blob: 931b91438cf1bb5abaeb98fdd0b3292af66e5bd7 [file] [log] [blame]
/*
* "Ostensibly Recursive's Twin" merge strategy, or "ort" for short. Meant
* as a drop-in replacement for the "recursive" merge strategy, allowing one
* to replace
*
* git merge [-s recursive]
*
* with
*
* git merge -s ort
*
* Note: git's parser allows the space between '-s' and its argument to be
* missing. (Should I have backronymed "ham", "alsa", "kip", "nap, "alvo",
* "cale", "peedy", or "ins" instead of "ort"?)
*/
#include "cache.h"
#include "merge-ort.h"
#include "alloc.h"
#include "blob.h"
#include "cache-tree.h"
#include "commit.h"
#include "commit-reach.h"
#include "diff.h"
#include "diffcore.h"
#include "dir.h"
#include "ll-merge.h"
#include "object-store.h"
#include "revision.h"
#include "strmap.h"
#include "submodule.h"
#include "tree.h"
#include "unpack-trees.h"
#include "xdiff-interface.h"
/*
* We have many arrays of size 3. Whenever we have such an array, the
* indices refer to one of the sides of the three-way merge. This is so
* pervasive that the constants 0, 1, and 2 are used in many places in the
* code (especially in arithmetic operations to find the other side's index
* or to compute a relevant mask), but sometimes these enum names are used
* to aid code clarity.
*
* See also 'filemask' and 'dirmask' in struct conflict_info; the "ith side"
* referred to there is one of these three sides.
*/
enum merge_side {
MERGE_BASE = 0,
MERGE_SIDE1 = 1,
MERGE_SIDE2 = 2
};
struct rename_info {
/*
* All variables that are arrays of size 3 correspond to data tracked
* for the sides in enum merge_side. Index 0 is almost always unused
* because we often only need to track information for MERGE_SIDE1 and
* MERGE_SIDE2 (MERGE_BASE can't have rename information since renames
* are determined relative to what changed since the MERGE_BASE).
*/
/*
* pairs: pairing of filenames from diffcore_rename()
*/
struct diff_queue_struct pairs[3];
/*
* dirs_removed: directories removed on a given side of history.
*/
struct strset dirs_removed[3];
/*
* dir_rename_count: tracking where parts of a directory were renamed to
*
* When files in a directory are renamed, they may not all go to the
* same location. Each strmap here tracks:
* old_dir => {new_dir => int}
* That is, dir_rename_count[side] is a strmap to a strintmap.
*/
struct strmap dir_rename_count[3];
/*
* dir_renames: computed directory renames
*
* This is a map of old_dir => new_dir and is derived in part from
* dir_rename_count.
*/
struct strmap dir_renames[3];
/*
* needed_limit: value needed for inexact rename detection to run
*
* If the current rename limit wasn't high enough for inexact
* rename detection to run, this records the limit needed. Otherwise,
* this value remains 0.
*/
int needed_limit;
};
struct merge_options_internal {
/*
* paths: primary data structure in all of merge ort.
*
* The keys of paths:
* * are full relative paths from the toplevel of the repository
* (e.g. "drivers/firmware/raspberrypi.c").
* * store all relevant paths in the repo, both directories and
* files (e.g. drivers, drivers/firmware would also be included)
* * these keys serve to intern all the path strings, which allows
* us to do pointer comparison on directory names instead of
* strcmp; we just have to be careful to use the interned strings.
* (Technically paths_to_free may track some strings that were
* removed from froms paths.)
*
* The values of paths:
* * either a pointer to a merged_info, or a conflict_info struct
* * merged_info contains all relevant information for a
* non-conflicted entry.
* * conflict_info contains a merged_info, plus any additional
* information about a conflict such as the higher orders stages
* involved and the names of the paths those came from (handy
* once renames get involved).
* * a path may start "conflicted" (i.e. point to a conflict_info)
* and then a later step (e.g. three-way content merge) determines
* it can be cleanly merged, at which point it'll be marked clean
* and the algorithm will ignore any data outside the contained
* merged_info for that entry
* * If an entry remains conflicted, the merged_info portion of a
* conflict_info will later be filled with whatever version of
* the file should be placed in the working directory (e.g. an
* as-merged-as-possible variation that contains conflict markers).
*/
struct strmap paths;
/*
* conflicted: a subset of keys->values from "paths"
*
* conflicted is basically an optimization between process_entries()
* and record_conflicted_index_entries(); the latter could loop over
* ALL the entries in paths AGAIN and look for the ones that are
* still conflicted, but since process_entries() has to loop over
* all of them, it saves the ones it couldn't resolve in this strmap
* so that record_conflicted_index_entries() can iterate just the
* relevant entries.
*/
struct strmap conflicted;
/*
* paths_to_free: additional list of strings to free
*
* If keys are removed from "paths", they are added to paths_to_free
* to ensure they are later freed. We avoid free'ing immediately since
* other places (e.g. conflict_info.pathnames[]) may still be
* referencing these paths.
*/
struct string_list paths_to_free;
/*
* output: special messages and conflict notices for various paths
*
* This is a map of pathnames (a subset of the keys in "paths" above)
* to strbufs. It gathers various warning/conflict/notice messages
* for later processing.
*/
struct strmap output;
/*
* renames: various data relating to rename detection
*/
struct rename_info renames;
/*
* current_dir_name, toplevel_dir: temporary vars
*
* These are used in collect_merge_info_callback(), and will set the
* various merged_info.directory_name for the various paths we get;
* see documentation for that variable and the requirements placed on
* that field.
*/
const char *current_dir_name;
const char *toplevel_dir;
/* call_depth: recursion level counter for merging merge bases */
int call_depth;
};
struct version_info {
struct object_id oid;
unsigned short mode;
};
struct merged_info {
/* if is_null, ignore result. otherwise result has oid & mode */
struct version_info result;
unsigned is_null:1;
/*
* clean: whether the path in question is cleanly merged.
*
* see conflict_info.merged for more details.
*/
unsigned clean:1;
/*
* basename_offset: offset of basename of path.
*
* perf optimization to avoid recomputing offset of final '/'
* character in pathname (0 if no '/' in pathname).
*/
size_t basename_offset;
/*
* directory_name: containing directory name.
*
* Note that we assume directory_name is constructed such that
* strcmp(dir1_name, dir2_name) == 0 iff dir1_name == dir2_name,
* i.e. string equality is equivalent to pointer equality. For this
* to hold, we have to be careful setting directory_name.
*/
const char *directory_name;
};
struct conflict_info {
/*
* merged: the version of the path that will be written to working tree
*
* WARNING: It is critical to check merged.clean and ensure it is 0
* before reading any conflict_info fields outside of merged.
* Allocated merge_info structs will always have clean set to 1.
* Allocated conflict_info structs will have merged.clean set to 0
* initially. The merged.clean field is how we know if it is safe
* to access other parts of conflict_info besides merged; if a
* conflict_info's merged.clean is changed to 1, the rest of the
* algorithm is not allowed to look at anything outside of the
* merged member anymore.
*/
struct merged_info merged;
/* oids & modes from each of the three trees for this path */
struct version_info stages[3];
/* pathnames for each stage; may differ due to rename detection */
const char *pathnames[3];
/* Whether this path is/was involved in a directory/file conflict */
unsigned df_conflict:1;
/*
* Whether this path is/was involved in a non-content conflict other
* than a directory/file conflict (e.g. rename/rename, rename/delete,
* file location based on possible directory rename).
*/
unsigned path_conflict:1;
/*
* For filemask and dirmask, the ith bit corresponds to whether the
* ith entry is a file (filemask) or a directory (dirmask). Thus,
* filemask & dirmask is always zero, and filemask | dirmask is at
* most 7 but can be less when a path does not appear as either a
* file or a directory on at least one side of history.
*
* Note that these masks are related to enum merge_side, as the ith
* entry corresponds to side i.
*
* These values come from a traverse_trees() call; more info may be
* found looking at tree-walk.h's struct traverse_info,
* particularly the documentation above the "fn" member (note that
* filemask = mask & ~dirmask from that documentation).
*/
unsigned filemask:3;
unsigned dirmask:3;
/*
* Optimization to track which stages match, to avoid the need to
* recompute it in multiple steps. Either 0 or at least 2 bits are
* set; if at least 2 bits are set, their corresponding stages match.
*/
unsigned match_mask:3;
};
/*** Function Grouping: various utility functions ***/
/*
* For the next three macros, see warning for conflict_info.merged.
*
* In each of the below, mi is a struct merged_info*, and ci was defined
* as a struct conflict_info* (but we need to verify ci isn't actually
* pointed at a struct merged_info*).
*
* INITIALIZE_CI: Assign ci to mi but only if it's safe; set to NULL otherwise.
* VERIFY_CI: Ensure that something we assigned to a conflict_info* is one.
* ASSIGN_AND_VERIFY_CI: Similar to VERIFY_CI but do assignment first.
*/
#define INITIALIZE_CI(ci, mi) do { \
(ci) = (!(mi) || (mi)->clean) ? NULL : (struct conflict_info *)(mi); \
} while (0)
#define VERIFY_CI(ci) assert(ci && !ci->merged.clean);
#define ASSIGN_AND_VERIFY_CI(ci, mi) do { \
(ci) = (struct conflict_info *)(mi); \
assert((ci) && !(mi)->clean); \
} while (0)
static void free_strmap_strings(struct strmap *map)
{
struct hashmap_iter iter;
struct strmap_entry *entry;
strmap_for_each_entry(map, &iter, entry) {
free((char*)entry->key);
}
}
static void clear_or_reinit_internal_opts(struct merge_options_internal *opti,
int reinitialize)
{
struct rename_info *renames = &opti->renames;
int i;
void (*strmap_func)(struct strmap *, int) =
reinitialize ? strmap_partial_clear : strmap_clear;
void (*strset_func)(struct strset *) =
reinitialize ? strset_partial_clear : strset_clear;
/*
* We marked opti->paths with strdup_strings = 0, so that we
* wouldn't have to make another copy of the fullpath created by
* make_traverse_path from setup_path_info(). But, now that we've
* used it and have no other references to these strings, it is time
* to deallocate them.
*/
free_strmap_strings(&opti->paths);
strmap_func(&opti->paths, 1);
/*
* All keys and values in opti->conflicted are a subset of those in
* opti->paths. We don't want to deallocate anything twice, so we
* don't free the keys and we pass 0 for free_values.
*/
strmap_func(&opti->conflicted, 0);
/*
* opti->paths_to_free is similar to opti->paths; we created it with
* strdup_strings = 0 to avoid making _another_ copy of the fullpath
* but now that we've used it and have no other references to these
* strings, it is time to deallocate them. We do so by temporarily
* setting strdup_strings to 1.
