xref: /freebsd/usr.bin/mail/head.c (revision 22cf89c938886d14f5796fc49f9f020c23ea8eaf)
1 /*-
2  * SPDX-License-Identifier: BSD-3-Clause
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 #ifndef lint
33 #if 0
34 static char sccsid[] = "@(#)head.c	8.2 (Berkeley) 4/20/95";
35 #endif
36 #endif /* not lint */
37 #include <sys/cdefs.h>
38 #include "rcv.h"
39 #include "extern.h"
40 
41 /*
42  * Mail -- a mail program
43  *
44  * Routines for processing and detecting headlines.
45  */
46 
47 /*
48  * See if the passed line buffer is a mail header.
49  * Return true if yes.  Note the extreme pains to
50  * accommodate all funny formats.
51  */
52 int
53 ishead(char linebuf[])
54 {
55 	struct headline hl;
56 	char parbuf[BUFSIZ];
57 
58 	if (strncmp(linebuf, "From ", 5) != 0)
59 		return (0);
60 	parse(linebuf, &hl, parbuf);
61 	if (hl.l_date == NULL) {
62 		fail(linebuf, "No date field");
63 		return (0);
64 	}
65 	if (!isdate(hl.l_date)) {
66 		fail(linebuf, "Date field not legal date");
67 		return (0);
68 	}
69 	/*
70 	 * I guess we got it!
71 	 */
72 	return (1);
73 }
74 
75 void
76 fail(const char *linebuf __unused, const char *reason __unused)
77 {
78 
79 	/*
80 	if (value("debug") == NULL)
81 		return;
82 	fprintf(stderr, "\"%s\"\nnot a header because %s\n", linebuf, reason);
83 	*/
84 }
85 
86 /*
87  * Split a headline into its useful components.
88  * Copy the line into dynamic string space, then set
89  * pointers into the copied line in the passed headline
90  * structure.  Actually, it scans.
91  */
92 void
93 parse(char line[], struct headline *hl, char pbuf[])
94 {
95 	char *cp, *sp;
96 	char word[LINESIZE];
97 
98 	hl->l_from = NULL;
99 	hl->l_tty = NULL;
100 	hl->l_date = NULL;
101 	cp = line;
102 	sp = pbuf;
103 	/*
104 	 * Skip over "From" first.
105 	 */
106 	cp = nextword(cp, word);
107 	/*
108 	 * Check for missing return-path.
109 	 */
110 	if (isdate(cp)) {
111 		hl->l_date = copyin(cp, &sp);
112 		return;
113 	}
114 	cp = nextword(cp, word);
115 	if (strlen(word) > 0)
116 		hl->l_from = copyin(word, &sp);
117 	if (cp != NULL && strncmp(cp, "tty", 3) == 0) {
118 		cp = nextword(cp, word);
119 		hl->l_tty = copyin(word, &sp);
120 	}
121 	if (cp != NULL)
122 		hl->l_date = copyin(cp, &sp);
123 }
124 
125 /*
126  * Copy the string on the left into the string on the right
127  * and bump the right (reference) string pointer by the length.
128  * Thus, dynamically allocate space in the right string, copying
129  * the left string into it.
130  */
131 char *
132 copyin(char *src, char **space)
133 {
134 	char *cp, *top;
135 
136 	top = cp = *space;
137 	while ((*cp++ = *src++) != '\0')
138 		;
139 	*space = cp;
140 	return (top);
141 }
142 
143 /*
144  * Test to see if the passed string is a ctime(3) generated
145  * date string as documented in the manual.  The template
146  * below is used as the criterion of correctness.
147  * Also, we check for a possible trailing time zone using
148  * the tmztype template.
149  *
150  * If the mail file is created by Sys V (Solaris), there are
151  * no seconds in the time. If the mail is created by another
152  * program such as imapd, it might have timezone as
153  * <-|+>nnnn (-0800 for instance) at the end.
