1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-27 18:06:36 +02:00
git/diffcore-rename.c

660 lines
17 KiB
C
Raw Normal View History

/*
* Copyright (C) 2005 Junio C Hamano
*/
#include "cache.h"
#include "diff.h"
#include "diffcore.h"
#include "hash.h"
/* Table of rename/copy destinations */
static struct diff_rename_dst {
struct diff_filespec *two;
struct diff_filepair *pair;
} *rename_dst;
static int rename_dst_nr, rename_dst_alloc;
static struct diff_rename_dst *locate_rename_dst(struct diff_filespec *two,
int insert_ok)
{
int first, last;
first = 0;
last = rename_dst_nr;
while (last > first) {
int next = (last + first) >> 1;
struct diff_rename_dst *dst = &(rename_dst[next]);
int cmp = strcmp(two->path, dst->two->path);
if (!cmp)
return dst;
if (cmp < 0) {
last = next;
continue;
}
first = next+1;
}
/* not found */
if (!insert_ok)
return NULL;
/* insert to make it at "first" */
if (rename_dst_alloc <= rename_dst_nr) {
rename_dst_alloc = alloc_nr(rename_dst_alloc);
rename_dst = xrealloc(rename_dst,
rename_dst_alloc * sizeof(*rename_dst));
}
rename_dst_nr++;
if (first < rename_dst_nr)
memmove(rename_dst + first + 1, rename_dst + first,
(rename_dst_nr - first - 1) * sizeof(*rename_dst));
rename_dst[first].two = alloc_filespec(two->path);
fill_filespec(rename_dst[first].two, two->sha1, two->mode);
rename_dst[first].pair = NULL;
return &(rename_dst[first]);
}
/* Table of rename/copy src files */
static struct diff_rename_src {
struct diff_filespec *one;
unsigned short score; /* to remember the break score */
} *rename_src;
static int rename_src_nr, rename_src_alloc;
static struct diff_rename_src *register_rename_src(struct diff_filespec *one,
unsigned short score)
{
int first, last;
first = 0;
last = rename_src_nr;
while (last > first) {
int next = (last + first) >> 1;
struct diff_rename_src *src = &(rename_src[next]);
int cmp = strcmp(one->path, src->one->path);
if (!cmp)
return src;
if (cmp < 0) {
last = next;
continue;
}
first = next+1;
}
/* insert to make it at "first" */
if (rename_src_alloc <= rename_src_nr) {
rename_src_alloc = alloc_nr(rename_src_alloc);
rename_src = xrealloc(rename_src,
rename_src_alloc * sizeof(*rename_src));
}
rename_src_nr++;
if (first < rename_src_nr)
memmove(rename_src + first + 1, rename_src + first,
(rename_src_nr - first - 1) * sizeof(*rename_src));
rename_src[first].one = one;
rename_src[first].score = score;
return &(rename_src[first]);
}
static int basename_same(struct diff_filespec *src, struct diff_filespec *dst)
{
int src_len = strlen(src->path), dst_len = strlen(dst->path);
while (src_len && dst_len) {
char c1 = src->path[--src_len];
char c2 = dst->path[--dst_len];
if (c1 != c2)
return 0;
if (c1 == '/')
return 1;
}
return (!src_len || src->path[src_len - 1] == '/') &&
(!dst_len || dst->path[dst_len - 1] == '/');
}
struct diff_score {
int src; /* index in rename_src */
int dst; /* index in rename_dst */
unsigned short score;
short name_score;
};
static int estimate_similarity(struct diff_filespec *src,
struct diff_filespec *dst,
int minimum_score)
{
/* src points at a file that existed in the original tree (or
* optionally a file in the destination tree) and dst points
* at a newly created file. They may be quite similar, in which
* case we want to say src is renamed to dst or src is copied into
* dst, and then some edit has been applied to dst.
*
* Compare them and return how similar they are, representing
* the score as an integer between 0 and MAX_SCORE.
*
* When there is an exact match, it is considered a better
* match than anything else; the destination does not even
* call into this function in that case.
*/
unsigned long max_size, delta_size, base_size, src_copied, literal_added;
unsigned long delta_limit;
int score;
/* We deal only with regular files. Symlink renames are handled
* only when they are exact matches --- in other words, no edits
* after renaming.
*/
if (!S_ISREG(src->mode) || !S_ISREG(dst->mode))
return 0;
/*
* Need to check that source and destination sizes are
* filled in before comparing them.
*
* If we already have "cnt_data" filled in, we know it's
* all good (avoid checking the size for zero, as that
* is a possible size - we really should have a flag to
* say whether the size is valid or not!)
*/
if (!src->cnt_data && diff_populate_filespec(src, 1))
return 0;
if (!dst->cnt_data && diff_populate_filespec(dst, 1))
return 0;
max_size = ((src->size > dst->size) ? src->size : dst->size);
base_size = ((src->size < dst->size) ? src->size : dst->size);
delta_size = max_size - base_size;
/* We would not consider edits that change the file size so
* drastically. delta_size must be smaller than
* (MAX_SCORE-minimum_score)/MAX_SCORE * min(src->size, dst->size).
*
* Note that base_size == 0 case is handled here already
* and the final score computation below would not have a
* divide-by-zero issue.
*/
if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE)
return 0;
if (!src->cnt_data && diff_populate_filespec(src, 0))
return 0;
if (!dst->cnt_data && diff_populate_filespec(dst, 0))
return 0;
delta_limit = (unsigned long)
(base_size * (MAX_SCORE-minimum_score) / MAX_SCORE);
if (diffcore_count_changes(src, dst,
&src->cnt_data, &dst->cnt_data,
delta_limit,
&src_copied, &literal_added))
return 0;
/* How similar are they?
