1 |
dpavlin |
2 |
/* |
2 |
|
|
* Copyright (C) 2004 Anders Gavare. All rights reserved. |
3 |
|
|
* |
4 |
|
|
* Redistribution and use in source and binary forms, with or without |
5 |
|
|
* modification, are permitted provided that the following conditions are met: |
6 |
|
|
* |
7 |
|
|
* 1. Redistributions of source code must retain the above copyright |
8 |
|
|
* notice, this list of conditions and the following disclaimer. |
9 |
|
|
* 2. Redistributions in binary form must reproduce the above copyright |
10 |
|
|
* notice, this list of conditions and the following disclaimer in the |
11 |
|
|
* documentation and/or other materials provided with the distribution. |
12 |
|
|
* 3. The name of the author may not be used to endorse or promote products |
13 |
|
|
* derived from this software without specific prior written permission. |
14 |
|
|
* |
15 |
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND |
16 |
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
17 |
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
18 |
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE |
19 |
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL |
20 |
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS |
21 |
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) |
22 |
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
23 |
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY |
24 |
|
|
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF |
25 |
|
|
* SUCH DAMAGE. |
26 |
|
|
* |
27 |
|
|
* |
28 |
|
|
* $Id: cp_removeblocks.c,v 1.11 2005/01/09 01:55:27 debug Exp $ |
29 |
|
|
* |
30 |
|
|
* This program copies a file, but only those blocks that are not zero- |
31 |
|
|
* filled. Typical usage would be if you have a harddisk image stored |
32 |
|
|
* as a file, which has all its zeroed blocks explicitly saved on disk, |
33 |
|
|
* and would like to save space. |
34 |
|
|
* |
35 |
|
|
* Example: You download a file called diskimage.gz from somewhere, |
36 |
|
|
* run gunzip on it, and the resulting file diskimage is |
37 |
|
|
* 1 GB large. ls -l reports the file size as 1 GB, and |
38 |
|
|
* so does 'du -k diskimage'. If a lot of the space used |
39 |
|
|
* by diskimage is actually zeroes, those parts do not need |
40 |
|
|
* to actually be saved. By running this program on diskimage: |
41 |
|
|
* |
42 |
|
|
* ./cp_removeblocks diskimage diskimage_compact |
43 |
|
|
* |
44 |
|
|
* you will get a file with the same functionality, but possibly |
45 |
|
|
* using less disk space. ('ls -l diskimage_compact' should |
46 |
|
|
* return the same size as for diskimage, but 'du -k' will |
47 |
|
|
* print only how many kb the file takes up on your disk.) |
48 |
|
|
* |
49 |
|
|
* You don't even need to gunzip the file to be 1 GB first, |
50 |
|
|
* you can pipe it through cp_removeblocks directly. |
51 |
|
|
* |
52 |
|
|
* gunzip -c file.img.gz | ./cp_removeblocks - file.img |
53 |
|
|
*/ |
54 |
|
|
|
55 |
|
|
#include <stdio.h> |
56 |
|
|
#include <stdlib.h> |
57 |
|
|
#include <string.h> |
58 |
|
|
#include <sys/types.h> |
59 |
|
|
|
60 |
|
|
#define BSIZE 512 |
61 |
|
|
|
62 |
|
|
|
63 |
|
|
int main(int argc, char *argv[]) |
64 |
|
|
{ |
65 |
|
|
FILE *f1, *f2; |
66 |
|
|
unsigned char buf[BSIZE]; |
67 |
|
|
off_t len; |
68 |
|
|
off_t in_pos = 0; |
69 |
|
|
int i, res, wrote_last = 0; |
70 |
|
|
|
71 |
|
|
if (argc != 3) { |
72 |
|
|
fprintf(stderr, "usage: %s infile outfile\n", argv[0]); |
73 |
|
|
fprintf(stderr, "if infile is \"-\", then stdin is used.\n"); |
74 |
|
|
fprintf(stderr, "if outfile is \"-\", then stdout is used.\n"); |
75 |
|
|
exit(1); |
76 |
|
|
} |
77 |
|
|
|
78 |
|
|
if (strcmp(argv[1], "-") == 0) |
79 |
|
|
f1 = stdin; |
80 |
|
|
else |
81 |
|
|
f1 = fopen(argv[1], "r"); |
82 |
|
|
|
83 |
|
|
if (f1 == NULL) { |
84 |
|
|
perror(argv[1]); |
85 |
|
|
exit(1); |
86 |
|
|
} |
87 |
|
|
|
88 |
|
|
if (strcmp(argv[2], "-") == 0) |
89 |
|
|
f2 = stdout; |
90 |
|
|
else |
91 |
|
|
f2 = fopen(argv[2], "w"); |
92 |
|
|
|
93 |
|
|
if (f2 == NULL) { |
94 |
|
|
perror(argv[2]); |
95 |
|
|
exit(1); |
96 |
|
|
} |
97 |
|
|
|
98 |
|
|
while (!feof(f1)) { |
99 |
|
|
len = fread(buf, 1, BSIZE, f1); |
100 |
|
|
|
101 |
|
|
if (len > 0) { |
102 |
|
|
/* Check for data in buf: */ |
103 |
|
|
for (i=0; i<len; i++) |
104 |
|
|
if (buf[i]) |
105 |
|
|
break; |
106 |
|
|
|
107 |
|
|
if (i < len) { |
108 |
|
|
fseeko(f2, in_pos, SEEK_SET); |
109 |
|
|
fwrite(buf, 1, len, f2); |
110 |
|
|
wrote_last = 1; |
111 |
|
|
} else |
112 |
|
|
wrote_last = 0; |
113 |
|
|
|
114 |
|
|
in_pos += len; |
115 |
|
|
} |
116 |
|
|
} |
117 |
|
|
|
118 |
|
|
/* |
119 |
|
|
* Copy the last byte explicitly, if necessary. |
120 |
|
|
* (This causes f2 to get the correct file size.) |
121 |
|
|
*/ |
122 |
|
|
if (!wrote_last && in_pos > 0) { |
123 |
|
|
res = fseeko(f2, in_pos - 1, SEEK_SET); |
124 |
|
|
if (res != 0) |
125 |
|
|
perror("fseeko(f2)"); |
126 |
|
|
|
127 |
|
|
buf[0] = '\0'; |
128 |
|
|
fwrite(&buf[0], 1, 1, f2); |
129 |
|
|
} |
130 |
|
|
|
131 |
|
|
fclose(f1); |
132 |
|
|
fclose(f2); |
133 |
|
|
|
134 |
|
|
return 0; |
135 |
|
|
} |
136 |
|
|
|