git-commit-vandalism/builtin/log.c

1662 lines
43 KiB
C
Raw Normal View History

/*
* Builtin "git log" and related commands (show, whatchanged)
*
* (C) Copyright 2006 Linus Torvalds
* 2006 Junio Hamano
*/
#include "cache.h"
#include "color.h"
#include "commit.h"
#include "diff.h"
#include "revision.h"
#include "log-tree.h"
#include "builtin.h"
#include "tag.h"
#include "reflog-walk.h"
#include "patch-ids.h"
#include "run-command.h"
#include "shortlog.h"
#include "remote.h"
#include "string-list.h"
#include "parse-options.h"
Implement line-history search (git log -L) This is a rewrite of much of Bo's work, mainly in an effort to split it into smaller, easier to understand routines. The algorithm is built around the struct range_set, which encodes a series of line ranges as intervals [a,b). This is used in two contexts: * A set of lines we are tracking (which will change as we dig through history). * To encode diffs, as pairs of ranges. The main routine is range_set_map_across_diff(). It processes the diff between a commit C and some parent P. It determines which diff hunks are relevant to the ranges tracked in C, and computes the new ranges for P. The algorithm is then simply to process history in topological order from newest to oldest, computing ranges and (partial) diffs. At branch points, we need to merge the ranges we are watching. We will find that many commits do not affect the chosen ranges, and mark them TREESAME (in addition to those already filtered by pathspec limiting). Another pass of history simplification then gets rid of such commits. This is wired as an extra filtering pass in the log machinery. This currently only reduces code duplication, but should allow for other simplifications and options to be used. Finally, we hook a diff printer into the output chain. Ideally we would wire directly into the diff logic, to optionally use features like word diff. However, that will require some major reworking of the diff chain, so we completely replace the output with our own diff for now. As this was a GSoC project, and has quite some history by now, many people have helped. In no particular order, thanks go to Jakub Narebski <jnareb@gmail.com> Jens Lehmann <Jens.Lehmann@web.de> Jonathan Nieder <jrnieder@gmail.com> Junio C Hamano <gitster@pobox.com> Ramsay Jones <ramsay@ramsay1.demon.co.uk> Will Palmer <wmpalmer@gmail.com> Apologies to everyone I forgot. Signed-off-by: Bo Yang <struggleyb.nku@gmail.com> Signed-off-by: Thomas Rast <trast@student.ethz.ch> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-28 17:47:32 +01:00
#include "line-log.h"
#include "branch.h"
#include "streaming.h"
#include "version.h"
#include "mailmap.h"
#include "gpg-interface.h"
/* Set a default date-time format for git log ("log.date" config variable) */
static const char *default_date_mode = NULL;
static int default_abbrev_commit;
static int default_show_root = 1;
static int decoration_style;
static int decoration_given;
static int use_mailmap_config;
static const char *fmt_patch_subject_prefix = "PATCH";
static const char *fmt_pretty;
static const char * const builtin_log_usage[] = {
N_("git log [<options>] [<revision range>] [[--] <path>...]\n")
N_(" or: git show [options] <object>..."),
NULL
};
Implement line-history search (git log -L) This is a rewrite of much of Bo's work, mainly in an effort to split it into smaller, easier to understand routines. The algorithm is built around the struct range_set, which encodes a series of line ranges as intervals [a,b). This is used in two contexts: * A set of lines we are tracking (which will change as we dig through history). * To encode diffs, as pairs of ranges. The main routine is range_set_map_across_diff(). It processes the diff between a commit C and some parent P. It determines which diff hunks are relevant to the ranges tracked in C, and computes the new ranges for P. The algorithm is then simply to process history in topological order from newest to oldest, computing ranges and (partial) diffs. At branch points, we need to merge the ranges we are watching. We will find that many commits do not affect the chosen ranges, and mark them TREESAME (in addition to those already filtered by pathspec limiting). Another pass of history simplification then gets rid of such commits. This is wired as an extra filtering pass in the log machinery. This currently only reduces code duplication, but should allow for other simplifications and options to be used. Finally, we hook a diff printer into the output chain. Ideally we would wire directly into the diff logic, to optionally use features like word diff. However, that will require some major reworking of the diff chain, so we completely replace the output with our own diff for now. As this was a GSoC project, and has quite some history by now, many people have helped. In no particular order, thanks go to Jakub Narebski <jnareb@gmail.com> Jens Lehmann <Jens.Lehmann@web.de> Jonathan Nieder <jrnieder@gmail.com> Junio C Hamano <gitster@pobox.com> Ramsay Jones <ramsay@ramsay1.demon.co.uk> Will Palmer <wmpalmer@gmail.com> Apologies to everyone I forgot. Signed-off-by: Bo Yang <struggleyb.nku@gmail.com> Signed-off-by: Thomas Rast <trast@student.ethz.ch> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-28 17:47:32 +01:00
struct line_opt_callback_data {
struct rev_info *rev;
const char *prefix;
struct string_list args;
};
static int parse_decoration_style(const char *var, const char *value)
{
switch (git_config_maybe_bool(var, value)) {
case 1:
return DECORATE_SHORT_REFS;
case 0:
return 0;
default:
break;
}
if (!strcmp(value, "full"))
return DECORATE_FULL_REFS;
else if (!strcmp(value, "short"))
return DECORATE_SHORT_REFS;
return -1;
}
static int decorate_callback(const struct option *opt, const char *arg, int unset)
{
if (unset)
decoration_style = 0;
else if (arg)
decoration_style = parse_decoration_style("command line", arg);
else
decoration_style = DECORATE_SHORT_REFS;
if (decoration_style < 0)
die("invalid --decorate option: %s", arg);
decoration_given = 1;
return 0;
}
Implement line-history search (git log -L) This is a rewrite of much of Bo's work, mainly in an effort to split it into smaller, easier to understand routines. The algorithm is built around the struct range_set, which encodes a series of line ranges as intervals [a,b). This is used in two contexts: * A set of lines we are tracking (which will change as we dig through history). * To encode diffs, as pairs of ranges. The main routine is range_set_map_across_diff(). It processes the diff between a commit C and some parent P. It determines which diff hunks are relevant to the ranges tracked in C, and computes the new ranges for P. The algorithm is then simply to process history in topological order from newest to oldest, computing ranges and (partial) diffs. At branch points, we need to merge the ranges we are watching. We will find that many commits do not affect the chosen ranges, and mark them TREESAME (in addition to those already filtered by pathspec limiting). Another pass of history simplification then gets rid of such commits. This is wired as an extra filtering pass in the log machinery. This currently only reduces code duplication, but should allow for other simplifications and options to be used. Finally, we hook a diff printer into the output chain. Ideally we would wire directly into the diff logic, to optionally use features like word diff. However, that will require some major reworking of the diff chain, so we completely replace the output with our own diff for now. As this was a GSoC project, and has quite some history by now, many people have helped. In no particular order, thanks go to Jakub Narebski <jnareb@gmail.com> Jens Lehmann <Jens.Lehmann@web.de> Jonathan Nieder <jrnieder@gmail.com> Junio C Hamano <gitster@pobox.com> Ramsay Jones <ramsay@ramsay1.demon.co.uk> Will Palmer <wmpalmer@gmail.com> Apologies to everyone I forgot. Signed-off-by: Bo Yang <struggleyb.nku@gmail.com> Signed-off-by: Thomas Rast <trast@student.ethz.ch> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-28 17:47:32 +01:00
static int log_line_range_callback(const struct option *option, const char *arg, int unset)
{
struct line_opt_callback_data *data = option->value;
if (!arg)
return -1;
data->rev->line_level_traverse = 1;
string_list_append(&data->args, arg);
return 0;
}
static void cmd_log_init_defaults(struct rev_info *rev)
{
if (fmt_pretty)
get_commit_format(fmt_pretty, rev);
rev->verbose_header = 1;
DIFF_OPT_SET(&rev->diffopt, RECURSIVE);
rev->diffopt.stat_width = -1; /* use full terminal width */
rev->diffopt.stat_graph_width = -1; /* respect statGraphWidth config */
rev->abbrev_commit = default_abbrev_commit;
rev->show_root_diff = default_show_root;
rev->subject_prefix = fmt_patch_subject_prefix;
DIFF_OPT_SET(&rev->diffopt, ALLOW_TEXTCONV);
if (default_date_mode)
rev->date_mode = parse_date_format(default_date_mode);
rev->diffopt.touched_flags = 0;
}
static void cmd_log_init_finish(int argc, const char **argv, const char *prefix,
struct rev_info *rev, struct setup_revision_opt *opt)
{
struct userformat_want w;
int quiet = 0, source = 0, mailmap = 0;
Implement line-history search (git log -L) This is a rewrite of much of Bo's work, mainly in an effort to split it into smaller, easier to understand routines. The algorithm is built around the struct range_set, which encodes a series of line ranges as intervals [a,b). This is used in two contexts: * A set of lines we are tracking (which will change as we dig through history). * To encode diffs, as pairs of ranges. The main routine is range_set_map_across_diff(). It processes the diff between a commit C and some parent P. It determines which diff hunks are relevant to the ranges tracked in C, and computes the new ranges for P. The algorithm is then simply to process history in topological order from newest to oldest, computing ranges and (partial) diffs. At branch points, we need to merge the ranges we are watching. We will find that many commits do not affect the chosen ranges, and mark them TREESAME (in addition to those already filtered by pathspec limiting). Another pass of history simplification then gets rid of such commits. This is wired as an extra filtering pass in the log machinery. This currently only reduces code duplication, but should allow for other simplifications and options to be used. Finally, we hook a diff printer into the output chain. Ideally we would wire directly into the diff logic, to optionally use features like word diff. However, that will require some major reworking of the diff chain, so we completely replace the output with our own diff for now. As this was a GSoC project, and has quite some history by now, many people have helped. In no particular order, thanks go to Jakub Narebski <jnareb@gmail.com> Jens Lehmann <Jens.Lehmann@web.de> Jonathan Nieder <jrnieder@gmail.com> Junio C Hamano <gitster@pobox.com> Ramsay Jones <ramsay@ramsay1.demon.co.uk> Will Palmer <wmpalmer@gmail.com> Apologies to everyone I forgot. Signed-off-by: Bo Yang <struggleyb.nku@gmail.com> Signed-off-by: Thomas Rast <trast@student.ethz.ch> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-28 17:47:32 +01:00
static struct line_opt_callback_data line_cb = {NULL, NULL, STRING_LIST_INIT_DUP};
const struct option builtin_log_options[] = {
OPT__QUIET(&quiet, N_("suppress diff output")),
OPT_BOOL(0, "source", &source, N_("show source")),
OPT_BOOL(0, "use-mailmap", &mailmap, N_("Use mail map file")),
{ OPTION_CALLBACK, 0, "decorate", NULL, NULL, N_("decorate options"),
PARSE_OPT_OPTARG, decorate_callback},
