Develop Reference

Parse value containing special character "/" gives wrong output using SAX parser

I am have below xml structure
<fs:AsReportedItem>
<fs:BookMark>/BODY[1]/DIV[3135]/DIV[0]/TABLE[0]/TBODY[0]/TR[32]/TD[5]/DIV[0]/FONT[0]/substr(1,2)
</fs:BookMark>
</fs:AsReportedItem>
I am parsing using SAX and reading tax value in the endElement() method
Here is my sample code
private void parseDocument() {
// parse
SAXParserFactory factory = SAXParserFactory.newInstance();
try {
SAXParser parser = factory.newSAXParser();
parser.parse(FileName, this);
} catch (ParserConfigurationException e) {
System.out.println("ParserConfig error");
} catch (SAXException e) {
System.out.println("SAXException : xml not well formed");
} catch (IOException e) {
System.out.println("IO error");
}
}
public void startElement(String s, String s1, String elementName, Attributes attributes) throws SAXException {
if (OrgDataPartitonObj != null && "fs:FinancialStatementLineItemDataItem".equals(OrgDataPartitonObj.getType())) {
FinancialStatementLineItemParser.startFinancialStatementLineItemParser(OrgDataPartitonObj,financialStatementLineItemObj, elementName, attributes);
}
}
public void endElement(String s, String s1, String element) throws SAXException {
if (OrgDataPartitonObj != null && "fs:FinancialStatementLineItemDataItem".equals(OrgDataPartitonObj.getType())) {
FinancialStatementLineItemParser.getEndElementFinancialStatementLineItemParser(financialStatementLineItemObj, element, tmpValue);
}
}
public static void getEndElementFinancialStatementLineItemParser(FinancialStatementLineItem financialStatementLineItemObj, String element, String tmpValue) {
if (element.equals("fs:BookMark")) {
financialStatementLineItemObj.setBookMark(tmpValue);
}
}
#Override
public void characters(char[] buffer, int start, int length) {
tmpValue = new String(buffer, start, length);
}
When i debug then i can see only this value /substr(1,2) all value with "/" is escaped
I dont know why i am not getting full value /BODY[1]/DIV[3135]/DIV[0]/TABLE[0]/TBODY[0]/TR[32]/TD[5]/DIV[0]/FONT[0]/substr(1,2)
If any escape character is used then where i have to use .

Here the sourcecode for a DefaultHandler which collects the text:
private static DefaultHandler getHandler() {
return new DefaultHandler() {
String text;
#Override
public void startElement(String uri, String localName, String qName, Attributes attributes)
throws SAXException {
if ("BookMark".equals(qName)) {
text = "";
}
}
#Override
public void characters(char[] ch, int start, int length) throws SAXException {
text += new String(ch).trim();
}
#Override
public void endElement(String uri, String localName, String qName) throws SAXException {
if ("BookMark".equals(qName)) {
System.out.println("endElement: " + text);
}
}
};
}

You need to change your characters()-method to
#Override
public void characters(char[] buffer, int start, int length) {
tmpValue += new String(buffer, start, length);
}
and you must reset tmpValue in the startElement()-method to "".

Just change character() method
#Override
public void characters(char[] buffer, int start, int length) {
tmpValue += new String(buffer, start, length);
}
And add this at last line in the endElement method .
public void endElement(String s, String s1, String element) throws SAXException {
if (OrgDataPartitonObj != null && "fs:FinancialStatementLineItemDataItem".equals(OrgDataPartitonObj.getType())) {
FinancialStatementLineItemParser.getEndElementFinancialStatementLineItemParser(financialStatementLineItemObj, element, tmpValue);
}
tmpValue="";
}

