1
0
mirror of https://github.com/git/git.git synced 2024-11-19 00:44:22 +01:00
git/tree-diff.c

297 lines
6.9 KiB
C
Raw Normal View History

/*
* Helper functions for tree diff generation
*/
#include "cache.h"
#include "diff.h"
#include "tree.h"
static char *malloc_base(const char *base, int baselen, const char *path, int pathlen)
{
char *newbase = xmalloc(baselen + pathlen + 2);
memcpy(newbase, base, baselen);
memcpy(newbase + baselen, path, pathlen);
memcpy(newbase + baselen + pathlen, "/", 2);
return newbase;
}
static void show_entry(struct diff_options *opt, const char *prefix, struct tree_desc *desc,
const char *base, int baselen);
static int compare_tree_entry(struct tree_desc *t1, struct tree_desc *t2, const char *base, int baselen, struct diff_options *opt)
{
unsigned mode1, mode2;
const char *path1, *path2;
const unsigned char *sha1, *sha2;
int cmp, pathlen1, pathlen2;
sha1 = tree_entry_extract(t1, &path1, &mode1);
sha2 = tree_entry_extract(t2, &path2, &mode2);
pathlen1 = tree_entry_len(path1, sha1);
pathlen2 = tree_entry_len(path2, sha2);
cmp = base_name_compare(path1, pathlen1, mode1, path2, pathlen2, mode2);
if (cmp < 0) {
show_entry(opt, "-", t1, base, baselen);
return -1;
}
if (cmp > 0) {
show_entry(opt, "+", t2, base, baselen);
return 1;
}
if (!opt->find_copies_harder && !hashcmp(sha1, sha2) && mode1 == mode2)
return 0;
/*
* If the filemode has changed to/from a directory from/to a regular
* file, we need to consider it a remove and an add.
*/
if (S_ISDIR(mode1) != S_ISDIR(mode2)) {
show_entry(opt, "-", t1, base, baselen);
show_entry(opt, "+", t2, base, baselen);
return 0;
}
if (opt->recursive && S_ISDIR(mode1)) {
int retval;
char *newbase = malloc_base(base, baselen, path1, pathlen1);
if (opt->tree_in_recursive)
opt->change(opt, mode1, mode2,
sha1, sha2, base, path1);
retval = diff_tree_sha1(sha1, sha2, newbase, opt);
free(newbase);
return retval;
}
opt->change(opt, mode1, mode2, sha1, sha2, base, path1);
return 0;
}
Set up for better tree diff optimizations This is mainly just a cleanup patch, and sets up for later changes where the tree-diff.c "interesting()" function can return more than just a yes/no value. In particular, it should be quite possible to say "no subsequent entries in this tree can possibly be interesting any more", and thus allow the callers to short-circuit the tree entirely. In fact, changing the callers to do so is trivial, and is really all this patch really does, because changing "interesting()" itself to say that nothing further is going to be interesting is definitely more complicated, considering that we may have arbitrary pathspecs. But in cleaning up the callers, this actually fixes a potential small performance issue in diff_tree(): if the second tree has a lot of uninterestign crud in it, we would keep on doing the "is it interesting?" check on the first tree for each uninteresting entry in the second one. The answer is obviously not going to change, so that was just not helping. The new code is clearer and simpler and avoids this issue entirely. I also renamed "interesting()" to "tree_entry_interesting()", because I got frustrated by the fact that - we actually had *another* function called "interesting()" in another file, and I couldn't tell from the profiles which one was the one that mattered more. - when rewriting it to return a ternary value, you can't just do if (interesting(...)) ... any more, but want to assign the return value to a local variable. The name of choice for that variable would normally be "interesting", so I just wanted to make the function name be more specific, and avoid that whole issue (even though I then didn't choose that name for either of the users, just to avoid confusion in the patch itself ;) In other words, this doesn't really change anything, but I think it's a good thing to do, and if somebody comes along and writes the logic for "yeah, none of the pathspecs you have are interesting", we now support that trivially. It could easily be a meaningful optimization for things like "blame", where there's just one pathspec, and stopping when you've seen it would allow you to avoid about 50% of the tree traversals on average. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-18 23:18:30 +01:00
/*
* Is a tree entry interesting given the pathspec we have?
