Merge branch 'fk/blame'

* fk/blame:
  blame: Rename detection (take 2)
  rev-lib: Make it easy to do rename tracking (take 2)
  Make it possible to not clobber object.util in sort_in_topological_order (take 2)
This commit is contained in:
Junio C Hamano 2006-03-13 00:01:52 -08:00
commit 4a6c77cc0a
6 changed files with 318 additions and 99 deletions

239
blame.c
View File

@ -14,6 +14,7 @@
#include "tree.h"
#include "blob.h"
#include "diff.h"
#include "diffcore.h"
#include "revision.h"
#define DEBUG 0
@ -34,7 +35,9 @@ struct util_info {
char *buf;
unsigned long size;
int num_lines;
// const char* path;
const char* pathname;
void* topo_data;
};
struct chunk {
@ -342,25 +345,34 @@ static int map_line(struct commit *commit, int line)
return info->line_map[line];
}
static int fill_util_info(struct commit *commit, const char *path)
static struct util_info* get_util(struct commit *commit)
{
struct util_info *util;
if (commit->object.util)
return 0;
struct util_info *util = commit->object.util;
if (util)
return util;
util = xmalloc(sizeof(struct util_info));
util->buf = NULL;
util->size = 0;
util->line_map = NULL;
util->num_lines = -1;
util->pathname = NULL;
commit->object.util = util;
return util;
}
if (get_blob_sha1(commit->tree, path, util->sha1)) {
free(util);
static int fill_util_info(struct commit *commit)
{
struct util_info *util = commit->object.util;
assert(util);
assert(util->pathname);
if (get_blob_sha1(commit->tree, util->pathname, util->sha1))
return 1;
} else {
util->buf = NULL;
util->size = 0;
util->line_map = NULL;
util->num_lines = -1;
commit->object.util = util;
else
return 0;
}
}
static void alloc_line_map(struct commit *commit)
@ -389,10 +401,11 @@ static void alloc_line_map(struct commit *commit)
static void init_first_commit(struct commit* commit, const char* filename)
{
struct util_info* util;
struct util_info* util = commit->object.util;
int i;
if (fill_util_info(commit, filename))
util->pathname = filename;
if (fill_util_info(commit))
die("fill_util_info failed");
alloc_line_map(commit);
@ -453,7 +466,7 @@ static void process_commits(struct rev_info *rev, const char *path,
if(num_parents == 0)
*initial = commit;
if(fill_util_info(commit, path))
if (fill_util_info(commit))
continue;
alloc_line_map(commit);
@ -471,7 +484,7 @@ static void process_commits(struct rev_info *rev, const char *path,
printf("parent: %s\n",
sha1_to_hex(parent->object.sha1));
if(fill_util_info(parent, path)) {
if (fill_util_info(parent)) {
num_parents--;
continue;
}
@ -511,6 +524,135 @@ static void process_commits(struct rev_info *rev, const char *path,
} while ((commit = get_revision(rev)) != NULL);
}
static int compare_tree_path(struct rev_info* revs,
struct commit* c1, struct commit* c2)
{
const char* paths[2];
struct util_info* util = c2->object.util;
paths[0] = util->pathname;
paths[1] = NULL;
diff_tree_setup_paths(get_pathspec(revs->prefix, paths));
return rev_compare_tree(c1->tree, c2->tree);
}
static int same_tree_as_empty_path(struct rev_info *revs, struct tree* t1,
const char* path)
{
const char* paths[2];
paths[0] = path;
paths[1] = NULL;
diff_tree_setup_paths(get_pathspec(revs->prefix, paths));
return rev_same_tree_as_empty(t1);
}
static const char* find_rename(struct commit* commit, struct commit* parent)
{
struct util_info* cutil = commit->object.util;
struct diff_options diff_opts;
const char *paths[1];
int i;
if (DEBUG) {
printf("find_rename commit: %s ",
sha1_to_hex(commit->object.sha1));
puts(sha1_to_hex(parent->object.sha1));
}
diff_setup(&diff_opts);
diff_opts.recursive = 1;
diff_opts.detect_rename = DIFF_DETECT_RENAME;
paths[0] = NULL;
diff_tree_setup_paths(paths);
if (diff_setup_done(&diff_opts) < 0)
die("diff_setup_done failed");
diff_tree_sha1(commit->tree->object.sha1, parent->tree->object.sha1,
"", &diff_opts);
diffcore_std(&diff_opts);
for (i = 0; i < diff_queued_diff.nr; i++) {
struct diff_filepair *p = diff_queued_diff.queue[i];
