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
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
|
/* -*- Mode:C; c-basic-offset:4; tab-width:8; indent-tabs-mode:t -*- */
/*
* Copyright (C) 2004-2024 by the University of Southern California
* $Id: a91d5228a362749a1ccff71f0fbdc092ac7ebdcc $
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program 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.
*
*/
/* setup environment */
#define _GNU_SOURCE 1
#define _FILE_OFFSET_BITS 64
#include <stdio.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <getopt.h>
#include <unistd.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <ctype.h>
#include <regex.h> //xxx need to check in autoconf
#include <assert.h>
#include "cryptopANT.h"
//autoconfigured
#include "config.h"
//long options
#define PASS4 256
#define PASS6 257
#define KTYPE 258
#define IPPREFIX 259
#define IPSUFFIX 260
#define IP4MAXLEN 15 //strlen("xxx.xxx.xxx.xxx")
#define IP6MAXLEN 39 //strlen("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:xxxx")
#define CBUF_SZ (IP6MAXLEN*2)
#define INITBUFSIZE 4096 //xxx need more space in case text expands due to IP scrambling
#if HAVE__U6_ADDR32
#define s6_addr32 __u6_addr.__u6_addr32
#endif
#if HAVE_REGEX_H
static const char REGEX4[]="((25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?))";
static const char REGEX6[]="(((([0-9A-Fa-f]{1,4}:){7}([0-9A-Fa-f]{1,4}|:))|(([0-9A-Fa-f]{1,4}:){6}(:[0-9A-Fa-f]{1,4}|((25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])(\\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])){3})|:))|(([0-9A-Fa-f]{1,4}:){5}(((:[0-9A-Fa-f]{1,4}){1,2})|:((25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])(\\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])){3})|:))|(([0-9A-Fa-f]{1,4}:){4}(((:[0-9A-Fa-f]{1,4}){1,3})|((:[0-9A-Fa-f]{1,4})?:((25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])(\\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])){3}))|:))|(([0-9A-Fa-f]{1,4}:){3}(((:[0-9A-Fa-f]{1,4}){1,4})|((:[0-9A-Fa-f]{1,4}){0,2}:((25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])(\\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])){3}))|:))|(([0-9A-Fa-f]{1,4}:){2}(((:[0-9A-Fa-f]{1,4}){1,5})|((:[0-9A-Fa-f]{1,4}){0,3}:((25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])(\\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])){3}))|:))|(([0-9A-Fa-f]{1,4}:){1}(((:[0-9A-Fa-f]{1,4}){1,6})|((:[0-9A-Fa-f]{1,4}){0,4}:((25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])(\\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])){3}))|:))|(:(((:[0-9A-Fa-f]{1,4}){1,7})|((:[0-9A-Fa-f]{1,4}){0,5}:((25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])(\\.(25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9]?[0-9])){3}))|:)))(%.+)?)";
#endif //HAVE_REGEX_H
static int pass_bits4 = 0;
static int pass_bits6 = 0;
static int reverse_mode = 0;
//buffers for in/out processing
static char *linebuf1 = NULL,*linebuf2 = NULL;
static size_t linebuf1_sz = 0, linebuf2_sz = 0;
static char cbuf[CBUF_SZ];
void
usage(const char *pname) {
fprintf(stderr,
"Read IP addresses from stdin and print scrambled addresses on stdout\n"
"USAGE:\n"
"\t%s [OPTIONS] [-r] key_file\n"
"\tWhere OPTIONS are:\n"
"\t\t--newkey|-G generate a new key key_file\n"