*
* Return:
* - positive for yes
* - zero for no
* - negative for "no, and no subsequent entries will be either"
*/
static int tree_entry_interesting(struct tree_desc *desc, const char *base, int baselen, struct diff_options *opt)
{
const char *path;
const unsigned char *sha1;
unsigned mode;
int i;
int pathlen;
if (!opt->nr_paths)
return 1;
sha1 = tree_entry_extract(desc, &path, &mode);
pathlen = tree_entry_len(path, sha1);
for (i=0; i < opt->nr_paths; i++) {
const char *match = opt->paths[i];
int matchlen = opt->pathlens[i];
if (baselen >= matchlen) {
/* If it doesn't match, move along... */
if (strncmp(base, match, matchlen))
continue;
/* The base is a subdirectory of a path which was specified. */
return 1;
}
/* Does the base match? */
if (strncmp(base, match, baselen))
continue;
match += baselen;
matchlen -= baselen;
if (pathlen > matchlen)
continue;
if (matchlen > pathlen) {
if (match[pathlen] != '/')
continue;
if (!S_ISDIR(mode))
continue;
}
if (strncmp(path, match, pathlen))
continue;
return 1;
}
return 0; /* No matches */
}
/* A whole sub-tree went away or appeared */
static void show_tree(struct diff_options *opt, const char *prefix, struct tree_desc *desc, const char *base, int baselen)
{
while (desc->size) {
Set up for better tree diff optimizations This is mainly just a cleanup patch, and sets up for later changes where the tree-diff.c "interesting()" function can return more than just a yes/no value. In particular, it should be quite possible to say "no subsequent entries in this tree can possibly be interesting any more", and thus allow the callers to short-circuit the tree entirely. In fact, changing the callers to do so is trivial, and is really all this patch really does, because changing "interesting()" itself to say that nothing further is going to be interesting is definitely more complicated, considering that we may have arbitrary pathspecs. But in cleaning up the callers, this actually fixes a potential small performance issue in diff_tree(): if the second tree has a lot of uninterestign crud in it, we would keep on doing the "is it interesting?" check on the first tree for each uninteresting entry in the second one. The answer is obviously not going to change, so that was just not helping. The new code is clearer and simpler and avoids this issue entirely. I also renamed "interesting()" to "tree_entry_interesting()", because I got frustrated by the fact that - we actually had *another* function called "interesting()" in another file, and I couldn't tell from the profiles which one was the one that mattered more. - when rewriting it to return a ternary value, you can't just do if (interesting(...)) ... any more, but want to assign the return value to a local variable. The name of choice for that variable would normally be "interesting", so I just wanted to make the function name be more specific, and avoid that whole issue (even though I then didn't choose that name for either of the users, just to avoid confusion in the patch itself ;) In other words, this doesn't really change anything, but I think it's a good thing to do, and if somebody comes along and writes the logic for "yeah, none of the pathspecs you have are interesting", we now support that trivially. It could easily be a meaningful optimization for things like "blame", where there's just one pathspec, and stopping when you've seen it would allow you to avoid about 50% of the tree traversals on average. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-18 23:18:30 +01:00
int show = tree_entry_interesting(desc, base, baselen, opt);
if (show < 0)
break;
if (show)
show_entry(opt, prefix, desc, base, baselen);
update_tree_entry(desc);
}
}
/* A file entry went away or appeared */
static void show_entry(struct diff_options *opt, const char *prefix, struct tree_desc *desc,
const char *base, int baselen)
{
unsigned mode;
const char *path;
const unsigned char *sha1 = tree_entry_extract(desc, &path, &mode);
if (opt->recursive && S_ISDIR(mode)) {
enum object_type type;
int pathlen = tree_entry_len(path, sha1);
char *newbase = malloc_base(base, baselen, path, pathlen);
struct tree_desc inner;
void *tree;
tree = read_sha1_file(sha1, &type, &inner.size);
if (!tree || type != OBJ_TREE)
die("corrupt tree sha %s", sha1_to_hex(sha1));
inner.buf = tree;
show_tree(opt, prefix, &inner, newbase, baselen + 1 + pathlen);
free(tree);
free(newbase);
} else {
opt->add_remove(opt, prefix[0], mode, sha1, base, path);
}
}
Set up for better tree diff optimizations This is mainly just a cleanup patch, and sets up for later changes where the tree-diff.c "interesting()" function can return more than just a yes/no value. In particular, it should be quite possible to say "no subsequent entries in this tree can possibly be interesting any more", and thus allow the callers to short-circuit the tree entirely. In fact, changing the callers to do so is trivial, and is really all this patch really does, because changing "interesting()" itself to say that nothing further is going to be interesting is definitely more complicated, considering that we may have arbitrary pathspecs. But in cleaning up the callers, this actually fixes a potential small performance issue in diff_tree(): if the second tree has a lot of uninterestign crud in it, we would keep on doing the "is it interesting?" check on the first tree for each uninteresting entry in the