git/mailmap.c
Ævar Arnfjörð Bjarmason 4e168333a8 shortlog: remove unused(?) "repo-abbrev" feature
Remove support for the magical "repo-abbrev" comment in .mailmap
files. This was added to .mailmap parsing in [1], as a generalized
feature of the git-shortlog Perl script added earlier in [2].

There was no documentation or tests for this feature, and I don't
think it's used in practice anymore.

What it did was to allow you to specify a single string to be
search-replaced with "/.../" in the .mailmap file. E.g. for
linux.git's current .mailmap:

    git archive --remote=git@gitlab.com:linux-kernel/linux.git \
        HEAD -- .mailmap | grep -a repo-abbrev
    # repo-abbrev: /pub/scm/linux/kernel/git/

Then when running e.g.:

    git shortlog --merges --author=Linus -1 v5.10-rc7..v5.10 | grep Merge

We'd emit (the [...] is mine):

      Merge tag [...]git://git.kernel.org/.../tip/tip

But will now emit:

      Merge tag [...]git.kernel.org/pub/scm/linux/kernel/git/tip/tip

I think at this point this is just a historical artifact we can get
rid of. It was initially meant for Linus's own use when we integrated
the Perl script[2], but since then it seems he's stopped using it.

Digging through Linus's release announcements on the LKML[3] the last
release I can find that made use of this output is Linux 2.6.25-rc6
back in March 2008[4]. Later on Linus started using --no-merges[5],
and nowadays seems to prefer some custom not-quite-shortlog format of
merges from lieutenants[6].

You will still see it on linux.git if you run "git shortlog" manually
yourself with --merges, with this removed you can still get the same
output with:

    git log --pretty=fuller v5.10-rc7..v5.10 |
    sed 's!/pub/scm/linux/kernel/git/!/.../!g' |
    git shortlog

Arguably we should do the same for the search-replacing of "[PATCH]"
at the beginning with "". That seems to be another relic of a bygone
era when linux.git patches would have their E-Mail subject lines
applied as-is by "git am" or whatever. But we documented that feature
in "git-shortlog(1)", and it seems more widely applicable than
something purely kernel-specific.

1. 7595e2ee6e (git-shortlog: make common repository prefix
   configurable with .mailmap, 2006-11-25)
2. fa375c7f1b (Add git-shortlog perl script, 2005-06-04)
3. https://lore.kernel.org/lkml/
4. https://lore.kernel.org/lkml/alpine.LFD.1.00.0803161651350.3020@woody.linux-foundation.org/
5. https://lore.kernel.org/lkml/BANLkTinrbh7Xi27an3uY7pDWrNKhJRYmEA@mail.gmail.com/
6. https://lore.kernel.org/lkml/CAHk-=wg1+kf1AVzXA-RQX0zjM6t9J2Kay9xyuNqcFHWV-y5ZYw@mail.gmail.com/

