.Locator;
  7. import org.xml.sax.SAXException;
  8.  
  9. import com.mongodb.DBObject;
  10. /*
  11.  * @author 
  12.  * @time 2015-11-8
  13.  * 主要是是implements ContentHandler，主要实现接口ContentHandler中的startDocument()、endDocument()、startElement()、endElement（）
  14.  * 另外自定义方法writeToMongoDB()、storeDBMongo()
  15.  * 
  16.  */
  17.  
  18. public class MyContentHandler implements ContentHandler {
  19. 	private StringBuffer buf;
  20. 	private String ctitle;
  21. 	private String cns;
  22. 	private String cid;
  23. 	private String ctext;
  24. 	private String ctimestamp;
  25. 	private int idnumber=0;
  26. 	List<Data> listdata=new ArrayList<Data>();
  27. 	List list=new ArrayList();		
  28. 	@Override
  29. 	public void setDocumentLocator(Locator locator) {
  30. 		// TODO Auto-generated method stub
  31.  
  32. 	}
  33.  
  34. 	@Override
  35. 	public void startDocument() throws SAXException {
  36. 		// TODO Auto-generated method stub
  37. 		buf=new StringBuffer();
  38.         System.out.println("*******解析开始*******");
  39. 	}
  40.  
  41. 	@Override
  42. 	public void endDocument() throws SAXException {
  43. 		// TODO Auto-generated method stub
  44. 		try {
  45. 			writeToMongoDB();
  46. 		} catch (Exception e) {
  47. 			// TODO Auto-generated catch block
  48. 			e.printStackTrace();
  49. 		}
  50. 		System.out.println("*******解析结束*******");
  51. 		
  52. 	}
  53.     //把数据导入MongoDB数据库中
  54. 	private void writeToMongoDB() throws Exception {
  55. 		// TODO Auto-generated method stub
  56. 		List<DBObject> dblist=new ArrayList<DBObject>();
  57. 		for(Data d:listdata){
  58. 			dblist.add(BSONT.mapToBSON(d.toJSONMap()));
  59. 		}
  60. 		
  61. 		MongoDBT.writeListToMongo("IP",27017,"databaseName","collectionName",dblist);
  62. 	}
  63.  
  64. 	@Override
  65. 	public void startPrefixMapping(String prefix,String uri)
  66. 			throws SAXException {
  67. 		// TODO Auto-generated method stub
  68. 	}
  69.  
  70. 	@Override
  71. 	public void endPrefixMapping(String prefix) throws SAXException {
  72. 		// TODO Auto-generated method stub
  73. 	}
  74.  
  75. 	@Override
  76. 	public void startElement(String uri,String localName,String qName,Attributes attributes) throws SAXException {
  77. 		// TODO Auto-generated method stub				
  78. 	       if(qName=="page"){
  79. 	    	   idnumber=1;
  80. 	       }
  81. 	       if(qName=="title"){
  82. 	    	   ctitle=qName;
  83. 	       }else if(qName=="ns"){
  84. 	    	   cns=qName;
  85. 	       }else if(qName=="id"&&idnumber==1){
  86. 	    	   cid=qName;
  87. 	    	   idnumber=0;
  88. 	       }else if(qName=="timestamp"){
  89. 	    	   ctimestamp=qName;	    		   
  90. 	       }else if(qName=="text"){
  91. 	     	   ctext=qName;
  92. 	       }
  93. 	       
  94. 	  }	        					
  95. 	@Override
  96. 	public void endElement(String uri,String qName)
  97. 			throws SAXException {
  98. 		// TODO Auto-generated method stub		
  99. 		if(ctitle==qName){
  100. 			String sss=buf.toString();
  101.         	ctitle="";
  102.         	list.add(sss);
  103.  			buf.setLength(0);
  104.  			
  105.         }else if(cns==qName){
  106.         	cns="";
  107.         	String sss=buf.toString();       	
  108.         	list.add(sss);
  109.  			buf.setLength(0);
  110.  			
  111.         }else if(cid==qName){        	
  112.         	cid="";
  113.         	String sss=buf.toString();
  114.         	list.add(sss);
  115.  			buf.setLength(0);
  116.  			
  117.         }else if(ctimestamp==qName){
  118.         	ctimestamp="";
  119.         	String sss=buf.toString();
  120.         	list.add(sss);
  121.  			buf.setLength(0);
  122.  			
