1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-10-28 12:59:41 +01:00
git/ident.c
Jeff King 4d9c7e6f45 am: reset cached ident date for each patch
When we compute the date to go in author/committer lines of
commits, or tagger lines of tags, we get the current date
once and then cache it for the rest of the program.  This is
a good thing in some cases, like "git commit", because it
means we do not racily assign different times to the
author/committer fields of a single commit object.

But as more programs start to make many commits in a single
process (e.g., the recently builtin "git am"), it means that
you'll get long strings of commits with identical committer
timestamps (whereas before, we invoked "git commit" many
times and got true timestamps).

This patch addresses it by letting callers reset the cached
time, which means they'll get a fresh time on their next
call to git_committer_info() or git_author_info(). The first
caller to do so is "git am", which resets the time for each
patch it applies.

It would be nice if we could just do this automatically
before filling in the ident fields of commit and tag
objects. Unfortunately, it's hard to know where a particular
logical operation begins and ends.

For instance, if commit_tree_extended() were to call
reset_ident_date() before getting the committer/author
ident, that doesn't quite work; sometimes the author info is
passed in to us as a parameter, and it may or may not have
come from a previous call to ident_default_date(). So in
those cases, we lose the property that the committer and the
author timestamp always match.

You could similarly put a date-reset at the end of
commit_tree_extended(). That actually works in the current
code base, but it's fragile. It makes the assumption that
after commit_tree_extended() finishes, the caller has no
other operations that would logically want to fall into the
same timestamp.

So instead we provide the tool to easily do the reset, and
let the high-level callers use it to annotate their own
logical operations.

There's no automated test, because it would be inherently
racy (it depends on whether the program takes multiple
seconds to run). But you can see the effect with something
like:

  # make a fake 100-patch series
  top=$(git rev-parse HEAD)
  bottom=$(git rev-list --first-parent -100 HEAD | tail -n 1)
  git log --format=email --reverse --first-parent \
          --binary -m -p $bottom..$top >patch

  # now apply it; this presumably takes multiple seconds
  git checkout --detach $bottom
  git am <patch

  # now count the number of distinct committer times;
  # prior to this patch, there would only be one, but
  # now we'd typically see several.
  git log --format=%ct $bottom.. | sort -u

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Helped-by: Paul Tan <pyokagan@gmail.com>
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-08-01 14:49:41 -07:00

