Merge branch 'en/ort-readiness'
Plug the ort merge backend throughout the rest of the system, and
start testing it as a replacement for the recursive backend.
* en/ort-readiness:
Add testing with merge-ort merge strategy
t6423: mark remaining expected failure under merge-ort as such
Revert "merge-ort: ignore the directory rename split conflict for now"
merge-recursive: add a bunch of FIXME comments documenting known bugs
merge-ort: write $GIT_DIR/AUTO_MERGE whenever we hit a conflict
t: mark several submodule merging tests as fixed under merge-ort
merge-ort: implement CE_SKIP_WORKTREE handling with conflicted entries
t6428: new test for SKIP_WORKTREE handling and conflicts
merge-ort: support subtree shifting
merge-ort: let renormalization change modify/delete into clean delete
merge-ort: have ll_merge() use a special attr_index for renormalization
merge-ort: add a special minimal index just for renormalization
merge-ort: use STABLE_QSORT instead of QSORT where required
diff --git a/merge-ort.c b/merge-ort.c
index 028d712..d1f4cf8 100644
--- a/merge-ort.c
+++ b/merge-ort.c
@@ -18,6 +18,7 @@
#include "merge-ort.h"
#include "alloc.h"
+#include "attr.h"
#include "blob.h"
#include "cache-tree.h"
#include "commit.h"
@@ -25,6 +26,7 @@
#include "diff.h"
#include "diffcore.h"
#include "dir.h"
+#include "entry.h"
#include "ll-merge.h"
#include "object-store.h"
#include "revision.h"
@@ -221,6 +223,16 @@ struct merge_options_internal {
struct rename_info renames;
/*
+ * attr_index: hacky minimal index used for renormalization
+ *
+ * renormalization code _requires_ an index, though it only needs to
+ * find a .gitattributes file within the index. So, when
+ * renormalization is important, we create a special index with just
+ * that one file.
+ */
+ struct index_state attr_index;
+
+ /*
* current_dir_name, toplevel_dir: temporary vars
*
* These are used in collect_merge_info_callback(), and will set the
@@ -399,6 +411,9 @@ static void clear_or_reinit_internal_opts(struct merge_options_internal *opti,
string_list_clear(&opti->paths_to_free, 0);
opti->paths_to_free.strdup_strings = 0;
+ if (opti->attr_index.cache_nr) /* true iff opt->renormalize */
+ discard_index(&opti->attr_index);
+
/* Free memory used by various renames maps */
for (i = MERGE_SIDE1; i <= MERGE_SIDE2; ++i) {
strintmap_func(&renames->dirs_removed[i]);
@@ -1187,6 +1202,63 @@ static int merge_submodule(struct merge_options *opt,
return 0;
}
+static void initialize_attr_index(struct merge_options *opt)
+{
+ /*
+ * The renormalize_buffer() functions require attributes, and
+ * annoyingly those can only be read from the working tree or from
+ * an index_state. merge-ort doesn't have an index_state, so we
+ * generate a fake one containing only attribute information.
