1 /*
2 * Copyright (C) 2003 Sean Chittenden <[email protected]>
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * 1. Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in the
12 * documentation and/or other materials provided with the distribution.
13 *
14 * THIS SOFTWARE IS PROVIDED BY THE PROJECT AND CONTRIBUTORS ``AS IS'' AND
15 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
16 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
17 * ARE DISCLAIMED. IN NO EVENT SHALL THE PROJECT OR CONTRIBUTORS BE LIABLE
18 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
19 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
20 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
21 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
22 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
23 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
24 * SUCH DAMAGE.
25 */
26
27 #include <sys/cdefs.h>
28 #include <sys/types.h>
29 #include <sys/param.h>
30
31 #include <ctype.h>
32 #include <err.h>
33 #include <errno.h>
34 #include <stdbool.h>
35 #include <stdlib.h>
36 #include <stdint.h>
37 #include <stdio.h>
38 #include <string.h>
39 #include <unistd.h>
40
41 #include "randomize_fd.h"
42
43 static struct rand_node *rand_root;
44 static struct rand_node *rand_tail;
45
46 static struct rand_node *
rand_node_allocate(void)47 rand_node_allocate(void)
48 {
49 struct rand_node *n;
50
51 n = (struct rand_node *)malloc(sizeof(struct rand_node));
52 if (n == NULL)
53 err(1, "malloc");
54
55 n->len = 0;
56 n->cp = NULL;
57 n->next = NULL;
58 return(n);
59 }
60
61 static void
rand_node_free(struct rand_node * n)62 rand_node_free(struct rand_node *n)
63 {
64 if (n != NULL) {
65 if (n->cp != NULL)
66 free(n->cp);
67
68 free(n);
69 }
70 }
71
72 static void
rand_node_free_rec(struct rand_node * n)73 rand_node_free_rec(struct rand_node *n)
74 {
75 if (n != NULL) {
76 if (n->next != NULL)
77 rand_node_free_rec(n->next);
78
79 rand_node_free(n);
80 }
81 }
82
83 static void
rand_node_append(struct rand_node * n)84 rand_node_append(struct rand_node *n)
85 {
86 if (rand_root == NULL)
87 rand_root = rand_tail = n;
88 else {
89 rand_tail->next = n;
90 rand_tail = n;
91 }
92 }
93
94 int
randomize_fd(int fd,int type,int unique,double denom)95 randomize_fd(int fd, int type, int unique, double denom)
96 {
97 u_char *buf;
98 u_int slen;
99 u_long i, j, numnode, selected;
100 struct rand_node *n, *prev;
101 int bufleft, eof, fndstr, ret;
102 size_t bufc, buflen;
103 ssize_t len;
104
105 rand_root = rand_tail = NULL;
106 bufc = i = 0;
107 bufleft = eof = fndstr = numnode = 0;
108
109 if (type == RANDOM_TYPE_UNSET)
110 type = RANDOM_TYPE_LINES;
111
112 buflen = sizeof(u_char) * MAXBSIZE;
113 buf = (u_char *)malloc(buflen);
114 if (buf == NULL)
115 err(1, "malloc");
116
117 while (!eof) {
118 /* Check to see if we have bits in the buffer */
119 if (bufleft == 0) {
120 len = read(fd, buf, buflen);
121 if (len == -1)
122 err(1, "read");
123 else if (len == 0) {
124 eof++;
125 break;
126 } else if ((size_t)len < buflen)
127 buflen = (size_t)len;
128
129 bufleft = (int)len;
130 }
131
132 /* Look for a newline */
133 for (i = bufc; i <= buflen && bufleft >= 0; i++, bufleft--) {
134 if (i == buflen) {
135 if (fndstr) {
136 if (!eof) {
137 memmove(buf, &buf[bufc], i - bufc);
138 i -= bufc;
139 bufc = 0;
140 len = read(fd, &buf[i], buflen - i);
141 if (len == -1)
142 err(1, "read");
143 else if (len == 0) {
144 eof++;
145 break;
146 } else if (len < (ssize_t)(buflen - i))
147 buflen = i + (size_t)len;
148
149 bufleft = (int)len;
150 fndstr = 0;
151 }
152 } else {
153 buflen *= 2;
154 buf = (u_char *)realloc(buf, buflen);
155 if (buf == NULL)
156 err(1, "realloc");
157
158 if (!eof) {
159 len = read(fd, &buf[i], buflen - i);
160 if (len == -1)
161 err(1, "read");
162 else if (len == 0) {
163 eof++;
164 break;
165 } else if (len < (ssize_t)(buflen - i))
166 buflen = i + (size_t)len;
167
168 bufleft = (int)len;
169 }
170
171 }
172 }
173
174 if ((type == RANDOM_TYPE_LINES && buf[i] == '\n') ||
175 (type == RANDOM_TYPE_WORDS && isspace(buf[i])) ||
176 (eof && i == buflen - 1)) {
177 make_token:
178 if (numnode == UINT32_MAX - 1) {
179 errno = EFBIG;
180 err(1, "too many delimiters");
181 }
182 numnode++;
183 n = rand_node_allocate();
184 if (-1 != (int)i) {
185 slen = i - (u_long)bufc;
186 n->len = slen + 2;
187 n->cp = (u_char *)malloc(slen + 2);
188 if (n->cp == NULL)
189 err(1, "malloc");
190
191 memmove(n->cp, &buf[bufc], slen);
192 n->cp[slen] = buf[i];
193 n->cp[slen + 1] = '\0';
194 bufc = i + 1;
195 }
196 rand_node_append(n);
197 fndstr = 1;
198 }
199 }
200 }
201
202 /* Necessary evil to compensate for files that don't end with a newline */
203 if (bufc != i) {
204 i--;
205 goto make_token;
206 }
207
208 (void)close(fd);
209
210 free(buf);
211
212 for (i = numnode; i > 0; i--) {
213 selected = arc4random_uniform(numnode);
214
215 for (j = 0, prev = n = rand_root; n != NULL; j++, prev = n, n = n->next) {
216 if (j == selected) {
217 if (n->cp == NULL)
218 break;
219
220 if (random_uniform_denom(denom)) {
221 ret = printf("%.*s",
222 (int)n->len - 1, n->cp);
223 if (ret < 0)
224 err(1, "printf");
225 }
226 if (unique) {
227 if (n == rand_root)
228 rand_root = n->next;
229 if (n == rand_tail)
230 rand_tail = prev;
231
232 prev->next = n->next;
233 rand_node_free(n);
234 numnode--;
235 }
236 break;
237 }
238 }
239 }
240
241 fflush(stdout);
242
243 if (!unique)
244 rand_node_free_rec(rand_root);
245
246 return(0);
247 }
248