about summary refs log tree commit diff
path: root/export.c
blob: b1f63b87194993a8b77fc76f7bd0511412aad9c1 (plain) (blame)
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
/* Copyright (C) 2020  C. McEnroe <june@causal.agency>
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <https://www.gnu.org/licenses/>.
 */

#include <err.h>
#include <inttypes.h>
#include <limits.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sysexits.h>
#include <time.h>
#include <unistd.h>

#include "archive.h"
#include "imap.h"

static const char *uidPath(uint32_t uid, const char *type) {
	static char buf[PATH_MAX];
	snprintf(buf, sizeof(buf), "UID/%" PRIu32 ".%s", uid, type);
	return buf;
}

static const char *messagePath(const char *messageID, const char *type) {
	static char buf[PATH_MAX];
	snprintf(buf, sizeof(buf), "message/%s.%s", messageID, type);
	return buf;
}

static void flatten(struct List *flat, struct List nested) {
	for (size_t i = 0; i < nested.len; ++i) {
		if (nested.ptr[i].type == List) {
			flatten(flat, nested.ptr[i].list);
		} else {
			listPush(flat, nested.ptr[i]);
		}
	}
}

enum Atom exportThreads(FILE *imap, struct List threads) {
	struct List uids = {0};
	flatten(&uids, threads);
	for (size_t i = uids.len - 1; i < uids.len; --i) {
		if (uids.ptr[i].type != Number) {
			errx(EX_PROTOCOL, "invalid thread UID");
		}
		uint32_t uid = uids.ptr[i].number;
		int error = 0;
		if (!error) error = access(uidPath(uid, "atom"), F_OK);
		if (!error) error = access(uidPath(uid, "html"), F_OK);
		if (!error) error = access(uidPath(uid, "mbox"), F_OK);
		if (!error) {
			uids.ptr[i] = uids.ptr[--uids.len];
		}
	}
	enum Atom tag = 0;
	if (!uids.len) goto done;

	tag = atom("exportThreads");
	fprintf(imap, "%s UID FETCH ", Atoms[tag]);
	for (size_t i = 0; i < uids.len; ++i) {
		fprintf(imap, "%s%" PRIu32, (i ? "," : ""), uids.ptr[i].number);
	}
	fprintf(
		imap,
		" ("
		"UID ENVELOPE "
		"BODY[HEADER.FIELDS (" MBOX_HEADERS ")] BODY[TEXT]"
		")\r\n"
	);

done:
	listFree(uids);
	return tag;
}

static struct Address parseAddress(struct List list) {
	if (list.len < 4) {
		errx(EX_PROTOCOL, "missing address structure fields");
	}
	struct Address addr = {0};
	if (list.ptr[0].type == String) {
		// TODO: Decode UTF-8 in name.
		addr.name = strdup(list.ptr[0].string);
		if (!addr.name) err(EX_OSERR, "strdup");
	}
	if (list.ptr[2].type == String) addr.mailbox = list.ptr[2].string;
	if (list.ptr[3].type == String) addr.host = list.ptr[3].string;
	return addr;
}

static struct AddressList parseAddressList(struct List list) {
	struct Address *addrs = calloc(list.len, sizeof(*addrs));
	if (!addrs) err(EX_OSERR, "calloc");
	for (size_t i = 0; i < list.len; ++i) {
		if (list.ptr[i].type != List) {
			errx(EX_PROTOCOL, "invalid address field");
		}
		addrs[i] = parseAddress(list.ptr[i].list);
	}
	return (struct AddressList) { list.len, addrs };
}

static char *parseID(char *id) {
	size_t len = strlen(id);
	if (id[0] != '<' || !len || id[len - 1] != '>') {
		errx(EX_PROTOCOL, "invalid message ID");
	}
	id[len - 1] = '\0';
	return &id[1];
}

static struct Envelope parseEnvelope(struct List list) {
	enum {
		Date, Subject, From, Sender, ReplyTo,
		To, Cc, Bcc, InReplyTo, MessageID,
		EnvelopeLen,
	};
	if (list.len < EnvelopeLen) {
		errx(EX_PROTOCOL, "missing envelope structure fields");
	}
	struct Envelope envelope = {0};

	if (list.ptr[Date].type != String) {
		errx(EX_PROTOCOL, "invalid envelope date field");
	}
	const char *date = list.ptr[Date].string;
	date = strptime(date, "%a, %e %b %Y %H:%M:%S %z", &envelope.date);
	if (!date) errx(EX_PROTOCOL, "invalid envelope date format");

	envelope.date.tm_isdst = -1;
	envelope.utc = mktime(&envelope.date);

	if (list.ptr[Subject].type != String) {
		errx(EX_PROTOCOL, "invalid envelope subject field");
	}
	// TODO: Decode UTF-8 in subject.
	envelope.subject = strdup(list.ptr[Subject].string);
	if (!envelope.subject) err(EX_OSERR, "strdup");