*/
opti->paths_to_free.strdup_strings = 1;
string_list_clear(&opti->paths_to_free, 0);
opti->paths_to_free.strdup_strings = 0;
/* Free memory used by various renames maps */
for (i = MERGE_SIDE1; i <= MERGE_SIDE2; ++i) {
struct hashmap_iter iter;
struct strmap_entry *entry;
strset_func(&renames->dirs_removed[i]);
strmap_for_each_entry(&renames->dir_rename_count[i],
&iter, entry) {
struct strintmap *counts = entry->value;
strintmap_clear(counts);
}
strmap_func(&renames->dir_rename_count[i], 1);
strmap_func(&renames->dir_renames[i], 0);
}
if (!reinitialize) {
struct hashmap_iter iter;
struct strmap_entry *e;
/* Release and free each strbuf found in output */
strmap_for_each_entry(&opti->output, &iter, e) {
struct strbuf *sb = e->value;
strbuf_release(sb);
/*
* While strictly speaking we don't need to free(sb)
* here because we could pass free_values=1 when
* calling strmap_clear() on opti->output, that would
* require strmap_clear to do another
* strmap_for_each_entry() loop, so we just free it
* while we're iterating anyway.
*/
free(sb);
}
strmap_clear(&opti->output, 0);
}
}
static int err(struct merge_options *opt, const char *err, ...)
{
va_list params;
struct strbuf sb = STRBUF_INIT;
strbuf_addstr(&sb, "error: ");
va_start(params, err);
strbuf_vaddf(&sb, err, params);
va_end(params);
error("%s", sb.buf);
strbuf_release(&sb);
return -1;
}
static void format_commit(struct strbuf *sb,
int indent,
struct commit *commit)
{
struct merge_remote_desc *desc;
struct pretty_print_context ctx = {0};
ctx.abbrev = DEFAULT_ABBREV;
strbuf_addchars(sb, ' ', indent);
desc = merge_remote_util(commit);
if (desc) {
strbuf_addf(sb, "virtual %s\n", desc->name);
return;
}
format_commit_message(commit, "%h %s", sb, &ctx);
strbuf_addch(sb, '\n');
}
__attribute__((format (printf, 4, 5)))
static void path_msg(struct merge_options *opt,
const char *path,
int omittable_hint, /* skippable under --remerge-diff */
const char *fmt, ...)
{
va_list ap;
struct strbuf *sb = strmap_get(&opt->priv->output, path);
if (!sb) {
sb = xmalloc(sizeof(*sb));
strbuf_init(sb, 0);
strmap_put(&opt->priv->output, path, sb);
}
va_start(ap, fmt);
strbuf_vaddf(sb, fmt, ap);
va_end(ap);
strbuf_addch(sb, '\n');
}
/* add a string to a strbuf, but converting "/" to "_" */
static void add_flattened_path(struct strbuf *out, const char *s)
{
size_t i = out->len;
strbuf_addstr(out, s);
for (; i < out->len; i++)
if (out->buf[i] == '/')
out->buf[i] = '_';
}
static char *unique_path(struct strmap *existing_paths,
const char *path,
const char *branch)
{
struct strbuf newpath = STRBUF_INIT;
int suffix = 0;
size_t base_len;
strbuf_addf(&newpath, "%s~", path);
add_flattened_path(&newpath, branch);
base_len = newpath.len;
while (strmap_contains(existing_paths, newpath.buf)) {
strbuf_setlen(&newpath, base_len);
strbuf_addf(&newpath, "_%d", suffix++);
}
return strbuf_detach(&newpath, NULL);
}
/*** Function Grouping: functions related to collect_merge_info() ***/
static void setup_path_info(struct merge_options *opt,
struct string_list_item *result,
const char *current_dir_name,
int current_dir_name_len,
char *fullpath, /* we'll take over ownership */
struct name_entry *names,
struct name_entry *merged_version,
unsigned is_null, /* boolean */
unsigned df_conflict, /* boolean */
unsigned filemask,
unsigned dirmask,
int resolved /* boolean */)
{
/* result->util is void*, so mi is a convenience typed variable */
struct merged_info *mi;
assert(!is_null || resolved);
assert(!df_conflict || !resolved); /* df_conflict implies !resolved */
assert(resolved == (merged_version != NULL));
mi = xcalloc(1, resolved ? sizeof(struct merged_info) :
sizeof(struct conflict_info));
mi->directory_name = current_dir_name;
mi->basename_offset = current_dir_name_len;
mi->clean = !!resolved;
if (resolved) {
mi->result.mode = merged_version->mode;
oidcpy(&mi->result.oid, &merged_version->oid);
mi->is_null = !!is_null;
} else {
int i;
struct conflict_info *ci;
ASSIGN_AND_VERIFY_CI(ci, mi);
for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) {
ci->pathnames[i] = fullpath;
ci->stages[i].mode = names[i].mode;
oidcpy(&ci->stages[i].oid, &names[i].oid);
}
ci->filemask = filemask;
ci->dirmask = dirmask;
ci->df_conflict = !!df_conflict;
if (dirmask)
/*
* Assume is_null for now, but if we have entries
* under the directory then when it is complete in
* write_completed_directory() it'll update this.
* Also, for D/F conflicts, we have to handle the
* directory first, then clear this bit and process
* the file to see how it is handled -- that occurs
* near the top of process_entry().
*/
mi->is_null = 1;
}
strmap_put(&opt->priv->paths, fullpath, mi);
result->string = fullpath;
result->util = mi;
}
static void collect_rename_info(struct merge_options *opt,
struct name_entry *names,
const char *dirname,
const char *fullname,
unsigned filemask,
unsigned dirmask,
unsigned match_mask)
{
struct rename_info *renames = &opt->priv->renames;
/* Update dirs_removed, as needed */
if (dirmask == 1 || dirmask == 3 || dirmask == 5) {
/* absent_mask = 0x07 - dirmask; sides = absent_mask/2 */
unsigned sides = (0x07 - dirmask)/2;
if (sides & 1)
strset_add(&renames->dirs_removed[1], fullname);
if (sides & 2)
strset_add(&renames->dirs_removed[2], fullname);
}
}
static int collect_merge_info_callback(int n,
unsigned long mask,
unsigned long dirmask,
struct name_entry *names,
struct traverse_info *info)
{
/*
* n is 3. Always.
* common ancestor (mbase) has mask 1, and stored in index 0 of names
* head of side 1 (side1) has mask 2, and stored in index 1 of names
* head of side 2 (side2) has mask 4, and stored in index 2 of names
*/
struct merge_options *opt = info->data;
struct merge_options_internal *opti = opt->priv;
struct string_list_item pi; /* Path Info */
struct conflict_info *ci; /* typed alias to pi.util (which is void*) */
struct name_entry *p;
size_t len;
char *fullpath;
const char *dirname = opti->current_dir_name;
unsigned filemask = mask & ~dirmask;
unsigned match_mask = 0; /* will be updated below */
unsigned mbase_null = !(mask & 1);
unsigned side1_null = !(mask & 2);
unsigned side2_null = !(mask & 4);
unsigned side1_matches_mbase = (!side1_null && !mbase_null &&
names[0].mode == names[1].mode &&
oideq(&names[0].oid, &names[1].oid));
unsigned side2_matches_mbase = (!side2_null && !mbase_null &&
names[0].mode == names[2].mode &&
oideq(&names[0].oid, &names[2].oid));
unsigned sides_match = (!side1_null && !side2_null &&
names[1].mode == names[2].mode &&
oideq(&names[1].oid, &names[2].oid));
/*
* Note: When a path is a file on one side of history and a directory
* in another, we have a directory/file conflict. In such cases, if
* the conflict doesn't resolve from renames and deletions, then we
* always leave directories where they are and move files out of the
* way. Thus, while struct conflict_info has a df_conflict field to
* track such conflicts, we ignore that field for any directories at
* a path and only pay attention to it for files at the given path.
* The fact that we leave directories were they are also means that
* we do not need to worry about getting additional df_conflict
* information propagated from parent directories down to children
* (unlike, say traverse_trees_recursive() in unpack-trees.c, which
* sets a newinfo.df_conflicts field specifically to propagate it).
*/
unsigned df_conflict = (filemask != 0) && (dirmask != 0);
/* n = 3 is a fundamental assumption. */
if (n != 3)
BUG("Called collect_merge_info_callback wrong");
/*
* A bunch of sanity checks verifying that traverse_trees() calls
* us the way I expect. Could just remove these at some point,
* though maybe they are helpful to future code readers.
*/
assert(mbase_null == is_null_oid(&names[0].oid));
assert(side1_null == is_null_oid(&names[1].oid));
assert(side2_null == is_null_oid(&names[2].oid));
assert(!mbase_null || !side1_null || !side2_null);
assert(mask > 0 && mask < 8);
/* Determine match_mask */
if (side1_matches_mbase)
match_mask = (side2_matches_mbase ? 7 : 3);
else if (side2_matches_mbase)
match_mask = 5;
else if (sides_match)
match_mask = 6;
/*
* Get the name of the relevant filepath, which we'll pass to
* setup_path_info() for tracking.
*/
p = names;
while (!p->mode)
p++;
len = traverse_path_len(info, p->pathlen);
/* +1 in both of the following lines to include the NUL byte */
fullpath = xmalloc(len + 1);
make_traverse_path(fullpath, len + 1, info, p->path, p->pathlen);
/*
* If mbase, side1, and side2 all match, we can resolve early. Even
* if these are trees, there will be no renames or anything
* underneath.
*/
if (side1_matches_mbase && side2_matches_mbase) {
/* mbase, side1, & side2 all match; use mbase as resolution */
setup_path_info(opt, &pi, dirname, info->pathlen, fullpath,
names, names+0, mbase_null, 0,
filemask, dirmask, 1);
return mask;
}
/*
* Gather additional information used in rename detection.
*/
collect_rename_info(opt, names, dirname, fullpath,
filemask, dirmask, match_mask);
/*
* Record information about the path so we can resolve later in
* process_entries.
*/
setup_path_info(opt, &pi, dirname, info->pathlen, fullpath,
names, NULL, 0, df_conflict, filemask, dirmask, 0);
ci = pi.util;
VERIFY_CI(ci);
ci->match_mask = match_mask;
/* If dirmask, recurse into subdirectories */
if (dirmask) {
struct traverse_info newinfo;
struct tree_desc t[3];
void *buf[3] = {NULL, NULL, NULL};
const char *original_dir_name;
int i, ret;
ci->match_mask &= filemask;
newinfo = *info;
newinfo.prev = info;
newinfo.name = p->path;
newinfo.namelen = p->pathlen;
newinfo.pathlen = st_add3(newinfo.pathlen, p->pathlen, 1);
/*
* If this directory we are about to recurse into cared about
* its parent directory (the current directory) having a D/F
* conflict, then we'd propagate the masks in this way:
* newinfo.df_conflicts |= (mask & ~dirmask);
* But we don't worry about propagating D/F conflicts. (See
* comment near setting of local df_conflict variable near
* the beginning of this function).
