git/builtin/checkout.c

1259 lines
36 KiB
C
Raw Normal View History

#include "builtin.h"
#include "config.h"
#include "checkout.h"
#include "lockfile.h"
#include "parse-options.h"
#include "refs.h"
#include "commit.h"
#include "tree.h"
#include "tree-walk.h"
#include "cache-tree.h"
#include "unpack-trees.h"
#include "dir.h"
#include "run-command.h"
#include "merge-recursive.h"
#include "branch.h"
#include "diff.h"
#include "revision.h"
#include "remote.h"
#include "blob.h"
#include "xdiff-interface.h"
#include "ll-merge.h"
#include "resolve-undo.h"
#include "submodule-config.h"
#include "submodule.h"
static const char * const checkout_usage[] = {
N_("git checkout [<options>] <branch>"),
N_("git checkout [<options>] [<branch>] -- <file>..."),
NULL,
};
struct checkout_opts {
int patch_mode;
int quiet;
int merge;
int force;
int force_detach;
int writeout_stage;
int overwrite_ignore;
int ignore_skipworktree;
int ignore_other_worktrees;
int show_progress;
const char *new_branch;
const char *new_branch_force;
const char *new_orphan_branch;
int new_branch_log;
enum branch_track track;
struct diff_options diff_options;
int branch_exists;
const char *prefix;
struct pathspec pathspec;
struct tree *source_tree;
};
static int post_checkout_hook(struct commit *old_commit, struct commit *new_commit,
int changed)
{
return run_hook_le(NULL, "post-checkout",
oid_to_hex(old_commit ? &old_commit->object.oid : &null_oid),
oid_to_hex(new_commit ? &new_commit->object.oid : &null_oid),
changed ? "1" : "0", NULL);
/* "new_commit" can be NULL when checking out from the index before
a commit exists. */
}
static int update_some(const struct object_id *oid, struct strbuf *base,
const char *pathname, unsigned mode, int stage, void *context)
{
int len;
struct cache_entry *ce;
int pos;
if (S_ISDIR(mode))
return READ_TREE_RECURSIVE;
len = base->len + strlen(pathname);
ce = xcalloc(1, cache_entry_size(len));
oidcpy(&ce->oid, oid);
memcpy(ce->name, base->buf, base->len);
memcpy(ce->name + base->len, pathname, len - base->len);
ce->ce_flags = create_ce_flags(0) | CE_UPDATE;
ce->ce_namelen = len;
ce->ce_mode = create_ce_mode(mode);
/*
* If the entry is the same as the current index, we can leave the old
* entry in place. Whether it is UPTODATE or not, checkout_entry will
* do the right thing.
*/
pos = cache_name_pos(ce->name, ce->ce_namelen);
if (pos >= 0) {
struct cache_entry *old = active_cache[pos];
if (ce->ce_mode == old->ce_mode &&
!oidcmp(&ce->oid, &old->oid)) {
old->ce_flags |= CE_UPDATE;
free(ce);
return 0;
}
}
add_cache_entry(ce, ADD_CACHE_OK_TO_ADD | ADD_CACHE_OK_TO_REPLACE);
return 0;
}
static int read_tree_some(struct tree *tree, const struct pathspec *pathspec)
{
read_tree_recursive(tree, "", 0, 0, pathspec, update_some, NULL);
/* update the index with the given tree's info
* for all args, expanding wildcards, and exit
* with any non-zero return code.
*/
return 0;
}
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 23:29:00 +08:00
static int skip_same_name(const struct cache_entry *ce, int pos)
{
while (++pos < active_nr &&
!strcmp(active_cache[pos]->name, ce->name))
; /* skip */
return pos;
}
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 23:29:00 +08:00
static int check_stage(int stage, const struct cache_entry *ce, int pos)
{
while (pos < active_nr &&
!strcmp(active_cache[pos]->name, ce->name)) {
if (ce_stage(active_cache[pos]) == stage)
return 0;
pos++;
}
if (stage == 2)
return error(_("path '%s' does not have our version"), ce->name);
else
return error(_("path '%s' does not have their version"), ce->name);
}
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 23:29:00 +08:00
static int check_stages(unsigned stages, const struct cache_entry *ce, int pos)
{
unsigned seen = 0;
const char *name = ce->name;
while (pos < active_nr) {
ce = active_cache[pos];
if (strcmp(name, ce->name))
break;
seen |= (1 << ce_stage(ce));
pos++;
}
if ((stages & seen) != stages)
return error(_("path '%s' does not have all necessary versions"),
name);
return 0;
}
static int checkout_stage(int stage, const struct cache_entry *ce, int pos,
const struct checkout *state)
{
while (pos < active_nr &&
!strcmp(active_cache[pos]->name, ce->name)) {
if (ce_stage(active_cache[pos]) == stage)
return checkout_entry(active_cache[pos], state, NULL);
pos++;
}
if (stage == 2)
return error(_("path '%s' does not have our version"), ce->name);
else
return error(_("path '%s' does not have their version"), ce->name);
}
static int checkout_merged(int pos, const struct checkout *state)
{
struct cache_entry *ce = active_cache[pos];
const char *path = ce->name;
mmfile_t ancestor, ours, theirs;
int status;
struct object_id oid;
mmbuffer_t result_buf;
struct object_id threeway[3];
unsigned mode = 0;
memset(threeway, 0, sizeof(threeway));
while (pos < active_nr) {
int stage;
stage = ce_stage(ce);
if (!stage || strcmp(path, ce->name))
break;
oidcpy(&threeway[stage - 1], &ce->oid);
if (stage == 2)
mode = create_ce_mode(ce->ce_mode);
pos++;
ce = active_cache[pos];
}
if (is_null_oid(&threeway[1]) || is_null_oid(&threeway[2]))
return error(_("path '%s' does not have necessary versions"), path);
read_mmblob(&ancestor, &threeway[0]);
read_mmblob(&ours, &threeway[1]);
read_mmblob(&theirs, &threeway[2]);
/*
* NEEDSWORK: re-create conflicts from merges with
* merge.renormalize set, too
*/
status = ll_merge(&result_buf, path, &ancestor, "base",
&ours, "ours", &theirs, "theirs", NULL);
free(ancestor.ptr);
free(ours.ptr);
free(theirs.ptr);
if (status < 0 || !result_buf.ptr) {
free(result_buf.ptr);
return error(_("path '%s': cannot merge"), path);
}
/*
* NEEDSWORK:
* There is absolutely no reason to write this as a blob object
* and create a phony cache entry. This hack is primarily to get
* to the write_entry() machinery that massages the contents to
* work-tree format and writes out which only allows it for a
* cache entry. The code in write_entry() needs to be refactored
* to allow us to feed a <buffer, size, mode> instead of a cache
* entry. Such a refactoring would help merge_recursive as well
* (it also writes the merge result to the object database even
* when it may contain conflicts).
