git-commit-vandalism/builtin-rev-list.c

295 lines
6.4 KiB
C
Raw Normal View History

#include "cache.h"
#include "refs.h"
#include "tag.h"
#include "commit.h"
#include "tree.h"
#include "blob.h"
#include "tree-walk.h"
#include "diff.h"
#include "revision.h"
#include "list-objects.h"
#include "builtin.h"
/* bits #0-15 in revision.h */
#define COUNTED (1u<<16)
static const char rev_list_usage[] =
"git-rev-list [OPTION] <commit-id>... [ -- paths... ]\n"
" limiting output:\n"
" --max-count=nr\n"
" --max-age=epoch\n"
" --min-age=epoch\n"
" --sparse\n"
" --no-merges\n"
" --remove-empty\n"
" --all\n"
" --stdin\n"
" ordering output:\n"
" --topo-order\n"
" --date-order\n"
" formatting output:\n"
" --parents\n"
" --objects | --objects-edge\n"
" --unpacked\n"
" --header | --pretty\n"
" --abbrev=nr | --no-abbrev\n"
" --abbrev-commit\n"
" special purpose:\n"
" --bisect"
;
static struct rev_info revs;
static int bisect_list;
static int show_timestamp;
static int hdr_termination;
Log message printout cleanups On Sun, 16 Apr 2006, Junio C Hamano wrote: > > In the mid-term, I am hoping we can drop the generate_header() > callchain _and_ the custom code that formats commit log in-core, > found in cmd_log_wc(). Ok, this was nastier than expected, just because the dependencies between the different log-printing stuff were absolutely _everywhere_, but here's a patch that does exactly that. The patch is not very easy to read, and the "--patch-with-stat" thing is still broken (it does not call the "show_log()" thing properly for merges). That's not a new bug. In the new world order it _should_ do something like if (rev->logopt) show_log(rev, rev->logopt, "---\n"); but it doesn't. I haven't looked at the --with-stat logic, so I left it alone. That said, this patch removes more lines than it adds, and in particular, the "cmd_log_wc()" loop is now a very clean: while ((commit = get_revision(rev)) != NULL) { log_tree_commit(rev, commit); free(commit->buffer); commit->buffer = NULL; } so it doesn't get much prettier than this. All the complexity is entirely hidden in log-tree.c, and any code that needs to flush the log literally just needs to do the "if (rev->logopt) show_log(...)" incantation. I had to make the combined_diff() logic take a "struct rev_info" instead of just a "struct diff_options", but that part is pretty clean. This does change "git whatchanged" from using "diff-tree" as the commit descriptor to "commit", and I changed one of the tests to reflect that new reality. Otherwise everything still passes, and my other tests look fine too. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-04-17 20:59:32 +02:00
static const char *header_prefix;
static void show_commit(struct commit *commit)
{
if (show_timestamp)
printf("%lu ", commit->date);
Log message printout cleanups On Sun, 16 Apr 2006, Junio C Hamano wrote: > > In the mid-term, I am hoping we can drop the generate_header() > callchain _and_ the custom code that formats commit log in-core, > found in cmd_log_wc(). Ok, this was nastier than expected, just because the dependencies between the different log-printing stuff were absolutely _everywhere_, but here's a patch that does exactly that. The patch is not very easy to read, and the "--patch-with-stat" thing is still broken (it does not call the "show_log()" thing properly for merges). That's not a new bug. In the new world order it _should_ do something like if (rev->logopt) show_log(rev, rev->logopt, "---\n"); but it doesn't. I haven't looked at the --with-stat logic, so I left it alone. That said, this patch removes more lines than it adds, and in particular, the "cmd_log_wc()" loop is now a very clean: while ((commit = get_revision(rev)) != NULL) { log_tree_commit(rev, commit); free(commit->buffer); commit->buffer = NULL; } so it doesn't get much prettier than this. All the complexity is entirely hidden in log-tree.c, and any code that needs to flush the log literally just needs to do the "if (rev->logopt) show_log(...)" incantation. I had to make the combined_diff() logic take a "struct rev_info" instead of just a "struct diff_options", but that part is pretty clean. This does change "git whatchanged" from using "diff-tree" as the commit descriptor to "commit", and I changed one of the tests to reflect that new reality. Otherwise everything still passes, and my other tests look fine too. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-04-17 20:59:32 +02:00