if (p->status == 'R' && !strcmp(p->one->path, cutil->pathname)) {
if (DEBUG)
printf("rename %s -> %s\n", p->one->path, p->two->path);
return p->two->path;
}
}
return 0;
}
static void simplify_commit(struct rev_info *revs, struct commit *commit)
{
struct commit_list **pp, *parent;
if (!commit->tree)
return;
if (!commit->parents) {
struct util_info* util = commit->object.util;
if (!same_tree_as_empty_path(revs, commit->tree,
util->pathname))
commit->object.flags |= TREECHANGE;
return;
}
pp = &commit->parents;
while ((parent = *pp) != NULL) {
struct commit *p = parent->item;
if (p->object.flags & UNINTERESTING) {
pp = &parent->next;
continue;
}
parse_commit(p);
switch (compare_tree_path(revs, p, commit)) {
case REV_TREE_SAME:
parent->next = NULL;
commit->parents = parent;
get_util(p)->pathname = get_util(commit)->pathname;
return;
case REV_TREE_NEW:
{
struct util_info* util = commit->object.util;
if (revs->remove_empty_trees &&
same_tree_as_empty_path(revs, p->tree,
util->pathname)) {
const char* new_name = find_rename(commit, p);
if (new_name) {
struct util_info* putil = get_util(p);
if (!putil->pathname)
putil->pathname = strdup(new_name);
} else {
*pp = parent->next;
continue;
}
}
}
/* fallthrough */
case REV_TREE_DIFFERENT:
pp = &parent->next;
if (!get_util(p)->pathname)
get_util(p)->pathname =
get_util(commit)->pathname;
continue;
}
die("bad tree compare for commit %s",
sha1_to_hex(commit->object.sha1));
}
commit->object.flags |= TREECHANGE;
}
struct commit_info
{
char* author;
@ -569,6 +711,18 @@ static const char* format_time(unsigned long time, const char* tz_str)
return time_buf;
}
static void topo_setter(struct commit* c, void* data)
{
struct util_info* util = c->object.util;
util->topo_data = data;
}
static void* topo_getter(struct commit* c)
{
struct util_info* util = c->object.util;
return util->topo_data;
}
int main(int argc, const char **argv)
{
int i;
@ -580,8 +734,8 @@ int main(int argc, const char **argv)
int sha1_len = 8;
int compability = 0;
int options = 1;
struct commit* start_commit;
int num_args;
const char* args[10];
struct rev_info rev;
@ -634,28 +788,29 @@ int main(int argc, const char **argv)
strcpy(filename_buf, filename);
filename = filename_buf;
{
struct commit* c;
if (get_sha1(commit, sha1))
die("get_sha1 failed, commit '%s' not found", commit);
c = lookup_commit_reference(sha1);
if (fill_util_info(c, filename)) {
printf("%s not found in %s\n", filename, commit);
return 1;
}
if (get_sha1(commit, sha1))
die("get_sha1 failed, commit '%s' not found", commit);
start_commit = lookup_commit_reference(sha1);
get_util(start_commit)->pathname = filename;
if (fill_util_info(start_commit)) {
printf("%s not found in %s\n", filename, commit);
return 1;
}
num_args = 0;
args[num_args++] = NULL;
args[num_args++] = "--topo-order";
args[num_args++] = "--remove-empty";
args[num_args++] = commit;
args[num_args++] = "--";
args[num_args++] = filename;
args[num_args] = NULL;
setup_revisions(num_args, args, &rev, "HEAD");
init_revisions(&rev);
rev.remove_empty_trees = 1;
rev.topo_order = 1;
rev.prune_fn = simplify_commit;
rev.topo_setter = topo_setter;
rev.topo_getter = topo_getter;
rev.limited = 1;
commit_list_insert(start_commit, &rev.commits);
args[0] = filename;
args[1] = NULL;
diff_tree_setup_paths(args);
prepare_revision_walk(&rev);
process_commits(&rev, filename, &initial);
@ -665,17 +820,21 @@ int main(int argc, const char **argv)
for (i = 0; i < num_blame_lines; i++) {
struct commit *c = blame_lines[i];
struct util_info* u;
if (!c)
c = initial;
u = c->object.util;
get_commit_info(c, &ci);
fwrite(sha1_to_hex(c->object.sha1), sha1_len, 1, stdout);
if(compability)
printf("\t(%10s\t%10s\t%d)", ci.author,
format_time(ci.author_time, ci.author_tz), i+1);
else
printf(" (%-15.15s %10s %*d) ", ci.author,
format_time(ci.author_time, ci.author_tz),
printf(" %s (%-15.15s %10s %*d) ", u->pathname,
ci.author, format_time(ci.author_time,
ci.author_tz),
max_digits, i+1);
if(i == num_blame_lines - 1) {

