How to remove particular attributes from arff file and produce modified arff? - feature-extraction

(not manually) i have 96 features and want to remove some 20 features from arff and produce modified arff. used weka for feature selection now want to remove those less imp features. can anyone suggest code for this

Here you go... just change the source and destination file path...
import java.io.File;
import weka.core.Instances;
import weka.core.converters.ArffLoader;
import weka.core.converters.ArffSaver;
import weka.filters.Filter;
import weka.filters.unsupervised.attribute.Remove;
public class Convert4 {
public static void main(String[] args) {
// TODO Auto-generated method stub
try
{
ArffLoader loader2= new ArffLoader();
loader2.setSource(new File("C:/Users/RAHUL/Desktop/stack.arff"));
Instances data2= loader2.getDataSet();
//Load Arff
String[] options = new String[2];
options[0] = "-R"; // "range"
options[1] = "1"; // first attribute
Remove remove = new Remove(); // new instance of filter
remove.setOptions(options); // set options
remove.setInputFormat(data2); // inform filter about dataset **AFTER** setting options
Instances newData2 = Filter.useFilter(data2, remove); // apply filter
ArffSaver saver = new ArffSaver();
saver.setInstances(newData2);
saver.setFile(new File("C:/Users/RAHUL/Desktop/stack2.arff"));
saver.writeBatch();
}
catch (Exception e)
{}
}
}
Cheers :)

Short answer is here for more, check this out https://stackoverflow.com/a/43972890/7588668
BufferedReader datafile = new BufferedReader(new FileReader("bbcsport.arff"));
BufferedReader attrfile = new BufferedReader(new FileReader("attributes.txt"));
Instances data = new Instances(datafile);
List<Integer> myList = new ArrayList<Integer>();
String line;
while ((line = attrfile.readLine()) != null) {
for (n = 0; n < data.numAttributes(); n++) {
if (data.attribute(n).name().equalsIgnoreCase(line)) {
if(!myList.contains(n))
myList.add(n);
}
}
}
int[] attrs = myList.stream().mapToInt(i -> i).toArray();
Remove remove = new Remove();
remove.setAttributeIndicesArray(attrs);
remove.setInvertSelection(false);
remove.setInputFormat(data); // init filter
Instances filtered = Filter.useFilter(data, remove);

