mirror of
https://github.com/git/git
synced 2024-08-25 10:45:59 +00:00
![jon@blackcubes.dyndns.org](/assets/img/avatar_default.png)
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 337cb3fb8d
.
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>
305 lines
6.2 KiB
C
305 lines
6.2 KiB
C
#include <ctype.h>
|
|
#include "tag.h"
|
|
#include "commit.h"
|
|
#include "cache.h"
|
|
|
|
const char *commit_type = "commit";
|
|
|
|
static struct commit *check_commit(struct object *obj, unsigned char *sha1)
|
|
{
|
|
if (obj->type != commit_type) {
|
|
error("Object %s is a %s, not a commit",
|
|
sha1_to_hex(sha1), obj->type);
|
|
return NULL;
|
|
}
|
|
return (struct commit *) obj;
|
|
}
|
|
|
|
struct commit *lookup_commit_reference(unsigned char *sha1)
|
|
{
|
|
struct object *obj = parse_object(sha1);
|
|
|
|
if (!obj)
|
|
return NULL;
|
|
if (obj->type == tag_type)
|
|
obj = ((struct tag *)obj)->tagged;
|
|
return check_commit(obj, sha1);
|
|
}
|
|
|
|
struct commit *lookup_commit(unsigned char *sha1)
|
|
{
|
|
struct object *obj = lookup_object(sha1);
|
|
if (!obj) {
|
|
struct commit *ret = xmalloc(sizeof(struct commit));
|
|
memset(ret, 0, sizeof(struct commit));
|
|
created_object(sha1, &ret->object);
|
|
ret->object.type = commit_type;
|
|
return ret;
|
|
}
|
|
if (!obj->type)
|
|
obj->type = commit_type;
|
|
return check_commit(obj, sha1);
|
|
}
|
|
|
|
static unsigned long parse_commit_date(const char *buf)
|
|
{
|
|
unsigned long date;
|
|
|
|
if (memcmp(buf, "author", 6))
|
|
return 0;
|
|
while (*buf++ != '\n')
|
|
/* nada */;
|
|
if (memcmp(buf, "committer", 9))
|
|
return 0;
|
|
while (*buf++ != '>')
|
|
/* nada */;
|
|
date = strtoul(buf, NULL, 10);
|
|
if (date == ULONG_MAX)
|
|
date = 0;
|
|
return date;
|
|
}
|
|
|
|
int parse_commit_buffer(struct commit *item, void *buffer, unsigned long size)
|
|
{
|
|
void *bufptr = buffer;
|
|
unsigned char parent[20];
|
|
|
|
if (item->object.parsed)
|
|
return 0;
|
|
item->object.parsed = 1;
|
|
get_sha1_hex(bufptr + 5, parent);
|
|
item->tree = lookup_tree(parent);
|
|
if (item->tree)
|
|
add_ref(&item->object, &item->tree->object);
|
|
bufptr += 46; /* "tree " + "hex sha1" + "\n" */
|
|
while (!memcmp(bufptr, "parent ", 7) &&
|
|
!get_sha1_hex(bufptr + 7, parent)) {
|
|
struct commit *new_parent = lookup_commit(parent);
|
|
if (new_parent) {
|
|
commit_list_insert(new_parent, &item->parents);
|
|
add_ref(&item->object, &new_parent->object);
|
|
}
|
|
bufptr += 48;
|
|
}
|
|
item->date = parse_commit_date(bufptr);
|
|
return 0;
|
|
}
|
|
|
|
int parse_commit(struct commit *item)
|
|
{
|
|
char type[20];
|
|
void *buffer;
|
|
unsigned long size;
|
|
int ret;
|
|
|
|
if (item->object.parsed)
|
|
return 0;
|
|
buffer = read_sha1_file(item->object.sha1, type, &size);
|
|
if (!buffer)
|
|
return error("Could not read %s",
|
|
sha1_to_hex(item->object.sha1));
|
|
if (strcmp(type, commit_type)) {
|
|
free(buffer);
|
|
return error("Object %s not a commit",
|
|
sha1_to_hex(item->object.sha1));
|
|
}
|
|
ret = parse_commit_buffer(item, buffer, size);
|
|
if (!ret) {
|
|
item->buffer = buffer;
|
|
return 0;
|
|
}
|
|
free(buffer);
|
|
return ret;
|
|
}
|
|
|
|
struct commit_list *commit_list_insert(struct commit *item, struct commit_list **list_p)
|
|
{
|
|
struct commit_list *new_list = xmalloc(sizeof(struct commit_list));
|
|
new_list->item = item;
|
|
new_list->next = *list_p;
|
|
*list_p = new_list;
|
|
return new_list;
|
|
}
|
|
|
|
void free_commit_list(struct commit_list *list)
|
|
{
|
|
while (list) {
|
|
struct commit_list *temp = list;
|
|
list = temp->next;
|
|
free(temp);
|
|
}
|
|
}
|
|
|
|
void insert_by_date(struct commit_list **list, struct commit *item)
|
|
{
|
|
struct commit_list **pp = list;
|
|