"\t\t--type=TYPE crypto to use for key generation (valid only with --newkey option)\n"
"\t\t supported choices are: blowfish (default), aes, sha1, md5\n"
"\t\t--pass4=<num> pass <num> higher bits of ipv4 addresses through unchanged\n"
"\t\t--pass6=<num> pass <num> higher bits of ipv6 addresses through unchanged\n"
#if HAVE_REGEX_H
"\t\t--ip-prefix=<regex> all ips must be prefixed by this regex prefix (both ipv4 and ipv6)\n"
"\t\t--ip-suffix=<regex> all ips must be followed by this regex suffix (both ipv4 and ipv6)\n"
"\t\t-t text mode: read text from stdin and scramble all addresses\n"
"\t\t that can be found using regex (use with caution)\n"
#endif //HAVE_REGEX_H
"\t\t-r reverse-mode i.e. for unscrambling ip addresses\n"
, pname);
exit(1);
}
int
anon_ip4_txt(const char *oldip, char *newip) {
struct in_addr ip4, ip4s;
if (inet_pton(AF_INET, oldip, &ip4) <= 0) {
fprintf(stderr, "don't understand address (%s)\n", oldip);
#ifdef HAVE_STRLCPY
strlcpy(newip, oldip, INITBUFSIZE);
#else
strcpy(newip, oldip); //copy without changing
#endif
} else {
ip4s.s_addr = (reverse_mode)
? unscramble_ip4(ip4.s_addr, pass_bits4)
: scramble_ip4(ip4.s_addr, pass_bits4);
if (newip != inet_ntop(AF_INET, &ip4s, newip, 256)) {
perror("Error: can't print new address");
exit(1);
}
}
return strlen(newip);
}
int
anon_ip6_txt(const char *oldip, char *newip) {
struct in6_addr ip6;
if (inet_pton(AF_INET6, oldip, &ip6) <= 0) {
fprintf(stderr, "don't understand address (%s)\n", oldip);
#ifdef HAVE_STRLCPY
strlcpy(newip, oldip, INITBUFSIZE);
#else
strcpy(newip, oldip); //copy without changing
#endif
} else {
if (reverse_mode) {
unscramble_ip6(&ip6, pass_bits6);
} else {
scramble_ip6(&ip6, pass_bits6);
}
if (newip != inet_ntop(AF_INET6, &ip6, newip, 256)) {
perror("Error: can't print new address");
exit(1);
}
}
return strlen(newip);
}
//return the pointer in 'in' buffer where processing stopped
const char*
search_replace_ip(const char *in, char *out, const regex_t *r,
int (*anonf)(const char*, char*), size_t *outsz) {
const char *c = in;
char *c2 = out;
regmatch_t re_match[2];
//0th element is the whole thing (including prefix and suffix)
//1st element is the IP address
while (0 == regexec(r, c, 2, re_match, 0)) {
const char *cc=c;
if (re_match[1].rm_so != -1) {
const char *ipbeg = cc + re_match[1].rm_so;
const char *ipend = cc + re_match[1].rm_eo;
size_t copylen = ipbeg - c; //from prev match to this one, pass-thru, including prefix
//copy from c..(beg-1), advance both pointers
while (c2 - out + copylen >= *outsz) {
*outsz *= 2;
out = realloc(out, *outsz);
if (out == NULL) {
fprintf(stderr, "Error: run out of buffer space\n");
exit(1);
}
}
memcpy(c2, c, copylen);
c += copylen;
c2+= copylen;
char hold = *ipend; //store last character, we'll need temporarly replace it with '\0'
*(char*)ipend = '\0';
size_t anoniplen = anonf(c, c2);
*(char*)ipend = hold; //restore
c = ipend;
c2 += anoniplen;
}
}
//copy the rest
size_t copylen = strlen(c) + 1;
while (c2 - out + copylen >= *outsz) {
*outsz *= 2;
out = realloc(out, *outsz);
if (out == NULL) {
fprintf(stderr, "Error: run out of buffer space\n");
exit(1);
}
}
memcpy(c2, c, copylen);
return out;
}
int
main(int argc, char *argv[])
{
FILE *keyfile = NULL;
const char *keyfn = NULL;
const char *pname = argv[0];
int opt;
int text_mode = 0;
int opt_newkey = 0;