*/
for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) {
if (i == 1 && side1_matches_mbase)
t[1] = t[0];
else if (i == 2 && side2_matches_mbase)
t[2] = t[0];
else if (i == 2 && sides_match)
t[2] = t[1];
else {
const struct object_id *oid = NULL;
if (dirmask & 1)
oid = &names[i].oid;
buf[i] = fill_tree_descriptor(opt->repo,
t + i, oid);
}
dirmask >>= 1;
}
original_dir_name = opti->current_dir_name;
opti->current_dir_name = pi.string;
ret = traverse_trees(NULL, 3, t, &newinfo);
opti->current_dir_name = original_dir_name;
for (i = MERGE_BASE; i <= MERGE_SIDE2; i++)
free(buf[i]);
if (ret < 0)
return -1;
}
return mask;
}
static int collect_merge_info(struct merge_options *opt,
struct tree *merge_base,
struct tree *side1,
struct tree *side2)
{
int ret;
struct tree_desc t[3];
struct traverse_info info;
opt->priv->toplevel_dir = "";
opt->priv->current_dir_name = opt->priv->toplevel_dir;
setup_traverse_info(&info, opt->priv->toplevel_dir);
info.fn = collect_merge_info_callback;
info.data = opt;
info.show_all_errors = 1;
parse_tree(merge_base);
parse_tree(side1);
parse_tree(side2);
init_tree_desc(t + 0, merge_base->buffer, merge_base->size);
init_tree_desc(t + 1, side1->buffer, side1->size);
init_tree_desc(t + 2, side2->buffer, side2->size);
trace2_region_enter("merge", "traverse_trees", opt->repo);
ret = traverse_trees(NULL, 3, t, &info);
trace2_region_leave("merge", "traverse_trees", opt->repo);
return ret;
}
/*** Function Grouping: functions related to threeway content merges ***/
static int find_first_merges(struct repository *repo,
const char *path,
struct commit *a,
struct commit *b,
struct object_array *result)
{
int i, j;
struct object_array merges = OBJECT_ARRAY_INIT;
struct commit *commit;
int contains_another;
char merged_revision[GIT_MAX_HEXSZ + 2];
const char *rev_args[] = { "rev-list", "--merges", "--ancestry-path",
"--all", merged_revision, NULL };
struct rev_info revs;
struct setup_revision_opt rev_opts;
memset(result, 0, sizeof(struct object_array));
memset(&rev_opts, 0, sizeof(rev_opts));
/* get all revisions that merge commit a */
xsnprintf(merged_revision, sizeof(merged_revision), "^%s",
oid_to_hex(&a->object.oid));
repo_init_revisions(repo, &revs, NULL);
rev_opts.submodule = path;
/* FIXME: can't handle linked worktrees in submodules yet */
revs.single_worktree = path != NULL;
setup_revisions(ARRAY_SIZE(rev_args)-1, rev_args, &revs, &rev_opts);
/* save all revisions from the above list that contain b */
if (prepare_revision_walk(&revs))
die("revision walk setup failed");
while ((commit = get_revision(&revs)) != NULL) {
struct object *o = &(commit->object);
if (in_merge_bases(b, commit))
add_object_array(o, NULL, &merges);
}
reset_revision_walk();
/* Now we've got all merges that contain a and b. Prune all
* merges that contain another found merge and save them in
* result.
*/
for (i = 0; i < merges.nr; i++) {
struct commit *m1 = (struct commit *) merges.objects[i].item;
contains_another = 0;
for (j = 0; j < merges.nr; j++) {
struct commit *m2 = (struct commit *) merges.objects[j].item;
if (i != j && in_merge_bases(m2, m1)) {
contains_another = 1;
break;
}
}
if (!contains_another)
add_object_array(merges.objects[i].item, NULL, result);
}
object_array_clear(&merges);
return result->nr;
}
static int merge_submodule(struct merge_options *opt,
const char *path,
const struct object_id *o,
const struct object_id *a,
const struct object_id *b,
struct object_id *result)
{
struct commit *commit_o, *commit_a, *commit_b;
int parent_count;
struct object_array merges;
struct strbuf sb = STRBUF_INIT;
int i;
int search = !opt->priv->call_depth;
/* store fallback answer in result in case we fail */
oidcpy(result, opt->priv->call_depth ? o : a);
/* we can not handle deletion conflicts */
if (is_null_oid(o))
return 0;
if (is_null_oid(a))
return 0;
if (is_null_oid(b))
return 0;
if (add_submodule_odb(path)) {
path_msg(opt, path, 0,
_("Failed to merge submodule %s (not checked out)"),
path);
return 0;
}
if (!(commit_o = lookup_commit_reference(opt->repo, o)) ||
!(commit_a = lookup_commit_reference(opt->repo, a)) ||
!(commit_b = lookup_commit_reference(opt->repo, b))) {
path_msg(opt, path, 0,
_("Failed to merge submodule %s (commits not present)"),
path);
return 0;
}
/* check whether both changes are forward */
if (!in_merge_bases(commit_o, commit_a) ||
!in_merge_bases(commit_o, commit_b)) {
path_msg(opt, path, 0,
_("Failed to merge submodule %s "
"(commits don't follow merge-base)"),
path);
return 0;
}
/* Case #1: a is contained in b or vice versa */
if (in_merge_bases(commit_a, commit_b)) {
oidcpy(result, b);
path_msg(opt, path, 1,
_("Note: Fast-forwarding submodule %s to %s"),
path, oid_to_hex(b));
return 1;
}
if (in_merge_bases(commit_b, commit_a)) {
oidcpy(result, a);
path_msg(opt, path, 1,
_("Note: Fast-forwarding submodule %s to %s"),
path, oid_to_hex(a));
return 1;
}
/*
* Case #2: There are one or more merges that contain a and b in
* the submodule. If there is only one, then present it as a
* suggestion to the user, but leave it marked unmerged so the
* user needs to confirm the resolution.
*/
/* Skip the search if makes no sense to the calling context. */
if (!search)
return 0;
/* find commit which merges them */
parent_count = find_first_merges(opt->repo, path, commit_a, commit_b,
&merges);
switch (parent_count) {
case 0:
path_msg(opt, path, 0, _("Failed to merge submodule %s"), path);
break;
case 1:
format_commit(&sb, 4,
(struct commit *)merges.objects[0].item);
path_msg(opt, path, 0,
_("Failed to merge submodule %s, but a possible merge "
"resolution exists:\n%s\n"),
path, sb.buf);
path_msg(opt, path, 1,
_("If this is correct simply add it to the index "
"for example\n"
"by using:\n\n"
" git update-index --cacheinfo 160000 %s \"%s\"\n\n"
"which will accept this suggestion.\n"),
oid_to_hex(&merges.objects[0].item->oid), path);
strbuf_release(&sb);
break;
default:
for (i = 0; i < merges.nr; i++)
format_commit(&sb, 4,
(struct commit *)merges.objects[i].item);
path_msg(opt, path, 0,
_("Failed to merge submodule %s, but multiple "
"possible merges exist:\n%s"), path, sb.buf);
strbuf_release(&sb);
}
object_array_clear(&merges);
return 0;
}
static int merge_3way(struct merge_options *opt,
const char *path,
const struct object_id *o,
const struct object_id *a,
const struct object_id *b,
const char *pathnames[3],
const int extra_marker_size,
mmbuffer_t *result_buf)
{
mmfile_t orig, src1, src2;
struct ll_merge_options ll_opts = {0};
char *base, *name1, *name2;
int merge_status;
ll_opts.renormalize = opt->renormalize;
ll_opts.extra_marker_size = extra_marker_size;
ll_opts.xdl_opts = opt->xdl_opts;
if (opt->priv->call_depth) {
ll_opts.virtual_ancestor = 1;
ll_opts.variant = 0;
} else {
switch (opt->recursive_variant) {
case MERGE_VARIANT_OURS:
ll_opts.variant = XDL_MERGE_FAVOR_OURS;
break;
case MERGE_VARIANT_THEIRS:
ll_opts.variant = XDL_MERGE_FAVOR_THEIRS;
break;
default:
ll_opts.variant = 0;
break;
}
}
assert(pathnames[0] && pathnames[1] && pathnames[2] && opt->ancestor);
if (pathnames[0] == pathnames[1] && pathnames[1] == pathnames[2]) {
base = mkpathdup("%s", opt->ancestor);
name1 = mkpathdup("%s", opt->branch1);
name2 = mkpathdup("%s", opt->branch2);
} else {
base = mkpathdup("%s:%s", opt->ancestor, pathnames[0]);
name1 = mkpathdup("%s:%s", opt->branch1, pathnames[1]);
name2 = mkpathdup("%s:%s", opt->branch2, pathnames[2]);
}
read_mmblob(&orig, o);
read_mmblob(&src1, a);
read_mmblob(&src2, b);
merge_status = ll_merge(result_buf, path, &orig, base,
&src1, name1, &src2, name2,
opt->repo->index, &ll_opts);
free(base);
free(name1);
free(name2);
free(orig.ptr);
free(src1.ptr);
free(src2.ptr);
return merge_status;
}
static int handle_content_merge(struct merge_options *opt,
const char *path,
const struct version_info *o,
const struct version_info *a,
const struct version_info *b,
const char *pathnames[3],
const int extra_marker_size,
struct version_info *result)
{
/*
* path is the target location where we want to put the file, and
* is used to determine any normalization rules in ll_merge.
*
* The normal case is that path and all entries in pathnames are
* identical, though renames can affect which path we got one of
* the three blobs to merge on various sides of history.
*
* extra_marker_size is the amount to extend conflict markers in
* ll_merge; this is neeed if we have content merges of content
* merges, which happens for example with rename/rename(2to1) and
* rename/add conflicts.
*/
unsigned clean = 1;
/*
* handle_content_merge() needs both files to be of the same type, i.e.
* both files OR both submodules OR both symlinks. Conflicting types
* needs to be handled elsewhere.
*/
assert((S_IFMT & a->mode) == (S_IFMT & b->mode));
/* Merge modes */
if (a->mode == b->mode || a->mode == o->mode)
result->mode = b->mode;
else {
/* must be the 100644/100755 case */
assert(S_ISREG(a->mode));
result->mode = a->mode;
clean = (b->mode == o->mode);
/*
* FIXME: If opt->priv->call_depth && !clean, then we really
* should not make result->mode match either a->mode or
* b->mode; that causes t6036 "check conflicting mode for
* regular file" to fail. It would be best to use some other
* mode, but we'll confuse all kinds of stuff if we use one
* where S_ISREG(result->mode) isn't true, and if we use
* something like 0100666, then tree-walk.c's calls to
* canon_mode() will just normalize that to 100644 for us and
* thus not solve anything.
