aboutsummaryrefslogtreecommitdiff
path: root/src/cmd/bzip2/bzip2recover.c
diff options
context:
space:
mode:
Diffstat (limited to 'src/cmd/bzip2/bzip2recover.c')
-rw-r--r--src/cmd/bzip2/bzip2recover.c435
1 files changed, 435 insertions, 0 deletions
diff --git a/src/cmd/bzip2/bzip2recover.c b/src/cmd/bzip2/bzip2recover.c
new file mode 100644
index 00000000..ba3d1756
--- /dev/null
+++ b/src/cmd/bzip2/bzip2recover.c
@@ -0,0 +1,435 @@
+
+/*-----------------------------------------------------------*/
+/*--- Block recoverer program for bzip2 ---*/
+/*--- bzip2recover.c ---*/
+/*-----------------------------------------------------------*/
+
+/*--
+ This program is bzip2recover, a program to attempt data
+ salvage from damaged files created by the accompanying
+ bzip2-1.0 program.
+
+ Copyright (C) 1996-2000 Julian R Seward. All rights reserved.
+
+ Redistribution and use in source and binary forms, with or without
+ modification, are permitted provided that the following conditions
+ are met:
+
+ 1. Redistributions of source code must retain the above copyright
+ notice, this list of conditions and the following disclaimer.
+
+ 2. The origin of this software must not be misrepresented; you must
+ not claim that you wrote the original software. If you use this
+ software in a product, an acknowledgment in the product
+ documentation would be appreciated but is not required.
+
+ 3. Altered source versions must be plainly marked as such, and must
+ not be misrepresented as being the original software.
+
+ 4. The name of the author may not be used to endorse or promote
+ products derived from this software without specific prior written
+ permission.
+
+ THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
+ OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
+ DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
+ GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+ Julian Seward, Cambridge, UK.
+ jseward@acm.org
+ bzip2/libbzip2 version 1.0 of 21 March 2000
+--*/
+
+/*--
+ This program is a complete hack and should be rewritten
+ properly. It isn't very complicated.
+--*/
+
+#include <stdio.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+
+typedef unsigned int UInt32;
+typedef int Int32;
+typedef unsigned char UChar;
+typedef char Char;
+typedef unsigned char Bool;
+#define True ((Bool)1)
+#define False ((Bool)0)
+
+
+Char inFileName[2000];
+Char outFileName[2000];
+Char progName[2000];
+
+UInt32 bytesOut = 0;
+UInt32 bytesIn = 0;
+
+
+/*---------------------------------------------------*/
+/*--- I/O errors ---*/
+/*---------------------------------------------------*/
+
+/*---------------------------------------------*/
+void readError ( void )
+{
+ fprintf ( stderr,
+ "%s: I/O error reading `%s', possible reason follows.\n",
+ progName, inFileName );
+ perror ( progName );
+ fprintf ( stderr, "%s: warning: output file(s) may be incomplete.\n",
+ progName );
+ exit ( 1 );
+}
+
+
+/*---------------------------------------------*/
+void writeError ( void )
+{
+ fprintf ( stderr,
+ "%s: I/O error reading `%s', possible reason follows.\n",
+ progName, inFileName );
+ perror ( progName );
+ fprintf ( stderr, "%s: warning: output file(s) may be incomplete.\n",
+ progName );
+ exit ( 1 );
+}
+
+
+/*---------------------------------------------*/
+void mallocFail ( Int32 n )
+{
+ fprintf ( stderr,
+ "%s: malloc failed on request for %d bytes.\n",
+ progName, n );
+ fprintf ( stderr, "%s: warning: output file(s) may be incomplete.\n",
+ progName );
+ exit ( 1 );
+}
+
+
+/*---------------------------------------------------*/
+/*--- Bit stream I/O ---*/
+/*---------------------------------------------------*/
+
+typedef
+ struct {
+ FILE* handle;
+ Int32 buffer;
+ Int32 buffLive;
+ Char mode;
+ }
+ BitStream;
+
+
+/*---------------------------------------------*/
+BitStream* bsOpenReadStream ( FILE* stream )
+{
+ BitStream *bs = malloc ( sizeof(BitStream) );
+ if (bs == NULL) mallocFail ( sizeof(BitStream) );
+ bs->handle = stream;
+ bs->buffer = 0;
+ bs->buffLive = 0;
+ bs->mode = 'r';
+ return bs;
+}
+
+
+/*---------------------------------------------*/
+BitStream* bsOpenWriteStream ( FILE* stream )
+{
+ BitStream *bs = malloc ( sizeof(BitStream) );
+ if (bs == NULL) mallocFail ( sizeof(BitStream) );
+ bs->handle = stream;
+ bs->buffer = 0;
+ bs->buffLive = 0;
+ bs->mode = 'w';
+ return bs;
+}
+
+
+/*---------------------------------------------*/
+void bsPutBit ( BitStream* bs, Int32 bit )
+{
+ if (bs->buffLive == 8) {
+ Int32 retVal = putc ( (UChar) bs->buffer, bs->handle );
+ if (retVal == EOF) writeError();
+ bytesOut++;
+ bs->buffLive = 1;
+ bs->buffer = bit & 0x1;
+ } else {
+ bs->buffer = ( (bs->buffer << 1) | (bit & 0x1) );
+ bs->buffLive++;
+ };
+}
+
+
+/*---------------------------------------------*/
+/*--
+ Returns 0 or 1, or 2 to indicate EOF.