+ */
+ struct merged_info *mi;
+ struct index_state *attr_index = &opt->priv->attr_index;
+ struct cache_entry *ce;
+
+ attr_index->initialized = 1;
+
+ if (!opt->renormalize)
+ return;
+
+ mi = strmap_get(&opt->priv->paths, GITATTRIBUTES_FILE);
+ if (!mi)
+ return;
+
+ if (mi->clean) {
+ int len = strlen(GITATTRIBUTES_FILE);
+ ce = make_empty_cache_entry(attr_index, len);
+ ce->ce_mode = create_ce_mode(mi->result.mode);
+ ce->ce_flags = create_ce_flags(0);
+ ce->ce_namelen = len;
+ oidcpy(&ce->oid, &mi->result.oid);
+ memcpy(ce->name, GITATTRIBUTES_FILE, len);
+ add_index_entry(attr_index, ce,
+ ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE);
+ get_stream_filter(attr_index, GITATTRIBUTES_FILE, &ce->oid);
+ } else {
+ int stage, len;
+ struct conflict_info *ci;
+
+ ASSIGN_AND_VERIFY_CI(ci, mi);
+ for (stage = 0; stage < 3; stage++) {
+ unsigned stage_mask = (1 << stage);
+
+ if (!(ci->filemask & stage_mask))
+ continue;
+ len = strlen(GITATTRIBUTES_FILE);
+ ce = make_empty_cache_entry(attr_index, len);
+ ce->ce_mode = create_ce_mode(ci->stages[stage].mode);
+ ce->ce_flags = create_ce_flags(stage);
+ ce->ce_namelen = len;
+ oidcpy(&ce->oid, &ci->stages[stage].oid);
+ memcpy(ce->name, GITATTRIBUTES_FILE, len);
+ add_index_entry(attr_index, ce,
+ ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE);
+ get_stream_filter(attr_index, GITATTRIBUTES_FILE,
+ &ce->oid);
+ }
+ }
+}
+
static int merge_3way(struct merge_options *opt,
const char *path,
const struct object_id *o,
@@ -1201,6 +1273,9 @@ static int merge_3way(struct merge_options *opt,
char *base, *name1, *name2;
int merge_status;
+ if (!opt->priv->attr_index.initialized)
+ initialize_attr_index(opt);
+
ll_opts.renormalize = opt->renormalize;
ll_opts.extra_marker_size = extra_marker_size;
ll_opts.xdl_opts = opt->xdl_opts;
@@ -1239,7 +1314,7 @@ static int merge_3way(struct merge_options *opt,
merge_status = ll_merge(result_buf, path, &orig, base,
&src1, name1, &src2, name2,
- opt->repo->index, &ll_opts);
+ &opt->priv->attr_index, &ll_opts);
free(base);
free(name1);
@@ -1562,18 +1637,7 @@ static void get_provisional_directory_renames(struct merge_options *opt,
"no destination getting a majority of the "
"files."),
source_dir);
- /*
- * We should mark this as unclean IF something attempts
- * to use this rename. We do not yet have the logic
- * in place to detect if this directory rename is being
- * used, and optimizations that reduce the number of
- * renames cause this to falsely trigger. For now,
- * just disable it, causing t6423 testcase 2a to break.
- * We'll later fix the detection, and when we do we
- * will re-enable setting *clean to 0 (and thereby fix
- * t6423 testcase 2a).
- */
- /* *clean = 0; */
+ *clean = 0;
} else {
strmap_put(&renames->dir_renames[side],
source_dir, (void*)best);
@@ -2404,7 +2468,7 @@ static int detect_and_process_renames(struct merge_options *opt,
clean &= collect_renames(opt, &combined, MERGE_SIDE2,
&renames->dir_renames[1],
&renames->dir_renames[2]);
- QSORT(combined.queue, combined.nr, compare_pairs);
+ STABLE_QSORT(combined.queue, combined.nr, compare_pairs);
trace2_region_leave("merge", "directory renames", opt->repo);
trace2_region_enter("merge", "process renames", opt->repo);
@@ -2474,6 +2538,61 @@ static int string_list_df_name_compare(const char *one, const char *two)
return onelen - twolen;
}
+static int read_oid_strbuf(struct merge_options *opt,
+ const struct object_id *oid,
+ struct strbuf *dst)
+{
+ void *buf;
+ enum object_type type;
+ unsigned long size;
+ buf = read_object_file(oid, &type, &size);
+ if (!buf)
+ return err(opt, _("cannot read object %s"), oid_to_hex(oid));
+ if (type != OBJ_BLOB) {
+ free(buf);
+ return err(opt, _("object %s is not a blob"), oid_to_hex(oid));
+ }
+ strbuf_attach(dst, buf, size, size + 1);
+ return 0;
+}
+
+static int blob_unchanged(struct merge_options *opt,
+ const struct version_info *base,
+ const struct version_info *side,
+ const char *path)
+{
+ struct strbuf basebuf = STRBUF_INIT;
+ struct strbuf sidebuf = STRBUF_INIT;
+ int ret = 0; /* assume changed for safety */
+ const struct index_state *idx = &opt->priv->attr_index;
+
+ if (!idx->initialized)
+ initialize_attr_index(opt);
+
+ if (base->mode != side->mode)
+ return 0;
+ if (oideq(&base->oid, &side->oid))
+ return 1;
+
+ if (read_oid_strbuf(opt, &base->oid, &basebuf) ||
+ read_oid_strbuf(opt, &side->oid, &sidebuf))
+ goto error_return;
+ /*
+ * Note: binary | is used so that both renormalizations are
+ * performed. Comparison can be skipped if both files are
+ * unchanged since their sha1s have already been compared.