*
* Figure out if there's some kind of way we can work around
* this...
*/
}
/*
* Trivial oid merge.
*
* Note: While one might assume that the next four lines would
* be unnecessary due to the fact that match_mask is often
* setup and already handled, renames don't always take care
* of that.
*/
if (oideq(&a->oid, &b->oid) || oideq(&a->oid, &o->oid))
oidcpy(&result->oid, &b->oid);
else if (oideq(&b->oid, &o->oid))
oidcpy(&result->oid, &a->oid);
/* Remaining rules depend on file vs. submodule vs. symlink. */
else if (S_ISREG(a->mode)) {
mmbuffer_t result_buf;
int ret = 0, merge_status;
int two_way;
/*
* If 'o' is different type, treat it as null so we do a
* two-way merge.
*/
two_way = ((S_IFMT & o->mode) != (S_IFMT & a->mode));
merge_status = merge_3way(opt, path,
two_way ? &null_oid : &o->oid,
&a->oid, &b->oid,
pathnames, extra_marker_size,
&result_buf);
if ((merge_status < 0) || !result_buf.ptr)
ret = err(opt, _("Failed to execute internal merge"));
if (!ret &&
write_object_file(result_buf.ptr, result_buf.size,
blob_type, &result->oid))
ret = err(opt, _("Unable to add %s to database"),
path);
free(result_buf.ptr);
if (ret)
return -1;
clean &= (merge_status == 0);
path_msg(opt, path, 1, _("Auto-merging %s"), path);
} else if (S_ISGITLINK(a->mode)) {
int two_way = ((S_IFMT & o->mode) != (S_IFMT & a->mode));
clean = merge_submodule(opt, pathnames[0],
two_way ? &null_oid : &o->oid,
&a->oid, &b->oid, &result->oid);
if (opt->priv->call_depth && two_way && !clean) {
result->mode = o->mode;
oidcpy(&result->oid, &o->oid);
}
} else if (S_ISLNK(a->mode)) {
if (opt->priv->call_depth) {
clean = 0;
result->mode = o->mode;
oidcpy(&result->oid, &o->oid);
} else {
switch (opt->recursive_variant) {
case MERGE_VARIANT_NORMAL:
clean = 0;
oidcpy(&result->oid, &a->oid);
break;
case MERGE_VARIANT_OURS:
oidcpy(&result->oid, &a->oid);
break;
case MERGE_VARIANT_THEIRS:
oidcpy(&result->oid, &b->oid);
break;
}
}
} else
BUG("unsupported object type in the tree: %06o for %s",
a->mode, path);
return clean;
}
/*** Function Grouping: functions related to detect_and_process_renames(), ***
*** which are split into directory and regular rename detection sections. ***/
/*** Function Grouping: functions related to directory rename detection ***/
struct collision_info {
struct string_list source_files;
unsigned reported_already:1;
};
/*
* Return a new string that replaces the beginning portion (which matches
* rename_info->key), with rename_info->util.new_dir. In perl-speak:
* new_path_name = (old_path =~ s/rename_info->key/rename_info->value/);
* NOTE:
* Caller must ensure that old_path starts with rename_info->key + '/'.
*/
static char *apply_dir_rename(struct strmap_entry *rename_info,
const char *old_path)
{
struct strbuf new_path = STRBUF_INIT;
const char *old_dir = rename_info->key;
const char *new_dir = rename_info->value;
int oldlen, newlen, new_dir_len;
oldlen = strlen(old_dir);
if (*new_dir == '\0')
/*
* If someone renamed/merged a subdirectory into the root
* directory (e.g. 'some/subdir' -> ''), then we want to
* avoid returning
* '' + '/filename'
* as the rename; we need to make old_path + oldlen advance
* past the '/' character.
*/
oldlen++;
new_dir_len = strlen(new_dir);
newlen = new_dir_len + (strlen(old_path) - oldlen) + 1;
strbuf_grow(&new_path, newlen);
strbuf_add(&new_path, new_dir, new_dir_len);
strbuf_addstr(&new_path, &old_path[oldlen]);
return strbuf_detach(&new_path, NULL);
}
static int path_in_way(struct strmap *paths, const char *path, unsigned side_mask)
{
struct merged_info *mi = strmap_get(paths, path);
struct conflict_info *ci;
if (!mi)
return 0;
INITIALIZE_CI(ci, mi);
return mi->clean || (side_mask & (ci->filemask | ci->dirmask));
}
/*
* See if there is a directory rename for path, and if there are any file
* level conflicts on the given side for the renamed location. If there is
* a rename and there are no conflicts, return the new name. Otherwise,
* return NULL.
*/
static char *handle_path_level_conflicts(struct merge_options *opt,
const char *path,
unsigned side_index,
struct strmap_entry *rename_info,
struct strmap *collisions)
{
char *new_path = NULL;
struct collision_info *c_info;
int clean = 1;
struct strbuf collision_paths = STRBUF_INIT;
/*
* entry has the mapping of old directory name to new directory name
* that we want to apply to path.
*/
new_path = apply_dir_rename(rename_info, path);
if (!new_path)
BUG("Failed to apply directory rename!");
/*
* The caller needs to have ensured that it has pre-populated
* collisions with all paths that map to new_path. Do a quick check
* to ensure that's the case.
*/
c_info = strmap_get(collisions, new_path);
if (c_info == NULL)
BUG("c_info is NULL");
/*
* Check for one-sided add/add/.../add conflicts, i.e.
* where implicit renames from the other side doing
* directory rename(s) can affect this side of history
* to put multiple paths into the same location. Warn
* and bail on directory renames for such paths.
*/
if (c_info->reported_already) {
clean = 0;
} else if (path_in_way(&opt->priv->paths, new_path, 1 << side_index)) {
c_info->reported_already = 1;
strbuf_add_separated_string_list(&collision_paths, ", ",
&c_info->source_files);
path_msg(opt, new_path, 0,
_("CONFLICT (implicit dir rename): Existing file/dir "
"at %s in the way of implicit directory rename(s) "
"putting the following path(s) there: %s."),
new_path, collision_paths.buf);
clean = 0;
} else if (c_info->source_files.nr > 1) {
c_info->reported_already = 1;
strbuf_add_separated_string_list(&collision_paths, ", ",
&c_info->source_files);
path_msg(opt, new_path, 0,
_("CONFLICT (implicit dir rename): Cannot map more "
"than one path to %s; implicit directory renames "
"tried to put these paths there: %s"),
new_path, collision_paths.buf);
clean = 0;
}
/* Free memory we no longer need */
strbuf_release(&collision_paths);
if (!clean && new_path) {
free(new_path);
return NULL;
}
return new_path;
}
static void dirname_munge(char *filename)
{
char *slash = strrchr(filename, '/');
if (!slash)
slash = filename;
*slash = '\0';
}
static void increment_count(struct strmap *dir_rename_count,
char *old_dir,
char *new_dir)
{
struct strintmap *counts;
struct strmap_entry *e;
/* Get the {new_dirs -> counts} mapping using old_dir */
e = strmap_get_entry(dir_rename_count, old_dir);
if (e) {
counts = e->value;
} else {
counts = xmalloc(sizeof(*counts));
strintmap_init_with_options(counts, 0, NULL, 1);
strmap_put(dir_rename_count, old_dir, counts);
}
/* Increment the count for new_dir */
strintmap_incr(counts, new_dir, 1);
}
static void update_dir_rename_counts(struct strmap *dir_rename_count,
struct strset *dirs_removed,
const char *oldname,
const char *newname)
{
char *old_dir = xstrdup(oldname);
char *new_dir = xstrdup(newname);
char new_dir_first_char = new_dir[0];
int first_time_in_loop = 1;
while (1) {
dirname_munge(old_dir);
dirname_munge(new_dir);
/*
* When renaming
* "a/b/c/d/e/foo.c" -> "a/b/some/thing/else/e/foo.c"
* then this suggests that both
* a/b/c/d/e/ => a/b/some/thing/else/e/
* a/b/c/d/ => a/b/some/thing/else/
* so we want to increment counters for both. We do NOT,
* however, also want to suggest that there was the following
* rename:
* a/b/c/ => a/b/some/thing/
* so we need to quit at that point.
*
* Note the when first_time_in_loop, we only strip off the
* basename, and we don't care if that's different.
*/
if (!first_time_in_loop) {
char *old_sub_dir = strchr(old_dir, '\0')+1;
char *new_sub_dir = strchr(new_dir, '\0')+1;
if (!*new_dir) {
/*
* Special case when renaming to root directory,
* i.e. when new_dir == "". In this case, we had
* something like
* a/b/subdir => subdir
* and so dirname_munge() sets things up so that
* old_dir = "a/b\0subdir\0"
* new_dir = "\0ubdir\0"
* We didn't have a '/' to overwrite a '\0' onto
* in new_dir, so we have to compare differently.
*/
if (new_dir_first_char != old_sub_dir[0] ||
strcmp(old_sub_dir+1, new_sub_dir))
break;
} else {
if (strcmp(old_sub_dir, new_sub_dir))
break;
}
}
if (strset_contains(dirs_removed, old_dir))
increment_count(dir_rename_count, old_dir, new_dir);
else
break;
/* If we hit toplevel directory ("") for old or new dir, quit */
if (!*old_dir || !*new_dir)
break;
first_time_in_loop = 0;
}
/* Free resources we don't need anymore */
free(old_dir);
free(new_dir);
}
static void compute_rename_counts(struct diff_queue_struct *pairs,
struct strmap *dir_rename_count,
struct strset *dirs_removed)
{
int i;
for (i = 0; i < pairs->nr; ++i) {
struct diff_filepair *pair = pairs->queue[i];
/* File not part of directory rename if it wasn't renamed */
if (pair->status != 'R')
continue;
/*
* Make dir_rename_count contain a map of a map:
* old_directory -> {new_directory -> count}
* In other words, for every pair look at the directories for
* the old filename and the new filename and count how many
* times that pairing occurs.
*/
update_dir_rename_counts(dir_rename_count, dirs_removed,
pair->one->path,
pair->two->path);
}
}
static void get_provisional_directory_renames(struct merge_options *opt,
unsigned side,
int *clean)
{
struct hashmap_iter iter;
struct strmap_entry *entry;
struct rename_info *renames = &opt->priv->renames;
compute_rename_counts(&renames->pairs[side],
&renames->dir_rename_count[side],
&renames->dirs_removed[side]);
/*
* Collapse
* dir_rename_count: old_directory -> {new_directory -> count}
* down to
* dir_renames: old_directory -> best_new_directory
* where best_new_directory is the one with the unique highest count.