524 lines
12 KiB
C

/*
* ident.c
*
* create git identifier lines of the form "name <email> date"
*
* Copyright (C) 2005 Linus Torvalds
*/
#include "cache.h"
static struct strbuf git_default_name = STRBUF_INIT;
static struct strbuf git_default_email = STRBUF_INIT;
static struct strbuf git_default_date = STRBUF_INIT;
static int default_email_is_bogus;
static int default_name_is_bogus;
static int ident_use_config_only;
#define IDENT_NAME_GIVEN 01
#define IDENT_MAIL_GIVEN 02
#define IDENT_ALL_GIVEN (IDENT_NAME_GIVEN|IDENT_MAIL_GIVEN)
static int committer_ident_explicitly_given;
static int author_ident_explicitly_given;
static int ident_config_given;
#ifdef NO_GECOS_IN_PWENT
#define get_gecos(ignored) "&"
#else
#define get_gecos(struct_passwd) ((struct_passwd)->pw_gecos)
#endif
static struct passwd *xgetpwuid_self(int *is_bogus)
{
struct passwd *pw;
errno = 0;
pw = getpwuid(getuid());
if (!pw) {
static struct passwd fallback;
fallback.pw_name = "unknown";
#ifndef NO_GECOS_IN_PWENT
fallback.pw_gecos = "Unknown";
#endif
pw = &fallback;
if (is_bogus)
*is_bogus = 1;
}
return pw;
}
static void copy_gecos(const struct passwd *w, struct strbuf *name)
{
char *src;
/* Traditionally GECOS field had office phone numbers etc, separated
* with commas. Also & stands for capitalized form of the login name.
*/
for (src = get_gecos(w); *src && *src != ','; src++) {
int ch = *src;
if (ch != '&')
strbuf_addch(name, ch);
else {
/* Sorry, Mr. McDonald... */
strbuf_addch(name, toupper(*w->pw_name));
strbuf_addstr(name, w->pw_name + 1);
}
}
}
static int add_mailname_host(struct strbuf *buf)
{
FILE *mailname;
struct strbuf mailnamebuf = STRBUF_INIT;
mailname = fopen("/etc/mailname", "r");
if (!mailname) {
if (errno != ENOENT)
warning("cannot open /etc/mailname: %s",
strerror(errno));
return -1;
}
if (strbuf_getline(&mailnamebuf, mailname) == EOF) {
if (ferror(mailname))
warning("cannot read /etc/mailname: %s",
strerror(errno));
strbuf_release(&mailnamebuf);
fclose(mailname);
return -1;
}
/* success! */
strbuf_addbuf(buf, &mailnamebuf);
strbuf_release(&mailnamebuf);
fclose(mailname);
return 0;
}
static int canonical_name(const char *host, struct strbuf *out)
{
int status = -1;
#ifndef NO_IPV6
struct addrinfo hints, *ai;
memset (&hints, '\0', sizeof (hints));
hints.ai_flags = AI_CANONNAME;
if (!getaddrinfo(host, NULL, &hints, &ai)) {
if (ai && strchr(ai->ai_canonname, '.')) {
strbuf_addstr(out, ai->ai_canonname);
status = 0;
}
freeaddrinfo(ai);
}
#else
struct hostent *he = gethostbyname(host);
if (he && strchr(he->h_name, '.')) {
strbuf_addstr(out, he->h_name);
status = 0;
}
#endif /* NO_IPV6 */
return status;
}
static void add_domainname(struct strbuf *out, int *is_bogus)
{
char buf[1024];
if (gethostname(buf, sizeof(buf))) {
warning("cannot get host name: %s", strerror(errno));
strbuf_addstr(out, "(none)");
*is_bogus = 1;
return;
}
if (strchr(buf, '.'))
strbuf_addstr(out, buf);
else if (canonical_name(buf, out) < 0) {
strbuf_addf(out, "%s.(none)", buf);
*is_bogus = 1;
}
}
static void copy_email(const struct passwd *pw, struct strbuf *email,
int *is_bogus)
{
/*
* Make up a fake email address
* (name + '@' + hostname [+ '.' + domainname])
*/
strbuf_addstr(email, pw->pw_name);
strbuf_addch(email, '@');
if (!add_mailname_host(email))
return; /* read from "/etc/mailname" (Debian) */
add_domainname(email, is_bogus);
}
const char *ident_default_name(void)
{
if (!git_default_name.len) {
copy_gecos(xgetpwuid_self(&default_name_is_bogus), &git_default_name);
strbuf_trim(&git_default_name);
}
return git_default_name.buf;
}
const char *ident_default_email(void)
{
if (!git_default_email.len) {
const char *email = getenv("EMAIL");
if (email && email[0]) {
strbuf_addstr(&git_default_email, email);
committer_ident_explicitly_given |= IDENT_MAIL_GIVEN;
author_ident_explicitly_given |= IDENT_MAIL_GIVEN;
} else
copy_email(xgetpwuid_self(&default_email_is_bogus),