154  */
155 
156 /*
157  * 'A'	An upper case char
158  * 'a'	A lower case char
159  * ' '	A space
160  * '0'	A digit
161  * 'O'	A digit or space
162  * 'p'	A punctuation char
163  * 'P'	A punctuation char or space
164  * ':'	A colon
165  * 'N'	A new line
166  */
167 
168 static char *date_formats[] = {
169 	"Aaa Aaa O0 00:00:00 0000",	   /* Mon Jan 01 23:59:59 2001 */
170 	"Aaa Aaa O0 00:00:00 AAA 0000",	   /* Mon Jan 01 23:59:59 PST 2001 */
171 	"Aaa Aaa O0 00:00:00 0000 p0000",  /* Mon Jan 01 23:59:59 2001 -0800 */
172 	"Aaa Aaa O0 00:00 0000",	   /* Mon Jan 01 23:59 2001 */
173 	"Aaa Aaa O0 00:00 AAA 0000",	   /* Mon Jan 01 23:59 PST 2001 */
174 	"Aaa Aaa O0 00:00 0000 p0000",	   /* Mon Jan 01 23:59 2001 -0800 */
175 	NULL
176 };
177 
178 int
179 isdate(char date[])
180 {
181 	int i;
182 
183 	for(i = 0; date_formats[i] != NULL; i++) {
184 		if (cmatch(date, date_formats[i]))
185 			return (1);
186 	}
187 	return (0);
188 }
189 
190 /*
191  * Match the given string (cp) against the given template (tp).
192  * Return 1 if they match, 0 if they don't
193  */
194 int
195 cmatch(char *cp, char *tp)
196 {
197 
198 	while (*cp != '\0' && *tp != '\0')
199 		switch (*tp++) {
200 		case 'a':
201 			if (!islower((unsigned char)*cp++))
202 				return (0);
203 			break;
204 		case 'A':
205 			if (!isupper((unsigned char)*cp++))
206 				return (0);
207 			break;
208 		case ' ':
209 			if (*cp++ != ' ')
210 				return (0);
211 			break;
212 		case '0':
213 			if (!isdigit((unsigned char)*cp++))
214 				return (0);
215 			break;
216 		case 'O':
217 			if (*cp != ' ' && !isdigit((unsigned char)*cp))
218 				return (0);
219 			cp++;
220 			break;
221 		case 'p':
222 			if (!ispunct((unsigned char)*cp++))
223 				return (0);
224 			break;
225 		case 'P':
226 			if (*cp != ' ' && !ispunct((unsigned char)*cp))
227 				return (0);
228 			cp++;
229 			break;
230 		case ':':
231 			if (*cp++ != ':')
232 				return (0);
233 			break;
234 		case 'N':
235 			if (*cp++ != '\n')
236 				return (0);
237 			break;
238 		}
239 	if (*cp != '\0' || *tp != '\0')
240 		return (0);
241 	return (1);
242 }
243 
244 /*
245  * Collect a liberal (space, tab delimited) word into the word buffer
246  * passed.  Also, return a pointer to the next word following that,
247  * or NULL if none follow.
248  */
249 char *
250 nextword(char *wp, char *wbuf)
251 {
252 	int c;
253 
254 	if (wp == NULL) {
255 		*wbuf = '\0';
256 		return (NULL);
257 	}
258 	while ((c = *wp++) != '\0' && c != ' ' && c != '\t') {
259 		*wbuf++ = c;
260 		if (c == '"') {
261  			while ((c = *wp++) != '\0' && c != '"')
262  				*wbuf++ = c;
263  			if (c == '"')
264  				*wbuf++ = c;
265 			else
266 				wp--;
267  		}
268 	}
269 	*wbuf = '\0';
270 	for (; c == ' ' || c == '\t'; c = *wp++)
271 		;
272 	if (c == '\0')
273 		return (NULL);
274 	return (wp - 1);
275 }
276