1 /* $NetBSD: head.c,v 1.24 2013/01/16 15:21:42 christos Exp $ */
2
3 /*
4 * Copyright (c) 1980, 1993
5 * The Regents of the University of California. All rights reserved.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 * 3. Neither the name of the University nor the names of its contributors
16 * may be used to endorse or promote products derived from this software
17 * without specific prior written permission.
18 *
19 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
20 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
21 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
22 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
23 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
24 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
25 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
26 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
27 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
28 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
29 * SUCH DAMAGE.
30 */
31
32 #include <sys/cdefs.h>
33 #ifndef lint
34 #if 0
35 static char sccsid[] = "@(#)head.c 8.2 (Berkeley) 4/20/95";
36 #else
37 __RCSID("$NetBSD: head.c,v 1.24 2013/01/16 15:21:42 christos Exp $");
38 #endif
39 #endif /* not lint */
40
41 #include "rcv.h"
42 #include "extern.h"
43
44 /*
45 * Mail -- a mail program
46 *
47 * Routines for processing and detecting headlines.
48 */
49
50 /*
51 * Match the given string (cp) against the given template (tp).
52 * Return 1 if they match, 0 if they don't
53 */
54 static int
cmatch(const char * cp,const char * tp)55 cmatch(const char *cp, const char *tp)
56 {
57
58 while (*cp && *tp)
59 switch (*tp++) {
60 case 'a':
61 if (!islower((unsigned char)*cp++))
62 return 0;
63 break;
64 case 'A':
65 if (!isupper((unsigned char)*cp++))
66 return 0;
67 break;
68 case ' ':
69 if (*cp++ != ' ')
70 return 0;
71 break;
72 case '0':
73 if (!isdigit((unsigned char)*cp++))
74 return 0;
75 break;
76 case 'O':
77 if (*cp != ' ' && !isdigit((unsigned char)*cp))
78 return 0;
79 cp++;
80 break;
81 case ':':
82 if (*cp++ != ':')
83 return 0;
84 break;
85 case 'N':
86 if (*cp++ != '\n')
87 return 0;
88 break;
89 case '+':
90 if (*cp != '+' && *cp != '-')
91 return 0;
92 cp++;
93 break;
94 }
95 if (*cp || *tp)
96 return 0;
97 return 1;
98 }
99
100 /*
101 * Test to see if the passed string is a ctime(3) generated
102 * date string as documented in the manual. The template
103 * below is used as the criterion of correctness.
104 * Also, we check for a possible trailing time zone using
105 * the tmztype template.
106 */
107
108 /*
109 * 'A' An upper case char
110 * 'a' A lower case char
111 * ' ' A space
112 * '0' A digit
113 * 'O' An optional digit or space
114 * ':' A colon
115 * 'N' A new line
116 * '+' A plus or minus sign
117 */
118 static struct cmatch_data {
119 size_t tlen;
120 char const *tdata;
121 } const cmatch_data[] = {
122 #define TSZ(a) (sizeof(a) - 1), a
123 { TSZ("Aaa Aaa O0 00:00:00 0000") }, /* BSD ctype */
124 { TSZ("Aaa Aaa O0 00:00 0000") }, /* SysV ctype */
125 { TSZ("Aaa Aaa O0 00:00:00 AAA 0000") }, /* BSD tmztype */
126 { TSZ("Aaa Aaa O0 00:00 AAA 0000") }, /* SysV tmztype */
127 /*
128 * RFC 822-alike From_ lines do not conform to RFC 4155, but seem to
129 * be used in the wild by UW-imap (MBX format plus)
130 */
131 { TSZ("Aaa Aaa O0 00:00:00 0000 +0000") }, /* RFC822, UT offset */
132 /*
133 * RFC 822 with zone spec:
134 * 1. military,
135 * 2. UT,
136 * 3. north america time zone strings
137 * note that 1. is strictly speaking not correct as some letters are
138 * not used
139 */
140 { TSZ("Aaa Aaa O0 00:00:00 0000 A") },
141 { TSZ("Aaa Aaa O0 00:00:00 0000 AA") },
142 { TSZ("Aaa Aaa O0 00:00:00 0000 AAA") },
143 { 0, NULL },
144 };
145
146 static int
isdate(const char date[])147 isdate(const char date[])
148 {
149 static size_t cmatch_minlen = 0;
150 struct cmatch_data const *cmdp;
151 size_t dl = strlen(date);
152
153 if (cmatch_minlen == 0)
154 for (cmdp = cmatch_data; cmdp->tdata != NULL; ++cmdp)
155 cmatch_minlen = MIN(cmatch_minlen, cmdp->tlen);
156
157 if (dl < cmatch_minlen)
158 return 0;
159
160 for (cmdp = cmatch_data; cmdp->tdata != NULL; ++cmdp)
161 if (dl == cmdp->tlen && cmatch(date, cmdp->tdata))
162 return 1;
163
164 return 0;
165 }
166
167 static void
fail(const char linebuf[],const char reason[])168 fail(const char linebuf[], const char reason[])
169 {
170 #ifndef FMT_PROG
171 if (debug)
172 (void)fprintf(stderr, "\"%s\"\nnot a header because %s\n",
173 linebuf, reason);
174 #endif
175 }
176
177 /*
178 * Collect a liberal (space, tab delimited) word into the word buffer
179 * passed. Also, return a pointer to the next word following that,
180 * or NULL if none follow.
