We Keep Coding

How to fix issue with StAX parsing in java using xml?

I am trying to parse the value displayName from an xml file I have. I am using the StAX way to do the parsing, however when I go to parse the code it grabs everything but the actual value I want. I honestly have no clue why because I strictly mention to grab the name that .equalsIgnoreCase(). I don't receive any errors, the only problem is I can't grab the value that I need.
Java:
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.util.Iterator;
import javax.xml.namespace.QName;
import javax.xml.stream.XMLEventReader;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.XMLStreamException;
import javax.xml.stream.events.*;
public class Driver {
private static boolean bname;
public static void main(String[] args) throws FileNotFoundException, XMLStreamException {
File file = new File("C:\\Users\\Robert\\Desktop\\root\\SDKCode\\src\\main\\java\\com\\example\\xmlClass\\data.xml");
parser(file);
}
public static void parser(File file) throws FileNotFoundException, XMLStreamException {
bname = false;
XMLInputFactory factory = XMLInputFactory.newInstance();
XMLEventReader eventReader = factory.createXMLEventReader(new FileReader(file));
while (eventReader.hasNext()) {
XMLEvent event = eventReader.nextEvent();
// This will trigger when the tag is of type <...>
if (event.isStartElement()) {
StartElement element = (StartElement) event;
Iterator<Attribute> iterator = element.getAttributes();
while (iterator.hasNext()) {
Attribute attribute = iterator.next();
QName name = attribute.getName();
String value = attribute.getValue();
System.out.println(name + " = " + value);
}
if (element.getName().toString().equalsIgnoreCase("displayName")) {
bname = true;
}
}
if (event.isEndElement()) {
EndElement element = (EndElement) event;
if (element.getName().toString().equalsIgnoreCase("displayName")) {
bname = false;
}
}
if (event.isCharacters()) {
// Depending upon the tag opened the data is retrieved .
Characters element = (Characters) event;
if (bname) {
System.out.println(element.getData());
}
}
}
}
}
XML:
<?xml version="1.0" encoding="UTF-8"?>
<results
xmlns="urn:www-collation-com:1.0"
xmlns:coll="urn:www-collation-com:1.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="urn:www-collation-com:1.0
urn:www-collation-com:1.0/results.xsd">
<WebServiceImpl array="1"
guid="FFVVRJ5618KJRHNFUIRV845NRUVHR" xsi:type="coll:com.model.topology.app.web.WebService">
<isPlaceholder>false</isPlaceholder>
<displayName>server.servername.siqom.siqom.us.com</displayName>
<hierarchyType>WebService</hierarchyType>
<hierarchyDomain>app.web</hierarchyDomain>
</WebServiceImpl>
</results>

How can I go back to Main method in my code, And depending on Condition?