  123.         }else if(ctext==qName){
  124.         	ctext="";
  125.         	String sss=buf.toString();
  126.         	list.add(sss);
  127.  			buf.setLength(0);
  128.  			//有些sss中虽然有重定向标记，但没有“[[”和“]]”,那么就会出现String的index不在范围内的问题
  129.         	if((sss.toUpperCase().contains("#REDIRECT")||sss.contains("#重定向"))&&sss.contains("[[")&&sss.contains("]]")){
  130.         		int i=sss.indexOf("[[");
  131.         		int j=sss.indexOf("]]");
  132.         		String s=sss.substring(i+2,j);
  133.         		list.add(s);
  134.         		list.add("redirect");
  135.         	}else{       		
  136.         		list.add("");
  137.         		list.add("article");
  138.         	}
  139.         }
  140. 			if(qName=="page"){
  141. 				storeDBMongo(list);								
  142. 			}
  143. 			   
  144. 	}
  145.  
  146. 	private void storeDBMongo(List lt) {
  147. 		// TODO Auto-generated method stub
  148. 		for(int i=0;i<list.size();i++){
  149. 			System.out.println(lt.get(i));
  150. 			
  151. 		}
  152. 		try {
  153. 			Data data=new Data();
  154. 			data.setTitle(list.get(0).toString());
  155. 			data.setNamespace(list.get(1).toString());
  156. 			data.setId(list.get(2).toString());
  157. 			data.setLastEsited(list.get(3).toString());
  158. 			data.setMarkup(list.get(4).toString());
  159. 			data.setTarget(list.get(5).toString());
  160. 			data.setType(list.get(6).toString());
  161. 			listdata.add(data);
  162. 			if(listdata.size()>=300){
  163. 				writeToMongoDB();
  164. 				listdata.clear();
  165. 			}
  166. 			list.clear();
  167. 		} catch (Exception e) {
  168. 			// TODO Auto-generated catch block
  169. 			e.printStackTrace();
  170. 		}
  171. 	}
  172.  
  173. 	@Override
  174. 	public void characters(char[] ch,int start,int length)
  175. 			throws SAXException {
  176. 		// TODO Auto-generated method stub
  177.         if(ctitle=="title"){
  178.         	buf.append(new String(ch,start,length));
  179.         }else if(cns=="ns"){        
  180.         	buf.append(new String(ch,length));       	
  181.         }else if(cid=="id"){       	      	
  182.         	buf.append(new String(ch,length));
  183.         	list.add(new String(ch,length));       	
  184.         }else if(ctimestamp=="timestamp"){
  185.         	buf.append(new String(ch,length));        	
  186.         }else if(ctext=="text"){
  187.         	buf.append(new String(ch,length));        	
  188.         }
  189.         
  190. 	}
  191.  
  192. 	@Override
  193. 	public void ignorableWhitespace(char[] ch,int length)
  194. 			throws SAXException {
  195. 		// TODO Auto-generated method stub
  196.  
  197. 	}
  198.  
  199. 	@Override
  200. 	public void processingInstruction(String target,String data)
  201. 			throws SAXException {
  202. 		// TODO Auto-generated method stub
  203.  
  204. 	}
  205.  
  206. 	@Override
  207. 	public void skippedEntity(String name) throws SAXException {
  208. 		// TODO Auto-generated method stub
  209.  
  210. 	}
  211. 	
  212. }

自定义类Data、JSONT

  1. import java.util.HashMap;
  2. import java.util.Map;
  3.  
  4.  
  5. public class Data {
  6. 	private String id;
  7. 	private String namespace;
  8. 	private String type;
  9. 	private String title;
  10. 	private String markup;
  11. 	private String lastEsited;
  12. 	private String target;
  13. 	public String getId() {
  14. 		return id;
  15. 	}
  16. 	public void setId(String id) {
  17. 		this.id = id;
  18. 	}
  19. 	public String getNamespace() {
  20. 		return namespace;
  21. 	}
  22. 	public void setNamespace(String namespace) {
  23. 		this.namespace = namespace;
  24. 	}
  25. 	public String getType() {
  26. 		return type;
  27. 	}
  28. 	public void setType(String type) {
  29. 		this.type = type;
  30. 	}
  31. 	public String getTitle() {
  32. 		return title;
  33. 	}
  34. 	public void setTitle(String title) {
  35. 		this.title = title;
  36. 	}
  37. 	public String getMarkup() {
  38. 		return markup;
  39. 	}
  40. 	public void setMarkup(String markup) {
  41. 		this.markup = markup;
  42. 	}
  43. 	public String getLastEsited() {
  44. 		return lastEsited;
  45. 	}
  46. 	public void setLastEsited(String lastEsited) {
  47. 		this.lastEsited = lastEsited;
  48. 	}
  49. 	public String getTarget() {
  50. 		return target;
  51. 	}
  52. 	public void setTarget(String target) {
  53. 		this.target = target;
  54. 	}
  55. 	public Map<String,Object> toJSONMap(){
  56. 		Map<String,Object> jsonmap=new HashMap<String,Object>();
  57. 		jsonmap.put("id",this.id);
  58. 		jsonmap.put("namespace",this.namespace);
  59. 		jsonmap.put("type",this.type);
  60. 		jsonmap.put("title",this.title);
  61. 		jsonmap.put("markup",this.markup);
  62. 		jsonmap.put("lastEsited",this.lastEsited);
  63. 		jsonmap.put("target",this.target);		
  64. 		return jsonmap;
  65. 	}
  66. 	