*/
if (write_object_file(result_buf.ptr, result_buf.size, blob_type, &oid))
die(_("Unable to add merge result for '%s'"), path);
free(result_buf.ptr);
ce = make_cache_entry(mode, oid.hash, path, 2, 0);
if (!ce)
die(_("make_cache_entry failed for path '%s'"), path);
status = checkout_entry(ce, state, NULL);
free(ce);
return status;
}
static int checkout_paths(const struct checkout_opts *opts,
const char *revision)
{
int pos;
struct checkout state = CHECKOUT_INIT;
static char *ps_matched;
struct object_id rev;
struct commit *head;
int errs = 0;
struct lock_file lock_file = LOCK_INIT;
if (opts->track != BRANCH_TRACK_UNSPECIFIED)
die(_("'%s' cannot be used with updating paths"), "--track");
if (opts->new_branch_log)
die(_("'%s' cannot be used with updating paths"), "-l");
if (opts->force && opts->patch_mode)
die(_("'%s' cannot be used with updating paths"), "-f");
if (opts->force_detach)
die(_("'%s' cannot be used with updating paths"), "--detach");
if (opts->merge && opts->patch_mode)
die(_("'%s' cannot be used with %s"), "--merge", "--patch");
if (opts->force && opts->merge)
die(_("'%s' cannot be used with %s"), "-f", "-m");
if (opts->new_branch)
die(_("Cannot update paths and switch to branch '%s' at the same time."),
opts->new_branch);
if (opts->patch_mode)
return run_add_interactive(revision, "--patch=checkout",
&opts->pathspec);
hold_locked_index(&lock_file, LOCK_DIE_ON_ERROR);
if (read_cache_preload(&opts->pathspec) < 0)
return error(_("index file corrupt"));
if (opts->source_tree)
read_tree_some(opts->source_tree, &opts->pathspec);
ps_matched = xcalloc(opts->pathspec.nr, 1);
checkout: avoid unnecessary match_pathspec calls In checkout_paths() we do this - for all updated items, call match_pathspec - for all items, call match_pathspec (inside unmerge_cache) - for all items, call match_pathspec (for showing "path .. is unmerged) - for updated items, call match_pathspec and update paths That's a lot of duplicate match_pathspec(s) and the function is not exactly cheap to be called so many times, especially on large indexes. This patch makes it call match_pathspec once per updated index entry, save the result in ce_flags and reuse the results in the following loops. The changes in 0a1283b (checkout $tree $path: do not clobber local changes in $path not in $tree - 2011-09-30) limit the affected paths to ones we read from $tree. We do not do anything to other modified entries in this case, so the "for all items" above could be modified to "for all updated items". But.. The command's behavior now is modified slightly: unmerged entries that match $path, but not updated by $tree, are now NOT touched. Although this should be considered a bug fix, not a regression. A new test is added for this change. And while at there, free ps_matched after use. The following command is tested on webkit, 215k entries. The pattern is chosen mainly to make match_pathspec sweat: git checkout -- "*[a-zA-Z]*[a-zA-Z]*[a-zA-Z]*" before after real 0m3.493s 0m2.737s user 0m2.239s 0m1.586s sys 0m1.252s 0m1.151s Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-27 13:58:21 +08:00
/*
* Make sure all pathspecs participated in locating the paths
* to be checked out.
*/
for (pos = 0; pos < active_nr; pos++) {
struct cache_entry *ce = active_cache[pos];
checkout: avoid unnecessary match_pathspec calls In checkout_paths() we do this - for all updated items, call match_pathspec - for all items, call match_pathspec (inside unmerge_cache) - for all items, call match_pathspec (for showing "path .. is unmerged) - for updated items, call match_pathspec and update paths That's a lot of duplicate match_pathspec(s) and the function is not exactly cheap to be called so many times, especially on large indexes. This patch makes it call match_pathspec once per updated index entry, save the result in ce_flags and reuse the results in the following loops. The changes in 0a1283b (checkout $tree $path: do not clobber local changes in $path not in $tree - 2011-09-30) limit the affected paths to ones we read from $tree. We do not do anything to other modified entries in this case, so the "for all items" above could be modified to "for all updated items". But.. The command's behavior now is modified slightly: unmerged entries that match $path, but not updated by $tree, are now NOT touched. Although this should be considered a bug fix, not a regression. A new test is added for this change. And while at there, free ps_matched after use. The following command is tested on webkit, 215k entries. The pattern is chosen mainly to make match_pathspec sweat: git checkout -- "*[a-zA-Z]*[a-zA-Z]*[a-zA-Z]*" before after real 0m3.493s 0m2.737s user 0m2.239s 0m1.586s sys 0m1.252s 0m1.151s Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-27 13:58:21 +08:00
ce->ce_flags &= ~CE_MATCHED;
if (!opts->ignore_skipworktree && ce_skip_worktree(ce))
continue;
if (opts->source_tree && !(ce->ce_flags & CE_UPDATE))
checkout: avoid unnecessary match_pathspec calls In checkout_paths() we do this - for all updated items, call match_pathspec - for all items, call match_pathspec (inside unmerge_cache) - for all items, call match_pathspec (for showing "path .. is unmerged) - for updated items, call match_pathspec and update paths That's a lot of duplicate match_pathspec(s) and the function is not exactly cheap to be called so many times, especially on large indexes. This patch makes it call match_pathspec once per updated index entry, save the result in ce_flags and reuse the results in the following loops. The changes in 0a1283b (checkout $tree $path: do not clobber local changes in $path not in $tree - 2011-09-30) limit the affected paths to ones we read from $tree. We do not do anything to other modified entries in this case, so the "for all items" above could be modified to "for all updated items". But.. The command's behavior now is modified slightly: unmerged entries that match $path, but not updated by $tree, are now NOT touched. Although this should be considered a bug fix, not a regression. A new test is added for this change. And while at there, free ps_matched after use. The following command is tested on webkit, 215k entries. The pattern is chosen mainly to make match_pathspec sweat: git checkout -- "*[a-zA-Z]*[a-zA-Z]*[a-zA-Z]*" before after real 0m3.493s 0m2.737s user 0m2.239s 0m1.586s sys 0m1.252s 0m1.151s Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-27 13:58:21 +08:00
/*
* "git checkout tree-ish -- path", but this entry
* is in the original index; it will not be checked
* out to the working tree and it does not matter
* if pathspec matched this entry. We will not do
* anything to this entry at all.
*/
continue;
checkout: avoid unnecessary match_pathspec calls In checkout_paths() we do this - for all updated items, call match_pathspec - for all items, call match_pathspec (inside unmerge_cache) - for all items, call match_pathspec (for showing "path .. is unmerged) - for updated items, call match_pathspec and update paths That's a lot of duplicate match_pathspec(s) and the function is not exactly cheap to be called so many times, especially on large indexes. This patch makes it call match_pathspec once per updated index entry, save the result in ce_flags and reuse the results in the following loops. The changes in 0a1283b (checkout $tree $path: do not clobber local changes in $path not in $tree - 2011-09-30) limit the affected paths to ones we read from $tree. We do not do anything to other modified entries in this case, so the "for all items" above could be modified to "for all updated items". But.. The command's behavior now is modified slightly: unmerged entries that match $path, but not updated by $tree, are now NOT touched. Although this should be considered a bug fix, not a regression. A new test is added for this change. And while at there, free ps_matched after use. The following command is tested on webkit, 215k entries. The pattern is chosen mainly to make match_pathspec sweat: git checkout -- "*[a-zA-Z]*[a-zA-Z]*[a-zA-Z]*" before after real 0m3.493s 0m2.737s user 0m2.239s 0m1.586s sys 0m1.252s 0m1.151s Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-27 13:58:21 +08:00
/*
* Either this entry came from the tree-ish we are
* checking the paths out of, or we are checking out
* of the index.
*
* If it comes from the tree-ish, we already know it
* matches the pathspec and could just stamp
* CE_MATCHED to it from update_some(). But we still
* need ps_matched and read_tree_recursive (and
* eventually tree_entry_interesting) cannot fill
* ps_matched yet. Once it can, we can avoid calling
* match_pathspec() for _all_ entries when
* opts->source_tree != NULL.
