使用unrar库 - 将文件提取到文件流缓冲区中

Question

使用unrar库 - 将文件提取到文件流缓冲区中

我需要的是能够将.rar文件中的文件提取到流中.我正在创建一个测试用例,以了解如何使用unrar源代码.我一直在寻找和修补一段时间,但我无法弄清楚如何使用该库.我很惊讶我甚至找不到文档或教程,考虑到常见的.rar档案.

我自己取得了一些进步,但并不总是有效.正确提取某些文件.其他文件由于某种原因混乱(但不完全是 "垃圾"二进制数据).到目前为止我所知道的通常是(但并不总是):

不工作的文件fileInfo.Method = 48.它们似乎是压缩率为100%的文件 - 即没有压缩
工作文件有fileInfo.Method = 49,50,51,52,或者53,它们分别对应于压缩速度最快,快速,正常,良好最好,

但我不知道为什么会这样.仍然找不到文档或工作示例.

下面是我到目前为止的测试用例源和一个示例rar存档,当使用此程序解压缩时,它具有工作文件和不工作文件.

/* put in the same directory as the unrar source files
 * compiling with:
 *   make clean
 *   make lib
 *   g++ rartest.cpp -o rartest libunrar.so -lboost_filesystem
 */

#include  <cstring>
#include  <iostream>
#include  <fstream>

#include  <boost/filesystem.hpp>

#define _UNIX
#define  RARDLL
#include  "dll.hpp"

using namespace std;
namespace fs = boost::filesystem;

//char fileName[100] = "testout0.jpg\0";
//
//// doens't work
//int PASCAL ProcessDataProc(unsigned char* buffer, int buffLen) {
//  cout  << "writing..." << endl;
//  ofstream outFile(fileName);
//  cout << buffLen << endl;
//  cout << outFile.write((const char*)buffer, buffLen) << endl;
//  cout  << "done writing..." << endl;
//  fileName[7]++;
//}

int CALLBACK CallbackProc(unsigned int msg, long myBuffer, long rarBuffer, long bufferLen) {
  switch(msg) {
    case UCM_CHANGEVOLUME:
      break;
    case UCM_PROCESSDATA:
      memcpy((char*)myBuffer, (char*)rarBuffer, bufferLen);
      break;
    case UCM_NEEDPASSWORD:
      break;
  }
  return 1;
}

int main(int argc, char* argv[]) {
  if (argc != 2)
    return 0;
  ifstream archiveStream(argv[1]);
  if (!archiveStream.is_open())
    cout << "fstream couldn't open file\n";

  // declare and set parameters
  HANDLE rarFile;
  RARHeaderDataEx fileInfo;
  RAROpenArchiveDataEx archiveInfo;
  memset(&archiveInfo, 0, sizeof(archiveInfo));
  archiveInfo.CmtBuf = NULL;
  //archiveInfo.OpenMode = RAR_OM_LIST;
  archiveInfo.OpenMode = RAR_OM_EXTRACT;
  archiveInfo.ArcName = argv[1];

  // Open file
  rarFile = RAROpenArchiveEx(&archiveInfo);
  if (archiveInfo.OpenResult != 0) {
    RARCloseArchive(rarFile);
    cout  << "unrar couldn't open" << endl;
    exit(1);
  }
  fileInfo.CmtBuf = NULL;

  cout  << archiveInfo.Flags << endl;

  // loop through archive
  int numFiles = 0;
  int fileSize;
  int RHCode;
  int PFCode;
  while(true) {
    RHCode = RARReadHeaderEx(rarFile, &fileInfo);
    if (RHCode != 0) break;

    numFiles++;
    fs::path path(fileInfo.FileName);
    fileSize = fileInfo.UnpSize;

    cout << fileInfo.Method << " " << fileInfo.FileName << " (" << fileInfo.UnpSize << ")" << endl;

    char fileBuffer[fileInfo.UnpSize];

    // not sure what this does
    //RARSetProcessDataProc(rarFile, ProcessDataProc);

    // works for some files, but not for others
    RARSetCallback(rarFile, CallbackProc, (long) &fileBuffer);
    PFCode = RARProcessFile(rarFile, RAR_TEST, NULL, NULL);

    // properly extracts to a directory... but I need a stream
    // and I don't want to write to disk, read it, and delete from disk
    //PFCode = RARProcessFile(rarFile, RAR_EXTRACT, ".", fileInfo.FileName);

    // just skips
    //PFCode = RARProcessFile(rarFile, RAR_SKIP, NULL, NULL);

    if (PFCode != 0) {
      RARCloseArchive(rarFile);
      cout  << "error processing this file\n" << endl;
      exit(1);
    }
    ofstream outFile(path.filename().c_str());
    outFile.write(fileBuffer, fileSize);
  }
  if (RHCode != ERAR_END_ARCHIVE)
    cout  << "error traversing through archive: " << RHCode << endl;
  RARCloseArchive(rarFile);

  cout  << "num files: " << numFiles << endl;

}

Run Code Online (Sandbox Code Playgroud)

更新:

我发现一个文件似乎是(声称是？)文档,但根据文件,我没有做错任何事情.我想我可能会被迫使用CRC检查缓冲区并在失败时实施解决方法.