if (header_prefix)
fputs(header_prefix, stdout);
if (commit->object.flags & BOUNDARY)
putchar('-');
else if (revs.left_right) {
if (commit->object.flags & SYMMETRIC_LEFT)
putchar('<');
else
putchar('>');
}
if (revs.abbrev_commit && revs.abbrev)
fputs(find_unique_abbrev(commit->object.sha1, revs.abbrev),
stdout);
else
fputs(sha1_to_hex(commit->object.sha1), stdout);
if (revs.parents) {
struct commit_list *parents = commit->parents;
while (parents) {
struct object *o = &(parents->item->object);
parents = parents->next;
if (o->flags & TMP_MARK)
continue;
printf(" %s", sha1_to_hex(o->sha1));
o->flags |= TMP_MARK;
}
/* TMP_MARK is a general purpose flag that can
* be used locally, but the user should clean
* things up after it is done with them.
*/
for (parents = commit->parents;
parents;
parents = parents->next)
parents->item->object.flags &= ~TMP_MARK;
}
if (revs.commit_format == CMIT_FMT_ONELINE)
putchar(' ');
else
putchar('\n');
if (revs.verbose_header) {
static char pretty_header[16384];
pretty_print_commit(revs.commit_format, commit, ~0,
pretty_header, sizeof(pretty_header),
revs.abbrev, NULL, NULL, revs.relative_date);
printf("%s%c", pretty_header, hdr_termination);
}
fflush(stdout);
if (commit->parents) {
free_commit_list(commit->parents);
commit->parents = NULL;
}
free(commit->buffer);
commit->buffer = NULL;
[PATCH] Modify git-rev-list to linearise the commit history in merge order. This patch linearises the GIT commit history graph into merge order which is defined by invariants specified in Documentation/git-rev-list.txt. The linearisation produced by this patch is superior in an objective sense to that produced by the existing git-rev-list implementation in that the linearisation produced is guaranteed to have the minimum number of discontinuities, where a discontinuity is defined as an adjacent pair of commits in the output list which are not related in a direct child-parent relationship. With this patch a graph like this: a4 --- | \ \ | b4 | |/ | | a3 | | | | | a2 | | | | c3 | | | | | c2 | b3 | | | /| | b2 | | | c1 | | / | b1 a1 | | | a0 | | / root Sorts like this: = a4 | c3 | c2 | c1 ^ b4 | b3 | b2 | b1 ^ a3 | a2 | a1 | a0 = root Instead of this: = a4 | c3 ^ b4 | a3 ^ c2 ^ b3 ^ a2 ^ b2 ^ c1 ^ a1 ^ b1 ^ a0 = root A test script, t/t6000-rev-list.sh, includes a test which demonstrates that the linearisation produced by --merge-order has less discontinuities than the linearisation produced by git-rev-list without the --merge-order flag specified. To see this, do the following: cd t ./t6000-rev-list.sh cd trash cat actual-default-order cat actual-merge-order The existing behaviour of git-rev-list is preserved, by default. To obtain the modified behaviour, specify --merge-order or --merge-order --show-breaks on the command line. This version of the patch has been tested on the git repository and also on the linux-2.6 repository and has reasonable performance on both - ~50-100% slower than the original algorithm. This version of the patch has incorporated a functional equivalent of the Linus' output limiting algorithm into the merge-order algorithm itself. This operates per the notes associated with Linus' commit 337cb3fb8da45f10fe9a0c3cf571600f55ead2ce. This version has incorporated Linus' feedback regarding proposed changes to rev-list.c. (see: [PATCH] Factor out filtering in rev-list.c) This version has improved the way sort_first_epoch marks commits as uninteresting. For more details about this change, refer to Documentation/git-rev-list.txt and http://blackcubes.dyndns.org/epoch/. Signed-off-by: Jon Seymour <jon.seymour@gmail.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-06 17:39:40 +02:00
}
static void show_object(struct object_array_entry *p)
{
/* An object with name "foo\n0000000..." can be used to
* confuse downstream git-pack-objects very badly.