char *opt_keytype = NULL;
#if HAVE_REGEX_H
char *opt_ipprefix = NULL;
char *opt_ipsuffix = NULL;
char regex4[4096];
char regex6[4096];
#endif //HAVE_REGEX_H
scramble_crypt_t key_crypto = SCRAMBLE_BLOWFISH;
struct option long_options[] = {
{"newkey",0, NULL, 'G'},
{"help", 0, NULL, 'h'},
{"pass4", 1, NULL, PASS4},
{"pass6", 1, NULL, PASS6},
{"type", 1, NULL, KTYPE},
#if HAVE_REGEX_H
{"text", 0, NULL, 't'},
{"ip-prefix", 1, NULL, IPPREFIX},
{"ip-suffix", 1, NULL, IPSUFFIX},
#endif //HAVE_REGEX_H
};
while((opt = getopt_long(argc, argv,
"Ghr"
#if HAVE_REGEX_H
"t"
#endif //HAVE_REGEX_H
, long_options, NULL)) != EOF) {
switch(opt) {
/* long options first: */
case PASS4:
pass_bits4 = atoi(optarg);
if (pass_bits4 < 0 || pass_bits4 > 32) {
fprintf(stderr, "Error: --pass4 option argument must be within [0..32]\n");
exit(1);
}
break;
case PASS6:
pass_bits6 = atoi(optarg);
if (pass_bits6 < 0 || pass_bits6 > 128) {
fprintf(stderr, "Error: --pass6 option argument must be within [0..128]\n");
exit(1);
}
break;
case KTYPE:
opt_keytype = optarg;
if (strcmp(opt_keytype, "blowfish") == 0) {
key_crypto = SCRAMBLE_BLOWFISH;
} else if (strcmp(opt_keytype, "aes") == 0) {
key_crypto = SCRAMBLE_AES;
} else if (strcmp(opt_keytype, "sha1") == 0) {
key_crypto = SCRAMBLE_SHA1;
} else if (strcmp(opt_keytype, "md5") == 0) {
key_crypto = SCRAMBLE_MD5;
} else {
fprintf(stderr, "Error: unsupported crypto key type: '%s' (can be one of: blowfish, aes, sha1, md5)\n", opt_keytype);
exit(1);
}
break;
#if HAVE_REGEX_H
case IPPREFIX:
opt_ipprefix = optarg;
break;
case IPSUFFIX:
opt_ipsuffix = optarg;
break;
case 't':
text_mode = 1;
break;
#endif //HAVE_REGEX_H
/* short options: */
case 'G':
opt_newkey = 1;
break;
case 'h':
usage(pname);
/* never returns */
break;
case 'r':
reverse_mode = 1;
break;
default:
usage(pname);
}
}
argc -= optind;
argv += optind;
if (argc != 1) {
usage(pname);
}
keyfn = argv[0];
if (opt_newkey && (text_mode || reverse_mode || pass_bits4 || pass_bits6)) {
fprintf(stderr, "Error: --newkey or -G is mutually exclusive with other options.\n");
exit(1);
}
if (opt_keytype && !opt_newkey) {
fprintf(stderr, "Error: --type requires --newkey (-G) option.\n");
exit(1);
}
#if HAVE_REGEX_H
if (!text_mode && (opt_ipprefix != NULL || opt_ipsuffix != NULL)) {
fprintf(stderr, "--ip-prefix and --ipsuffix require text mode (-t).\n");
exit(1);
}
#endif //HAVE_REGEX_H
if ((keyfile = fopen(keyfn, "r")) == NULL) {
if (!opt_newkey) {
/* no keyfile, but supposed to exist */
fprintf(stderr, "Error: cannot open the key_file: '%s': %s\n", keyfn, strerror(errno));
exit(1);
}
} else {
if (opt_newkey) {
/* keyfile exists, but asked to make new one */
fprintf(stderr, "Error: keyfile '%s' already exists, remove it before trying to generate a new one.\n",
keyfn);
exit(1);
}
}
if (keyfile) fclose(keyfile);
if (scramble_init_from_file(keyfn, key_crypto, key_crypto, NULL) < 0) {
fprintf(stderr, "Error: can't initialize from keyfile '%s'\n", keyfn);
exit(1);
}
if (opt_newkey) {
//only generating mode
exit(0);
}
if (!text_mode && setvbuf(stdout, NULL, _IOLBF, 0) < 0) {
fprintf(stderr, "Error: setting line buffering: %s\n", strerror(errno));
exit(1);
}
#if 1 //HAVE_REGEX_H
if (text_mode) {
linebuf1_sz = INITBUFSIZE;
linebuf2_sz = INITBUFSIZE;
linebuf1 = malloc(linebuf1_sz);
linebuf2 = malloc(linebuf2_sz);
