|
diff --git a/parsing.c b/parsing.c index f37c49d..c9e4350 100644 --- a/ parsing.c+++ b/ parsing.c |
|
@@ -85,49 +85,53 @@ char *parse_user(char *t, char **name, char **email, unsigned long *date) |
85 | p++; |
85 | p++; |
86 | break; |
86 | break; |
87 | } else if (mode == 3 && isdigit(*p)) { |
87 | } else if (mode == 3 && isdigit(*p)) { |
88 | *date = atol(p); |
88 | *date = atol(p); |
89 | mode++; |
89 | mode++; |
90 | } else if (*p == '\n') { |
90 | } else if (*p == '\n') { |
91 | p++; |
91 | p++; |
92 | break; |
92 | break; |
93 | } |
93 | } |
94 | p++; |
94 | p++; |
95 | } |
95 | } |
96 | return p; |
96 | return p; |
97 | } |
97 | } |
98 | |
98 | |
99 | #ifdef NO_ICONV |
99 | #ifdef NO_ICONV |
100 | #define reencode(a, b, c) |
100 | #define reencode(a, b, c) |
101 | #else |
101 | #else |
102 | const char *reencode(char **txt, const char *src_enc, const char *dst_enc) |
102 | const char *reencode(char **txt, const char *src_enc, const char *dst_enc) |
103 | { |
103 | { |
104 | char *tmp; |
104 | char *tmp; |
105 | |
105 | |
106 | if (!txt || !*txt || !src_enc || !dst_enc) |
106 | if (!txt || !*txt || !src_enc || !dst_enc) |
107 | return *txt; |
107 | return *txt; |
108 | |
108 | |
109 | tmp = reencode_string(*txt, src_enc, dst_enc); |
109 | /* no encoding needed if src_enc equals dst_enc */ |
| |
110 | if(!strcasecmp(src_enc, dst_enc)) |
| |
111 | return *txt; |
| |
112 | |
| |
113 | tmp = reencode_string(*txt, dst_enc, src_enc); |
110 | if (tmp) { |
114 | if (tmp) { |
111 | free(*txt); |
115 | free(*txt); |
112 | *txt = tmp; |
116 | *txt = tmp; |
113 | } |
117 | } |
114 | return *txt; |
118 | return *txt; |
115 | } |
119 | } |
116 | #endif |
120 | #endif |
117 | |
121 | |
118 | struct commitinfo *cgit_parse_commit(struct commit *commit) |
122 | struct commitinfo *cgit_parse_commit(struct commit *commit) |
119 | { |
123 | { |
120 | struct commitinfo *ret; |
124 | struct commitinfo *ret; |
121 | char *p = commit->buffer, *t = commit->buffer; |
125 | char *p = commit->buffer, *t = commit->buffer; |
122 | |
126 | |
123 | ret = xmalloc(sizeof(*ret)); |
127 | ret = xmalloc(sizeof(*ret)); |
124 | ret->commit = commit; |
128 | ret->commit = commit; |
125 | ret->author = NULL; |
129 | ret->author = NULL; |
126 | ret->author_email = NULL; |
130 | ret->author_email = NULL; |
127 | ret->committer = NULL; |
131 | ret->committer = NULL; |
128 | ret->committer_email = NULL; |
132 | ret->committer_email = NULL; |
129 | ret->subject = NULL; |
133 | ret->subject = NULL; |
130 | ret->msg = NULL; |
134 | ret->msg = NULL; |
131 | ret->msg_encoding = NULL; |
135 | ret->msg_encoding = NULL; |
132 | |
136 | |
133 | if (p == NULL) |
137 | if (p == NULL) |
@@ -139,85 +143,87 @@ struct commitinfo *cgit_parse_commit(struct commit *commit) |
139 | p += 46; // "tree " + hex[40] + "\n" |
143 | p += 46; // "tree " + hex[40] + "\n" |
140 | |
144 | |
141 | while (!strncmp(p, "parent ", 7)) |
145 | while (!strncmp(p, "parent ", 7)) |
142 | p += 48; // "parent " + hex[40] + "\n" |
146 | p += 48; // "parent " + hex[40] + "\n" |
143 | |
147 | |
144 | if (p && !strncmp(p, "author ", 7)) { |
148 | if (p && !strncmp(p, "author ", 7)) { |
145 | p = parse_user(p + 7, &ret->author, &ret->author_email, |
149 | p = parse_user(p + 7, &ret->author, &ret->author_email, |
146 | &ret->author_date); |
150 | &ret->author_date); |
147 | } |
151 | } |
148 | |
152 | |
149 | if (p && !strncmp(p, "committer ", 9)) { |
153 | if (p && !strncmp(p, "committer ", 9)) { |
150 | p = parse_user(p + 9, &ret->committer, &ret->committer_email, |
154 | p = parse_user(p + 9, &ret->committer, &ret->committer_email, |
151 | &ret->committer_date); |
155 | &ret->committer_date); |
152 | } |
156 | } |
153 | |
157 | |
154 | if (p && !strncmp(p, "encoding ", 9)) { |