*/
strmap_for_each_entry(&renames->dir_rename_count[side], &iter, entry) {
const char *source_dir = entry->key;
struct strintmap *counts = entry->value;
struct hashmap_iter count_iter;
struct strmap_entry *count_entry;
int max = 0;
int bad_max = 0;
const char *best = NULL;
strintmap_for_each_entry(counts, &count_iter, count_entry) {
const char *target_dir = count_entry->key;
intptr_t count = (intptr_t)count_entry->value;
if (count == max)
bad_max = max;
else if (count > max) {
max = count;
best = target_dir;
}
}
if (bad_max == max) {
path_msg(opt, source_dir, 0,
_("CONFLICT (directory rename split): "
"Unclear where to rename %s to; it was "
"renamed to multiple other directories, with "
"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; */
} else {
strmap_put(&renames->dir_renames[side],
source_dir, (void*)best);
}
}
}
static void handle_directory_level_conflicts(struct merge_options *opt)
{
struct hashmap_iter iter;
struct strmap_entry *entry;
struct string_list duplicated = STRING_LIST_INIT_NODUP;
struct rename_info *renames = &opt->priv->renames;
struct strmap *side1_dir_renames = &renames->dir_renames[MERGE_SIDE1];
struct strmap *side2_dir_renames = &renames->dir_renames[MERGE_SIDE2];
int i;
strmap_for_each_entry(side1_dir_renames, &iter, entry) {
if (strmap_contains(side2_dir_renames, entry->key))
string_list_append(&duplicated, entry->key);
}
for (i = 0; i < duplicated.nr; i++) {
strmap_remove(side1_dir_renames, duplicated.items[i].string, 0);
strmap_remove(side2_dir_renames, duplicated.items[i].string, 0);
}
string_list_clear(&duplicated, 0);
}
static struct strmap_entry *check_dir_renamed(const char *path,
struct strmap *dir_renames)
{
char *temp = xstrdup(path);
char *end;
struct strmap_entry *e = NULL;
while ((end = strrchr(temp, '/'))) {
*end = '\0';
e = strmap_get_entry(dir_renames, temp);
if (e)
break;
}
free(temp);
return e;
}
static void compute_collisions(struct strmap *collisions,
struct strmap *dir_renames,
struct diff_queue_struct *pairs)
{
int i;
strmap_init_with_options(collisions, NULL, 0);
if (strmap_empty(dir_renames))
return;
/*
* Multiple files can be mapped to the same path due to directory
* renames done by the other side of history. Since that other
* side of history could have merged multiple directories into one,
* if our side of history added the same file basename to each of
* those directories, then all N of them would get implicitly
* renamed by the directory rename detection into the same path,
* and we'd get an add/add/.../add conflict, and all those adds
* from *this* side of history. This is not representable in the
* index, and users aren't going to easily be able to make sense of
* it. So we need to provide a good warning about what's
* happening, and fall back to no-directory-rename detection
* behavior for those paths.
*
* See testcases 9e and all of section 5 from t6043 for examples.
*/
for (i = 0; i < pairs->nr; ++i) {
struct strmap_entry *rename_info;
struct collision_info *collision_info;
char *new_path;
struct diff_filepair *pair = pairs->queue[i];
if (pair->status != 'A' && pair->status != 'R')
continue;
rename_info = check_dir_renamed(pair->two->path, dir_renames);
if (!rename_info)
continue;
new_path = apply_dir_rename(rename_info, pair->two->path);
assert(new_path);
collision_info = strmap_get(collisions, new_path);
if (collision_info) {
free(new_path);
} else {
collision_info = xcalloc(1,
sizeof(struct collision_info));
string_list_init(&collision_info->source_files, 0);
strmap_put(collisions, new_path, collision_info);
}
string_list_insert(&collision_info->source_files,
pair->two->path);
}
}
static char *check_for_directory_rename(struct merge_options *opt,
const char *path,
unsigned side_index,
struct strmap *dir_renames,
struct strmap *dir_rename_exclusions,
struct strmap *collisions,
int *clean_merge)
{
char *new_path = NULL;
struct strmap_entry *rename_info;
struct strmap_entry *otherinfo = NULL;
const char *new_dir;
if (strmap_empty(dir_renames))
return new_path;
rename_info = check_dir_renamed(path, dir_renames);
if (!rename_info)
return new_path;
/* old_dir = rename_info->key; */
new_dir = rename_info->value;
/*
* This next part is a little weird. We do not want to do an
* implicit rename into a directory we renamed on our side, because
* that will result in a spurious rename/rename(1to2) conflict. An
* example:
* Base commit: dumbdir/afile, otherdir/bfile
* Side 1: smrtdir/afile, otherdir/bfile
* Side 2: dumbdir/afile, dumbdir/bfile
* Here, while working on Side 1, we could notice that otherdir was
* renamed/merged to dumbdir, and change the diff_filepair for
* otherdir/bfile into a rename into dumbdir/bfile. However, Side
* 2 will notice the rename from dumbdir to smrtdir, and do the
* transitive rename to move it from dumbdir/bfile to
* smrtdir/bfile. That gives us bfile in dumbdir vs being in
* smrtdir, a rename/rename(1to2) conflict. We really just want
* the file to end up in smrtdir. And the way to achieve that is
* to not let Side1 do the rename to dumbdir, since we know that is
* the source of one of our directory renames.
*
* That's why otherinfo and dir_rename_exclusions is here.
*
* As it turns out, this also prevents N-way transient rename
* confusion; See testcases 9c and 9d of t6043.
*/
otherinfo = strmap_get_entry(dir_rename_exclusions, new_dir);
if (otherinfo) {
path_msg(opt, rename_info->key, 1,
_("WARNING: Avoiding applying %s -> %s rename "
"to %s, because %s itself was renamed."),
rename_info->key, new_dir, path, new_dir);
return NULL;
}
new_path = handle_path_level_conflicts(opt, path, side_index,
rename_info, collisions);
*clean_merge &= (new_path != NULL);
return new_path;
}
static void apply_directory_rename_modifications(struct merge_options *opt,
struct diff_filepair *pair,
char *new_path)
{
/*
* The basic idea is to get the conflict_info from opt->priv->paths
* at old path, and insert it into new_path; basically just this:
* ci = strmap_get(&opt->priv->paths, old_path);
* strmap_remove(&opt->priv->paths, old_path, 0);
* strmap_put(&opt->priv->paths, new_path, ci);
* However, there are some factors complicating this:
* - opt->priv->paths may already have an entry at new_path
* - Each ci tracks its containing directory, so we need to
* update that
* - If another ci has the same containing directory, then
* the two char*'s MUST point to the same location. See the
* comment in struct merged_info. strcmp equality is not
* enough; we need pointer equality.
* - opt->priv->paths must hold the parent directories of any
* entries that are added. So, if this directory rename
* causes entirely new directories, we must recursively add
* parent directories.
* - For each parent directory added to opt->priv->paths, we
* also need to get its parent directory stored in its
* conflict_info->merged.directory_name with all the same
* requirements about pointer equality.
*/
struct string_list dirs_to_insert = STRING_LIST_INIT_NODUP;
struct conflict_info *ci, *new_ci;
struct strmap_entry *entry;
const char *branch_with_new_path, *branch_with_dir_rename;
const char *old_path = pair->two->path;
const char *parent_name;
const char *cur_path;
int i, len;
entry = strmap_get_entry(&opt->priv->paths, old_path);
old_path = entry->key;
ci = entry->value;
VERIFY_CI(ci);
/* Find parent directories missing from opt->priv->paths */
cur_path = new_path;
while (1) {
/* Find the parent directory of cur_path */
char *last_slash = strrchr(cur_path, '/');
if (last_slash) {
parent_name = xstrndup(cur_path, last_slash - cur_path);
} else {
parent_name = opt->priv->toplevel_dir;
break;
}
/* Look it up in opt->priv->paths */
entry = strmap_get_entry(&opt->priv->paths, parent_name);
if (entry) {
free((char*)parent_name);
parent_name = entry->key; /* reuse known pointer */
break;
}
/* Record this is one of the directories we need to insert */
string_list_append(&dirs_to_insert, parent_name);
cur_path = parent_name;
}
/* Traverse dirs_to_insert and insert them into opt->priv->paths */
for (i = dirs_to_insert.nr-1; i >= 0; --i) {
struct conflict_info *dir_ci;
char *cur_dir = dirs_to_insert.items[i].string;
dir_ci = xcalloc(1, sizeof(*dir_ci));
dir_ci->merged.directory_name = parent_name;
len = strlen(parent_name);
/* len+1 because of trailing '/' character */
dir_ci->merged.basename_offset = (len > 0 ? len+1 : len);
dir_ci->dirmask = ci->filemask;
strmap_put(&opt->priv->paths, cur_dir, dir_ci);
parent_name = cur_dir;
}
/*
* We are removing old_path from opt->priv->paths. old_path also will
* eventually need to be freed, but it may still be used by e.g.
* ci->pathnames. So, store it in another string-list for now.
*/
string_list_append(&opt->priv->paths_to_free, old_path);
assert(ci->filemask == 2 || ci->filemask == 4);
assert(ci->dirmask == 0);
strmap_remove(&opt->priv->paths, old_path, 0);
branch_with_new_path = (ci->filemask == 2) ? opt->branch1 : opt->branch2;
branch_with_dir_rename = (ci->filemask == 2) ? opt->branch2 : opt->branch1;
/* Now, finally update ci and stick it into opt->priv->paths */
ci->merged.directory_name = parent_name;
len = strlen(parent_name);
ci->merged.basename_offset = (len > 0 ? len+1 : len);
new_ci = strmap_get(&opt->priv->paths, new_path);
if (!new_ci) {
/* Place ci back into opt->priv->paths, but at new_path */
strmap_put(&opt->priv->paths, new_path, ci);
} else {
int index;
/* A few sanity checks */
VERIFY_CI(new_ci);
assert(ci->filemask == 2 || ci->filemask == 4);
assert((new_ci->filemask & ci->filemask) == 0);
assert(!new_ci->merged.clean);
/* Copy stuff from ci into new_ci */
new_ci->filemask |= ci->filemask;
if (new_ci->dirmask)
new_ci->df_conflict = 1;
index = (ci->filemask >> 1);
new_ci->pathnames[index] = ci->pathnames[index];
new_ci->stages[index].mode = ci->stages[index].mode;
oidcpy(&new_ci->stages[index].oid, &ci->stages[index].oid);
free(ci);
ci = new_ci;
}
if (opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_TRUE) {
/* Notify user of updated path */
if (pair->status == 'A')
path_msg(opt, new_path, 1,
_("Path updated: %s added in %s inside a "
"directory that was renamed in %s; moving "
"it to %s."),
old_path, branch_with_new_path,
branch_with_dir_rename, new_path);
else
path_msg(opt, new_path, 1,
_("Path updated: %s renamed to %s in %s, "
"inside a directory that was renamed in %s; "
"moving it to %s."),
pair->one->path, old_path, branch_with_new_path,
branch_with_dir_rename, new_path);
} else {
/*
* opt->detect_directory_renames has the value
* MERGE_DIRECTORY_RENAMES_CONFLICT, so mark these as conflicts.