&git_default_email, &default_email_is_bogus);
strbuf_trim(&git_default_email);
}
return git_default_email.buf;
}
static const char *ident_default_date(void)
{
if (!git_default_date.len)
datestamp(&git_default_date);
return git_default_date.buf;
}
void reset_ident_date(void)
{
strbuf_reset(&git_default_date);
}
static int crud(unsigned char c)
{
return c <= 32 ||
c == '.' ||
c == ',' ||
c == ':' ||
c == ';' ||
c == '<' ||
c == '>' ||
c == '"' ||
c == '\\' ||
c == '\'';
}
/*
* Copy over a string to the destination, but avoid special
* characters ('\n', '<' and '>') and remove crud at the end
*/
static void strbuf_addstr_without_crud(struct strbuf *sb, const char *src)
{
size_t i, len;
unsigned char c;
/* Remove crud from the beginning.. */
while ((c = *src) != 0) {
if (!crud(c))
break;
src++;
}
/* Remove crud from the end.. */
len = strlen(src);
while (len > 0) {
c = src[len-1];
if (!crud(c))
break;
--len;
}
/*
* Copy the rest to the buffer, but avoid the special
* characters '\n' '<' and '>' that act as delimiters on
* an identification line. We can only remove crud, never add it,
* so 'len' is our maximum.
*/
strbuf_grow(sb, len);
for (i = 0; i < len; i++) {
c = *src++;
switch (c) {
case '\n': case '<': case '>':
continue;
}
sb->buf[sb->len++] = c;
}
sb->buf[sb->len] = '\0';
}
/*
* Reverse of fmt_ident(); given an ident line, split the fields
* to allow the caller to parse it.
* Signal a success by returning 0, but date/tz fields of the result
* can still be NULL if the input line only has the name/email part
* (e.g. reading from a reflog entry).
*/
int split_ident_line(struct ident_split *split, const char *line, int len)
{
const char *cp;
size_t span;
int status = -1;
memset(split, 0, sizeof(*split));
split->name_begin = line;
for (cp = line; *cp && cp < line + len; cp++)
if (*cp == '<') {
split->mail_begin = cp + 1;
break;
}
if (!split->mail_begin)
return status;
for (cp = split->mail_begin - 2; line <= cp; cp--)
if (!isspace(*cp)) {
split->name_end = cp + 1;
break;
}
if (!split->name_end) {
/* no human readable name */
split->name_end = split->name_begin;
}
for (cp = split->mail_begin; cp < line + len; cp++)
if (*cp == '>') {
split->mail_end = cp;
break;
}
if (!split->mail_end)
return status;
/*
* Look from the end-of-line to find the trailing ">" of the mail
* address, even though we should already know it as split->mail_end.
* This can help in cases of broken idents with an extra ">" somewhere
* in the email address. Note that we are assuming the timestamp will
* never have a ">" in it.
*
* Note that we will always find some ">" before going off the front of
* the string, because will always hit the split->mail_end closing
* bracket.
*/
for (cp = line + len - 1; *cp != '>'; cp--)
;
for (cp = cp + 1; cp < line + len && isspace(*cp); cp++)
;
if (line + len <= cp)
goto person_only;
split->date_begin = cp;
span = strspn(cp, "0123456789");
if (!span)
goto person_only;
split->date_end = split->date_begin + span;
for (cp = split->date_end; cp < line + len && isspace(*cp); cp++)
;
if (line + len <= cp || (*cp != '+' && *cp != '-'))
goto person_only;
split->tz_begin = cp;
span = strspn(cp + 1, "0123456789");
if (!span)
goto person_only;
split->tz_end = split->tz_begin + 1 + span;
return 0;
person_only:
split->date_begin = NULL;
split->date_end = NULL;
split->tz_begin = NULL;
split->tz_end = NULL;
return 0;
}
static const char *env_hint =
"\n"
"*** Please tell me who you are.\n"
"\n"
"Run\n"
"\n"
" git config --global user.email \"you@example.com\"\n"
" git config --global user.name \"Your Name\"\n"
"\n"
"to set your account\'s default identity.\n"
"Omit --global to set the identity only in this repository.\n"
"\n";
const char *fmt_ident(const char *name, const char *email,
const char *date_str, int flag)
{
static struct strbuf ident = STRBUF_INIT;
int strict = (flag & IDENT_STRICT);
int want_date = !(flag & IDENT_NO_DATE);
int want_name = !(flag & IDENT_NO_NAME);