181 */
182 static const char *
nextword(const char * wp,char * wbuf)183 nextword(const char *wp, char *wbuf)
184 {
185 if (wp == NULL) {
186 *wbuf = 0;
187 return NULL;
188 }
189 while (*wp && !is_WSP(*wp)) {
190 *wbuf++ = *wp;
191 if (*wp++ == '"') {
192 while (*wp && *wp != '"')
193 *wbuf++ = *wp++;
194 if (*wp == '"')
195 *wbuf++ = *wp++;
196 }
197 }
198 *wbuf = '\0';
199 wp = skip_WSP(wp);
200 if (*wp == '\0')
201 return NULL;
202 return wp;
203 }
204
205 /*
206 * Copy the string on the left into the string on the right
207 * and bump the right (reference) string pointer by the length.
208 * Thus, dynamically allocate space in the right string, copying
209 * the left string into it.
210 */
211 static char *
copyin(const char * src,char ** space)212 copyin(const char *src, char **space)
213 {
214 char *cp;
215 char *begin;
216
217 begin = cp = *space;
218 while ((*cp++ = *src++) != '\0')
219 continue;
220 *space = cp;
221 return begin;
222 }
223
224 /*
225 * Split a headline into its useful components.
226 * Copy the line into dynamic string space, then set
227 * pointers into the copied line in the passed headline
228 * structure. Actually, it scans.
229 *
230 * XXX - line[], pbuf[], and word[] must be LINESIZE in length or
231 * overflow can occur in nextword() or copyin().
232 */
233 PUBLIC void
parse(const char line[],struct headline * hl,char pbuf[])234 parse(const char line[], struct headline *hl, char pbuf[])
235 {
236 const char *cp;
237 char *sp;
238 char word[LINESIZE];
239
240 hl->l_from = NULL;
241 hl->l_tty = NULL;
242 hl->l_date = NULL;
243 cp = line;
244 sp = pbuf;
245 /*
246 * Skip over "From" first.
247 */
248 cp = nextword(cp, word);
249 cp = nextword(cp, word);
250 if (*word)
251 hl->l_from = copyin(word, &sp);
252 if (cp != NULL && cp[0] == 't' && cp[1] == 't' && cp[2] == 'y') {
253 cp = nextword(cp, word);
254 hl->l_tty = copyin(word, &sp);
255 }
256 if (cp != NULL)
257 hl->l_date = copyin(cp, &sp);
258 }
259
260 /*
261 * See if the passed line buffer is a mail header.
262 * Return true if yes. Note the extreme pains to
263 * accommodate all funny formats.
264 */
265 PUBLIC int
ishead(const char linebuf[])266 ishead(const char linebuf[])
267 {
268 const char *cp;
269 struct headline hl;
270 char parbuf[LINESIZE];
271
272 cp = linebuf;
273 if (*cp++ != 'F' || *cp++ != 'r' || *cp++ != 'o' || *cp++ != 'm' ||
274 *cp++ != ' ')
275 return 0;
276 parse(linebuf, &hl, parbuf);
277 if (hl.l_from == NULL || hl.l_date == NULL) {
278 fail(linebuf, "No from or date field");
279 return 0;
280 }
281 if (!isdate(hl.l_date)) {
282 fail(linebuf, "Date field not legal date");
283 return 0;
284 }
285 /*
286 * I guess we got it!
287 */
288 return 1;
289 }
290