Revision 1335d76e4569fa84e52dc24c88c04daeae6e160e authored by Junio C Hamano on 08 July 2016, 17:59:15 UTC, committed by Junio C Hamano on 12 July 2016, 20:06:43 UTC
When merge_recursive() decides what the correct blob object merge result for a path should be, it uses update_file_flags() helper function to write it out to a working tree file and then calls add_cacheinfo(). The add_cacheinfo() function in turn calls make_cache_entry() to create a new cache entry to replace the higher-stage entries for the path that represents the conflict. The make_cache_entry() function calls refresh_cache_entry() to fill in the cached stat information. To mark a cache entry as up-to-date, the data is re-read from the file in the working tree, and goes through convert_to_git() conversion to be compared with the blob object name the new cache entry records. It is important to note that this happens while the higher-stage entries, which are going to be replaced with the new entry, are still in the index. Unfortunately, the convert_to_git() conversion has a misguided "safer crlf" mechanism baked in, and looks at the existing cache entry for the path to decide how to convert the contents in the working tree file. If our side (i.e. stage#2) records a text blob with CRLF in it, even when the system is configured to record LF in blobs and convert them to CRLF upon checkout (and back to LF upon checkin), the "safer crlf" mechanism stops us doing so. This especially poses a problem during a renormalizing merge, where the merge result for the path is computed by first "normalizing" the blobs involved in the merge by using convert_to_working_tree() followed by convert_to_git() with "safer crlf" disabled. The merge result that is computed correctly and fed to add_cacheinfo() via update_file_flags() does _not_ match what refresh_cache_entry() sees by converting the working tree file via convert_to_git(). We can work this around by not refreshing the new cache entry in make_cache_entry() called by add_cacheinfo(). After add_cacheinfo() adds the new entry, we can call refresh_cache_entry() on that, knowing that addition of this new cache entry would have removed the stale cache entries that had CRLF in stage #2 that were carried over before the renormalizing merge started and will not interfere with the correct recording of the result. The test update was taken from a series by Torsten Bögershausen that attempted to fix this with a different approach. Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com> Reviewed-by: Torsten Bögershausen <tboegi@web.de>
1 parent 6523728
tree.c
#include "cache.h"
#include "cache-tree.h"
#include "tree.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include "tree-walk.h"
const char *tree_type = "tree";
static int read_one_entry_opt(const unsigned char *sha1, const char *base, int baselen, const char *pathname, unsigned mode, int stage, int opt)
{
int len;
unsigned int size;
struct cache_entry *ce;
if (S_ISDIR(mode))
return READ_TREE_RECURSIVE;
len = strlen(pathname);
size = cache_entry_size(baselen + len);
ce = xcalloc(1, size);
ce->ce_mode = create_ce_mode(mode);
ce->ce_flags = create_ce_flags(stage);
ce->ce_namelen = baselen + len;
memcpy(ce->name, base, baselen);
memcpy(ce->name + baselen, pathname, len+1);
hashcpy(ce->sha1, sha1);
return add_cache_entry(ce, opt);
}
static int read_one_entry(const unsigned char *sha1, struct strbuf *base,
const char *pathname, unsigned mode, int stage,
void *context)
{
return read_one_entry_opt(sha1, base->buf, base->len, pathname,
mode, stage,
ADD_CACHE_OK_TO_ADD|ADD_CACHE_SKIP_DFCHECK);
}
/*
* This is used when the caller knows there is no existing entries at
* the stage that will conflict with the entry being added.