Implement line-history search (git log -L) This is a rewrite of much of Bo's work, mainly in an effort to split it into smaller, easier to understand routines. The algorithm is built around the struct range_set, which encodes a series of line ranges as intervals [a,b). This is used in two contexts: * A set of lines we are tracking (which will change as we dig through history). * To encode diffs, as pairs of ranges. The main routine is range_set_map_across_diff(). It processes the diff between a commit C and some parent P. It determines which diff hunks are relevant to the ranges tracked in C, and computes the new ranges for P. The algorithm is then simply to process history in topological order from newest to oldest, computing ranges and (partial) diffs. At branch points, we need to merge the ranges we are watching. We will find that many commits do not affect the chosen ranges, and mark them TREESAME (in addition to those already filtered by pathspec limiting). Another pass of history simplification then gets rid of such commits. This is wired as an extra filtering pass in the log machinery. This currently only reduces code duplication, but should allow for other simplifications and options to be used. Finally, we hook a diff printer into the output chain. Ideally we would wire directly into the diff logic, to optionally use features like word diff. However, that will require some major reworking of the diff chain, so we completely replace the output with our own diff for now. As this was a GSoC project, and has quite some history by now, many people have helped. In no particular order, thanks go to Jakub Narebski <jnareb@gmail.com> Jens Lehmann <Jens.Lehmann@web.de> Jonathan Nieder <jrnieder@gmail.com> Junio C Hamano <gitster@pobox.com> Ramsay Jones <ramsay@ramsay1.demon.co.uk> Will Palmer <wmpalmer@gmail.com> Apologies to everyone I forgot. Signed-off-by: Bo Yang <struggleyb.nku@gmail.com> Signed-off-by: Thomas Rast <trast@student.ethz.ch> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-28 17:47:32 +01:00
OPT_CALLBACK('L', NULL, &line_cb, "n,m:file",
"Process line range n,m in file, counting from 1",
log_line_range_callback),
OPT_END()
};
Implement line-history search (git log -L) This is a rewrite of much of Bo's work, mainly in an effort to split it into smaller, easier to understand routines. The algorithm is built around the struct range_set, which encodes a series of line ranges as intervals [a,b). This is used in two contexts: * A set of lines we are tracking (which will change as we dig through history). * To encode diffs, as pairs of ranges. The main routine is range_set_map_across_diff(). It processes the diff between a commit C and some parent P. It determines which diff hunks are relevant to the ranges tracked in C, and computes the new ranges for P. The algorithm is then simply to process history in topological order from newest to oldest, computing ranges and (partial) diffs. At branch points, we need to merge the ranges we are watching. We will find that many commits do not affect the chosen ranges, and mark them TREESAME (in addition to those already filtered by pathspec limiting). Another pass of history simplification then gets rid of such commits. This is wired as an extra filtering pass in the log machinery. This currently only reduces code duplication, but should allow for other simplifications and options to be used. Finally, we hook a diff printer into the output chain. Ideally we would wire directly into the diff logic, to optionally use features like word diff. However, that will require some major reworking of the diff chain, so we completely replace the output with our own diff for now. As this was a GSoC project, and has quite some history by now, many people have helped. In no particular order, thanks go to Jakub Narebski <jnareb@gmail.com> Jens Lehmann <Jens.Lehmann@web.de> Jonathan Nieder <jrnieder@gmail.com> Junio C Hamano <gitster@pobox.com> Ramsay Jones <ramsay@ramsay1.demon.co.uk> Will Palmer <wmpalmer@gmail.com> Apologies to everyone I forgot. Signed-off-by: Bo Yang <struggleyb.nku@gmail.com> Signed-off-by: Thomas Rast <trast@student.ethz.ch> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-28 17:47:32 +01:00
line_cb.rev = rev;
line_cb.prefix = prefix;
mailmap = use_mailmap_config;
argc = parse_options(argc, argv, prefix,
builtin_log_options, builtin_log_usage,
PARSE_OPT_KEEP_ARGV0 | PARSE_OPT_KEEP_UNKNOWN |
PARSE_OPT_KEEP_DASHDASH);
if (quiet)
rev->diffopt.output_format |= DIFF_FORMAT_NO_OUTPUT;
log: fix --quiet synonym for -s Originally the "--quiet" option was parsed by the diff-option parser into the internal QUICK option. This had the effect of silencing diff output from the log (which was not intended, but happened to work and people started to use it). But it also had other odd side effects at the diff level (for example, it would suppress the second commit in "git show A B"). To fix this, commit 1c40c36 converted log to parse-options and handled the "quiet" option separately, not passing it on to the diff code. However, it simply ignored the option, which was a regression for people using it as a synonym for "-s". Commit 01771a8 then fixed that by interpreting the option to add DIFF_FORMAT_NO_OUTPUT to the list of output formats. However, that commit did not fix it in all cases. It sets the flag after setup_revisions is called. Naively, this makes sense because you would expect the setup_revisions parser to overwrite our output format flag if "-p" or another output format flag is seen. However, that is not how the NO_OUTPUT flag works. We actually store it in the bit-field as just another format. At the end of setup_revisions, we call diff_setup_done, which post-processes the bitfield and clears any other formats if we have set NO_OUTPUT. By setting the flag after setup_revisions is done, diff_setup_done does not have a chance to make this tweak, and we end up with other format options still set. As a result, the flag would have no effect in "git log -p --quiet" or "git show --quiet". Fix it by setting the format flag before the call to setup_revisions. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-08-28 23:29:34 +02:00
argc = setup_revisions(argc, argv, rev, opt);
/* Any arguments at this point are not recognized */
if (argc > 1)
die("unrecognized argument: %s", argv[1]);
memset(&w, 0, sizeof(w));
userformat_find_requirements(NULL, &w);
if (!rev->show_notes_given && (!rev->pretty_given || w.notes))
rev->show_notes = 1;
if (rev->show_notes)
init_display_notes(&rev->notes_opt);
if (rev->diffopt.pickaxe || rev->diffopt.filter)
rev->always_show_header = 0;
if (DIFF_OPT_TST(&rev->diffopt, FOLLOW_RENAMES)) {
Finally implement "git log --follow" Ok, I've really held off doing this too damn long, because I'm lazy, and I was always hoping that somebody else would do it. But no, people keep asking for it, but nobody actually did anything, so I decided I might as well bite the bullet, and instead of telling people they could add a "--follow" flag to "git log" to do what they want to do, I decided that it looks like I just have to do it for them.. The code wasn't actually that complicated, in that the diffstat for this patch literally says "70 insertions(+), 1 deletions(-)", but I will have to admit that in order to get to this fairly simple patch, you did have to know and understand the internal git diff generation machinery pretty well, and had to really be able to follow how commit generation interacts with generating patches and generating the log. So I suspect that while I was right that it wasn't that hard, I might have been expecting too much of random people - this patch does seem to be firmly in the core "Linus or Junio" territory. To make a long story short: I'm sorry for it taking so long until I just did it. I'm not going to guarantee that this works for everybody, but you really can just look at the patch, and after the appropriate appreciative noises ("Ooh, aah") over how clever I am, you can then just notice that the code itself isn't really that complicated. All the real new code is in the new "try_to_follow_renames()" function. It really isn't rocket science: we notice that the pathname we were looking at went away, so we start a full tree diff and try to see if we can instead make that pathname be a rename or a copy from some other previous pathname. And if we can, we just continue, except we show *that* particular diff, and ever after we use the _previous_ pathname. One thing to look out for: the "rename detection" is considered to be a singular event in the _linear_ "git log" output! That's what people want to do, but I just wanted to point out that this patch is *not* carrying around a "commit,pathname" kind of pair and it's *not* going to be able to notice the file coming from multiple *different* files in earlier history. IOW, if you use "git log --follow", then you get the stupid CVS/SVN kind of "files have single identities" kind of semantics, and git log will just pick the identity based on the normal move/copy heuristics _as_if_ the history could be linearized. Put another way: I think the model is broken, but given the broken model, I think this patch does just about as well as you can do. If you have merges with the same "file" having different filenames over the two branches, git will just end up picking _one_ of the pathnames at the point where the newer one goes away. It never looks at multiple pathnames in parallel. And if you understood all that, you probably didn't need it explained, and if you didn't understand the above blathering, it doesn't really mtter to you. What matters to you is that you can now do git log -p --follow builtin-rev-list.c and it will find the point where the old "rev-list.c" got renamed to "builtin-rev-list.c" and show it as such. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-19 23:22:46 +02:00
rev->always_show_header = 0;
if (rev->diffopt.pathspec.nr != 1)
Finally implement "git log --follow" Ok, I've really held off doing this too damn long, because I'm lazy, and I was always hoping that somebody else would do it. But no, people keep asking for it, but nobody actually did anything, so I decided I might as well bite the bullet, and instead of telling people they could add a "--follow" flag to "git log" to do what they want to do, I decided that it looks like I just have to do it for them.. The code wasn't actually that complicated, in that the diffstat for this patch literally says "70 insertions(+), 1 deletions(-)", but I will have to admit that in order to get to this fairly simple patch, you did have to know and understand the internal git diff generation machinery pretty well, and had to really be able to follow how commit generation interacts with generating patches and generating the log. So I suspect that while I was right that it wasn't that hard, I might have been expecting too much of random people - this patch does seem to be firmly in the core "Linus or Junio" territory. To make a long story short: I'm sorry for it taking so long until I just did it. I'm not going to guarantee that this works for everybody, but you really can just look at the patch, and after the appropriate appreciative noises ("Ooh, aah") over how clever I am, you can then just notice that the code itself isn't really that complicated. All the real new code is in the new "try_to_follow_renames()" function. It really isn't rocket science: we notice that the pathname we were looking at went away, so we start a full tree diff and try to see if we can instead make that pathname be a rename or a copy from some other previous pathname. And if we can, we just continue, except we show *that* particular diff, and ever after we use the _previous_ pathname. One thing to look out for: the "rename detection" is considered to be a singular event in the _linear_ "git log" output! That's what people want to do, but I just wanted to point out that this patch is *not* carrying around a "commit,pathname" kind of pair and it's *not* going to be able to notice the file coming from multiple *different* files in earlier history. IOW, if you use "git log --follow", then you get the stupid CVS/SVN kind of "files have single identities" kind of semantics, and git log will just pick the identity based on the normal move/copy heuristics _as_if_ the history could be linearized. Put another way: I think the model is broken, but given the broken model, I think this patch does just about as well as you can do. If you have merges with the same "file" having different filenames over the two branches, git will just end up picking _one_ of the pathnames at the point where the newer one goes away. It never looks at multiple pathnames in parallel. And if you understood all that, you probably didn't need it explained, and if you didn't understand the above blathering, it doesn't really mtter to you. What matters to you is that you can now do git log -p --follow builtin-rev-list.c and it will find the point where the old "rev-list.c" got renamed to "builtin-rev-list.c" and show it as such. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-19 23:22:46 +02:00
usage("git logs can only follow renames on one pathname at a time");
}
if (source)
rev->show_source = 1;
if (mailmap) {
rev->mailmap = xcalloc(1, sizeof(struct string_list));
read_mailmap(rev->mailmap, NULL);
}
if (rev->pretty_given && rev->commit_format == CMIT_FMT_RAW) {
/*
* "log --pretty=raw" is special; ignore UI oriented
* configuration variables such as decoration.
