head.c revision 108988 
1/*
2 * Copyright (c) 1980, 1993
3 *	The Regents of the University of California.  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 * 3. All advertising materials mentioning features or use of this software
14 *    must display the following acknowledgement:
15 *	This product includes software developed by the University of
16 *	California, Berkeley and its contributors.
17 * 4. Neither the name of the University nor the names of its contributors
18 *    may be used to endorse or promote products derived from this software
19 *    without specific prior written permission.
20 *
21 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
22 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
23 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
24 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
25 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
26 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
27 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
28 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
29 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
30 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
31 * SUCH DAMAGE.
32 */
33
34#ifndef lint
35#if 0
36static char sccsid[] = "@(#)head.c	8.2 (Berkeley) 4/20/95";
37#endif
38#endif /* not lint */
39#include <sys/cdefs.h>
40__FBSDID("$FreeBSD: head/usr.bin/mail/head.c 108988 2003-01-09 05:08:37Z mikeh $");
41
42#include "rcv.h"
43#include "extern.h"
44
45/*
46 * Mail -- a mail program
47 *
48 * Routines for processing and detecting headlines.
49 */
50
51/*
52 * See if the passed line buffer is a mail header.
53 * Return true if yes.  Note the extreme pains to
54 * accomodate all funny formats.
55 */
56int
57ishead(linebuf)
58	char linebuf[];
59{
60	struct headline hl;
61	char parbuf[BUFSIZ];
62
63	if (strncmp(linebuf, "From ", 5) != 0)
64		return (0);
65	parse(linebuf, &hl, parbuf);
66	if (hl.l_date == NULL) {
67		fail(linebuf, "No date field");
68		return (0);
69	}
70	if (!isdate(hl.l_date)) {
71		fail(linebuf, "Date field not legal date");
72		return (0);
73	}
74	/*
75	 * I guess we got it!
76	 */
77	return (1);
78}
79
80/*ARGSUSED*/
81void
82fail(linebuf, reason)
83	const char *linebuf, *reason;
84{
85
86	/*
87	if (value("debug") == NULL)
88		return;
89	fprintf(stderr, "\"%s\"\nnot a header because %s\n", linebuf, reason);
90	*/
91}
92
93/*
94 * Split a headline into its useful components.
95 * Copy the line into dynamic string space, then set
96 * pointers into the copied line in the passed headline
97 * structure.  Actually, it scans.
98 */
99void
100parse(line, hl, pbuf)
101	char line[], pbuf[];
102	struct headline *hl;
103{
104	char *cp, *sp;
105	char word[LINESIZE];
106
107	hl->l_from = NULL;
108	hl->l_tty = NULL;
109	hl->l_date = NULL;
110	cp = line;
111	sp = pbuf;
112	/*
113	 * Skip over "From" first.
114	 */
115	cp = nextword(cp, word);
116	/*
117	 * Check for missing return-path.
118	 */
119	if (isdate(cp)) {
120		hl->l_date = copyin(cp, &sp);
121		return;
122	}
123	cp = nextword(cp, word);
124	if (strlen(word) > 0)
125		hl->l_from = copyin(word, &sp);
126	if (cp != NULL && strncmp(cp, "tty", 3) == 0) {
127		cp = nextword(cp, word);
128		hl->l_tty = copyin(word, &sp);
129	}
130	if (cp != NULL)
131		hl->l_date = copyin(cp, &sp);
132}
133
134/*
135 * Copy the string on the left into the string on the right
136 * and bump the right (reference) string pointer by the length.
137 * Thus, dynamically allocate space in the right string, copying
138 * the left string into it.
139 */
140char *
141copyin(src, space)
142	char *src;
143	char **space;
144{
145	char *cp, *top;
146
147	top = cp = *space;
148	while ((*cp++ = *src++) != '\0')
149		;
150	*space = cp;
151	return (top);
152}
153
154/*
155 * Test to see if the passed string is a ctime(3) generated
156 * date string as documented in the manual.  The template
157 * below is used as the criterion of correctness.