*/
ci->path_conflict = 1;
if (pair->status == 'A')
path_msg(opt, new_path, 0,
_("CONFLICT (file location): %s added in %s "
"inside a directory that was renamed in %s, "
"suggesting it should perhaps be moved to "
"%s."),
old_path, branch_with_new_path,
branch_with_dir_rename, new_path);
else
path_msg(opt, new_path, 0,
_("CONFLICT (file location): %s renamed to %s "
"in %s, inside a directory that was renamed "
"in %s, suggesting it should perhaps be "
"moved to %s."),
pair->one->path, old_path, branch_with_new_path,
branch_with_dir_rename, new_path);
}
/*
* Finally, record the new location.
*/
pair->two->path = new_path;
}
/*** Function Grouping: functions related to regular rename detection ***/
static int process_renames(struct merge_options *opt,
struct diff_queue_struct *renames)
{
int clean_merge = 1, i;
for (i = 0; i < renames->nr; ++i) {
const char *oldpath = NULL, *newpath;
struct diff_filepair *pair = renames->queue[i];
struct conflict_info *oldinfo = NULL, *newinfo = NULL;
struct strmap_entry *old_ent, *new_ent;
unsigned int old_sidemask;
int target_index, other_source_index;
int source_deleted, collision, type_changed;
const char *rename_branch = NULL, *delete_branch = NULL;
old_ent = strmap_get_entry(&opt->priv->paths, pair->one->path);
new_ent = strmap_get_entry(&opt->priv->paths, pair->two->path);
if (old_ent) {
oldpath = old_ent->key;
oldinfo = old_ent->value;
}
newpath = pair->two->path;
if (new_ent) {
newpath = new_ent->key;
newinfo = new_ent->value;
}
/*
* If pair->one->path isn't in opt->priv->paths, that means
* that either directory rename detection removed that
* path, or a parent directory of oldpath was resolved and
* we don't even need the rename; in either case, we can
* skip it. If oldinfo->merged.clean, then the other side
* of history had no changes to oldpath and we don't need
* the rename and can skip it.
*/
if (!oldinfo || oldinfo->merged.clean)
continue;
/*
* diff_filepairs have copies of pathnames, thus we have to
* use standard 'strcmp()' (negated) instead of '=='.
*/
if (i + 1 < renames->nr &&
!strcmp(oldpath, renames->queue[i+1]->one->path)) {
/* Handle rename/rename(1to2) or rename/rename(1to1) */
const char *pathnames[3];
struct version_info merged;
struct conflict_info *base, *side1, *side2;
unsigned was_binary_blob = 0;
pathnames[0] = oldpath;
pathnames[1] = newpath;
pathnames[2] = renames->queue[i+1]->two->path;
base = strmap_get(&opt->priv->paths, pathnames[0]);
side1 = strmap_get(&opt->priv->paths, pathnames[1]);
side2 = strmap_get(&opt->priv->paths, pathnames[2]);
VERIFY_CI(base);
VERIFY_CI(side1);
VERIFY_CI(side2);
if (!strcmp(pathnames[1], pathnames[2])) {
/* Both sides renamed the same way */
assert(side1 == side2);
memcpy(&side1->stages[0], &base->stages[0],
sizeof(merged));
side1->filemask |= (1 << MERGE_BASE);
/* Mark base as resolved by removal */
base->merged.is_null = 1;
base->merged.clean = 1;
/* We handled both renames, i.e. i+1 handled */
i++;
/* Move to next rename */
continue;
}
/* This is a rename/rename(1to2) */
clean_merge = handle_content_merge(opt,
pair->one->path,
&base->stages[0],
&side1->stages[1],
&side2->stages[2],
pathnames,
1 + 2 * opt->priv->call_depth,
&merged);
if (!clean_merge &&
merged.mode == side1->stages[1].mode &&
oideq(&merged.oid, &side1->stages[1].oid))
was_binary_blob = 1;
memcpy(&side1->stages[1], &merged, sizeof(merged));
if (was_binary_blob) {
/*
* Getting here means we were attempting to
* merge a binary blob.
*
* Since we can't merge binaries,
* handle_content_merge() just takes one
* side. But we don't want to copy the
* contents of one side to both paths. We
* used the contents of side1 above for
* side1->stages, let's use the contents of
* side2 for side2->stages below.
*/
oidcpy(&merged.oid, &side2->stages[2].oid);
merged.mode = side2->stages[2].mode;
}
memcpy(&side2->stages[2], &merged, sizeof(merged));
side1->path_conflict = 1;
side2->path_conflict = 1;
/*
* TODO: For renames we normally remove the path at the
* old name. It would thus seem consistent to do the
* same for rename/rename(1to2) cases, but we haven't
* done so traditionally and a number of the regression
* tests now encode an expectation that the file is
* left there at stage 1. If we ever decide to change
* this, add the following two lines here:
* base->merged.is_null = 1;
* base->merged.clean = 1;
* and remove the setting of base->path_conflict to 1.
*/
base->path_conflict = 1;
path_msg(opt, oldpath, 0,
_("CONFLICT (rename/rename): %s renamed to "
"%s in %s and to %s in %s."),
pathnames[0],
pathnames[1], opt->branch1,
pathnames[2], opt->branch2);
i++; /* We handled both renames, i.e. i+1 handled */
continue;
}
VERIFY_CI(oldinfo);
VERIFY_CI(newinfo);
target_index = pair->score; /* from collect_renames() */
assert(target_index == 1 || target_index == 2);
other_source_index = 3 - target_index;
old_sidemask = (1 << other_source_index); /* 2 or 4 */
source_deleted = (oldinfo->filemask == 1);
collision = ((newinfo->filemask & old_sidemask) != 0);
type_changed = !source_deleted &&
(S_ISREG(oldinfo->stages[other_source_index].mode) !=
S_ISREG(newinfo->stages[target_index].mode));
if (type_changed && collision) {
/*
* special handling so later blocks can handle this...
*
* if type_changed && collision are both true, then this
* was really a double rename, but one side wasn't
* detected due to lack of break detection. I.e.
* something like
* orig: has normal file 'foo'
* side1: renames 'foo' to 'bar', adds 'foo' symlink
* side2: renames 'foo' to 'bar'
* In this case, the foo->bar rename on side1 won't be
* detected because the new symlink named 'foo' is
* there and we don't do break detection. But we detect
* this here because we don't want to merge the content
* of the foo symlink with the foo->bar file, so we
* have some logic to handle this special case. The
* easiest way to do that is make 'bar' on side1 not
* be considered a colliding file but the other part
* of a normal rename. If the file is very different,
* well we're going to get content merge conflicts
* anyway so it doesn't hurt. And if the colliding
* file also has a different type, that'll be handled
* by the content merge logic in process_entry() too.
*
* See also t6430, 'rename vs. rename/symlink'
*/
collision = 0;
}
if (source_deleted) {
if (target_index == 1) {
rename_branch = opt->branch1;
delete_branch = opt->branch2;
} else {
rename_branch = opt->branch2;
delete_branch = opt->branch1;
}
}
assert(source_deleted || oldinfo->filemask & old_sidemask);
/* Need to check for special types of rename conflicts... */
if (collision && !source_deleted) {
/* collision: rename/add or rename/rename(2to1) */
const char *pathnames[3];
struct version_info merged;
struct conflict_info *base, *side1, *side2;
unsigned clean;
pathnames[0] = oldpath;
pathnames[other_source_index] = oldpath;
pathnames[target_index] = newpath;
base = strmap_get(&opt->priv->paths, pathnames[0]);
side1 = strmap_get(&opt->priv->paths, pathnames[1]);
side2 = strmap_get(&opt->priv->paths, pathnames[2]);
VERIFY_CI(base);
VERIFY_CI(side1);
VERIFY_CI(side2);
clean = handle_content_merge(opt, pair->one->path,
&base->stages[0],
&side1->stages[1],
&side2->stages[2],
pathnames,
1 + 2 * opt->priv->call_depth,
&merged);
memcpy(&newinfo->stages[target_index], &merged,
sizeof(merged));
if (!clean) {
path_msg(opt, newpath, 0,
_("CONFLICT (rename involved in "
"collision): rename of %s -> %s has "
"content conflicts AND collides "
"with another path; this may result "
"in nested conflict markers."),
oldpath, newpath);
}
} else if (collision && source_deleted) {
/*
* rename/add/delete or rename/rename(2to1)/delete:
* since oldpath was deleted on the side that didn't
* do the rename, there's not much of a content merge
* we can do for the rename. oldinfo->merged.is_null
* was already set, so we just leave things as-is so
* they look like an add/add conflict.
*/
newinfo->path_conflict = 1;
path_msg(opt, newpath, 0,
_("CONFLICT (rename/delete): %s renamed "
"to %s in %s, but deleted in %s."),
oldpath, newpath, rename_branch, delete_branch);
} else {
/*
* a few different cases...start by copying the
* existing stage(s) from oldinfo over the newinfo
* and update the pathname(s).
*/
memcpy(&newinfo->stages[0], &oldinfo->stages[0],
sizeof(newinfo->stages[0]));
newinfo->filemask |= (1 << MERGE_BASE);
newinfo->pathnames[0] = oldpath;
if (type_changed) {
/* rename vs. typechange */
/* Mark the original as resolved by removal */
memcpy(&oldinfo->stages[0].oid, &null_oid,
sizeof(oldinfo->stages[0].oid));
oldinfo->stages[0].mode = 0;
oldinfo->filemask &= 0x06;
} else if (source_deleted) {
/* rename/delete */
newinfo->path_conflict = 1;
path_msg(opt, newpath, 0,
_("CONFLICT (rename/delete): %s renamed"
" to %s in %s, but deleted in %s."),
oldpath, newpath,
rename_branch, delete_branch);
} else {
/* normal rename */
memcpy(&newinfo->stages[other_source_index],
&oldinfo->stages[other_source_index],
sizeof(newinfo->stages[0]));
newinfo->filemask |= (1 << other_source_index);
newinfo->pathnames[other_source_index] = oldpath;
}
}
if (!type_changed) {
/* Mark the original as resolved by removal */
oldinfo->merged.is_null = 1;
oldinfo->merged.clean = 1;
}
}
return clean_merge;
}
static int compare_pairs(const void *a_, const void *b_)
{
const struct diff_filepair *a = *((const struct diff_filepair **)a_);
const struct diff_filepair *b = *((const struct diff_filepair **)b_);
return strcmp(a->one->path, b->one->path);
}
/* Call diffcore_rename() to compute which files have changed on given side */
static void detect_regular_renames(struct merge_options *opt,
struct tree *merge_base,
struct tree *side,
unsigned side_index)
{
struct diff_options diff_opts;
struct rename_info *renames = &opt->priv->renames;
repo_diff_setup(opt->repo, &diff_opts);
diff_opts.flags.recursive = 1;
diff_opts.flags.rename_empty = 0;
diff_opts.detect_rename = DIFF_DETECT_RENAME;
diff_opts.rename_limit = opt->rename_limit;
if (opt->rename_limit <= 0)
diff_opts.rename_limit = 1000;
diff_opts.rename_score = opt->rename_score;
diff_opts.show_rename_progress = opt->show_rename_progress;
diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
diff_setup_done(&diff_opts);
trace2_region_enter("diff", "diffcore_rename", opt->repo);
diff_tree_oid(&merge_base->object.oid, &side->object.oid, "",
&diff_opts);
diffcore_std(&diff_opts);
trace2_region_leave("diff", "diffcore_rename", opt->repo);
if (diff_opts.needed_rename_limit > renames->needed_limit)
renames->needed_limit = diff_opts.needed_rename_limit;
renames->pairs[side_index] = diff_queued_diff;
diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
diff_queued_diff.nr = 0;
diff_queued_diff.queue = NULL;
diff_flush(&diff_opts);
}
/*
* Get information of all renames which occurred in 'side_pairs', discarding
* non-renames.
