Read Content of Bzip file

INTRODUCTION

This post will help to unzip bz2 file which contains a list of XML files and generate JSON out of it.

Consider the content in the XML file as single line string.

SOFTWARES & TOOLS

1. Eclipse.
2. Commons-compress-1.10.jar
3. Jackson-all-1.9.0.jar

My Input files are: Employees1.xml.bz2 & Employees2.xml.bz2

My Output files are: Employees1.json & Employees2.json

IMPLEMENTATION

1. package jbr.json_xmlbzip;  
2.   
3. import java.io.BufferedInputStream;  
4. import java.io.BufferedReader;  
5. import java.io.File;  
6. import java.io.FileInputStream;  
7. import java.io.FileNotFoundException;  
8. import java.io.FileOutputStream;  
9. import java.io.IOException;  
10. import java.io.InputStreamReader;  
11. import java.util.ArrayList;  
12. import java.util.List;  
13. import java.util.Map;  
14. import java.util.TreeMap;  
15.   
16. import javax.xml.parsers.DocumentBuilder;  
17. import javax.xml.parsers.DocumentBuilderFactory;  
18. import javax.xml.parsers.ParserConfigurationException;  
19. import javax.xml.xpath.XPath;  
20. import javax.xml.xpath.XPathConstants;  
21. import javax.xml.xpath.XPathExpressionException;  
22. import javax.xml.xpath.XPathFactory;  
23.   
24. import org.apache.commons.compress.compressors.CompressorException;  
25. import org.apache.commons.compress.compressors.CompressorInputStream;  
26. import org.apache.commons.compress.compressors.CompressorStreamFactory;  
27. import org.codehaus.jackson.JsonGenerationException;  
28. import org.codehaus.jackson.map.JsonMappingException;  
29. import org.codehaus.jackson.map.ObjectMapper;  
30. import org.w3c.dom.Document;  
31. import org.w3c.dom.Node;  
32. import org.w3c.dom.NodeList;  
33. import org.xml.sax.SAXException;  
34.   
35. public class JsonFromBzipXml {  
36.   
37.   public static FileInputStream fis;  
38.   public static DocumentBuilderFactory docBuilderFactory;  
39.   public static DocumentBuilder docBuilder;  
40.   public static Document xmlDocument;  
41.   public static XPath xpathObj;  
42.   
43.   public void loadConfig(File inputFile) {  
44.     try {  
45.       fis = new FileInputStream(inputFile);  
46.       docBuilderFactory = DocumentBuilderFactory.newInstance();  
47.       docBuilder = docBuilderFactory.newDocumentBuilder();  
48.       xmlDocument = docBuilder.parse(fis);  
49.       xpathObj = XPathFactory.newInstance().newXPath();  
50.     } catch (FileNotFoundException fe) {  
51.       fe.printStackTrace();  
52.     } catch (ParserConfigurationException pe) {  
53.       pe.printStackTrace();  
54.     } catch (IOException ie) {  
55.       ie.printStackTrace();  
56.     } catch (SAXException se) {  
57.       se.printStackTrace();  
58.     }  
59.   }  
60.   
61.   /** 
62.    * Start the Json Conversion 
63.    *  
64.    * @param args 
65.    * @throws IOException 
66.    * @throws CompressorException 
67.    */  
68.   public static void main(String[] args) throws IOException, CompressorException, XPathExpressionException {  
69.     JsonFromBzipXml converter = new JsonFromBzipXml();  
70.     converter.generateJson();  
71.   }  
72.   
73.   public void generateJson() throws XPathExpressionException {  
74.     Map<String, List<Map<String, String>>> employees = new TreeMap<>();  
75.     Map<String, String> employee = null;  
76.   
77.     File xmlFile = null;  
78.     FileInputStream fileInputStream = null;  
79.     BufferedInputStream bufferedInputStream = null;  
80.     CompressorInputStream compressorInputStream = null;  
81.     BufferedReader bufferedReader = null;  
82.   
83.     try {  
84.       File[] bzipFiles = new File(JsonConstants.INPUT_BZIP_DIRECTORY).listFiles();  
85.   
86.       for (File bzipFile : bzipFiles) {  
87.   
88.         List<Map<String, String>> empList = new ArrayList<>();  
89.   
90.         // Unzip bzip Files  
