git/ident.c

533 lines
12 KiB
C
Raw Normal View History

/*
* ident.c
*
* create git identifier lines of the form "name <email> date"
*
* Copyright (C) 2005 Linus Torvalds
*/
#include "cache.h"
#include "config.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)
ident: check /etc/mailname if email is unknown Before falling back to gethostname(), check /etc/mailname if GIT_AUTHOR_EMAIL is not set in the environment or through config files. Only fall back if /etc/mailname cannot be opened or read. The /etc/mailname convention comes from Debian policy section 11.6 ("mail transport, delivery and user agents"), though maybe it could be useful sometimes on other machines, too. The lack of this support was noticed by various people in different ways: - Ian observed that git was choosing the address 'ian@anarres.relativity.greenend.org.uk' rather than 'ian@davenant.greenend.org.uk' as it should have done. - Jonathan noticed that operations like "git commit" were needlessly slow when using a resolver that was slow to handle reverse DNS lookups. Alas, after this patch, if /etc/mailname is set up and the [user] name and email configuration aren't, the committer email will not provide a charming reminder of which machine commits were made on any more. But I think it's worth it. Mechanics: the functionality of reading mailname goes in its own function, so people who care about other distros can easily add an implementation to a similar location without making copy_email() too long and losing clarity. While at it, we split out the fallback default logic that does gethostname(), too (rearranging it a little and adding a check for errors from gethostname while at it). Based on a patch by Gerrit Pape <pape@smarden.org>. Requested-by: Ian Jackson <ijackson@chiark.greenend.org.uk> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-03 14:16:33 +08:00
{
FILE *mailname;
struct strbuf mailnamebuf = STRBUF_INIT;
ident: check /etc/mailname if email is unknown Before falling back to gethostname(), check /etc/mailname if GIT_AUTHOR_EMAIL is not set in the environment or through config files. Only fall back if /etc/mailname cannot be opened or read. The /etc/mailname convention comes from Debian policy section 11.6 ("mail transport, delivery and user agents"), though maybe it could be useful sometimes on other machines, too. The lack of this support was noticed by various people in different ways: - Ian observed that git was choosing the address 'ian@anarres.relativity.greenend.org.uk' rather than 'ian@davenant.greenend.org.uk' as it should have done. - Jonathan noticed that operations like "git commit" were needlessly slow when using a resolver that was slow to handle reverse DNS lookups. Alas, after this patch, if /etc/mailname is set up and the [user] name and email configuration aren't, the committer email will not provide a charming reminder of which machine commits were made on any more. But I think it's worth it. Mechanics: the functionality of reading mailname goes in its own function, so people who care about other distros can easily add an implementation to a similar location without making copy_email() too long and losing clarity. While at it, we split out the fallback default logic that does gethostname(), too (rearranging it a little and adding a check for errors from gethostname while at it). Based on a patch by Gerrit Pape <pape@smarden.org>. Requested-by: Ian Jackson <ijackson@chiark.greenend.org.uk> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-03 14:16:33 +08:00
mailname = fopen_or_warn("/etc/mailname", "r");
if (!mailname)
ident: check /etc/mailname if email is unknown Before falling back to gethostname(), check /etc/mailname if GIT_AUTHOR_EMAIL is not set in the environment or through config files. Only fall back if /etc/mailname cannot be opened or read. The /etc/mailname convention comes from Debian policy section 11.6 ("mail transport, delivery and user agents"), though maybe it could be useful sometimes on other machines, too. The lack of this support was noticed by various people in different ways: - Ian observed that git was choosing the address 'ian@anarres.relativity.greenend.org.uk' rather than 'ian@davenant.greenend.org.uk' as it should have done. - Jonathan noticed that operations like "git commit" were needlessly slow when using a resolver that was slow to handle reverse DNS lookups. Alas, after this patch, if /etc/mailname is set up and the [user] name and email configuration aren't, the committer email will not provide a charming reminder of which machine commits were made on any more. But I think it's worth it. Mechanics: the functionality of reading mailname goes in its own function, so people who care about other distros can easily add an implementation to a similar location without making copy_email() too long and losing clarity. While at it, we split out the fallback default logic that does gethostname(), too (rearranging it a little and adding a check for errors from gethostname while at it). Based on a patch by Gerrit Pape <pape@smarden.org>. Requested-by: Ian Jackson <ijackson@chiark.greenend.org.uk> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-03 14:16:33 +08:00
return -1;
if (strbuf_getline(&mailnamebuf, mailname) == EOF) {
