development/git
development/git
1
0
Fork 0
mirror of https://github.com/git/git synced 2024-10-30 14:03:28 +00:00
Code Issues Projects Releases Packages Wiki Activity
git/xdiff/xmerge.c

495 lines
12 KiB
C
Raw Normal View History

xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
/*
* LibXDiff by Davide Libenzi ( File Differential Library )
* Copyright (C) 2003-2006 Davide Libenzi, Johannes E. Schindelin
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include "xinclude.h"
typedef struct s_xdmerge {
struct s_xdmerge *next;
/*
* 0 = conflict,
* 1 = no conflict, take first,
* 2 = no conflict, take second.
*/
int mode;
long i1, i2;
long chg1, chg2;
} xdmerge_t;
static int xdl_append_merge(xdmerge_t **merge, int mode,
long i1, long chg1, long i2, long chg2)
{
xdmerge_t *m = *merge;
xdl_merge(): fix and simplify conflict handling Suppose you have changes in new1 to the original lines 10-20, and changes in new2 to the original lines 15-25, then the changes to 10-25 conflict. But it is possible that the next changes in new1 still overlap with this change to new2. So, in the next iteration we have to look at the same change to new2 again. The old code tried to be a bit too clever. The new code is shorter and more to the point: do not fiddle with the ranges at all. Also, xdl_append_merge() tries harder to combine conflicts. This is necessary, because with the above simplification, some conflicts would not be recognized as conflicts otherwise: In the above scenario, it is possible that there is no other change to new1. Absent the combine logic, the change in new2 would be recorded _again_, but as a non-conflict. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de>
2006-12-05 21:15:35 +00:00
if (m && (i1 <= m->i1 + m->chg1 || i2 <= m->i2 + m->chg2)) {
if (mode != m->mode)
m->mode = 0;
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
m->chg1 = i1 + chg1 - m->i1;
m->chg2 = i2 + chg2 - m->i2;
} else {
m = xdl_malloc(sizeof(xdmerge_t));
if (!m)
return -1;
m->next = NULL;
m->mode = mode;
m->i1 = i1;
m->chg1 = chg1;
m->i2 = i2;
m->chg2 = chg2;
if (*merge)
(*merge)->next = m;
*merge = m;
}
return 0;
}
static int xdl_cleanup_merge(xdmerge_t *c)
{
int count = 0;
xdmerge_t *next_c;
/* were there conflicts? */
for (; c; c = next_c) {
if (c->mode == 0)
count++;
next_c = c->next;
free(c);
}
return count;
}
static int xdl_merge_cmp_lines(xdfenv_t *xe1, int i1, xdfenv_t *xe2, int i2,
int line_count, long flags)
{
int i;
xrecord_t **rec1 = xe1->xdf2.recs + i1;
xrecord_t **rec2 = xe2->xdf2.recs + i2;
for (i = 0; i < line_count; i++) {
int result = xdl_recmatch(rec1[i]->ptr, rec1[i]->size,
rec2[i]->ptr, rec2[i]->size, flags);
if (!result)
return -1;
}
return 0;
}
static int xdl_recs_copy(xdfenv_t *xe, int i, int count, int add_nl, char *dest)
{
xrecord_t **recs = xe->xdf2.recs + i;
int size = 0;
if (count < 1)
return 0;
for (i = 0; i < count; size += recs[i++]->size)
if (dest)
memcpy(dest + size, recs[i]->ptr, recs[i]->size);
if (add_nl) {
i = recs[count - 1]->size;
if (i == 0 || recs[count - 1]->ptr[i - 1] != '\n') {
if (dest)
dest[size] = '\n';
size++;
}
}
return size;
}
static int xdl_fill_merge_buffer(xdfenv_t *xe1, const char *name1,
xdfenv_t *xe2, const char *name2, xdmerge_t *m, char *dest)
{
const int marker_size = 7;
int marker1_size = (name1 ? strlen(name1) + 1 : 0);
int marker2_size = (name2 ? strlen(name2) + 1 : 0);
int conflict_marker_size = 3 * (marker_size + 1)
+ marker1_size + marker2_size;
int size, i1, j;
for (size = i1 = 0; m; m = m->next) {