In this program I am Reading .xlsx file. And adding cell data to vector, if vector size is less-than 12 no need to read remaining data, and i need to go main method.
How can I do in my program ?
This is my Code :
package com.read;
import java.text.SimpleDateFormat;
import java.util.Calendar;
import java.util.Vector;
import org.apache.poi.openxml4j.opc.OPCPackage;
import java.io.InputStream;
import org.apache.poi.xssf.eventusermodel.XSSFReader;
import org.apache.poi.xssf.model.SharedStringsTable;
import org.apache.poi.xssf.usermodel.XSSFRichTextString;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;
import org.xml.sax.helpers.XMLReaderFactory;
public class SendDataToDb {
public static void main(String[] args) {
SendDataToDb sd = new SendDataToDb();
try {
sd.processOneSheet("C:/Users/User/Desktop/New folder/Untitled 2.xlsx");
System.out.println("in Main method");
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public void processOneSheet(String filename) throws Exception {
System.out.println("executing Process Method");
OPCPackage pkg = OPCPackage.open(filename);
XSSFReader r = new XSSFReader( pkg );
SharedStringsTable sst = r.getSharedStringsTable();
System.out.println("count "+sst.getCount());
XMLReader parser = fetchSheetParser(sst);
// To look up the Sheet Name / Sheet Order / rID,
// you need to process the core Workbook stream.
// Normally it's of the form rId# or rSheet#
InputStream sheet2 = r.getSheet("rId2");
System.out.println("Sheet2");
InputSource sheetSource = new InputSource(sheet2);
parser.parse(sheetSource);
sheet2.close();
}
public XMLReader fetchSheetParser(SharedStringsTable sst) throws SAXException {
//System.out.println("EXECUTING fetchSheetParser METHOD");
XMLReader parser = XMLReaderFactory.createXMLReader("org.apache.xerces.parsers.SAXParser");
ContentHandler handler = new SheetHandler(sst);
parser.setContentHandler(handler);
System.out.println("Method :fetchSheetParser");
return parser;
}
/**
* See org.xml.sax.helpers.DefaultHandler javadocs
*/
private class SheetHandler extends DefaultHandler {
private SharedStringsTable sst;
private String lastContents;
private boolean nextIsString;
Vector values = new Vector(20);
private SheetHandler(SharedStringsTable sst) {
this.sst = sst;
}
public void startElement(String uri, String localName, String name,
Attributes attributes) throws SAXException {
// c => cell
//long l = Long.valueOf(attributes.getValue("r"));
if(name.equals("c")){
columnNum++;
}
if(name.equals("c")) {
// Print the cell reference
// Figure out if the value is an index in the SST
String cellType = attributes.getValue("t");
if(cellType != null && cellType.equals("s")) {
nextIsString = true;
} else {
nextIsString = false;
}
}
// Clear contents cache
lastContents = "";
}
public void endElement(String uri, String localName, String name)
throws SAXException {
//System.out.println("Method :222222222");
// Process the last contents as required.
// Do now, as characters() may be called more than once
if(nextIsString) {
int idx = Integer.parseInt(lastContents);
lastContents = new XSSFRichTextString(sst.getEntryAt(idx)).toString();
nextIsString = false;
}
// v => contents of a cell
// Output after we've seen the string contents
if(name.equals("v")) {
values.add(lastContents);
}
if(name.equals("row")) {
System.out.println(values);
//values.setSize(50);
System.out.println(values.size()+" "+values.capacity());
//********************************************************
//I AM CHECKING CONDITION HERE, IF CONDITION IS TRUE I NEED STOP THE REMAINING PROCESS AND GO TO MAIN METHOD.
if(values.size() < 12)
values.removeAllElements();
//WHAT CODE I NEED TO WRITE HERE TO STOP THE EXECUTION OF REMAINING PROCESS AND GO TO MAIN
//***************************************************************
}
}
public void characters(char[] ch, int start, int length)
throws SAXException {
//System.out.println("method : 333333333333");
lastContents += new String(ch, start, length);
}
}
}
check the code in between lines of //******************************
and
//******************************************

You can throw a SAXException wherever you want the parsing to stop:
throw new SAXException("<Your message>")
and handle it in the main method.

After your checking, you should throw the Exception to get out from there and get it back to the main method.
throw new Exception("vector size has to be less than 12");

Web scraper not creating CSV file

I have created a web scraper which brings the market data of share rates from the website of stock exchange. www.psx.com.pk in that site there is a hyperlink of Market Summary. From that link I have to scrap the data. I have created a program which is as follows.
package com.market_summary;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.ArrayList;
import java.util.Date;
import java.util.Iterator;
import java.util.Locale;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
public class ComMarket_summary {
boolean writeCSVToConsole = true;
boolean writeCSVToFile = true;
boolean sortTheList = true;
boolean writeToConsole;
boolean writeToFile;
public static Document doc = null;
public static Elements tbodyElements = null;
public static Elements elements = null;
public static Elements tdElements = null;
public static Elements trElement2 = null;
public static String Dcomma = ",";
public static String line = "";
public static ArrayList<Elements> sampleList = new ArrayList<Elements>();
public static void createConnection() throws IOException {
System.setProperty("http.proxyHost", "191.1.1.202");
System.setProperty("http.proxyPort", "8080");
String tempUrl = "http://www.psx.com.pk/index.php";
doc = Jsoup.connect(tempUrl).get();
System.out.println("Successfully Connected");
}
public static void parsingHTML() throws Exception {
File fold = new File("C:\\market_smry.csv");
fold.delete();
File fnew = new File("C:\\market_smry.csv");
for (Element table : doc.getElementsByTag("table")) {
for (Element trElement : table.getElementsByTag("tr")) {
trElement2 = trElement.getElementsByTag("td");
tdElements = trElement.getElementsByTag("td");
FileWriter sb = new FileWriter(fnew, true);
if (trElement.hasClass("marketData")) {
for (Iterator<Element> it = tdElements.iterator(); it.hasNext();) {
if (it.hasNext()) {
sb.append("\r\n");
}
for (Iterator<Element> it2 = trElement2.iterator(); it.hasNext();) {
Element tdElement2 = it.next();
final String content = tdElement2.text();
if (it2.hasNext()) {
sb.append(formatData(content));
sb.append(" | ");
}
}
System.out.println(sb.toString());
sb.flush();
sb.close();
}
}
System.out.println(sampleList.add(tdElements));
}
}
}
private static final SimpleDateFormat FORMATTER_MMM_d_yyyy = new SimpleDateFormat("MMM d, yyyy", Locale.US);
private static final SimpleDateFormat FORMATTER_dd_MMM_yyyy = new SimpleDateFormat("dd-MMM-YYYY", Locale.US);
public static String formatData(String text) {
String tmp = null;
try {
Date d = FORMATTER_MMM_d_yyyy.parse(text);
tmp = FORMATTER_dd_MMM_yyyy.format(d);
} catch (ParseException pe) {
tmp = text;
}
return tmp;
}
public static void main(String[] args) throws IOException, Exception {
createConnection();
parsingHTML();
}
}
Now, the problem is when I execute this program it should create a .csv file but what actually happens is it's not creating any file. When I debug this code I found that program is not entering in the loop. I don't understand that why it is doing so. While when I run the same program on the other website which have slightly different page structure it is running fine.
What I understand that this data is present in the #document which is a virtual element and doesn't mean anything that's why program can't read it while there is no such thing in other website. Kindly, help me out to read the data inside the #document element.

