提取gz文件中的压缩部分数据,C语言实现

   gz文件是gzip产生的压缩文件。前几天接到一个小任务,说是要将其中被压缩的数据提取出来。于是动手写了个小程序实现之。

   关于gzip文件格式的相关信息,可以查看RFC 1952



代码如下:

#include
#include
#include
#include

int main(int argc,char* argv[])
{
	FILE* sfp=NULL;
	FILE* dfp=NULL;
	int readnum;
	int count=0;	/*for tail cross two bufs*/
	unsigned char uc_magic;
	unsigned char uc_temp;
	int FLG_FEXTRA_SET=0;
	int FLG_FNAME_SET=0;
	int FLG_FCOMMENT_SET=0;
	int FLG_FHCRC_SET=0;
	unsigned int xlen=0;


	unsigned char buf[4096]="";
	unsigned char buf2[4096]="";
	unsigned char result[4096]="";

	if(argc<2)
	{
		printf("usage main your gz file\n");
		return(0);
	}

	sfp=fopen(argv[1],"rb");
	if(sfp==NULL)
	{
		printf("open file error! errmsg:%s\n",strerror(errno));
		return(0);
	}

	dfp=fopen("result","wb+");

	/*check file magic number*/

	uc_magic=fgetc(sfp);

	if(uc_magic!=0x1f)
	{
		printf("error this is not a gz file!\n");
		fclose(sfp);
		fclose(dfp);
		return(0);
	}

	uc_magic=fgetc(sfp);
	if(uc_magic!=0x8b)
	{
		printf("error this is not a gz file!\n");
		fclose(sfp);
		fclose(dfp);
		return(0);
	}

	/*ignore the CM byte*/
	fseek(sfp,1,SEEK_CUR);


	/*read FLG*/
	uc_temp=fgetc(sfp);
	
	if(uc_temp==EOF)
	{
		printf("end of file when read FLG\n");
		fclose(sfp);
		fclose(dfp);
		return(0);
	}


	/*check FLG.FEXTRA*/
	if(uc_temp&0x04)
	{
		FLG_FEXTRA_SET=1;
	}

	/*check FLG.FNAME*/
	if(uc_temp&0x08)
	{
		FLG_FNAME_SET=1;
	}

	/*check FLG.FCOMMENT*/
	if(uc_temp&0x10)
	{
		FLG_FCOMMENT_SET=1;
	}


	/*skip MIME 4 bytes,skip XFL 1 byte, skip OS 1 byte */
	fseek(sfp,6,SEEK_CUR);

	/*FLG.FEXTRA is seted */
	if(FLG_FEXTRA_SET)
	{
		/*skip s1 and s2 read XLEN,and skip XLEN byte*/
		fseek(sfp,2,SEEK_CUR);
		fread(&xlen,2,1,sfp);

		fseek(sfp,xlen,SEEK_CUR);
	}

	/*FLG.FNAME is seted*/
	if(FLG_FNAME_SET)
	{
		/*ignore file name,read until 0 occur*/
		while(fgetc(sfp));
	}

	/*FLG.FCOMMENT is seted*/
	if(FLG_FCOMMENT_SET)
	{
		/*ignore comments,read until 0 occur*/
		while(fgetc(sfp));
	}

	/*FLG.FHCRC is seted*/
	if(FLG_FHCRC_SET)
	{
		fseek(sfp,2,SEEK_CUR);
	}

	/*fread return 0 when content length is not engouh*/
	while((readnum=fread(buf,1,4096,sfp))!=0)
	{
		if(feof(sfp))
		{
			/* EOF cut CRC32 and ISIZE 8 bytes*/
			/*  be care when the tail cross two buf~~~~*/
			if(readnum<8)
			{
				/* tail does cross two buf~~hell!!*/
				memcpy(buf,buf2,count-(8-readnum));
				memcpy(result,buf,count-(8-readnum));
				fwrite(result,count-(8-readnum),1,dfp);
				break;
			}
			else
			{
				if(count!=0)
				{
					memcpy(result,buf2,count);
				
					fwrite(result,count,1,dfp);
				}

				memcpy(result,buf,readnum-8);
				fwrite(result,readnum-8,1,dfp);

				break;
			}

		}
		else
		{
			if(count!=0)
			{
				memcpy(result,buf2,count);
				fwrite(result,count,1,dfp);
				
				memcpy(buf2,buf,readnum);
				count=readnum;
			}
			else
			{
				
				memcpy(buf2,buf,readnum);
				count=readnum;

			}

		}
	}



	fclose(sfp);

	fflush(dfp);
	fclose(dfp);


	return(0);
}


你可能感兴趣的:(提取gz文件中的压缩部分数据,C语言实现)