+--*/
+Int32 bsGetBit ( BitStream* bs )
+{
+ if (bs->buffLive > 0) {
+ bs->buffLive --;
+ return ( ((bs->buffer) >> (bs->buffLive)) & 0x1 );
+ } else {
+ Int32 retVal = getc ( bs->handle );
+ if ( retVal == EOF ) {
+ if (errno != 0) readError();
+ return 2;
+ }
+ bs->buffLive = 7;
+ bs->buffer = retVal;
+ return ( ((bs->buffer) >> 7) & 0x1 );
+ }
+}
+
+
+/*---------------------------------------------*/
+void bsClose ( BitStream* bs )
+{
+ Int32 retVal;
+
+ if ( bs->mode == 'w' ) {
+ while ( bs->buffLive < 8 ) {
+ bs->buffLive++;
+ bs->buffer <<= 1;
+ };
+ retVal = putc ( (UChar) (bs->buffer), bs->handle );
+ if (retVal == EOF) writeError();
+ bytesOut++;
+ retVal = fflush ( bs->handle );
+ if (retVal == EOF) writeError();
+ }
+ retVal = fclose ( bs->handle );
+ if (retVal == EOF) {
+ if (bs->mode == 'w') writeError(); else readError();
+ }
+ free ( bs );
+}
+
+
+/*---------------------------------------------*/
+void bsPutUChar ( BitStream* bs, UChar c )
+{
+ Int32 i;
+ for (i = 7; i >= 0; i--)
+ bsPutBit ( bs, (((UInt32) c) >> i) & 0x1 );
+}
+
+
+/*---------------------------------------------*/
+void bsPutUInt32 ( BitStream* bs, UInt32 c )
+{
+ Int32 i;
+
+ for (i = 31; i >= 0; i--)
+ bsPutBit ( bs, (c >> i) & 0x1 );
+}
+
+
+/*---------------------------------------------*/
+Bool endsInBz2 ( Char* name )
+{
+ Int32 n = strlen ( name );
+ if (n <= 4) return False;
+ return
+ (name[n-4] == '.' &&
+ name[n-3] == 'b' &&
+ name[n-2] == 'z' &&
+ name[n-1] == '2');
+}
+
+
+/*---------------------------------------------------*/
+/*--- ---*/
+/*---------------------------------------------------*/
+
+#define BLOCK_HEADER_HI 0x00003141UL
+#define BLOCK_HEADER_LO 0x59265359UL
+
+#define BLOCK_ENDMARK_HI 0x00001772UL
+#define BLOCK_ENDMARK_LO 0x45385090UL
+
+
+UInt32 bStart[20000];
+UInt32 bEnd[20000];
+UInt32 rbStart[20000];
+UInt32 rbEnd[20000];
+
+Int32 main ( Int32 argc, Char** argv )
+{
+ FILE* inFile;
+ FILE* outFile;
+ BitStream* bsIn, *bsWr;
+ Int32 currBlock, b, wrBlock;
+ UInt32 bitsRead;
+ Int32 rbCtr;
+
+
+ UInt32 buffHi, buffLo, blockCRC;
+ Char* p;
+
+ strcpy ( progName, argv[0] );
+ inFileName[0] = outFileName[0] = 0;
+
+ fprintf ( stderr, "bzip2recover 1.0: extracts blocks from damaged .bz2 files.\n" );
+
+ if (argc != 2) {
+ fprintf ( stderr, "%s: usage is `%s damaged_file_name'.\n",
+ progName, progName );
+ exit(1);
+ }
+
+ strcpy ( inFileName, argv[1] );
+
+ inFile = fopen ( inFileName, "rb" );
+ if (inFile == NULL) {
+ fprintf ( stderr, "%s: can't read `%s'\n", progName, inFileName );
+ exit(1);
+ }
+
+ bsIn = bsOpenReadStream ( inFile );
+ fprintf ( stderr, "%s: searching for block boundaries ...\n", progName );
+
+ bitsRead = 0;
+ buffHi = buffLo = 0;
+ currBlock = 0;
+ bStart[currBlock] = 0;
+
+ rbCtr = 0;
+
+ while (True) {
+ b = bsGetBit ( bsIn );
+ bitsRead++;
+ if (b == 2) {
+ if (bitsRead >= bStart[currBlock] &&
+ (bitsRead - bStart[currBlock]) >= 40) {
+ bEnd[currBlock] = bitsRead-1;
+ if (currBlock > 0)
+ fprintf ( stderr, " block %d runs from %d to %d (incomplete)\n",
+ currBlock, bStart[currBlock], bEnd[currBlock] );
+ } else