  67. }
  68.  
  69.  
  70. /*
  71.  *    NextMap-Crawler Module
  72.  *    
  73.  *    Copyright (C) 2002-2014,Institute of Geographic Sciences and Natural Resources Research,*    Chinese Academy of Sciences
  74.  *
  75.  *    This library is free software; you can redistribute it and/or
  76.  *    modify it under the terms of the GNU Lesser General Public
  77.  *    License as published by the Free Software Foundation;
  78.  *    version 2.1 of the License.
  79.  *
  80.  *    This library is distributed in the hope that it will be useful,*    but WITHOUT ANY WARRANTY; without even the implied warranty of
  81.  *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  82.  *    Lesser General Public License for more details.
  83.  */
  84.  
  85.  
  86. import java.io.IOException;
  87. import java.io.StringWriter;
  88. import java.util.List;
  89. import java.util.Map;
  90.  
  91. import com.fasterxml.jackson.databind.ObjectMapper;
  92.  
  93. /**
  94.  * 
  95.  * @author zhuhaichuan
  96.  * @date 2015-11-8
  97.  * 
  98.  *   
  99.  */
  100.  
  101. public class JSONT {
  102. 	public static String mapToJSONString(Map map) {
  103. 	    StringWriter sw = new StringWriter();
  104. 	    try {
  105. 	      ObjectMapper mapper = new ObjectMapper();
  106. 	      mapper.writeValue(sw,map);
  107. 	    } catch (IOException e) {
  108. 	      // TODO Auto-generated catch block
  109. 	      e.printStackTrace();
  110. 	    }
  111. 	    return sw.toString();
  112. 	  }
  113.  
  114. 	  /**
  115. 	   * 
  116. 	   * @param list
  117. 	   * @return
  118. 	   */
  119. 	  public static String listToJSONString(List list) {
  120. 	    StringWriter sw = new StringWriter();
  121. 	    try {
  122. 	      ObjectMapper mapper = new ObjectMapper();
  123. 	      mapper.writeValue(sw,list);
  124. 	    } catch (IOException e) {
  125. 	      // TODO Auto-generated catch block
  126. 	      e.printStackTrace();
  127. 	    }
  128. 	    return sw.toString();
  129. 	  }
  130.  
  131. 	  /**
  132. 	   * 
  133. 	   * @param list
  134. 	   * @return
  135. 	   */
  136. 	  public static String beanToJSONString(Object bean) {
  137. 	    StringWriter sw = new StringWriter();
  138. 	    try {
  139. 	      ObjectMapper mapper = new ObjectMapper();
  140. 	      mapper.writeValue(sw,bean);
  141. 	    } catch (IOException e) {
  142. 	      // TODO Auto-generated catch block
  143. 	      e.printStackTrace();
  144. 	    }
  145. 	    return sw.toString();
  146. 	  }
  147.  
  148. 	  /**
  149. 	   * 
  150. 	   * @param jsonstr
  151. 	   * @return
  152. 	   */
  153. 	  public static Map jsonToMap(String jsonstr) {
  154. 	    Map map = null;
  155. 	    try {
  156. 	      ObjectMapper mapper = new ObjectMapper();
  157. 	      map = mapper.readValue(jsonstr,Map.class);
  158. 	    } catch (IOException e) {
  159. 	      // TODO Auto-generated catch block
  160. 	      e.printStackTrace();
  161. 	    }
  162. 	    return map;
  163. 	  }
  164.  
  165. 	  /**
  166. 	   * 
  167. 	   * @param jsonstr
  168. 	   * @return
  169. 	   */
  170. 	  public static List jsonToList(String jsonstr) {
  171. 	    List list = null;
  172. 	    try {
  173. 	      ObjectMapper mapper = new ObjectMapper();
  174. 	      list = mapper.readValue(jsonstr,List.class);
  175. 	    } catch (IOException e) {
  176. 	      // TODO Auto-generated catch block
  177. 	      e.printStackTrace();
  178. 	    }
  179. 	    return list;
  180. 	  }
  181. }
还有就是类MyErrorHandler 
  1. import org.xml.sax.ErrorHandler;
  2. import org.xml.sax.SAXException;
  3. import org.xml.sax.SAXParseException;
  4.  
  5.  
  6. public class MyErrorHandler implements ErrorHandler {
  7.  