*/
if (!decoration_given)
decoration_style = 0;
if (!rev->abbrev_commit_given)
rev->abbrev_commit = 0;
}
if (decoration_style) {
rev->show_decorations = 1;
load_ref_decorations(decoration_style);
}
Implement line-history search (git log -L) This is a rewrite of much of Bo's work, mainly in an effort to split it into smaller, easier to understand routines. The algorithm is built around the struct range_set, which encodes a series of line ranges as intervals [a,b). This is used in two contexts: * A set of lines we are tracking (which will change as we dig through history). * To encode diffs, as pairs of ranges. The main routine is range_set_map_across_diff(). It processes the diff between a commit C and some parent P. It determines which diff hunks are relevant to the ranges tracked in C, and computes the new ranges for P. The algorithm is then simply to process history in topological order from newest to oldest, computing ranges and (partial) diffs. At branch points, we need to merge the ranges we are watching. We will find that many commits do not affect the chosen ranges, and mark them TREESAME (in addition to those already filtered by pathspec limiting). Another pass of history simplification then gets rid of such commits. This is wired as an extra filtering pass in the log machinery. This currently only reduces code duplication, but should allow for other simplifications and options to be used. Finally, we hook a diff printer into the output chain. Ideally we would wire directly into the diff logic, to optionally use features like word diff. However, that will require some major reworking of the diff chain, so we completely replace the output with our own diff for now. As this was a GSoC project, and has quite some history by now, many people have helped. In no particular order, thanks go to Jakub Narebski <jnareb@gmail.com> Jens Lehmann <Jens.Lehmann@web.de> Jonathan Nieder <jrnieder@gmail.com> Junio C Hamano <gitster@pobox.com> Ramsay Jones <ramsay@ramsay1.demon.co.uk> Will Palmer <wmpalmer@gmail.com> Apologies to everyone I forgot. Signed-off-by: Bo Yang <struggleyb.nku@gmail.com> Signed-off-by: Thomas Rast <trast@student.ethz.ch> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-28 17:47:32 +01:00
if (rev->line_level_traverse)
line_log_init(rev, line_cb.prefix, &line_cb.args);
setup_pager();
}
static void cmd_log_init(int argc, const char **argv, const char *prefix,
struct rev_info *rev, struct setup_revision_opt *opt)
{
cmd_log_init_defaults(rev);
cmd_log_init_finish(argc, argv, prefix, rev, opt);
}
Enhance --early-output format This makes --early-output a bit more advanced, and actually makes it generate multiple "Final output:" headers as it updates things asynchronously. I realize that the "Final output:" line is now illogical, since it's not really final until it also says "done", but It now _always_ generates a "Final output:" header in front of any commit list, and that output header gives you a *guess* at the maximum number of commits available. However, it should be noted that the guess can be completely off: I do a reasonable job estimating it, but it is not meant to be exact. So what happens is that you may get output like this: - at 0.1 seconds: Final output: 2 incomplete .. 2 commits listed .. - half a second later: Final output: 33 incomplete .. 33 commits listed .. - another half a second after that: Final output: 71 incomplete .. 71 commits listed .. - another half second later: Final output: 136 incomplete .. 100 commits listed: we hit the --early-output limit, and .. will only output 100 commits, and after this you'll not .. see an "incomplete" report any more since you got as much .. early output as you asked for! - .. and then finally: Final output: 73106 done .. all the commits .. The above is a real-life scenario on my current kernel tree after having flushed all the caches. Tested with the experimental gitk patch that Paul sent out, and by looking at the actual log output (and verifying that my commit count guesses actually match real life fairly well). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-04 21:12:05 +01:00
/*
* This gives a rough estimate for how many commits we
* will print out in the list.
*/
static int estimate_commit_count(struct rev_info *rev, struct commit_list *list)
{
int n = 0;
while (list) {
struct commit *commit = list->item;
unsigned int flags = commit->object.flags;
list = list->next;
if (!(flags & (TREESAME | UNINTERESTING)))
n++;
Enhance --early-output format This makes --early-output a bit more advanced, and actually makes it generate multiple "Final output:" headers as it updates things asynchronously. I realize that the "Final output:" line is now illogical, since it's not really final until it also says "done", but It now _always_ generates a "Final output:" header in front of any commit list, and that output header gives you a *guess* at the maximum number of commits available. However, it should be noted that the guess can be completely off: I do a reasonable job estimating it, but it is not meant to be exact. So what happens is that you may get output like this: - at 0.1 seconds: Final output: 2 incomplete .. 2 commits listed .. - half a second later: Final output: 33 incomplete .. 33 commits listed .. - another half a second after that: Final output: 71 incomplete .. 71 commits listed .. - another half second later: Final output: 136 incomplete .. 100 commits listed: we hit the --early-output limit, and .. will only output 100 commits, and after this you'll not .. see an "incomplete" report any more since you got as much .. early output as you asked for! - .. and then finally: Final output: 73106 done .. all the commits .. The above is a real-life scenario on my current kernel tree after having flushed all the caches. Tested with the experimental gitk patch that Paul sent out, and by looking at the actual log output (and verifying that my commit count guesses actually match real life fairly well). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-04 21:12:05 +01:00
}
return n;
}
static void show_early_header(struct rev_info *rev, const char *stage, int nr)
{
if (rev->shown_one) {
rev->shown_one = 0;
if (rev->commit_format != CMIT_FMT_ONELINE)
putchar(rev->diffopt.line_termination);
}
printf(_("Final output: %d %s\n"), nr, stage);
Enhance --early-output format This makes --early-output a bit more advanced, and actually makes it generate multiple "Final output:" headers as it updates things asynchronously. I realize that the "Final output:" line is now illogical, since it's not really final until it also says "done", but It now _always_ generates a "Final output:" header in front of any commit list, and that output header gives you a *guess* at the maximum number of commits available. However, it should be noted that the guess can be completely off: I do a reasonable job estimating it, but it is not meant to be exact. So what happens is that you may get output like this: - at 0.1 seconds: Final output: 2 incomplete .. 2 commits listed .. - half a second later: Final output: 33 incomplete .. 33 commits listed .. - another half a second after that: Final output: 71 incomplete .. 71 commits listed .. - another half second later: Final output: 136 incomplete .. 100 commits listed: we hit the --early-output limit, and .. will only output 100 commits, and after this you'll not .. see an "incomplete" report any more since you got as much .. early output as you asked for! - .. and then finally: Final output: 73106 done .. all the commits .. The above is a real-life scenario on my current kernel tree after having flushed all the caches. Tested with the experimental gitk patch that Paul sent out, and by looking at the actual log output (and verifying that my commit count guesses actually match real life fairly well). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-04 21:12:05 +01:00
}
static struct itimerval early_output_timer;
Enhance --early-output format This makes --early-output a bit more advanced, and actually makes it generate multiple "Final output:" headers as it updates things asynchronously. I realize that the "Final output:" line is now illogical, since it's not really final until it also says "done", but It now _always_ generates a "Final output:" header in front of any commit list, and that output header gives you a *guess* at the maximum number of commits available. However, it should be noted that the guess can be completely off: I do a reasonable job estimating it, but it is not meant to be exact. So what happens is that you may get output like this: - at 0.1 seconds: Final output: 2 incomplete .. 2 commits listed .. - half a second later: Final output: 33 incomplete .. 33 commits listed .. - another half a second after that: Final output: 71 incomplete .. 71 commits listed .. - another half second later: Final output: 136 incomplete .. 100 commits listed: we hit the --early-output limit, and .. will only output 100 commits, and after this you'll not .. see an "incomplete" report any more since you got as much .. early output as you asked for! - .. and then finally: Final output: 73106 done .. all the commits .. The above is a real-life scenario on my current kernel tree after having flushed all the caches. Tested with the experimental gitk patch that Paul sent out, and by looking at the actual log output (and verifying that my commit count guesses actually match real life fairly well). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-04 21:12:05 +01:00
static void log_show_early(struct rev_info *revs, struct commit_list *list)
{
int i = revs->early_output;
Enhance --early-output format This makes --early-output a bit more advanced, and actually makes it generate multiple "Final output:" headers as it updates things asynchronously. I realize that the "Final output:" line is now illogical, since it's not really final until it also says "done", but It now _always_ generates a "Final output:" header in front of any commit list, and that output header gives you a *guess* at the maximum number of commits available. However, it should be noted that the guess can be completely off: I do a reasonable job estimating it, but it is not meant to be exact. So what happens is that you may get output like this: - at 0.1 seconds: Final output: 2 incomplete .. 2 commits listed .. - half a second later: Final output: 33 incomplete .. 33 commits listed .. - another half a second after that: Final output: 71 incomplete .. 71 commits listed .. - another half second later: Final output: 136 incomplete .. 100 commits listed: we hit the --early-output limit, and .. will only output 100 commits, and after this you'll not .. see an "incomplete" report any more since you got as much .. early output as you asked for! - .. and then finally: Final output: 73106 done .. all the commits .. The above is a real-life scenario on my current kernel tree after having flushed all the caches. Tested with the experimental gitk patch that Paul sent out, and by looking at the actual log output (and verifying that my commit count guesses actually match real life fairly well). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-04 21:12:05 +01:00
int show_header = 1;
