gpt4 book ai didi

algorithm - LZW 压缩似乎无法正常工作

转载 作者:塔克拉玛干 更新时间:2023-11-03 06:27:07 26 4
gpt4 key购买 nike

我试图让这段代码正常工作,但当我尝试编码时,它似乎无法正常工作。我有一个 60 字节的文本文件。我对其进行编码,输出文件为 100 字节。当我解码该文件时,它变成了 65 字节。它解码正确,但文件大小比原始文件大。我尝试对 jpg 进行编码,但文件大小确实减小了,但是之后我无法打开文件。我试图解码 jpg 文件但它没有用,好像 cmd 已卡住。这是我尝试使用的代码。

import java.util.*;
import java.io.*;

public class LZW {

// Dictionary
public static short DSIZE = 256;
public static int DSIZEINT = 256;

/** Compress a string to a list of output symbols. */
public static List<Short> compress(String uncompressed) {
// Build the dictionary.
short dictSize = DSIZE;
Map<String,Short> dictionary = new HashMap<String,Short>();
for (short i = 0; i < DSIZE; i++)
dictionary.put("" + (char)i, i);

String w = "";
List<Short> result = new ArrayList<Short>();
for (char c : uncompressed.toCharArray()) {
String wc = w + c;
if (dictionary.containsKey(wc))
w = wc;
else {
result.add(dictionary.get(w));
// Add wc to the dictionary.
dictionary.put(wc, dictSize++);
w = "" + c;
}
}

// Output the code for w.
if (!w.equals(""))
result.add(dictionary.get(w));
return result;
}

/** Compress a string to a list of output symbols, supporting larger filesizes. */
public static List<Integer> compressInt(String uncompressed) {
// Build the dictionary.
int dictSize = DSIZEINT;
Map<String,Integer> dictionary = new HashMap<String,Integer>();
for (int i = 0; i < DSIZEINT; i++)
dictionary.put("" + (char)i, i);

String w = "";
List<Integer> result = new ArrayList<Integer>();
for (char c : uncompressed.toCharArray()) {
String wc = w + c;
if (dictionary.containsKey(wc))
w = wc;
else {
result.add(dictionary.get(w));
// Add wc to the dictionary.
dictionary.put(wc, dictSize++);
w = "" + c;
}
}

// Output the code for w.
if (!w.equals(""))
result.add(dictionary.get(w));
return result;
}

/** Decompress a list of output ks to a string. */
public static String decompress(List<Short> compressed) {
// Build the dictionary.
short dictSize = DSIZE;
Map<Short,String> dictionary = new HashMap<Short,String>();
for (short i = 0; i < DSIZE; i++)
dictionary.put(i, "" + (char)i);

String w = "" + (char)(short)compressed.remove(0);
String result = w;
for (short k : compressed) {
String entry;
if (dictionary.containsKey(k))
entry = dictionary.get(k);
else if (k == dictSize)
entry = w + w.charAt(0);
else
throw new IllegalArgumentException("Bad compressed k: " + k);

result += entry;

// Add w+entry[0] to the dictionary.
dictionary.put(dictSize++, w + entry.charAt(0));

w = entry;
}
return result;
}

/** Decompress a list of output ks to a string, supporting larger filesizes. */
public static String decompressInt(List<Integer> compressed) {
// Build the dictionary.
int dictSize = DSIZE;
Map<Integer,String> dictionary = new HashMap<Integer,String>();
for (int i = 0; i < DSIZE; i++)
dictionary.put(i, "" + (char)i);

String w = "" + (char)(int)compressed.remove(0);
String result = w;
for (int k : compressed) {
String entry;
if (dictionary.containsKey(k))
entry = dictionary.get(k);
else if (k == dictSize)
entry = w + w.charAt(0);
else
throw new IllegalArgumentException("Bad compressed k: " + k);

result += entry;

// Add w+entry[0] to the dictionary.
dictionary.put(dictSize++, w + entry.charAt(0));

w = entry;
}
return result;
}

public static void main(String[] args) {

String example = "";
String s = "";
int command = 0;