Related

Combining forms while retaining form fonts in itext7

I am trying to fill and combine multiple forms without flattening(need to keep them interactive for users). However I notice a problem. I have PDF files that contain the forms I am trying to fill. The form fields have their fonts set in adobe PDF. I notice after I combine the forms the fields lose their original fonts. Here is my program.
using iText.Forms;
using iText.Kernel.Pdf;
using System;
using System.Collections.Generic;
using System.IO;
using System.Runtime.CompilerServices;
using System.Threading.Tasks;
namespace PdfCombineTest
{
class Program
{
static void Main(string[] args)
{
Stream file1;
Stream file2;
using (var stream = new FileStream("./pdf-form-1.pdf", FileMode.Open, FileAccess.Read))
{
file1 = Program.Fill(stream, new[] { KeyValuePair.Create("Text1", "TESTING"), KeyValuePair.Create("CheckBox1", "Yes") });
}
using (var stream = new FileStream("./pdf-form-2.pdf", FileMode.Open, FileAccess.Read))
{
file2 = Program.Fill(stream, new[] { KeyValuePair.Create("Text2", "text 2 text") });
}
using (Stream output = Program.Combine(new[] { file1, file2 }))
{
using (var fileStream = File.Create("./output.pdf"))
{
output.CopyTo(fileStream);
}
}
}
public static Stream Combine(params Stream[] streams)
{
MemoryStream copyStream = new MemoryStream();
PdfWriter writer = new PdfWriter(copyStream);
writer.SetSmartMode(true);
writer.SetCloseStream(false);
PdfPageFormCopier formCopier = new PdfPageFormCopier();
using (PdfDocument combined = new PdfDocument(writer))
{
combined.InitializeOutlines();
foreach (var stream in streams)
{
using (PdfDocument document = new PdfDocument(new PdfReader(stream)))
{
document.CopyPagesTo(1, document.GetNumberOfPages(), combined, formCopier);
}
}
}
copyStream.Seek(0, SeekOrigin.Begin);
return copyStream;
}
public static Stream Fill(Stream inputStream, IEnumerable<KeyValuePair<string, string>> keyValuePairs)
{
MemoryStream outputStream = new MemoryStream();
PdfWriter writer = new PdfWriter(outputStream);
writer.SetCloseStream(false);
using (PdfDocument document = new PdfDocument(new PdfReader(inputStream), writer))
{
PdfAcroForm acroForm = PdfAcroForm.GetAcroForm(document, true);
acroForm.SetGenerateAppearance(true);
IDictionary<string, iText.Forms.Fields.PdfFormField> fields = acroForm.GetFormFields();
foreach (var kvp in keyValuePairs)
{
fields[kvp.Key].SetValue(kvp.Value);
}
}
outputStream.Seek(0, SeekOrigin.Begin);
return outputStream;
}
}
}
I've noticed after several hours of debugging that PdfPageFormCopier excludes the default resources which contain fonts when merging form fields, is there a way around this? The project I'm working on currently does this process in ItextSharp and it works as intended. However we are looking to migrate to iText7.
Here are links to some sample pdf's I made I can't upload the actual pdf's I'm working with but these display the same problem.
https://www.dropbox.com/s/pukt91d4xe8gmmo/pdf-form-1.pdf?dl=0
https://www.dropbox.com/s/c52x6bc99gnrvo6/pdf-form-2.pdf?dl=0
So my solution was to modify the PdfPageFormCopier class from iText. The main issue is in the function below.
public virtual void Copy(PdfPage fromPage, PdfPage toPage) {
if (documentFrom != fromPage.GetDocument()) {
documentFrom = fromPage.GetDocument();
formFrom = PdfAcroForm.GetAcroForm(documentFrom, false);
}
if (documentTo != toPage.GetDocument()) {
documentTo = toPage.GetDocument();
formTo = PdfAcroForm.GetAcroForm(documentTo, true);
}
if (formFrom == null) {
return;
}
//duplicate AcroForm dictionary
IList<PdfName> excludedKeys = new List<PdfName>();
excludedKeys.Add(PdfName.Fields);
excludedKeys.Add(PdfName.DR);
PdfDictionary dict = formFrom.GetPdfObject().CopyTo(documentTo, excludedKeys, false);
formTo.GetPdfObject().MergeDifferent(dict);
IDictionary<String, PdfFormField> fieldsFrom = formFrom.GetFormFields();
if (fieldsFrom.Count <= 0) {
return;
}
IDictionary<String, PdfFormField> fieldsTo = formTo.GetFormFields();
IList<PdfAnnotation> annots = toPage.GetAnnotations();
foreach (PdfAnnotation annot in annots) {
if (!annot.GetSubtype().Equals(PdfName.Widget)) {
continue;
}
CopyField(toPage, fieldsFrom, fieldsTo, annot);
}
}
Specifically the line here.
excludedKeys.Add(PdfName.DR);
If you walk the the code in the CopyField() function eventually you will end in the PdfFormField class. You can see the constructor below.
public PdfFormField(PdfDictionary pdfObject)
: base(pdfObject) {
EnsureObjectIsAddedToDocument(pdfObject);
SetForbidRelease();
RetrieveStyles();
}
The function RetrieveStyles() will try to set the font for the field based on the default appearance. However that will not work. Due to the function below.
private PdfFont ResolveFontName(String fontName) {
PdfDictionary defaultResources = (PdfDictionary)GetAcroFormObject(PdfName.DR, PdfObject.DICTIONARY);
PdfDictionary defaultFontDic = defaultResources != null ? defaultResources.GetAsDictionary(PdfName.Font) :
null;
if (fontName != null && defaultFontDic != null) {
PdfDictionary daFontDict = defaultFontDic.GetAsDictionary(new PdfName(fontName));
if (daFontDict != null) {
return GetDocument().GetFont(daFontDict);
}
}
return null;
}
You see it is trying to see if the font exists in the default resources which was explicitly excluded in the PdfPageFormCopier class. It will never find the font.
So my solution was to create my own class that implements the IPdfPageExtraCopier interface. I copied the code from the PdfPageFormCopier class and removed the one line excluding the default resources. Then I use my own copier class in my code. Not the prettiest solution but it works.