Long Story Short
Change your temp url to http://www.psx.com.pk/phps/index1.php
Explanation
There is no table in the document of http://www.psx.com.pk/index.php.
Instead it is showing it's content in two frameset.
One is dummy with url http://www.psx.com.pk/phps/blank.php.
Another one is the real page which is showing actual data and it's url is
http://www.psx.com.pk/phps/index1.php

Parsing issue in Java StAX XML

I've been searching for a solution to this problem and found nothing. I'm creating a simple chat over Java TCP/IP sockets as an assignment and I've encountered a problem creating an XML string containing the letter åäö.
Lets say I pass an XMLObject with the fields
name="Server", color="#FF0000" text="åäö"
the generated xmlstring that is returned by the parser will be
<?xml version="1.0"?><message sender="Server"><text color="#FF0000”>???</text></message>
åäö turns into ???. Any idea? Thanks!
** UPDATE**
Ok, so I just realised the problem arises when getting some text from a JTextArea.
If I run this code:
package self.edu.javaprojekt.view;
import self.edu.javaprojekt.model.XMLObject;
import self.edu.javaprojekt.model.XMLParser;
public class Test {
/**
* #param args
*/
public static void main(String[] args) {
XMLObject object = new XMLObject();
object.setColor("#FF0000");
object.setSender("Server");
object.setText("åäö");
String parsed = XMLParser.parse(object);
System.out.println(parsed);
System.out.println(XMLParser.parse(parsed));
}
}
I get the proper result:
<?xml version="1.0" encoding="UTF-8"?><message sender="Server"><text color="#FF0000">åäö</text></message>
XMLObject [sender=Server, text=åäö, color=#FF0000]
But with a text area. The text that is returned in the following method is added to an XMLObject and then sent for parsing.
public String readAndClearMessageArea() {
String text = messageTextArea.getText();
appendToPane("\n" + controller.getName() + ": " + text, controller.getColor());
messageTextArea.setText("");
return text;
}
I get the weird result. Any new ideas? Thanks!!
This is the parser
package self.edu.javaprojekt.model;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.InputStream;
import java.io.OutputStream;
import java.io.UnsupportedEncodingException;
import java.nio.ByteBuffer;
import java.nio.charset.Charset;
import java.util.Iterator;
import javax.xml.stream.XMLEventFactory;
import javax.xml.stream.XMLEventReader;
import javax.xml.stream.XMLEventWriter;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.XMLOutputFactory;
import javax.xml.stream.XMLStreamException;
import javax.xml.stream.events.Attribute;
import javax.xml.stream.events.Characters;
import javax.xml.stream.events.EndElement;
import javax.xml.stream.events.StartDocument;
import javax.xml.stream.events.StartElement;
import javax.xml.stream.events.XMLEvent;
public class XMLParser {
public static final String MESSAGE_TAG = "message";
public static final String SENDER_TAG = "sender";
public static final String TEXT_TAG = "text";
public static final String COLOR_TAG = "color";
public static final String DISCONNECT_TAG = "disconnect";
public static final String ENCRYPTED_TAG = "encrypted";
public static final String ENCRYPTED_TYPE_TAG = "type";
public static final String KEY_REQUEST_TAG = "keyrequest";
public static String parse(XMLObject object) {
// create an XMLOutputFactory
XMLOutputFactory outputFactory = XMLOutputFactory.newInstance();
// create XMLEventWriter
XMLEventWriter eventWriter;
ByteArrayOutputStream out = new ByteArrayOutputStream();
String xmlString = "";
try {
eventWriter = outputFactory.createXMLEventWriter(out);
// create an EventFactory
XMLEventFactory eventFactory = XMLEventFactory.newInstance();
//XMLEvent end = eventFactory.createDTD("\n");
//XMLEvent tab = eventFactory.createDTD("\t");
// create and write Start Tag
StartDocument startDocument = eventFactory.createStartDocument("UTF-8");
eventWriter.add(startDocument);
// create message open tag
//eventWriter.add(end);
StartElement messageStartElement = eventFactory.createStartElement(
