1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352
|
// This file is part of par2cmdline (a PAR 2.0 compatible file verification and
// repair tool). See http://parchive.sourceforge.net for details of PAR 2.0.
//
// Copyright (c) 2003 Peter Brian Clements
// Copyright (c) 2019 Michael D. Nahas
//
// par2cmdline is free software; you can redistribute it and/or modify
// it under the terms of the GNU General Public License as published by
// the Free Software Foundation; either version 2 of the License, or
// (at your option) any later version.
//
// par2cmdline is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
//
// You should have received a copy of the GNU General Public License
// along with this program; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#include "libpar2internal.h"
#ifdef _MSC_VER
#ifdef _DEBUG
#undef THIS_FILE
static char THIS_FILE[]=__FILE__;
#define new DEBUG_NEW
#endif
#endif
Par2CreatorSourceFile::Par2CreatorSourceFile(void)
{
descriptionpacket = 0;
verificationpacket = 0;
diskfile = 0;
filesize = 0;
//diskfilename;
//parfilename;
blockcount = 0;
contextfull = 0;
}
Par2CreatorSourceFile::~Par2CreatorSourceFile(void)
{
delete descriptionpacket;
delete verificationpacket;
delete diskfile;
delete contextfull;
}
// Open the source file, compute the MD5 Hash of the whole file and the first
// 16k of the file, and then compute the FileId and store the results
// in a file description packet and a file verification packet.
#ifdef _OPENMP
bool Par2CreatorSourceFile::Open(NoiseLevel noiselevel, std::ostream &sout, std::ostream &serr, const string &extrafile, u64 blocksize, bool deferhashcomputation, string basepath, u64 totalsize, u64 &totalprogress)
#else
bool Par2CreatorSourceFile::Open(NoiseLevel noiselevel, std::ostream &sout, std::ostream &serr, const string &extrafile, u64 blocksize, bool deferhashcomputation, string basepath)
#endif
{
// Get the filename and filesize
diskfilename = extrafile;
filesize = DiskFile::GetFileSize(extrafile);
// Work out how many blocks the file will be sliced into
blockcount = (u32)((filesize + blocksize-1) / blocksize);
// Determine what filename to record in the PAR2 files
parfilename = diskfilename;
parfilename.erase(0, basepath.length());
parfilename = DescriptionPacket::TranslateFilenameFromLocalToPar2(sout, serr, noiselevel, parfilename);
// Create the Description and Verification packets
descriptionpacket = new DescriptionPacket;
descriptionpacket->Create(parfilename, filesize);
verificationpacket = new VerificationPacket;
verificationpacket->Create(blockcount);
// Create the diskfile object
diskfile = new DiskFile(sout, serr);
// Open the source file
if (!diskfile->Open(diskfilename, filesize))
return false;
// Do we want to defer the computation of the full file hash, and
// the block crc and hashes. This is only permitted if there
// is sufficient memory available to create all recovery blocks
// in one pass of the source files (i.e. chunksize == blocksize)
if (deferhashcomputation)
{
// Initialise a buffer to read the first 16k of the source file
size_t buffersize = 16 * 1024;
if (buffersize > filesize)
buffersize = (size_t)filesize;
char *buffer = new char[buffersize];
// Read the data from the file
if (!diskfile->Read(0, buffer, buffersize))
{
diskfile->Close();
delete [] buffer;
return false;
}
// Compute the hash of the data read from the file
MD5Context context;
context.Update(buffer, buffersize);
delete [] buffer;
MD5Hash hash;
context.Final(hash);
// Store the hash in the descriptionpacket and compute the file id
descriptionpacket->Hash16k(hash);
// Compute the fileid and store it in the verification packet.
descriptionpacket->ComputeFileId();
verificationpacket->FileId(descriptionpacket->FileId());
// Allocate an MD5 context for computing the file hash
// during the recovery data generation phase
contextfull = new MD5Context;
}
else
{
// Initialise a buffer to read the source file
size_t buffersize = 1024*1024;
if (buffersize > min(blocksize,filesize))
buffersize = (size_t)min(blocksize,filesize);
char *buffer = new char[buffersize];
// Get ready to start reading source file to compute the hashes and crcs
u64 offset = 0;
u32 blocknumber = 0;
u64 need = blocksize;
MD5Context filecontext;
MD5Context blockcontext;
u32 blockcrc = 0;
// Whilst we have not reached the end of the file
while (offset < filesize)
{
// Work out how much we can read
size_t want = (size_t)min(filesize-offset, (u64)buffersize);
// Read some data from the file into the buffer
if (!diskfile->Read(offset, buffer, want))
{
diskfile->Close();
delete [] buffer;
return false;
}
// If the new data passes the 16k boundary, compute the 16k hash for the file
if (offset < 16384 && offset + want >= 16384)
{
filecontext.Update(buffer, (size_t)(16384-offset));
MD5Context temp = filecontext;
MD5Hash hash;
temp.Final(hash);
// Store the 16k hash in the file description packet
descriptionpacket->Hash16k(hash);
if (offset + want > 16384)
{
filecontext.Update(&buffer[16384-offset], (size_t)(offset+want)-16384);
}
}
else
{
filecontext.Update(buffer, want);
}
// Get ready to update block hashes and crcs
u32 used = 0;
// Whilst we have not used all of the data we just read
while (used < want)
{
// How much of it can we use for the current block
u32 use = (u32)min(need, (u64)(want-used));
blockcrc = ~0 ^ CRCUpdateBlock(~0 ^ blockcrc, use, &buffer[used]);
blockcontext.Update(&buffer[used], use);
used += use;
need -= use;
// Have we finished the current block
if (need == 0)
{
MD5Hash blockhash;
blockcontext.Final(blockhash);
// Store the block hash and block crc in the file verification packet.