91.         fileInputStream = new FileInputStream(bzipFile);  
92.         bufferedInputStream = new BufferedInputStream(fileInputStream);  
93.         compressorInputStream = new CompressorStreamFactory().createCompressorInputStream(bufferedInputStream);  
94.         bufferedReader = new BufferedReader(new InputStreamReader(compressorInputStream));  
95.   
96.         String line = null;  
97.   
98.         // System.out.println(bzipFile);  
99.   
100.         while ((line = bufferedReader.readLine()) != null) {  
101.           employee = new TreeMap<>();  
102.           xmlFile = new File(bzipFile.getName().replace(".bz2", ""));  
103.           xmlFile.createNewFile();  
104.           FileOutputStream fileOutputStream = new FileOutputStream(xmlFile);  
105.           fileOutputStream.write(line.getBytes());  
106.           // System.out.println(line);  
107.   
108.           // Load the xml file  
109.           loadConfig(xmlFile);  
110.   
111.           System.out.println("\n===Retrieve all Elements of an Employee====");  
112.           String xpath = "/Employees/Employee";  
113.           System.out.println("xpath: " + xpath);  
114.           Node node = (Node) xpathObj.compile(xpath).evaluate(xmlDocument, XPathConstants.NODE);  
115.           if (null != node) {  
116.             NodeList nodeList = node.getChildNodes();  
117.   
118.             for (int i = 0; null != nodeList && i < nodeList.getLength(); i++) {  
119.               Node subNode = nodeList.item(i);  
120.               if (subNode.getNodeType() == Node.ELEMENT_NODE)  
121.                 System.out.println(nodeList.item(i).getNodeName() + " : " + subNode.getFirstChild().getNodeValue());  
122.               employee.put(nodeList.item(i).getNodeName(), subNode.getFirstChild().getNodeValue());  
123.             }  
124.           }  
125.   
126.           fileOutputStream.close();  
127.         } // end while  
128.   
129.         empList.add(employee);  
130.         employees.put("employees", empList);  
131.         toJsonFromMap(employees, JsonConstants.OUTPUT_JSON_DIRECTORY + xmlFile.getName().replace(".xml", ".json"));  
132.   
133.       } // end for  
134.   
135.     } catch (IOException ioException) {  
136.       ioException.printStackTrace();  
137.     } catch (CompressorException ce) {  
138.       ce.printStackTrace();  
139.     }  
140.   }  
141.   
142.   public static void toJsonFromMap(Map map, String outputFile) {  
143.     try {  
144.       new ObjectMapper().writeValue(new File(outputFile), map);  
145.     } catch (JsonGenerationException e) {  
146.       e.printStackTrace();  
147.     } catch (JsonMappingException e) {  
148.       e.printStackTrace();  
149.     } catch (IOException e) {  
150.       e.printStackTrace();  
151.     }  
152.   }  
153.   
154.   public static String toJsonFromList1(List list) {  
155.     String value = "";  
156.     try {  
157.       value = new ObjectMapper().writeValueAsString(list);  
158.     } catch (JsonGenerationException e) {  
159.       e.printStackTrace();  
160.     } catch (JsonMappingException e) {  
161.       e.printStackTrace();  
162.     } catch (IOException e) {  
163.       e.printStackTrace();  
164.     }  
165.   
166.     return value;  
167.   }  
168.   
169.   public interface JsonConstants {  
170.     String INPUT_BZIP_DIRECTORY = "input/bzip";  
171.     String OUTPUT_JSON_DIRECTORY = "output/bzip-jsons/";  
172.   }  
173. }  

OUTPUT

Console

===Retrieve all Elements of an Employee==== xpath: /Employees/Employee firstname : Ranjith lastname : Sekar age : 30 address : Chennai email : ranjith@gmail.com ===Retrieve all Elements of an Employee==== xpath: /Employees/Employee firstname : Ranjith lastname : Sekar age : 30 address : Chennai email : ranjith@gmail.com

JSON File

{"employees":[{"address":"Chennai","age":"30","email":"ranjith@gmail.com","firstname":"Ranjith","lastname":"Sekar"}]}