toposort: rename "lifo" field The primary invariant of sort_in_topological_order() is that a parent commit is not emitted until all children of it are. When traversing a forked history like this with "git log C E": A----B----C \ D----E we ensure that A is emitted after all of B, C, D, and E are done, B has to wait until C is done, and D has to wait until E is done. In some applications, however, we would further want to control how these child commits B, C, D and E on two parallel ancestry chains are shown. Most of the time, we would want to see C and B emitted together, and then E and D, and finally A (i.e. the --topo-order output). The "lifo" parameter of the sort_in_topological_order() function is used to control this behaviour. We start the traversal by knowing two commits, C and E. While keeping in mind that we also need to inspect E later, we pick C first to inspect, and we notice and record that B needs to be inspected. By structuring the "work to be done" set as a LIFO stack, we ensure that B is inspected next, before other in-flight commits we had known that we will need to inspect, e.g. E. When showing in --date-order, we would want to see commits ordered by timestamps, i.e. show C, E, B and D in this order before showing A, possibly mixing commits from two parallel histories together. When "lifo" parameter is set to false, the function keeps the "work to be done" set sorted in the date order to realize this semantics. After inspecting C, we add B to the "work to be done" set, but the next commit we inspect from the set is E which is newer than B. The name "lifo", however, is too strongly tied to the way how the function implements its behaviour, and does not describe what the behaviour _means_. Replace this field with an enum rev_sort_order, with two possible values: REV_SORT_IN_GRAPH_ORDER and REV_SORT_BY_COMMIT_DATE, and update the existing code. The mechanical replacement rule is: "lifo == 0" is equivalent to "sort_order == REV_SORT_BY_COMMIT_DATE" "lifo == 1" is equivalent to "sort_order == REV_SORT_IN_GRAPH_ORDER" Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-07 01:07:14 +02:00
sort_in_topological_order(&list, revs->sort_order);
while (list && i) {
struct commit *commit = list->item;
Enhance --early-output format This makes --early-output a bit more advanced, and actually makes it generate multiple "Final output:" headers as it updates things asynchronously. I realize that the "Final output:" line is now illogical, since it's not really final until it also says "done", but It now _always_ generates a "Final output:" header in front of any commit list, and that output header gives you a *guess* at the maximum number of commits available. However, it should be noted that the guess can be completely off: I do a reasonable job estimating it, but it is not meant to be exact. So what happens is that you may get output like this: - at 0.1 seconds: Final output: 2 incomplete .. 2 commits listed .. - half a second later: Final output: 33 incomplete .. 33 commits listed .. - another half a second after that: Final output: 71 incomplete .. 71 commits listed .. - another half second later: Final output: 136 incomplete .. 100 commits listed: we hit the --early-output limit, and .. will only output 100 commits, and after this you'll not .. see an "incomplete" report any more since you got as much .. early output as you asked for! - .. and then finally: Final output: 73106 done .. all the commits .. The above is a real-life scenario on my current kernel tree after having flushed all the caches. Tested with the experimental gitk patch that Paul sent out, and by looking at the actual log output (and verifying that my commit count guesses actually match real life fairly well). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-04 21:12:05 +01:00
switch (simplify_commit(revs, commit)) {
case commit_show:
if (show_header) {
int n = estimate_commit_count(revs, list);
show_early_header(revs, "incomplete", n);
show_header = 0;
}
log_tree_commit(revs, commit);
i--;
break;
case commit_ignore:
break;
case commit_error:
return;
}
list = list->next;
}
Enhance --early-output format This makes --early-output a bit more advanced, and actually makes it generate multiple "Final output:" headers as it updates things asynchronously. I realize that the "Final output:" line is now illogical, since it's not really final until it also says "done", but It now _always_ generates a "Final output:" header in front of any commit list, and that output header gives you a *guess* at the maximum number of commits available. However, it should be noted that the guess can be completely off: I do a reasonable job estimating it, but it is not meant to be exact. So what happens is that you may get output like this: - at 0.1 seconds: Final output: 2 incomplete .. 2 commits listed .. - half a second later: Final output: 33 incomplete .. 33 commits listed .. - another half a second after that: Final output: 71 incomplete .. 71 commits listed .. - another half second later: Final output: 136 incomplete .. 100 commits listed: we hit the --early-output limit, and .. will only output 100 commits, and after this you'll not .. see an "incomplete" report any more since you got as much .. early output as you asked for! - .. and then finally: Final output: 73106 done .. all the commits .. The above is a real-life scenario on my current kernel tree after having flushed all the caches. Tested with the experimental gitk patch that Paul sent out, and by looking at the actual log output (and verifying that my commit count guesses actually match real life fairly well). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-04 21:12:05 +01:00
/* Did we already get enough commits for the early output? */
if (!i)
return;
/*
* ..if no, then repeat it twice a second until we
* do.
*
* NOTE! We don't use "it_interval", because if the
* reader isn't listening, we want our output to be
* throttled by the writing, and not have the timer
* trigger every second even if we're blocked on a
* reader!
*/
early_output_timer.it_value.tv_sec = 0;
early_output_timer.it_value.tv_usec = 500000;
setitimer(ITIMER_REAL, &early_output_timer, NULL);
}
static void early_output(int signal)
{
show_early_output = log_show_early;
}
static void setup_early_output(struct rev_info *rev)
{
struct sigaction sa;
/*
* Set up the signal handler, minimally intrusively:
* we only set a single volatile integer word (not
* using sigatomic_t - trying to avoid unnecessary
* system dependencies and headers), and using
* SA_RESTART.
*/
memset(&sa, 0, sizeof(sa));
sa.sa_handler = early_output;
sigemptyset(&sa.sa_mask);
sa.sa_flags = SA_RESTART;
sigaction(SIGALRM, &sa, NULL);
/*
* If we can get the whole output in less than a
* tenth of a second, don't even bother doing the
* early-output thing..
*
* This is a one-time-only trigger.
*/
Enhance --early-output format This makes --early-output a bit more advanced, and actually makes it generate multiple "Final output:" headers as it updates things asynchronously. I realize that the "Final output:" line is now illogical, since it's not really final until it also says "done", but It now _always_ generates a "Final output:" header in front of any commit list, and that output header gives you a *guess* at the maximum number of commits available. However, it should be noted that the guess can be completely off: I do a reasonable job estimating it, but it is not meant to be exact. So what happens is that you may get output like this: - at 0.1 seconds: Final output: 2 incomplete .. 2 commits listed .. - half a second later: Final output: 33 incomplete .. 33 commits listed .. - another half a second after that: Final output: 71 incomplete .. 71 commits listed .. - another half second later: Final output: 136 incomplete .. 100 commits listed: we hit the --early-output limit, and .. will only output 100 commits, and after this you'll not .. see an "incomplete" report any more since you got as much .. early output as you asked for! - .. and then finally: Final output: 73106 done .. all the commits .. The above is a real-life scenario on my current kernel tree after having flushed all the caches. Tested with the experimental gitk patch that Paul sent out, and by looking at the actual log output (and verifying that my commit count guesses actually match real life fairly well). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-04 21:12:05 +01:00
early_output_timer.it_value.tv_sec = 0;
early_output_timer.it_value.tv_usec = 100000;
setitimer(ITIMER_REAL, &early_output_timer, NULL);
}
static void finish_early_output(struct rev_info *rev)
{
Enhance --early-output format This makes --early-output a bit more advanced, and actually makes it generate multiple "Final output:" headers as it updates things asynchronously. I realize that the "Final output:" line is now illogical, since it's not really final until it also says "done", but It now _always_ generates a "Final output:" header in front of any commit list, and that output header gives you a *guess* at the maximum number of commits available. However, it should be noted that the guess can be completely off: I do a reasonable job estimating it, but it is not meant to be exact. So what happens is that you may get output like this: - at 0.1 seconds: Final output: 2 incomplete .. 2 commits listed .. - half a second later: Final output: 33 incomplete .. 33 commits listed .. - another half a second after that: Final output: 71 incomplete .. 71 commits listed .. - another half second later: Final output: 136 incomplete .. 100 commits listed: we hit the --early-output limit, and .. will only output 100 commits, and after this you'll not .. see an "incomplete" report any more since you got as much .. early output as you asked for! - .. and then finally: Final output: 73106 done .. all the commits .. The above is a real-life scenario on my current kernel tree after having flushed all the caches. Tested with the experimental gitk patch that Paul sent out, and by looking at the actual log output (and verifying that my commit count guesses actually match real life fairly well). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-04 21:12:05 +01:00
int n = estimate_commit_count(rev, rev->commits);
signal(SIGALRM, SIG_IGN);
Enhance --early-output format This makes --early-output a bit more advanced, and actually makes it generate multiple "Final output:" headers as it updates things asynchronously. I realize that the "Final output:" line is now illogical, since it's not really final until it also says "done", but It now _always_ generates a "Final output:" header in front of any commit list, and that output header gives you a *guess* at the maximum number of commits available. However, it should be noted that the guess can be completely off: I do a reasonable job estimating it, but it is not meant to be exact. So what happens is that you may get output like this: - at 0.1 seconds: Final output: 2 incomplete .. 2 commits listed .. - half a second later: Final output: 33 incomplete .. 33 commits listed .. - another half a second after that: Final output: 71 incomplete .. 71 commits listed .. - another half second later: Final output: 136 incomplete .. 100 commits listed: we hit the --early-output limit, and .. will only output 100 commits, and after this you'll not .. see an "incomplete" report any more since you got as much .. early output as you asked for! - .. and then finally: Final output: 73106 done .. all the commits .. The above is a real-life scenario on my current kernel tree after having flushed all the caches. Tested with the experimental gitk patch that Paul sent out, and by looking at the actual log output (and verifying that my commit count guesses actually match real life fairly well). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-04 21:12:05 +01:00
show_early_header(rev, "done", n);
}
static int cmd_log_walk(struct rev_info *rev)
{
struct commit *commit;
int saved_nrl = 0;
int saved_dcctc = 0;
if (rev->early_output)
setup_early_output(rev);
if (prepare_revision_walk(rev))
die(_("revision walk setup failed"));
if (rev->early_output)
finish_early_output(rev);
/*
* For --check and --exit-code, the exit code is based on CHECK_FAILED
* and HAS_CHANGES being accumulated in rev->diffopt, so be careful to
* retain that state information if replacing rev->diffopt in this loop
*/
while ((commit = get_revision(rev)) != NULL) {
if (!log_tree_commit(rev, commit) &&
rev->max_count >= 0)
/*
* We decremented max_count in get_revision,
* but we didn't actually show the commit.