158 * Also, we check for a possible trailing time zone using
159 * the tmztype template.
160 *
161 * If the mail file is created by Sys V (Solaris), there are
162 * no seconds in the time. If the mail is created by another
163 * program such as imapd, it might have timezone as
164 * <-|+>nnnn (-0800 for instance) at the end.
165 */
166
167/*
168 * 'A'	An upper case char
169 * 'a'	A lower case char
170 * ' '	A space
171 * '0'	A digit
172 * 'O'	A digit or space
173 * 'p'	A punctuation char
174 * 'P'	A punctuation char or space
175 * ':'	A colon
176 * 'N'	A new line
177 */
178
179static char *date_formats[] = {
180	"Aaa Aaa O0 00:00:00 0000",	   /* Mon Jan 01 23:59:59 2001 */
181	"Aaa Aaa O0 00:00:00 AAA 0000",	   /* Mon Jan 01 23:59:59 PST 2001 */
182	"Aaa Aaa O0 00:00:00 0000 p0000",  /* Mon Jan 01 23:59:59 2001 -0800 */
183	"Aaa Aaa O0 00:00 0000",	   /* Mon Jan 01 23:59 2001 */
184	"Aaa Aaa O0 00:00 AAA 0000",	   /* Mon Jan 01 23:59 PST 2001 */
185	"Aaa Aaa O0 00:00 0000 p0000",	   /* Mon Jan 01 23:59 2001 -0800 */
186	NULL
187};
188
189int
190isdate(date)
191	char date[];
192{
193	int i;
194
195	for(i = 0; date_formats[i] != NULL; i++) {
196		if (cmatch(date, date_formats[i]))
197			return (1);
198	}
199	return (0);
200}
201
202/*
203 * Match the given string (cp) against the given template (tp).
204 * Return 1 if they match, 0 if they don't
205 */
206int
207cmatch(cp, tp)
208	char *cp, *tp;
209{
210
211	while (*cp != '\0' && *tp != '\0')
212		switch (*tp++) {
213		case 'a':
214			if (!islower((unsigned char)*cp++))
215				return (0);
216			break;
217		case 'A':
218			if (!isupper((unsigned char)*cp++))
219				return (0);
220			break;
221		case ' ':
222			if (*cp++ != ' ')
223				return (0);
224			break;
225		case '0':
226			if (!isdigit((unsigned char)*cp++))
227				return (0);
228			break;
229		case 'O':
230			if (*cp != ' ' && !isdigit((unsigned char)*cp))
231				return (0);
232			cp++;
233			break;
234		case 'p':
235			if (!ispunct((unsigned char)*cp++))
236				return (0);
237			break;
238		case 'P':
239			if (*cp != ' ' && !ispunct((unsigned char)*cp))
240				return (0);
241			cp++;
242			break;
243		case ':':
244			if (*cp++ != ':')
245				return (0);
246			break;
247		case 'N':
248			if (*cp++ != '\n')
249				return (0);
250			break;
251		}
252	if (*cp != '\0' || *tp != '\0')
253		return (0);
254	return (1);
255}
256
257/*
258 * Collect a liberal (space, tab delimited) word into the word buffer
259 * passed.  Also, return a pointer to the next word following that,
260 * or NULL if none follow.
261 */
262char *
263nextword(wp, wbuf)
264	char *wp, *wbuf;
265{
266	int c;
267
268	if (wp == NULL) {
269		*wbuf = '\0';
270		return (NULL);
271	}
272	while ((c = *wp++) != '\0' && c != ' ' && c != '\t') {
273		*wbuf++ = c;
274		if (c == '"') {
275 			while ((c = *wp++) != '\0' && c != '"')
276 				*wbuf++ = c;
277 			if (c == '"')
278 				*wbuf++ = c;
279			else
280				wp--;
281 		}
282	}
283	*wbuf = '\0';
284	for (; c == ' ' || c == '\t'; c = *wp++)
285		;
286	if (c == '\0')
287		return (NULL);
288	return (wp - 1);
289}
290