我正在用C++实现一个LZW算法。
字典的大小是用户输入的,但最小值是256,因此它应该适用于二进制文件。如果它到达字典的末尾,它会转到索引0,并从那里覆盖它。
例如,如果我放入一个alice in wonderland script,并用512的字典大小压缩它,我得到的是this dictionary。
但我在解压缩和解压缩压缩文件looks like this的输出字典时遇到了问题。
我的解压代码如下所示
struct dictionary
{
vector<unsigned char> entry;
vector<bool> bits;
};
void decompress(dictionary dict[], vector<bool> file, int dictionarySize, int numberOfBits)
{
//in this example
//dictionarySize = 512, tells the max size of the dictionary, and goes back to 0 if it reaches 513
//numberOfBits = log2(512) = 9
//dictionary dict[] contains bits and strings (strings can be empty)
// dict[0] =
// entry = (unsigned char)0
// bits = (if numberOfBits = 9) 000000001
// dict[255] =
// entry = (unsigned char)255
// bits = (if numberOfBits = 9) 011111111
// so the next entry will be dict[next] (next is currently 256)
// dict[256] =
// entry = what gets added in the code below
// bits = 100000000
// all the bits are already set previously (dictionary size is int dictionarySize) so in this case all the bits from 0 to 511 are already set, entries are set from 0 to 255, so extended ASCII
vector<bool> currentCode;
vector<unsigned char> currentString;
vector<unsigned char> temp;
int next=256;
bool found=false;
for(int i=0;i<file.size();i+=numberOfBits)
{
for(int j=0;j<numberOfBits;j++)
{
currentCode.push_back(file[i+j]);
}
for(int j=0;j<dictionarySize;j++)
{
// when the currentCode (size numberOfBits) gets found in the dictionary
if(currentCode==dict[j].bits)
{
currentString = dict[j].entry;
// if the current string isnt empty, then it means it found the characted in the dictionary
if(!currentString.empty())
{
found = true;
}
}
}
//if the currentCode in the dictionary has a string value attached to it
if(found)
{
for(int j=0;j<currentString.size();j++)
{
cout<<currentString[j];
}
temp.push_back(currentString[0]);
// so it doesnt just push 1 character into the dictionary
// example, if first read character is 'r', it is already in the dictionary so it doesnt get added
if(temp.size()>1)
{
// if next is more than 511, writing to that index would cause an error, so it resets back to 0 and goes back up
if(next>dictionarySize-1) //next > 512-1
{
next = 0;
}
dict[next].entry.clear();
dict[next].entry = temp;
next++;
}
//temp = currentString;
}
else
{
currentString = temp;
currentString.push_back(temp[0]);
for(int j=0;j<currentString.size();j++)
{
cout<<currentString[j];
}
// if next is more than 511, writing to that index would cause an error, so it resets back to 0 and goes back up
if(next>dictionarySize-1)
{
next = 0;
}
dict[next].entry.clear();
dict[next].entry = currentString;
next++;
//break;
}
temp = currentString;
// currentCode gets cleared, and written into in the next iteration
currentCode.clear();
//cout<<endl;
found = false;
}
}我现在卡住了,不知道在这里修复什么来修复输出。我还注意到,如果我把一个字典放得足够大,所以它不会绕过字典(它不会到达末尾,也不会从0开始),它会起作用。
发布于 2020-05-30 16:55:00
您使用的文件数据量太大,无法调试。从小的字符串开始。我举了一个来自Wikli的很好的例子:
输入:"abacdacacadaad“步输入匹配输出new_entry new_index a 0 b 1 c 2D 3 1 abacdacacadaad a 0 ab 4 2 bacdacacadaad b 1 ba 5 3 acdacacadaad a 0 ac 6 4 cdacacadaad c 2 cd 7 5 dacacadaad d 3 da 8 6 acacadaadac 6 aca 9 7 acadaad aca 9 acad 10 8 daad da 8 daa 11 9 ad a 0 ad 12 10 d d 3输出:"0102369803“
因此您可以通过交叉匹配输入/输出和字典内容来逐步调试代码。一旦正确完成,您就可以对解码执行相同的操作:
输入:"0102369803“阶跃输入输出new_entry new_index a 0 b 1 c 2 d 3 1 0 a 2 1 b ab4 3 0 a ba 5 4 2 c ac 6 5 3 d cd 7 6 6 ac da 8 7 9 aca 9 8 8 da acad 10 9 0 adaa 11 10 3 d ad 12输出:"abacdacacadaad“
然后才能移动到文件并清除字典handling.