ident: check /etc/mailname if email is unknown Before falling back to gethostname(), check /etc/mailname if GIT_AUTHOR_EMAIL is not set in the environment or through config files. Only fall back if /etc/mailname cannot be opened or read. The /etc/mailname convention comes from Debian policy section 11.6 ("mail transport, delivery and user agents"), though maybe it could be useful sometimes on other machines, too. The lack of this support was noticed by various people in different ways: - Ian observed that git was choosing the address 'ian@anarres.relativity.greenend.org.uk' rather than 'ian@davenant.greenend.org.uk' as it should have done. - Jonathan noticed that operations like "git commit" were needlessly slow when using a resolver that was slow to handle reverse DNS lookups. Alas, after this patch, if /etc/mailname is set up and the [user] name and email configuration aren't, the committer email will not provide a charming reminder of which machine commits were made on any more. But I think it's worth it. Mechanics: the functionality of reading mailname goes in its own function, so people who care about other distros can easily add an implementation to a similar location without making copy_email() too long and losing clarity. While at it, we split out the fallback default logic that does gethostname(), too (rearranging it a little and adding a check for errors from gethostname while at it). Based on a patch by Gerrit Pape <pape@smarden.org>. Requested-by: Ian Jackson <ijackson@chiark.greenend.org.uk> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-03 14:16:33 +08:00
if (ferror(mailname))
warning_errno("cannot read /etc/mailname");
strbuf_release(&mailnamebuf);
ident: check /etc/mailname if email is unknown Before falling back to gethostname(), check /etc/mailname if GIT_AUTHOR_EMAIL is not set in the environment or through config files. Only fall back if /etc/mailname cannot be opened or read. The /etc/mailname convention comes from Debian policy section 11.6 ("mail transport, delivery and user agents"), though maybe it could be useful sometimes on other machines, too. The lack of this support was noticed by various people in different ways: - Ian observed that git was choosing the address 'ian@anarres.relativity.greenend.org.uk' rather than 'ian@davenant.greenend.org.uk' as it should have done. - Jonathan noticed that operations like "git commit" were needlessly slow when using a resolver that was slow to handle reverse DNS lookups. Alas, after this patch, if /etc/mailname is set up and the [user] name and email configuration aren't, the committer email will not provide a charming reminder of which machine commits were made on any more. But I think it's worth it. Mechanics: the functionality of reading mailname goes in its own function, so people who care about other distros can easily add an implementation to a similar location without making copy_email() too long and losing clarity. While at it, we split out the fallback default logic that does gethostname(), too (rearranging it a little and adding a check for errors from gethostname while at it). Based on a patch by Gerrit Pape <pape@smarden.org>. Requested-by: Ian Jackson <ijackson@chiark.greenend.org.uk> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-03 14:16:33 +08:00
fclose(mailname);
return -1;
}
/* success! */
strbuf_addbuf(buf, &mailnamebuf);
strbuf_release(&mailnamebuf);
ident: check /etc/mailname if email is unknown Before falling back to gethostname(), check /etc/mailname if GIT_AUTHOR_EMAIL is not set in the environment or through config files. Only fall back if /etc/mailname cannot be opened or read. The /etc/mailname convention comes from Debian policy section 11.6 ("mail transport, delivery and user agents"), though maybe it could be useful sometimes on other machines, too. The lack of this support was noticed by various people in different ways: - Ian observed that git was choosing the address 'ian@anarres.relativity.greenend.org.uk' rather than 'ian@davenant.greenend.org.uk' as it should have done. - Jonathan noticed that operations like "git commit" were needlessly slow when using a resolver that was slow to handle reverse DNS lookups. Alas, after this patch, if /etc/mailname is set up and the [user] name and email configuration aren't, the committer email will not provide a charming reminder of which machine commits were made on any more. But I think it's worth it. Mechanics: the functionality of reading mailname goes in its own function, so people who care about other distros can easily add an implementation to a similar location without making copy_email() too long and losing clarity. While at it, we split out the fallback default logic that does gethostname(), too (rearranging it a little and adding a check for errors from gethostname while at it). Based on a patch by Gerrit Pape <pape@smarden.org>. Requested-by: Ian Jackson <ijackson@chiark.greenend.org.uk> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-03 14:16:33 +08:00
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)) {
ident: handle NULL ai_canonname We call getaddrinfo() to try to convert a short hostname into a fully-qualified one (to use it as an email domain). If there isn't a canonical name, getaddrinfo() will generally return either a NULL addrinfo list, or one in which ai->ai_canonname is a copy of the original name. However, if the result of gethostname() looks like an IP address, then getaddrinfo() behaves differently on some systems. On OS X, it will return a "struct addrinfo" with a NULL ai_canonname, and we segfault feeding it to strchr(). This is hard to test reliably because it involves not only a system where we we have to fallback to gethostname() to come up with an ident, but also where the hostname is a number with no dots. But I was able to replicate the bug by faking a hostname, like: diff --git a/ident.c b/ident.c index e20a772..b790d28 100644 --- a/ident.c +++ b/ident.c @@ -128,6 +128,7 @@ static void add_domainname(struct strbuf *out, int *is_bogus) *is_bogus = 1; return; } + xsnprintf(buf, sizeof(buf), "1"); if (strchr(buf, '.')) strbuf_addstr(out, buf); else if (canonical_name(buf, out) < 0) { and running "git var GIT_AUTHOR_IDENT" on an OS X system. Before this patch it segfaults, and after we correctly complain of the bogus "user@1.(none)" address (though this bogus address would be suitable for non-object uses like writing reflogs). Reported-by: Jonas Thiel <jonas.lierschied@gmx.de> Diagnosed-by: John Keeping <john@keeping.me.uk> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-09-23 12:37:53 +08:00