*/
rev->max_count++;
if (!rev->reflog_info) {
/* we allow cycles in reflog ancestry */
free(commit->buffer);
commit->buffer = NULL;
}
free_commit_list(commit->parents);
commit->parents = NULL;
if (saved_nrl < rev->diffopt.needed_rename_limit)
saved_nrl = rev->diffopt.needed_rename_limit;
if (rev->diffopt.degraded_cc_to_c)
saved_dcctc = 1;
}
rev->diffopt.degraded_cc_to_c = saved_dcctc;
rev->diffopt.needed_rename_limit = saved_nrl;
if (rev->diffopt.output_format & DIFF_FORMAT_CHECKDIFF &&
DIFF_OPT_TST(&rev->diffopt, CHECK_FAILED)) {
return 02;
}
return diff_result_code(&rev->diffopt, 0);
}
static int git_log_config(const char *var, const char *value, void *cb)
{
if (!strcmp(var, "format.pretty"))
return git_config_string(&fmt_pretty, var, value);
if (!strcmp(var, "format.subjectprefix"))
return git_config_string(&fmt_patch_subject_prefix, var, value);
if (!strcmp(var, "log.abbrevcommit")) {
default_abbrev_commit = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "log.date"))
return git_config_string(&default_date_mode, var, value);
if (!strcmp(var, "log.decorate")) {
decoration_style = parse_decoration_style(var, value);
if (decoration_style < 0)
decoration_style = 0; /* maybe warn? */
return 0;
}
if (!strcmp(var, "log.showroot")) {
default_show_root = git_config_bool(var, value);
return 0;
}
if (starts_with(var, "color.decorate."))
return parse_decorate_color_config(var, 15, value);
if (!strcmp(var, "log.mailmap")) {
use_mailmap_config = git_config_bool(var, value);
return 0;
}
if (grep_config(var, value, cb) < 0)
return -1;
if (git_gpg_config(var, value, cb) < 0)
return -1;
return git_diff_ui_config(var, value, cb);
}
int cmd_whatchanged(int argc, const char **argv, const char *prefix)
{
struct rev_info rev;
struct setup_revision_opt opt;
init_grep_defaults();
git_config(git_log_config, NULL);
init_revisions(&rev, prefix);
rev.diff = 1;
gitweb.cgi history not shown This does: - add a "rev.simplify_history" flag which defaults to on - it turns it off for "git whatchanged" (which thus now has real semantics outside of "git log") - it adds a command line flag ("--full-history") to turn it off for others (ie you can make "git log" and "gitk" etc get the semantics if you want to. Now, just as an example of _why_ you really really really want to simplify history by default, apply this patch, install it, and try these two command lines: gitk --full-history -- git.c gitk -- git.c and compare the output. So with this, you can also now do git whatchanged -p -- gitweb.cgi git log -p --full-history -- gitweb.cgi and it will show the old history of gitweb.cgi, even though it's not relevant to the _current_ state of the name "gitweb.cgi" NOTE NOTE NOTE! It will still actually simplify away merges that didn't change anything at all into either child. That creates these bogus strange discontinuities if you look at it with "gitk" (look at the --full-history gitk output for git.c, and you'll see a few strange cases). So the whole "--parent" thing ends up somewhat bogus with --full-history because of this, but I'm not sure it's worth even worrying about. I don't think you'd ever want to really use "--full-history" with the graphical representation, I just give it as an example exactly to show _why_ doing so would be insane. I think this is trivial enough and useful enough to be worth merging into the stable branch. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-11 19:57:35 +02:00
rev.simplify_history = 0;
memset(&opt, 0, sizeof(opt));
opt.def = "HEAD";
opt.revarg_opt = REVARG_COMMITTISH;
cmd_log_init(argc, argv, prefix, &rev, &opt);
if (!rev.diffopt.output_format)
rev.diffopt.output_format = DIFF_FORMAT_RAW;
return cmd_log_walk(&rev);
}
static void show_tagger(char *buf, int len, struct rev_info *rev)
{
struct strbuf out = STRBUF_INIT;
struct pretty_print_context pp = {0};
pp.fmt = rev->commit_format;
pp.date_mode = rev->date_mode;
pp_user_info(&pp, "Tagger", &out, buf, get_log_output_encoding());
printf("%s", out.buf);
strbuf_release(&out);
}
static int show_blob_object(const unsigned char *sha1, struct rev_info *rev, const char *obj_name)
{
unsigned char sha1c[20];
struct object_context obj_context;
char *buf;
unsigned long size;
fflush(stdout);
if (!DIFF_OPT_TOUCHED(&rev->diffopt, ALLOW_TEXTCONV) ||
!DIFF_OPT_TST(&rev->diffopt, ALLOW_TEXTCONV))
return stream_blob_to_fd(1, sha1, NULL, 0);
if (get_sha1_with_context(obj_name, 0, sha1c, &obj_context))
die("Not a valid object name %s", obj_name);
if (!obj_context.path[0] ||
!textconv_object(obj_context.path, obj_context.mode, sha1c, 1, &buf, &size))
return stream_blob_to_fd(1, sha1, NULL, 0);
if (!buf)
die("git show %s: bad file", obj_name);
write_or_die(1, buf, size);
return 0;
}
static int show_tag_object(const unsigned char *sha1, struct rev_info *rev)
{
unsigned long size;
enum object_type type;
char *buf = read_sha1_file(sha1, &type, &size);
int offset = 0;
if (!buf)
return error(_("Could not read object %s"), sha1_to_hex(sha1));
assert(type == OBJ_TAG);
while (offset < size && buf[offset] != '\n') {
int new_offset = offset + 1;
while (new_offset < size && buf[new_offset++] != '\n')
; /* do nothing */
if (starts_with(buf + offset, "tagger "))
show_tagger(buf + offset + 7,
new_offset - offset - 7, rev);
offset = new_offset;
}
if (offset < size)
fwrite(buf + offset, size - offset, 1, stdout);
free(buf);
return 0;
}
static int show_tree_object(const unsigned char *sha1,
const char *base, int baselen,
const char *pathname, unsigned mode, int stage, void *context)
{
printf("%s%s\n", pathname, S_ISDIR(mode) ? "/" : "");
return 0;
}
static void show_rev_tweak_rev(struct rev_info *rev, struct setup_revision_opt *opt)
{
if (rev->ignore_merges) {
/* There was no "-m" on the command line */
rev->ignore_merges = 0;
if (!rev->first_parent_only && !rev->combine_merges) {
/* No "--first-parent", "-c", nor "--cc" */
rev->combine_merges = 1;
rev->dense_combined_merges = 1;
}
}
if (!rev->diffopt.output_format)
rev->diffopt.output_format = DIFF_FORMAT_PATCH;
}
int cmd_show(int argc, const char **argv, const char *prefix)
{
struct rev_info rev;
struct object_array_entry *objects;
struct setup_revision_opt opt;
struct pathspec match_all;
int i, count, ret = 0;
init_grep_defaults();
git_config(git_log_config, NULL);
memset(&match_all, 0, sizeof(match_all));
init_revisions(&rev, prefix);
rev.diff = 1;
rev.always_show_header = 1;
rev.no_walk = REVISION_WALK_NO_WALK_SORTED;
rev.diffopt.stat_width = -1; /* Scale to real terminal size */
memset(&opt, 0, sizeof(opt));
opt.def = "HEAD";
opt.tweak = show_rev_tweak_rev;
cmd_log_init(argc, argv, prefix, &rev, &opt);
if (!rev.no_walk)
return cmd_log_walk(&rev);
count = rev.pending.nr;
objects = rev.pending.objects;
for (i = 0; i < count && !ret; i++) {
struct object *o = objects[i].item;
const char *name = objects[i].name;
switch (o->type) {
case OBJ_BLOB:
ret = show_blob_object(o->sha1, &rev, name);
break;
case OBJ_TAG: {
struct tag *t = (struct tag *)o;
if (rev.shown_one)
putchar('\n');
printf("%stag %s%s\n",
diff_get_color_opt(&rev.diffopt, DIFF_COMMIT),
t->tag,
diff_get_color_opt(&rev.diffopt, DIFF_RESET));
ret = show_tag_object(o->sha1, &rev);
rev.shown_one = 1;
if (ret)
break;
o = parse_object(t->tagged->sha1);
if (!o)
ret = error(_("Could not read object %s"),
sha1_to_hex(t->tagged->sha1));
objects[i].item = o;
i--;
break;
}
case OBJ_TREE:
if (rev.shown_one)
putchar('\n');
printf("%stree %s%s\n\n",
diff_get_color_opt(&rev.diffopt, DIFF_COMMIT),
name,
diff_get_color_opt(&rev.diffopt, DIFF_RESET));
read_tree_recursive((struct tree *)o, "", 0, 0, &match_all,
show_tree_object, NULL);
rev.shown_one = 1;
break;
case OBJ_COMMIT:
rev.pending.nr = rev.pending.alloc = 0;
rev.pending.objects = NULL;
add_object_array(o, name, &rev.pending);
ret = cmd_log_walk(&rev);
break;
default:
ret = error(_("Unknown type: %d"), o->type);
}
}
free(objects);
return ret;
}
/*
* This is equivalent to "git log -g --abbrev-commit --pretty=oneline"
*/
int cmd_log_reflog(int argc, const char **argv, const char *prefix)
{
struct rev_info rev;
struct setup_revision_opt opt;
init_grep_defaults();
git_config(git_log_config, NULL);
init_revisions(&rev, prefix);
init_reflog_walk(&rev.reflog_info);
rev.verbose_header = 1;
memset(&opt, 0, sizeof(opt));
opt.def = "HEAD";
cmd_log_init_defaults(&rev);
rev.abbrev_commit = 1;
rev.commit_format = CMIT_FMT_ONELINE;
rev.use_terminator = 1;
rev.always_show_header = 1;
cmd_log_init_finish(argc, argv, prefix, &rev, &opt);
return cmd_log_walk(&rev);
}
int cmd_log(int argc, const char **argv, const char *prefix)
{
struct rev_info rev;
struct setup_revision_opt opt;