	for (size_t i = From; i <= Bcc; ++i) {
		if (list.ptr[i].type == List) continue;
		if (list.ptr[i].type == Atom && list.ptr[i].atom == AtomNil) {
			list.ptr[i].type = List;
			list.ptr[i].list = (struct List) {0};
			continue;
		}
		errx(EX_PROTOCOL, "invalid envelope address field");
	}
	for (size_t i = From; i <= ReplyTo; ++i) {
		if (!list.ptr[i].list.len || list.ptr[i].list.ptr[0].type != List) {
			errx(EX_PROTOCOL, "invalid envelope address field");
		}
	}
	envelope.from = parseAddress(list.ptr[From].list.ptr[0].list);
	envelope.sender = parseAddress(list.ptr[Sender].list.ptr[0].list);
	envelope.replyTo = parseAddress(list.ptr[ReplyTo].list.ptr[0].list);
	envelope.to = parseAddressList(list.ptr[To].list);
	envelope.cc = parseAddressList(list.ptr[Cc].list);
	envelope.bcc = parseAddressList(list.ptr[Bcc].list);

	if (list.ptr[InReplyTo].type == String) {
		envelope.inReplyTo = parseID(list.ptr[InReplyTo].string);
	}
	if (list.ptr[MessageID].type != String) {
		errx(EX_PROTOCOL, "invalid envelope message-id field");
	}
	envelope.messageID = parseID(list.ptr[MessageID].string);

	return envelope;
}

static enum Atom AtomBody;
static enum Atom AtomEnvelope;
static enum Atom AtomHeaderFields;
static enum Atom AtomText;
static enum Atom AtomUID;

void exportData(struct List items) {
	if (!AtomBody) AtomBody = atom("BODY");
	if (!AtomEnvelope) AtomEnvelope = atom("ENVELOPE");
	if (!AtomHeaderFields) AtomHeaderFields = atom("HEADER.FIELDS");
	if (!AtomText) AtomText = atom("TEXT");
	if (!AtomUID) AtomUID = atom("UID");

	uint32_t uid = 0;
	struct Envelope envelope = {0};
	char *header = NULL;
	char *body = NULL;

	for (size_t i = 0; i + 1 < items.len; i += 2) {
		enum Atom name;
		if (items.ptr[i].type == Atom) {
			name = items.ptr[i].atom;
		} else if (
			items.ptr[i].type == List &&
			items.ptr[i].list.len &&
			items.ptr[i].list.ptr[0].type == Atom
		) {
			name = items.ptr[i].list.ptr[0].atom;
		} else {
			errx(EX_PROTOCOL, "invalid data item name");
		}

		if (name == AtomBody) {
			i--;
			continue;
		} else if (name == AtomUID) {
			if (items.ptr[i + 1].type != Number) {
				errx(EX_PROTOCOL, "invalid UID data item value");
			}
			uid = items.ptr[i + 1].number;
		} else if (name == AtomEnvelope) {
			if (items.ptr[i + 1].type != List) {
				errx(EX_PROTOCOL, "invalid ENVELOPE data item value");
			}
			envelope = parseEnvelope(items.ptr[i + 1].list);
		} else if (name == AtomHeaderFields) {
			if (items.ptr[i + 1].type != String) {
				errx(EX_PROTOCOL, "invalid BODY[HEADER.FIELDS] data item value");
			}
			header = items.ptr[i + 1].string;
		} else if (name == AtomText) {
			if (items.ptr[i + 1].type != String) {
				errx(EX_PROTOCOL, "invalid BODY[TEXT] data item value");
			}
			body = items.ptr[i + 1].string;
		}
	}

	if (!uid) errx(EX_PROTOCOL, "missing UID data item");
	if (!envelope.subject) errx(EX_PROTOCOL, "missing ENVELOPE data item");
	if (!header) errx(EX_PROTOCOL, "missing BODY[HEADER.FIELDS] data item");
	if (!body) errx(EX_PROTOCOL, "missing BODY[TEXT] data item");

	const char *path;
	FILE *file;
	int error;

	path = uidPath(uid, "mbox");
	file = fopen(path, "w");
	if (!file) err(EX_CANTCREAT, "%s", path);
	error = mboxFrom(file)
		|| mboxHeader(file, header)
		|| mboxBody(file, body)
		|| fclose(file);
	if (error) err(EX_IOERR, "%s", path);

	const char *dest = messagePath(envelope.messageID, "mbox");
	error = link(path, dest);
	if (error) err(EX_CANTCREAT, "%s", dest);

	path = uidPath(uid, "html");
	file = fopen(path, "w");
	if (!file) err(EX_CANTCREAT, "%s", path);
	error = htmlEnvelope(file, &envelope)
		|| fclose(file);
	if (error) err(EX_IOERR, "%s", path);

	path = uidPath(uid, "atom");
	file = fopen(path, "w");
	if (!file) err(EX_CANTCREAT, "%s", path);
	error = atomEnvelope(file, &envelope)
		|| fclose(file);
	if (error) err(EX_IOERR, "%s", path);

	envelopeFree(envelope);
}