View File

@ -569,10 +569,28 @@ int count_parents(struct commit * commit)
return count;
}
void topo_sort_default_setter(struct commit *c, void *data)
{
c->object.util = data;
}
void *topo_sort_default_getter(struct commit *c)
{
return c->object.util;
}
/*
* Performs an in-place topological sort on the list supplied.
*/
void sort_in_topological_order(struct commit_list ** list, int lifo)
{
sort_in_topological_order_fn(list, lifo, topo_sort_default_setter,
topo_sort_default_getter);
}
void sort_in_topological_order_fn(struct commit_list ** list, int lifo,
topo_sort_set_fn_t setter,
topo_sort_get_fn_t getter)
{
struct commit_list * next = *list;
struct commit_list * work = NULL, **insert;
@ -596,7 +614,7 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
next=*list;
while (next) {
next_nodes->list_item = next;
next->item->object.util = next_nodes;
setter(next->item, next_nodes);
next_nodes++;
next = next->next;
}
@ -606,8 +624,8 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
struct commit_list * parents = next->item->parents;
while (parents) {
struct commit * parent=parents->item;
struct sort_node * pn = (struct sort_node *)parent->object.util;
struct sort_node * pn = (struct sort_node *) getter(parent);
if (pn)
pn->indegree++;
parents=parents->next;
@ -624,7 +642,7 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
next=*list;
insert = &work;
while (next) {
struct sort_node * node = (struct sort_node *)next->item->object.util;
struct sort_node * node = (struct sort_node *) getter(next->item);
if (node->indegree == 0) {
insert = &commit_list_insert(next->item, insert)->next;
@ -637,15 +655,15 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
sort_by_date(&work);
while (work) {
struct commit * work_item = pop_commit(&work);
struct sort_node * work_node = (struct sort_node *)work_item->object.util;
struct sort_node * work_node = (struct sort_node *) getter(work_item);
struct commit_list * parents = work_item->parents;
while (parents) {
struct commit * parent=parents->item;
struct sort_node * pn = (struct sort_node *)parent->object.util;
struct sort_node * pn = (struct sort_node *) getter(parent);
if (pn) {
/*
/*
* parents are only enqueued for emission
* when all their children have been emitted thereby
* guaranteeing topological order.
@ -667,7 +685,7 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
*pptr = work_node->list_item;
pptr = &(*pptr)->next;
*pptr = NULL;
work_item->object.util = NULL;
setter(work_item, NULL);
}
free(nodes);
}

View File

@ -65,15 +65,29 @@ int count_parents(struct commit * commit);
/*
* Performs an in-place topological sort of list supplied.
*
* Pre-conditions:
* Pre-conditions for sort_in_topological_order:
* all commits in input list and all parents of those
* commits must have object.util == NULL
*
* Post-conditions:
*
* Pre-conditions for sort_in_topological_order_fn:
* all commits in input list and all parents of those
* commits must have getter(commit) == NULL
*
* Post-conditions:
* invariant of resulting list is:
* a reachable from b => ord(b) < ord(a)
* in addition, when lifo == 0, commits on parallel tracks are
* sorted in the dates order.
*/
typedef void (*topo_sort_set_fn_t)(struct commit*, void *data);
typedef void* (*topo_sort_get_fn_t)(struct commit*);
void topo_sort_default_setter(struct commit *c, void *data);
void *topo_sort_default_getter(struct commit *c);
void sort_in_topological_order(struct commit_list ** list, int lifo);
void sort_in_topological_order_fn(struct commit_list ** list, int lifo,
topo_sort_set_fn_t setter,
topo_sort_get_fn_t getter);
#endif /* COMMIT_H */

View File

@ -190,7 +190,7 @@ static int count_distance(struct commit_list *entry)
if (commit->object.flags & (UNINTERESTING | COUNTED))
break;
if (!revs.paths || (commit->object.flags & TREECHANGE))
if (!revs.prune_fn || (commit->object.flags & TREECHANGE))
nr++;
commit->object.flags |= COUNTED;
p = commit->parents;
@ -224,7 +224,7 @@ static struct commit_list *find_bisection(struct commit_list *list)
nr = 0;
p = list;
while (p) {
if (!revs.paths || (p->item->object.flags & TREECHANGE))
if (!revs.prune_fn || (p->item->object.flags & TREECHANGE))
nr++;
p = p->next;
}
@ -234,7 +234,7 @@ static struct commit_list *find_bisection(struct commit_list *list)
for (p = list; p; p = p->next) {
int distance;
if (revs.paths && !(p->item->object.flags & TREECHANGE))
if (revs.prune_fn && !(p->item->object.flags & TREECHANGE))
continue;
distance = count_distance(p);