init_grep_defaults();
git_config(git_log_config, NULL);
init_revisions(&rev, prefix);
rev.always_show_header = 1;
memset(&opt, 0, sizeof(opt));
opt.def = "HEAD";
opt.revarg_opt = REVARG_COMMITTISH;
cmd_log_init(argc, argv, prefix, &rev, &opt);
return cmd_log_walk(&rev);
}
/* format-patch */
static const char *fmt_patch_suffix = ".patch";
static int numbered = 0;
static int auto_number = 1;
static char *default_attach = NULL;
static struct string_list extra_hdr;
static struct string_list extra_to;
static struct string_list extra_cc;
static void add_header(const char *value)
{
struct string_list_item *item;
int len = strlen(value);
while (len && value[len - 1] == '\n')
len--;
if (!strncasecmp(value, "to: ", 4)) {
item = string_list_append(&extra_to, value + 4);
len -= 4;
} else if (!strncasecmp(value, "cc: ", 4)) {
item = string_list_append(&extra_cc, value + 4);
len -= 4;
} else {
item = string_list_append(&extra_hdr, value);
}
item->string[len] = '\0';
}
#define THREAD_SHALLOW 1
#define THREAD_DEEP 2
static int thread;
static int do_signoff;
static const char *signature = git_version_string;
static int config_cover_letter;
enum {
COVER_UNSET,
COVER_OFF,
COVER_ON,
COVER_AUTO
};
static int git_format_config(const char *var, const char *value, void *cb)
{
if (!strcmp(var, "format.headers")) {
if (!value)
die(_("format.headers without value"));
add_header(value);
return 0;
}
if (!strcmp(var, "format.suffix"))
return git_config_string(&fmt_patch_suffix, var, value);
if (!strcmp(var, "format.to")) {
if (!value)
return config_error_nonbool(var);
string_list_append(&extra_to, value);
return 0;
}
if (!strcmp(var, "format.cc")) {
if (!value)
return config_error_nonbool(var);
string_list_append(&extra_cc, value);
return 0;
}
if (!strcmp(var, "diff.color") || !strcmp(var, "color.diff") ||
!strcmp(var, "color.ui")) {
return 0;
}
if (!strcmp(var, "format.numbered")) {
if (value && !strcasecmp(value, "auto")) {
auto_number = 1;
return 0;
}
numbered = git_config_bool(var, value);
auto_number = auto_number && numbered;
return 0;
}
if (!strcmp(var, "format.attach")) {
if (value && *value)
default_attach = xstrdup(value);
else
default_attach = xstrdup(git_version_string);
return 0;
}
if (!strcmp(var, "format.thread")) {
if (value && !strcasecmp(value, "deep")) {
thread = THREAD_DEEP;
return 0;
}
if (value && !strcasecmp(value, "shallow")) {
thread = THREAD_SHALLOW;
return 0;
}
thread = git_config_bool(var, value) && THREAD_SHALLOW;
return 0;
}
if (!strcmp(var, "format.signoff")) {
do_signoff = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "format.signature"))
return git_config_string(&signature, var, value);
if (!strcmp(var, "format.coverletter")) {
if (value && !strcasecmp(value, "auto")) {
config_cover_letter = COVER_AUTO;
return 0;
}
config_cover_letter = git_config_bool(var, value) ? COVER_ON : COVER_OFF;
return 0;
}
return git_log_config(var, value, cb);
}
static FILE *realstdout = NULL;
static const char *output_directory = NULL;
static int outdir_offset;
static int reopen_stdout(struct commit *commit, const char *subject,
struct rev_info *rev, int quiet)
{
struct strbuf filename = STRBUF_INIT;
int suffix_len = strlen(rev->patch_suffix) + 1;
if (output_directory) {
strbuf_addstr(&filename, output_directory);
if (filename.len >=
PATH_MAX - FORMAT_PATCH_NAME_MAX - suffix_len)
return error(_("name of output directory is too long"));
if (filename.buf[filename.len - 1] != '/')
strbuf_addch(&filename, '/');
}
if (rev->numbered_files)
strbuf_addf(&filename, "%d", rev->nr);
else if (commit)
fmt_output_commit(&filename, commit, rev);
else
fmt_output_subject(&filename, subject, rev);
if (!quiet)
fprintf(realstdout, "%s\n", filename.buf + outdir_offset);
if (freopen(filename.buf, "w", stdout) == NULL)
return error(_("Cannot open patch file %s"), filename.buf);
strbuf_release(&filename);
return 0;
}
static void get_patch_ids(struct rev_info *rev, struct patch_ids *ids)
{
struct rev_info check_rev;
struct commit *commit;
struct object *o1, *o2;
unsigned flags1, flags2;
if (rev->pending.nr != 2)
die(_("Need exactly one range."));
o1 = rev->pending.objects[0].item;
flags1 = o1->flags;
o2 = rev->pending.objects[1].item;
flags2 = o2->flags;
if ((flags1 & UNINTERESTING) == (flags2 & UNINTERESTING))
die(_("Not a range."));
init_patch_ids(ids);
/* given a range a..b get all patch ids for b..a */
init_revisions(&check_rev, rev->prefix);
check_rev.max_parents = 1;
o1->flags ^= UNINTERESTING;
o2->flags ^= UNINTERESTING;
add_pending_object(&check_rev, o1, "o1");
add_pending_object(&check_rev, o2, "o2");
if (prepare_revision_walk(&check_rev))
die(_("revision walk setup failed"));
while ((commit = get_revision(&check_rev)) != NULL) {
add_commit_patch_id(commit, ids);
}
/* reset for next revision walk */
clear_commit_marks((struct commit *)o1,
SEEN | UNINTERESTING | SHOWN | ADDED);
clear_commit_marks((struct commit *)o2,
SEEN | UNINTERESTING | SHOWN | ADDED);
o1->flags = flags1;
o2->flags = flags2;
}
static void gen_message_id(struct rev_info *info, char *base)
{
struct strbuf buf = STRBUF_INIT;
strbuf_addf(&buf, "%s.%lu.git.%s", base,
(unsigned long) time(NULL),
git_committer_info(IDENT_NO_NAME|IDENT_NO_DATE|IDENT_STRICT));
info->message_id = strbuf_detach(&buf, NULL);
}
static void print_signature(void)
{
if (signature && *signature)
printf("-- \n%s\n\n", signature);
}
static void add_branch_description(struct strbuf *buf, const char *branch_name)
{
struct strbuf desc = STRBUF_INIT;
if (!branch_name || !*branch_name)
return;
read_branch_desc(&desc, branch_name);
if (desc.len) {
strbuf_addch(buf, '\n');
strbuf_add(buf, desc.buf, desc.len);
strbuf_addch(buf, '\n');
}
}
static char *find_branch_name(struct rev_info *rev)
{
int i, positive = -1;
unsigned char branch_sha1[20];
const unsigned char *tip_sha1;
const char *ref;
char *full_ref, *branch = NULL;
for (i = 0; i < rev->cmdline.nr; i++) {
if (rev->cmdline.rev[i].flags & UNINTERESTING)
continue;
if (positive < 0)
positive = i;
else
return NULL;
}
if (positive < 0)
return NULL;
ref = rev->cmdline.rev[positive].name;
tip_sha1 = rev->cmdline.rev[positive].item->sha1;
if (dwim_ref(ref, strlen(ref), branch_sha1, &full_ref) &&
starts_with(full_ref, "refs/heads/") &&
!hashcmp(tip_sha1, branch_sha1))
branch = xstrdup(full_ref + strlen("refs/heads/"));
free(full_ref);
return branch;
}
static void make_cover_letter(struct rev_info *rev, int use_stdout,
struct commit *origin,
int nr, struct commit **list,
const char *branch_name,
int quiet)
{
const char *committer;
const char *body = "*** SUBJECT HERE ***\n\n*** BLURB HERE ***\n";
const char *msg;
struct shortlog log;
struct strbuf sb = STRBUF_INIT;
int i;
const char *encoding = "UTF-8";
struct diff_options opts;
int need_8bit_cte = 0;
struct pretty_print_context pp = {0};
struct commit *head = list[0];
if (rev->commit_format != CMIT_FMT_EMAIL)
die(_("Cover letter needs email format"));
committer = git_committer_info(0);
if (!use_stdout &&
reopen_stdout(NULL, rev->numbered_files ? NULL : "cover-letter", rev, quiet))
return;
log_write_email_headers(rev, head, &pp.subject, &pp.after_subject,
&need_8bit_cte);
for (i = 0; !need_8bit_cte && i < nr; i++)
if (has_non_ascii(list[i]->buffer))
need_8bit_cte = 1;
if (!branch_name)
branch_name = find_branch_name(rev);
msg = body;
pp.fmt = CMIT_FMT_EMAIL;
pp.date_mode = DATE_RFC2822;
pp_user_info(&pp, NULL, &sb, committer, encoding);
pp_title_line(&pp, &msg, &sb, encoding, need_8bit_cte);
pp_remainder(&pp, &msg, &sb, 0);
add_branch_description(&sb, branch_name);
printf("%s\n", sb.buf);
strbuf_release(&sb);
shortlog_init(&log);
log.wrap_lines = 1;
log.wrap = 72;
log.in1 = 2;
log.in2 = 4;
for (i = 0; i < nr; i++)
shortlog_add_commit(&log, list[i]);
shortlog_output(&log);
/*
* We can only do diffstat with a unique reference point
*/
if (!origin)
return;
memcpy(&opts, &rev->diffopt, sizeof(opts));
opts.output_format = DIFF_FORMAT_SUMMARY | DIFF_FORMAT_DIFFSTAT;
diff_setup_done(&opts);
diff_tree_sha1(origin->tree->object.sha1,
head->tree->object.sha1,
"", &opts);
diffcore_std(&opts);
diff_flush(&opts);
printf("\n");
print_signature();
}
static const char *clean_message_id(const char *msg_id)
{
char ch;
const char *a, *z, *m;
m = msg_id;
while ((ch = *m) && (isspace(ch) || (ch == '<')))
m++;
a = m;
z = NULL;
while ((ch = *m)) {
if (!isspace(ch) && (ch != '>'))
z = m;
m++;
}
if (!z)
die(_("insane in-reply-to: %s"), msg_id);
if (++z == m)
return a;
return xmemdupz(a, z - a);
}
static const char *set_outdir(const char *prefix, const char *output_directory)
{
if (output_directory && is_absolute_path(output_directory))