if (m->mode == 0) {
size += xdl_recs_copy(xe1, i1, m->i1 - i1, 0,
dest ? dest + size : NULL);
if (dest) {
for (j = 0; j < marker_size; j++)
dest[size++] = '<';
if (marker1_size) {
dest[size] = ' ';
memcpy(dest + size + 1, name1,
marker1_size - 1);
size += marker1_size;
}
dest[size++] = '\n';
} else
size += conflict_marker_size;
size += xdl_recs_copy(xe1, m->i1, m->chg1, 1,
dest ? dest + size : NULL);
if (dest) {
for (j = 0; j < marker_size; j++)
dest[size++] = '=';
dest[size++] = '\n';
}
size += xdl_recs_copy(xe2, m->i2, m->chg2, 1,
dest ? dest + size : NULL);
if (dest) {
for (j = 0; j < marker_size; j++)
dest[size++] = '>';
if (marker2_size) {
dest[size] = ' ';
memcpy(dest + size + 1, name2,
marker2_size - 1);
size += marker2_size;
}
dest[size++] = '\n';
}
} else if (m->mode == 1)
size += xdl_recs_copy(xe1, i1, m->i1 + m->chg1 - i1, 0,
dest ? dest + size : NULL);
else if (m->mode == 2)
size += xdl_recs_copy(xe2, m->i2 - m->i1 + i1,
m->i1 + m->chg2 - i1, 0,
dest ? dest + size : NULL);
Fix yet another subtle xdl_merge() bug In very obscure cases, a merge can hit an unexpected code path (where the original code went as far as saying that this was a bug). This failing merge was noticed by Alexandre Juillard. The problem is that the original file contains something like this: -- snip -- two non-empty lines before two empty lines after two empty lines -- snap -- and this snippet is reduced to _one_ empty line in _both_ new files. However, it is ambiguous as to which hunk takes the empty line: the first or the second one? Indeed in Alexandre's example files, the xdiff algorithm attributes the empty line to the first hunk in one case, and to the second hunk in the other case. (Trimming down the example files _changes_ that behaviour!) Thus, the call to xdl_merge_cmp_lines() has no chance to realize that the change is actually identical in both new files. Therefore, xdl_refine_conflicts() finds an empty diff script, which was not expected there, because (the original author of xdl_merge() thought) xdl_merge_cmp_lines() would catch that case earlier. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-31 01:07:41 +00:00
else
continue;
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
i1 = m->i1 + m->chg1;
}
size += xdl_recs_copy(xe1, i1, xe1->xdf2.nrec - i1, 0,
dest ? dest + size : NULL);
return size;
}
/*
* Sometimes, changes are not quite identical, but differ in only a few
* lines. Try hard to show only these few lines as conflicting.
*/
static int xdl_refine_conflicts(xdfenv_t *xe1, xdfenv_t *xe2, xdmerge_t *m,
xpparam_t const *xpp)
{
for (; m; m = m->next) {
mmfile_t t1, t2;
xdfenv_t xe;
xdchange_t *xscr, *x;
int i1 = m->i1, i2 = m->i2;
/* let's handle just the conflicts */
if (m->mode)
continue;
xdl_merge(): fix a segmentation fault when refining conflicts The function xdl_refine_conflicts() tries to break down huge conflicts by doing a diff on the conflicting regions. However, this does not make sense when one side is empty. Worse, when one side is not only empty, but after EOF, the code accessed unmapped memory. Noticed by Luben Tuikov, Shawn Pearce and Alexandre Julliard, the latter providing a test case. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-28 16:13:33 +00:00
/* no sense refining a conflict when one side is empty */
if (m->chg1 == 0 || m->chg2 == 0)
continue;
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
/*
* This probably does not work outside git, since
* we have a very simple mmfile structure.
