C++实现tar包解析

tar(tape archive)是Unix和类Unix系统上文件打包工具，可以将多个文件合并为一个文件，使用tar工具打出来的包称为tar包。一般打包后的文件名后缀为”.tar”，也可以为其它。tar代表未被压缩的tar文件，已被压缩的tar文件则追加压缩文件的扩展名，如经过gzip压缩后的tar文件，扩展名为”.tar.gz”。在windows系统中用WinRAR也可以解压缩打开tar包。tar文件格式已经成为POSIX标准，最初是POSIX.1-1998，目前是POSIX.1-2001.

tar中的数据都是以512字节为单位。tar由两部分组成即头部+内容，其中头部是512字节的头部结构，内容是存放一个文件内容的地方。

tar文件格式的详细介绍可以参考：https://en.wikipedia.org/wiki/Tar_(computing)#File_header

通过执行以下命令生成测试tar包：

tar -cvf test.tar *

test.tar中包含两个文件blog_info.txt和github_info.txt.

其中blog_info.txt文件内容如下：

name: fengbingchun
address: http://blog.csdn.net/fengbingchun?viewmode=contents

github_info.txt文件内容如下：

name: fengbingchun
address: https://github.com/fengbingchun

实现代码tar.hpp:

#ifndef FBC_MESSY_TEST_TAR_HPP_
#define FBC_MESSY_TEST_TAR_HPP_

#include <vector>
#include <string>

/* reference:
	http://www.gnu.org/software/tar/manual/html_node/Standard.html
	http://stackoverflow.com/questions/2505042/how-to-parse-a-tar-file-in-c
	http://directory.fsf.org/wiki/Libtar
	http://work.freenet59.ru/svn/pkgsrc_haiku/trunk/archivers/libarchive/files/contrib/untar.c
	https://codeistry.wordpress.com/2014/08/14/how-to-parse-a-tar-file/
	http://stackoverflow.com/questions/17862383/how-to-know-the-files-inside-the-tar-parser
	https://en.wikipedia.org/wiki/Tar_(computing)
*/

/* tar Header Block, from POSIX 1003.1-1990.  */

/* POSIX header.  */

typedef struct posix_header
{                                     /* byte offset */
	char name[100];               /*   0 */
	char mode[8];                 /* 100 */
	char uid[8];                  /* 108 */
	char gid[8];                  /* 116 */
	char size[12];                /* 124 */
	char mtime[12];               /* 136 */
	char chksum[8];               /* 148 */
	char typeflag;                /* 156 */
	char linkname[100];           /* 157 */
	char magic[6];                /* 257 */
	char version[2];              /* 263 */
	char uname[32];               /* 265 */
	char gname[32];               /* 297 */
	char devmajor[8];             /* 329 */
	char devminor[8];             /* 337 */
	char prefix[155];             /* 345 */
                                      /* 500 */
} tar_posix_header;

/*
	location  size  field
	0         100   File name
	100       8     File mode
	108       8     Owner's numeric user ID
	116       8     Group's numeric user ID
	124       12    File size in bytes
	136       12    Last modification time in numeric Unix time format
	148       8     Checksum for header block
	156       1     Link indicator (file type)
	157       100   Name of linked file
*/

#define TMAGIC   "ustar"        /* ustar and a null */
#define TMAGLEN  6
#define TVERSION "00"           /* 00 and no null */
#define TVERSLEN 2

/* Values used in typeflag field.  */
#define REGTYPE  '0'            /* regular file */
#define AREGTYPE '\0'           /* regular file */
#define LNKTYPE  '1'            /* link */
#define SYMTYPE  '2'            /* reserved */
#define CHRTYPE  '3'            /* character special */
#define BLKTYPE  '4'            /* block special */
#define DIRTYPE  '5'            /* directory */
#define FIFOTYPE '6'            /* FIFO special */
#define CONTTYPE '7'            /* reserved */

class TarFile {
public:
	TarFile(const char* tar_name);
	bool IsValidTarFile();
	std::vector<std::string> GetFileNames();
	bool GetFileContents(const char* file_name, char* contents);
	size_t GetFileSize(const char* file_name);
	size_t GetTarSize();
	~TarFile();
private:
	FILE* file;
	size_t size;
	std::vector<std::string> file_names;
	std::vector<size_t> file_sizes;
	std::vector<size_t> file_data_start_addrs;
};

int test_tar();