View File

@ -199,31 +199,27 @@ static int everybody_uninteresting(struct commit_list *orig)
return 1;
}
#define TREE_SAME 0
#define TREE_NEW 1
#define TREE_DIFFERENT 2
static int tree_difference = TREE_SAME;
static int tree_difference = REV_TREE_SAME;
static void file_add_remove(struct diff_options *options,
int addremove, unsigned mode,
const unsigned char *sha1,
const char *base, const char *path)
{
int diff = TREE_DIFFERENT;
int diff = REV_TREE_DIFFERENT;
/*
* Is it an add of a new file? It means that
* the old tree didn't have it at all, so we
* will turn "TREE_SAME" -> "TREE_NEW", but
* leave any "TREE_DIFFERENT" alone (and if
* it already was "TREE_NEW", we'll keep it
* "TREE_NEW" of course).
* Is it an add of a new file? It means that the old tree
* didn't have it at all, so we will turn "REV_TREE_SAME" ->
* "REV_TREE_NEW", but leave any "REV_TREE_DIFFERENT" alone
* (and if it already was "REV_TREE_NEW", we'll keep it
* "REV_TREE_NEW" of course).
*/
if (addremove == '+') {
diff = tree_difference;
if (diff != TREE_SAME)
if (diff != REV_TREE_SAME)
return;
diff = TREE_NEW;
diff = REV_TREE_NEW;
}
tree_difference = diff;
}
@ -234,7 +230,7 @@ static void file_change(struct diff_options *options,
const unsigned char *new_sha1,
const char *base, const char *path)
{
tree_difference = TREE_DIFFERENT;
tree_difference = REV_TREE_DIFFERENT;
}
static struct diff_options diff_opt = {
@ -243,19 +239,19 @@ static struct diff_options diff_opt = {
.change = file_change,
};
static int compare_tree(struct tree *t1, struct tree *t2)
int rev_compare_tree(struct tree *t1, struct tree *t2)
{
if (!t1)
return TREE_NEW;
return REV_TREE_NEW;
if (!t2)
return TREE_DIFFERENT;
tree_difference = TREE_SAME;
return REV_TREE_DIFFERENT;
tree_difference = REV_TREE_SAME;
if (diff_tree_sha1(t1->object.sha1, t2->object.sha1, "", &diff_opt) < 0)
return TREE_DIFFERENT;
return REV_TREE_DIFFERENT;
return tree_difference;
}
static int same_tree_as_empty(struct tree *t1)
int rev_same_tree_as_empty(struct tree *t1)
{
int retval;
void *tree;
@ -288,7 +284,7 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
return;
if (!commit->parents) {
if (!same_tree_as_empty(commit->tree))
if (!rev_same_tree_as_empty(commit->tree))
commit->object.flags |= TREECHANGE;
return;
}
@ -298,8 +294,8 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
struct commit *p = parent->item;
parse_commit(p);
switch (compare_tree(p->tree, commit->tree)) {
case TREE_SAME:
switch (rev_compare_tree(p->tree, commit->tree)) {
case REV_TREE_SAME:
if (p->object.flags & UNINTERESTING) {
/* Even if a merge with an uninteresting
* side branch brought the entire change
@ -314,13 +310,14 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
commit->parents = parent;
return;
case TREE_NEW:
if (revs->remove_empty_trees && same_tree_as_empty(p->tree)) {
case REV_TREE_NEW:
if (revs->remove_empty_trees &&
rev_same_tree_as_empty(p->tree)) {
*pp = parent->next;
continue;
}
/* fallthrough */
case TREE_DIFFERENT:
case REV_TREE_DIFFERENT:
tree_changed = 1;
pp = &parent->next;
continue;
@ -368,8 +365,8 @@ static void add_parents_to_list(struct rev_info *revs, struct commit *commit, st
* simplify the commit history and find the parent
* that has no differences in the path set if one exists.
*/
if (revs->paths)
try_to_simplify_commit(revs, commit);
if (revs->prune_fn)
revs->prune_fn(revs, commit);
parent = commit->parents;
while (parent) {
@ -391,9 +388,6 @@ static void limit_list(struct rev_info *revs)
struct commit_list *newlist = NULL;
struct commit_list **p = &newlist;
if (revs->paths)
diff_tree_setup_paths(revs->paths);
while (list) {
struct commit_list *entry = list;
struct commit *commit = list->item;
@ -445,6 +439,23 @@ static void handle_all(struct rev_info *revs, unsigned flags)
for_each_ref(handle_one_ref);
}
void init_revisions(struct rev_info *revs)
{
memset(revs, 0, sizeof(*revs));
revs->lifo = 1;
revs->dense = 1;
revs->prefix = setup_git_directory();
revs->max_age = -1;
revs->min_age = -1;
revs->max_count = -1;
revs->prune_fn = NULL;
revs->prune_data = NULL;
revs->topo_setter = topo_sort_default_setter;
revs->topo_getter = topo_sort_default_getter;
}
/*
* Parse revision information, filling in the "rev_info" structure,
* and removing the used arguments from the argument list.
@ -458,13 +469,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
const char **unrecognized = argv + 1;
int left = 1;
memset(revs, 0, sizeof(*revs));
revs->lifo = 1;
revs->dense = 1;
revs->prefix = setup_git_directory();
revs->max_age = -1;
revs->min_age = -1;
revs->max_count = -1;
init_revisions(revs);
/* First, search for "--" */
seen_dashdash = 0;
@ -474,7 +479,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
continue;
argv[i] = NULL;
argc = i;
revs->paths = get_pathspec(revs->prefix, argv + i + 1);
revs->prune_data = get_pathspec(revs->prefix, argv + i + 1);
seen_dashdash = 1;
break;
}
@ -638,7 +643,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
if (lstat(argv[j], &st) < 0)
die("'%s': %s", arg, strerror(errno));
}
revs->paths = get_pathspec(revs->prefix, argv + i);
revs->prune_data = get_pathspec(revs->prefix, argv + i);
break;
}
commit = get_commit_reference(revs, arg, sha1, flags ^ local_flags);
@ -652,8 +657,13 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
commit = get_commit_reference(revs, def, sha1, 0);
add_one_commit(commit, revs);
}
if (revs->paths)
if (revs->prune_data) {
diff_tree_setup_paths(revs->prune_data);
revs->prune_fn = try_to_simplify_commit;
revs->limited = 1;
}
return left;
}
@ -663,7 +673,9 @@ void prepare_revision_walk(struct rev_info *revs)
if (revs->limited)
limit_list(revs);
if (revs->topo_order)
sort_in_topological_order(&revs->commits, revs->lifo);
sort_in_topological_order_fn(&revs->commits, revs->lifo,
revs->topo_setter,
revs->topo_getter);
}
static int rewrite_one(struct commit **pp)
@ -719,7 +731,7 @@ struct commit *get_revision(struct rev_info *revs)
return NULL;
if (revs->no_merges && commit->parents && commit->parents->next)
goto next;
if (revs->paths && revs->dense) {
if (revs->prune_fn && revs->dense) {
if (!(commit->object.flags & TREECHANGE))
goto next;
rewrite_parents(commit);