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-01-12 14:04:42 -08:00

342 lines
8.3 KiB
C

#include "cache.h"
#include "string-list.h"
#include "mailmap.h"
#include "object-store.h"
#define DEBUG_MAILMAP 0
#if DEBUG_MAILMAP
#define debug_mm(...) fprintf(stderr, __VA_ARGS__)
#define debug_str(X) ((X) ? (X) : "(none)")
#else
static inline void debug_mm(const char *format, ...) {}
static inline const char *debug_str(const char *s) { return s; }
#endif
const char *git_mailmap_file;
const char *git_mailmap_blob;
struct mailmap_info {
char *name;
char *email;
};
struct mailmap_entry {
/* name and email for the simple mail-only case */
char *name;
char *email;
/* name and email for the complex mail and name matching case */
struct string_list namemap;
};
static void free_mailmap_info(void *p, const char *s)
{
struct mailmap_info *mi = (struct mailmap_info *)p;
debug_mm("mailmap: -- complex: '%s' -> '%s' <%s>\n",
s, debug_str(mi->name), debug_str(mi->email));
free(mi->name);
free(mi->email);
}
static void free_mailmap_entry(void *p, const char *s)
{
struct mailmap_entry *me = (struct mailmap_entry *)p;
debug_mm("mailmap: removing entries for <%s>, with %d sub-entries\n",
s, me->namemap.nr);
debug_mm("mailmap: - simple: '%s' <%s>\n",
debug_str(me->name), debug_str(me->email));
free(me->name);
free(me->email);
me->namemap.strdup_strings = 1;
string_list_clear_func(&me->namemap, free_mailmap_info);
}
/*
* On some systems (e.g. MinGW 4.0), string.h has _only_ inline
* definition of strcasecmp and no non-inline implementation is
* supplied anywhere, which is, eh, "unusual"; we cannot take an
* address of such a function to store it in namemap.cmp. This is
* here as a workaround---do not assign strcasecmp directly to
* namemap.cmp until we know no systems that matter have such an
* "unusual" string.h.
*/
static int namemap_cmp(const char *a, const char *b)
{
return strcasecmp(a, b);
}
static void add_mapping(struct string_list *map,
char *new_name, char *new_email,
char *old_name, char *old_email)
{
struct mailmap_entry *me;
struct string_list_item *item;
if (old_email == NULL) {
old_email = new_email;
new_email = NULL;
}
item = string_list_insert(map, old_email);
if (item->util) {
me = (struct mailmap_entry *)item->util;
} else {
me = xcalloc(1, sizeof(struct mailmap_entry));
me->namemap.strdup_strings = 1;
me->namemap.cmp = namemap_cmp;
item->util = me;
}
if (old_name == NULL) {
debug_mm("mailmap: adding (simple) entry for '%s'\n", old_email);
/* Replace current name and new email for simple entry */
if (new_name) {
free(me->name);
me->name = xstrdup(new_name);
}
if (new_email) {
free(me->email);
me->email = xstrdup(new_email);
}
} else {
struct mailmap_info *mi = xcalloc(1, sizeof(struct mailmap_info));
debug_mm("mailmap: adding (complex) entry for '%s'\n", old_email);
mi->name = xstrdup_or_null(new_name);
mi->email = xstrdup_or_null(new_email);
string_list_insert(&me->namemap, old_name)->util = mi;
}
debug_mm("mailmap: '%s' <%s> -> '%s' <%s>\n",
debug_str(old_name), old_email,
debug_str(new_name), debug_str(new_email));
}
static char *parse_name_and_email(char *buffer, char **name,
char **email, int allow_empty_email)
{
char *left, *right, *nstart, *nend;
*name = *email = NULL;
if ((left = strchr(buffer, '<')) == NULL)
return NULL;
if ((right = strchr(left+1, '>')) == NULL)
return NULL;
if (!allow_empty_email && (left+1 == right))
return NULL;
/* remove whitespace from beginning and end of name */
nstart = buffer;
while (isspace(*nstart) && nstart < left)
++nstart;
nend = left-1;
while (nend > nstart && isspace(*nend))
--nend;
*name = (nstart <= nend ? nstart : NULL);
*email = left+1;
*(nend+1) = '\0';
*right++ = '\0';
return (*right == '\0' ? NULL : right);
}
static void read_mailmap_line(struct string_list *map, char *buffer)
{
char *name1 = NULL, *email1 = NULL, *name2 = NULL, *email2 = NULL;
if (buffer[0] == '#')
return;
if ((name2 = parse_name_and_email(buffer, &name1, &email1, 0)) != NULL)
parse_name_and_email(name2, &name2, &email2, 1);
if (email1)