return output_directory;
if (!prefix || !*prefix) {
if (output_directory)
return output_directory;
/* The user did not explicitly ask for "./" */
outdir_offset = 2;
return "./";
}
outdir_offset = strlen(prefix);
if (!output_directory)
return prefix;
return xstrdup(prefix_filename(prefix, outdir_offset,
output_directory));
}
static const char * const builtin_format_patch_usage[] = {
N_("git format-patch [options] [<since> | <revision range>]"),
NULL
};
static int keep_subject = 0;
static int keep_callback(const struct option *opt, const char *arg, int unset)
{
((struct rev_info *)opt->value)->total = -1;
keep_subject = 1;
return 0;
}
static int subject_prefix = 0;
static int subject_prefix_callback(const struct option *opt, const char *arg,
int unset)
{
subject_prefix = 1;
((struct rev_info *)opt->value)->subject_prefix = arg;
return 0;
}
static int numbered_cmdline_opt = 0;
static int numbered_callback(const struct option *opt, const char *arg,
int unset)
{
*(int *)opt->value = numbered_cmdline_opt = unset ? 0 : 1;
if (unset)
auto_number = 0;
return 0;
}
static int no_numbered_callback(const struct option *opt, const char *arg,
int unset)
{
return numbered_callback(opt, arg, 1);
}
static int output_directory_callback(const struct option *opt, const char *arg,
int unset)
{
const char **dir = (const char **)opt->value;
if (*dir)
die(_("Two output directories?"));
*dir = arg;
return 0;
}
static int thread_callback(const struct option *opt, const char *arg, int unset)
{
int *thread = (int *)opt->value;
if (unset)
*thread = 0;
else if (!arg || !strcmp(arg, "shallow"))
*thread = THREAD_SHALLOW;
else if (!strcmp(arg, "deep"))
*thread = THREAD_DEEP;
else
return 1;
return 0;
}
static int attach_callback(const struct option *opt, const char *arg, int unset)
{
struct rev_info *rev = (struct rev_info *)opt->value;
if (unset)
rev->mime_boundary = NULL;
else if (arg)
rev->mime_boundary = arg;
else
rev->mime_boundary = git_version_string;
rev->no_inline = unset ? 0 : 1;
return 0;
}
static int inline_callback(const struct option *opt, const char *arg, int unset)
{
struct rev_info *rev = (struct rev_info *)opt->value;
if (unset)
rev->mime_boundary = NULL;
else if (arg)
rev->mime_boundary = arg;
else
rev->mime_boundary = git_version_string;
rev->no_inline = 0;
return 0;
}
static int header_callback(const struct option *opt, const char *arg, int unset)
{
if (unset) {
string_list_clear(&extra_hdr, 0);
string_list_clear(&extra_to, 0);
string_list_clear(&extra_cc, 0);
} else {
add_header(arg);
}
return 0;
}
static int to_callback(const struct option *opt, const char *arg, int unset)
{
if (unset)
string_list_clear(&extra_to, 0);
else
string_list_append(&extra_to, arg);
return 0;
}
static int cc_callback(const struct option *opt, const char *arg, int unset)
{
if (unset)
string_list_clear(&extra_cc, 0);
else
string_list_append(&extra_cc, arg);
return 0;
}
static int from_callback(const struct option *opt, const char *arg, int unset)
{
char **from = opt->value;
free(*from);
if (unset)
*from = NULL;
else if (arg)
*from = xstrdup(arg);
else
*from = xstrdup(git_committer_info(IDENT_NO_DATE));
return 0;
}
int cmd_format_patch(int argc, const char **argv, const char *prefix)
{
struct commit *commit;
struct commit **list = NULL;
struct rev_info rev;
struct setup_revision_opt s_r_opt;
int nr = 0, total, i;
int use_stdout = 0;
int start_number = -1;
int just_numbers = 0;
int ignore_if_in_upstream = 0;
int cover_letter = -1;
int boundary_count = 0;
int no_binary_diff = 0;
struct commit *origin = NULL;
const char *in_reply_to = NULL;
struct patch_ids ids;
struct strbuf buf = STRBUF_INIT;
int use_patch_format = 0;
int quiet = 0;
int reroll_count = -1;
char *branch_name = NULL;
char *from = NULL;
const struct option builtin_format_patch_options[] = {
{ OPTION_CALLBACK, 'n', "numbered", &numbered, NULL,
N_("use [PATCH n/m] even with a single patch"),
PARSE_OPT_NOARG, numbered_callback },
{ OPTION_CALLBACK, 'N', "no-numbered", &numbered, NULL,
N_("use [PATCH] even with multiple patches"),
PARSE_OPT_NOARG, no_numbered_callback },
OPT_BOOL('s', "signoff", &do_signoff, N_("add Signed-off-by:")),
OPT_BOOL(0, "stdout", &use_stdout,
N_("print patches to standard out")),
OPT_BOOL(0, "cover-letter", &cover_letter,
N_("generate a cover letter")),
OPT_BOOL(0, "numbered-files", &just_numbers,
N_("use simple number sequence for output file names")),
OPT_STRING(0, "suffix", &fmt_patch_suffix, N_("sfx"),
N_("use <sfx> instead of '.patch'")),
OPT_INTEGER(0, "start-number", &start_number,
N_("start numbering patches at <n> instead of 1")),
OPT_INTEGER('v', "reroll-count", &reroll_count,
N_("mark the series as Nth re-roll")),
{ OPTION_CALLBACK, 0, "subject-prefix", &rev, N_("prefix"),
N_("Use [<prefix>] instead of [PATCH]"),
PARSE_OPT_NONEG, subject_prefix_callback },
{ OPTION_CALLBACK, 'o', "output-directory", &output_directory,
N_("dir"), N_("store resulting files in <dir>"),
PARSE_OPT_NONEG, output_directory_callback },
{ OPTION_CALLBACK, 'k', "keep-subject", &rev, NULL,
N_("don't strip/add [PATCH]"),
PARSE_OPT_NOARG | PARSE_OPT_NONEG, keep_callback },
OPT_BOOL(0, "no-binary", &no_binary_diff,
N_("don't output binary diffs")),
OPT_BOOL(0, "ignore-if-in-upstream", &ignore_if_in_upstream,
N_("don't include a patch matching a commit upstream")),
{ OPTION_SET_INT, 'p', "no-stat", &use_patch_format, NULL,
N_("show patch format instead of default (patch + stat)"),
PARSE_OPT_NONEG | PARSE_OPT_NOARG, NULL, 1},
OPT_GROUP(N_("Messaging")),
{ OPTION_CALLBACK, 0, "add-header", NULL, N_("header"),
N_("add email header"), 0, header_callback },
{ OPTION_CALLBACK, 0, "to", NULL, N_("email"), N_("add To: header"),
0, to_callback },
{ OPTION_CALLBACK, 0, "cc", NULL, N_("email"), N_("add Cc: header"),
0, cc_callback },
{ OPTION_CALLBACK, 0, "from", &from, N_("ident"),
N_("set From address to <ident> (or committer ident if absent)"),
PARSE_OPT_OPTARG, from_callback },
OPT_STRING(0, "in-reply-to", &in_reply_to, N_("message-id"),
N_("make first mail a reply to <message-id>")),
{ OPTION_CALLBACK, 0, "attach", &rev, N_("boundary"),
N_("attach the patch"), PARSE_OPT_OPTARG,
attach_callback },
{ OPTION_CALLBACK, 0, "inline", &rev, N_("boundary"),
N_("inline the patch"),
PARSE_OPT_OPTARG | PARSE_OPT_NONEG,
inline_callback },
{ OPTION_CALLBACK, 0, "thread", &thread, N_("style"),
N_("enable message threading, styles: shallow, deep"),
PARSE_OPT_OPTARG, thread_callback },
OPT_STRING(0, "signature", &signature, N_("signature"),
N_("add a signature")),
OPT__QUIET(&quiet, N_("don't print the patch filenames")),
OPT_END()
};
extra_hdr.strdup_strings = 1;
extra_to.strdup_strings = 1;
extra_cc.strdup_strings = 1;
init_grep_defaults();
git_config(git_format_config, NULL);
init_revisions(&rev, prefix);
rev.commit_format = CMIT_FMT_EMAIL;
rev.verbose_header = 1;
rev.diff = 1;
rev.max_parents = 1;
DIFF_OPT_SET(&rev.diffopt, RECURSIVE);
rev.subject_prefix = fmt_patch_subject_prefix;
memset(&s_r_opt, 0, sizeof(s_r_opt));
s_r_opt.def = "HEAD";
s_r_opt.revarg_opt = REVARG_COMMITTISH;
if (default_attach) {
rev.mime_boundary = default_attach;
rev.no_inline = 1;
}
/*
* Parse the arguments before setup_revisions(), or something
* like "git format-patch -o a123 HEAD^.." may fail; a123 is
* possibly a valid SHA1.
*/
argc = parse_options(argc, argv, prefix, builtin_format_patch_options,
builtin_format_patch_usage,
PARSE_OPT_KEEP_ARGV0 | PARSE_OPT_KEEP_UNKNOWN |
PARSE_OPT_KEEP_DASHDASH);
if (0 < reroll_count) {
struct strbuf sprefix = STRBUF_INIT;
strbuf_addf(&sprefix, "%s v%d",
rev.subject_prefix, reroll_count);
rev.reroll_count = reroll_count;
rev.subject_prefix = strbuf_detach(&sprefix, NULL);
}
for (i = 0; i < extra_hdr.nr; i++) {
strbuf_addstr(&buf, extra_hdr.items[i].string);
strbuf_addch(&buf, '\n');
}
if (extra_to.nr)
strbuf_addstr(&buf, "To: ");
for (i = 0; i < extra_to.nr; i++) {
if (i)
strbuf_addstr(&buf, " ");
strbuf_addstr(&buf, extra_to.items[i].string);
if (i + 1 < extra_to.nr)
strbuf_addch(&buf, ',');
strbuf_addch(&buf, '\n');
}
if (extra_cc.nr)
strbuf_addstr(&buf, "Cc: ");
for (i = 0; i < extra_cc.nr; i++) {
if (i)
strbuf_addstr(&buf, " ");
strbuf_addstr(&buf, extra_cc.items[i].string);
if (i + 1 < extra_cc.nr)
strbuf_addch(&buf, ',');
strbuf_addch(&buf, '\n');
}
rev.extra_headers = strbuf_detach(&buf, NULL);
if (from) {
if (split_ident_line(&rev.from_ident, from, strlen(from)))
die(_("invalid ident line: %s"), from);
}
if (start_number < 0)
start_number = 1;
/*
* If numbered is set solely due to format.numbered in config,
* and it would conflict with --keep-subject (-k) from the
* command line, reset "numbered".