*/
static int read_one_entry_quick(const unsigned char *sha1, struct strbuf *base,
const char *pathname, unsigned mode, int stage,
void *context)
{
return read_one_entry_opt(sha1, base->buf, base->len, pathname,
mode, stage,
ADD_CACHE_JUST_APPEND);
}
static int read_tree_1(struct tree *tree, struct strbuf *base,
int stage, const struct pathspec *pathspec,
read_tree_fn_t fn, void *context)
{
struct tree_desc desc;
struct name_entry entry;
unsigned char sha1[20];
int len, oldlen = base->len;
enum interesting retval = entry_not_interesting;
if (parse_tree(tree))
return -1;
init_tree_desc(&desc, tree->buffer, tree->size);
while (tree_entry(&desc, &entry)) {
if (retval != all_entries_interesting) {
retval = tree_entry_interesting(&entry, base, 0, pathspec);
if (retval == all_entries_not_interesting)
break;
if (retval == entry_not_interesting)
continue;
}
switch (fn(entry.sha1, base,
entry.path, entry.mode, stage, context)) {
case 0:
continue;
case READ_TREE_RECURSIVE:
break;
default:
return -1;
}
if (S_ISDIR(entry.mode))
hashcpy(sha1, entry.sha1);
else if (S_ISGITLINK(entry.mode)) {
struct commit *commit;
commit = lookup_commit(entry.sha1);
if (!commit)
die("Commit %s in submodule path %s%s not found",
sha1_to_hex(entry.sha1),
base->buf, entry.path);
if (parse_commit(commit))
die("Invalid commit %s in submodule path %s%s",
sha1_to_hex(entry.sha1),
base->buf, entry.path);
hashcpy(sha1, commit->tree->object.oid.hash);
}
else
continue;
len = tree_entry_len(&entry);
strbuf_add(base, entry.path, len);
strbuf_addch(base, '/');
retval = read_tree_1(lookup_tree(sha1),
base, stage, pathspec,
fn, context);
strbuf_setlen(base, oldlen);
if (retval)
return -1;
}
return 0;
}
int read_tree_recursive(struct tree *tree,
const char *base, int baselen,
int stage, const struct pathspec *pathspec,
read_tree_fn_t fn, void *context)
{
struct strbuf sb = STRBUF_INIT;
int ret;
strbuf_add(&sb, base, baselen);
ret = read_tree_1(tree, &sb, stage, pathspec, fn, context);
strbuf_release(&sb);
return ret;
}
static int cmp_cache_name_compare(const void *a_, const void *b_)
{
const struct cache_entry *ce1, *ce2;
ce1 = *((const struct cache_entry **)a_);
ce2 = *((const struct cache_entry **)b_);
return cache_name_stage_compare(ce1->name, ce1->ce_namelen, ce_stage(ce1),
ce2->name, ce2->ce_namelen, ce_stage(ce2));
}
int read_tree(struct tree *tree, int stage, struct pathspec *match)
{
read_tree_fn_t fn = NULL;
int i, err;
/*
* Currently the only existing callers of this function all
* call it with stage=1 and after making sure there is nothing
* at that stage; we could always use read_one_entry_quick().
*
* But when we decide to straighten out git-read-tree not to
* use unpack_trees() in some cases, this will probably start
* to matter.
*/
/*
* See if we have cache entry at the stage. If so,
* do it the original slow way, otherwise, append and then
* sort at the end.
*/
for (i = 0; !fn && i < active_nr; i++) {
const struct cache_entry *ce = active_cache[i];
if (ce_stage(ce) == stage)
fn = read_one_entry;
}
if (!fn)
fn = read_one_entry_quick;
err = read_tree_recursive(tree, "", 0, stage, match, fn, NULL);
if (fn == read_one_entry || err)
return err;
/*
* Sort the cache entry -- we need to nuke the cache tree, though.
*/
cache_tree_free(&active_cache_tree);
qsort(active_cache, active_nr, sizeof(active_cache[0]),
cmp_cache_name_compare);
return 0;
}
struct tree *lookup_tree(const unsigned char *sha1)
{
struct object *obj = lookup_object(sha1);
if (!obj)
return create_object(sha1, alloc_tree_node());
return object_as_type(obj, OBJ_TREE, 0);
}
int parse_tree_buffer(struct tree *item, void *buffer, unsigned long size)
{
if (item->object.parsed)
return 0;
item->object.parsed = 1;
item->buffer = buffer;
item->size = size;
return 0;
}
int parse_tree_gently(struct tree *item, int quiet_on_missing)
{
enum object_type type;
void *buffer;
unsigned long size;
if (item->object.parsed)
return 0;
buffer = read_sha1_file(item->object.oid.hash, &type, &size);
if (!buffer)
return quiet_on_missing ? -1 :
error("Could not read %s",
oid_to_hex(&item->object.oid));
if (type != OBJ_TREE) {
free(buffer);
return error("Object %s not a tree",
oid_to_hex(&item->object.oid));
}
return parse_tree_buffer(item, buffer, size);
}
void free_tree_buffer(struct tree *tree)
{
free(tree->buffer);
tree->buffer = NULL;
tree->size = 0;
tree->object.parsed = 0;
}
struct tree *parse_tree_indirect(const unsigned char *sha1)
{
struct object *obj = parse_object(sha1);
do {
if (!obj)
return NULL;
if (obj->type == OBJ_TREE)
return (struct tree *) obj;
else if (obj->type == OBJ_COMMIT)
obj = &(((struct commit *) obj)->tree->object);
else if (obj->type == OBJ_TAG)
obj = ((struct tag *) obj)->tagged;
else
return NULL;
if (!obj->parsed)
parse_object(obj->oid.hash);
} while (1);
}
Computing file changes ...