+ */
+ if (renormalize_buffer(idx, path, basebuf.buf, basebuf.len, &basebuf) |
+ renormalize_buffer(idx, path, sidebuf.buf, sidebuf.len, &sidebuf))
+ ret = (basebuf.len == sidebuf.len &&
+ !memcmp(basebuf.buf, sidebuf.buf, basebuf.len));
+
+error_return:
+ strbuf_release(&basebuf);
+ strbuf_release(&sidebuf);
+ return ret;
+}
+
struct directory_versions {
/*
* versions: list of (basename -> version_info)
@@ -2549,6 +2668,7 @@ static void write_tree(struct object_id *result_oid,
*/
relevant_entries.items = versions->items + offset;
relevant_entries.nr = versions->nr - offset;
+ /* No need for STABLE_QSORT -- filenames must be unique */
QSORT(relevant_entries.items, relevant_entries.nr, tree_entry_order);
/* Pre-allocate some space in buf */
@@ -3060,8 +3180,13 @@ static void process_entry(struct merge_options *opt,
modify_branch = (side == 1) ? opt->branch1 : opt->branch2;
delete_branch = (side == 1) ? opt->branch2 : opt->branch1;
- if (ci->path_conflict &&
- oideq(&ci->stages[0].oid, &ci->stages[side].oid)) {
+ if (opt->renormalize &&
+ blob_unchanged(opt, &ci->stages[0], &ci->stages[side],
+ path)) {
+ ci->merged.is_null = 1;
+ ci->merged.clean = 1;
+ } else if (ci->path_conflict &&
+ oideq(&ci->stages[0].oid, &ci->stages[side].oid)) {
/*
* This came from a rename/delete; no action to take,
* but avoid printing "modify/delete" conflict notice
@@ -3233,23 +3358,27 @@ static int checkout(struct merge_options *opt,
return ret;
}
-static int record_conflicted_index_entries(struct merge_options *opt,
- struct index_state *index,
- struct strmap *paths,
- struct strmap *conflicted)
+static int record_conflicted_index_entries(struct merge_options *opt)
{
struct hashmap_iter iter;
struct strmap_entry *e;
+ struct index_state *index = opt->repo->index;
+ struct checkout state = CHECKOUT_INIT;
int errs = 0;
int original_cache_nr;
- if (strmap_empty(conflicted))
+ if (strmap_empty(&opt->priv->conflicted))
return 0;
+ /* If any entries have skip_worktree set, we'll have to check 'em out */
+ state.force = 1;
+ state.quiet = 1;
+ state.refresh_cache = 1;
+ state.istate = index;
original_cache_nr = index->cache_nr;
/* Put every entry from paths into plist, then sort */
- strmap_for_each_entry(conflicted, &iter, e) {
+ strmap_for_each_entry(&opt->priv->conflicted, &iter, e) {
const char *path = e->key;
struct conflict_info *ci = e->value;
int pos;
@@ -3290,9 +3419,23 @@ static int record_conflicted_index_entries(struct merge_options *opt,
* the higher order stages. Thus, we need override
* the CE_SKIP_WORKTREE bit and manually write those
* files to the working disk here.
- *
- * TODO: Implement this CE_SKIP_WORKTREE fixup.
*/
+ if (ce_skip_worktree(ce)) {
+ struct stat st;
+
+ if (!lstat(path, &st)) {
+ char *new_name = unique_path(&opt->priv->paths,
+ path,
+ "cruft");
+
+ path_msg(opt, path, 1,
+ _("Note: %s not up to date and in way of checking out conflicted version; old copy renamed to %s"),
+ path, new_name);
+ errs |= rename(path, new_name);
+ free(new_name);
+ }
+ errs |= checkout_entry(ce, &state, NULL, NULL);
+ }
/*
* Mark this cache entry for removal and instead add
@@ -3324,6 +3467,11 @@ static int record_conflicted_index_entries(struct merge_options *opt,
* entries we added to the end into their right locations.