verificationpacket->SetBlockHashAndCRC(blocknumber, blockhash, blockcrc);
blocknumber++;
// More blocks
if (blocknumber < blockcount)
{
need = blocksize;
blockcontext.Reset();
blockcrc = 0;
}
}
}
if (noiselevel > nlQuiet)
{
// Display progress
#ifdef _OPENMP
u32 oldfraction = (u32)(1000 * totalprogress / totalsize);
#pragma omp atomic
totalprogress += want;
u32 newfraction = (u32)(1000 * totalprogress / totalsize);
#else
u32 oldfraction = (u32)(1000 * offset / filesize);
u32 newfraction = (u32)(1000 * (offset + want) / filesize);
#endif
if (oldfraction != newfraction)
{
#pragma omp critical
sout << newfraction/10 << '.' << newfraction%10 << "%\r" << flush;
}
}
offset += want;
}
// Did we finish the last block
if (need > 0)
{
blockcrc = ~0 ^ CRCUpdateBlock(~0 ^ blockcrc, (size_t)need);
blockcontext.Update((size_t)need);
MD5Hash blockhash;
blockcontext.Final(blockhash);
// Store the block hash and block crc in the file verification packet.
verificationpacket->SetBlockHashAndCRC(blocknumber, blockhash, blockcrc);
blocknumber++;
need = 0;
}
// Finish computing the file hash.
MD5Hash filehash;
filecontext.Final(filehash);
// Store the file hash in the file description packet.
descriptionpacket->HashFull(filehash);
// Did we compute the 16k hash.
if (offset < 16384)
{
// Store the 16k hash in the file description packet.
descriptionpacket->Hash16k(filehash);
}
delete [] buffer;
// Compute the fileid and store it in the verification packet.
descriptionpacket->ComputeFileId();
verificationpacket->FileId(descriptionpacket->FileId());
}
return true;
}
void Par2CreatorSourceFile::Close(void)
{
diskfile->Close();
}
void Par2CreatorSourceFile::RecordCriticalPackets(list<CriticalPacket*> &criticalpackets)
{
// Add the file description packet and file verification packet to
// the critical packet list.
criticalpackets.push_back(descriptionpacket);
criticalpackets.push_back(verificationpacket);
}
bool Par2CreatorSourceFile::CompareLess(const Par2CreatorSourceFile* const &left, const Par2CreatorSourceFile* const &right)
{
// Sort source files based on fileid
return left->descriptionpacket->FileId() < right->descriptionpacket->FileId();
}
const MD5Hash& Par2CreatorSourceFile::FileId(void) const
{
// Get the file id hash
return descriptionpacket->FileId();
}
void Par2CreatorSourceFile::InitialiseSourceBlocks(vector<DataBlock>::iterator &sourceblock, u64 blocksize)
{
for (u32 blocknum=0; blocknum<blockcount; blocknum++)
{
// Configure each source block to an appropriate offset and length within the source file.
sourceblock->SetLocation(diskfile, // file
blocknum * blocksize); // offset
sourceblock->SetLength(min(blocksize, filesize - (u64)blocknum * blocksize)); // length
sourceblock++;
}
}
void Par2CreatorSourceFile::UpdateHashes(u32 blocknumber, const void *buffer, size_t length)
{
// Compute the crc and hash of the data
u32 blockcrc = ~0 ^ CRCUpdateBlock(~0, length, buffer);
MD5Context blockcontext;
blockcontext.Update(buffer, length);
MD5Hash blockhash;
blockcontext.Final(blockhash);
// Store the results in the verification packet
verificationpacket->SetBlockHashAndCRC(blocknumber, blockhash, blockcrc);
// Update the full file hash, but don't go beyond the end of the file
const u64 len = filesize - (u64) blocknumber * (u64) length;
if ((u64)length > len)
{
length = (size_t)(len);
}
assert(contextfull != 0);
contextfull->Update(buffer, length);
}
void Par2CreatorSourceFile::FinishHashes(void)
{
assert(contextfull != 0);
// Finish computation of the full file hash
MD5Hash hash;
contextfull->Final(hash);
// Store it in the description packet
descriptionpacket->HashFull(hash);
}
|