How to write the BufferedWriter out of main function

Now I use the sax parser to analysis the xml file(the following sample code comes from tutorialspoint). I want to output all the things to a txt file using the BufferedWriter when we call the characters function, while I don't get a way to make this. If I write this BufferedWriter in the characters function, it will only output the last string, since it will only record the last call. If I write this BufferedWriter in the main function, since they are two classes, the UserHandler couldn't recognize the BufferedWriter created in the main function(the dblpSax class). I also tried sth to make a class instance, while I still got involved troubles. Could you give me a way to make this? Thanks.
The Bufferwriter I want to use is as follows:
File writename = new File("output.txt");
writename.createNewFile();
BufferedWriter out = new BufferedWriter(new FileWriter(writename));
public class dblpSax{
public static void main(String[] args){
try {
File inputFile = new File("student.txt");
SAXParserFactory factory = SAXParserFactory.newInstance();
SAXParser saxParser = factory.newSAXParser();
UserHandler userhandler = new UserHandler();
saxParser.parse(inputFile, userhandler);
} catch (Exception e) {
e.printStackTrace();
}
}
}
class UserHandler extends DefaultHandler {
boolean bFirstName = false;
boolean bLastName = false;
boolean bNickName = false;
boolean bMarks = false;
public void startElement(String uri,
String localName, String qName, Attributes attributes)
throws SAXException {
if (qName.equalsIgnoreCase("student")) {
String rollNo = attributes.getValue("rollno");
System.out.println("Roll No : " + rollNo);
} else if (qName.equalsIgnoreCase("firstname")) {
bFirstName = true;
} else if (qName.equalsIgnoreCase("lastname")) {
bLastName = true;
} else if (qName.equalsIgnoreCase("nickname")) {
bNickName = true;
}
else if (qName.equalsIgnoreCase("marks")) {
bMarks = true;
}
}
public void endElement(String uri,
String localName, String qName) throws SAXException {
if (qName.equalsIgnoreCase("student")) {
System.out.println("End Element :" + qName);
}
}
public void characters(char ch[],
int start, int length) throws SAXException {
if (bFirstName) {
System.out.println("First Name: "
+ new String(ch, start, length));
bFirstName = false;
} else if (bLastName) {
System.out.println("Last Name: "
+ new String(ch, start, length));
bLastName = false;
} else if (bNickName) {
System.out.println("Nick Name: "
+ new String(ch, start, length));
bNickName = false;
} else if (bMarks) {
System.out.println("Marks: "
+ new String(ch, start, length));
bMarks = false;
}
}
}

You need a BufferedWriter at the same level as the parsing, best customizable outside the DefaultHandler.
try (BufferedWriter out = new BufferedWriter(....)) {
UserHandler userhandler = new UserHandler(out);
saxParser.parse(inputFile, userhandler);
}
} catch (Exception e) {
e.printStackTrace();
}
}
}
class UserHandler extends DefaultHandler {
private final BufferedWriter out; // Or PrintWriter
UserHandler(BufferedWriter out) {
this.out = out;
}
And then one can all out.write everywhere.

Java Xml Element - Get node position in the file

I have XML file and I want to get position of a node.
<Root>
<Node1></Node1>
</Root>
I want to get 1) start and end positions; 2) start and end lines
How to do that? Thanks

Create a Reader that keeps track of position information you want:
static public class MyReader extends Reader {
final private Reader internalReader;
private int pos;
private int line;
public MyReader(Reader internalReader) {
this.internalReader = internalReader;
}
public int getPos() {
return pos;
}
public int getLine() {
return line;
}
#Override
public int read(char[] cbuf, int off, int len) throws IOException {
int chars_read = internalReader.read(cbuf, off, 1);
pos += chars_read;
if(cbuf[off] =='\n' && chars_read > 0) {
line++;
}
return chars_read;
}
#Override
public void close() throws IOException {
internalReader.close();
}
}
Use that with a ContentHandler that stores the position information in some data structure associated with the elements.
String xmlString = "<Root>\n"
+ " <Node1></Node1>\n"
+ "</Root>";
StringReader strReader = new StringReader(xmlString);
MyReader reader = new MyReader(strReader);
SAXParserFactory factory = SAXParserFactory.newInstance();
SAXParser parser = factory.newSAXParser();
XMLReader xmlreader = parser.getXMLReader();
Map<String,List<Integer>> startMap = new HashMap<>();
Map<String,List<Integer>> endMap = new HashMap<>();
Map<String,List<Integer>> startLineMap = new HashMap<>();
Map<String,List<Integer>> endLineMap = new HashMap<>();
DefaultHandler handler = new DefaultHandler() {
#Override
public void endElement(String uri, String localName, String qName) throws SAXException {
super.endElement(uri, localName, qName); //To change body of generated methods, choose Tools | Templates.
List<Integer> l = endMap.get(qName);
if(null == l) {
l = new ArrayList<>();
}
l.add(reader.getPos());
endMap.put(qName, l);
List<Integer> ll = endLineMap.get(qName);
if(null == ll) {
ll= new ArrayList<>();
}
ll.add(reader.getLine());
endLineMap.put(qName, ll);
}
#Override
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
super.startElement(uri, localName, qName, attributes); //To change body of generated methods, choose Tools | Templates.
List<Integer> l = startMap.get(qName);
if(null == l) {
l = new ArrayList<>();
}
l.add(reader.getPos());
startMap.put(qName, l);
List<Integer> ll = startLineMap.get(qName);
if(null == ll) {
ll= new ArrayList<>();
}
ll.add(reader.getLine());
startLineMap.put(qName, ll);
}
};
xmlreader.setContentHandler(handler);
xmlreader.parse(new InputSource(reader));
System.out.println("startMap = " + startMap);
System.out.println("endMap = " + endMap);
System.out.println("startLineMap = " + startLineMap);
System.out.println("endLineMap = " + endLineMap);

