about summary refs log tree commit diff
path: root/parsing.c
blob: f903c7c220285246faacfc1beeedb5081ffbf61b (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
/* parsing.c: parsing of config files
 *
 * Copyright (C) 2006-2014 cgit Development Team <cgit@lists.zx2c4.com>
 *
 * Licensed under GNU General Public License v2
 *   (see COPYING for full license text)
 */

#include "cgit.h"

/*
 * url syntax: [repo ['/' cmd [ '/' path]]]
 *   repo: any valid repo url, may contain '/'
 *   cmd:  log | commit | diff | tree | view | blob | snapshot
 *   path: any valid path, may contain '/'
 *
 */
void cgit_parse_url(const char *url)
{
	char *c, *cmd, *p;
	struct cgit_repo *repo;

	ctx.repo = NULL;
	if (!url || url[0] == '\0')
		return;

	ctx.repo = cgit_get_repoinfo(url);
	if (ctx.repo) {
		ctx.qry.repo = ctx.repo->url;
		return;
	}

	cmd = NULL;
	c = strchr(url, '/');
	while (c) {
		c[0] = '\0';
		repo = cgit_get_repoinfo(url);
		if (repo) {
			ctx.repo = repo;
			cmd = c;
		}
		c[0] = '/';
		c = strchr(c + 1, '/');
	}

	if (ctx.repo) {
		ctx.qry.repo = ctx.repo->url;
		p = strchr(cmd + 1, '/');
		if (p) {
			p[0] = '\0';
			if (p[1])
				ctx.qry.path = trim_end(p + 1, '/');
		}
		if (cmd[1])
			ctx.qry.page = xstrdup(cmd + 1);
		return;
	}
}

static char *substr(const char *head, const char *tail)
{
	char *buf;

	if (tail < head)
		return xstrdup("");
	buf = xmalloc(tail - head + 1);
	strncpy(buf, head, tail - head);
	buf[tail - head] = '\0';
	return buf;
}

static void parse_user(const char *t, char **name, char **email, unsigned long *date)
{
	struct ident_split ident;
	unsigned email_len;

	if (!split_ident_line(&ident, t, strchrnul(t, '\n') - t)) {
		*name = substr(ident.name_begin, ident.name_end);

		email_len = ident.mail_end - ident.mail_begin;
		*email = xmalloc(strlen("<") + email_len + strlen(">") + 1);
		sprintf(*email, "<%.*s>", email_len, ident.mail_begin);

		if (ident.date_begin)
			*date = strtoul(ident.date_begin, NULL, 10);
	}
}

#ifdef NO_ICONV
#define reencode(a, b, c)
#else
static const char *reencode(char **txt, const char *src_enc, const char *dst_enc)
{
	char *tmp;

	if (!txt)
		return NULL;

	if (!*txt || !src_enc || !dst_enc)
		return *txt;

	/* no encoding needed if src_enc equals dst_enc */
	if (!strcasecmp(src_enc, dst_enc))
		return *txt;

	tmp = reencode_string(*txt, dst_enc, src_enc);
	if (tmp) {
		free(*txt);
		*txt = tmp;
	}
	return *txt;
}
#endif

static const char *next_header_line(const char *p)
{
	p = strchr(p, '\n');
	if (!p)
		return NULL;
	return p + 1;
}

static int end_of_header(const char *p)
{
	return !p || (*p == '\n');
}

struct commitinfo *cgit_parse_commit(struct commit *commit)
{
	const int sha1hex_len = 40;
	struct commitinfo *ret;
	const char *p = get_cached_commit_buffer(commit, NULL);
	const char *t;

	ret = xcalloc(1, sizeof(struct commitinfo));
	ret->commit = commit;

	if (!p)
		return ret;

	if (!skip_prefix(p, "tree ", &p))
		die("Bad commit: %s", sha1_to_hex(commit->object.sha1));
	p += sha1hex_len + 1;

	while (skip_prefix(p, "parent ", &p))
		p += sha1hex_len + 1;

	if (p && skip_prefix(p, "author ", &p)) {
		parse_user(p, &ret->author, &ret->author_email,
			&ret->author_date);
		p = next_header_line(p);
	}

	if (p && skip_prefix(p, "committer ", &p)) {
		parse_user(p, &ret->committer, &ret->committer_email,
			&ret->committer_date);
		p = next_header_line(p);
	}

	if (p && skip_prefix(p, "encoding ", &p)) {
		t = strchr(p, '\n');
		if (t) {
			ret->msg_encoding = substr(p, t + 1);
			p = t + 1;
		}
	}

	if (!ret->msg_encoding)
		ret->msg_encoding = xstrdup("UTF-8");

	while (!end_of_header(p))
		p = next_header_line(p);
	while (p && *p == '\n')
		p++;
	if (!p)
		return ret;

	t = strchrnul(p, '\n');
	ret->subject = substr(p, t);
	while (*t == '\n')
		t++;
	ret->msg = xstrdup(t);

	reencode(&ret->author, ret->msg_encoding, PAGE_ENCODING);
	reencode(&ret->author_email, ret->msg_encoding, PAGE_ENCODING);
	reencode(&ret->committer, ret->msg_encoding, PAGE_ENCODING);
	reencode(&ret->committer_email, ret->msg_encoding, PAGE_ENCODING);
	reencode(&ret->subject, ret->msg_encoding, PAGE_ENCODING);
	reencode(&ret->msg, ret->msg_encoding, PAGE_ENCODING);

	return ret;
}

struct taginfo *cgit_parse_tag(struct tag *tag)
{
	void *data;
	enum object_type type;
	unsigned long size;
	const char *p;
	struct taginfo *ret = NULL;

	data = read_sha1_file(tag->object.sha1, &type, &size);
	if (!data || type != OBJ_TAG)
		goto cleanup;

	ret = xcalloc(1, sizeof(struct taginfo));

	for (p = data; !end_of_header(p); p = next_header_line(p)) {
		if (skip_prefix(p, "tagger ", &p)) {
			parse_user(p, &ret->tagger, &ret->tagger_email,
				&ret->tagger_date);
		}
	}

	while (p && *p == '\n')
		p++;

	if (p && *p)
		ret->msg = xstrdup(p);

cleanup:
	free(data);
	return ret;
}