*/
t1.ptr = (char *)xe1->xdf2.recs[m->i1]->ptr;
xdl_merge(): fix an off-by-one bug The line range is i1 .. (i1 + chg1 - 1), not i1 .. (i1 + chg1). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-29 23:24:32 +00:00
t1.size = xe1->xdf2.recs[m->i1 + m->chg1 - 1]->ptr
+ xe1->xdf2.recs[m->i1 + m->chg1 - 1]->size - t1.ptr;
t2.ptr = (char *)xe2->xdf2.recs[m->i2]->ptr;
t2.size = xe2->xdf2.recs[m->i2 + m->chg2 - 1]->ptr
+ xe2->xdf2.recs[m->i2 + m->chg2 - 1]->size - t2.ptr;
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
if (xdl_do_diff(&t1, &t2, xpp, &xe) < 0)
return -1;
if (xdl_change_compact(&xe.xdf1, &xe.xdf2, xpp->flags) < 0 ||
xdl_change_compact(&xe.xdf2, &xe.xdf1, xpp->flags) < 0 ||
xdl_build_script(&xe, &xscr) < 0) {
xdl_free_env(&xe);
return -1;
}
if (!xscr) {
Fix yet another subtle xdl_merge() bug In very obscure cases, a merge can hit an unexpected code path (where the original code went as far as saying that this was a bug). This failing merge was noticed by Alexandre Juillard. The problem is that the original file contains something like this: -- snip -- two non-empty lines before two empty lines after two empty lines -- snap -- and this snippet is reduced to _one_ empty line in _both_ new files. However, it is ambiguous as to which hunk takes the empty line: the first or the second one? Indeed in Alexandre's example files, the xdiff algorithm attributes the empty line to the first hunk in one case, and to the second hunk in the other case. (Trimming down the example files _changes_ that behaviour!) Thus, the call to xdl_merge_cmp_lines() has no chance to realize that the change is actually identical in both new files. Therefore, xdl_refine_conflicts() finds an empty diff script, which was not expected there, because (the original author of xdl_merge() thought) xdl_merge_cmp_lines() would catch that case earlier. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-31 01:07:41 +00:00
/* If this happens, the changes are identical. */
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
xdl_free_env(&xe);
Fix yet another subtle xdl_merge() bug In very obscure cases, a merge can hit an unexpected code path (where the original code went as far as saying that this was a bug). This failing merge was noticed by Alexandre Juillard. The problem is that the original file contains something like this: -- snip -- two non-empty lines before two empty lines after two empty lines -- snap -- and this snippet is reduced to _one_ empty line in _both_ new files. However, it is ambiguous as to which hunk takes the empty line: the first or the second one? Indeed in Alexandre's example files, the xdiff algorithm attributes the empty line to the first hunk in one case, and to the second hunk in the other case. (Trimming down the example files _changes_ that behaviour!) Thus, the call to xdl_merge_cmp_lines() has no chance to realize that the change is actually identical in both new files. Therefore, xdl_refine_conflicts() finds an empty diff script, which was not expected there, because (the original author of xdl_merge() thought) xdl_merge_cmp_lines() would catch that case earlier. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-12-31 01:07:41 +00:00
m->mode = 4;
continue;
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
}
x = xscr;
m->i1 = xscr->i1 + i1;
m->chg1 = xscr->chg1;
m->i2 = xscr->i2 + i2;
m->chg2 = xscr->chg2;
while (xscr->next) {
xdmerge_t *m2 = xdl_malloc(sizeof(xdmerge_t));
if (!m2) {
xdl_free_env(&xe);
xdl_free_script(x);
return -1;
}
xscr = xscr->next;
m2->next = m->next;
m->next = m2;
m = m2;
m->mode = 0;
m->i1 = xscr->i1 + i1;
m->chg1 = xscr->chg1;
m->i2 = xscr->i2 + i2;
m->chg2 = xscr->chg2;
}
xdl_free_env(&xe);
xdl_free_script(x);
}
return 0;
}
