//compressing pdf file
//Writng Compress File
public void PDFCompressFile(string content)
{
//string fileName = "compressed.cmu";
// Create a new file
writeBitByBit bit = new writeBitByBit(CompName); //creating an instance of bit write
//writing tree info
PQueue.cNode top = root;
printHeaderTree(top, bit);
int c;
string code = "0"; //initializing
for (int i = 0; i < content.Length; ++i) //reading char from string containg input
{
Console.WriteLine(content[i]);
if (HuffmanCode.ContainsKey(content[i]))
{
code = HuffmanCode[content[i]]; //reading character's huffman code from th Code table
}
else
{
//if not fount in table do nothing
}
for (int j = 0; j < code.Length; ++j) //reading each character from the Huffman code like if code for A = 011 the first 0 then 1 and then 1
{
if (code[j] == '0')
{
bit.BitWrite(0); //calling writing function with 0
}
else
{
bit.BitWrite(1); //calling writing function with 1
}
}
}
//now we need to write psedu_EOF so that we don't reed extra bytes from the file
code = HuffmanCode[(char)Pseudo_EOF];
for (int i = 0; i < code.Length; ++i) //reading each character from the Huffman code like if code for A = 011 the first 0 then 1 and then 1
{
if (code[i] == '0')
{
bit.BitWrite(0); //calling writing function with 0
}
else
{
bit.BitWrite(1); //calling writing function with 1
}
}
bit.close();
}
//entering values in map inside nodes and arranging those nodes in Priority queue with smallest frequencies in front
public PQueue.PriorityQueue nodesinQueue(Dictionary <char, int> Dic)
{
PQueue.cNode node = new PQueue.cNode(); //node created
PQueue.PriorityQueue pQueue = new PQueue.PriorityQueue(); //queue created
foreach (KeyValuePair <char, int> kvp in Dic) //reading from frequency dictionary
{
node.value = kvp.Key;
node.frequency = kvp.Value; //setting the values of node
pQueue.insertWithPriority(node); //entering the node
node = new PQueue.cNode();
}
return(pQueue);
}
//calculating codes making tree
public PQueue.cNode HuffmanEncoding(PQueue.PriorityQueue pQueue)
{
int n = pQueue.count;
while (n != 1)
{
PQueue.cNode node = new PQueue.cNode();
node.leftZero = pQueue.remove();
node.rightOne = pQueue.remove();
node.frequency = node.leftZero.frequency + node.rightOne.frequency;
node.value = '~'; //just adding a temp value to middle nodes
pQueue.insertWithPriority(node);
n = pQueue.count;
}
return(pQueue.Top());
}
//writing tree
public void printHeaderTree(PQueue.cNode top, writeBitByBit bit)
{
if (top == null)
{
return;
}
if (top.leftZero == null && top.rightOne == null)
{
bit.ByteWrite('1');
bit.ByteWrite(top.value);
}
else
{
bit.ByteWrite('0');
printHeaderTree(top.leftZero, bit);
printHeaderTree(top.rightOne, bit);
}
}
public void printPreorder(PQueue.cNode node)
{
if (node == null)
{
return;
}
/* first print data of node */
if (node.leftZero == null && node.rightOne == null)
{
Console.Write(node.value + " ");
}
/* then recur on left sutree */
printPreorder(node.leftZero);
/* now recur on right subtree */
printPreorder(node.rightOne);
}
public string fileExten; // file extension stoing var
//decompress the file
public void decompress(string fileName, FileStream fs2)
{
readBitByBit bit = new readBitByBit(fileName);
FileTreeroot = ReadTreeHeader(bit);
program.printPreorder(FileTreeroot);
var output = new StreamWriter(fs2);
int returnbit = -1;
char leaf = '1'; //checking if we reached the end of file
// PQueue.cNode top = root;
PQueue.cNode top = FileTreeroot;
while (true) //will run until we found the pseduo_EOF
{
if (top.leftZero == null && top.rightOne == null) //if leaf node is reached
{
leaf = top.value;
if (leaf == (char)program.Pseudo_EOF) //if it is last letter close the file
{
output.Close();
break;
}
else