解决方案来源(谢谢,Denis Krjuchkov!):

/* put in the same directory as the unrar source files
 * compiling with:
 *   make clean
 *   make lib
 *   g++ rartest.cpp -o rartest libunrar.so -lboost_filesystem
 */

#include  <cstring>
#include  <iostream>
#include  <fstream>

#include  <boost/filesystem.hpp>
#include    <boost/crc.hpp>

#define _UNIX
#define  RARDLL
#include  "dll.hpp"

using namespace std;
namespace fs = boost::filesystem;

//char fileName[100] = "testout0.jpg\0";
//
//// doens't work
//int PASCAL ProcessDataProc(unsigned char* buffer, int buffLen) {
//  cout  << "writing..." << endl;
//  ofstream outFile(fileName);
//  cout << buffLen << endl;
//  cout << outFile.write((const char*)buffer, buffLen) << endl;
//  cout  << "done writing..." << endl;
//  fileName[7]++;
//}

int CALLBACK CallbackProc(unsigned int msg, long myBufferPtr, long rarBuffer, long bytesProcessed) {
  switch(msg) {
    case UCM_CHANGEVOLUME:
      return -1;
      break;
    case UCM_PROCESSDATA:
      memcpy(*(char**)myBufferPtr, (char*)rarBuffer, bytesProcessed);
      *(char**)myBufferPtr += bytesProcessed;
      return 1;
      break;
    case UCM_NEEDPASSWORD:
      return -1;
      break;
  }
}

int main(int argc, char* argv[]) {
  if (argc != 2)
    return 0;
  ifstream archiveStream(argv[1]);
  if (!archiveStream.is_open())
    cout << "fstream couldn't open file\n";

  // declare and set parameters
  RARHANDLE rarFile;  // I renamed this macro in dll.hpp for my own purposes
  RARHANDLE rarFile2;
  RARHeaderDataEx fileInfo;
  RAROpenArchiveDataEx archiveInfo;
  memset(&archiveInfo, 0, sizeof(archiveInfo));
  archiveInfo.CmtBuf = NULL;
  //archiveInfo.OpenMode = RAR_OM_LIST;
  archiveInfo.OpenMode = RAR_OM_EXTRACT;
  archiveInfo.ArcName = argv[1];

  // Open file
  rarFile = RAROpenArchiveEx(&archiveInfo);
  rarFile2 = RAROpenArchiveEx(&archiveInfo);
  if (archiveInfo.OpenResult != 0) {
    RARCloseArchive(rarFile);
    cout  << "unrar couldn't open" << endl;
    exit(1);
  }
  fileInfo.CmtBuf = NULL;

//  cout  << archiveInfo.Flags << endl;

  // loop through archive
  int numFiles = 0;
  int fileSize;
  int RHCode;
  int PFCode;
  int crcVal;
  bool workaroundUsed = false;
    char currDir[2] = ".";
    char tmpFile[11] = "buffer.tmp";
  while(true) {
    RHCode = RARReadHeaderEx(rarFile, &fileInfo);
    if (RHCode != 0) break;
    RARReadHeaderEx(rarFile2, &fileInfo);

    numFiles++;
    fs::path path(fileInfo.FileName);
    fileSize = fileInfo.UnpSize;
    crcVal = fileInfo.FileCRC;

    cout << dec << fileInfo.Method << " " << fileInfo.FileName << " (" << fileInfo.UnpSize << ")" << endl;
    cout << " " << hex << uppercase << crcVal << endl;

    char fileBuffer[fileSize];
    char* bufferPtr = fileBuffer;

    // not sure what this does
    //RARSetProcessDataProc(rarFile, ProcessDataProc);

    // works for some files, but not for others
    RARSetCallback(rarFile, CallbackProc, (long) &bufferPtr);
    PFCode = RARProcessFile(rarFile, RAR_TEST, NULL, NULL);

    // properly extracts to a directory... but I need a stream
    // and I don't want to write to disk, read it, and delete from disk
//    PFCode = RARProcessFile(rarFile, RAR_EXTRACT, currDir, fileInfo.FileName);

    // just skips
    //PFCode = RARProcessFile(rarFile, RAR_SKIP, NULL, NULL);

    if (PFCode != 0) {
      RARCloseArchive(rarFile);
      cout  << "error processing this file\n" << endl;
      exit(1);
    }

    // crc check
    boost::crc_32_type crc32result;
    crc32result.process_bytes(&fileBuffer, fileSize);
    cout << " " << hex << uppercase << crc32result.checksum() << endl;

    // old workaround - crc check always succeeds now!
    if (crcVal == crc32result.checksum()) {
      RARProcessFile(rarFile2, RAR_SKIP, NULL, NULL);
    }
    else {
      workaroundUsed = true;
      RARProcessFile(rarFile2, RAR_EXTRACT, currDir, tmpFile);
      ifstream inFile(tmpFile);
      inFile.read(fileBuffer, fileSize);
    }

    ofstream outFile(path.filename().c_str());
    outFile.write(fileBuffer, fileSize);
  }
  if (workaroundUsed) remove(tmpFile);
  if (RHCode != ERAR_END_ARCHIVE)
    cout  << "error traversing through archive: " << RHCode << endl;
  RARCloseArchive(rarFile);

  cout  << dec << "num files: " << numFiles << endl;

}

Run Code Online (Sandbox Code Playgroud)

Answer 1

Den*_*s K 6

我不熟悉unrar,在快速阅读文档之后我认为你假设每个文件只调用一次CallbackProc.但是,我认为unrar可能会多次调用它.它解压缩一些数据然后调用CallbackProc,然后解压缩下一个数据块并再次调用CallbackProc,迭代该过程直到处理完所有数据.您应该记住实际写入缓冲区的字节数,并在相应的偏移量处追加新数据.

归档时间：	15 年，8 月前
查看次数：	9548 次
最近记录：	12 年，3 月前