Browse Source

Status update on merge-recursive in C

This is just an update for people being interested. Alex and me were
busy with that project for a few days now. While it has progressed nicely,
there are quite a couple TODOs in merge-recursive.c, just search for "TODO".

For impatient people: yes, it passes all the tests, and yes, according
to the evil test Alex did, it is faster than the Python script.

But no, it is not yet finished. Biggest points are:

- there are still three external calls
- in the end, it should not be necessary to write the index more than once
  (just before exiting)
- a lot of things can be refactored to make the code easier and shorter

BTW we cannot just plug in git-merge-tree yet, because git-merge-tree
does not handle renames at all.

This patch is meant for testing, and as such,

- it compile the program to git-merge-recur
- it adjusts the scripts and tests to use git-merge-recur instead of
  git-merge-recursive
- it provides "TEST", a script to execute the tests regarding -recursive
- it inlines the changes to read-cache.c (read_cache_from(), discard_cache()
  and refresh_cache_entry())

Brought to you by Alex Riesen and Dscho

Signed-off-by: Junio C Hamano <junkio@cox.net>
maint
Johannes Schindelin 19 years ago committed by Junio C Hamano
parent
commit
6d297f8137
  1. 8
      Makefile
  2. 10
      TEST
  3. 4
      cache.h
  4. 6
      git-merge.sh
  5. 4
      git-rebase.sh
  6. 1560
      merge-recursive.c
  7. 105
      path-list.c
  8. 22
      path-list.h
  9. 104
      read-cache.c
  10. 2
      t/t3402-rebase-merge.sh

8
Makefile

@ -167,7 +167,8 @@ PROGRAMS = \ @@ -167,7 +167,8 @@ PROGRAMS = \
git-upload-pack$X git-verify-pack$X \
git-symbolic-ref$X \
git-name-rev$X git-pack-redundant$X git-repo-config$X git-var$X \
git-describe$X git-merge-tree$X git-blame$X git-imap-send$X
git-describe$X git-merge-tree$X git-blame$X git-imap-send$X \
git-merge-recur$X

BUILT_INS = git-log$X git-whatchanged$X git-show$X git-update-ref$X \
git-count-objects$X git-diff$X git-push$X git-mailsplit$X \
@ -615,6 +616,11 @@ git-http-push$X: revision.o http.o http-push.o $(GITLIBS) @@ -615,6 +616,11 @@ git-http-push$X: revision.o http.o http-push.o $(GITLIBS)
$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \
$(LIBS) $(CURL_LIBCURL) $(EXPAT_LIBEXPAT)

merge-recursive.o path-list.o: path-list.h
git-merge-recur$X: merge-recursive.o path-list.o $(LIB_FILE)
$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) \
$(LIBS)

$(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
$(patsubst git-%$X,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
$(DIFF_OBJS): diffcore.h

10
TEST

@ -0,0 +1,10 @@ @@ -0,0 +1,10 @@
#!/bin/sh -x
cd t || exit
./t3400-rebase.sh "$@" && \
./t6020-merge-df.sh "$@" && \
./t3401-rebase-partial.sh "$@" && \
./t6021-merge-criss-cross.sh "$@" && \
./t3402-rebase-merge.sh "$@" && \
./t6022-merge-rename.sh "$@" && \
./t6010-merge-base.sh "$@" && \
:

4
cache.h

@ -115,6 +115,7 @@ static inline unsigned int create_ce_mode(unsigned int mode) @@ -115,6 +115,7 @@ static inline unsigned int create_ce_mode(unsigned int mode)
extern struct cache_entry **active_cache;
extern unsigned int active_nr, active_alloc, active_cache_changed;
extern struct cache_tree *active_cache_tree;
extern int cache_errno;

#define GIT_DIR_ENVIRONMENT "GIT_DIR"
#define DEFAULT_GIT_DIR_ENVIRONMENT ".git"
@ -142,13 +143,16 @@ extern void verify_non_filename(const char *prefix, const char *name); @@ -142,13 +143,16 @@ extern void verify_non_filename(const char *prefix, const char *name);