second one. The answer is obviously not going to change, so that was just not helping. The new code is clearer and simpler and avoids this issue entirely. I also renamed "interesting()" to "tree_entry_interesting()", because I got frustrated by the fact that - we actually had *another* function called "interesting()" in another file, and I couldn't tell from the profiles which one was the one that mattered more. - when rewriting it to return a ternary value, you can't just do if (interesting(...)) ... any more, but want to assign the return value to a local variable. The name of choice for that variable would normally be "interesting", so I just wanted to make the function name be more specific, and avoid that whole issue (even though I then didn't choose that name for either of the users, just to avoid confusion in the patch itself ;) In other words, this doesn't really change anything, but I think it's a good thing to do, and if somebody comes along and writes the logic for "yeah, none of the pathspecs you have are interesting", we now support that trivially. It could easily be a meaningful optimization for things like "blame", where there's just one pathspec, and stopping when you've seen it would allow you to avoid about 50% of the tree traversals on average. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-18 23:18:30 +01:00
static void skip_uninteresting(struct tree_desc *t, const char *base, int baselen, struct diff_options *opt)
{
while (t->size) {
int show = tree_entry_interesting(t, base, baselen, opt);
if (!show) {
update_tree_entry(t);
continue;
}
/* Skip it all? */
if (show < 0)
t->size = 0;
return;
}
}
int diff_tree(struct tree_desc *t1, struct tree_desc *t2, const char *base, struct diff_options *opt)
{
int baselen = strlen(base);
Set up for better tree diff optimizations This is mainly just a cleanup patch, and sets up for later changes where the tree-diff.c "interesting()" function can return more than just a yes/no value. In particular, it should be quite possible to say "no subsequent entries in this tree can possibly be interesting any more", and thus allow the callers to short-circuit the tree entirely. In fact, changing the callers to do so is trivial, and is really all this patch really does, because changing "interesting()" itself to say that nothing further is going to be interesting is definitely more complicated, considering that we may have arbitrary pathspecs. But in cleaning up the callers, this actually fixes a potential small performance issue in diff_tree(): if the second tree has a lot of uninterestign crud in it, we would keep on doing the "is it interesting?" check on the first tree for each uninteresting entry in the second one. The answer is obviously not going to change, so that was just not helping. The new code is clearer and simpler and avoids this issue entirely. I also renamed "interesting()" to "tree_entry_interesting()", because I got frustrated by the fact that - we actually had *another* function called "interesting()" in another file, and I couldn't tell from the profiles which one was the one that mattered more. - when rewriting it to return a ternary value, you can't just do if (interesting(...)) ... any more, but want to assign the return value to a local variable. The name of choice for that variable would normally be "interesting", so I just wanted to make the function name be more specific, and avoid that whole issue (even though I then didn't choose that name for either of the users, just to avoid confusion in the patch itself ;) In other words, this doesn't really change anything, but I think it's a good thing to do, and if somebody comes along and writes the logic for "yeah, none of the pathspecs you have are interesting", we now support that trivially. It could easily be a meaningful optimization for things like "blame", where there's just one pathspec, and stopping when you've seen it would allow you to avoid about 50% of the tree traversals on average. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-18 23:18:30 +01:00
for (;;) {
if (opt->quiet && opt->has_changes)
break;
Set up for better tree diff optimizations This is mainly just a cleanup patch, and sets up for later changes where the tree-diff.c "interesting()" function can return more than just a yes/no value. In particular, it should be quite possible to say "no subsequent entries in this tree can possibly be interesting any more", and thus allow the callers to short-circuit the tree entirely. In fact, changing the callers to do so is trivial, and is really all this patch really does, because changing "interesting()" itself to say that nothing further is going to be interesting is definitely more complicated, considering that we may have arbitrary pathspecs. But in cleaning up the callers, this actually fixes a potential small performance issue in diff_tree(): if the second tree has a lot of uninterestign crud in it, we would keep on doing the "is it interesting?" check on the first tree for each uninteresting entry in the second one. The answer is obviously not going to change, so that was just not helping. The new code is clearer and simpler and avoids this issue entirely. I also renamed "interesting()" to "tree_entry_interesting()", because I got frustrated by the fact that - we actually had *another* function called "interesting()" in another file, and I