{
output.Write(leaf); //else write in file
top = FileTreeroot; //again start from root
}
}
returnbit = bit.bitRead();
if (returnbit == 0) //if not leaf keep on reading the file
{
top = top.leftZero;
}
else if (returnbit == 1)
{
top = top.rightOne;
}
}
output.Close();
bit.close();
}
public PQueue.cNode ReadTreeHeader(readBitByBit bit)
{
char c = bit.ByteRead();
PQueue.cNode node = new PQueue.cNode();
if (c == '1')
{
node = new PQueue.cNode();
node.value = bit.ByteRead();
return(node);
}
else
{
PQueue.cNode leftChild = ReadTreeHeader(bit);
PQueue.cNode rightChild = ReadTreeHeader(bit);
node = new PQueue.cNode('0', leftChild, rightChild);
return(node);
}
}
//to calculate code from tree
public void HuffCode(PQueue.cNode root, string str)
{
if (root == null) //base case
{
return;
}
if (root.leftZero == null && root.rightOne == null) //if we reached at leaf node
{
try
{
HuffmanCode.Add(root.value, str); //if it is not already in the Dictionary As i haven't added pseduEOF in Code before it will be added here
}
catch
{
HuffmanCode[root.value] = str; //if it is in the dictionary just edit 2nd value
}
}
else
{
HuffCode(root.leftZero, str + "0"); //concatination to form the code
HuffCode(root.rightOne, str + "1");
}
}
private void Compression_Click(object sender, RoutedEventArgs e)
{
string filename = fileName;
//myObj.comleteFlag = 0;
if (fileExt == ".pdf" || fileExt == ".docx")
{
if (fileExt == ".docx")
{
try
{
// Open a doc file.
Application app = new Application();
Microsoft.Office.Interop.Word.Document document = app.Documents.Open(fileName);
// Select all words from word file
int total = document.Words.Count;
for (int i = 1; i <= total; i++)
{
// Reading from word document into a string
content += document.Words[i].Text;
}
// Close word.
Console.WriteLine(content);
app.Quit();
}
catch
{
MessageBox.Show("File is used by another Process");
throw new ArgumentException("File is used by another Process.");
}
}
if (fileExt == ".pdf")
{
try
{
StringBuilder fileContent = new StringBuilder();
using (PdfReader pdfReader = new PdfReader(filename))
{
for (int k = 1; k <= pdfReader.NumberOfPages; k++)
{
fileContent.Append(PdfTextExtractor.GetTextFromPage(pdfReader, k));
}
}
content = fileContent.ToString();
}
catch
{
MessageBox.Show("File is used by another Process");
throw new ArgumentException("File is used by another Process.");
}
}
//string content;
Dictionary <char, int> Dic = new Dictionary <char, int>();
Dic = myObj.frequencyPDF(content);
// myObj.printMap(Dic);
//getting frequency
//entering data in nodes then storing them in queue
PQueue.PriorityQueue pQueue = new PQueue.PriorityQueue();
pQueue = myObj.nodesinQueue(Dic);
// pQueue.print();
//creating encooding tree
myObj.root = myObj.HuffmanEncoding(pQueue);
PQueue.cNode top = myObj.root; //temporary storing the value
// Console.WriteLine(top.getValue());
myObj.HuffCode(top, "");
// myObj.printCodes(myObj.HuffmanCode);
}
else
{
FileStream fs;
try
{
fs = File.OpenRead(fileName);
}
catch
{
MessageBox.Show("No File has been Uploaded");
throw new ArgumentException("A file should be uploaded.");
}
//String fs = File.ReadAllText(fileName);
Dictionary <char, int> Dic = new Dictionary <char, int>();
//Dic = myObj.frequency(fs);
Dic = myObj.frequency(fs);
// myObj.printMap(Dic);
//getting frequency
//entering data in nodes then storing them in queue
PQueue.PriorityQueue pQueue = new PQueue.PriorityQueue();
pQueue = myObj.nodesinQueue(Dic);
// pQueue.print();
//creating encooding tree
myObj.root = myObj.HuffmanEncoding(pQueue);
PQueue.cNode top = myObj.root; //temporary storing the value
// Console.WriteLine(top.getValue());
myObj.HuffCode(top, "");
// myObj.printCodes(myObj.HuffmanCode);