*/
const char *ep = strchr(p->name, '\n');
if (ep) {
printf("%s %.*s\n", sha1_to_hex(p->item->sha1),
(int) (ep - p->name),
p->name);
}
else
printf("%s %s\n", sha1_to_hex(p->item->sha1), p->name);
}
static void show_edge(struct commit *commit)
{
printf("-%s\n", sha1_to_hex(commit->object.sha1));
}
/*
* This is a truly stupid algorithm, but it's only
* used for bisection, and we just don't care enough.
*
* We care just barely enough to avoid recursing for
* non-merge entries.
*/
static int count_distance(struct commit_list *entry)
{
int nr = 0;
while (entry) {
struct commit *commit = entry->item;
struct commit_list *p;
if (commit->object.flags & (UNINTERESTING | COUNTED))
break;
if (!revs.prune_fn || (commit->object.flags & TREECHANGE))
nr++;
commit->object.flags |= COUNTED;
p = commit->parents;
entry = p;
if (p) {
p = p->next;
while (p) {
nr += count_distance(p);
p = p->next;
}
}
}
return nr;
}
static void clear_distance(struct commit_list *list)
{
while (list) {
struct commit *commit = list->item;
commit->object.flags &= ~COUNTED;
list = list->next;
}
}
static struct commit_list *find_bisection(struct commit_list *list)
{
int nr, closest;
struct commit_list *p, *best;
nr = 0;
p = list;
while (p) {
if (!revs.prune_fn || (p->item->object.flags & TREECHANGE))
nr++;
p = p->next;
}
Fix path-limited "rev-list --bisect" termination condition. In a path-limited bisection, when the $bad commit is not changing the limited path, and the number of suspects is 1, the code miscounted and returned $bad from find_bisection(), which is not marked with TREECHANGE. This is of course filtered by the output routine, resulting in an empty output, in turn causing git-bisect driver to say "$bad was both good and bad". Illustration. Suppose you have these four commits, and only C changes path P. You know D is bad and A is good. A---B---C*--D git-bisect driver runs this to find a bisection point: $ git rev-list --bisect A..D -- P which calls find_bisection() with B, C and D. The set of commits that is given to this function is the same set of commits as rev-list without --bisect option and pathspec returns. Among them, only C is marked with TREECHANGE. Let's call the set of commits given to find_bisection() that are marked with TREECHANGE (or all of them if no path limiter is in effect) "the bisect set". In the above example, the size of the bisect set is 1 (contains only "C"). For each commit in its input, find_bisection() computes the number of commits it can reach in the bisect set. For a commit in the bisect set, this number includes itself, so the number is 1 or more. This number is called "depth", and computed by count_distance() function. When you have a bisect set of N commits, and a commit has depth D, how good is your bisection if you returned that commit? How good this bisection is can be measured by how many commits are effectively tested "together" by testing one commit. Currently you have (N-1) untested commits (the tip of the bisect set, although it is included in the bisect set, is already known to be bad). If the commit with depth D turns out to be bad, then your next bisect set will have D commits and you will have (D-1) untested commits left, which means you tested (N-1)-(D-1) = (N-D) commits with this bisection. If it turns out to be good, then your next bisect set will have (N-D) commits, and you will have (N-D-1) untested commits left, which means you tested (N-1)-(N-D-1) = D commits with this bisection. Therefore, the goodness of this bisection is is min(N-D, D), and find_bisection() function tries to find a commit that maximizes this, by initializing "closest" variable to 0 and whenever a commit with the goodness that is larger than the current "closest" is found, that commit and its goodness are remembered by updating "closest" variable. The "the commit with the best goodness so far" is kept in "best" variable, and is initialized to a commit that happens to be at the beginning of the list of commits given to this function (which may or may not be in the bisect set when path-limit is in use). However, when N is 1, then the sole tree-changing commit has depth of 1, and min(N-D, D) evaluates to 0. This is not larger than the initial value of "closest", and the "so far the best one" commit is never replaced in the loop. When path-limit is not in use, this is not a problem, as any commit in the input set is tree-changing. But when path-limit is in use, and when the starting "bad" commit does not change the specified path, it is not correct to return it. Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-23 21:34:49 +01:00