xdl_merge(): introduce XDL_MERGE_ZEALOUS_ALNUM When a merge conflicts, there are often common lines that are not really common, such as empty lines or lines containing a single curly bracket. With XDL_MERGE_ZEALOUS_ALNUM, we use the following heuristics: when a hunk does not contain any letters or digits, it is treated as conflicting. In other words, a conflict which used to look like this: <<<<<<< a = 1; ======= output(); >>>>>>> } } } <<<<<<< output(); ======= b = 1; >>>>>>> will look like this with ZEALOUS_ALNUM: <<<<<<< a = 1; } } } output(); ======= output(); } } } b = 1; >>>>>>> To demonstrate this, git-merge-file has been switched from XDL_MERGE_ZEALOUS to XDL_MERGE_ZEALOUS_ALNUM. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-17 19:07:40 +00:00
static int line_contains_alnum(const char *ptr, long size)
{
while (size--)
if (isalnum(*(ptr++)))
return 1;
return 0;
}
static int lines_contain_alnum(xdfenv_t *xe, int i, int chg)
{
for (; chg; chg--, i++)
if (line_contains_alnum(xe->xdf2.recs[i]->ptr,
xe->xdf2.recs[i]->size))
return 1;
return 0;
}
xdl_merge(): make XDL_MERGE_ZEALOUS output simpler When a merge conflicts, there are often less than three common lines between two conflicting regions. Since a conflict takes up as many lines as are conflicting, plus three lines for the commit markers, the output will be shorter (and thus, simpler) in this case, if the common lines will be merged into the conflicting regions. This patch merges up to three common lines into the conflicts. For example, what looked like this before this patch: <<<<<<< if (a == 1) ======= if (a != 0) >>>>>>> { int i; <<<<<<< a = 0; ======= a = !a; >>>>>>> will now look like this: <<<<<<< if (a == 1) { int i; a = 0; ======= if (a != 0) { int i; a = !a; >>>>>>> Suggested Linus (based on ideas by "Voltage Spike" -- if that name is real, it is mighty cool). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-17 19:07:19 +00:00
/*
* This function merges m and m->next, marking everything between those hunks
* as conflicting, too.
*/
static void xdl_merge_two_conflicts(xdmerge_t *m)
{
xdmerge_t *next_m = m->next;
m->chg1 = next_m->i1 + next_m->chg1 - m->i1;
m->chg2 = next_m->i2 + next_m->chg2 - m->i2;
m->next = next_m->next;
free(next_m);
}
/*
* If there are less than 3 non-conflicting lines between conflicts,
* it appears simpler -- because it takes up less (or as many) lines --
* if the lines are moved into the conflicts.
*/
xdl_merge(): introduce XDL_MERGE_ZEALOUS_ALNUM When a merge conflicts, there are often common lines that are not really common, such as empty lines or lines containing a single curly bracket. With XDL_MERGE_ZEALOUS_ALNUM, we use the following heuristics: when a hunk does not contain any letters or digits, it is treated as conflicting. In other words, a conflict which used to look like this: <<<<<<< a = 1; ======= output(); >>>>>>> } } } <<<<<<< output(); ======= b = 1; >>>>>>> will look like this with ZEALOUS_ALNUM: <<<<<<< a = 1; } } } output(); ======= output(); } } } b = 1; >>>>>>> To demonstrate this, git-merge-file has been switched from XDL_MERGE_ZEALOUS to XDL_MERGE_ZEALOUS_ALNUM. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-17 19:07:40 +00:00
static int xdl_simplify_non_conflicts(xdfenv_t *xe1, xdmerge_t *m,
int simplify_if_no_alnum)
xdl_merge(): make XDL_MERGE_ZEALOUS output simpler When a merge conflicts, there are often less than three common lines between two conflicting regions. Since a conflict takes up as many lines as are conflicting, plus three lines for the commit markers, the output will be shorter (and thus, simpler) in this case, if the common lines will be merged into the conflicting regions. This patch merges up to three common lines into the conflicts. For example, what looked like this before this patch: <<<<<<< if (a == 1) ======= if (a != 0) >>>>>>> { int i; <<<<<<< a = 0; ======= a = !a; >>>>>>> will now look like this: <<<<<<< if (a == 1) { int i; a = 0; ======= if (a != 0) { int i; a = !a; >>>>>>> Suggested Linus (based on ideas by "Voltage Spike" -- if that name is real, it is mighty cool). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-17 19:07:19 +00:00