couldn't tell from the profiles which one was the one that mattered more. - when rewriting it to return a ternary value, you can't just do if (interesting(...)) ... any more, but want to assign the return value to a local variable. The name of choice for that variable would normally be "interesting", so I just wanted to make the function name be more specific, and avoid that whole issue (even though I then didn't choose that name for either of the users, just to avoid confusion in the patch itself ;) In other words, this doesn't really change anything, but I think it's a good thing to do, and if somebody comes along and writes the logic for "yeah, none of the pathspecs you have are interesting", we now support that trivially. It could easily be a meaningful optimization for things like "blame", where there's just one pathspec, and stopping when you've seen it would allow you to avoid about 50% of the tree traversals on average. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-18 23:18:30 +01:00
if (opt->nr_paths) {
skip_uninteresting(t1, base, baselen, opt);
skip_uninteresting(t2, base, baselen, opt);
}
if (!t1->size) {
Set up for better tree diff optimizations This is mainly just a cleanup patch, and sets up for later changes where the tree-diff.c "interesting()" function can return more than just a yes/no value. In particular, it should be quite possible to say "no subsequent entries in this tree can possibly be interesting any more", and thus allow the callers to short-circuit the tree entirely. In fact, changing the callers to do so is trivial, and is really all this patch really does, because changing "interesting()" itself to say that nothing further is going to be interesting is definitely more complicated, considering that we may have arbitrary pathspecs. But in cleaning up the callers, this actually fixes a potential small performance issue in diff_tree(): if the second tree has a lot of uninterestign crud in it, we would keep on doing the "is it interesting?" check on the first tree for each uninteresting entry in the second one. The answer is obviously not going to change, so that was just not helping. The new code is clearer and simpler and avoids this issue entirely. I also renamed "interesting()" to "tree_entry_interesting()", because I got frustrated by the fact that - we actually had *another* function called "interesting()" in another file, and I couldn't tell from the profiles which one was the one that mattered more. - when rewriting it to return a ternary value, you can't just do if (interesting(...)) ... any more, but want to assign the return value to a local variable. The name of choice for that variable would normally be "interesting", so I just wanted to make the function name be more specific, and avoid that whole issue (even though I then didn't choose that name for either of the users, just to avoid confusion in the patch itself ;) In other words, this doesn't really change anything, but I think it's a good thing to do, and if somebody comes along and writes the logic for "yeah, none of the pathspecs you have are interesting", we now support that trivially. It could easily be a meaningful optimization for things like "blame", where there's just one pathspec, and stopping when you've seen it would allow you to avoid about 50% of the tree traversals on average. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-18 23:18:30 +01:00
if (!t2->size)
break;
show_entry(opt, "+", t2, base, baselen);
update_tree_entry(t2);
continue;
}
if (!t2->size) {
show_entry(opt, "-", t1, base, baselen);
update_tree_entry(t1);
continue;
}
switch (compare_tree_entry(t1, t2, base, baselen, opt)) {
case -1:
update_tree_entry(t1);
continue;
case 0:
update_tree_entry(t1);
/* Fallthrough */
case 1:
update_tree_entry(t2);
continue;
}
die("git-diff-tree: internal error");
}
return 0;
}
int diff_tree_sha1(const unsigned char *old, const unsigned char *new, const char *base, struct diff_options *opt)
{
void *tree1, *tree2;
struct tree_desc t1, t2;
int retval;
tree1 = read_object_with_reference(old, tree_type, &t1.size, NULL);
if (!tree1)
die("unable to read source tree (%s)", sha1_to_hex(old));
tree2 = read_object_with_reference(new, tree_type, &t2.size, NULL);
if (!tree2)
die("unable to read destination tree (%s)", sha1_to_hex(new));
t1.buf = tree1;
t2.buf = tree2;
retval = diff_tree(&t1, &t2, base, opt);
free(tree1);
free(tree2);
return retval;
}
int diff_root_tree_sha1(const unsigned char *new, const char *base, struct diff_options *opt)
{
int retval;
void *tree;
struct tree_desc empty, real;
tree = read_object_with_reference(new, tree_type, &real.size, NULL);
if (!tree)
die("unable to read root tree (%s)", sha1_to_hex(new));
real.buf = tree;
empty.size = 0;
empty.buf = "";
retval = diff_tree(&empty, &real, base, opt);
free(tree);
return retval;
}
static int count_paths(const char **paths)
{
int i = 0;
while (*paths++)
i++;
return i;
}
void diff_tree_release_paths(struct diff_options *opt)
{
free(opt->pathlens);
}
void diff_tree_setup_paths(const char **p, struct diff_options *opt)
{
opt->nr_paths = 0;
opt->pathlens = NULL;
opt->paths = NULL;
if (p) {
int i;
opt->paths = p;
opt->nr_paths = count_paths(p);
if (opt->nr_paths == 0) {
opt->pathlens = NULL;
return;
}
opt->pathlens = xmalloc(opt->nr_paths * sizeof(int));
for (i=0; i < opt->nr_paths; i++)
opt->pathlens[i] = strlen(p[i]);
}
}