rerere: explain the primary codepath

Explain the internals of rerere as in-code comments, while
sprinkling "NEEDSWORK" comment to highlight iffy bits and
questionable assumptions.

This one covers the codepath reached from rerere(), the primary
interface to the subsystem.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Junio C Hamano 2015-06-30 22:40:35 -07:00
Родитель 4b68c2a087
Коммит cc899eca55
1 изменённых файлов: 82 добавлений и 13 удалений

Просмотреть файл

@ -206,6 +206,21 @@ static int is_cmarker(char *buf, int marker_char, int marker_size)
return isspace(*buf);
}
/*
* Read contents a file with conflicts, normalize the conflicts
* by (1) discarding the common ancestor version in diff3-style,
* (2) reordering our side and their side so that whichever sorts
* alphabetically earlier comes before the other one, while
* computing the "conflict ID", which is just an SHA-1 hash of
* one side of the conflict, NUL, the other side of the conflict,
* and NUL concatenated together.
*
* Return the number of conflict hunks found.
*
* NEEDSWORK: the logic and theory of operation behind this conflict
* normalization may deserve to be documented somewhere, perhaps in
* Documentation/technical/rerere.txt.
*/
static int handle_path(unsigned char *sha1, struct rerere_io *io, int marker_size)
{
git_SHA_CTX ctx;
@ -276,6 +291,10 @@ static int handle_path(unsigned char *sha1, struct rerere_io *io, int marker_siz
return hunk_no;
}
/*
* Scan the path for conflicts, do the "handle_path()" thing above, and
* return the number of conflict hunks found.
*/
static int handle_file(const char *path, unsigned char *sha1, const char *output)
{
int hunk_no = 0;
@ -515,12 +534,26 @@ int rerere_remaining(struct string_list *merge_rr)
return 0;
}
/*
* Find the conflict identified by "name"; the change between its
* "preimage" (i.e. a previous contents with conflict markers) and its
* "postimage" (i.e. the corresponding contents with conflicts
* resolved) may apply cleanly to the contents stored in "path", i.e.
* the conflict this time around.
*
* Returns 0 for successful replay of recorded resolution, or non-zero
* for failure.
*/
static int merge(const char *name, const char *path)
{
int ret;
mmfile_t cur = {NULL, 0}, base = {NULL, 0}, other = {NULL, 0};
mmbuffer_t result = {NULL, 0};
/*
* Normalize the conflicts in path and write it out to
* "thisimage" temporary file.
*/
if (handle_file(path, NULL, rerere_path(name, "thisimage")) < 0)
return 1;
@ -530,14 +563,25 @@ static int merge(const char *name, const char *path)
ret = 1;
goto out;
}
/*
* A three-way merge. Note that this honors user-customizable
* low-level merge driver settings.
*/
ret = ll_merge(&result, path, &base, NULL, &cur, "", &other, "", NULL);
if (!ret) {
FILE *f;
/*
* A successful replay of recorded resolution.
* Mark that "postimage" was used to help gc.
*/
if (utime(rerere_path(name, "postimage"), NULL) < 0)
warning("failed utime() on %s: %s",
rerere_path(name, "postimage"),
strerror(errno));
/* Update "path" with the resolution */
f = fopen(path, "w");
if (!f)
return error("Could not open %s: %s", path,
@ -590,41 +634,61 @@ static int do_plain_rerere(struct string_list *rr, int fd)
find_conflict(&conflict);
/*
* MERGE_RR records paths with conflicts immediately after merge
* failed. Some of the conflicted paths might have been hand resolved
* in the working tree since then, but the initial run would catch all
* and register their preimages.
* MERGE_RR records paths with conflicts immediately after
* merge failed. Some of the conflicted paths might have been
* hand resolved in the working tree since then, but the
* initial run would catch all and register their preimages.
*/
for (i = 0; i < conflict.nr; i++) {
const char *path = conflict.items[i].string;
if (!string_list_has_string(rr, path)) {
unsigned char sha1[20];
char *hex;
int ret;
/*
* Ask handle_file() to scan and assign a
* conflict ID. No need to write anything out
* yet.
*/
ret = handle_file(path, sha1, NULL);
if (ret < 1)
continue;
hex = xstrdup(sha1_to_hex(sha1));
string_list_insert(rr, path)->util = hex;
/*
* If the directory does not exist, create
* it. mkdir_in_gitdir() will fail with
* EEXIST if there already is one.
*
* NEEDSWORK: make sure "gc" does not remove
* preimage without removing the directory.
*/
if (mkdir_in_gitdir(git_path("rr-cache/%s", hex)))
continue;
/*
* We are the first to encounter this
* conflict. Ask handle_file() to write the
* normalized contents to the "preimage" file.
*/
handle_file(path, NULL, rerere_path(hex, "preimage"));
fprintf(stderr, "Recorded preimage for '%s'\n", path);
}
}
/*
* Now some of the paths that had conflicts earlier might have been
* hand resolved. Others may be similar to a conflict already that
* was resolved before.
* Some of the paths that had conflicts earlier might have
* been resolved by the user. Others may be similar to a
* conflict already that was resolved before.
*/
for (i = 0; i < rr->nr; i++) {
int ret;
const char *path = rr->items[i].string;
const char *name = (const char *)rr->items[i].util;
/* Is there a recorded resolution we could attempt to apply? */
if (has_rerere_resolution(name)) {
if (merge(name, path))
continue;
@ -638,13 +702,13 @@ static int do_plain_rerere(struct string_list *rr, int fd)
goto mark_resolved;
}
/* Let's see if we have resolved it. */
/* Let's see if the user has resolved it. */
ret = handle_file(path, NULL, NULL);
if (ret)
continue;
fprintf(stderr, "Recorded resolution for '%s'.\n", path);
copy_file(rerere_path(name, "postimage"), path, 0666);
fprintf(stderr, "Recorded resolution for '%s'.\n", path);
mark_resolved:
free(rr->items[i].util);
rr->items[i].util = NULL;
@ -698,6 +762,11 @@ int setup_rerere(struct string_list *merge_rr, int flags)
return fd;
}
/*
* The main entry point that is called internally from codepaths that
* perform mergy operations, possibly leaving conflicted index entries
* and working tree files.
*/
int rerere(int flags)
{
struct string_list merge_rr = STRING_LIST_INIT_DUP;