* what percentage of material in dst are from source?
*/
if (!dst->size)
score = 0; /* should not happen */
else
score = (int)(src_copied * MAX_SCORE / max_size);
return score;
}
static void record_rename_pair(int dst_index, int src_index, int score)
{
struct diff_filespec *src, *dst;
struct diff_filepair *dp;
[PATCH] Rename/copy detection fix. The rename/copy detection logic in earlier round was only good enough to show patch output and discussion on the mailing list about the diff-raw format updates revealed many problems with it. This patch fixes all the ones known to me, without making things I want to do later impossible, mostly related to patch reordering. (1) Earlier rename/copy detector determined which one is rename and which one is copy too early, which made it impossible to later introduce diffcore transformers to reorder patches. This patch fixes it by moving that logic to the very end of the processing. (2) Earlier output routine diff_flush() was pruning all the "no-change" entries indiscriminatingly. This was done due to my false assumption that one of the requirements in the diff-raw output was not to show such an entry (which resulted in my incorrect comment about "diff-helper never being able to be equivalent to built-in diff driver"). My special thanks go to Linus for correcting me about this. When we produce diff-raw output, for the downstream to be able to tell renames from copies, sometimes it _is_ necessary to output "no-change" entries, and this patch adds diffcore_prune() function for doing it. (3) Earlier diff_filepair structure was trying to be not too specific about rename/copy operations, but the purpose of the structure was to record one or two paths, which _was_ indeed about rename/copy. This patch discards xfrm_msg field which was trying to be generic for this wrong reason, and introduces a couple of fields (rename_score and rename_rank) that are explicitly specific to rename/copy logic. One thing to note is that the information in a single diff_filepair structure _still_ does not distinguish renames from copies, and it is deliberately so. This is to allow patches to be reordered in later stages. (4) This patch also adds some tests about diff-raw format output and makes sure that necessary "no-change" entries appear on the output. Signed-off-by: Junio C Hamano <junkio@cox.net> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-23 06:26:09 +02:00
if (rename_dst[dst_index].pair)
die("internal error: dst already matched.");
src = rename_src[src_index].one;
src->rename_used++;
src->count++;
dst = rename_dst[dst_index].two;
dst->count++;
dp = diff_queue(NULL, src, dst);
dp->renamed_pair = 1;
if (!strcmp(src->path, dst->path))
dp->score = rename_src[src_index].score;
else
dp->score = score;
rename_dst[dst_index].pair = dp;
}
/*
* We sort the rename similarity matrix with the score, in descending
* order (the most similar first).
*/
static int score_compare(const void *a_, const void *b_)
{
const struct diff_score *a = a_, *b = b_;
/* sink the unused ones to the bottom */
if (a->dst < 0)
return (0 <= b->dst);
else if (b->dst < 0)
return -1;
if (a->score == b->score)
return b->name_score - a->name_score;
return b->score - a->score;
}
struct file_similarity {
int src_dst, index;
struct diff_filespec *filespec;
struct file_similarity *next;
};
static int find_identical_files(struct file_similarity *src,
struct file_similarity *dst,
struct diff_options *options)
{
int renames = 0;
/*
* Walk over all the destinations ...
*/
do {
Fix a pathological case in git detecting proper renames Kumar Gala had a case in the u-boot archive with multiple renames of files with identical contents, and git would turn those into multiple "copy" operations of one of the sources, and just deleting the other sources. This patch makes the git exact rename detection prefer to spread out the renames over the multiple sources, rather than do multiple copies of one source. NOTE! The changes are a bit larger than required, because I also renamed the variables named "one" and "two" to "target" and "source" respectively. That makes the logic easier to follow, especially as the "one" was illogically the target and not the soruce, for purely historical reasons (this piece of code used to traverse over sources and targets in the wrong order, and when we fixed that, we didn't fix the names back then. So I fixed them now). The important part of this change is just the trivial score calculations for when files have identical contents: /* Give higher scores to sources that haven't been used already */ score = !source->rename_used; score += basename_same(source, target); and when we have multiple choices we'll now pick the choice that gets the best rename score, rather than only looking at whether the basename matched. It's worth noting a few gotchas: - this scoring is currently only done for the "exact match" case. In particular, in Kumar's example, even after this patch, the inexact match case is still done as a copy+delete rather than as two renames: delete mode 100644 board/cds/mpc8555cds/u-boot.lds copy board/{cds => freescale}/mpc8541cds/u-boot.lds (97%) rename board/{cds/mpc8541cds => freescale/mpc8555cds}/u-boot.lds (97%) because apparently the "cds/mpc8541cds/u-boot.lds" copy looked a bit more similar to both end results. That said, I *suspect* we just have the exact same issue there - the similarity analysis just gave identical (or at least very _close_ to identical) similarity points, and we do not have any logic to prefer multiple renames over a copy/delete there. That is a separate patch. - When you have identical contents and identical basenames, the actual entry that is chosen is still picked fairly "at random" for the first one (but the subsequent ones will prefer entries that haven't already been used). It's not actually really random, in that it actually depends on the relative alphabetical order of the files (which in turn will have impacted the order that the entries got hashed!), so it gives consistent results that can be explained. But I wanted to point it out as an issue for when anybody actually does cross-renames. In Kumar's case the choice is the right one (and for a single normal directory rename it should always be, since the relative alphabetical sorting of the files will be identical), and we now get: rename board/{cds => freescale}/mpc8541cds/init.S (100%) rename board/{cds => freescale}/mpc8548cds/init.S (100%) which is the "expected" answer. However, it might still be better to change the pedantic "exact same basename" on/off choice into a more graduated "how similar are the pathnames" scoring situation, in order to be more likely to get the exact rename choice that people *expect* to see, rather than other alternatives that may *technically* be equally good, but are surprising to a human. It's also unclear whether we should consider "basenames are equal" or "have already used this as a source" to be more important. This gives them equal weight, but I suspect we might want to just multiple the "basenames are equal" weight by two, or something, to prefer equal basenames even if that causes a copy/delete pair. I dunno. Anyway, what I'm just saying in a really long-winded manner is that I think this is right as-is, but it's not the complete solution, and it may want some further tweaking in the future. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-29 22:30:13 +01:00