if (ai && ai->ai_canonname && 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)
ident: check /etc/mailname if email is unknown Before falling back to gethostname(), check /etc/mailname if GIT_AUTHOR_EMAIL is not set in the environment or through config files. Only fall back if /etc/mailname cannot be opened or read. The /etc/mailname convention comes from Debian policy section 11.6 ("mail transport, delivery and user agents"), though maybe it could be useful sometimes on other machines, too. The lack of this support was noticed by various people in different ways: - Ian observed that git was choosing the address 'ian@anarres.relativity.greenend.org.uk' rather than 'ian@davenant.greenend.org.uk' as it should have done. - Jonathan noticed that operations like "git commit" were needlessly slow when using a resolver that was slow to handle reverse DNS lookups. Alas, after this patch, if /etc/mailname is set up and the [user] name and email configuration aren't, the committer email will not provide a charming reminder of which machine commits were made on any more. But I think it's worth it. Mechanics: the functionality of reading mailname goes in its own function, so people who care about other distros can easily add an implementation to a similar location without making copy_email() too long and losing clarity. While at it, we split out the fallback default logic that does gethostname(), too (rearranging it a little and adding a check for errors from gethostname while at it). Based on a patch by Gerrit Pape <pape@smarden.org>. Requested-by: Ian Jackson <ijackson@chiark.greenend.org.uk> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-03 14:16:33 +08:00
{
char buf[HOST_NAME_MAX + 1];
ident: check /etc/mailname if email is unknown Before falling back to gethostname(), check /etc/mailname if GIT_AUTHOR_EMAIL is not set in the environment or through config files. Only fall back if /etc/mailname cannot be opened or read. The /etc/mailname convention comes from Debian policy section 11.6 ("mail transport, delivery and user agents"), though maybe it could be useful sometimes on other machines, too. The lack of this support was noticed by various people in different ways: - Ian observed that git was choosing the address 'ian@anarres.relativity.greenend.org.uk' rather than 'ian@davenant.greenend.org.uk' as it should have done. - Jonathan noticed that operations like "git commit" were needlessly slow when using a resolver that was slow to handle reverse DNS lookups. Alas, after this patch, if /etc/mailname is set up and the [user] name and email configuration aren't, the committer email will not provide a charming reminder of which machine commits were made on any more. But I think it's worth it. Mechanics: the functionality of reading mailname goes in its own function, so people who care about other distros can easily add an implementation to a similar location without making copy_email() too long and losing clarity. While at it, we split out the fallback default logic that does gethostname(), too (rearranging it a little and adding a check for errors from gethostname while at it). Based on a patch by Gerrit Pape <pape@smarden.org>. Requested-by: Ian Jackson <ijackson@chiark.greenend.org.uk> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-03 14:16:33 +08:00
if (xgethostname(buf, sizeof(buf))) {
warning_errno("cannot get host name");
strbuf_addstr(out, "(none)");
*is_bogus = 1;
ident: check /etc/mailname if email is unknown Before falling back to gethostname(), check /etc/mailname if GIT_AUTHOR_EMAIL is not set in the environment or through config files. Only fall back if /etc/mailname cannot be opened or read. The /etc/mailname convention comes from Debian policy section 11.6 ("mail transport, delivery and user agents"), though maybe it could be useful sometimes on other machines, too. The lack of this support was noticed by various people in different ways: - Ian observed that git was choosing the address 'ian@anarres.relativity.greenend.org.uk' rather than 'ian@davenant.greenend.org.uk' as it should have done. - Jonathan noticed that operations like "git commit" were needlessly slow when using a resolver that was slow to handle reverse DNS lookups. Alas, after this patch, if /etc/mailname is set up and the [user] name and email configuration aren't, the committer email will not provide a charming reminder of which machine commits were made on any more. But I think it's worth it. Mechanics: the functionality of reading mailname goes in its own function, so people who care about other distros can easily add an implementation to a similar location without making copy_email() too long and losing clarity. While at it, we split out the fallback default logic that does gethostname(), too (rearranging it a little and adding a check for errors from gethostname while at it). Based on a patch by Gerrit Pape <pape@smarden.org>. Requested-by: Ian Jackson <ijackson@chiark.greenend.org.uk> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-03 14:16:33 +08:00
return;
}
if (strchr(buf, '.'))