add_mapping(map, name1, email1, name2, email2);
}
static int read_mailmap_file(struct string_list *map, const char *filename)
{
char buffer[1024];
FILE *f;
if (!filename)
return 0;
f = fopen(filename, "r");
if (!f) {
if (errno == ENOENT)
return 0;
return error_errno("unable to open mailmap at %s", filename);
}
while (fgets(buffer, sizeof(buffer), f) != NULL)
read_mailmap_line(map, buffer);
fclose(f);
return 0;
}
static void read_mailmap_string(struct string_list *map, char *buf)
{
while (*buf) {
char *end = strchrnul(buf, '\n');
if (*end)
*end++ = '\0';
read_mailmap_line(map, buf);
buf = end;
}
}
static int read_mailmap_blob(struct string_list *map, const char *name)
{
struct object_id oid;
char *buf;
unsigned long size;
enum object_type type;
if (!name)
return 0;
if (get_oid(name, &oid) < 0)
return 0;
buf = read_object_file(&oid, &type, &size);
if (!buf)
return error("unable to read mailmap object at %s", name);
if (type != OBJ_BLOB)
return error("mailmap is not a blob: %s", name);
read_mailmap_string(map, buf);
free(buf);
return 0;
}
int read_mailmap(struct string_list *map)
{
int err = 0;
map->strdup_strings = 1;
map->cmp = namemap_cmp;
if (!git_mailmap_blob && is_bare_repository())
git_mailmap_blob = "HEAD:.mailmap";
err |= read_mailmap_file(map, ".mailmap");
if (startup_info->have_repository)
err |= read_mailmap_blob(map, git_mailmap_blob);
err |= read_mailmap_file(map, git_mailmap_file);
return err;
}
void clear_mailmap(struct string_list *map)
{
debug_mm("mailmap: clearing %d entries...\n", map->nr);
map->strdup_strings = 1;
string_list_clear_func(map, free_mailmap_entry);
debug_mm("mailmap: cleared\n");
}
/*
* Look for an entry in map that match string[0:len]; string[len]
* does not have to be NUL (but it could be).
*/
static struct string_list_item *lookup_prefix(struct string_list *map,
const char *string, size_t len)
{
int i = string_list_find_insert_index(map, string, 1);
if (i < 0) {
/* exact match */
i = -1 - i;
if (!string[len])
return &map->items[i];
/*
* that map entry matches exactly to the string, including
* the cruft at the end beyond "len". That is not a match
* with string[0:len] that we are looking for.
*/
} else if (!string[len]) {
/*
* asked with the whole string, and got nothing. No
* matching entry can exist in the map.
*/
return NULL;
}
/*
* i is at the exact match to an overlong key, or location the
* overlong key would be inserted, which must come after the
* real location of the key if one exists.
*/
while (0 <= --i && i < map->nr) {
int cmp = strncasecmp(map->items[i].string, string, len);
if (cmp < 0)
/*
* "i" points at a key definitely below the prefix;
* the map does not have string[0:len] in it.
*/
break;
else if (!cmp && !map->items[i].string[len])
/* found it */
return &map->items[i];
/*
* otherwise, the string at "i" may be string[0:len]
* followed by a string that sorts later than string[len:];
* keep trying.
*/
}
return NULL;
}
int map_user(struct string_list *map,
const char **email, size_t *emaillen,
const char **name, size_t *namelen)
{
struct string_list_item *item;
struct mailmap_entry *me;
debug_mm("map_user: map '%.*s' <%.*s>\n",
(int)*namelen, debug_str(*name),
(int)*emaillen, debug_str(*email));
item = lookup_prefix(map, *email, *emaillen);
if (item != NULL) {
me = (struct mailmap_entry *)item->util;
if (me->namemap.nr) {
/*
* The item has multiple items, so we'll look up on
* name too. If the name is not found, we choose the
* simple entry.
*/
struct string_list_item *subitem;
subitem = lookup_prefix(&me->namemap, *name, *namelen);
if (subitem)
item = subitem;
}
}
if (item != NULL) {
struct mailmap_info *mi = (struct mailmap_info *)item->util;
if (mi->name == NULL && mi->email == NULL) {
debug_mm("map_user: -- (no simple mapping)\n");
return 0;
}
if (mi->email) {
*email = mi->email;
*emaillen = strlen(*email);
}
if (mi->name) {
*name = mi->name;
*namelen = strlen(*name);
}
debug_mm("map_user: to '%.*s' <%.*s>\n",
(int)*namelen, debug_str(*name),
(int)*emaillen, debug_str(*email));
return 1;
}
debug_mm("map_user: --\n");
return 0;
}