memset(regex4, 0, sizeof(regex4));
memset(regex6, 0, sizeof(regex6));
if (opt_ipprefix != NULL) {
strncat(regex4, opt_ipprefix, sizeof(regex4)-1);
strncat(regex6, opt_ipprefix, sizeof(regex6)-1);
}
strncat(regex4, REGEX4, sizeof(regex4)-1);
strncat(regex6, REGEX6, sizeof(regex6)-1);
if (opt_ipsuffix != NULL) {
strncat(regex4, opt_ipsuffix, sizeof(regex4)-1);
strncat(regex6, opt_ipsuffix, sizeof(regex6)-1);
}
if (regex4[sizeof(regex4)-1] != '\0' ||
regex6[sizeof(regex6)-1] != '\0') {
fprintf(stderr, "Error: regex for ip addresses is too long.");
exit(1);
}
regex_t r4, r6;
if (0 != regcomp(&r4, regex4, REG_EXTENDED|REG_NEWLINE))
exit(1);
if (0 != regcomp(&r6, regex6, REG_EXTENDED|REG_NEWLINE))
exit(1);
linebuf1[linebuf1_sz-1]='x'; //anything but zero
//xxx todo: use buffered reading/writing
while (fgets(linebuf1, linebuf1_sz, stdin) != NULL) {
//fgets adds a terminating '\0', reading stops after an EOF or a newline
if (linebuf1[linebuf1_sz-1] == '\0' && linebuf1[linebuf1_sz-2] != '\n') {
//filled the buffer, but no newline; xxx remove newline dependency
fprintf(stderr, "Error: input lines are too long; maximum supported is %zd.\n",
linebuf1_sz-1);
exit(1);
}
//read a full line, can be anonymized in full
linebuf2 = (char*)search_replace_ip(linebuf1, linebuf2, &r4, &anon_ip4_txt, &linebuf2_sz);
linebuf1 = (char*)search_replace_ip(linebuf2, linebuf1, &r6, &anon_ip6_txt, &linebuf1_sz);
//output
fputs(linebuf1, stdout);
}
regfree(&r4);
regfree(&r6);
free(linebuf1);
free(linebuf2);
return 0;
}
#endif
for (;;) {
int af;
int i;
int prefix = 0;
char *plen = NULL;
char *c;
struct in_addr ip4, ip4s;
struct in6_addr ip6, ip6s;
void *new = NULL;
// char *c2;
if (fgets(cbuf, CBUF_SZ, stdin) == NULL)
break;
for (i = strnlen(cbuf, CBUF_SZ-1)-1; i >= 0; --i) {
if (!isgraph(cbuf[i]))
cbuf[i] = '\0';
}
plen = NULL;
/* first see if this is a network */
if (NULL != (c = strchr(cbuf, '/'))) {
/* this is a network */
plen = c + 1;
if (!isdigit(*plen)) {
fprintf(stderr, "can't parse network prefix (%s)\n", cbuf);
continue;
}
*c = '\0';
prefix = atoi(plen);
}
/* first try ipv4 */
af= AF_INET;
if (inet_pton(af, cbuf, &ip4) <= 0) {
/* next try ipv6 */
af= AF_INET6;
if (inet_pton(af, cbuf, &ip6) <= 0) {
fprintf(stderr, "don't understand address (%s)\n", cbuf);
continue;
}
ip6s = ip6;
if (reverse_mode) {
unscramble_ip6(&ip6s, pass_bits6);
} else {
scramble_ip6(&ip6s, pass_bits6);
}
new = &ip6s;
/* if it was a network, zero out host bits */
if (plen && prefix < 128) {
int hostbits = 128 - prefix;
i = 3;
while (hostbits >= 32) {
ip6s.s6_addr32[i] = 0;
--i;
hostbits -= 32;
}
if (hostbits > 0) {
ip6s.s6_addr32[i] = htonl(ntohl(ip6s.s6_addr32[i])
& (0xffffffffUL << hostbits));
}
}
} else {
ip4s.s_addr = (reverse_mode)
? unscramble_ip4(ip4.s_addr, pass_bits4)
: scramble_ip4(ip4.s_addr, pass_bits4);
new = &ip4s;
/* if it was a network, zero out host bits */
if (plen && prefix < 32) {
int hostbits = 32 - prefix;
ip4s.s_addr = ntohl(ip4s.s_addr);
if (hostbits == 32)
ip4s.s_addr = 0;
else
ip4s.s_addr &= 0xffffffffUL << hostbits;
ip4s.s_addr = htonl(ip4s.s_addr);
}
}
if (cbuf != inet_ntop(af, new, cbuf, CBUF_SZ)) {
perror("Error: can't print new address");
exit(1);
}
printf("%s", cbuf);
if (plen)
printf("/%d", prefix);
printf("\n");
}
scramble_cleanup();
return 0;
}
|