/* Initialize and use the cache information */
extern int read_cache(void);
extern int read_cache_from(const char *path);
extern int write_cache(int newfd, struct cache_entry **cache, int entries);
extern int discard_cache(void);
extern int verify_path(const char *path);
extern int cache_name_pos(const char *name, int namelen);
#define ADD_CACHE_OK_TO_ADD 1 /* Ok to add */
#define ADD_CACHE_OK_TO_REPLACE 2 /* Ok to replace file/directory */
#define ADD_CACHE_SKIP_DFCHECK 4 /* Ok to skip DF conflict checks */
extern int add_cache_entry(struct cache_entry *ce, int option);
extern struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really);
extern int remove_cache_entry_at(int pos);
extern int remove_file_from_cache(const char *path);
extern int ce_same_name(struct cache_entry *a, struct cache_entry *b);

6
git-merge.sh

@ -9,15 +9,15 @@ USAGE='[-n] [--no-commit] [--squash] [-s <strategy>]... <merge-message> <head> < @@ -9,15 +9,15 @@ USAGE='[-n] [--no-commit] [--squash] [-s <strategy>]... <merge-message> <head> <
LF='
'

all_strategies='recursive octopus resolve stupid ours'
default_twohead_strategies='recursive'
all_strategies='recur recur octopus resolve stupid ours'
default_twohead_strategies='recur'
default_octopus_strategies='octopus'
no_trivial_merge_strategies='ours'
use_strategies=

index_merge=t
if test "@@NO_PYTHON@@"; then
all_strategies='resolve octopus stupid ours'
all_strategies='recur resolve octopus stupid ours'
default_twohead_strategies='resolve'
fi


4
git-rebase.sh

@ -35,7 +35,7 @@ If you would prefer to skip this patch, instead run \"git rebase --skip\". @@ -35,7 +35,7 @@ If you would prefer to skip this patch, instead run \"git rebase --skip\".
To restore the original branch and stop rebasing run \"git rebase --abort\".
"
unset newbase
strategy=recursive
strategy=recur
do_merge=
dotest=$GIT_DIR/.dotest-merge
prec=4
@ -292,7 +292,7 @@ then @@ -292,7 +292,7 @@ then
exit $?
fi

if test "@@NO_PYTHON@@" && test "$strategy" = "recursive"
if test "@@NO_PYTHON@@" && test "$strategy" = "recur"
then
die 'The recursive merge strategy currently relies on Python,
which this installation of git was not configured with. Please consider

1560
merge-recursive.c

File diff suppressed because it is too large Load Diff

105
path-list.c

@ -0,0 +1,105 @@ @@ -0,0 +1,105 @@
#include <stdio.h>
#include "cache.h"
#include "path-list.h"

/* if there is no exact match, point to the index where the entry could be
* inserted */
static int get_entry_index(const struct path_list *list, const char *path,
int *exact_match)
{
int left = -1, right = list->nr;

while (left + 1 < right) {
int middle = (left + right) / 2;
int compare = strcmp(path, list->items[middle].path);
if (compare < 0)
right = middle;
else if (compare > 0)
left = middle;
else {
*exact_match = 1;
return middle;
}
}

*exact_match = 0;
return right;
}

/* returns -1-index if already exists */
static int add_entry(struct path_list *list, const char *path)
{
int exact_match;
int index = get_entry_index(list, path, &exact_match);

if (exact_match)
return -1 - index;

if (list->nr + 1 >= list->alloc) {
list->alloc += 32;
list->items = xrealloc(list->items, list->alloc
* sizeof(struct path_list_item));
}
if (index < list->nr)
memmove(list->items + index + 1, list->items + index,
(list->nr - index)
* sizeof(struct path_list_item));
list->items[index].path = list->strdup_paths ?
strdup(path) : (char *)path;
list->items[index].util = NULL;
list->nr++;

return index;
}

struct path_list_item *path_list_insert(const char *path, struct path_list *list)
{
int index = add_entry(list, path);

if (index < 0)
index = 1 - index;

return list->items + index;
}

int path_list_has_path(const struct path_list *list, const char *path)
{
int exact_match;
get_entry_index(list, path, &exact_match);
return exact_match;
}

struct path_list_item *path_list_lookup(const char *path, struct path_list *list)
{
int exact_match, i = get_entry_index(list, path, &exact_match);
if (!exact_match)
return NULL;
return list->items + i;
}

void path_list_clear(struct path_list *list, int free_items)
{
if (list->items) {
int i;
if (free_items)
for (i = 0; i < list->nr; i++) {
if (list->strdup_paths)
free(list->items[i].path);
if (list->items[i].util)
free(list->items[i].util);
}
free(list->items);
}
list->items = NULL;
list->nr = list->alloc = 0;
}

void print_path_list(const char *text, const struct path_list *p)
{
int i;
if ( text )
printf("%s\n", text);
for (i = 0; i < p->nr; i++)
printf("%s:%p\n", p->items[i].path, p->items[i].util);
}