struct diff_filespec *target = dst->filespec;
struct file_similarity *p, *best;
Fix a pathological case in git detecting proper renames Kumar Gala had a case in the u-boot archive with multiple renames of files with identical contents, and git would turn those into multiple "copy" operations of one of the sources, and just deleting the other sources. This patch makes the git exact rename detection prefer to spread out the renames over the multiple sources, rather than do multiple copies of one source. NOTE! The changes are a bit larger than required, because I also renamed the variables named "one" and "two" to "target" and "source" respectively. That makes the logic easier to follow, especially as the "one" was illogically the target and not the soruce, for purely historical reasons (this piece of code used to traverse over sources and targets in the wrong order, and when we fixed that, we didn't fix the names back then. So I fixed them now). The important part of this change is just the trivial score calculations for when files have identical contents: /* Give higher scores to sources that haven't been used already */ score = !source->rename_used; score += basename_same(source, target); and when we have multiple choices we'll now pick the choice that gets the best rename score, rather than only looking at whether the basename matched. It's worth noting a few gotchas: - this scoring is currently only done for the "exact match" case. In particular, in Kumar's example, even after this patch, the inexact match case is still done as a copy+delete rather than as two renames: delete mode 100644 board/cds/mpc8555cds/u-boot.lds copy board/{cds => freescale}/mpc8541cds/u-boot.lds (97%) rename board/{cds/mpc8541cds => freescale/mpc8555cds}/u-boot.lds (97%) because apparently the "cds/mpc8541cds/u-boot.lds" copy looked a bit more similar to both end results. That said, I *suspect* we just have the exact same issue there - the similarity analysis just gave identical (or at least very _close_ to identical) similarity points, and we do not have any logic to prefer multiple renames over a copy/delete there. That is a separate patch. - When you have identical contents and identical basenames, the actual entry that is chosen is still picked fairly "at random" for the first one (but the subsequent ones will prefer entries that haven't already been used). It's not actually really random, in that it actually depends on the relative alphabetical order of the files (which in turn will have impacted the order that the entries got hashed!), so it gives consistent results that can be explained. But I wanted to point it out as an issue for when anybody actually does cross-renames. In Kumar's case the choice is the right one (and for a single normal directory rename it should always be, since the relative alphabetical sorting of the files will be identical), and we now get: rename board/{cds => freescale}/mpc8541cds/init.S (100%) rename board/{cds => freescale}/mpc8548cds/init.S (100%) which is the "expected" answer. However, it might still be better to change the pedantic "exact same basename" on/off choice into a more graduated "how similar are the pathnames" scoring situation, in order to be more likely to get the exact rename choice that people *expect* to see, rather than other alternatives that may *technically* be equally good, but are surprising to a human. It's also unclear whether we should consider "basenames are equal" or "have already used this as a source" to be more important. This gives them equal weight, but I suspect we might want to just multiple the "basenames are equal" weight by two, or something, to prefer equal basenames even if that causes a copy/delete pair. I dunno. Anyway, what I'm just saying in a really long-winded manner is that I think this is right as-is, but it's not the complete solution, and it may want some further tweaking in the future. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-29 22:30:13 +01:00
int i = 100, best_score = -1;
/*
* .. to find the best source match
*/
best = NULL;
for (p = src; p; p = p->next) {
Fix a pathological case in git detecting proper renames Kumar Gala had a case in the u-boot archive with multiple renames of files with identical contents, and git would turn those into multiple "copy" operations of one of the sources, and just deleting the other sources. This patch makes the git exact rename detection prefer to spread out the renames over the multiple sources, rather than do multiple copies of one source. NOTE! The changes are a bit larger than required, because I also renamed the variables named "one" and "two" to "target" and "source" respectively. That makes the logic easier to follow, especially as the "one" was illogically the target and not the soruce, for purely historical reasons (this piece of code used to traverse over sources and targets in the wrong order, and when we fixed that, we didn't fix the names back then. So I fixed them now). The important part of this change is just the trivial score calculations for when files have identical contents: /* Give higher scores to sources that haven't been used already */ score = !source->rename_used; score += basename_same(source, target); and when we have multiple choices we'll now pick the choice that gets the best rename score, rather than only looking at whether the basename matched. It's worth noting a few gotchas: - this scoring is currently only done for the "exact match" case. In particular, in Kumar's example, even after this patch, the inexact match case is still done as a copy+delete rather than as two renames: delete mode 100644 board/cds/mpc8555cds/u-boot.lds copy board/{cds => freescale}/mpc8541cds/u-boot.lds (97%) rename board/{cds/mpc8541cds => freescale/mpc8555cds}/u-boot.lds (97%) because apparently the "cds/mpc8541cds/u-boot.lds" copy looked a bit more similar to both end results. That said, I *suspect* we just have the exact same issue there - the similarity analysis just gave identical (or at least