{
int result = 0;
if (!m)
return result;
for (;;) {
xdmerge_t *next_m = m->next;
int begin, end;
if (!next_m)
return result;
begin = m->i1 + m->chg1;
end = next_m->i1;
xdl_merge(): introduce XDL_MERGE_ZEALOUS_ALNUM When a merge conflicts, there are often common lines that are not really common, such as empty lines or lines containing a single curly bracket. With XDL_MERGE_ZEALOUS_ALNUM, we use the following heuristics: when a hunk does not contain any letters or digits, it is treated as conflicting. In other words, a conflict which used to look like this: <<<<<<< a = 1; ======= output(); >>>>>>> } } } <<<<<<< output(); ======= b = 1; >>>>>>> will look like this with ZEALOUS_ALNUM: <<<<<<< a = 1; } } } output(); ======= output(); } } } b = 1; >>>>>>> To demonstrate this, git-merge-file has been switched from XDL_MERGE_ZEALOUS to XDL_MERGE_ZEALOUS_ALNUM. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-17 19:07:40 +00:00
if (m->mode != 0 || next_m->mode != 0 ||
(end - begin > 3 &&
(!simplify_if_no_alnum ||
lines_contain_alnum(xe1, begin, end - begin)))) {
xdl_merge(): make XDL_MERGE_ZEALOUS output simpler When a merge conflicts, there are often less than three common lines between two conflicting regions. Since a conflict takes up as many lines as are conflicting, plus three lines for the commit markers, the output will be shorter (and thus, simpler) in this case, if the common lines will be merged into the conflicting regions. This patch merges up to three common lines into the conflicts. For example, what looked like this before this patch: <<<<<<< if (a == 1) ======= if (a != 0) >>>>>>> { int i; <<<<<<< a = 0; ======= a = !a; >>>>>>> will now look like this: <<<<<<< if (a == 1) { int i; a = 0; ======= if (a != 0) { int i; a = !a; >>>>>>> Suggested Linus (based on ideas by "Voltage Spike" -- if that name is real, it is mighty cool). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-17 19:07:19 +00:00
m = next_m;
xdl_merge(): introduce XDL_MERGE_ZEALOUS_ALNUM When a merge conflicts, there are often common lines that are not really common, such as empty lines or lines containing a single curly bracket. With XDL_MERGE_ZEALOUS_ALNUM, we use the following heuristics: when a hunk does not contain any letters or digits, it is treated as conflicting. In other words, a conflict which used to look like this: <<<<<<< a = 1; ======= output(); >>>>>>> } } } <<<<<<< output(); ======= b = 1; >>>>>>> will look like this with ZEALOUS_ALNUM: <<<<<<< a = 1; } } } output(); ======= output(); } } } b = 1; >>>>>>> To demonstrate this, git-merge-file has been switched from XDL_MERGE_ZEALOUS to XDL_MERGE_ZEALOUS_ALNUM. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-17 19:07:40 +00:00
} else {
xdl_merge(): make XDL_MERGE_ZEALOUS output simpler When a merge conflicts, there are often less than three common lines between two conflicting regions. Since a conflict takes up as many lines as are conflicting, plus three lines for the commit markers, the output will be shorter (and thus, simpler) in this case, if the common lines will be merged into the conflicting regions. This patch merges up to three common lines into the conflicts. For example, what looked like this before this patch: <<<<<<< if (a == 1) ======= if (a != 0) >>>>>>> { int i; <<<<<<< a = 0; ======= a = !a; >>>>>>> will now look like this: <<<<<<< if (a == 1) { int i; a = 0; ======= if (a != 0) { int i; a = !a; >>>>>>> Suggested Linus (based on ideas by "Voltage Spike" -- if that name is real, it is mighty cool). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-17 19:07:19 +00:00