  8. 	@Override
  9. 	public void warning(SAXParseException exception) throws SAXException {
  10. 		// TODO Auto-generated method stub
  11. 		System.out.println("*******WARNING******");
  12.         System.out.println("行号：" + exception.getLineNumber());
  13.         System.out.println("列号：" + exception.getColumnNumber());
  14.         System.out.println("exception信息：" + exception.getMessage());
  15.         System.out.println("********************");
  16. 	}
  17.  
  18. 	@Override
  19. 	public void error(SAXParseException exception) throws SAXException {
  20. 		// TODO Auto-generated method stub
  21. 		System.out.println("******* ERROR ******");
  22.         System.out.println("行号：" + exception.getLineNumber());
  23.         System.out.println("列号：" + exception.getColumnNumber());
  24.         System.out.println("exception信息：" + exception.getMessage());
  25.         System.out.println("********************");
  26. 	}
  27.  
  28. 	@Override
  29. 	public void fatalError(SAXParseException exception) throws SAXException {
  30. 		// TODO Auto-generated method stub
  31. 		System.out.println("******** FATAL ERROR ********");
  32.         System.out.println("行号：" + exception.getLineNumber());
  33.         System.out.println("列号：" + exception.getColumnNumber());
  34.         System.out.println("exception信息" + exception.getMessage());
  35.         System.out.println("*****************************");
  36. 	}
  37.  
  38. }

自定义MongoDBT类 
  1. import java.util.ArrayList;
  2. import java.util.List;
  3.  
  4. import com.mongodb.DB;
  5. import com.mongodb.DBCollection;
  6. import com.mongodb.DBObject;
  7. import com.mongodb.Mongo;
  8.  
  9.  
  10. public class MongoDBT {
  11. 	public static void writeListToMongo(String ip,int port,String dbname,String collname,List<DBObject> list) throws Exception{
  12. 		Mongo mongo=new Mongo(ip,port);		
  13. 		DB db=mongo.getDB(dbname);
  14. 		DBCollection collection=db.getCollection(collname);
  15. 		List<DBObject> dblist=new ArrayList<DBObject>();
  16. 		for(int i=0;i<list.size();i++){
  17. 			dblist.add(list.get(i));
  18. 		}
  19. 		collection.insert(dblist);
  20. 		mongo.close();
  21. 	}
  22. }

猜你在找的XML相关文章

10分钟掌握XML、JSON及其解析
引言 NOKIA 有句著名的广告语：“科技以人为本”。任何技术都是为了满足人的生产生活需要而...
[CXF REST标准实战系列] 一、JAXB xml与javaBean的转换
Writer：BYSocket（泥沙砖瓦浆木匠） 微博：BYSocket 豆瓣：BYSocket Reprint it anywhere...
[CXF REST标准实战系列] 一、JAXB xml与javaBean的转换
Writer：BYSocket（泥沙砖瓦浆木匠） 微博：BYSocket 豆瓣：BYSocket Reprint it anywhere...
10分钟掌握XML、JSON及其解析
http://blog.jobbole.com/79252/ 引言 NOKIA 有句著名的广告语：“科技以人为本”。任何技...
自定义圆形控件RoundImageView并认识一下attr.xml
(点击上方公众号，可快速关注) 公众号：smart_android 作者：耿广龙｜loonggg 点击“阅读原...
10分钟掌握XML、JSON及其解析
引言 NOKIA 有句著名的广告语：“科技以人为本”。任何技术都是为了满足人的生产生活需要而...
10分钟掌握XML、JSON及其解析(上)
 (点击上方公众号，可快速关注) 来源： Long Luo 的博客 链接：http://longluo.github.i...
10分钟掌握XML、JSON及其解析(中)
接上文 二、JSON XML很好很强大，但是最近有另外一个时代弄潮儿，这就是JSON。现在JSON的光...
10分钟掌握XML、JSON及其解析(下)
接上文 2.4 如何解析JSON？ Android JSON所有相关类，都在org.json包下。 包括JSONObject、...
10分钟掌握XML、JSON及其解析
原文出处：  Long Luo 的博客（@Long_Luo）   引言 NOKIA 有句著名的广告语：“科技以人...
HTMLHTML5JavaScriptCSSjQueryBootstrapAngularjsTypeScriptVueDojoJsonElectronNode.jsextjsExpress XMLES6AjaxFlashUnityReactFlexAnt DesignWeb前端微信小程序微信公众号
关闭广告单独headers封装代码提示错误整数正则非0开头跳页出页码antd table提示URL未注册公众号支付vue hash模式iSlider车牌键盘循环图片echarts 双折左右布局DllPlugin对象创建打字游戏圈选两栏云函数蒙版ES2020橱窗无缝滚动轮播色块碰撞组件销毁文档操作