#endif // FBC_MESSY_TEST_TAR_HPP_

tar.cpp：

#include "tar.hpp"

TarFile::TarFile(const char* tar_name)
	: file(nullptr), size(0)
{
	file_names.clear();
	file_sizes.clear();
	file_data_start_addrs.clear();
	file = fopen(tar_name, "rb");
}

TarFile::~TarFile()
{
	if (file) {
		fclose(file);
		file = nullptr;
	}
	file_names.clear();
	file_sizes.clear();
	file_data_start_addrs.clear();
}

bool TarFile::IsValidTarFile()
{
	if (!file) return false;

	const int block_size{ 512 };
	unsigned char buf[block_size];
	tar_posix_header* header = (tar_posix_header*)buf;
	memset(buf, 0, block_size);

	fseek(file, 0, SEEK_END);
	size = ftell(file);
	fseek(file, 0, SEEK_SET);
	if (size % block_size != 0) {
		fprintf(stderr, "tar file size should be a multiple of 512 bytes: %d\n", size);
		return false;
	}

	size_t pos{ 0 };

	while (1) {
		size_t read_size = fread(buf, block_size, 1, file);
		if (read_size != 1) break;
		if (strncmp(header->magic, TMAGIC, 5)) break;

		pos += block_size;
		size_t file_size{0};
		sscanf(header->size, "%lo", &file_size);
		size_t file_block_count = (file_size + block_size - 1) / block_size;

		switch (header->typeflag) {
			case '0': // intentionally dropping through
			case '\0':
				// normal file
				file_sizes.push_back(file_size);
				file_names.push_back(std::string(header->name));
				file_data_start_addrs.push_back(pos);
				break;
			case '1':
				// hard link
				break;
			case '2':
				// symbolic link
				break;
			case '3':
				// device file/special file
				break;
			case '4':
				// block device
				break;
			case '5':
				// directory
				break;
			case '6':
				// named pipe
				break;
			default:
				break;
		}

		pos += file_block_count * block_size;
		fseek(file, pos, SEEK_SET);
	}

	fseek(file, 0, SEEK_SET);

	return true;
}

std::vector<std::string> TarFile::GetFileNames()
{
	return file_names;
}

bool TarFile::GetFileContents(const char* file_name, char* contents)
{
	bool flag = false;
	for (int i = 0; i < file_names.size(); i++) {
		std::string name_(file_name);

		if (file_names[i].compare(name_) == 0) {
			int file_size = file_sizes[i];
			flag = true;
			fseek(file, file_data_start_addrs[i], SEEK_SET);
			fread(contents, file_size, 1, file);
			fseek(file, 0, SEEK_SET);

			break;
		}
	}

	return flag;
}

size_t TarFile::GetFileSize(const char* file_name)
{
	size_t file_size{0};

	for (int i = 0; i < file_names.size(); i++) {
		std::string name_(file_name);

		if (file_names[i].compare(name_) == 0) {
			file_size = file_sizes[i];
			break;
		}
	}

	return file_size;
}

size_t TarFile::GetTarSize()
{
	return size;
}

//////////////////////////////////////////////
int test_tar()
{
	const std::string tar_file_path{ "E:/GitCode/Messy_Test/testdata/test.tar" };
	TarFile tarfile(tar_file_path.c_str());

	bool is_valid_tar_file = tarfile.IsValidTarFile();
	if (!is_valid_tar_file) {
		fprintf(stderr, "it is not a valid tar file: %s\n", tar_file_path.c_str());
		return -1;
	}

	fprintf(stderr, "tar file size: %d byte\n", tarfile.GetTarSize());

	std::vector<std::string> file_names = tarfile.GetFileNames();
	fprintf(stderr, "tar file count: %d\n", file_names.size());
	for (auto name : file_names) {
		fprintf(stderr, "=====================================\n");
		size_t file_size = tarfile.GetFileSize(name.c_str());
		fprintf(stderr, "file name: %s,  size: %d byte\n", name.c_str(), file_size);

		char* contents = new char[file_size + 1];
		tarfile.GetFileContents(name.c_str(), contents);
		contents[file_size] = '\0';

		fprintf(stderr, "contents:\n%s\n", contents);
		delete[] contents;
	}

	return 0;
}

测试结果如下：

GitHub：https://github.com/fengbingchun/Messy_Test