*/
if (numbered && keep_subject && !numbered_cmdline_opt)
numbered = 0;
if (numbered && keep_subject)
die (_("-n and -k are mutually exclusive."));
if (keep_subject && subject_prefix)
die (_("--subject-prefix and -k are mutually exclusive."));
rev.preserve_subject = keep_subject;
argc = setup_revisions(argc, argv, &rev, &s_r_opt);
if (argc > 1)
die (_("unrecognized argument: %s"), argv[1]);
if (rev.diffopt.output_format & DIFF_FORMAT_NAME)
die(_("--name-only does not make sense"));
if (rev.diffopt.output_format & DIFF_FORMAT_NAME_STATUS)
die(_("--name-status does not make sense"));
if (rev.diffopt.output_format & DIFF_FORMAT_CHECKDIFF)
die(_("--check does not make sense"));
if (!use_patch_format &&
(!rev.diffopt.output_format ||
rev.diffopt.output_format == DIFF_FORMAT_PATCH))
rev.diffopt.output_format = DIFF_FORMAT_DIFFSTAT | DIFF_FORMAT_SUMMARY;
/* Always generate a patch */
rev.diffopt.output_format |= DIFF_FORMAT_PATCH;
if (!DIFF_OPT_TST(&rev.diffopt, TEXT) && !no_binary_diff)
DIFF_OPT_SET(&rev.diffopt, BINARY);
if (rev.show_notes)
init_display_notes(&rev.notes_opt);
if (!use_stdout)
output_directory = set_outdir(prefix, output_directory);
else
setup_pager();
if (output_directory) {
if (use_stdout)
die(_("standard output, or directory, which one?"));
if (mkdir(output_directory, 0777) < 0 && errno != EEXIST)
die_errno(_("Could not create directory '%s'"),
output_directory);
}
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 02:42:35 +02:00
if (rev.pending.nr == 1) {
int check_head = 0;
if (rev.max_count < 0 && !rev.show_root_diff) {
/*
* This is traditional behaviour of "git format-patch
* origin" that prepares what the origin side still
* does not have.
*/
rev.pending.objects[0].item->flags |= UNINTERESTING;
add_head_to_pending(&rev);
check_head = 1;
}
/*
* Otherwise, it is "format-patch -22 HEAD", and/or
* "format-patch --root HEAD". The user wants
* get_revision() to do the usual traversal.
*/
if (!strcmp(rev.pending.objects[0].name, "HEAD"))
check_head = 1;
if (check_head) {
unsigned char sha1[20];
const char *ref;
ref = resolve_ref_unsafe("HEAD", sha1, 1, NULL);
if (ref && starts_with(ref, "refs/heads/"))
branch_name = xstrdup(ref + strlen("refs/heads/"));
else
branch_name = xstrdup(""); /* no branch */
}
}
/*
* We cannot move this anywhere earlier because we do want to
* know if --root was given explicitly from the command line.
*/
rev.show_root_diff = 1;
if (ignore_if_in_upstream) {
/* Don't say anything if head and upstream are the same. */
if (rev.pending.nr == 2) {
struct object_array_entry *o = rev.pending.objects;
if (hashcmp(o[0].item->sha1, o[1].item->sha1) == 0)
return 0;
}
get_patch_ids(&rev, &ids);
}
if (!use_stdout)
realstdout = xfdopen(xdup(1), "w");
if (prepare_revision_walk(&rev))
die(_("revision walk setup failed"));
rev.boundary = 1;
while ((commit = get_revision(&rev)) != NULL) {
if (commit->object.flags & BOUNDARY) {
boundary_count++;
origin = (boundary_count == 1) ? commit : NULL;
continue;
}
if (ignore_if_in_upstream &&
has_commit_patch_id(commit, &ids))
continue;
nr++;
list = xrealloc(list, nr * sizeof(list[0]));
list[nr - 1] = commit;
}
if (nr == 0)
/* nothing to do */
return 0;
total = nr;
if (!keep_subject && auto_number && total > 1)
numbered = 1;
if (numbered)
rev.total = total + start_number - 1;
if (cover_letter == -1) {
if (config_cover_letter == COVER_AUTO)
cover_letter = (total > 1);
else
cover_letter = (config_cover_letter == COVER_ON);
}
if (in_reply_to || thread || cover_letter)
rev.ref_message_ids = xcalloc(1, sizeof(struct string_list));
if (in_reply_to) {
const char *msgid = clean_message_id(in_reply_to);
string_list_append(rev.ref_message_ids, msgid);
}
rev.numbered_files = just_numbers;
rev.patch_suffix = fmt_patch_suffix;
if (cover_letter) {
if (thread)
gen_message_id(&rev, "cover");
make_cover_letter(&rev, use_stdout,
origin, nr, list, branch_name, quiet);
total++;
start_number--;
}
rev.add_signoff = do_signoff;
while (0 <= --nr) {
int shown;
commit = list[nr];
rev.nr = total - nr + (start_number - 1);
/* Make the second and subsequent mails replies to the first */
if (thread) {
/* Have we already had a message ID? */
if (rev.message_id) {
/*
* For deep threading: make every mail
* a reply to the previous one, no
* matter what other options are set.
*
* For shallow threading:
*
* Without --cover-letter and
* --in-reply-to, make every mail a
* reply to the one before.
*
* With --in-reply-to but no
* --cover-letter, make every mail a
* reply to the <reply-to>.
*
* With --cover-letter, make every
* mail but the cover letter a reply
* to the cover letter. The cover
* letter is a reply to the
* --in-reply-to, if specified.
*/
if (thread == THREAD_SHALLOW
&& rev.ref_message_ids->nr > 0
&& (!cover_letter || rev.nr > 1))
free(rev.message_id);
else
string_list_append(rev.ref_message_ids,
rev.message_id);
}
gen_message_id(&rev, sha1_to_hex(commit->object.sha1));
}
if (!use_stdout &&
reopen_stdout(rev.numbered_files ? NULL : commit, NULL, &rev, quiet))
die(_("Failed to create output files"));
shown = log_tree_commit(&rev, commit);
free(commit->buffer);
commit->buffer = NULL;
/* We put one extra blank line between formatted
* patches and this flag is used by log-tree code
* to see if it needs to emit a LF before showing
* the log; when using one file per patch, we do
* not want the extra blank line.
*/
if (!use_stdout)
rev.shown_one = 0;
if (shown) {
if (rev.mime_boundary)
printf("\n--%s%s--\n\n\n",
mime_boundary_leader,
rev.mime_boundary);
else
print_signature();
}
if (!use_stdout)
fclose(stdout);
}
free(list);
free(branch_name);
string_list_clear(&extra_to, 0);
string_list_clear(&extra_cc, 0);
string_list_clear(&extra_hdr, 0);
if (ignore_if_in_upstream)
free_patch_ids(&ids);
return 0;
}
static int add_pending_commit(const char *arg, struct rev_info *revs, int flags)
{
unsigned char sha1[20];
if (get_sha1(arg, sha1) == 0) {
struct commit *commit = lookup_commit_reference(sha1);
if (commit) {
commit->object.flags |= flags;
add_pending_object(revs, &commit->object, arg);
return 0;
}
}
return -1;
}
static const char * const cherry_usage[] = {
N_("git cherry [-v] [<upstream> [<head> [<limit>]]]"),
NULL
};
static void print_commit(char sign, struct commit *commit, int verbose,
int abbrev)
{
if (!verbose) {
printf("%c %s\n", sign,
find_unique_abbrev(commit->object.sha1, abbrev));
} else {
struct strbuf buf = STRBUF_INIT;
pp_commit_easy(CMIT_FMT_ONELINE, commit, &buf);
printf("%c %s %s\n", sign,
find_unique_abbrev(commit->object.sha1, abbrev),
buf.buf);
strbuf_release(&buf);
}
}
int cmd_cherry(int argc, const char **argv, const char *prefix)
{
struct rev_info revs;
struct patch_ids ids;
struct commit *commit;
struct commit_list *list = NULL;
struct branch *current_branch;
const char *upstream;
const char *head = "HEAD";
const char *limit = NULL;
int verbose = 0, abbrev = 0;
struct option options[] = {
OPT__ABBREV(&abbrev),
OPT__VERBOSE(&verbose, N_("be verbose")),
OPT_END()
};
argc = parse_options(argc, argv, prefix, options, cherry_usage, 0);
switch (argc) {
case 3:
limit = argv[2];
/* FALLTHROUGH */
case 2:
head = argv[1];
/* FALLTHROUGH */
case 1:
upstream = argv[0];
break;
default:
current_branch = branch_get(NULL);
if (!current_branch || !current_branch->merge
|| !current_branch->merge[0]
|| !current_branch->merge[0]->dst) {
fprintf(stderr, _("Could not find a tracked"
" remote branch, please"
" specify <upstream> manually.\n"));
usage_with_options(cherry_usage, options);
}
upstream = current_branch->merge[0]->dst;
}
init_revisions(&revs, prefix);
revs.max_parents = 1;
if (add_pending_commit(head, &revs, 0))
die(_("Unknown commit %s"), head);
if (add_pending_commit(upstream, &revs, UNINTERESTING))
die(_("Unknown commit %s"), upstream);
/* Don't say anything if head and upstream are the same. */
if (revs.pending.nr == 2) {
struct object_array_entry *o = revs.pending.objects;
if (hashcmp(o[0].item->sha1, o[1].item->sha1) == 0)
return 0;
}
get_patch_ids(&revs, &ids);
if (limit && add_pending_commit(limit, &revs, UNINTERESTING))
die(_("Unknown commit %s"), limit);
/* reverse the list of commits */
if (prepare_revision_walk(&revs))
die(_("revision walk setup failed"));
while ((commit = get_revision(&revs)) != NULL) {
commit_list_insert(commit, &list);
}
while (list) {
char sign = '+';
commit = list->item;
if (has_commit_patch_id(commit, &ids))
sign = '-';
print_commit(sign, commit, verbose, abbrev);
list = list->next;
}
free_patch_ids(&ids);
return 0;
}