top = myObj.root; //temporary storing the value
}
MessageBox.Show("Compress Done Save File.");
}
//decompress the file
public void pdfDecompress(string fileName)
{
readBitByBit bit = new readBitByBit(fileName);
FileTreeroot = ReadTreeHeader(bit);
program.printPreorder(FileTreeroot);
int returnbit = -1; //initializing
char leaf = '1'; //checking if we reached the end of file
string content = null; //initializing
PQueue.cNode top = FileTreeroot;
while (true) //will run until we found the pseduo_EOF
{
if (top.leftZero == null && top.rightOne == null) //if leaf node is reached
{
leaf = top.value;
if (leaf == (char)program.Pseudo_EOF) //if it is last letter close the file
{
break;
}
else
{
content = content + leaf.ToString();
}
top = FileTreeroot; //again start from root
}
returnbit = bit.bitRead();
if (returnbit == 0) //if not leaf keep on reading the file
{
top = top.leftZero;
}
else if (returnbit == 1)
{
top = top.rightOne;
}
}
bit.close();
string newC = null;
try
{
newC = content.Substring(3); // in case of empty file
}
catch
{
}
//create pdf
if (fileExten == ".pdf")
{
Document document = new Document(PageSize.A4, 50, 35, 50, 35);
PdfWriter pdfWriter = PdfWriter.GetInstance(document, new FileStream(decmpFile, FileMode.Create));
document.Open();
Paragraph p = new Paragraph();
p.Font = FontFactory.GetFont(FontFactory.TIMES_ROMAN, 12f, BaseColor.BLACK);
p.Add(newC);
document.Add(p);
document.Close();
}
if (fileExten == ".docx")
{
var doc = DocX.Create(decmpFile);
doc.InsertParagraph(newC).Font("Times New Roman").FontSize(12d); //inserting paragraph
doc.Save();
}
}
//Writng Compress File
public void WriteCompressFile(FileStream fs)
{
// Create a new file
writeBitByBit bit = new writeBitByBit(CompName); //creating an instance of bit write
//writing tree info
PQueue.cNode top = root;
printHeaderTree(top, bit);
string code = "0";
if (fileExten1 == ".csv") //code for csv is different because that code cause problem with csv files
{
var sr = new StreamReader(fs); //opeining input file to be compreesed so to read from it and compare and store
int c;
while ((c = sr.Read()) != -1) //reading char from input file
{
if (frequencyMap.ContainsKey((char)c)) //while calculating frequencies we don't calculate 10 which is LF so we use try to avoid exception when 10 comes as it is not present in the HuffmanCode directory
{
code = HuffmanCode[(char)c]; //reading character's huffman code from th Code table
}
for (int i = 0; i < code.Length; ++i) //reading each character from the Huffman code like if code for A = 011 the first 0 then 1 and then 1
{
if (code[i] == '0')
{
bit.BitWrite(0); //calling writing function with 0
}
else
{
bit.BitWrite(1); //calling writing function with 1
}
}
}
}
else //code for .txt and .cpp .c .cs
{
using (var sr1 = new StreamReader(fs))
{
while (!sr1.EndOfStream)
{
string s = sr1.ReadLine();
foreach (char ch in s)
{
if (frequencyMap.ContainsKey(ch))
{
code = HuffmanCode[ch]; //reading character's huffman code from th Code table
}
for (int i = 0; i < code.Length; ++i) //reading each character from the Huffman code like if code for A = 011 the first 0 then 1 and then 1
{
if (code[i] == '0')
{
bit.BitWrite(0); //calling writing function with 0
}
else
{
bit.BitWrite(1); //calling writing function with 1
}
}
}
}
}
}
//now we need to write psedu_EOF so that we don't reed extra bytes from the file
code = HuffmanCode[(char)Pseudo_EOF];
for (int i = 0; i < code.Length; ++i) //reading each character from the Huffman code like if code for A = 011 the first 0 then 1 and then 1
{
if (code[i] == '0')
{
bit.BitWrite(0); //calling writing function with 0
}
else
{
bit.BitWrite(1); //calling writing function with 1
}
}
bit.close();
fs.Close();
}