struct commit_list *p;
|
|
while ((p = *pp) != NULL) {
|
|
if (p->item->date < item->date) {
|
|
break;
|
|
}
|
|
pp = &p->next;
|
|
}
|
|
commit_list_insert(item, pp);
|
|
}
|
|
|
|
|
|
void sort_by_date(struct commit_list **list)
|
|
{
|
|
struct commit_list *ret = NULL;
|
|
while (*list) {
|
|
insert_by_date(&ret, (*list)->item);
|
|
*list = (*list)->next;
|
|
}
|
|
*list = ret;
|
|
}
|
|
|
|
struct commit *pop_most_recent_commit(struct commit_list **list,
|
|
unsigned int mark)
|
|
{
|
|
struct commit *ret = (*list)->item;
|
|
struct commit_list *parents = ret->parents;
|
|
struct commit_list *old = *list;
|
|
|
|
*list = (*list)->next;
|
|
free(old);
|
|
|
|
while (parents) {
|
|
struct commit *commit = parents->item;
|
|
parse_commit(commit);
|
|
if (!(commit->object.flags & mark)) {
|
|
commit->object.flags |= mark;
|
|
insert_by_date(list, commit);
|
|
}
|
|
parents = parents->next;
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Generic support for pretty-printing the header
|
|
*/
|
|
static int get_one_line(const char *msg, unsigned long len)
|
|
{
|
|
int ret = 0;
|
|
|
|
while (len--) {
|
|
char c = *msg++;
|
|
ret++;
|
|
if (c == '\n')
|
|
break;
|
|
if (!c)
|
|
return 0;
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
static int add_author_info(enum cmit_fmt fmt, char *buf, const char *line, int len)
|
|
{
|
|
char *date;
|
|
unsigned int namelen;
|
|
unsigned long time;
|
|
int tz, ret;
|
|
|
|
line += strlen("author ");
|
|
date = strchr(line, '>');
|
|
if (!date)
|
|
return 0;
|
|
namelen = ++date - line;
|
|
time = strtoul(date, &date, 10);
|
|
tz = strtol(date, NULL, 10);
|
|
|
|
ret = sprintf(buf, "Author: %.*s\n", namelen, line);
|
|
if (fmt == CMIT_FMT_MEDIUM)
|
|
ret += sprintf(buf + ret, "Date: %s\n", show_date(time, tz));
|
|
return ret;
|
|
}
|
|
|
|
static int is_empty_line(const char *line, int len)
|
|
{
|
|
while (len && isspace(line[len-1]))
|
|
len--;
|
|
return !len;
|
|
}
|
|
|
|
unsigned long pretty_print_commit(enum cmit_fmt fmt, const char *msg, unsigned long len, char *buf, unsigned long space)
|
|
{
|
|
int hdr = 1, body = 0;
|
|
unsigned long offset = 0;
|
|
|
|
for (;;) {
|
|
const char *line = msg;
|
|
int linelen = get_one_line(msg, len);
|
|
|
|
if (!linelen)
|
|
break;
|
|
|
|
/*
|
|
* We want some slop for indentation and a possible
|
|
* final "...". Thus the "+ 20".
|
|
*/
|
|
if (offset + linelen + 20 > space) {
|
|
memcpy(buf + offset, " ...\n", 8);
|
|
offset += 8;
|
|
break;
|
|
}
|
|
|
|
msg += linelen;
|
|
len -= linelen;
|
|
if (hdr) {
|
|
if (linelen == 1) {
|
|
hdr = 0;
|
|
buf[offset++] = '\n';
|
|
continue;
|
|
}
|
|
if (fmt == CMIT_FMT_RAW) {
|
|
memcpy(buf + offset, line, linelen);
|
|
offset += linelen;
|
|
continue;
|
|
}
|
|
if (!memcmp(line, "author ", 7))
|
|
offset += add_author_info(fmt, buf + offset, line, linelen);
|
|
continue;
|
|
}
|
|
|
|
if (is_empty_line(line, linelen)) {
|
|
if (!body)
|
|
continue;
|
|
if (fmt == CMIT_FMT_SHORT)
|
|
break;
|
|
} else {
|
|
body = 1;
|
|
}
|
|
memset(buf + offset, ' ', 4);
|
|
memcpy(buf + offset + 4, line, linelen);
|
|
offset += linelen + 4;
|
|
}
|
|
/* Make sure there is an EOLN */
|
|
if (buf[offset - 1] != '\n')
|
|
buf[offset++] = '\n';
|
|
buf[offset] = '\0';
|
|
return offset;
|
|
}
|
|
|
|
struct commit *pop_commit(struct commit_list **stack)
|
|
{
|
|
struct commit_list *top = *stack;
|
|
struct commit *item = top ? top->item : NULL;
|
|
|
|
if (top) {
|
|
*stack = top->next;
|
|
free(top);
|
|
}
|
|
return item;
|
|
}
|
|
|
|
int count_parents(struct commit * commit)
|
|
{
|
|
int count = 0;
|
|
struct commit_list * parents = commit->parents;
|
|
for (count=0;parents; parents=parents->next,count++)
|
|
;
|
|
return count;
|
|
}
|
|
|