aboutsummaryrefslogtreecommitdiffstats
path: root/rfc822.c
blob: 02910dfc95a67272c8c413a695181a649fbd11ed (plain)
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
/*
 * rfc822.c -- code for slicing and dicing RFC822 mail headers
 *
 * Copyright 1996 by Eric S. Raymond
 * All rights reserved.
 * For license terms, see the file COPYING in this directory.
 */

#include  <stdio.h>
#include  <ctype.h>
#include  <string.h>
#if defined(STDC_HEADERS)
#include  <stdlib.h>
#endif

#include  "fetchmail.h"

void reply_hack(buf, host)
/* hack message headers so replies will work properly */
char *buf;		/* header to be hacked */
const char *host;	/* server hostname */
{
    const char *from;
    int parendepth, state = 0, tokencount = 0;
    char mycopy[POPBUFSIZE+1];

    if (strncmp("From: ", buf, 6)
	&& strncmp("To: ", buf, 4)
	&& strncmp("Reply-", buf, 6)
	&& strncmp("Cc: ", buf, 4)
	&& strncmp("Bcc: ", buf, 5)) {
	return;
    }

    strcpy(mycopy, buf);
    for (from = mycopy; *from; from++)
    {
	switch (state)
	{
	case 0:   /* before header colon */
	    if (*from == ':')
		state = 1;
	    break;

	case 1:   /* we've seen the colon, we're looking for addresses */
	    if (*from == '"')
		state = 3;
	    else if (*from == '(')
	    {
		parendepth = 1;
		state = 4;    
	    }
	    else if (*from == '<' || isalnum(*from))
		state = 5;
	    else if (isspace(*from))
		state = 2;
	    break;

	case 2:	    /* found a token boundary -- reset without copying */
	    if (*from != ' ' && *from != '\t')
	    {
		tokencount++;
		state = 1;
		--from;
		continue;
	    }

	case 3:   /* we're in a quoted human name, copy and ignore */
	    if (*from == '"')
		state = 1;
	    break;

	case 4:   /* we're in a parenthesized human name, copy and ignore */
	    if (*from == '(')
		++parendepth;
	    else if (*from == ')')
		--parendepth;
	    if (parendepth == 0)
		state = 1;
	    break;

	case 5:   /* the real work gets done here */
	    /*
	     * We're in something that might be an address part,
	     * either a bare unquoted/unparenthesized text or text
	     * enclosed in <> as per RFC822.
	     */
	    /* if the address part contains an @, don't mess with it */
	    if (*from == '@')
		state = 6;

	    /* If the address token is not properly terminated, ignore it. */
	    else if (*from == ' ' || *from == '\t')
	    {
		const char *cp;

		/*
		 * The only lookahead case.  If we're looking at space or tab,
		 * we might be looking at a local name immediately followed
		 * by a human name.
		 */
		for (cp = from; isspace(*cp); cp++)
		    continue;
		if (*cp == '(')
		{
		    strcpy(buf, "@");
		    strcat(buf, host);
		    buf += strlen(buf);
		    state = 1;
		}
	    }

	    /*
	     * On proper termination with no @, insert hostname.
	     * Case '>' catches <>-enclosed mail IDs.  Case ',' catches
	     * comma-separated bare IDs.
	     */
	    else if (strchr(">,", *from))
	    {
		strcpy(buf, "@");
		strcat(buf, host);
		buf += strlen(buf);
		tokencount = 0;
		state = 1;
	    }

	    /* a single local name alone on the line */
	    else if (*from == '\n' && tokencount == 1)
	    {
		strcpy(buf, "@");
		strcat(buf, host);
		buf += strlen(buf);
		state = 2;
	    }

	    /* everything else, including alphanumerics, just passes through */
	    break;

	case 6:   /* we're in a remote mail ID, no need to append hostname */
	    if (*from == '>' || *from == ',' || isspace(*from))
		state = 1;
	    break;
	}