result++;
xdl_merge_two_conflicts(m);
}
}
}
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
/*
* level == 0: mark all overlapping changes as conflict
* level == 1: mark overlapping changes as conflict only if not identical
* level == 2: analyze non-identical changes for minimal conflict set
xdl_merge(): introduce XDL_MERGE_ZEALOUS_ALNUM When a merge conflicts, there are often common lines that are not really common, such as empty lines or lines containing a single curly bracket. With XDL_MERGE_ZEALOUS_ALNUM, we use the following heuristics: when a hunk does not contain any letters or digits, it is treated as conflicting. In other words, a conflict which used to look like this: <<<<<<< a = 1; ======= output(); >>>>>>> } } } <<<<<<< output(); ======= b = 1; >>>>>>> will look like this with ZEALOUS_ALNUM: <<<<<<< a = 1; } } } output(); ======= output(); } } } b = 1; >>>>>>> To demonstrate this, git-merge-file has been switched from XDL_MERGE_ZEALOUS to XDL_MERGE_ZEALOUS_ALNUM. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-17 19:07:40 +00:00
* level == 3: analyze non-identical changes for minimal conflict set, but
* treat hunks not containing any letter or number as conflicting
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
*
* returns < 0 on error, == 0 for no conflicts, else number of conflicts
*/
static int xdl_do_merge(xdfenv_t *xe1, xdchange_t *xscr1, const char *name1,
xdfenv_t *xe2, xdchange_t *xscr2, const char *name2,
int level, xpparam_t const *xpp, mmbuffer_t *result) {
xdmerge_t *changes, *c;
int i1, i2, chg1, chg2;
c = changes = NULL;
while (xscr1 && xscr2) {
if (!changes)
changes = c;
if (xscr1->i1 + xscr1->chg1 < xscr2->i1) {
i1 = xscr1->i2;
i2 = xscr2->i2 - xscr2->i1 + xscr1->i1;
chg1 = xscr1->chg2;
chg2 = xscr1->chg1;
if (xdl_append_merge(&c, 1, i1, chg1, i2, chg2)) {
xdl_cleanup_merge(changes);
return -1;
}
xscr1 = xscr1->next;
continue;
}
if (xscr2->i1 + xscr2->chg1 < xscr1->i1) {
i1 = xscr1->i2 - xscr1->i1 + xscr2->i1;
i2 = xscr2->i2;
chg1 = xscr2->chg1;
chg2 = xscr2->chg2;
if (xdl_append_merge(&c, 2, i1, chg1, i2, chg2)) {
xdl_cleanup_merge(changes);
return -1;
}
xscr2 = xscr2->next;
continue;
}
if (level < 1 || xscr1->i1 != xscr2->i1 ||
xscr1->chg1 != xscr2->chg1 ||
xscr1->chg2 != xscr2->chg2 ||
xdl_merge_cmp_lines(xe1, xscr1->i2,
xe2, xscr2->i2,
xscr1->chg2, xpp->flags)) {
/* conflict */
int off = xscr1->i1 - xscr2->i1;
int ffo = off + xscr1->chg1 - xscr2->chg1;
i1 = xscr1->i2;
i2 = xscr2->i2;
if (off > 0)
i1 -= off;
else
i2 += off;
chg1 = xscr1->i2 + xscr1->chg2 - i1;
chg2 = xscr2->i2 + xscr2->chg2 - i2;
if (ffo > 0)
chg2 += ffo;
else
chg1 -= ffo;
if (xdl_append_merge(&c, 0, i1, chg1, i2, chg2)) {
xdl_cleanup_merge(changes);
return -1;
}
}
i1 = xscr1->i1 + xscr1->chg1;
i2 = xscr2->i1 + xscr2->chg1;
xdl_merge(): fix and simplify conflict handling Suppose you have changes in new1 to the original lines 10-20, and changes in new2 to the original lines 15-25, then the changes to 10-25 conflict. But it is possible that the next changes in new1 still overlap with this change to new2. So, in the next iteration we have to look at the same change to new2 again. The old code tried to be a bit too clever. The new code is shorter and more to the point: do not fiddle with the ranges at all. Also, xdl_append_merge() tries harder to combine conflicts. This is necessary, because with the above simplification, some conflicts would not be recognized as conflicts otherwise: In the above scenario, it is possible that there is no other change to new1. Absent the combine logic, the change in new2 would be recorded _again_, but as a non-conflict. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de>