*/
if (ce_path_match(ce, &opts->pathspec, ps_matched))
checkout: avoid unnecessary match_pathspec calls In checkout_paths() we do this - for all updated items, call match_pathspec - for all items, call match_pathspec (inside unmerge_cache) - for all items, call match_pathspec (for showing "path .. is unmerged) - for updated items, call match_pathspec and update paths That's a lot of duplicate match_pathspec(s) and the function is not exactly cheap to be called so many times, especially on large indexes. This patch makes it call match_pathspec once per updated index entry, save the result in ce_flags and reuse the results in the following loops. The changes in 0a1283b (checkout $tree $path: do not clobber local changes in $path not in $tree - 2011-09-30) limit the affected paths to ones we read from $tree. We do not do anything to other modified entries in this case, so the "for all items" above could be modified to "for all updated items". But.. The command's behavior now is modified slightly: unmerged entries that match $path, but not updated by $tree, are now NOT touched. Although this should be considered a bug fix, not a regression. A new test is added for this change. And while at there, free ps_matched after use. The following command is tested on webkit, 215k entries. The pattern is chosen mainly to make match_pathspec sweat: git checkout -- "*[a-zA-Z]*[a-zA-Z]*[a-zA-Z]*" before after real 0m3.493s 0m2.737s user 0m2.239s 0m1.586s sys 0m1.252s 0m1.151s Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-27 13:58:21 +08:00
ce->ce_flags |= CE_MATCHED;
}
if (report_path_error(ps_matched, &opts->pathspec, opts->prefix)) {
checkout: avoid unnecessary match_pathspec calls In checkout_paths() we do this - for all updated items, call match_pathspec - for all items, call match_pathspec (inside unmerge_cache) - for all items, call match_pathspec (for showing "path .. is unmerged) - for updated items, call match_pathspec and update paths That's a lot of duplicate match_pathspec(s) and the function is not exactly cheap to be called so many times, especially on large indexes. This patch makes it call match_pathspec once per updated index entry, save the result in ce_flags and reuse the results in the following loops. The changes in 0a1283b (checkout $tree $path: do not clobber local changes in $path not in $tree - 2011-09-30) limit the affected paths to ones we read from $tree. We do not do anything to other modified entries in this case, so the "for all items" above could be modified to "for all updated items". But.. The command's behavior now is modified slightly: unmerged entries that match $path, but not updated by $tree, are now NOT touched. Although this should be considered a bug fix, not a regression. A new test is added for this change. And while at there, free ps_matched after use. The following command is tested on webkit, 215k entries. The pattern is chosen mainly to make match_pathspec sweat: git checkout -- "*[a-zA-Z]*[a-zA-Z]*[a-zA-Z]*" before after real 0m3.493s 0m2.737s user 0m2.239s 0m1.586s sys 0m1.252s 0m1.151s Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-27 13:58:21 +08:00
free(ps_matched);
return 1;
checkout: avoid unnecessary match_pathspec calls In checkout_paths() we do this - for all updated items, call match_pathspec - for all items, call match_pathspec (inside unmerge_cache) - for all items, call match_pathspec (for showing "path .. is unmerged) - for updated items, call match_pathspec and update paths That's a lot of duplicate match_pathspec(s) and the function is not exactly cheap to be called so many times, especially on large indexes. This patch makes it call match_pathspec once per updated index entry, save the result in ce_flags and reuse the results in the following loops. The changes in 0a1283b (checkout $tree $path: do not clobber local changes in $path not in $tree - 2011-09-30) limit the affected paths to ones we read from $tree. We do not do anything to other modified entries in this case, so the "for all items" above could be modified to "for all updated items". But.. The command's behavior now is modified slightly: unmerged entries that match $path, but not updated by $tree, are now NOT touched. Although this should be considered a bug fix, not a regression. A new test is added for this change. And while at there, free ps_matched after use. The following command is tested on webkit, 215k entries. The pattern is chosen mainly to make match_pathspec sweat: git checkout -- "*[a-zA-Z]*[a-zA-Z]*[a-zA-Z]*" before after real 0m3.493s 0m2.737s user 0m2.239s 0m1.586s sys 0m1.252s 0m1.151s Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-27 13:58:21 +08:00
}
free(ps_matched);
/* "checkout -m path" to recreate conflicted state */
if (opts->merge)
checkout: avoid unnecessary match_pathspec calls In checkout_paths() we do this - for all updated items, call match_pathspec - for all items, call match_pathspec (inside unmerge_cache) - for all items, call match_pathspec (for showing "path .. is unmerged) - for updated items, call match_pathspec and update paths That's a lot of duplicate match_pathspec(s) and the function is not exactly cheap to be called so many times, especially on large indexes. This patch makes it call match_pathspec once per updated index entry, save the result in ce_flags and reuse the results in the following loops. The changes in 0a1283b (checkout $tree $path: do not clobber local changes in $path not in $tree - 2011-09-30) limit the affected paths to ones we read from $tree. We do not do anything to other modified entries in this case, so the "for all items" above could be modified to "for all updated items". But.. The command's behavior now is modified slightly: unmerged entries that match $path, but not updated by $tree, are now NOT touched. Although this should be considered a bug fix, not a regression. A new test is added for this change. And while at there, free ps_matched after use. The following command is tested on webkit, 215k entries. The pattern is chosen mainly to make match_pathspec sweat: git checkout -- "*[a-zA-Z]*[a-zA-Z]*[a-zA-Z]*" before after real 0m3.493s 0m2.737s user 0m2.239s 0m1.586s sys 0m1.252s 0m1.151s Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-27 13:58:21 +08:00
unmerge_marked_index(&the_index);
/* Any unmerged paths? */
for (pos = 0; pos < active_nr; pos++) {
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 23:29:00 +08:00
const struct cache_entry *ce = active_cache[pos];