closest = -1;
best = list;
for (p = list; p; p = p->next) {
int distance;
if (revs.prune_fn && !(p->item->object.flags & TREECHANGE))
continue;
distance = count_distance(p);
clear_distance(list);
if (nr - distance < distance)
distance = nr - distance;
if (distance > closest) {
best = p;
closest = distance;
}
}
if (best)
best->next = NULL;
return best;
}
static void read_revisions_from_stdin(struct rev_info *revs)
{
char line[1000];
while (fgets(line, sizeof(line), stdin) != NULL) {
int len = strlen(line);
if (line[len - 1] == '\n')
line[--len] = 0;
if (!len)
break;
if (line[0] == '-')
die("options not supported in --stdin mode");
if (handle_revision_arg(line, revs, 0, 1))
die("bad revision '%s'", line);
}
}
int cmd_rev_list(int argc, const char **argv, const char *prefix)
{
struct commit_list *list;
int i;
int read_from_stdin = 0;
git_config(git_default_config);
init_revisions(&revs, prefix);
revs.abbrev = 0;
revs.commit_format = CMIT_FMT_UNSPECIFIED;
argc = setup_revisions(argc, argv, &revs, NULL);
for (i = 1 ; i < argc; i++) {
2005-10-21 06:25:09 +02:00
const char *arg = argv[i];
if (!strcmp(arg, "--header")) {
revs.verbose_header = 1;
continue;
}
if (!strcmp(arg, "--timestamp")) {
show_timestamp = 1;
continue;
}
if (!strcmp(arg, "--bisect")) {
bisect_list = 1;
continue;
}
if (!strcmp(arg, "--stdin")) {
if (read_from_stdin++)
die("--stdin given twice?");
read_revisions_from_stdin(&revs);
continue;
}
usage(rev_list_usage);
}
if (revs.commit_format != CMIT_FMT_UNSPECIFIED) {
/* The command line has a --pretty */
hdr_termination = '\n';
if (revs.commit_format == CMIT_FMT_ONELINE)
Log message printout cleanups On Sun, 16 Apr 2006, Junio C Hamano wrote: > > In the mid-term, I am hoping we can drop the generate_header() > callchain _and_ the custom code that formats commit log in-core, > found in cmd_log_wc(). Ok, this was nastier than expected, just because the dependencies between the different log-printing stuff were absolutely _everywhere_, but here's a patch that does exactly that. The patch is not very easy to read, and the "--patch-with-stat" thing is still broken (it does not call the "show_log()" thing properly for merges). That's not a new bug. In the new world order it _should_ do something like if (rev->logopt) show_log(rev, rev->logopt, "---\n"); but it doesn't. I haven't looked at the --with-stat logic, so I left it alone. That said, this patch removes more lines than it adds, and in particular, the "cmd_log_wc()" loop is now a very clean: while ((commit = get_revision(rev)) != NULL) { log_tree_commit(rev, commit); free(commit->buffer); commit->buffer = NULL; } so it doesn't get much prettier than this. All the complexity is entirely hidden in log-tree.c, and any code that needs to flush the log literally just needs to do the "if (rev->logopt) show_log(...)" incantation. I had to make the combined_diff() logic take a "struct rev_info" instead of just a "struct diff_options", but that part is pretty clean. This does change "git whatchanged" from using "diff-tree" as the commit descriptor to "commit", and I changed one of the tests to reflect that new reality. Otherwise everything still passes, and my other tests look fine too. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-04-17 20:59:32 +02:00
header_prefix = "";
else