一旦你在小字母表上成功地完成了LZW,你可以尝试使用完整的字母表和位编码。您知道,LZW流可以以任何位长度(而不仅仅是8/16/32/64位)进行编码,这会极大地影响压缩比(就所使用的数据属性而言)。因此,我会尝试以变量(或预定义的位长)对数据进行通用访问。
有点好奇,所以我编写了一个简单的C++/VCL示例来进行压缩:
//---------------------------------------------------------------------------
// LZW
const int LZW_bits=12; // encoded bitstream size
const int LZW_size=1<<LZW_bits; // dictinary size
// bitstream R/W
DWORD bitstream_tmp=0;
//---------------------------------------------------------------------------
// return LZW_bits from dat[adr,bit] and increment position (adr,bit)
DWORD bitstream_read(BYTE *dat,int siz,int &adr,int &bit,int bits)
{
DWORD a=0,m=(1<<bits)-1;
// save tmp if enough bits
if (bit>=bits){ a=(bitstream_tmp>>(bit-bits))&m; bit-=bits; return a; }
for (;;)
{
// insert byte
bitstream_tmp<<=8;
bitstream_tmp&=0xFFFFFF00;
bitstream_tmp|=dat[adr]&255;
adr++; bit+=8;
// save tmp if enough bits
if (bit>=bits){ a=(bitstream_tmp>>(bit-bits))&m; bit-=bits; return a; }
// end of data
if (adr>=siz) return 0;
}
}
//---------------------------------------------------------------------------
// write LZW_bits from a to dat[adr,bit] and increment position (adr,bit)
// return true if buffer is full
bool bitstream_write(BYTE *dat,int siz,int &adr,int &bit,int bits,DWORD a)
{
a<<=32-bits; // align to MSB
// save tmp if aligned
if ((adr<siz)&&(bit==32)){ dat[adr]=(bitstream_tmp>>24)&255; adr++; bit-=8; }
if ((adr<siz)&&(bit==24)){ dat[adr]=(bitstream_tmp>>16)&255; adr++; bit-=8; }
if ((adr<siz)&&(bit==16)){ dat[adr]=(bitstream_tmp>> 8)&255; adr++; bit-=8; }
if ((adr<siz)&&(bit== 8)){ dat[adr]=(bitstream_tmp )&255; adr++; bit-=8; }
// process all bits of a
for (;bits;bits--)
{
// insert bit
bitstream_tmp<<=1;
bitstream_tmp&=0xFFFFFFFE;
bitstream_tmp|=(a>>31)&1;
a<<=1; bit++;
// save tmp if aligned
if ((adr<siz)&&(bit==32)){ dat[adr]=(bitstream_tmp>>24)&255; adr++; bit-=8; }
if ((adr<siz)&&(bit==24)){ dat[adr]=(bitstream_tmp>>16)&255; adr++; bit-=8; }
if ((adr<siz)&&(bit==16)){ dat[adr]=(bitstream_tmp>> 8)&255; adr++; bit-=8; }
if ((adr<siz)&&(bit== 8)){ dat[adr]=(bitstream_tmp )&255; adr++; bit-=8; }
}
return (adr>=siz);
}
//---------------------------------------------------------------------------
bool str_compare(char *s0,int l0,char *s1,int l1)
{
if (l1<l0) return false;
for (;l0;l0--,s0++,s1++)
if (*s0!=*s1) return false;
return true;
}
//---------------------------------------------------------------------------
AnsiString LZW_encode(AnsiString raw)
{
AnsiString lzw="";
int i,j,k,l;
int adr,bit;
DWORD a;
const int siz=32; // bitstream buffer
BYTE buf[siz];
AnsiString dict[LZW_size]; // dictionary
int dicts=0; // actual size of dictionary
// init dictionary
for (dicts=0;dicts<256;dicts++) dict[dicts]=char(dicts); // full 8bit binary alphabet
// for (dicts=0;dicts<4;dicts++) dict[dicts]=char('a'+dicts); // test alphabet "a,b,c,d"
l=raw.Length();
adr=0; bit=0;
for (i=0;i<l;)
{
i&=i;
// find match in dictionary
for (j=dicts-1;j>=0;j--)
if (str_compare(dict[j].c_str(),dict[j].Length(),raw.c_str()+i,l-i))
{
i+=dict[j].Length();
if (i<l) // add new entry in dictionary (if not end of input)
{
// clear dictionary if full
if (dicts>=LZW_size) dicts=256; // full 8bit binary alphabet