strbuf_addstr(out, buf);
else if (canonical_name(buf, out) < 0) {
strbuf_addf(out, "%s.(none)", buf);
*is_bogus = 1;
}
ident: check /etc/mailname if email is unknown Before falling back to gethostname(), check /etc/mailname if GIT_AUTHOR_EMAIL is not set in the environment or through config files. Only fall back if /etc/mailname cannot be opened or read. The /etc/mailname convention comes from Debian policy section 11.6 ("mail transport, delivery and user agents"), though maybe it could be useful sometimes on other machines, too. The lack of this support was noticed by various people in different ways: - Ian observed that git was choosing the address 'ian@anarres.relativity.greenend.org.uk' rather than 'ian@davenant.greenend.org.uk' as it should have done. - Jonathan noticed that operations like "git commit" were needlessly slow when using a resolver that was slow to handle reverse DNS lookups. Alas, after this patch, if /etc/mailname is set up and the [user] name and email configuration aren't, the committer email will not provide a charming reminder of which machine commits were made on any more. But I think it's worth it. Mechanics: the functionality of reading mailname goes in its own function, so people who care about other distros can easily add an implementation to a similar location without making copy_email() too long and losing clarity. While at it, we split out the fallback default logic that does gethostname(), too (rearranging it a little and adding a check for errors from gethostname while at it). Based on a patch by Gerrit Pape <pape@smarden.org>. Requested-by: Ian Jackson <ijackson@chiark.greenend.org.uk> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-03 14:16:33 +08:00
}
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))
ident: check /etc/mailname if email is unknown Before falling back to gethostname(), check /etc/mailname if GIT_AUTHOR_EMAIL is not set in the environment or through config files. Only fall back if /etc/mailname cannot be opened or read. The /etc/mailname convention comes from Debian policy section 11.6 ("mail transport, delivery and user agents"), though maybe it could be useful sometimes on other machines, too. The lack of this support was noticed by various people in different ways: - Ian observed that git was choosing the address 'ian@anarres.relativity.greenend.org.uk' rather than 'ian@davenant.greenend.org.uk' as it should have done. - Jonathan noticed that operations like "git commit" were needlessly slow when using a resolver that was slow to handle reverse DNS lookups. Alas, after this patch, if /etc/mailname is set up and the [user] name and email configuration aren't, the committer email will not provide a charming reminder of which machine commits were made on any more. But I think it's worth it. Mechanics: the functionality of reading mailname goes in its own function, so people who care about other distros can easily add an implementation to a similar location without making copy_email() too long and losing clarity. While at it, we split out the fallback default logic that does gethostname(), too (rearranging it a little and adding a check for errors from gethostname while at it). Based on a patch by Gerrit Pape <pape@smarden.org>. Requested-by: Ian Jackson <ijackson@chiark.greenend.org.uk> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Improved-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-03 14:16:33 +08:00
return; /* read from "/etc/mailname" (Debian) */
add_domainname(email, is_bogus);
}
const char *ident_default_name(void)
{
if (!(ident_config_given & IDENT_NAME_GIVEN) && !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 (!(ident_config_given & IDENT_MAIL_GIVEN) && !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;
}
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>
2016-08-02 03:37:00 +08:00
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 == '\'';
}
static int has_non_crud(const char *str)
{
for (; *str; str++) {
if (!crud(*str))
return 1;
}
return 0;
}
/*
* 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;
split_ident: parse timestamp from end of line Split_ident currently parses left to right. Given this input: Your Name <email@example.com> 123456789 -0500\n We assume the name starts the line and runs until the first "<". That starts the email address, which runs until the first ">". Everything after that is assumed to be the timestamp. This works fine in the normal case, but is easily broken by corrupted ident lines that contain an extra ">". Some examples seen in the wild are: 1. Name <email>-<> 123456789 -0500\n 2. Name <email> <Name<email>> 123456789 -0500\n 3. Name1 <email1>, Name2 <email2> 123456789 -0500\n Currently each of these produces some email address (which is not necessarily the one the user intended) and end up with a NULL date (which is generally interpreted as the