*/
static int collect_renames(struct merge_options *opt,
struct diff_queue_struct *result,
unsigned side_index,
struct strmap *dir_renames_for_side,
struct strmap *rename_exclusions)
{
int i, clean = 1;
struct strmap collisions;
struct diff_queue_struct *side_pairs;
struct hashmap_iter iter;
struct strmap_entry *entry;
struct rename_info *renames = &opt->priv->renames;
side_pairs = &renames->pairs[side_index];
compute_collisions(&collisions, dir_renames_for_side, side_pairs);
for (i = 0; i < side_pairs->nr; ++i) {
struct diff_filepair *p = side_pairs->queue[i];
char *new_path; /* non-NULL only with directory renames */
if (p->status != 'A' && p->status != 'R') {
diff_free_filepair(p);
continue;
}
new_path = check_for_directory_rename(opt, p->two->path,
side_index,
dir_renames_for_side,
rename_exclusions,
&collisions,
&clean);
if (p->status != 'R' && !new_path) {
diff_free_filepair(p);
continue;
}
if (new_path)
apply_directory_rename_modifications(opt, p, new_path);
/*
* p->score comes back from diffcore_rename_extended() with
* the similarity of the renamed file. The similarity is
* was used to determine that the two files were related
* and are a rename, which we have already used, but beyond
* that we have no use for the similarity. So p->score is
* now irrelevant. However, process_renames() will need to
* know which side of the merge this rename was associated
* with, so overwrite p->score with that value.
*/
p->score = side_index;
result->queue[result->nr++] = p;
}
/* Free each value in the collisions map */
strmap_for_each_entry(&collisions, &iter, entry) {
struct collision_info *info = entry->value;
string_list_clear(&info->source_files, 0);
}
/*
* In compute_collisions(), we set collisions.strdup_strings to 0
* so that we wouldn't have to make another copy of the new_path
* allocated by apply_dir_rename(). But now that we've used them
* and have no other references to these strings, it is time to
* deallocate them.
*/
free_strmap_strings(&collisions);
strmap_clear(&collisions, 1);
return clean;
}
static int detect_and_process_renames(struct merge_options *opt,
struct tree *merge_base,
struct tree *side1,
struct tree *side2)
{
struct diff_queue_struct combined;
struct rename_info *renames = &opt->priv->renames;
int need_dir_renames, s, clean = 1;
memset(&combined, 0, sizeof(combined));
trace2_region_enter("merge", "regular renames", opt->repo);
detect_regular_renames(opt, merge_base, side1, MERGE_SIDE1);
detect_regular_renames(opt, merge_base, side2, MERGE_SIDE2);
trace2_region_leave("merge", "regular renames", opt->repo);
trace2_region_enter("merge", "directory renames", opt->repo);
need_dir_renames =
!opt->priv->call_depth &&
(opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_TRUE ||
opt->detect_directory_renames == MERGE_DIRECTORY_RENAMES_CONFLICT);
if (need_dir_renames) {
get_provisional_directory_renames(opt, MERGE_SIDE1, &clean);
get_provisional_directory_renames(opt, MERGE_SIDE2, &clean);
handle_directory_level_conflicts(opt);
}
ALLOC_GROW(combined.queue,
renames->pairs[1].nr + renames->pairs[2].nr,
combined.alloc);
clean &= collect_renames(opt, &combined, MERGE_SIDE1,
&renames->dir_renames[2],
&renames->dir_renames[1]);
clean &= collect_renames(opt, &combined, MERGE_SIDE2,
&renames->dir_renames[1],
&renames->dir_renames[2]);
QSORT(combined.queue, combined.nr, compare_pairs);
trace2_region_leave("merge", "directory renames", opt->repo);
trace2_region_enter("merge", "process renames", opt->repo);
clean &= process_renames(opt, &combined);
trace2_region_leave("merge", "process renames", opt->repo);
/* Free memory for renames->pairs[] and combined */
for (s = MERGE_SIDE1; s <= MERGE_SIDE2; s++) {
free(renames->pairs[s].queue);
DIFF_QUEUE_CLEAR(&renames->pairs[s]);
}
if (combined.nr) {
int i;
for (i = 0; i < combined.nr; i++)
diff_free_filepair(combined.queue[i]);
free(combined.queue);
}
return clean;
}
/*** Function Grouping: functions related to process_entries() ***/
static int string_list_df_name_compare(const char *one, const char *two)
{
int onelen = strlen(one);
int twolen = strlen(two);
/*
* Here we only care that entries for D/F conflicts are
* adjacent, in particular with the file of the D/F conflict
* appearing before files below the corresponding directory.
* The order of the rest of the list is irrelevant for us.
*
* To achieve this, we sort with df_name_compare and provide
* the mode S_IFDIR so that D/F conflicts will sort correctly.
* We use the mode S_IFDIR for everything else for simplicity,
* since in other cases any changes in their order due to
* sorting cause no problems for us.
*/
int cmp = df_name_compare(one, onelen, S_IFDIR,
two, twolen, S_IFDIR);
/*
* Now that 'foo' and 'foo/bar' compare equal, we have to make sure
* that 'foo' comes before 'foo/bar'.
*/
if (cmp)
return cmp;
return onelen - twolen;
}
struct directory_versions {
/*
* versions: list of (basename -> version_info)
*
* The basenames are in reverse lexicographic order of full pathnames,
* as processed in process_entries(). This puts all entries within
* a directory together, and covers the directory itself after
* everything within it, allowing us to write subtrees before needing
* to record information for the tree itself.
*/
struct string_list versions;
/*
* offsets: list of (full relative path directories -> integer offsets)
*
* Since versions contains basenames from files in multiple different
* directories, we need to know which entries in versions correspond
* to which directories. Values of e.g.
* "" 0
* src 2
* src/moduleA 5
* Would mean that entries 0-1 of versions are files in the toplevel
* directory, entries 2-4 are files under src/, and the remaining
* entries starting at index 5 are files under src/moduleA/.
*/
struct string_list offsets;
/*
* last_directory: directory that previously processed file found in
*
* last_directory starts NULL, but records the directory in which the
* previous file was found within. As soon as
* directory(current_file) != last_directory
* then we need to start updating accounting in versions & offsets.
* Note that last_directory is always the last path in "offsets" (or
* NULL if "offsets" is empty) so this exists just for quick access.
*/
const char *last_directory;
/* last_directory_len: cached computation of strlen(last_directory) */
unsigned last_directory_len;
};
static int tree_entry_order(const void *a_, const void *b_)
{
const struct string_list_item *a = a_;
const struct string_list_item *b = b_;
const struct merged_info *ami = a->util;
const struct merged_info *bmi = b->util;
return base_name_compare(a->string, strlen(a->string), ami->result.mode,
b->string, strlen(b->string), bmi->result.mode);
}
static void write_tree(struct object_id *result_oid,
struct string_list *versions,
unsigned int offset,
size_t hash_size)
{
size_t maxlen = 0, extra;
unsigned int nr = versions->nr - offset;
struct strbuf buf = STRBUF_INIT;
struct string_list relevant_entries = STRING_LIST_INIT_NODUP;
int i;
/*
* We want to sort the last (versions->nr-offset) entries in versions.
* Do so by abusing the string_list API a bit: make another string_list
* that contains just those entries and then sort them.
*
* We won't use relevant_entries again and will let it just pop off the
* stack, so there won't be allocation worries or anything.
*/
relevant_entries.items = versions->items + offset;
relevant_entries.nr = versions->nr - offset;
QSORT(relevant_entries.items, relevant_entries.nr, tree_entry_order);
/* Pre-allocate some space in buf */
extra = hash_size + 8; /* 8: 6 for mode, 1 for space, 1 for NUL char */
for (i = 0; i < nr; i++) {
maxlen += strlen(versions->items[offset+i].string) + extra;
}
strbuf_grow(&buf, maxlen);
/* Write each entry out to buf */
for (i = 0; i < nr; i++) {
struct merged_info *mi = versions->items[offset+i].util;
struct version_info *ri = &mi->result;
strbuf_addf(&buf, "%o %s%c",
ri->mode,
versions->items[offset+i].string, '\0');
strbuf_add(&buf, ri->oid.hash, hash_size);
}
/* Write this object file out, and record in result_oid */
write_object_file(buf.buf, buf.len, tree_type, result_oid);
strbuf_release(&buf);
}
static void record_entry_for_tree(struct directory_versions *dir_metadata,
const char *path,
struct merged_info *mi)
{
const char *basename;
if (mi->is_null)
/* nothing to record */
return;
basename = path + mi->basename_offset;
assert(strchr(basename, '/') == NULL);
string_list_append(&dir_metadata->versions,
basename)->util = &mi->result;
}
static void write_completed_directory(struct merge_options *opt,
const char *new_directory_name,
struct directory_versions *info)
{
const char *prev_dir;
struct merged_info *dir_info = NULL;
unsigned int offset;
/*
* Some explanation of info->versions and info->offsets...