Can't get my String switch statement to hit anything but default

I am trying to use a switch statement to pass a LinkedHashMap to the correct class constructor for a school project(I just added the rest of the code).
The code reads takes in a txt file and based off the first word in the text sends the hash map.
I can't seem to get a hit on the case report I am testing.
I have even tried just making everything into an if-else-if structure,
and that still didn't work out,
I've tried using a private enum method to no avail.
I am at a loss here.
I am running Java 8.
I am open to any suggestion on optimizing the code as well.
Thanks.
package linkedlist;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.io.PrintWriter;
import java.io.UnsupportedEncodingException;
import java.util.LinkedHashMap;
import java.util.Map;
import java.util.logging.Level;
import java.util.logging.Logger;
import javax.swing.JButton;
import javax.swing.JFileChooser;
import javax.swing.JLabel;
/**
*
* #author admin
*/
public class TextReaderGUI extends javax.swing.JFrame {
JFileChooser fileChooser = new JFileChooser();
String rawText;
String[] text;
public String listType;
private JButton fileChooserButton;
private JLabel statusLabel;
/**
* Creates new form TextReaderGUI
*/
public TextReaderGUI() {
initComponents();
}
/**
* This method is called from within the constructor to initialize the form.
* WARNING: Do NOT modify this code. The content of this method is always
* regenerated by the Form Editor.
*/
#SuppressWarnings("unchecked")
// <editor-fold defaultstate="collapsed" desc="Generated Code">
private void initComponents() {
fileChooserButton = new javax.swing.JButton();
statusLabel = new javax.swing.JLabel();
setDefaultCloseOperation(javax.swing.WindowConstants.EXIT_ON_CLOSE);
fileChooserButton.setText("File Chooser");
fileChooserButton.addActionListener(new java.awt.event.ActionListener() {
public void actionPerformed(java.awt.event.ActionEvent evt) {
fileChooserButtonActionPerformed(evt);
}
});
statusLabel.setText("Status: ");
javax.swing.GroupLayout layout = new javax.swing.GroupLayout(getContentPane());
getContentPane().setLayout(layout);
layout.setHorizontalGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING).addGroup(layout
.createSequentialGroup()
.addGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING)
.addGroup(layout.createSequentialGroup().addGap(14, 14, 14).addComponent(fileChooserButton))
.addGroup(layout.createSequentialGroup().addGap(36, 36, 36).addComponent(statusLabel)))
.addContainerGap(264, Short.MAX_VALUE)));
layout.setVerticalGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING)
.addGroup(layout.createSequentialGroup().addGap(16, 16, 16).addComponent(fileChooserButton)
.addGap(18, 18, 18).addComponent(statusLabel).addContainerGap(221, Short.MAX_VALUE)));
pack();
}// </editor-fold>
private void fileChooserButtonActionPerformed(java.awt.event.ActionEvent evt) {
// TODO add your handling code here:
try {
int returnVal = fileChooser.showOpenDialog(this);
if (returnVal == JFileChooser.APPROVE_OPTION) {
File file = fileChooser.getSelectedFile();
rawText = "";
BufferedReader reader = new BufferedReader(new FileReader(file));
StringBuilder stringb = new StringBuilder();
String s;
while ((s = reader.readLine()) != null) {
stringb.append(s);
stringb.append("\n"); // this makes sure that java sees when a new line has started
}
rawText = stringb.toString();
statusLabel.setText("Status: " + file.getName());
}
} catch (IOException e) {
statusLabel.setText("Status" + e);
}
text = rawText.split("\n"); // creating a string array split at each line break
Map<String, String> lines = new LinkedHashMap<>();
for (int i = 0; i < text.length; i++) { // this sets the first word of the line = key
String[] currentLine = text[i].split("\\s+"); // splits the words in the current line to an array
if (i == 0) {
listType = currentLine[0].replaceAll("\n", "").replaceAll("\\s+", ""); // determines listType to pass
}
if (currentLine.length > 1 && i > 0) {
lines.put(currentLine[0] + " " + i, currentLine[1]); // if two words exist on a line
// the first is the key second is the value
} else if (currentLine.length == 1 && i > 0) { // keeps list type out of key values
lines.put(currentLine[0] + " " + i, ""); // " " + i is used to ensure that each command is unique key
}
}
lines.keySet().forEach((name) -> {// Testing to see if document was correctly placed into the HashMap
String key = name;
String value = lines.get(name);
System.out.println(key + " " + value + "\n");
});
System.out.println(listType); // testing to see if list type was correctly stored
switch (listType) {
case "stack":
Stack stack = new Stack((LinkedHashMap) lines);
break;
case "queue":
Queue queue = new Queue((LinkedHashMap) lines);
break;
case "dll":
Dll dll = new Dll((LinkedHashMap) lines);
break;
case "sll":
System.out.println("almost there");
Sll sll = new Sll((LinkedHashMap) lines);
break;
case "cll":
Cll cll = new Cll((LinkedHashMap) lines);
break;
default:
System.out.println("something went wrong here");
break;
}
}
}