very _close_ to identical) similarity points, and we do not have any logic to prefer multiple renames over a copy/delete there. That is a separate patch. - When you have identical contents and identical basenames, the actual entry that is chosen is still picked fairly "at random" for the first one (but the subsequent ones will prefer entries that haven't already been used). It's not actually really random, in that it actually depends on the relative alphabetical order of the files (which in turn will have impacted the order that the entries got hashed!), so it gives consistent results that can be explained. But I wanted to point it out as an issue for when anybody actually does cross-renames. In Kumar's case the choice is the right one (and for a single normal directory rename it should always be, since the relative alphabetical sorting of the files will be identical), and we now get: rename board/{cds => freescale}/mpc8541cds/init.S (100%) rename board/{cds => freescale}/mpc8548cds/init.S (100%) which is the "expected" answer. However, it might still be better to change the pedantic "exact same basename" on/off choice into a more graduated "how similar are the pathnames" scoring situation, in order to be more likely to get the exact rename choice that people *expect* to see, rather than other alternatives that may *technically* be equally good, but are surprising to a human. It's also unclear whether we should consider "basenames are equal" or "have already used this as a source" to be more important. This gives them equal weight, but I suspect we might want to just multiple the "basenames are equal" weight by two, or something, to prefer equal basenames even if that causes a copy/delete pair. I dunno. Anyway, what I'm just saying in a really long-winded manner is that I think this is right as-is, but it's not the complete solution, and it may want some further tweaking in the future. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-29 22:30:13 +01:00
int score;
struct diff_filespec *source = p->filespec;
/* False hash collision? */
Fix a pathological case in git detecting proper renames Kumar Gala had a case in the u-boot archive with multiple renames of files with identical contents, and git would turn those into multiple "copy" operations of one of the sources, and just deleting the other sources. This patch makes the git exact rename detection prefer to spread out the renames over the multiple sources, rather than do multiple copies of one source. NOTE! The changes are a bit larger than required, because I also renamed the variables named "one" and "two" to "target" and "source" respectively. That makes the logic easier to follow, especially as the "one" was illogically the target and not the soruce, for purely historical reasons (this piece of code used to traverse over sources and targets in the wrong order, and when we fixed that, we didn't fix the names back then. So I fixed them now). The important part of this change is just the trivial score calculations for when files have identical contents: /* Give higher scores to sources that haven't been used already */ score = !source->rename_used; score += basename_same(source, target); and when we have multiple choices we'll now pick the choice that gets the best rename score, rather than only looking at whether the basename matched. It's worth noting a few gotchas: - this scoring is currently only done for the "exact match" case. In particular, in Kumar's example, even after this patch, the inexact match case is still done as a copy+delete rather than as two renames: delete mode 100644 board/cds/mpc8555cds/u-boot.lds copy board/{cds => freescale}/mpc8541cds/u-boot.lds (97%) rename board/{cds/mpc8541cds => freescale/mpc8555cds}/u-boot.lds (97%) because apparently the "cds/mpc8541cds/u-boot.lds" copy looked a bit more similar to both end results. That said, I *suspect* we just have the exact same issue there - the similarity analysis just gave identical (or at least very _close_ to identical) similarity points, and we do not have any logic to prefer multiple renames over a copy/delete there. That is a separate patch. - When you have identical contents and identical basenames, the actual entry that is chosen is still picked fairly "at random" for the first one (but the subsequent ones will prefer entries that haven't already been used). It's not actually really random, in that it actually depends on the relative alphabetical order of the files (which in turn will have impacted the order that the entries got hashed!), so it gives consistent results that can be explained. But I wanted to point it out as an issue for when anybody actually does cross-renames. In Kumar's case the choice is the right one (and for a single normal directory rename it should always be, since the relative alphabetical sorting of the files will be identical), and we now get: rename board/{cds => freescale}/mpc8541cds/init.S (100%) rename board/{cds => freescale}/mpc8548cds/init.S (100%) which is the "expected" answer. However, it might still be better to change the pedantic "exact same basename" on/off choice into a more graduated "how similar are the pathnames" scoring situation, in order to be more likely to get the exact rename choice that people *expect* to see, rather than other alternatives that may *technically* be equally good, but are surprising to a human. It's also unclear whether we should consider "basenames are equal" or "have already used this as a source" to be more important. This gives them equal weight, but I suspect we might want to just multiple the "basenames are equal" weight by two, or something, to prefer equal basenames even if that causes a copy/delete pair. I dunno. Anyway, what I'm just saying in a really long-winded manner is that I think this is right as-is, but it's not the complete solution, and it may want some further tweaking in the future. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-29 22:30:13 +01:00
if (hashcmp(source->sha1, target->sha1))
continue;
/* Non-regular files? If so, the modes must match! */