2006-12-05 21:15:35 +00:00
if (i1 >= i2)
xdl_merge(): fix thinko If one side's block (of changed lines) ends later than the other side's block, the former should be tested against the next block of the other side, not vice versa. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-29 23:25:11 +00:00
xscr2 = xscr2->next;
xdl_merge(): fix and simplify conflict handling Suppose you have changes in new1 to the original lines 10-20, and changes in new2 to the original lines 15-25, then the changes to 10-25 conflict. But it is possible that the next changes in new1 still overlap with this change to new2. So, in the next iteration we have to look at the same change to new2 again. The old code tried to be a bit too clever. The new code is shorter and more to the point: do not fiddle with the ranges at all. Also, xdl_append_merge() tries harder to combine conflicts. This is necessary, because with the above simplification, some conflicts would not be recognized as conflicts otherwise: In the above scenario, it is possible that there is no other change to new1. Absent the combine logic, the change in new2 would be recorded _again_, but as a non-conflict. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de>
2006-12-05 21:15:35 +00:00
if (i2 >= i1)
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
xscr1 = xscr1->next;
}
while (xscr1) {
if (!changes)
changes = c;
i1 = xscr1->i2;
i2 = xscr1->i1 + xe2->xdf2.nrec - xe2->xdf1.nrec;
chg1 = xscr1->chg2;
chg2 = xscr1->chg1;
if (xdl_append_merge(&c, 1, i1, chg1, i2, chg2)) {
xdl_cleanup_merge(changes);
return -1;
}
xscr1 = xscr1->next;
}
while (xscr2) {
if (!changes)
changes = c;
i1 = xscr2->i1 + xe1->xdf2.nrec - xe1->xdf1.nrec;
i2 = xscr2->i2;
chg1 = xscr2->chg1;
chg2 = xscr2->chg2;
if (xdl_append_merge(&c, 2, i1, chg1, i2, chg2)) {
xdl_cleanup_merge(changes);
return -1;
}
xscr2 = xscr2->next;
}
if (!changes)
changes = c;
/* refine conflicts */
xdl_merge(): make XDL_MERGE_ZEALOUS output simpler When a merge conflicts, there are often less than three common lines between two conflicting regions. Since a conflict takes up as many lines as are conflicting, plus three lines for the commit markers, the output will be shorter (and thus, simpler) in this case, if the common lines will be merged into the conflicting regions. This patch merges up to three common lines into the conflicts. For example, what looked like this before this patch: <<<<<<< if (a == 1) ======= if (a != 0) >>>>>>> { int i; <<<<<<< a = 0; ======= a = !a; >>>>>>> will now look like this: <<<<<<< if (a == 1) { int i; a = 0; ======= if (a != 0) { int i; a = !a; >>>>>>> Suggested Linus (based on ideas by "Voltage Spike" -- if that name is real, it is mighty cool). Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-17 19:07:19 +00:00
if (level > 1 &&
(xdl_refine_conflicts(xe1, xe2, changes, xpp) < 0 ||
xdl_merge(): introduce XDL_MERGE_ZEALOUS_ALNUM When a merge conflicts, there are often common lines that are not really common, such as empty lines or lines containing a single curly bracket. With XDL_MERGE_ZEALOUS_ALNUM, we use the following heuristics: when a hunk does not contain any letters or digits, it is treated as conflicting. In other words, a conflict which used to look like this: <<<<<<< a = 1; ======= output(); >>>>>>> } } } <<<<<<< output(); ======= b = 1; >>>>>>> will look like this with ZEALOUS_ALNUM: <<<<<<< a = 1; } } } output(); ======= output(); } } } b = 1; >>>>>>> To demonstrate this, git-merge-file has been switched from XDL_MERGE_ZEALOUS to XDL_MERGE_ZEALOUS_ALNUM. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-17 19:07:40 +00:00
xdl_simplify_non_conflicts(xe1, changes, level > 2) < 0)) {
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
xdl_cleanup_merge(changes);
return -1;
}