MEF - Two way import and export

I'm using MEF in order to execute plugins code in my project.
1. I'm loading my dll sources :
public void AssembleComponents()
{
try
{
//Creating an instance of aggregate catalog. It aggregates other catalogs
var aggregateCatalog = new AggregateCatalog();
//Build the directory path where the parts will be available
var directoryPath =
string.Concat(Path.GetDirectoryName(Assembly.GetExecutingAssembly().CodeBase)
.Split('\\').Reverse().Skip(4).Reverse().Aggregate((a, b) => a + "\\" + b)
, "\\", "ExportComponents\\Components");
string localPath = new Uri(directoryPath).LocalPath;
//Load parts from the available dlls in the specified path using the directory catalog
var directoryCatalog = new DirectoryCatalog(localPath, "*.dll");
//Load parts from the current assembly if available
var asmCatalog = new AssemblyCatalog(Assembly.GetExecutingAssembly());
//Add to the aggregate catalog
aggregateCatalog.Catalogs.Add(directoryCatalog);
aggregateCatalog.Catalogs.Add(asmCatalog);
//Crete the composition container
var container = new CompositionContainer(aggregateCatalog);
// Composable parts are created here i.e. the Import and Export components assembles here
container.ComposeParts(this);
}
catch (Exception ex)
{
throw ex;
}
}
I'm going through my plugins and executing a "Validate" method :
public List<string> Validate(string operationType)
{
List<string> res = null;
foreach (System.Lazy<IValidationRules, IPluginMetadata> plugin in ChekcsPlugins)
{
if (plugin.Metadata.DisplayName == operationType)
{
res = plugin.Value.Validate();
break;
}
}
return res;
}
I'm know how to export back a returned value once the "Validate" is done but what i need is to return values at run time back during the method execution.
Is it possible?

Pulling this custom readDataFile function into Eclipse to print .dat file data to console

Goal: Get the data from a .dat file and print it to the console in Eclipse
Resources: fpfret.java and PointF.java and dichromatic.dat
I have resolved all my issues and have just a few console errors, here's my code and my question is: How do I add the getCodeBase() method?
package frp3;
import java.io.BufferedInputStream;
import java.io.DataInputStream;
import java.io.EOFException;
import java.net.URL;
import java.util.Vector;
public class FileRead {
public static void main(String[] args) { //getDocumentBase
System.out.println(readDataFile(getCodeBase() + "dichromatic.dat", 300, 750));
}
private static String getCodeBase() {
// TODO Auto-generated method stub
return null;
}
#SuppressWarnings("unchecked")
private static PointF[] readDataFile(String filename, int min, int max) {
#SuppressWarnings("rawtypes")
Vector v = new Vector();
try {
DataInputStream dis = new DataInputStream(new BufferedInputStream((new URL(filename)).openStream()));
float f0, f1;
while (true) {
try {
f0 = dis.readFloat();
f1 = dis.readFloat();
if (min < 0 || max < 0 || (f0 >= min && f0 <= max)) {
v.addElement(new PointF(f0, f1));
}
}
catch (EOFException eof) {
break;
}
}
}
catch (Exception e) {
e.printStackTrace();
}
PointF[] array = new PointF[v.size()];
for (int i = 0; i < v.size(); i++) {
array[i] = (PointF) v.elementAt(i);
}
return array;
}
}
Here's my console errors:
java.net.MalformedURLException: no protocol: nulldichromatic.dat
at java.net.URL.<init>(Unknown Source)
at java.net.URL.<init>(Unknown Source)
at java.net.URL.<init>(Unknown Source)
at frp3.FileRead.readDataFile(FileRead.java:27)
at frp3.FileRead.main(FileRead.java:12)
[Lfrp3.PointF;#29be513c
Here's my Project View in Eclipse:
Alright. This is actually more complex then I thought at first pass. Basically, readDataFile expects the dichromatic.dat file to be a resource available on the Internet. Look at the following line from readDataFile:
DataInputStream dis = new DataInputStream(new BufferedInputStream((new URL(filename)).openStream()));
Basically, whatever filename gets passed in, is used as a URL. For your use-case, where your file is hosted on your local filesystem, I recommend a few changes.
First, replace the above DataInputStream declaration line with:
DataInputStream dis = new DataInputStream(new BufferedInputStream(new FileInputStream(filename)));
Second, replace getCodeBase with:
private static String getCodeBase() {
return "";
}
I've simply replace null with an empty string. Since "dichromatic.dat" is in the root of your project, it should be sufficient to use an empty string, indicating project root, as the result for getCodeBase(), as the result of that function gets pre-pended to "dichromatic.dat" before being passed to readDataFile as filename.
If you put dichromatic.dat in a different place, just modify that empty string to be the "path" that leads to the file.
Hope this helps.
Forgot to mention -- be sure to update your imports list to include import java.io.FileInputStream -- although Eclipse should handle this gracefully for you.