Fix a pathological case in git detecting proper renames Kumar Gala had a case in the u-boot archive with multiple renames of files with identical contents, and git would turn those into multiple "copy" operations of one of the sources, and just deleting the other sources. This patch makes the git exact rename detection prefer to spread out the renames over the multiple sources, rather than do multiple copies of one source. NOTE! The changes are a bit larger than required, because I also renamed the variables named "one" and "two" to "target" and "source" respectively. That makes the logic easier to follow, especially as the "one" was illogically the target and not the soruce, for purely historical reasons (this piece of code used to traverse over sources and targets in the wrong order, and when we fixed that, we didn't fix the names back then. So I fixed them now). The important part of this change is just the trivial score calculations for when files have identical contents: /* Give higher scores to sources that haven't been used already */ score = !source->rename_used; score += basename_same(source, target); and when we have multiple choices we'll now pick the choice that gets the best rename score, rather than only looking at whether the basename matched. It's worth noting a few gotchas: - this scoring is currently only done for the "exact match" case. In particular, in Kumar's example, even after this patch, the inexact match case is still done as a copy+delete rather than as two renames: delete mode 100644 board/cds/mpc8555cds/u-boot.lds copy board/{cds => freescale}/mpc8541cds/u-boot.lds (97%) rename board/{cds/mpc8541cds => freescale/mpc8555cds}/u-boot.lds (97%) because apparently the "cds/mpc8541cds/u-boot.lds" copy looked a bit more similar to both end results. That said, I *suspect* we just have the exact same issue there - the similarity analysis just gave identical (or at least very _close_ to identical) similarity points, and we do not have any logic to prefer multiple renames over a copy/delete there. That is a separate patch. - When you have identical contents and identical basenames, the actual entry that is chosen is still picked fairly "at random" for the first one (but the subsequent ones will prefer entries that haven't already been used). It's not actually really random, in that it actually depends on the relative alphabetical order of the files (which in turn will have impacted the order that the entries got hashed!), so it gives consistent results that can be explained. But I wanted to point it out as an issue for when anybody actually does cross-renames. In Kumar's case the choice is the right one (and for a single normal directory rename it should always be, since the relative alphabetical sorting of the files will be identical), and we now get: rename board/{cds => freescale}/mpc8541cds/init.S (100%) rename board/{cds => freescale}/mpc8548cds/init.S (100%) which is the "expected" answer. However, it might still be better to change the pedantic "exact same basename" on/off choice into a more graduated "how similar are the pathnames" scoring situation, in order to be more likely to get the exact rename choice that people *expect* to see, rather than other alternatives that may *technically* be equally good, but are surprising to a human. It's also unclear whether we should consider "basenames are equal" or "have already used this as a source" to be more important. This gives them equal weight, but I suspect we might want to just multiple the "basenames are equal" weight by two, or something, to prefer equal basenames even if that causes a copy/delete pair. I dunno. Anyway, what I'm just saying in a really long-winded manner is that I think this is right as-is, but it's not the complete solution, and it may want some further tweaking in the future. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-29 22:30:13 +01:00
if (!S_ISREG(source->mode) || !S_ISREG(target->mode)) {
if (source->mode != target->mode)
continue;
}
Fix a pathological case in git detecting proper renames Kumar Gala had a case in the u-boot archive with multiple renames of files with identical contents, and git would turn those into multiple "copy" operations of one of the sources, and just deleting the other sources. This patch makes the git exact rename detection prefer to spread out the renames over the multiple sources, rather than do multiple copies of one source. NOTE! The changes are a bit larger than required, because I also renamed the variables named "one" and "two" to "target" and "source" respectively. That makes the logic easier to follow, especially as the "one" was illogically the target and not the soruce, for purely historical reasons (this piece of code used to traverse over sources and targets in the wrong order, and when we fixed that, we didn't fix the names back then. So I fixed them now). The important part of this change is just the trivial score calculations for when files have identical contents: /* Give higher scores to sources that haven't been used already */ score = !source->rename_used; score += basename_same(source, target); and when we have multiple choices we'll now pick the choice that gets the best rename score, rather than only looking at whether the basename matched. It's worth noting a few gotchas: - this scoring is currently only done for the "exact match" case. In particular, in Kumar's example, even after this patch, the inexact match case is still done as a copy+delete rather than as two renames: delete mode 100644 board/cds/mpc8555cds/u-boot.lds copy board/{cds => freescale}/mpc8541cds/u-boot.lds (97%) rename board/{cds/mpc8541cds => freescale/mpc8555cds}/u-boot.lds (97%) because apparently the "cds/mpc8541cds/u-boot.lds" copy looked a bit more similar to both end results. That said, I *suspect* we just have the exact same issue there - the similarity analysis just gave identical (or at least very _close_ to identical) similarity points, and we do not have any logic to prefer multiple renames over a copy/delete there. That is a separate patch. - When you have identical contents and identical basenames, the actual entry that is chosen is still picked fairly "at random" for the first one (but the subsequent ones will prefer entries that haven't already been used). It's not actually really random, in that it actually depends on the relative alphabetical order of the files (which in turn will have impacted the order that the entries got hashed!), so it gives consistent results that can be explained. But I wanted to point it out as an issue for when anybody actually does cross-renames. In Kumar's case the choice is the right one (and for a single normal directory rename it should always be, since the relative alphabetical sorting of the files will be identical), and we now get: rename board/{cds => freescale}/mpc8541cds/init.S (100%) rename board/{cds => freescale}/mpc8548cds/init.S (100%) which is the "expected" answer. However, it might still be better to change the pedantic "exact same basename" on/off choice into a more graduated "how similar are the pathnames" scoring situation, in order to be more likely to get the exact rename choice that people *expect* to see, rather than other alternatives that may *technically* be equally good, but are surprising to a human. It's also unclear whether we should consider "basenames are equal" or "have already used this as a source" to be more important. This gives them equal weight, but I suspect we might want to just multiple the "basenames are equal" weight by two, or something, to prefer equal basenames even if that causes a copy/delete pair. I dunno. Anyway, what I'm just saying in a really long-winded manner is that I think this is right as-is, but it's not the complete solution, and it may want some further tweaking in the future. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-29 22:30:13 +01:00