"", "", MESSAGE_TAG);
eventWriter.add(messageStartElement);
eventWriter.add(eventFactory.createAttribute(SENDER_TAG,
object.getSender()));
//eventWriter.add(end);
// create the text
//eventWriter.add(tab);
StartElement textStartElement = eventFactory.createStartElement("",
"", TEXT_TAG);
eventWriter.add(textStartElement);
eventWriter.add(eventFactory.createAttribute(COLOR_TAG,
object.getColor()));
Characters characters = eventFactory.createCharacters(object.getText());
eventWriter.add(characters);
//eventWriter.add(tab);
eventWriter.add(eventFactory.createEndElement("", "", TEXT_TAG));
//eventWriter.add(end);
eventWriter.add(eventFactory.createEndElement("", "", MESSAGE_TAG));
//eventWriter.add(end);
eventWriter.add(eventFactory.createEndDocument());
eventWriter.close();
xmlString = out.toString("UTF-8");
} catch (XMLStreamException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (UnsupportedEncodingException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return xmlString;
}
#SuppressWarnings("unchecked")
public static XMLObject parse(String string) {
XMLObject object = null;
try {
// First, create a new XMLInputFactory
XMLInputFactory inputFactory = XMLInputFactory.newInstance();
// Setup a new eventReader
InputStream in;
if (!string.equals("")) {
in = new ByteArrayInputStream(Charset.forName("UTF-8")
.encode(string).array());
} else {
in = new FileInputStream("xmltest.txt");
}
XMLEventReader eventReader = inputFactory.createXMLEventReader(in);
// read the XML document
while (eventReader.hasNext()) {
XMLEvent event = eventReader.nextEvent();
if (event.isStartElement()) {
StartElement startElement = event.asStartElement();
// If we have a message
if (startElement.getName().getLocalPart()
.equals(MESSAGE_TAG)) {
object = new XMLObject();
// We read the attributes from this tag and add the
// sender
// attribute to our object
Iterator<Attribute> attributes = startElement
.getAttributes();
while (attributes.hasNext()) {
Attribute attribute = attributes.next();
if (attribute.getName().getLocalPart()
.equals(SENDER_TAG)) {
object.setSender(attribute.getValue());
}
}
}
if (startElement.getName().getLocalPart().equals(TEXT_TAG)) {
// We read the attributes from this tag and add the
// color
// attribute to our object
Iterator<Attribute> attributes = startElement
.getAttributes();
while (attributes.hasNext()) {
Attribute attribute = attributes.next();
if (attribute.getName().getLocalPart()
.equals(COLOR_TAG)) {
object.setColor(attribute.getValue());
}
}
// And then get the text
event = eventReader.nextEvent();
object.setText(event.asCharacters().getData());
continue;
}
}
// If we reach the end of the message, return the object
if (event.isEndElement()) {
EndElement endElement = event.asEndElement();
if (endElement.getName().getLocalPart().equals(MESSAGE_TAG)) {
return object;
}
}
}
} catch (XMLStreamException | FileNotFoundException e) {
e.printStackTrace();
}
return null;
}
}
This is the class holding the xml values
package self.edu.javaprojekt.model;
public class XMLObject {
private String sender, text, color;
public String getSender() {
return sender;
}
public String getText() {
return text;
}
public String getColor() {
return color;
}
public void setSender(String sender) {
this.sender = sender;
}
public void setText(String text) {
this.text = text;
}
public void setColor(String color) {
this.color = color;
}
#Override
public String toString() {
return "XMLObject [sender=" + sender + ", text=" + text + ", color="
+ color + "]";
}
}

I have seen this before, you can use the different encoding to see which one work for you. But try ISO-8859-1 or UTF-16. Not sure which encoding you need.

Low memory writing/reading with Apache POI

I'm trying to write a pretty large XLSX file (4M+ cells) and I'm having some memory issues.
I can't use SXSSF since I also need to read the existing cells in the template.
Is there anything I can do to reduce the memory footprint?
Perhaps combine streaming reading and streaming writing?