//Check for correct argument
if(args.length != 1) {
System.out.println("Please enter 1 argument.\nArg1: Command ('encode', 'decode', 'encodeInt', 'decodeInt')\nAnd ensure that you are feeding in an input file and output file using '<' and '>'");
System.exit(1);
}
if(args[0].equals("encode")){
command = 1;
}
else if(args[0].equals("decode")){
command = 2;
}
else if(args[0].equals("encodeInt")){
command = 3;
}
else if(args[0].equals("decodeInt")){
command = 4;
}
else {
System.out.println("Please use either 'encode', 'decode', 'encodeInt', 'decodeInt' as the argument.");
System.exit(1);
}

long start;
long elapsedTime;

//Compress
if(command == 1){

//Read input file
s = BinaryStdIn.readString();

//The actual compression
start = System.nanoTime();
List<Short> compressed = compress(s);
elapsedTime = System.nanoTime() - start;

//System.err.println(compressed);

//first writes the number of ints to write
BinaryStdOut.write(compressed.size());
//writes compression (to file)
Iterator<Short> compressIterator = compressed.iterator();
while (compressIterator.hasNext()){
BinaryStdOut.write(compressIterator.next());
}

System.err.println("LZW Encode time: " + elapsedTime + " ns");

}
//Decompress
else if(command == 2){

//Build Integer List with input
List<Short> compressed = new ArrayList<Short>();
int size = BinaryStdIn.readInt();
while(size > 0){
try{
compressed.add(BinaryStdIn.readShort());
}
catch(RuntimeException e){
System.err.print("*");
}
size--;
}

//System.err.println(compressed);

//The actual decompression
start = System.nanoTime();
String decompressed = decompress(compressed);
elapsedTime = System.nanoTime() - start;

//Print out decompressed data (to file)
System.out.println(decompressed);

System.err.println("LZW Decode time: " + elapsedTime + " ns");

}
//Compress using Integer size
else if(command == 3){

//Read input file
s = BinaryStdIn.readString();

//The actual compression
start = System.nanoTime();
List<Integer> compressed = compressInt(s);
elapsedTime = System.nanoTime() - start;

//System.err.println(compressed);

//first writes the number of ints to write
BinaryStdOut.write(compressed.size());
//writes compression (to file)
Iterator<Integer> compressIterator = compressed.iterator();
while (compressIterator.hasNext()){
BinaryStdOut.write(compressIterator.next());
}

System.err.println("LZW Encode time: " + elapsedTime + " ns");

}
//Decompress using Integer size
else if(command == 4){

//Build Integer List with input
List<Integer> compressed = new ArrayList<Integer>();
int size = BinaryStdIn.readInt();
while(size > 0){
try{
compressed.add(BinaryStdIn.readInt());
}
catch(RuntimeException e){
System.err.print("*");
}
size--;
}

//System.err.println(compressed);

//The actual decompression
start = System.nanoTime();
String decompressed = decompressInt(compressed);
elapsedTime = System.nanoTime() - start;

//Print out decompressed data (to file)
System.out.println(decompressed);

System.err.println("LZW Decode time: " + elapsedTime + " ns");

}

BinaryStdOut.close();


}
}

感谢任何帮助。谢谢。

最佳答案

即使是最好的压缩算法也会偶尔产生比输入大的输出。事实上,找到这样的输入是一个很好的测试用例。 LZW 通过查找重复序列进行压缩,因此没有任何重复序列的输入必然会变大。

我曾经不得不像这样创建一个测试输入。我认为它类似于“ABCD...ACBDEG...”。

编辑:现在我更仔细地查看了代码,我看到您正在将 Shorts 列表写入输出。那几乎肯定是错误的;必要的步骤之一是将每个输出 token 打包成最少的位数,而您完全错过了这一步。

从你的描述来看,代码还有其他问题,但现在一个就够了。

关于algorithm - LZW 压缩似乎无法正常工作,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/23410153/

26 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com