checkout: avoid unnecessary match_pathspec calls In checkout_paths() we do this - for all updated items, call match_pathspec - for all items, call match_pathspec (inside unmerge_cache) - for all items, call match_pathspec (for showing "path .. is unmerged) - for updated items, call match_pathspec and update paths That's a lot of duplicate match_pathspec(s) and the function is not exactly cheap to be called so many times, especially on large indexes. This patch makes it call match_pathspec once per updated index entry, save the result in ce_flags and reuse the results in the following loops. The changes in 0a1283b (checkout $tree $path: do not clobber local changes in $path not in $tree - 2011-09-30) limit the affected paths to ones we read from $tree. We do not do anything to other modified entries in this case, so the "for all items" above could be modified to "for all updated items". But.. The command's behavior now is modified slightly: unmerged entries that match $path, but not updated by $tree, are now NOT touched. Although this should be considered a bug fix, not a regression. A new test is added for this change. And while at there, free ps_matched after use. The following command is tested on webkit, 215k entries. The pattern is chosen mainly to make match_pathspec sweat: git checkout -- "*[a-zA-Z]*[a-zA-Z]*[a-zA-Z]*" before after real 0m3.493s 0m2.737s user 0m2.239s 0m1.586s sys 0m1.252s 0m1.151s Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-27 13:58:21 +08:00
if (ce->ce_flags & CE_MATCHED) {
if (!ce_stage(ce))
continue;
if (opts->force) {
warning(_("path '%s' is unmerged"), ce->name);
} else if (opts->writeout_stage) {
errs |= check_stage(opts->writeout_stage, ce, pos);
} else if (opts->merge) {
errs |= check_stages((1<<2) | (1<<3), ce, pos);
} else {
errs = 1;
error(_("path '%s' is unmerged"), ce->name);
}
pos = skip_same_name(ce, pos) - 1;
}
}
if (errs)
return 1;
/* Now we are committed to check them out */
state.force = 1;
state.refresh_cache = 1;
state.istate = &the_index;
enable_delayed_checkout(&state);
for (pos = 0; pos < active_nr; pos++) {
struct cache_entry *ce = active_cache[pos];
checkout: avoid unnecessary match_pathspec calls In checkout_paths() we do this - for all updated items, call match_pathspec - for all items, call match_pathspec (inside unmerge_cache) - for all items, call match_pathspec (for showing "path .. is unmerged) - for updated items, call match_pathspec and update paths That's a lot of duplicate match_pathspec(s) and the function is not exactly cheap to be called so many times, especially on large indexes. This patch makes it call match_pathspec once per updated index entry, save the result in ce_flags and reuse the results in the following loops. The changes in 0a1283b (checkout $tree $path: do not clobber local changes in $path not in $tree - 2011-09-30) limit the affected paths to ones we read from $tree. We do not do anything to other modified entries in this case, so the "for all items" above could be modified to "for all updated items". But.. The command's behavior now is modified slightly: unmerged entries that match $path, but not updated by $tree, are now NOT touched. Although this should be considered a bug fix, not a regression. A new test is added for this change. And while at there, free ps_matched after use. The following command is tested on webkit, 215k entries. The pattern is chosen mainly to make match_pathspec sweat: git checkout -- "*[a-zA-Z]*[a-zA-Z]*[a-zA-Z]*" before after real 0m3.493s 0m2.737s user 0m2.239s 0m1.586s sys 0m1.252s 0m1.151s Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-03-27 13:58:21 +08:00
if (ce->ce_flags & CE_MATCHED) {
if (!ce_stage(ce)) {
errs |= checkout_entry(ce, &state, NULL);
continue;
}
if (opts->writeout_stage)
errs |= checkout_stage(opts->writeout_stage, ce, pos, &state);
else if (opts->merge)
errs |= checkout_merged(pos, &state);
pos = skip_same_name(ce, pos) - 1;
}
}
errs |= finish_delayed_checkout(&state);
if (write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
die(_("unable to write new index file"));
read_ref_full("HEAD", 0, &rev, NULL);
Convert lookup_commit* to struct object_id Convert lookup_commit, lookup_commit_or_die, lookup_commit_reference, and lookup_commit_reference_gently to take struct object_id arguments. Introduce a temporary in parse_object buffer in order to convert this function. This is required since in order to convert parse_object and parse_object_buffer, lookup_commit_reference_gently and lookup_commit_or_die would need to be converted. Not introducing a temporary would therefore require that lookup_commit_or_die take a struct object_id *, but lookup_commit would take unsigned char *, leaving a confusing and hard-to-use interface. parse_object_buffer will lose this temporary in a later patch. This commit was created with manual changes to commit.c, commit.h, and object.c, plus the following semantic patch: @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1.hash, E2) + lookup_commit_reference_gently(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1->hash, E2) + lookup_commit_reference_gently(E1, E2) @@ expression E1; @@ - lookup_commit_reference(E1.hash) + lookup_commit_reference(&E1) @@ expression E1; @@ - lookup_commit_reference(E1->hash) + lookup_commit_reference(E1) @@ expression E1; @@ - lookup_commit(E1.hash) + lookup_commit(&E1) @@ expression E1; @@ - lookup_commit(E1->hash) + lookup_commit(E1) @@ expression E1, E2; @@ - lookup_commit_or_die(E1.hash, E2) + lookup_commit_or_die(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_or_die(E1->hash, E2) + lookup_commit_or_die(E1, E2) Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-07 06:10:10 +08:00
head = lookup_commit_reference_gently(&rev, 1);
errs |= post_checkout_hook(head, head, 0);
return errs;
}
static void show_local_changes(struct object *head,
const struct diff_options *opts)
{
struct rev_info rev;
/* I think we want full paths, even if we're in a subdirectory. */
init_revisions(&rev, NULL);
rev.diffopt.flags = opts->flags;
rev.diffopt.output_format |= DIFF_FORMAT_NAME_STATUS;
diff_setup_done(&rev.diffopt);
add_pending_object(&rev, head, NULL);
run_diff_index(&rev, 0);
}
static void describe_detached_head(const char *msg, struct commit *commit)
{
struct strbuf sb = STRBUF_INIT;
if (!parse_commit(commit))
pp_commit_easy(CMIT_FMT_ONELINE, commit, &sb);
if (print_sha1_ellipsis()) {
fprintf(stderr, "%s %s... %s\n", msg,
find_unique_abbrev(commit->object.oid.hash, DEFAULT_ABBREV), sb.buf);
} else {
fprintf(stderr, "%s %s %s\n", msg,
find_unique_abbrev(commit->object.oid.hash, DEFAULT_ABBREV), sb.buf);
}
strbuf_release(&sb);
}
static int reset_tree(struct tree *tree, const struct checkout_opts *o,
int worktree, int *writeout_error)
{
struct unpack_trees_options opts;
struct tree_desc tree_desc;
memset(&opts, 0, sizeof(opts));
opts.head_idx = -1;
opts.update = worktree;
opts.skip_unmerged = !worktree;
opts.reset = 1;
opts.merge = 1;
opts.fn = oneway_merge;
opts.verbose_update = o->show_progress;
opts.src_index = &the_index;
opts.dst_index = &the_index;
parse_tree(tree);
init_tree_desc(&tree_desc, tree->buffer, tree->size);
switch (unpack_trees(1, &tree_desc, &opts)) {
case -2:
*writeout_error = 1;
/*
* We return 0 nevertheless, as the index is all right
* and more importantly we have made best efforts to
* update paths in the work tree, and we cannot revert
* them.