// if (dicts>=LZW_size) dicts=4; // test alphabet "a,b,c,d"
else{
dict[dicts]=dict[j]+AnsiString(raw[i+1]); // AnsiString index starts from 1 hence the +1
dicts++;
}
}
a=j; j=-1; break; // full binary output
// a='0'+j; j=-1; break; // test ASCII output
}
// store result to bitstream
if (bitstream_write(buf,siz,adr,bit,LZW_bits,a))
{
// append buf to lzw
k=lzw.Length();
lzw.SetLength(k+adr);
for (j=0;j<adr;j++) lzw[j+k+1]=buf[j];
// reset buf
adr=0;
}
}
if (bit)
{
// store the remainding bits with zeropad
bitstream_write(buf,siz,adr,bit,LZW_bits-bit,0);
}
if (adr)
{
// append buf to lzw
k=lzw.Length();
lzw.SetLength(k+adr);
for (j=0;j<adr;j++) lzw[j+k+1]=buf[j];
}
return lzw;
}
//---------------------------------------------------------------------------
AnsiString LZW_decode(AnsiString lzw)
{
AnsiString raw="";
int adr,bit,siz,ix;
DWORD a;
AnsiString dict[LZW_size]; // dictionary
int dicts=0; // actual size of dictionary
// init dictionary
for (dicts=0;dicts<256;dicts++) dict[dicts]=char(dicts); // full 8bit binary alphabet
// for (dicts=0;dicts<4;dicts++) dict[dicts]=char('a'+dicts); // test alphabet "a,b,c,d"
siz=lzw.Length();
adr=0; bit=0; ix=-1;
for (adr=0;(adr<siz)||(bit>=LZW_bits);)
{
a=bitstream_read(lzw.c_str(),siz,adr,bit,LZW_bits);
// a-='0'; // test ASCII input
// clear dictionary if full
if (dicts>=LZW_size){ dicts=4; ix=-1; }
// new dictionary entry
if (ix>=0)
{
if (a>=dicts){ dict[dicts]=dict[ix]+AnsiString(dict[ix][1]); dicts++; }
else { dict[dicts]=dict[ix]+AnsiString(dict[a ][1]); dicts++; }
} ix=a;
// update decoded output
raw+=dict[a];
}
return raw;
}
//---------------------------------------------------------------------------并使用// test ASCII input行输出:
txt="abacdacacadaad"
enc="0102369803"
dec="abacdacacadaad"其中AnsiString是我使用的唯一的VCL东西,它只是自分配字符串变量,注意它的索引从1开始。
AnsiString s;
s[5] // character access (1 is first character)
s.Length() // returns size
s.c_str() // returns char*
s.SetLength(size) // resize所以只要用你找到的任何字符串...
如果您没有使用BYTE,DWORD,请使用unsigned char和unsigned int ...
看起来它也适用于长文本(大于字典和/或位流缓冲区大小)。但是,要注意,清除可能会在几个不同的代码位置完成,但必须在编码器/解码器中同步,否则在清除数据后会损坏数据。
该示例可以只使用"a,b,c,d"字母表,也可以使用完整的8it字母表。当前设置为8位。如果您想要更改它,只需取消// test ASCII input行并删除代码中的// full 8bit binary alphabet行即可。
要测试交叉缓冲区和边界,您可以使用:
const int LZW_bits=12; // encoded bitstream size
const int LZW_size=1<<LZW_bits; // dictinary size此外,还包括:
const int siz=32; // bitstream buffer常量...这也会影响性能,因此可以根据自己的喜好进行调整。当心bitstream_write没有优化,可能会有相当大的速度……
另外,为了调试4位对齐编码,我使用十六进制打印的编码数据(十六进制字符串是其ASCII版本的两倍),如下所示(忽略VCL内容):
AnsiString txt="abacdacacadaadddddddaaaaaaaabcccddaaaaaaaaa",enc,dec,hex;
enc=LZW_encode(txt);
dec=LZW_decode(enc);
// convert to hex
hex=""; for (int i=1,l=enc.Length();i<=l;i++) hex+=AnsiString().sprintf("%02X",enc[i]);
mm_log->Lines->Add("\""+txt+"\"");
mm_log->Lines->Add("\""+hex+"\"");
mm_log->Lines->Add("\""+dec+"\"");
mm_log->Lines->Add(AnsiString().sprintf("ratio: %i%",(100*enc.Length()/dec.Length())));和结果:
"abacdacacadaadddddddaaaaaaaabcccddaaaaaaaaa"
"06106206106306410210510406106410FFFFFF910A10706110FFFFFFD10E06206311110910FFFFFFE11410FFFFFFD0"
"abacdacacadaadddddddaaaaaaaabcccddaaaaaaaaa"
ratio: 81%https://stackoverflow.com/questions/62086402
复制相似问题