*/
remove_marked_cache_entries(index, 1);
+ /*
+ * No need for STABLE_QSORT -- cmp_cache_name_compare sorts primarily
+ * on filename and secondarily on stage, and (name, stage #) are a
+ * unique tuple.
+ */
QSORT(index->cache, index->cache_nr, cmp_cache_name_compare);
return errs;
@@ -3337,7 +3485,8 @@ void merge_switch_to_result(struct merge_options *opt,
{
assert(opt->priv == NULL);
if (result->clean >= 0 && update_worktree_and_index) {
- struct merge_options_internal *opti = result->priv;
+ const char *filename;
+ FILE *fp;
trace2_region_enter("merge", "checkout", opt->repo);
if (checkout(opt, head, result->tree)) {
@@ -3348,14 +3497,22 @@ void merge_switch_to_result(struct merge_options *opt,
trace2_region_leave("merge", "checkout", opt->repo);
trace2_region_enter("merge", "record_conflicted", opt->repo);
- if (record_conflicted_index_entries(opt, opt->repo->index,
- &opti->paths,
- &opti->conflicted)) {
+ opt->priv = result->priv;
+ if (record_conflicted_index_entries(opt)) {
/* failure to function */
+ opt->priv = NULL;
result->clean = -1;
return;
}
+ opt->priv = NULL;
trace2_region_leave("merge", "record_conflicted", opt->repo);
+
+ trace2_region_enter("merge", "write_auto_merge", opt->repo);
+ filename = git_path_auto_merge(opt->repo);
+ fp = xfopen(filename, "w");
+ fprintf(fp, "%s\n", oid_to_hex(&result->tree->object.oid));
+ fclose(fp);
+ trace2_region_leave("merge", "write_auto_merge", opt->repo);
}
if (display_update_msgs) {
@@ -3400,6 +3557,8 @@ void merge_finalize(struct merge_options *opt,
{
struct merge_options_internal *opti = result->priv;
+ if (opt->renormalize)
+ git_attr_set_direction(GIT_ATTR_CHECKIN);
assert(opt->priv == NULL);
clear_or_reinit_internal_opts(opti, 0);
@@ -3408,6 +3567,23 @@ void merge_finalize(struct merge_options *opt,
/*** Function Grouping: helper functions for merge_incore_*() ***/
+static struct tree *shift_tree_object(struct repository *repo,
+ struct tree *one, struct tree *two,
+ const char *subtree_shift)
+{
+ struct object_id shifted;
+
+ if (!*subtree_shift) {
+ shift_tree(repo, &one->object.oid, &two->object.oid, &shifted, 0);
+ } else {
+ shift_tree_by(repo, &one->object.oid, &two->object.oid, &shifted,
+ subtree_shift);
+ }
+ if (oideq(&two->object.oid, &shifted))
+ return two;
+ return lookup_tree(repo, &shifted);
+}
+
static inline void set_commit_tree(struct commit *c, struct tree *t)
{
c->maybe_tree = t;
@@ -3475,6 +3651,10 @@ static void merge_start(struct merge_options *opt, struct merge_result *result)
/* Default to histogram diff. Actually, just hardcode it...for now. */
opt->xdl_opts = DIFF_WITH_ALG(opt, HISTOGRAM_DIFF);
+ /* Handle attr direction stuff for renormalization */
+ if (opt->renormalize)
+ git_attr_set_direction(GIT_ATTR_CHECKOUT);
+
/* Initialization of opt->priv, our internal merge data */
trace2_region_enter("merge", "allocate/init", opt->repo);
if (opt->priv) {
@@ -3533,6 +3713,13 @@ static void merge_ort_nonrecursive_internal(struct merge_options *opt,
{
struct object_id working_tree_oid;
+ if (opt->subtree_shift) {
+ side2 = shift_tree_object(opt->repo, side1, side2,
+ opt->subtree_shift);
+ merge_base = shift_tree_object(opt->repo, side1, merge_base,
+ opt->subtree_shift);
+ }
+
trace2_region_enter("merge", "collect_merge_info", opt->repo);
if (collect_merge_info(opt, merge_base, side1, side2) != 0) {
/*