*/
consistently use "fallthrough" comments in switches Gcc 7 adds -Wimplicit-fallthrough, which can warn when a switch case falls through to the next case. The general idea is that the compiler can't tell if this was intentional or not, so you should annotate any intentional fall-throughs as such, leaving it to complain about any unannotated ones. There's a GNU __attribute__ which can be used for annotation, but of course we'd have to #ifdef it away on non-gcc compilers. Gcc will also recognize specially-formatted comments, which matches our current practice. Let's extend that practice to all of the unannotated sites (which I did look over and verify that they were behaving as intended). Ideally in each case we'd actually give some reasons in the comment about why we're falling through, or what we're falling through to. And gcc does support that with -Wimplicit-fallthrough=2, which relaxes the comment pattern matching to anything that contains "fallthrough" (or a variety of spelling variants). However, this isn't the default for -Wimplicit-fallthrough, nor for -Wextra. In the name of simplicity, it's probably better for us to support the default level, which requires "fallthrough" to be the only thing in the comment (modulo some window dressing like "else" and some punctuation; see the gcc manual for the complete set of patterns). This patch suppresses all warnings due to -Wimplicit-fallthrough. We might eventually want to add that to the DEVELOPER Makefile knob, but we should probably wait until gcc 7 is more widely adopted (since earlier versions will complain about the unknown warning type). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-09-21 14:25:41 +08:00
/* fallthrough */
case 0:
return 0;
default:
return 128;
}
}
struct branch_info {
const char *name; /* The short name used */
const char *path; /* The full name of a real branch */
struct commit *commit; /* The named commit */
/*
* if not null the branch is detached because it's already
* checked out in this checkout
*/
char *checkout;
};
static void setup_branch_path(struct branch_info *branch)
{
struct strbuf buf = STRBUF_INIT;
strbuf_branchname(&buf, branch->name, INTERPRET_BRANCH_LOCAL);
if (strcmp(buf.buf, branch->name))
branch->name = xstrdup(buf.buf);
strbuf_splice(&buf, 0, 0, "refs/heads/", 11);
branch->path = strbuf_detach(&buf, NULL);
}
static int merge_working_tree(const struct checkout_opts *opts,
struct branch_info *old_branch_info,
struct branch_info *new_branch_info,
int *writeout_error)
{
int ret;
struct lock_file lock_file = LOCK_INIT;
hold_locked_index(&lock_file, LOCK_DIE_ON_ERROR);
if (read_cache_preload(NULL) < 0)
return error(_("index file corrupt"));
resolve_undo_clear();
if (opts->force) {
ret = reset_tree(new_branch_info->commit->tree, opts, 1, writeout_error);
if (ret)
return ret;
} else {
struct tree_desc trees[2];
struct tree *tree;
struct unpack_trees_options topts;
memset(&topts, 0, sizeof(topts));
topts.head_idx = -1;
topts.src_index = &the_index;
topts.dst_index = &the_index;
setup_unpack_trees_porcelain(&topts, "checkout");
unpack-trees: allow Porcelain to give different error messages The plumbing output is sacred as it is an API. We _could_ change it if it is broken in such a way that it cannot convey necessary information fully, but we just do not _reword_ for the sake of rewording. If somebody does not like it, s/he is complaining too late. S/he should have been here in early May 2005 and make the language used by the API closer to what humans read. S/he wasn't here. Too bad, and it is too late. And people who complain should look at a bigger picture. Look at what was suggested by one of them and think for five seconds: $ git checkout mytopic -fatal: Entry 'frotz' not uptodate. Cannot merge. +fatal: Entry 'frotz' has local changes. Cannot merge. If you do not see something wrong with this output, your brain has already been rotten with use of git for too long a time. Nobody asked us to "merge" but why are we talking about "Cannot merge"? This patch introduces a mechanism to allow Porcelains to specify messages that are different from the ones that is given by the underlying plumbing implementation of read-tree, so that we can reword the message Porcelains give without disrupting the output from the plumbing. $ git-checkout pu error: You have local changes to 'Makefile'; cannot switch branches. There are other places that ask unpack_trees() to n-way merge, detect issues and let it issue error message on its own, but I did this as a demonstration and replaced only one message. Yes I know about C99 structure initializers. I'd love to use them but we try to be nice to compilers without it. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-05-18 03:03:49 +08:00
refresh_cache(REFRESH_QUIET);
if (unmerged_cache()) {
error(_("you need to resolve your current index first"));
return 1;
}
/* 2-way merge to the new branch */
topts.initial_checkout = is_cache_unborn();
topts.update = 1;
topts.merge = 1;
topts.gently = opts->merge && old_branch_info->commit;
topts.verbose_update = opts->show_progress;
topts.fn = twoway_merge;
if (opts->overwrite_ignore) {
topts.dir = xcalloc(1, sizeof(*topts.dir));
topts.dir->flags |= DIR_SHOW_IGNORED;
setup_standard_excludes(topts.dir);
}
tree = parse_tree_indirect(old_branch_info->commit ?
&old_branch_info->commit->object.oid :
the_hash_algo->empty_tree);
init_tree_desc(&trees[0], tree->buffer, tree->size);
tree = parse_tree_indirect(&new_branch_info->commit->object.oid);
init_tree_desc(&trees[1], tree->buffer, tree->size);
ret = unpack_trees(2, trees, &topts);
if (ret == -1) {
/*
* Unpack couldn't do a trivial merge; either
* give up or do a real merge, depending on
* whether the merge flag was used.
*/
struct tree *result;
struct tree *work;
struct merge_options o;
if (!opts->merge)
return 1;
/*
* Without old_branch_info->commit, the below is the same as
* the two-tree unpack we already tried and failed.
*/
if (!old_branch_info->commit)
return 1;
/* Do more real merge */
/*
* We update the index fully, then write the
* tree from the index, then merge the new
* branch with the current tree, with the old
* branch as the base. Then we reset the index
* (but not the working tree) to the new
* branch, leaving the working tree as the
* merged version, but skipping unmerged
* entries in the index.
*/
add_files_to_cache(NULL, NULL, 0);
/*
* NEEDSWORK: carrying over local changes
* when branches have different end-of-line
* normalization (or clean+smudge rules) is
* a pain; plumb in an option to set
* o.renormalize?
*/
init_merge_options(&o);
o.verbosity = 0;
work = write_tree_from_memory(&o);
ret = reset_tree(new_branch_info->commit->tree, opts, 1,
writeout_error);
if (ret)
return ret;
o.ancestor = old_branch_info->name;
o.branch1 = new_branch_info->name;
o.branch2 = "local";
ret = merge_trees(&o, new_branch_info->commit->tree, work,
old_branch_info->commit->tree, &result);
prepare the builtins for a libified merge_recursive() Previously, callers of merge_trees() or merge_recursive() expected that code to die() with an error message. This used to be okay because we called those commands from scripts, and had a chance to print out a message in case the command failed fatally (read: with exit code 128). As scripting incurs its own set of problems (portability, speed, idiosyncrasies of different shells, limited data structures leading to inefficient code), we are converting more and more of these scripts into builtins, using library functions directly. We already tried to use merge_recursive() directly in the builtin git-am, for example. Unfortunately, we had to roll it back temporarily because some of the code in merge-recursive.c still deemed it okay to call die(), when the builtin am code really wanted to print out a useful advice after the merge failed fatally. In the next commits, we want to fix that. The code touched by this commit expected merge_trees() to die() with some useful message when there is an error condition, but merge_trees() is going to be improved by converting all die() calls to return error() instead (i.e. return value -1 after printing out the message as before), so that the caller can react more flexibly. This is a step to prepare for the version of merge_trees() that no longer dies, even if we just imitate the previous behavior by calling exit(128): this is what callers of e.g. `git merge` have come to expect. Note that the callers of the sequencer (revert and cherry-pick) already fail fast even for the return value -1; The only difference is that they now get a chance to say "<command> failed". A caller of merge_trees() might want handle error messages themselves (or even suppress them). As this patch is already complex enough, we leave that change for a later patch. Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-07-27 00:06:02 +08:00