22
path-list.h

@ -0,0 +1,22 @@ @@ -0,0 +1,22 @@
#ifndef _PATH_LIST_H_
#define _PATH_LIST_H_

struct path_list_item {
char *path;
void *util;
};
struct path_list
{
struct path_list_item *items;
unsigned int nr, alloc;
unsigned int strdup_paths:1;
};

void print_path_list(const char *text, const struct path_list *p);

int path_list_has_path(const struct path_list *list, const char *path);
void path_list_clear(struct path_list *list, int free_items);
struct path_list_item *path_list_insert(const char *path, struct path_list *list);
struct path_list_item *path_list_lookup(const char *path, struct path_list *list);

#endif /* _PATH_LIST_H_ */

104
read-cache.c

@ -24,6 +24,11 @@ unsigned int active_nr = 0, active_alloc = 0, active_cache_changed = 0; @@ -24,6 +24,11 @@ unsigned int active_nr = 0, active_alloc = 0, active_cache_changed = 0;

struct cache_tree *active_cache_tree = NULL;

int cache_errno = 0;

static void *cache_mmap = NULL;
static size_t cache_mmap_size = 0;

/*
* This only updates the "non-critical" parts of the directory
* cache, ie the parts that aren't tracked by GIT, and only used
@ -577,22 +582,6 @@ int add_cache_entry(struct cache_entry *ce, int option) @@ -577,22 +582,6 @@ int add_cache_entry(struct cache_entry *ce, int option)
return 0;
}

/* Three functions to allow overloaded pointer return; see linux/err.h */
static inline void *ERR_PTR(long error)
{
return (void *) error;
}

static inline long PTR_ERR(const void *ptr)
{
return (long) ptr;
}

static inline long IS_ERR(const void *ptr)
{
return (unsigned long)ptr > (unsigned long)-1000L;
}

/*
* "refresh" does not calculate a new sha1 file or bring the
* cache up-to-date for mode/content changes. But what it
@ -604,14 +593,16 @@ static inline long IS_ERR(const void *ptr) @@ -604,14 +593,16 @@ static inline long IS_ERR(const void *ptr)
* For example, you'd want to do this after doing a "git-read-tree",
* to link up the stat cache details with the proper files.
*/
static struct cache_entry *refresh_entry(struct cache_entry *ce, int really)
struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really)
{
struct stat st;
struct cache_entry *updated;
int changed, size;

if (lstat(ce->name, &st) < 0)
return ERR_PTR(-errno);
if (lstat(ce->name, &st) < 0) {
cache_errno = errno;
return NULL;
}

changed = ce_match_stat(ce, &st, really);
if (!changed) {
@ -619,11 +610,13 @@ static struct cache_entry *refresh_entry(struct cache_entry *ce, int really) @@ -619,11 +610,13 @@ static struct cache_entry *refresh_entry(struct cache_entry *ce, int really)
!(ce->ce_flags & htons(CE_VALID)))
; /* mark this one VALID again */
else
return NULL;
return ce;
}

if (ce_modified(ce, &st, really))
return ERR_PTR(-EINVAL);
if (ce_modified(ce, &st, really)) {
cache_errno = EINVAL;
return NULL;
}

size = ce_size(ce);
updated = xmalloc(size);
@ -666,13 +659,13 @@ int refresh_cache(unsigned int flags) @@ -666,13 +659,13 @@ int refresh_cache(unsigned int flags)
continue;
}

new = refresh_entry(ce, really);
if (!new)
new = refresh_cache_entry(ce, really);
if (new == ce)
continue;
if (IS_ERR(new)) {
if (not_new && PTR_ERR(new) == -ENOENT)
if (!new) {
if (not_new && cache_errno == ENOENT)
continue;
if (really && PTR_ERR(new) == -EINVAL) {
if (really && cache_errno == EINVAL) {
/* If we are doing --really-refresh that
* means the index is not valid anymore.
*/
@ -728,40 +721,44 @@ static int read_index_extension(const char *ext, void *data, unsigned long sz) @@ -728,40 +721,44 @@ static int read_index_extension(const char *ext, void *data, unsigned long sz)
}