epoch by "git log" and friends). But in each case we could get the correct timestamp simply by parsing from the right-hand side, looking backwards for the final ">", and then reading the timestamp from there. In general, it's a losing battle to try to automatically guess what the user meant with their broken crud. But this particular workaround is probably worth doing. One, it's dirt simple, and can't impact non-broken cases. Two, it doesn't catch a single breakage we've seen, but rather a large class of errors (i.e., any breakage inside the email angle brackets may affect the email, but won't spill over into the timestamp parsing). And three, the timestamp is arguably more valuable to get right, because it can affect correctness (e.g., in --until cutoffs). This patch implements the right-to-left scheme described above. We adjust the tests in t4212, which generate a commit with such a broken ident, and now gets the timestamp right. We also add a test that fsck continues to detect the breakage. For reference, here are pointers to the breakages seen (as numbered above): [1] http://article.gmane.org/gmane.comp.version-control.git/221441 [2] http://article.gmane.org/gmane.comp.version-control.git/222362 [3] http://perl5.git.perl.org/perl.git/commit/13b79730adea97e660de84bbe67f9d7cbe344302 Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-10-15 06:45:00 +08:00
/*
* 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_("\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");
Re-fix "builtin-commit: fix --signoff" An earlier fix to the said commit was incomplete; it mixed up the meaning of the flag parameter passed to the internal fmt_ident() function, so this corrects it. git_author_info() and git_committer_info() can be told to issue a warning when no usable user information is found, and optionally can be told to error out. Operations that actually use the information to record a new commit or a tag will still error out, but the caller to leave reflog record will just silently use bogus user information. Not warning on misconfigured user information while writing a reflog entry is somewhat debatable, but it is probably nicer to the users to silently let it pass, because the only information you are losing is who checked out the branch. * git_author_info() and git_committer_info() used to take 1 (positive int) to error out with a warning on misconfiguration; this is now signalled with a symbolic constant IDENT_ERROR_ON_NO_NAME. * These functions used to take -1 (negative int) to warn but continue; this is now signalled with a symbolic constant IDENT_WARN_ON_NO_NAME. * fmt_ident() function implements the above error reporting behaviour common to git_author_info() and git_committer_info(). A symbolic constant IDENT_NO_DATE can be or'ed in to the flag parameter to make it return only the "Name <email@address.xz>". * fmt_name() is a thin wrapper around fmt_ident() that always passes IDENT_ERROR_ON_NO_NAME and IDENT_NO_DATE. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-12-09 09:32:08 +08:00
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 (!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);
}
}
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 (strict && !has_non_crud(name))
die(_("name consists only of disallowed characters: %s"), name);
}
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);
}
Re-fix "builtin-commit: fix --signoff" An earlier fix to the said commit was incomplete; it mixed up the meaning of the flag parameter passed to the internal fmt_ident() function, so this corrects it. git_author_info() and git_committer_info() can be told to issue a warning when no usable user information is found, and optionally can be told to error out. Operations that actually use the information to record a new commit or a tag will still error out, but the caller to leave reflog record will just silently use bogus user information. Not warning on misconfigured user information while writing a reflog entry is somewhat debatable, but it is probably nicer to the users to silently let it pass, because the only information you are losing is who checked out the branch. * git_author_info() and git_committer_info() used to take 1 (positive int) to error out with a warning on misconfiguration; this is now signalled with a symbolic constant IDENT_ERROR_ON_NO_NAME. * These functions used to take -1 (negative int) to warn but continue; this is now signalled with a symbolic constant IDENT_WARN_ON_NO_NAME. * fmt_ident() function implements the above error reporting behaviour common to git_author_info() and git_committer_info(). A symbolic constant IDENT_NO_DATE can be or'ed in to the flag parameter to make it return only the "Name <email@address.xz>". * fmt_name() is a thin wrapper around fmt_ident() that always passes IDENT_ERROR_ON_NO_NAME and IDENT_NO_DATE. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-12-09 09:32:08 +08:00