/* Give higher scores to sources that haven't been used already */
score = !source->rename_used;
if (source->rename_used && options->detect_rename != DIFF_DETECT_COPY)
continue;
Fix a pathological case in git detecting proper renames Kumar Gala had a case in the u-boot archive with multiple renames of files with identical contents, and git would turn those into multiple "copy" operations of one of the sources, and just deleting the other sources. This patch makes the git exact rename detection prefer to spread out the renames over the multiple sources, rather than do multiple copies of one source. NOTE! The changes are a bit larger than required, because I also renamed the variables named "one" and "two" to "target" and "source" respectively. That makes the logic easier to follow, especially as the "one" was illogically the target and not the soruce, for purely historical reasons (this piece of code used to traverse over sources and targets in the wrong order, and when we fixed that, we didn't fix the names back then. So I fixed them now). The important part of this change is just the trivial score calculations for when files have identical contents: /* Give higher scores to sources that haven't been used already */ score = !source->rename_used; score += basename_same(source, target); and when we have multiple choices we'll now pick the choice that gets the best rename score, rather than only looking at whether the basename matched. It's worth noting a few gotchas: - this scoring is currently only done for the "exact match" case. In particular, in Kumar's example, even after this patch, the inexact match case is still done as a copy+delete rather than as two renames: delete mode 100644 board/cds/mpc8555cds/u-boot.lds copy board/{cds => freescale}/mpc8541cds/u-boot.lds (97%) rename board/{cds/mpc8541cds => freescale/mpc8555cds}/u-boot.lds (97%) because apparently the "cds/mpc8541cds/u-boot.lds" copy looked a bit more similar to both end results. That said, I *suspect* we just have the exact same issue there - the similarity analysis just gave identical (or at least very _close_ to identical) similarity points, and we do not have any logic to prefer multiple renames over a copy/delete there. That is a separate patch. - When you have identical contents and identical basenames, the actual entry that is chosen is still picked fairly "at random" for the first one (but the subsequent ones will prefer entries that haven't already been used). It's not actually really random, in that it actually depends on the relative alphabetical order of the files (which in turn will have impacted the order that the entries got hashed!), so it gives consistent results that can be explained. But I wanted to point it out as an issue for when anybody actually does cross-renames. In Kumar's case the choice is the right one (and for a single normal directory rename it should always be, since the relative alphabetical sorting of the files will be identical), and we now get: rename board/{cds => freescale}/mpc8541cds/init.S (100%) rename board/{cds => freescale}/mpc8548cds/init.S (100%) which is the "expected" answer. However, it might still be better to change the pedantic "exact same basename" on/off choice into a more graduated "how similar are the pathnames" scoring situation, in order to be more likely to get the exact rename choice that people *expect* to see, rather than other alternatives that may *technically* be equally good, but are surprising to a human. It's also unclear whether we should consider "basenames are equal" or "have already used this as a source" to be more important. This gives them equal weight, but I suspect we might want to just multiple the "basenames are equal" weight by two, or something, to prefer equal basenames even if that causes a copy/delete pair. I dunno. Anyway, what I'm just saying in a really long-winded manner is that I think this is right as-is, but it's not the complete solution, and it may want some further tweaking in the future. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-29 22:30:13 +01:00
score += basename_same(source, target);
if (score > best_score) {
best = p;
best_score = score;
if (score == 2)
break;
}
/* Too many identical alternatives? Pick one */
if (!--i)
break;
}
if (best) {
record_rename_pair(dst->index, best->index, MAX_SCORE);
renames++;
}
} while ((dst = dst->next) != NULL);
return renames;
}
static void free_similarity_list(struct file_similarity *p)
{
while (p) {
struct file_similarity *entry = p;
p = p->next;
free(entry);
}
}
static int find_same_files(void *ptr, void *data)
{
int ret;
struct file_similarity *p = ptr;
struct file_similarity *src = NULL, *dst = NULL;
struct diff_options *options = data;
/* Split the hash list up into sources and destinations */
do {
struct file_similarity *entry = p;
p = p->next;
if (entry->src_dst < 0) {
entry->next = src;
src = entry;
} else {
entry->next = dst;
dst = entry;
}
} while (p);
/*
* If we have both sources *and* destinations, see if
* we can match them up
*/
ret = (src && dst) ? find_identical_files(src, dst, options) : 0;
/* Free the hashes and return the number of renames found */
free_similarity_list(src);
free_similarity_list(dst);
return ret;
}
static unsigned int hash_filespec(struct diff_filespec *filespec)
{
unsigned int hash;
if (!filespec->sha1_valid) {
if (diff_populate_filespec(filespec, 0))
return 0;
hash_sha1_file(filespec->data, filespec->size, "blob", filespec->sha1);
}
memcpy(&hash, filespec->sha1, sizeof(hash));
return hash;
}
static void insert_file_table(struct hash_table *table, int src_dst, int index, struct diff_filespec *filespec)
{
void **pos;
unsigned int hash;
struct file_similarity *entry = xmalloc(sizeof(*entry));
entry->src_dst = src_dst;
entry->index = index;
entry->filespec = filespec;
entry->next = NULL;
hash = hash_filespec(filespec);
pos = insert_hash(hash, entry, table);
/* We already had an entry there? */
if (pos) {
entry->next = *pos;
*pos = entry;
}
}
/*
* Find exact renames first.
*
* The first round matches up the up-to-date entries,
* and then during the second round we try to match
* cache-dirty entries as well.