if (want_name) {
int using_default = 0;
if (!name) {
if (strict && ident_use_config_only
&& !(ident_config_given & IDENT_NAME_GIVEN)) {
fputs(env_hint, stderr);
die("no name was given and auto-detection is disabled");
}
name = ident_default_name();
using_default = 1;
if (strict && default_name_is_bogus) {
fputs(env_hint, stderr);
die("unable to auto-detect name (got '%s')", name);
}
}
if (!*name) {
struct passwd *pw;
if (strict) {
if (using_default)
fputs(env_hint, stderr);
die("empty ident name (for <%s>) not allowed", email);
}
pw = xgetpwuid_self(NULL);
name = pw->pw_name;
}
}
if (!email) {
if (strict && ident_use_config_only
&& !(ident_config_given & IDENT_MAIL_GIVEN)) {
fputs(env_hint, stderr);
die("no email was given and auto-detection is disabled");
}
email = ident_default_email();
if (strict && default_email_is_bogus) {
fputs(env_hint, stderr);
die("unable to auto-detect email address (got '%s')", email);
}
}
strbuf_reset(&ident);
if (want_name) {
strbuf_addstr_without_crud(&ident, name);
strbuf_addstr(&ident, " <");
}
strbuf_addstr_without_crud(&ident, email);
if (want_name)
strbuf_addch(&ident, '>');
if (want_date) {
strbuf_addch(&ident, ' ');
if (date_str && date_str[0]) {
if (parse_date(date_str, &ident) < 0)
die("invalid date format: %s", date_str);
}
else
strbuf_addstr(&ident, ident_default_date());
}
return ident.buf;
}
const char *fmt_name(const char *name, const char *email)
{
return fmt_ident(name, email, NULL, IDENT_STRICT | IDENT_NO_DATE);
}
const char *git_author_info(int flag)
{
if (getenv("GIT_AUTHOR_NAME"))
author_ident_explicitly_given |= IDENT_NAME_GIVEN;
if (getenv("GIT_AUTHOR_EMAIL"))
author_ident_explicitly_given |= IDENT_MAIL_GIVEN;
return fmt_ident(getenv("GIT_AUTHOR_NAME"),
getenv("GIT_AUTHOR_EMAIL"),
getenv("GIT_AUTHOR_DATE"),
flag);
}
const char *git_committer_info(int flag)
{
if (getenv("GIT_COMMITTER_NAME"))
committer_ident_explicitly_given |= IDENT_NAME_GIVEN;
if (getenv("GIT_COMMITTER_EMAIL"))
committer_ident_explicitly_given |= IDENT_MAIL_GIVEN;
return fmt_ident(getenv("GIT_COMMITTER_NAME"),
getenv("GIT_COMMITTER_EMAIL"),
getenv("GIT_COMMITTER_DATE"),
flag);
}
static int ident_is_sufficient(int user_ident_explicitly_given)
{
#ifndef WINDOWS
return (user_ident_explicitly_given & IDENT_MAIL_GIVEN);
#else
return (user_ident_explicitly_given == IDENT_ALL_GIVEN);
#endif
}
int committer_ident_sufficiently_given(void)
{
return ident_is_sufficient(committer_ident_explicitly_given);
}
int author_ident_sufficiently_given(void)
{
return ident_is_sufficient(author_ident_explicitly_given);
}
int git_ident_config(const char *var, const char *value, void *data)
{
if (!strcmp(var, "user.useconfigonly")) {
ident_use_config_only = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "user.name")) {
if (!value)
return config_error_nonbool(var);
strbuf_reset(&git_default_name);
strbuf_addstr(&git_default_name, value);
committer_ident_explicitly_given |= IDENT_NAME_GIVEN;
author_ident_explicitly_given |= IDENT_NAME_GIVEN;
ident_config_given |= IDENT_NAME_GIVEN;
return 0;
}
if (!strcmp(var, "user.email")) {
if (!value)
return config_error_nonbool(var);
strbuf_reset(&git_default_email);
strbuf_addstr(&git_default_email, value);
committer_ident_explicitly_given |= IDENT_MAIL_GIVEN;
author_ident_explicitly_given |= IDENT_MAIL_GIVEN;
ident_config_given |= IDENT_MAIL_GIVEN;
return 0;
}
return 0;
}
static int buf_cmp(const char *a_begin, const char *a_end,
const char *b_begin, const char *b_end)
{
int a_len = a_end - a_begin;
int b_len = b_end - b_begin;
int min = a_len < b_len ? a_len : b_len;
int cmp;
cmp = memcmp(a_begin, b_begin, min);
if (cmp)
return cmp;
return a_len - b_len;
}
int ident_cmp(const struct ident_split *a,
const struct ident_split *b)
{
int cmp;
cmp = buf_cmp(a->mail_begin, a->mail_end,
b->mail_begin, b->mail_end);
if (cmp)
return cmp;
return buf_cmp(a->name_begin, a->name_end,
b->name_begin, b->name_end);
}