if (ret < 0)
exit(128);
ret = reset_tree(new_branch_info->commit->tree, opts, 0,
writeout_error);
strbuf_release(&o.obuf);
if (ret)
return ret;
}
}
if (!active_cache_tree)
active_cache_tree = cache_tree();
if (!cache_tree_fully_valid(active_cache_tree))
cache_tree_update(&the_index, WRITE_TREE_SILENT | WRITE_TREE_REPAIR);
if (write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
die(_("unable to write new index file"));
if (!opts->force && !opts->quiet)
show_local_changes(&new_branch_info->commit->object, &opts->diff_options);
return 0;
}
static void report_tracking(struct branch_info *new_branch_info)
{
struct strbuf sb = STRBUF_INIT;
struct branch *branch = branch_get(new_branch_info->name);
if (!format_tracking_info(branch, &sb, AHEAD_BEHIND_FULL))
return;
fputs(sb.buf, stdout);
strbuf_release(&sb);
}
static void update_refs_for_switch(const struct checkout_opts *opts,
struct branch_info *old_branch_info,
struct branch_info *new_branch_info)
{
struct strbuf msg = STRBUF_INIT;
const char *old_desc, *reflog_msg;
if (opts->new_branch) {
if (opts->new_orphan_branch) {
char *refname;
refname = mkpathdup("refs/heads/%s", opts->new_orphan_branch);
if (opts->new_branch_log &&
!should_autocreate_reflog(refname)) {
int ret;
struct strbuf err = STRBUF_INIT;
ret = safe_create_reflog(refname, 1, &err);
if (ret) {
fprintf(stderr, _("Can not do reflog for '%s': %s\n"),
opts->new_orphan_branch, err.buf);
strbuf_release(&err);
free(refname);
return;
}
strbuf_release(&err);
}
free(refname);
}
else
create_branch(opts->new_branch, new_branch_info->name,
opts->new_branch_force ? 1 : 0,
opts->new_branch_force ? 1 : 0,
opts->new_branch_log,
opts->quiet,
opts->track);
new_branch_info->name = opts->new_branch;
setup_branch_path(new_branch_info);
}
old_desc = old_branch_info->name;
if (!old_desc && old_branch_info->commit)
old_desc = oid_to_hex(&old_branch_info->commit->object.oid);
reflog_msg = getenv("GIT_REFLOG_ACTION");
if (!reflog_msg)
strbuf_addf(&msg, "checkout: moving from %s to %s",
old_desc ? old_desc : "(invalid)", new_branch_info->name);
else
strbuf_insert(&msg, 0, reflog_msg, strlen(reflog_msg));
if (!strcmp(new_branch_info->name, "HEAD") && !new_branch_info->path && !opts->force_detach) {
/* Nothing to do. */
} else if (opts->force_detach || !new_branch_info->path) { /* No longer on any branch. */
update_ref(msg.buf, "HEAD", &new_branch_info->commit->object.oid, NULL,
REF_NO_DEREF, UPDATE_REFS_DIE_ON_ERR);
if (!opts->quiet) {
if (old_branch_info->path &&
advice_detached_head && !opts->force_detach)
detach_advice(new_branch_info->name);
describe_detached_head(_("HEAD is now at"), new_branch_info->commit);
}
} else if (new_branch_info->path) { /* Switch branches. */
if (create_symref("HEAD", new_branch_info->path, msg.buf) < 0)
die(_("unable to update HEAD"));
if (!opts->quiet) {
if (old_branch_info->path && !strcmp(new_branch_info->path, old_branch_info->path)) {
if (opts->new_branch_force)
fprintf(stderr, _("Reset branch '%s'\n"),
new_branch_info->name);
else
fprintf(stderr, _("Already on '%s'\n"),
new_branch_info->name);
} else if (opts->new_branch) {
if (opts->branch_exists)
fprintf(stderr, _("Switched to and reset branch '%s'\n"), new_branch_info->name);
else
fprintf(stderr, _("Switched to a new branch '%s'\n"), new_branch_info->name);
} else {
fprintf(stderr, _("Switched to branch '%s'\n"),
new_branch_info->name);
}
}
if (old_branch_info->path && old_branch_info->name) {
if (!ref_exists(old_branch_info->path) && reflog_exists(old_branch_info->path))
delete_reflog(old_branch_info->path);
}
}
remove_branch_state();
strbuf_release(&msg);
if (!opts->quiet &&
(new_branch_info->path || (!opts->force_detach && !strcmp(new_branch_info->name, "HEAD"))))
report_tracking(new_branch_info);
}
static int add_pending_uninteresting_ref(const char *refname,
const struct object_id *oid,
int flags, void *cb_data)
{
add_pending_oid(cb_data, refname, oid, UNINTERESTING);
return 0;
}
static void describe_one_orphan(struct strbuf *sb, struct commit *commit)
{
strbuf_addstr(sb, " ");
strbuf_add_unique_abbrev(sb, &commit->object.oid, DEFAULT_ABBREV);
strbuf_addch(sb, ' ');
if (!parse_commit(commit))
pp_commit_easy(CMIT_FMT_ONELINE, commit, sb);
strbuf_addch(sb, '\n');
}
#define ORPHAN_CUTOFF 4
static void suggest_reattach(struct commit *commit, struct rev_info *revs)
{
struct commit *c, *last = NULL;
struct strbuf sb = STRBUF_INIT;
int lost = 0;
while ((c = get_revision(revs)) != NULL) {
if (lost < ORPHAN_CUTOFF)
describe_one_orphan(&sb, c);
last = c;
lost++;
}
if (ORPHAN_CUTOFF < lost) {
int more = lost - ORPHAN_CUTOFF;
if (more == 1)
describe_one_orphan(&sb, last);
else
strbuf_addf(&sb, _(" ... and %d more.\n"), more);
}
fprintf(stderr,
Q_(
/* The singular version */
"Warning: you are leaving %d commit behind, "
"not connected to\n"
"any of your branches:\n\n"
"%s\n",
/* The plural version */
"Warning: you are leaving %d commits behind, "
"not connected to\n"
"any of your branches:\n\n"
"%s\n",
/* Give ngettext() the count */
lost),
lost,
sb.buf);
strbuf_release(&sb);
if (advice_detached_head)
fprintf(stderr,
Q_(
/* The singular version */
"If you want to keep it by creating a new branch, "
"this may be a good time\nto do so with:\n\n"
" git branch <new-branch-name> %s\n\n",
/* The plural version */
"If you want to keep them by creating a new branch, "
"this may be a good time\nto do so with:\n\n"
" git branch <new-branch-name> %s\n\n",
/* Give ngettext() the count */
lost),
find_unique_abbrev(commit->object.oid.hash, DEFAULT_ABBREV));
}
/*
* We are about to leave commit that was at the tip of a detached
* HEAD. If it is not reachable from any ref, this is the last chance
* for the user to do so without resorting to reflog.
*/
static void orphaned_commit_warning(struct commit *old_commit, struct commit *new_commit)
{
struct rev_info revs;
struct object *object = &old_commit->object;
init_revisions(&revs, NULL);
setup_revisions(0, NULL, &revs, NULL);
object->flags &= ~UNINTERESTING;
add_pending_object(&revs, object, oid_to_hex(&object->oid));
for_each_ref(add_pending_uninteresting_ref, &revs);
add_pending_oid(&revs, "HEAD", &new_commit->object.oid, UNINTERESTING);
if (prepare_revision_walk(&revs))
die(_("internal error in revision walk"));
if (!(old_commit->object.flags & UNINTERESTING))
suggest_reattach(old_commit, &revs);
else
describe_detached_head(_("Previous HEAD position was"), old_commit);
/* Clean up objects used, as they will be reused. */
clear_commit_marks_all(ALL_REV_FLAGS);
}
static int switch_branches(const struct checkout_opts *opts,
struct branch_info *new_branch_info)
{
int ret = 0;
struct branch_info old_branch_info;
void *path_to_free;
struct object_id rev;
int flag, writeout_error = 0;
memset(&old_branch_info, 0, sizeof(old_branch_info));
old_branch_info.path = path_to_free = resolve_refdup("HEAD", 0, &rev, &flag);
if (old_branch_info.path)
old_branch_info.commit = lookup_commit_reference_gently(&rev, 1);
if (!(flag & REF_ISSYMREF))
old_branch_info.path = NULL;
if (old_branch_info.path)
skip_prefix(old_branch_info.path, "refs/heads/", &old_branch_info.name);
if (!new_branch_info->name) {
new_branch_info->name = "HEAD";
new_branch_info->commit = old_branch_info.commit;
if (!new_branch_info->commit)
die(_("You are on a branch yet to be born"));
parse_commit_or_die(new_branch_info->commit);
}
ret = merge_working_tree(opts, &old_branch_info, new_branch_info, &writeout_error);
if (ret) {
free(path_to_free);
return ret;
}
if (!opts->quiet && !old_branch_info.path && old_branch_info.commit && new_branch_info->commit != old_branch_info.commit)
orphaned_commit_warning(old_branch_info.commit, new_branch_info->commit);
update_refs_for_switch(opts, &old_branch_info, new_branch_info);
ret = post_checkout_hook(old_branch_info.commit, new_branch_info->commit, 1);
free(path_to_free);
return ret || writeout_error;
}
static int git_checkout_config(const char *var, const char *value, void *cb)
{
if (!strcmp(var, "diff.ignoresubmodules")) {
struct checkout_opts *opts = cb;
handle_ignore_submodules_arg(&opts->diff_options, value);
return 0;
}
if (starts_with(var, "submodule."))