158 | if (p && !strncmp(p, "encoding ", 9)) { |
155 | p += 9; |
159 | p += 9; |
156 | t = strchr(p, '\n'); |
160 | t = strchr(p, '\n'); |
157 | if (t) { |
161 | if (t) { |
158 | ret->msg_encoding = substr(p, t + 1); |
162 | ret->msg_encoding = substr(p, t + 1); |
159 | p = t + 1; |
163 | p = t + 1; |
160 | } |
164 | } |
161 | } |
165 | } |
162 | |
166 | |
| |
167 | /* if no special encoding is found, assume UTF-8 */ |
| |
168 | if(!ret->msg_encoding) |
| |
169 | ret->msg_encoding = xstrdup("UTF-8"); |
| |
170 | |
163 | // skip unknown header fields |
171 | // skip unknown header fields |
164 | while (p && *p && (*p != '\n')) { |
172 | while (p && *p && (*p != '\n')) { |
165 | p = strchr(p, '\n'); |
173 | p = strchr(p, '\n'); |
166 | if (p) |
174 | if (p) |
167 | p++; |
175 | p++; |
168 | } |
176 | } |
169 | |
177 | |
170 | // skip empty lines between headers and message |
178 | // skip empty lines between headers and message |
171 | while (p && *p == '\n') |
179 | while (p && *p == '\n') |
172 | p++; |
180 | p++; |
173 | |
181 | |
174 | if (!p) |
182 | if (!p) |
175 | return ret; |
183 | return ret; |
176 | |
184 | |
177 | t = strchr(p, '\n'); |
185 | t = strchr(p, '\n'); |
178 | if (t) { |
186 | if (t) { |
179 | ret->subject = substr(p, t); |
187 | ret->subject = substr(p, t); |
180 | p = t + 1; |
188 | p = t + 1; |
181 | |
189 | |
182 | while (p && *p == '\n') { |
190 | while (p && *p == '\n') { |
183 | p = strchr(p, '\n'); |
191 | p = strchr(p, '\n'); |
184 | if (p) |
192 | if (p) |
185 | p++; |
193 | p++; |
186 | } |
194 | } |
187 | if (p) |
195 | if (p) |
188 | ret->msg = xstrdup(p); |
196 | ret->msg = xstrdup(p); |
189 | } else |
197 | } else |
190 | ret->subject = xstrdup(p); |
198 | ret->subject = xstrdup(p); |
191 | |
199 | |
192 | if (ret->msg_encoding) { |
200 | reencode(&ret->author, ret->msg_encoding, PAGE_ENCODING); |
193 | reencode(&ret->author, PAGE_ENCODING, ret->msg_encoding); |
201 | reencode(&ret->author_email, ret->msg_encoding, PAGE_ENCODING); |
194 | reencode(&ret->author_email, PAGE_ENCODING, ret->msg_encoding); |
202 | reencode(&ret->committer, ret->msg_encoding, PAGE_ENCODING); |
195 | reencode(&ret->committer, PAGE_ENCODING, ret->msg_encoding); |
203 | reencode(&ret->committer_email, ret->msg_encoding, PAGE_ENCODING); |
196 | reencode(&ret->committer_email, PAGE_ENCODING, ret->msg_encoding); |
204 | reencode(&ret->subject, ret->msg_encoding, PAGE_ENCODING); |
197 | reencode(&ret->subject, PAGE_ENCODING, ret->msg_encoding); |
205 | reencode(&ret->msg, ret->msg_encoding, PAGE_ENCODING); |
198 | reencode(&ret->msg, PAGE_ENCODING, ret->msg_encoding); |
| |
199 | } |
| |
200 | |
206 | |
201 | return ret; |
207 | return ret; |
202 | } |
208 | } |
203 | |
209 | |
204 | |
210 | |
205 | struct taginfo *cgit_parse_tag(struct tag *tag) |
211 | struct taginfo *cgit_parse_tag(struct tag *tag) |
206 | { |
212 | { |
207 | void *data; |
213 | void *data; |
208 | enum object_type type; |
214 | enum object_type type; |
209 | unsigned long size; |
215 | unsigned long size; |
210 | char *p; |
216 | char *p; |
211 | struct taginfo *ret; |
217 | struct taginfo *ret; |
212 | |
218 | |
213 | data = read_sha1_file(tag->object.sha1, &type, &size); |
219 | data = read_sha1_file(tag->object.sha1, &type, &size); |
214 | if (!data || type != OBJ_TAG) { |
220 | if (!data || type != OBJ_TAG) { |
215 | free(data); |
221 | free(data); |
216 | return 0; |
222 | return 0; |
217 | } |
223 | } |
218 | |
224 | |
219 | ret = xmalloc(sizeof(*ret)); |
225 | ret = xmalloc(sizeof(*ret)); |
220 | ret->tagger = NULL; |
226 | ret->tagger = NULL; |
221 | ret->tagger_email = NULL; |
227 | ret->tagger_email = NULL; |
222 | ret->tagger_date = 0; |
228 | ret->tagger_date = 0; |
223 | ret->msg = NULL; |
229 | ret->msg = NULL; |
|