int read_cache(void)
{
return read_cache_from(get_index_file());
}

/* remember to discard_cache() before reading a different cache! */
int read_cache_from(const char *path)
{
int fd, i;
struct stat st;
unsigned long size, offset;
void *map;
unsigned long offset;
struct cache_header *hdr;

errno = EBUSY;
if (active_cache)
if (cache_mmap)
return active_nr;

errno = ENOENT;
index_file_timestamp = 0;
fd = open(get_index_file(), O_RDONLY);
fd = open(path, O_RDONLY);
if (fd < 0) {
if (errno == ENOENT)
return 0;
die("index file open failed (%s)", strerror(errno));
}

size = 0; /* avoid gcc warning */
map = MAP_FAILED;
cache_mmap = MAP_FAILED;
if (!fstat(fd, &st)) {
size = st.st_size;
cache_mmap_size = st.st_size;
errno = EINVAL;
if (size >= sizeof(struct cache_header) + 20)
map = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
if (cache_mmap_size >= sizeof(struct cache_header) + 20)
cache_mmap = mmap(NULL, cache_mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
}
close(fd);
if (map == MAP_FAILED)
if (cache_mmap == MAP_FAILED)
die("index file mmap failed (%s)", strerror(errno));

hdr = map;
if (verify_hdr(hdr, size) < 0)
hdr = cache_mmap;
if (verify_hdr(hdr, cache_mmap_size) < 0)
goto unmap;

active_nr = ntohl(hdr->hdr_entries);
@ -770,12 +767,12 @@ int read_cache(void) @@ -770,12 +767,12 @@ int read_cache(void)

offset = sizeof(*hdr);
for (i = 0; i < active_nr; i++) {
struct cache_entry *ce = (struct cache_entry *) ((char *) map + offset);
struct cache_entry *ce = (struct cache_entry *) ((char *) cache_mmap + offset);
offset = offset + ce_size(ce);
active_cache[i] = ce;
}
index_file_timestamp = st.st_mtime;
while (offset <= size - 20 - 8) {
while (offset <= cache_mmap_size - 20 - 8) {
/* After an array of active_nr index entries,
* there can be arbitrary number of extended
* sections, each of which is prefixed with
@ -783,10 +780,10 @@ int read_cache(void) @@ -783,10 +780,10 @@ int read_cache(void)
* in 4-byte network byte order.
*/
unsigned long extsize;
memcpy(&extsize, (char *) map + offset + 4, 4);
memcpy(&extsize, (char *) cache_mmap + offset + 4, 4);
extsize = ntohl(extsize);
if (read_index_extension(((const char *) map) + offset,
(char *) map + offset + 8,
if (read_index_extension(((const char *) cache_mmap) + offset,
(char *) cache_mmap + offset + 8,
extsize) < 0)
goto unmap;
offset += 8;
@ -795,11 +792,28 @@ int read_cache(void) @@ -795,11 +792,28 @@ int read_cache(void)
return active_nr;

unmap:
munmap(map, size);
munmap(cache_mmap, cache_mmap_size);
errno = EINVAL;
die("index file corrupt");
}

int discard_cache()
{
int ret;

if (cache_mmap == NULL)
return 0;
ret = munmap(cache_mmap, cache_mmap_size);
cache_mmap = NULL;
cache_mmap_size = 0;
active_nr = active_cache_changed = 0;
index_file_timestamp = 0;
cache_tree_free(&active_cache_tree);

/* no need to throw away allocated active_cache */
return ret;
}

#define WRITE_BUFFER_SIZE 8192
static unsigned char write_buffer[WRITE_BUFFER_SIZE];
static unsigned long write_buffer_len;

2
t/t3402-rebase-merge.sh

@ -51,7 +51,7 @@ test_expect_success setup ' @@ -51,7 +51,7 @@ test_expect_success setup '
'

test_expect_success 'reference merge' '
git merge -s recursive "reference merge" HEAD master
git merge -s recur "reference merge" HEAD master
'

test_expect_success rebase '

Loading…
Cancel
Save