+ currBlock--;
+ break;
+ }
+ buffHi = (buffHi << 1) | (buffLo >> 31);
+ buffLo = (buffLo << 1) | (b & 1);
+ if ( ( (buffHi & 0x0000ffff) == BLOCK_HEADER_HI
+ && buffLo == BLOCK_HEADER_LO)
+ ||
+ ( (buffHi & 0x0000ffff) == BLOCK_ENDMARK_HI
+ && buffLo == BLOCK_ENDMARK_LO)
+ ) {
+ if (bitsRead > 49)
+ bEnd[currBlock] = bitsRead-49; else
+ bEnd[currBlock] = 0;
+ if (currBlock > 0 &&
+ (bEnd[currBlock] - bStart[currBlock]) >= 130) {
+ fprintf ( stderr, " block %d runs from %d to %d\n",
+ rbCtr+1, bStart[currBlock], bEnd[currBlock] );
+ rbStart[rbCtr] = bStart[currBlock];
+ rbEnd[rbCtr] = bEnd[currBlock];
+ rbCtr++;
+ }
+ currBlock++;
+
+ bStart[currBlock] = bitsRead;
+ }
+ }
+
+ bsClose ( bsIn );
+
+ /*-- identified blocks run from 1 to rbCtr inclusive. --*/
+
+ if (rbCtr < 1) {
+ fprintf ( stderr,
+ "%s: sorry, I couldn't find any block boundaries.\n",
+ progName );
+ exit(1);
+ };
+
+ fprintf ( stderr, "%s: splitting into blocks\n", progName );
+
+ inFile = fopen ( inFileName, "rb" );
+ if (inFile == NULL) {
+ fprintf ( stderr, "%s: can't open `%s'\n", progName, inFileName );
+ exit(1);
+ }
+ bsIn = bsOpenReadStream ( inFile );
+
+ /*-- placate gcc's dataflow analyser --*/
+ blockCRC = 0; bsWr = 0;
+
+ bitsRead = 0;
+ outFile = NULL;
+ wrBlock = 0;
+ while (True) {
+ b = bsGetBit(bsIn);
+ if (b == 2) break;
+ buffHi = (buffHi << 1) | (buffLo >> 31);
+ buffLo = (buffLo << 1) | (b & 1);
+ if (bitsRead == 47+rbStart[wrBlock])
+ blockCRC = (buffHi << 16) | (buffLo >> 16);
+
+ if (outFile != NULL && bitsRead >= rbStart[wrBlock]
+ && bitsRead <= rbEnd[wrBlock]) {
+ bsPutBit ( bsWr, b );
+ }
+
+ bitsRead++;
+
+ if (bitsRead == rbEnd[wrBlock]+1) {
+ if (outFile != NULL) {
+ bsPutUChar ( bsWr, 0x17 ); bsPutUChar ( bsWr, 0x72 );
+ bsPutUChar ( bsWr, 0x45 ); bsPutUChar ( bsWr, 0x38 );
+ bsPutUChar ( bsWr, 0x50 ); bsPutUChar ( bsWr, 0x90 );
+ bsPutUInt32 ( bsWr, blockCRC );
+ bsClose ( bsWr );
+ }
+ if (wrBlock >= rbCtr) break;
+ wrBlock++;
+ } else
+ if (bitsRead == rbStart[wrBlock]) {
+ outFileName[0] = 0;
+ sprintf ( outFileName, "rec%4d", wrBlock+1 );
+ for (p = outFileName; *p != 0; p++) if (*p == ' ') *p = '0';
+ strcat ( outFileName, inFileName );
+ if ( !endsInBz2(outFileName)) strcat ( outFileName, ".bz2" );
+
+ fprintf ( stderr, " writing block %d to `%s' ...\n",
+ wrBlock+1, outFileName );
+
+ outFile = fopen ( outFileName, "wb" );
+ if (outFile == NULL) {
+ fprintf ( stderr, "%s: can't write `%s'\n",
+ progName, outFileName );
+ exit(1);
+ }
+ bsWr = bsOpenWriteStream ( outFile );
+ bsPutUChar ( bsWr, 'B' ); bsPutUChar ( bsWr, 'Z' );
+ bsPutUChar ( bsWr, 'h' ); bsPutUChar ( bsWr, '9' );
+ bsPutUChar ( bsWr, 0x31 ); bsPutUChar ( bsWr, 0x41 );
+ bsPutUChar ( bsWr, 0x59 ); bsPutUChar ( bsWr, 0x26 );
+ bsPutUChar ( bsWr, 0x53 ); bsPutUChar ( bsWr, 0x59 );
+ }
+ }
+
+ fprintf ( stderr, "%s: finished\n", progName );
+ return 0;
+}
+
+
+
+/*-----------------------------------------------------------*/
+/*--- end bzip2recover.c ---*/
+/*-----------------------------------------------------------*/
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-02 21:14:43 +0000