To handle large data with low memory, the best and I think the only option is SXSSF api-s.
If you need to read some data of the existing cells, I assume you do not need the entire 4M+ at the same time.
In such a case based on your application requirement, you can handle the window size yourself and keep in memory only the amount of data you need at a particular time.
You can start by looking at the example at :
http://poi.apache.org/spreadsheet/how-to.html#sxssf
Something as
SXSSFWorkbook wb = new SXSSFWorkbook(-1); // turn off auto-flushing and accumulate all rows in memory
// manually control how rows are flushed to disk
if(rownum % NOR == 0) {
((SXSSFSheet)sh).flushRows(NOR); // retain NOR last rows and flush all others
Hope this helps.

I used SAX parser to process events of the XML document presentation. This is
import com.sun.org.apache.xerces.internal.parsers.SAXParser;
import org.apache.poi.openxml4j.opc.PackageAccess;
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.xssf.eventusermodel.XSSFReader;
import org.apache.poi.xssf.model.SharedStringsTable;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xssf.usermodel.XSSFRichTextString;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;
import java.io.BufferedInputStream;
import java.io.InputStream;
import java.util.Collections;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
public class LowMemoryExcelFileReader {
private String file;
public LowMemoryExcelFileReader(String file) {
this.file = file;
}
public List<String[]> read() {
try {
return processFirstSheet(file);
} catch (Exception e) {
throw new RuntimeException(e);
}
}
private List<String []> readSheet(Sheet sheet) {
List<String []> res = new LinkedList<>();
Iterator<Row> rowIterator = sheet.rowIterator();
while (rowIterator.hasNext()) {
Row row = rowIterator.next();
int cellsNumber = row.getLastCellNum();
String [] cellsValues = new String[cellsNumber];
Iterator<Cell> cellIterator = row.cellIterator();
int cellIndex = 0;
while (cellIterator.hasNext()) {
Cell cell = cellIterator.next();
cellsValues[cellIndex++] = cell.getStringCellValue();
}
res.add(cellsValues);
}
return res;
}
public String getFile() {
return file;
}
public void setFile(String file) {
this.file = file;
}
private List<String []> processFirstSheet(String filename) throws Exception {
OPCPackage pkg = OPCPackage.open(filename, PackageAccess.READ);
XSSFReader r = new XSSFReader(pkg);
SharedStringsTable sst = r.getSharedStringsTable();
SheetHandler handler = new SheetHandler(sst);
XMLReader parser = fetchSheetParser(handler);
Iterator<InputStream> sheetIterator = r.getSheetsData();
if (!sheetIterator.hasNext()) {
return Collections.emptyList();
}
InputStream sheetInputStream = sheetIterator.next();
BufferedInputStream bisSheet = new BufferedInputStream(sheetInputStream);
InputSource sheetSource = new InputSource(bisSheet);
parser.parse(sheetSource);
List<String []> res = handler.getRowCache();
bisSheet.close();
return res;
}
public XMLReader fetchSheetParser(ContentHandler handler) throws SAXException {
XMLReader parser = new SAXParser();
parser.setContentHandler(handler);
return parser;
}
/**
* See org.xml.sax.helpers.DefaultHandler javadocs
*/
private static class SheetHandler extends DefaultHandler {
private static final String ROW_EVENT = "row";
private static final String CELL_EVENT = "c";
private SharedStringsTable sst;
private String lastContents;
private boolean nextIsString;
private List<String> cellCache = new LinkedList<>();
private List<String[]> rowCache = new LinkedList<>();
private SheetHandler(SharedStringsTable sst) {
this.sst = sst;
}
public void startElement(String uri, String localName, String name,
Attributes attributes) throws SAXException {
// c => cell
if (CELL_EVENT.equals(name)) {
String cellType = attributes.getValue("t");
if(cellType != null && cellType.equals("s")) {
nextIsString = true;
} else {
nextIsString = false;
}
} else if (ROW_EVENT.equals(name)) {
if (!cellCache.isEmpty()) {
rowCache.add(cellCache.toArray(new String[cellCache.size()]));
}
cellCache.clear();
}
// Clear contents cache
lastContents = "";
}
public void endElement(String uri, String localName, String name)
throws SAXException {
// Process the last contents as required.
// Do now, as characters() may be called more than once
if(nextIsString) {
int idx = Integer.parseInt(lastContents);
lastContents = new XSSFRichTextString(sst.getEntryAt(idx)).toString();
nextIsString = false;
}
// v => contents of a cell
// Output after we've seen the string contents
if(name.equals("v")) {
cellCache.add(lastContents);
}
}
public void characters(char[] ch, int start, int length)
throws SAXException {
lastContents += new String(ch, start, length);
}
public List<String[]> getRowCache() {
return rowCache;
}
}
}