return git_default_submodule_config(var, value, NULL);
return git_xmerge_config(var, value, NULL);
}
static int parse_branchname_arg(int argc, const char **argv,
int dwim_new_local_branch_ok,
struct branch_info *new_branch_info,
struct checkout_opts *opts,
struct object_id *rev)
{
struct tree **source_tree = &opts->source_tree;
const char **new_branch = &opts->new_branch;
int argcount = 0;
struct object_id branch_rev;
const char *arg;
int dash_dash_pos;
int has_dash_dash = 0;
int i;
/*
* case 1: git checkout <ref> -- [<paths>]
*
* <ref> must be a valid tree, everything after the '--' must be
* a path.
*
* case 2: git checkout -- [<paths>]
*
* everything after the '--' must be paths.
*
* case 3: git checkout <something> [--]
*
* (a) If <something> is a commit, that is to
* switch to the branch or detach HEAD at it. As a special case,
* if <something> is A...B (missing A or B means HEAD but you can
* omit at most one side), and if there is a unique merge base
* between A and B, A...B names that merge base.
*
* (b) If <something> is _not_ a commit, either "--" is present
* or <something> is not a path, no -t or -b was given, and
* and there is a tracking branch whose name is <something>
* in one and only one remote, then this is a short-hand to
* fork local <something> from that remote-tracking branch.
*
* (c) Otherwise, if "--" is present, treat it like case (1).
*
* (d) Otherwise :
* - if it's a reference, treat it like case (1)
* - else if it's a path, treat it like case (2)
* - else: fail.
*
* case 4: git checkout <something> <paths>
*
* The first argument must not be ambiguous.
* - If it's *only* a reference, treat it like case (1).
* - If it's only a path, treat it like case (2).
* - else: fail.
*
*/
if (!argc)
return 0;
arg = argv[0];
dash_dash_pos = -1;
for (i = 0; i < argc; i++) {
if (!strcmp(argv[i], "--")) {
dash_dash_pos = i;
break;
}
}
if (dash_dash_pos == 0)
return 1; /* case (2) */
else if (dash_dash_pos == 1)
has_dash_dash = 1; /* case (3) or (1) */
else if (dash_dash_pos >= 2)
die(_("only one reference expected, %d given."), dash_dash_pos);
if (!strcmp(arg, "-"))
arg = "@{-1}";
if (get_oid_mb(arg, rev)) {
/*
* Either case (3) or (4), with <something> not being
* a commit, or an attempt to use case (1) with an
* invalid ref.
*
* It's likely an error, but we need to find out if
* we should auto-create the branch, case (3).(b).
*/
int recover_with_dwim = dwim_new_local_branch_ok;
check_filename: tighten dwim-wildcard ambiguity When specifying both revisions and pathnames, we allow "<rev> -- <pathspec>" to be spelled without the "--" as long as it is not ambiguous. The original logic was something like: 1. Resolve each item with get_sha1(). If successful, we know it can be a <rev>. Verify that it _isn't_ a filename, using verify_non_filename(), and complain of ambiguity otherwise. 2. If get_sha1() didn't succeed, make sure that it _is_ a file, using verify_filename(). If not, complain that it is neither a <rev> nor a <pathspec>. Both verify_filename() and verify_non_filename() rely on check_filename(), which definitely said "yes, this is a file" or "no, it is not" using lstat(). Commit 28fcc0b (pathspec: avoid the need of "--" when wildcard is used, 2015-05-02) introduced a convenience feature: check_filename() will consider anything with wildcard meta-characters as a possible filename, without even checking the filesystem. This works well for case 2. For such a wildcard, we would previously have died and said "it is neither". Post-28fcc0b, we assume it's a pathspec and proceed. But it makes some instances of case 1 worse. We may have an extended sha1 expression that contains meta-characters (e.g., "HEAD^{/foo.*bar}"), and we now complain that it's also a filename, due to the wildcard characters (even though that wildcard would not match anything in the filesystem). One solution would be to actually expand the pathname and see if it matches anything on the filesystem. But that's potentially expensive, and we do not have to be so rigorous for this DWIM magic (if you want rigor, use "--"). Instead, we can just use different rules for cases 1 and 2. When we know something is a rev, we will complain only if it meets a much higher standard for "this is also a file"; namely that it actually exists in the filesystem. Case 2 remains the same: we use the looser "it could be a filename" standard introduced by 28fcc0b. We can accomplish this by pulling the wildcard logic out of check_filename() and putting it into verify_filename(). Its partner verify_non_filename() does not need a change, since check_filename() goes back to implementing the "higher standard". Besides these two callers of check_filename(), there is one other: git-checkout does a similar DWIM itself. It hits this code path only after get_sha1() has returned failure, making it case 2, which gets the special wildcard treatment. Note that we drop the tests in t2019 in favor of a more complete set in t6133. t2019 was not the right place for them (it's about refname ambiguity, not dwim parsing ambiguity), and the second test explicitly checked for the opposite result of the case we are fixing here (which didn't really make any sense; as shown by the test_must_fail in the test, it would only serve to annoy people). Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-02-11 05:14:46 +08:00
if (!has_dash_dash &&
(check_filename(opts->prefix, arg) || !no_wildcard(arg)))
recover_with_dwim = 0;
/*
* Accept "git checkout foo" and "git checkout foo --"
* as candidates for dwim.
