@matheusbsbs / matheus-bagliano / commits / 388c7f8a27

mailmap: remove email copy and length limitation

In map_user(), we have email pointer that points at the beginning of an e-mail address, but the buffer is not terminated with a NUL after the e-mail address. It typically has ">" after the address, and it could have even more if it comes from author/committer line in a commit object. Or it may not have ">" after it. We used to copy the e-mail address proper into a temporary buffer before asking the string-list API to find the e-mail address in the mailmap, because string_list_lookup() function only takes a NUL terminated full string. Introduce a helper function lookup_prefix that takes the email pointer and the length, and finds a matching entry in the string list used for the mailmap, by doing the following: - First ask string_list_find_insert_index() where in its sorted list the e-mail address we have (including the possible trailing junk ">...") would be inserted. - It could find an exact match (e.g. we had a clean e-mail address without any trailing junk). We can return the item in that case. - Or it could return the index of an item that sorts after the e-mail address we have. - If we did not find an exact match against a clean e-mail address, then the record we are looking for in the mailmap has to exist before the index returned by the function (i.e. "email>junk" always sorts later than "email"). Iterate, starting from that index, down the map->items[] array until we find the exact record we are looking for, or we see a record with a key that definitely sorts earlier than the e-mail we are looking for (i.e. when we are looking for "email" in "email>junk", a record in the mailmap that begins with "emaik" strictly sorts before "email", if such a key existed in the mailmap). This, together with the earlier enhancement to support case-insensitive sorting, allow us to remove an extra copy of email buffer to downcase it. A part of this is based on Antoine Pelisse's previous work. Signed-off-by: Junio C Hamano <gitster@pobox.com>

Junio C Hamano committed Jan 5, 2013 at 22:26 UTC 388c7f8a275a40697cee2eec5fb124ae8457bf77

1 file changed +59 -16

mailmap.c

+59 -16

@@ -174,6 +174,7 @@ static int read_single_mailmap(struct string_list *map, const char *filename, ch

174 int read_mailmap(struct string_list *map, char **repo_abbrev)

175 {

176 map->strdup_strings = 1;

177 + map->cmp = strcasecmp;

178 /* each failure returns 1, so >1 means both calls failed */

179 return read_single_mailmap(map, ".mailmap", repo_abbrev) +

180 read_single_mailmap(map, git_mailmap_file, repo_abbrev) > 1;

@@ -187,14 +188,64 @@ void clear_mailmap(struct string_list *map)

188 debug_mm("mailmap: cleared\n");

189 }

190

191 +/*

192 + * Look for an entry in map that match string[0:len]; string[len]

193 + * does not have to be NUL (but it could be).

194 + */

195 +static struct string_list_item *lookup_prefix(struct string_list *map,

196 + const char *string, size_t len)

197 +{

198 + int i = string_list_find_insert_index(map, string, 1);

199 + if (i < 0) {

200 + /* exact match */

201 + i = -1 - i;

202 + if (!string[len])

203 + return &map->items[i];

204 + /*

205 + * that map entry matches exactly to the string, including

206 + * the cruft at the end beyond "len". That is not a match

207 + * with string[0:len] that we are looking for.

208 + */

209 + } else if (!string[len]) {

210 + /*

211 + * asked with the whole string, and got nothing. No

212 + * matching entry can exist in the map.

213 + */

214 + return NULL;

215 + }

216 +

217 + /*

218 + * i is at the exact match to an overlong key, or location the

219 + * overlong key would be inserted, which must come after the

220 + * real location of the key if one exists.

221 + */

222 + while (0 <= --i && i < map->nr) {

223 + int cmp = strncasecmp(map->items[i].string, string, len);

224 + if (cmp < 0)

225 + /*

226 + * "i" points at a key definitely below the prefix;

227 + * the map does not have string[0:len] in it.

228 + */

229 + break;

230 + else if (!cmp && !map->items[i].string[len])

231 + /* found it */

232 + return &map->items[i];

233 + /*

234 + * otherwise, the string at "i" may be string[0:len]

235 + * followed by a string that sorts later than string[len:];

236 + * keep trying.

237 + */

238 + }

239 + return NULL;

240 +}

241 +

242 int map_user(struct string_list *map,

243 char *email, int maxlen_email, char *name, int maxlen_name)

244 {

245 char *end_of_email;

246 struct string_list_item *item;

247 struct mailmap_entry *me;

196 - char buf[1024], *mailbuf;

197 - int i;

248 + size_t maillen;

249

250 /* figure out space requirement for email */

251 end_of_email = strchr(email, '>');

@@ -204,18 +255,12 @@ int map_user(struct string_list *map,

255 if (!end_of_email)

256 return 0;

257 }

207 - if (end_of_email - email + 1 < sizeof(buf))

208 - mailbuf = buf;

209 - else

210 - mailbuf = xmalloc(end_of_email - email + 1);

211 -

212 - /* downcase the email address */

213 - for (i = 0; i < end_of_email - email; i++)

214 - mailbuf[i] = tolower(email[i]);

215 - mailbuf[i] = 0;

216 -

217 - debug_mm("map_user: map '%s' <%s>\n", name, mailbuf);

218 - item = string_list_lookup(map, mailbuf);

258 +

259 + maillen = end_of_email - email;

260 +

261 + debug_mm("map_user: map '%s' <%.*s>\n", name, maillen, email);

262 +

263 + item = lookup_prefix(map, email, maillen);

264 if (item != NULL) {

265 me = (struct mailmap_entry *)item->util;

266 if (me->namemap.nr) {

@@ -226,8 +271,6 @@ int map_user(struct string_list *map,

271 item = subitem;

272 }

273 }

229 - if (mailbuf != buf)

230 - free(mailbuf);

274 if (item != NULL) {

275 struct mailmap_info *mi = (struct mailmap_info *)item->util;

276 if (mi->name == NULL && (mi->email == NULL || maxlen_email == 0)) {