	/* all characters from the old buffer get copied to the new one */
	*buf++ = *from;
    }
    *buf++ = '\0';
}

char *nxtaddr(hdr)
/* parse addresses in succession out of a specified RFC822 header */
const char *hdr;	/* header to be parsed, NUL to continue previous hdr */
{
    static char *tp, address[POPBUFSIZE+1];
    static const char *hp;
    static int	state;
    int parendepth;

    /*
     * Note 1: RFC822 escaping with \ is *not* handled.  Note 2: it is
     * important that this routine not stop on \r, since we use \r as
     * a marker for RFC822 continuations elsewhere.
     */

    if (hdr)
    {
	hp = hdr;
	state = 0;
    }

    for (; *hp; hp++)
    {
	switch (state)
	{
	case 0:   /* before header colon */
	    if (*hp == '\n')
	    {
		state = 6;
		return(NULL);
	    }
	    else if (*hp == ':')
	    {
		state = 1;
		tp = address;
	    }
	    break;

	case 1:   /* we've seen the colon, now grab the address */
	    if (*hp == '\n')	/* end of address list */
	    {
	        *tp++ = '\0';
		state = 6;
		return(tp = address);
	    }
	    else if (*hp == ',')  /* end of address */
	    {
		if (tp > address)
		{
		    *tp++ = '\0';
		    ++hp;
		    return(tp = address);
		}
	    }
	    else if (*hp == '"') /* quoted string */
	    {
	        state = 2;
		*tp++ = *hp;
	    }
	    else if (*hp == '(') /* address comment -- ignore */
	    {
		parendepth = 1;
		state = 3;    
	    }
	    else if (*hp == '<') /* begin <address> */
	    {
		state = 4;
		tp = address;
	    }
	    else if (isspace(*hp)) /* ignore space */
	        state = 1;
	    else   /* just take it */
	    {
		state = 1;
		*tp++ = *hp;
	    }
	    break;

	case 2:   /* we're in a quoted string, copy verbatim */
	    if (*hp == '\n')
	    {
		state = 6;
		return(NULL);
	    }
	    if (*hp != '"')
	        *tp++ = *hp;
	    else if (*hp == '"')
	    {
	        *tp++ = *hp;
		state = 1;
	    }
	    break;

	case 3:   /* we're in a parenthesized comment, ignore */
	    if (*hp == '\n')
		return(NULL);
	    else if (*hp == '(')
		++parendepth;
	    else if (*hp == ')')
		--parendepth;
	    if (parendepth == 0)
		state = 1;
	    break;

	case 4:   /* possible <>-enclosed address */
	    if (*hp == '>') /* end of address */
	    {
		*tp++ = '\0';
		state = 1;
		++hp;
		return(tp = address);
	    }
	    else if (*hp == '<')  /* nested <> */
	        tp = address;
	    else if (*hp == '"') /* quoted address */
	    {
	        *tp++ = *hp;
		state = 5;
	    }
	    else  /* just copy address */
		*tp++ = *hp;
	    break;

	case 5:   /* we're in a quoted address, copy verbatim */
	    if (*hp == '\n')  /* mismatched quotes */
	    {
		state = 6;
		return(NULL);
	    }
	    if (*hp != '"')  /* just copy it if it isn't a quote */
	        *tp++ = *hp;
	    else if (*hp == '"')  /* end of quoted string */
	    {
	        *tp++ = *hp;
		state = 4;
	    }
	    break;

	case 6:	/* after last address */
	    return(NULL);
	    break;
	}
    }

    return(NULL);
}

#ifdef TESTMAIN
main(int argc, char *argv[])
{
    char	buf[POPBUFSIZE], *cp;

    while (fgets(buf, sizeof(buf)-1, stdin))
    {
	if (strncmp("From: ", buf, 6)
		    && strncmp("To: ", buf, 4)
		    && strncmp("Reply-", buf, 6)
		    && strncmp("Cc: ", buf, 4)
		    && strncmp("Bcc: ", buf, 5))
	    continue;
	else
	    if ((cp = nxtaddr(buf)) != (char *)NULL)
		do {
		    printf("Address: %s\n", cp);
		} while
		    ((cp = nxtaddr((char *)NULL)) != (char *)NULL);

    }
}
#endif /* TESTMAIN */

/* rfc822.c end */