Log message printout cleanups On Sun, 16 Apr 2006, Junio C Hamano wrote: > > In the mid-term, I am hoping we can drop the generate_header() > callchain _and_ the custom code that formats commit log in-core, > found in cmd_log_wc(). Ok, this was nastier than expected, just because the dependencies between the different log-printing stuff were absolutely _everywhere_, but here's a patch that does exactly that. The patch is not very easy to read, and the "--patch-with-stat" thing is still broken (it does not call the "show_log()" thing properly for merges). That's not a new bug. In the new world order it _should_ do something like if (rev->logopt) show_log(rev, rev->logopt, "---\n"); but it doesn't. I haven't looked at the --with-stat logic, so I left it alone. That said, this patch removes more lines than it adds, and in particular, the "cmd_log_wc()" loop is now a very clean: while ((commit = get_revision(rev)) != NULL) { log_tree_commit(rev, commit); free(commit->buffer); commit->buffer = NULL; } so it doesn't get much prettier than this. All the complexity is entirely hidden in log-tree.c, and any code that needs to flush the log literally just needs to do the "if (rev->logopt) show_log(...)" incantation. I had to make the combined_diff() logic take a "struct rev_info" instead of just a "struct diff_options", but that part is pretty clean. This does change "git whatchanged" from using "diff-tree" as the commit descriptor to "commit", and I changed one of the tests to reflect that new reality. Otherwise everything still passes, and my other tests look fine too. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-04-17 20:59:32 +02:00
header_prefix = "commit ";
}
else if (revs.verbose_header)
/* Only --header was specified */
revs.commit_format = CMIT_FMT_RAW;
list = revs.commits;
if ((!list &&
(!(revs.tag_objects||revs.tree_objects||revs.blob_objects) &&
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
!revs.pending.nr)) ||
revs.diff)
usage(rev_list_usage);
save_commit_buffer = revs.verbose_header || revs.grep_filter;
track_object_refs = 0;
rev-list --bisect: limit list before bisecting. I noticed bisect does not work well without both good and bad. Running this script in git.git repository would give you quite different results: #!/bin/sh initial=e83c5163316f89bfbde7d9ab23ca2e25604af290 mid0=`git rev-list --bisect ^$initial --all` git rev-list $mid0 | wc -l git rev-list ^$mid0 --all | wc -l mid1=`git rev-list --bisect --all` git rev-list $mid1 | wc -l git rev-list ^$mid1 --all | wc -l The $initial commit is the very first commit you made. The first midpoint bisects things evenly as designed, but the latter does not. The reason I got interested in this was because I was wondering if something like the following would help people converting a huge repository from foreign SCM, or preparing a repository to be fetched over plain dumb HTTP only: #!/bin/sh N=4 P=.git/objects/pack bottom= while test 0 \< $N do N=$((N-1)) if test -z "$bottom" then newbottom=`git rev-list --bisect --all` else newbottom=`git rev-list --bisect ^$bottom --all` fi if test -z "$bottom" then rev_list="$newbottom" elif test 0 = $N then rev_list="^$bottom --all" else rev_list="^$bottom $newbottom" fi p=$(git rev-list --unpacked --objects $rev_list | git pack-objects $P/pack) git show-index <$P/pack-$p.idx | wc -l bottom=$newbottom done The idea is to pack older half of the history to one pack, then older half of the remaining history to another, to continue a few times, using finer granularity as we get closer to the tip. This may not matter, since for a truly huge history, running bisect number of times could be quite time consuming, and we might be better off running "git rev-list --all" once into a temporary file, and manually pick cut-off points from the resulting list of commits. After all we are talking about "approximately half" for such an usage, and older history does not matter much. Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-04-15 00:57:32 +02:00
if (bisect_list)
revs.limited = 1;
prepare_revision_walk(&revs);
if (revs.tree_objects)
mark_edges_uninteresting(revs.commits, &revs, show_edge);
if (bisect_list)
revs.commits = find_bisection(revs.commits);
traverse_commit_list(&revs, show_commit, show_object);
return 0;
}