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"),
Re-fix "builtin-commit: fix --signoff" An earlier fix to the said commit was incomplete; it mixed up the meaning of the flag parameter passed to the internal fmt_ident() function, so this corrects it. git_author_info() and git_committer_info() can be told to issue a warning when no usable user information is found, and optionally can be told to error out. Operations that actually use the information to record a new commit or a tag will still error out, but the caller to leave reflog record will just silently use bogus user information. Not warning on misconfigured user information while writing a reflog entry is somewhat debatable, but it is probably nicer to the users to silently let it pass, because the only information you are losing is who checked out the branch. * git_author_info() and git_committer_info() used to take 1 (positive int) to error out with a warning on misconfiguration; this is now signalled with a symbolic constant IDENT_ERROR_ON_NO_NAME. * These functions used to take -1 (negative int) to warn but continue; this is now signalled with a symbolic constant IDENT_WARN_ON_NO_NAME. * fmt_ident() function implements the above error reporting behaviour common to git_author_info() and git_committer_info(). A symbolic constant IDENT_NO_DATE can be or'ed in to the flag parameter to make it return only the "Name <email@address.xz>". * fmt_name() is a thin wrapper around fmt_ident() that always passes IDENT_ERROR_ON_NO_NAME and IDENT_NO_DATE. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-12-09 09:32:08 +08:00
flag);
}
Re-fix "builtin-commit: fix --signoff" An earlier fix to the said commit was incomplete; it mixed up the meaning of the flag parameter passed to the internal fmt_ident() function, so this corrects it. git_author_info() and git_committer_info() can be told to issue a warning when no usable user information is found, and optionally can be told to error out. Operations that actually use the information to record a new commit or a tag will still error out, but the caller to leave reflog record will just silently use bogus user information. Not warning on misconfigured user information while writing a reflog entry is somewhat debatable, but it is probably nicer to the users to silently let it pass, because the only information you are losing is who checked out the branch. * git_author_info() and git_committer_info() used to take 1 (positive int) to error out with a warning on misconfiguration; this is now signalled with a symbolic constant IDENT_ERROR_ON_NO_NAME. * These functions used to take -1 (negative int) to warn but continue; this is now signalled with a symbolic constant IDENT_WARN_ON_NO_NAME. * fmt_ident() function implements the above error reporting behaviour common to git_author_info() and git_committer_info(). A symbolic constant IDENT_NO_DATE can be or'ed in to the flag parameter to make it return only the "Name <email@address.xz>". * fmt_name() is a thin wrapper around fmt_ident() that always passes IDENT_ERROR_ON_NO_NAME and IDENT_NO_DATE. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-12-09 09:32:08 +08:00
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"),
Re-fix "builtin-commit: fix --signoff" An earlier fix to the said commit was incomplete; it mixed up the meaning of the flag parameter passed to the internal fmt_ident() function, so this corrects it. git_author_info() and git_committer_info() can be told to issue a warning when no usable user information is found, and optionally can be told to error out. Operations that actually use the information to record a new commit or a tag will still error out, but the caller to leave reflog record will just silently use bogus user information. Not warning on misconfigured user information while writing a reflog entry is somewhat debatable, but it is probably nicer to the users to silently let it pass, because the only information you are losing is who checked out the branch. * git_author_info() and git_committer_info() used to take 1 (positive int) to error out with a warning on misconfiguration; this is now signalled with a symbolic constant IDENT_ERROR_ON_NO_NAME. * These functions used to take -1 (negative int) to warn but continue; this is now signalled with a symbolic constant IDENT_WARN_ON_NO_NAME. * fmt_ident() function implements the above error reporting behaviour common to git_author_info() and git_committer_info(). A symbolic constant IDENT_NO_DATE can be or'ed in to the flag parameter to make it return only the "Name <email@address.xz>". * fmt_name() is a thin wrapper around fmt_ident() that always passes IDENT_ERROR_ON_NO_NAME and IDENT_NO_DATE. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-12-09 09:32:08 +08:00
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);
}