*
* process_entries() iterates over all relevant files AND
* directories in reverse lexicographic order, and calls this
* function. Thus, an example of the paths that process_entries()
* could operate on (along with the directories for those paths
* being shown) is:
*
* xtract.c ""
* tokens.txt ""
* src/moduleB/umm.c src/moduleB
* src/moduleB/stuff.h src/moduleB
* src/moduleB/baz.c src/moduleB
* src/moduleB src
* src/moduleA/foo.c src/moduleA
* src/moduleA/bar.c src/moduleA
* src/moduleA src
* src ""
* Makefile ""
*
* info->versions:
*
* always contains the unprocessed entries and their
* version_info information. For example, after the first five
* entries above, info->versions would be:
*
* xtract.c <xtract.c's version_info>
* token.txt <token.txt's version_info>
* umm.c <src/moduleB/umm.c's version_info>
* stuff.h <src/moduleB/stuff.h's version_info>
* baz.c <src/moduleB/baz.c's version_info>
*
* Once a subdirectory is completed we remove the entries in
* that subdirectory from info->versions, writing it as a tree
* (write_tree()). Thus, as soon as we get to src/moduleB,
* info->versions would be updated to
*
* xtract.c <xtract.c's version_info>
* token.txt <token.txt's version_info>
* moduleB <src/moduleB's version_info>
*
* info->offsets:
*
* helps us track which entries in info->versions correspond to
* which directories. When we are N directories deep (e.g. 4
* for src/modA/submod/subdir/), we have up to N+1 unprocessed
* directories (+1 because of toplevel dir). Corresponding to
* the info->versions example above, after processing five entries
* info->offsets will be:
*
* "" 0
* src/moduleB 2
*
* which is used to know that xtract.c & token.txt are from the
* toplevel dirctory, while umm.c & stuff.h & baz.c are from the
* src/moduleB directory. Again, following the example above,
* once we need to process src/moduleB, then info->offsets is
* updated to
*
* "" 0
* src 2
*
* which says that moduleB (and only moduleB so far) is in the
* src directory.
*
* One unique thing to note about info->offsets here is that
* "src" was not added to info->offsets until there was a path
* (a file OR directory) immediately below src/ that got
* processed.
*
* Since process_entry() just appends new entries to info->versions,
* write_completed_directory() only needs to do work if the next path
* is in a directory that is different than the last directory found
* in info->offsets.
*/
/*
* If we are working with the same directory as the last entry, there
* is no work to do. (See comments above the directory_name member of
* struct merged_info for why we can use pointer comparison instead of
* strcmp here.)
*/
if (new_directory_name == info->last_directory)
return;
/*
* If we are just starting (last_directory is NULL), or last_directory
* is a prefix of the current directory, then we can just update
* info->offsets to record the offset where we started this directory
* and update last_directory to have quick access to it.
*/
if (info->last_directory == NULL ||
!strncmp(new_directory_name, info->last_directory,
info->last_directory_len)) {
uintptr_t offset = info->versions.nr;
info->last_directory = new_directory_name;
info->last_directory_len = strlen(info->last_directory);
/*
* Record the offset into info->versions where we will
* start recording basenames of paths found within
* new_directory_name.
*/
string_list_append(&info->offsets,
info->last_directory)->util = (void*)offset;
return;
}
/*
* The next entry that will be processed will be within
* new_directory_name. Since at this point we know that
* new_directory_name is within a different directory than
* info->last_directory, we have all entries for info->last_directory
* in info->versions and we need to create a tree object for them.
*/
dir_info = strmap_get(&opt->priv->paths, info->last_directory);
assert(dir_info);
offset = (uintptr_t)info->offsets.items[info->offsets.nr-1].util;
if (offset == info->versions.nr) {
/*
* Actually, we don't need to create a tree object in this
* case. Whenever all files within a directory disappear
* during the merge (e.g. unmodified on one side and
* deleted on the other, or files were renamed elsewhere),
* then we get here and the directory itself needs to be
* omitted from its parent tree as well.
*/
dir_info->is_null = 1;
} else {
/*
* Write out the tree to the git object directory, and also
* record the mode and oid in dir_info->result.
*/
dir_info->is_null = 0;
dir_info->result.mode = S_IFDIR;
write_tree(&dir_info->result.oid, &info->versions, offset,
opt->repo->hash_algo->rawsz);
}
/*
* We've now used several entries from info->versions and one entry
* from info->offsets, so we get rid of those values.
*/
info->offsets.nr--;
info->versions.nr = offset;
/*
* Now we've taken care of the completed directory, but we need to
* prepare things since future entries will be in
* new_directory_name. (In particular, process_entry() will be
* appending new entries to info->versions.) So, we need to make
* sure new_directory_name is the last entry in info->offsets.
*/
prev_dir = info->offsets.nr == 0 ? NULL :
info->offsets.items[info->offsets.nr-1].string;
if (new_directory_name != prev_dir) {
uintptr_t c = info->versions.nr;
string_list_append(&info->offsets,
new_directory_name)->util = (void*)c;
}
/* And, of course, we need to update last_directory to match. */
info->last_directory = new_directory_name;
info->last_directory_len = strlen(info->last_directory);
}
/* Per entry merge function */
static void process_entry(struct merge_options *opt,
const char *path,
struct conflict_info *ci,
struct directory_versions *dir_metadata)
{
int df_file_index = 0;
VERIFY_CI(ci);
assert(ci->filemask >= 0 && ci->filemask <= 7);
/* ci->match_mask == 7 was handled in collect_merge_info_callback() */
assert(ci->match_mask == 0 || ci->match_mask == 3 ||
ci->match_mask == 5 || ci->match_mask == 6);
if (ci->dirmask) {
record_entry_for_tree(dir_metadata, path, &ci->merged);
if (ci->filemask == 0)
/* nothing else to handle */
return;
assert(ci->df_conflict);
}
if (ci->df_conflict && ci->merged.result.mode == 0) {
int i;
/*
* directory no longer in the way, but we do have a file we
* need to place here so we need to clean away the "directory
* merges to nothing" result.
*/
ci->df_conflict = 0;
assert(ci->filemask != 0);
ci->merged.clean = 0;
ci->merged.is_null = 0;
/* and we want to zero out any directory-related entries */
ci->match_mask = (ci->match_mask & ~ci->dirmask);
ci->dirmask = 0;
for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) {
if (ci->filemask & (1 << i))
continue;
ci->stages[i].mode = 0;
oidcpy(&ci->stages[i].oid, &null_oid);
}
} else if (ci->df_conflict && ci->merged.result.mode != 0) {
/*
* This started out as a D/F conflict, and the entries in
* the competing directory were not removed by the merge as
* evidenced by write_completed_directory() writing a value
* to ci->merged.result.mode.
*/
struct conflict_info *new_ci;
const char *branch;
const char *old_path = path;
int i;
assert(ci->merged.result.mode == S_IFDIR);
/*
* If filemask is 1, we can just ignore the file as having
* been deleted on both sides. We do not want to overwrite
* ci->merged.result, since it stores the tree for all the
* files under it.
*/
if (ci->filemask == 1) {
ci->filemask = 0;
return;
}
/*
* This file still exists on at least one side, and we want
* the directory to remain here, so we need to move this
* path to some new location.
*/
new_ci = xcalloc(1, sizeof(*new_ci));
/* We don't really want new_ci->merged.result copied, but it'll
* be overwritten below so it doesn't matter. We also don't
* want any directory mode/oid values copied, but we'll zero
* those out immediately. We do want the rest of ci copied.
*/
memcpy(new_ci, ci, sizeof(*ci));
new_ci->match_mask = (new_ci->match_mask & ~new_ci->dirmask);
new_ci->dirmask = 0;
for (i = MERGE_BASE; i <= MERGE_SIDE2; i++) {
if (new_ci->filemask & (1 << i))
continue;
/* zero out any entries related to directories */
new_ci->stages[i].mode = 0;
oidcpy(&new_ci->stages[i].oid, &null_oid);
}
/*
* Find out which side this file came from; note that we
* cannot just use ci->filemask, because renames could cause
* the filemask to go back to 7. So we use dirmask, then
* pick the opposite side's index.
*/
df_file_index = (ci->dirmask & (1 << 1)) ? 2 : 1;
branch = (df_file_index == 1) ? opt->branch1 : opt->branch2;
path = unique_path(&opt->priv->paths, path, branch);
strmap_put(&opt->priv->paths, path, new_ci);
path_msg(opt, path, 0,
_("CONFLICT (file/directory): directory in the way "
"of %s from %s; moving it to %s instead."),
old_path, branch, path);
/*
* Zero out the filemask for the old ci. At this point, ci
* was just an entry for a directory, so we don't need to
* do anything more with it.
*/
ci->filemask = 0;
/*
* Now note that we're working on the new entry (path was
* updated above.
*/
ci = new_ci;
}
/*
* NOTE: Below there is a long switch-like if-elseif-elseif... block
* which the code goes through even for the df_conflict cases
* above.
*/
if (ci->match_mask) {
ci->merged.clean = 1;
if (ci->match_mask == 6) {
/* stages[1] == stages[2] */
ci->merged.result.mode = ci->stages[1].mode;
oidcpy(&ci->merged.result.oid, &ci->stages[1].oid);
} else {
/* determine the mask of the side that didn't match */
unsigned int othermask = 7 & ~ci->match_mask;
int side = (othermask == 4) ? 2 : 1;
ci->merged.result.mode = ci->stages[side].mode;
ci->merged.is_null = !ci->merged.result.mode;
oidcpy(&ci->merged.result.oid, &ci->stages[side].oid);
assert(othermask == 2 || othermask == 4);
assert(ci->merged.is_null ==
(ci->filemask == ci->match_mask));
}
} else if (ci->filemask >= 6 &&
(S_IFMT & ci->stages[1].mode) !=
(S_IFMT & ci->stages[2].mode)) {
/* Two different items from (file/submodule/symlink) */
if (opt->priv->call_depth) {
/* Just use the version from the merge base */
ci->merged.clean = 0;
oidcpy(&ci->merged.result.oid, &ci->stages[0].oid);
ci->merged.result.mode = ci->stages[0].mode;
ci->merged.is_null = (ci->merged.result.mode == 0);
} else {
/* Handle by renaming one or both to separate paths. */
unsigned o_mode = ci->stages[0].mode;
unsigned a_mode = ci->stages[1].mode;
unsigned b_mode = ci->stages[2].mode;
struct conflict_info *new_ci;
const char *a_path = NULL, *b_path = NULL;
int rename_a = 0, rename_b = 0;
new_ci = xmalloc(sizeof(*new_ci));
if (S_ISREG(a_mode))
rename_a = 1;
else if (S_ISREG(b_mode))
rename_b = 1;
else {
rename_a = 1;
rename_b = 1;
}
path_msg(opt, path, 0,
_("CONFLICT (distinct types): %s had different "
"types on each side; renamed %s of them so "
"each can be recorded somewhere."),
path,
(rename_a && rename_b) ? _("both") : _("one"));
ci->merged.clean = 0;
memcpy(new_ci, ci, sizeof(*new_ci));
/* Put b into new_ci, removing a from stages */
new_ci->merged.result.mode = ci->stages[2].mode;
oidcpy(&new_ci->merged.result.oid, &ci->stages[2].oid);
new_ci->stages[1].mode = 0;