Can't parse File and Handler in SAXParser

I'm passing in an XML file and a handler to the SAXParser but I'm getting this error:
The attributes for the parse method are defined as (File, DefaultHandler) which match exactly, so I'm not sure where I'm going wrong. Here is the full method:
public String readXML (File readFile) throws Exception {
SAXParserFactory saxFactory = SAXParserFactory.newInstance();
SAXParser saxParser = saxFactory.newSAXParser();
final String outputString = "";
DefaultHandler handler = new DefaultHandler() {
boolean bArtist = false;
boolean bAlbumName = false;
boolean bYear = false;
boolean bGenre = false;
public void startElement(String uri, String localName, String qName, Attributes attr)
throws SAXException {
if (qName.equalsIgnoreCase("ARTIST")) { bArtist = true; }
if (qName.equalsIgnoreCase("ALBUMNAME")) { bAlbumName = true; }
if (qName.equalsIgnoreCase("YEAR")) { bYear = true; }
if (qName.equalsIgnoreCase("GENRE")) { bGenre = true; }
}
public void characters(char ch[], int start, int length) {
if (bArtist) {
outputString.concat("Artist: " + new String(ch,start,length) + "\n");
}
if(bAlbumName) {
outputString.concat("Album: " + new String(ch,start,length) + "\n");
}
if(bYear) {
outputString.concat("Year: " + new String(ch,start,length) + "\n");
}
if(bGenre) {
outputString.concat("Genre: " + new String(ch,start,length) + "\n");
}
outputString.concat("\n");
}
};
saxParser.parse(readFile,handler);
return outputString;
}

It should be org.xml.sax.helpers.DefaultHandler
not jdk.internal...
so
import org.xml.sax.helpers.DefaultHandler;
You should probably also define the class that extends the DefaultHandler not just inline it.

Unable to read special characters from xml using java

When i try to read the xml from java using SAX parser, it is unable to read the content in element present after special character
For ex:
<title>It's too difficult</title>
After reading using the SAX parser, it's displaying only It
How to handle special characters. My sample code is as below
package com.test.java;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
public class ReadXMLUsingSAXParser {
public static void main(String argv[]) {
try {
SAXParserFactory factory = SAXParserFactory.newInstance();
SAXParser saxParser = factory.newSAXParser();
DefaultHandler handler = new DefaultHandler() {
int titleCount;
boolean title = false;
boolean description = false;
public void startElement(String uri, String localName,
String qName, Attributes attributes)
throws SAXException {
// System.out.println("Start Element :" + qName);
if (qName.equalsIgnoreCase("title")) {
title = true;
titleCount+=1;
}
if (qName.equalsIgnoreCase("description")) {
description = true;
}
}
public void endElement(String uri, String localName,
String qName)
throws SAXException {
// System.out.println("End Element :" + qName);
}
public void characters(char ch[], int start, int length)
throws SAXException {
if (title&&titleCount>2) {
System.out.println("title : "
+ new String(ch, start, length)+":"+titleCount);
title = false;
}
if (description) {
System.out.println("description : "
+ new String(ch, start, length));
description = false;
}
}
};
saxParser.parse("C:\\Documents and Settings\\sukumar\\Desktop\\sample.xml", handler);
} catch (Exception e) {
e.printStackTrace();
}
}
}

The characters(char ch[], int start, int length) methode does not read full lines, you should store the characters in a StringBuffer and use it in the endElemen method.
E.g.:
private StringBuffer buffer = new StringBuffer();
public void endElement(String uri, String localName,
String qName)
throws SAXException {
if (qName.equalsIgnoreCase("title")) {
System.out.println("title: " + buffer);
}else if (qName.equalsIgnoreCase("description")) {
System.out.println("description: " + buffer);
}
buffer = new StringBuffer();
}
public void characters(char ch[], int start, int length)
throws SAXException {
buffer.append(new String(ch, start, length));
}