*/
static int find_exact_renames(struct diff_options *options)
{
int i;
struct hash_table file_table;
init_hash(&file_table);
for (i = 0; i < rename_src_nr; i++)
insert_file_table(&file_table, -1, i, rename_src[i].one);
for (i = 0; i < rename_dst_nr; i++)
insert_file_table(&file_table, 1, i, rename_dst[i].two);
/* Find the renames */
i = for_each_hash(&file_table, find_same_files, options);
/* .. and free the hash data structure */
free_hash(&file_table);
return i;
}
#define NUM_CANDIDATE_PER_DST 4
static void record_if_better(struct diff_score m[], struct diff_score *o)
{
int i, worst;
/* find the worst one */
worst = 0;
for (i = 1; i < NUM_CANDIDATE_PER_DST; i++)
if (score_compare(&m[i], &m[worst]) > 0)
worst = i;
/* is it better than the worst one? */
if (score_compare(&m[worst], o) > 0)
m[worst] = *o;
}
static int find_renames(struct diff_score *mx, int dst_cnt, int minimum_score, int copies)
{
int count = 0, i;
for (i = 0; i < dst_cnt * NUM_CANDIDATE_PER_DST; i++) {
struct diff_rename_dst *dst;
if ((mx[i].dst < 0) ||
(mx[i].score < minimum_score))
break; /* there is no more usable pair. */
dst = &rename_dst[mx[i].dst];
if (dst->pair)
continue; /* already done, either exact or fuzzy. */
if (!copies && rename_src[mx[i].src].one->rename_used)
continue;
record_rename_pair(mx[i].dst, mx[i].src, mx[i].score);
count++;
}
return count;
}
void diffcore_rename(struct diff_options *options)
{
int detect_rename = options->detect_rename;
int minimum_score = options->rename_score;
int rename_limit = options->rename_limit;
struct diff_queue_struct *q = &diff_queued_diff;
struct diff_queue_struct outq;
struct diff_score *mx;
int i, j, rename_count;
int num_create, num_src, dst_cnt;
if (!minimum_score)
minimum_score = DEFAULT_RENAME_SCORE;
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
if (!DIFF_FILE_VALID(p->one)) {
if (!DIFF_FILE_VALID(p->two))
continue; /* unmerged */
else if (options->single_follow &&
strcmp(options->single_follow, p->two->path))
continue; /* not interested */
else
locate_rename_dst(p->two, 1);
}
else if (!DIFF_FILE_VALID(p->two)) {
/*
* If the source is a broken "delete", and
* they did not really want to get broken,
* that means the source actually stays.
* So we increment the "rename_used" score
* by one, to indicate ourselves as a user
*/
if (p->broken_pair && !p->score)
p->one->rename_used++;
register_rename_src(p->one, p->score);
}
else if (detect_rename == DIFF_DETECT_COPY) {
/*
* Increment the "rename_used" score by
* one, to indicate ourselves as a user.
*/
p->one->rename_used++;
register_rename_src(p->one, p->score);
}
}
if (rename_dst_nr == 0 || rename_src_nr == 0)
goto cleanup; /* nothing to do */
Do exact rename detection regardless of rename limits Now that the exact rename detection is linear-time (with a very small constant factor to boot), there is no longer any reason to limit it by the number of files involved. In some trivial testing, I created a repository with a directory that had a hundred thousand files in it (all with different contents), and then moved that directory to show the effects of renaming 100,000 files. With the new code, that resulted in [torvalds@woody big-rename]$ time ~/git/git show -C | wc -l 400006 real 0m2.071s user 0m1.520s sys 0m0.576s ie the code can correctly detect the hundred thousand renames in about 2 seconds (the number "400006" comes from four lines for each rename: diff --git a/really-big-dir/file-1-1-1-1-1 b/moved-big-dir/file-1-1-1-1-1 similarity index 100% rename from really-big-dir/file-1-1-1-1-1 rename to moved-big-dir/file-1-1-1-1-1 and the extra six lines is from a one-liner commit message and all the commit information and spacing). Most of those two seconds weren't even really the rename detection, it's really all the other stuff needed to get there. With the old code, this wouldn't have been practically possible. Doing a pairwise check of the ten billion possible pairs would have been prohibitively expensive. In fact, even with the rename limiter in place, the old code would waste a lot of time just on the diff_filespec checks, and despite not even trying to find renames, it used to look like: [torvalds@woody big-rename]$ time git show -C | wc -l 1400006 real 0m12.337s user 0m12.285s sys 0m0.192s ie we used to take 12 seconds for this load and not even do any rename detection! (The number 1400006 comes from fourteen lines per file moved: seven lines each for the delete and the create of a one-liner file, and the same extra six lines of commit information). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-10-25 20:24:47 +02:00
/*
* We really want to cull the candidates list early
* with cheap tests in order to avoid doing deltas.