Copying rich text and images from one document to MIME in another document

I have a solution for copying rich text content from one document to MIME in another document. See http://per.lausten.dk/blog/2012/12/xpages-dynamically-updating-rich-text-content-in-a-ckeditor.html. I use this in an application as a way for the user to insert content templates in a new document and have the content appear on-the-fly in the CKEditor.
The problem is that inline images are not included in the copying - only a reference to temporary storage of the images. This means that the images are only visible for the current user in the current session. So not very useful.
How can I include images?
Update October 4, 2013:
I'm still looking for a solution to this.
I finally got it work. It was much more simple and did not even involve MIME. The trick was to modify the image tags in the working HTML to include the base64 encoded image so that the src tag could use this format (here shown with a gif as example):
src="data:image/gif;base64,<base64 encoded image>"
I already had the code necessary to get the HTML from the rich text field (see my blog post already mentioned in my question). So all I needed was to replace the image src tags with the correct src format including the base64 encoded image.
The following code gets the HTML and goes through each of the included images and modifies the src tag:
String html = this.document.getValue(fieldName).toString();
if (null != html) {
final List<FileRowData> fileRowDataList = document.getEmbeddedImagesList(fieldName);
if (null != fileRowDataList) {
final Matcher matcher = imgRegExp.matcher(html);
while (matcher.find()) {
String src = matcher.group();
final String srcToken = "src=\"";
final int x = src.indexOf(srcToken);
final int y = src.indexOf("\"", x + srcToken.length());
final String srcText = src.substring(x + srcToken.length(), y);
for (FileRowData fileRowData : fileRowDataList) {
final String srcImage = fileRowData.getHref();
final String cidImage = ((AttachmentValueHolder) fileRowData).getCID();
final String typeImage = ((AttachmentValueHolder) fileRowData).getType();
final String persistentName = ((AttachmentValueHolder) fileRowData).getPersistentName();
// Add base 64 image inline (src="data:image/gif;base64,<name>")
if (srcText.endsWith(srcImage)) {
final String newSrc = src.replace(srcText, "data:" + typeImage + ";base64," + getBase64(persistentName));
html = html.replace(src, newSrc);
}
}
}
}
}
Here is the getBase64() method that base64 encodes an image:
private String getBase64(final String fileName) {
String returnText = "";
try {
BASE64Encoder base64Enc = new BASE64Encoder();
ByteArrayOutputStream output = new ByteArrayOutputStream();
base64Enc.encode(this.getEmbeddedImageStream(fileName), output);
returnText = output.toString();
} catch (NotesException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return returnText;
}
Some of the code is from the emailBean by Tony McGuckin.
Can you get a handle to the inline image by the DominoDocument.AttachmentValueHolder, see http://public.dhe.ibm.com/software/dw/lotus/Domino-Designer/JavaDocs/XPagesExtAPI/8.5.2/com/ibm/xsp/model/domino/wrapped/DominoDocument.AttachmentValueHolder.html
I blogged about attachments inside notes documents, see http://www.domino-weblog.nl/weblogs/Domino_Blog.nsf/dx/xpages-tip-get-easily-access-to-your-attachments-in-java.htm
Gruesome hack (you need to sort out authentication and server names)
The SSJS (getting the source from a view)
var unid = curRow.getUniversalID();
var body = getComponent("body1");
var magic = new demo.HTMLMagic();
magic.doMagic(database, unid, body);
The Java
package demo;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.List;
import org.apache.http.HttpHost;
import org.apache.http.HttpResponse;
import org.apache.http.HttpVersion;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.conn.ClientConnectionManager;
import org.apache.http.conn.scheme.PlainSocketFactory;
import org.apache.http.conn.scheme.Scheme;
import org.apache.http.conn.scheme.SchemeRegistry;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.impl.conn.tsccm.ThreadSafeClientConnManager;
import org.apache.http.params.BasicHttpParams;