/* output */
if (result) {
int size = xdl_fill_merge_buffer(xe1, name1, xe2, name2,
changes, NULL);
result->ptr = xdl_malloc(size);
if (!result->ptr) {
xdl_cleanup_merge(changes);
return -1;
}
result->size = size;
xdl_fill_merge_buffer(xe1, name1, xe2, name2, changes,
result->ptr);
}
return xdl_cleanup_merge(changes);
}
int xdl_merge(mmfile_t *orig, mmfile_t *mf1, const char *name1,
mmfile_t *mf2, const char *name2,
xpparam_t const *xpp, int level, mmbuffer_t *result) {
xdchange_t *xscr1, *xscr2;
xdfenv_t xe1, xe2;
xmerge: make return value from xdl_merge() more usable. The callers would want to know if the resulting merge is clean; do not discard that information away after calling xdl_do_merge(). Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-29 20:06:49 +00:00
int status;
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
result->ptr = NULL;
result->size = 0;
if (xdl_do_diff(orig, mf1, xpp, &xe1) < 0 ||
xdl_do_diff(orig, mf2, xpp, &xe2) < 0) {
return -1;
}
if (xdl_change_compact(&xe1.xdf1, &xe1.xdf2, xpp->flags) < 0 ||
xdl_change_compact(&xe1.xdf2, &xe1.xdf1, xpp->flags) < 0 ||
xdl_build_script(&xe1, &xscr1) < 0) {
xdl_free_env(&xe1);
return -1;
}
if (xdl_change_compact(&xe2.xdf1, &xe2.xdf2, xpp->flags) < 0 ||
xdl_change_compact(&xe2.xdf2, &xe2.xdf1, xpp->flags) < 0 ||
xdl_build_script(&xe2, &xscr2) < 0) {
xdl_free_env(&xe2);
return -1;
}
xmerge: make return value from xdl_merge() more usable. The callers would want to know if the resulting merge is clean; do not discard that information away after calling xdl_do_merge(). Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-29 20:06:49 +00:00
status = 0;
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
if (xscr1 || xscr2) {
if (!xscr1) {
result->ptr = xdl_malloc(mf2->size);
memcpy(result->ptr, mf2->ptr, mf2->size);
result->size = mf2->size;
} else if (!xscr2) {
result->ptr = xdl_malloc(mf1->size);
memcpy(result->ptr, mf1->ptr, mf1->size);
result->size = mf1->size;
xmerge: make return value from xdl_merge() more usable. The callers would want to know if the resulting merge is clean; do not discard that information away after calling xdl_do_merge(). Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-29 20:06:49 +00:00
} else {
status = xdl_do_merge(&xe1, xscr1, name1,
&xe2, xscr2, name2,
level, xpp, result);
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
}
xdl_free_script(xscr1);
xdl_free_script(xscr2);
}
xdl_free_env(&xe1);
xdl_free_env(&xe2);
xmerge: make return value from xdl_merge() more usable. The callers would want to know if the resulting merge is clean; do not discard that information away after calling xdl_do_merge(). Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-29 20:06:49 +00:00
return status;
xdiff: add xdl_merge() This new function implements the functionality of RCS merge, but in-memory. It returns < 0 on error, otherwise the number of conflicts. Finding the conflicting lines can be a very expensive task. You can control the eagerness of this algorithm: - a level value of 0 means that all overlapping changes are treated as conflicts, - a value of 1 means that if the overlapping changes are identical, it is not treated as a conflict. - If you set level to 2, overlapping changes will be analyzed, so that almost identical changes will not result in huge conflicts. Rather, only the conflicting lines will be shown inside conflict markers. With each increasing level, the algorithm gets slower, but more accurate. Note that the code for level 2 depends on the simple definition of mmfile_t specific to git, and therefore it will be harder to port that to LibXDiff. Signed-off-by: Johannes Schindelin <Johannes.Schindelin@gmx.de> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-11-21 22:24:34 +00:00
}
Reference in a new issue Copy permalink