*/
rename_count = find_exact_renames(options);
Do exact rename detection regardless of rename limits Now that the exact rename detection is linear-time (with a very small constant factor to boot), there is no longer any reason to limit it by the number of files involved. In some trivial testing, I created a repository with a directory that had a hundred thousand files in it (all with different contents), and then moved that directory to show the effects of renaming 100,000 files. With the new code, that resulted in [torvalds@woody big-rename]$ time ~/git/git show -C | wc -l 400006 real 0m2.071s user 0m1.520s sys 0m0.576s ie the code can correctly detect the hundred thousand renames in about 2 seconds (the number "400006" comes from four lines for each rename: diff --git a/really-big-dir/file-1-1-1-1-1 b/moved-big-dir/file-1-1-1-1-1 similarity index 100% rename from really-big-dir/file-1-1-1-1-1 rename to moved-big-dir/file-1-1-1-1-1 and the extra six lines is from a one-liner commit message and all the commit information and spacing). Most of those two seconds weren't even really the rename detection, it's really all the other stuff needed to get there. With the old code, this wouldn't have been practically possible. Doing a pairwise check of the ten billion possible pairs would have been prohibitively expensive. In fact, even with the rename limiter in place, the old code would waste a lot of time just on the diff_filespec checks, and despite not even trying to find renames, it used to look like: [torvalds@woody big-rename]$ time git show -C | wc -l 1400006 real 0m12.337s user 0m12.285s sys 0m0.192s ie we used to take 12 seconds for this load and not even do any rename detection! (The number 1400006 comes from fourteen lines per file moved: seven lines each for the delete and the create of a one-liner file, and the same extra six lines of commit information). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-10-25 20:24:47 +02:00
/* Did we only want exact renames? */
if (minimum_score == MAX_SCORE)
goto cleanup;
/*
* Calculate how many renames are left (but all the source
* files still remain as options for rename/copies!)
*/
num_create = (rename_dst_nr - rename_count);
num_src = rename_src_nr;
/* All done? */
if (!num_create)
goto cleanup;
/*
* This basically does a test for the rename matrix not
* growing larger than a "rename_limit" square matrix, ie:
*
* num_create * num_src > rename_limit * rename_limit
*
* but handles the potential overflow case specially (and we
* assume at least 32-bit integers)
*/
if (rename_limit <= 0 || rename_limit > 32767)
rename_limit = 32767;
if ((num_create > rename_limit && num_src > rename_limit) ||
(num_create * num_src > rename_limit * rename_limit)) {
if (options->warn_on_too_large_rename)
warning("too many files (created: %d deleted: %d), skipping inexact rename detection", num_create, num_src);
goto cleanup;
}
mx = xcalloc(num_create * NUM_CANDIDATE_PER_DST, sizeof(*mx));
for (dst_cnt = i = 0; i < rename_dst_nr; i++) {
struct diff_filespec *two = rename_dst[i].two;
struct diff_score *m;
if (rename_dst[i].pair)
continue; /* dealt with exact match already. */
m = &mx[dst_cnt * NUM_CANDIDATE_PER_DST];
for (j = 0; j < NUM_CANDIDATE_PER_DST; j++)
m[j].dst = -1;
for (j = 0; j < rename_src_nr; j++) {
struct diff_filespec *one = rename_src[j].one;
struct diff_score this_src;
this_src.score = estimate_similarity(one, two,
minimum_score);
this_src.name_score = basename_same(one, two);
this_src.dst = i;
this_src.src = j;
record_if_better(m, &this_src);
/*
* Once we run estimate_similarity,
* We do not need the text anymore.
*/
diff_free_filespec_blob(one);
diff_free_filespec_blob(two);
}
dst_cnt++;
}
/* cost matrix sorted by most to least similar pair */
qsort(mx, dst_cnt * NUM_CANDIDATE_PER_DST, sizeof(*mx), score_compare);
rename_count += find_renames(mx, dst_cnt, minimum_score, 0);
if (detect_rename == DIFF_DETECT_COPY)
rename_count += find_renames(mx, dst_cnt, minimum_score, 1);
free(mx);
cleanup:
/* At this point, we have found some renames and copies and they
* are recorded in rename_dst. The original list is still in *q.
*/
DIFF_QUEUE_CLEAR(&outq);
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
struct diff_filepair *pair_to_free = NULL;
if (!DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) {
/*
* Creation
*
* We would output this create record if it has
* not been turned into a rename/copy already.
*/
struct diff_rename_dst *dst =
locate_rename_dst(p->two, 0);
if (dst && dst->pair) {
diff_q(&outq, dst->pair);
pair_to_free = p;
}
else
/* no matching rename/copy source, so
* record this as a creation.
*/
diff_q(&outq, p);
}
else if (DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two)) {
/*
* Deletion
*
* We would output this delete record if:
*
* (1) this is a broken delete and the counterpart
* broken create remains in the output; or
* (2) this is not a broken delete, and rename_dst
* does not have a rename/copy to move p->one->path
* out of existence.
*
* Otherwise, the counterpart broken create
* has been turned into a rename-edit; or
* delete did not have a matching create to
* begin with.
*/
if (DIFF_PAIR_BROKEN(p)) {
/* broken delete */
struct diff_rename_dst *dst =
locate_rename_dst(p->one, 0);
if (dst && dst->pair)
/* counterpart is now rename/copy */
pair_to_free = p;
}
else {
if (p->one->rename_used)
/* this path remains */
pair_to_free = p;
}
if (pair_to_free)
;
else
diff_q(&outq, p);
}
else if (!diff_unmodified_pair(p))
/* all the usual ones need to be kept */
diff_q(&outq, p);
else
/* no need to keep unmodified pairs */
pair_to_free = p;
if (pair_to_free)
diff_free_filepair(pair_to_free);
}
diff_debug_queue("done copying original", &outq);
free(q->queue);
*q = outq;
diff_debug_queue("done collapsing", q);
for (i = 0; i < rename_dst_nr; i++)
free_filespec(rename_dst[i].two);
free(rename_dst);
rename_dst = NULL;
rename_dst_nr = rename_dst_alloc = 0;
free(rename_src);
rename_src = NULL;
rename_src_nr = rename_src_alloc = 0;
return;
}