import org.apache.http.params.HttpParams;
import org.apache.http.params.HttpProtocolParams;
import net.htmlparser.jericho.Attribute;
import net.htmlparser.jericho.Attributes;
import net.htmlparser.jericho.HTMLElementName;
import net.htmlparser.jericho.OutputDocument;
import net.htmlparser.jericho.Source;
import net.htmlparser.jericho.StartTag;
import lotus.domino.Database;
import lotus.domino.NotesException;
import com.ibm.misc.BASE64Encoder;
import com.ibm.xsp.component.xp.XspInputRichText;
import com.ibm.xsp.http.IMimeMultipart;
import com.ibm.xsp.model.domino.wrapped.DominoRichTextItem;
public class HTMLMagic {
private HttpClient httpClient = null;
private HttpHost httpHost = null;
//TODO: that needs to be resolved smarter
private static final String HOSTNAME = "localhost";
public void doMagic(final Database database, final String unid, final XspInputRichText body) throws NotesException,
ClientProtocolException, IOException {
final String docURL = "http://" + HOSTNAME + "/__" + database.getReplicaID() + ".nsf/0/" + unid + "/Body?OpenField";
final String fixedHTML = this.fixHTML(docURL);
IMimeMultipart result = DominoRichTextItem.convertToMime("-- copied text--<br />" + fixedHTML);
body.setValue(result);
}
private String fixHTML(final String rawHTMLstring) throws ClientProtocolException, IOException {
HttpHost target = this.getHttpHost();
HttpClient client = this.getHttpClient();
HttpGet get = new HttpGet(rawHTMLstring);
HttpResponse response = client.execute(target, get);
InputStream data = response.getEntity().getContent();
Source rawHTML = new Source(data);
OutputDocument outputDocument = new OutputDocument(rawHTML);
StringBuilder sb = new StringBuilder();
String tagName = HTMLElementName.IMG;
String attName = "src";
List<StartTag> links = rawHTML.getAllStartTags(tagName);
for (StartTag onelink : links) {
String href = onelink.getAttributeValue(attName);
if (href != null) {
String replace = this.urltoData(href);
if (replace != null) {
sb.setLength(0);
sb.append("<");
sb.append(tagName);
sb.append(" ");
sb.append(attName);
sb.append("=\"");
sb.append(replace);
sb.append("\"");
Attributes atts = onelink.getAttributes();
if (!atts.isEmpty()) {
for (int i = 0; i < atts.size(); i++) {
Attribute att = atts.get(i);
if (!att.getName().equals(attName)) {
sb.append(" ");
sb.append(att.getName());
sb.append("=\"");
sb.append(att.getValue());
sb.append("\" ");
}
}
}
sb.append(">");
outputDocument.replace(onelink, sb.toString());
}
}
}
return outputDocument.toString();
}
private HttpClient getHttpClient() {
if (this.httpClient == null) {
// general setup
SchemeRegistry supportedSchemes = new SchemeRegistry();
// Register the "http" protocol scheme, it is required
// by the default operator to look up socket factories.
supportedSchemes.register(new Scheme("http", PlainSocketFactory.getSocketFactory(), 80));
// prepare parameters
HttpParams params = new BasicHttpParams();
HttpProtocolParams.setVersion(params, HttpVersion.HTTP_1_1);
HttpProtocolParams.setContentCharset(params, "UTF-8");
HttpProtocolParams.setUseExpectContinue(params, true);
ClientConnectionManager connMgr = new ThreadSafeClientConnManager(params, supportedSchemes);
this.httpClient = new DefaultHttpClient(connMgr, params);
}
return this.httpClient;
}
private HttpHost getHttpHost() {
if (this.httpHost == null) {
this.httpHost = new HttpHost(HOSTNAME, 80, "http");
}
return this.httpHost;
}
private String urltoData(final String href) throws ClientProtocolException, IOException {
StringBuilder sb = new StringBuilder();
sb.append("data:image/");
sb.append(href.substring(href.lastIndexOf("FieldElemFormat=") + 1));
sb.append(";base64,");
// Here go the Image data
HttpHost target = this.getHttpHost();
HttpClient client = this.getHttpClient();
HttpGet get = new HttpGet(href);
HttpResponse response = client.execute(target, get);
InputStream data = response.getEntity().getContent();
BASE64Encoder encoder = new BASE64Encoder();
OutputStream output = new ByteArrayOutputStream();
encoder.encode(data, output);
sb.append(output.toString());
output.close();
return sb.toString();
}
}
Would be curious if that works for you. The Notes client can't show inline HTML images

Resources