View File

@ -7,6 +7,10 @@
#define SHOWN (1u<<3)
#define TMP_MARK (1u<<4) /* for isolated cases; clean after use */
struct rev_info;
typedef void (prune_fn_t)(struct rev_info *revs, struct commit *commit);
struct rev_info {
/* Starting list */
struct commit_list *commits;
@ -14,7 +18,8 @@ struct rev_info {
/* Basic information */
const char *prefix;
const char **paths;
void *prune_data;
prune_fn_t *prune_fn;
/* Traversal flags */
unsigned int dense:1,
@ -33,9 +38,20 @@ struct rev_info {
int max_count;
unsigned long max_age;
unsigned long min_age;
topo_sort_set_fn_t topo_setter;
topo_sort_get_fn_t topo_getter;
};
#define REV_TREE_SAME 0
#define REV_TREE_NEW 1
#define REV_TREE_DIFFERENT 2
/* revision.c */
extern int rev_same_tree_as_empty(struct tree *t1);
extern int rev_compare_tree(struct tree *t1, struct tree *t2);
extern void init_revisions(struct rev_info *revs);
extern int setup_revisions(int argc, const char **argv, struct rev_info *revs, const char *def);
extern void prepare_revision_walk(struct rev_info *revs);
extern struct commit *get_revision(struct rev_info *revs);