*/
if (!(argc == 1 && !has_dash_dash) &&
!(argc == 2 && has_dash_dash))
recover_with_dwim = 0;
if (recover_with_dwim) {
checkout: Use remote refspecs when DWIMming tracking branches The DWIM mode of checkout allows you to run "git checkout foo" when there is no existing local ref or path called "foo", and there is exactly _one_ remote with a remote-tracking branch called "foo". Git will automatically create a new local branch called "foo" using the remote-tracking "foo" as its starting point and configured upstream. For example, consider the following unconventional (but perfectly valid) remote setup: [remote "origin"] fetch = refs/heads/*:refs/remotes/origin/* [remote "frotz"] fetch = refs/heads/*:refs/remotes/frotz/nitfol/* Case 1: Assume both "origin" and "frotz" have remote-tracking branches called "foo", at "refs/remotes/origin/foo" and "refs/remotes/frotz/nitfol/foo" respectively. In this case "git checkout foo" should fail, because there is more than one remote with a "foo" branch. Case 2: Assume only "frotz" have a remote-tracking branch called "foo". In this case "git checkout foo" should succeed, and create a local branch "foo" from "refs/remotes/frotz/nitfol/foo", using remote branch "foo" from "frotz" as its upstream. The current code hardcodes the assumption that all remote-tracking branches must match the "refs/remotes/$remote/*" pattern (which is true for remotes with "conventional" refspecs, but not true for the "frotz" remote above). When running "git checkout foo", the current code looks for exactly one ref matching "refs/remotes/*/foo", hence in the above example, it fails to find "refs/remotes/frotz/nitfol/foo", which causes it to fail both case #1 and #2. The better way to handle the above example is to actually study the fetch refspecs to deduce the candidate remote-tracking branches for "foo"; i.e. assume "foo" is a remote branch being fetched, and then map "refs/heads/foo" through the refspecs in order to get the corresponding remote-tracking branches "refs/remotes/origin/foo" and "refs/remotes/frotz/nitfol/foo". Finally we check which of these happens to exist in the local repo, and if there is exactly one, we have an unambiguous match for "git checkout foo", and may proceed. This fixes most of the failing tests introduced in the previous patch. Signed-off-by: Johan Herland <johan@herland.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-22 05:52:01 +08:00
const char *remote = unique_tracking_name(arg, rev);
if (remote) {
*new_branch = arg;
arg = remote;
/* DWIMmed to create local branch, case (3).(b) */
} else {
recover_with_dwim = 0;
}
}
if (!recover_with_dwim) {
if (has_dash_dash)
die(_("invalid reference: %s"), arg);
return argcount;
}
}
/* we can't end up being in (2) anymore, eat the argument */
argcount++;
argv++;
argc--;
new_branch_info->name = arg;
setup_branch_path(new_branch_info);
if (!check_refname_format(new_branch_info->path, 0) &&
!read_ref(new_branch_info->path, &branch_rev))
oidcpy(rev, &branch_rev);
else
new_branch_info->path = NULL; /* not an existing branch */
new_branch_info->commit = lookup_commit_reference_gently(rev, 1);
if (!new_branch_info->commit) {
/* not a commit */
*source_tree = parse_tree_indirect(rev);
} else {
parse_commit_or_die(new_branch_info->commit);
*source_tree = new_branch_info->commit->tree;
}
if (!*source_tree) /* case (1): want a tree */
die(_("reference is not a tree: %s"), arg);
if (!has_dash_dash) { /* case (3).(d) -> (1) */
/*
* Do not complain the most common case
* git checkout branch
* even if there happen to be a file called 'branch';
* it would be extremely annoying.
*/
if (argc)
verify_non_filename(opts->prefix, arg);
} else {
argcount++;
argv++;
argc--;
}
return argcount;
}
static int switch_unborn_to_new_branch(const struct checkout_opts *opts)
{
int status;
struct strbuf branch_ref = STRBUF_INIT;
if (!opts->new_branch)
die(_("You are on a branch yet to be born"));
strbuf_addf(&branch_ref, "refs/heads/%s", opts->new_branch);
status = create_symref("HEAD", branch_ref.buf, "checkout -b");
strbuf_release(&branch_ref);
if (!opts->quiet)
fprintf(stderr, _("Switched to a new branch '%s'\n"),
opts->new_branch);
return status;
}
static int checkout_branch(struct checkout_opts *opts,
struct branch_info *new_branch_info)
{
if (opts->pathspec.nr)
die(_("paths cannot be used with switching branches"));
if (opts->patch_mode)
die(_("'%s' cannot be used with switching branches"),
"--patch");
if (opts->writeout_stage)
die(_("'%s' cannot be used with switching branches"),
"--ours/--theirs");
if (opts->force && opts->merge)
die(_("'%s' cannot be used with '%s'"), "-f", "-m");
if (opts->force_detach && opts->new_branch)
die(_("'%s' cannot be used with '%s'"),
"--detach", "-b/-B/--orphan");
if (opts->new_orphan_branch) {
if (opts->track != BRANCH_TRACK_UNSPECIFIED)
die(_("'%s' cannot be used with '%s'"), "--orphan", "-t");
} else if (opts->force_detach) {
if (opts->track != BRANCH_TRACK_UNSPECIFIED)
die(_("'%s' cannot be used with '%s'"), "--detach", "-t");
} else if (opts->track == BRANCH_TRACK_UNSPECIFIED)
opts->track = git_branch_track;
if (new_branch_info->name && !new_branch_info->commit)
die(_("Cannot switch branch to a non-commit '%s'"),
new_branch_info->name);
if (new_branch_info->path && !opts->force_detach && !opts->new_branch &&
!opts->ignore_other_worktrees) {
int flag;
char *head_ref = resolve_refdup("HEAD", 0, NULL, &flag);
if (head_ref &&
(!(flag & REF_ISSYMREF) || strcmp(head_ref, new_branch_info->path)))
die_if_checked_out(new_branch_info->path, 1);
free(head_ref);
}
if (!new_branch_info->commit && opts->new_branch) {
struct object_id rev;
int flag;
if (!read_ref_full("HEAD", 0, &rev, &flag) &&
(flag & REF_ISSYMREF) && is_null_oid(&rev))
return switch_unborn_to_new_branch(opts);
}
return switch_branches(opts, new_branch_info);
}
int cmd_checkout(int argc, const char **argv, const char *prefix)
{
struct checkout_opts opts;
struct branch_info new_branch_info;
char *conflict_style = NULL;
int dwim_new_local_branch = 1;
struct option options[] = {
OPT__QUIET(&opts.quiet, N_("suppress progress reporting")),
OPT_STRING('b', NULL, &opts.new_branch, N_("branch"),
N_("create and checkout a new branch")),
OPT_STRING('B', NULL, &opts.new_branch_force, N_("branch"),
N_("create/reset and checkout a branch")),
OPT_BOOL('l', NULL, &opts.new_branch_log, N_("create reflog for new branch")),
OPT_BOOL(0, "detach", &opts.force_detach, N_("detach HEAD at named commit")),
OPT_SET_INT('t', "track", &opts.track, N_("set upstream info for new branch"),
BRANCH_TRACK_EXPLICIT),
OPT_STRING(0, "orphan", &opts.new_orphan_branch, N_("new-branch"), N_("new unparented branch")),
OPT_SET_INT('2', "ours", &opts.writeout_stage, N_("checkout our version for unmerged files"),
2),
OPT_SET_INT('3', "theirs", &opts.writeout_stage, N_("checkout their version for unmerged files"),
3),
OPT__FORCE(&opts.force, N_("force checkout (throw away local modifications)")),
OPT_BOOL('m', "merge", &opts.merge, N_("perform a 3-way merge with the new branch")),
OPT_BOOL(0, "overwrite-ignore", &opts.overwrite_ignore, N_("update ignored files (default)")),
OPT_STRING(0, "conflict", &conflict_style, N_("style"),
N_("conflict style (merge or diff3)")),
OPT_BOOL('p', "patch", &opts.patch_mode, N_("select hunks interactively")),
OPT_BOOL(0, "ignore-skip-worktree-bits", &opts.ignore_skipworktree,
N_("do not limit pathspecs to sparse entries only")),
OPT_HIDDEN_BOOL(0, "guess", &dwim_new_local_branch,
N_("second guess 'git checkout <no-such-branch>'")),
OPT_BOOL(0, "ignore-other-worktrees", &opts.ignore_other_worktrees,
N_("do not check if another worktree is holding the given ref")),
{ OPTION_CALLBACK, 0, "recurse-submodules", NULL,
"checkout", "control recursive updating of submodules",
PARSE_OPT_OPTARG, option_parse_recurse_submodules_worktree_updater },
OPT_BOOL(0, "progress", &opts.show_progress, N_("force progress reporting")),
OPT_END(),
};
memset(&opts, 0, sizeof(opts));
memset(&new_branch_info, 0, sizeof(new_branch_info));
opts.overwrite_ignore = 1;
opts.prefix = prefix;
opts.show_progress = -1;
git_config(git_checkout_config, &opts);
opts.track = BRANCH_TRACK_UNSPECIFIED;
argc = parse_options(argc, argv, prefix, options, checkout_usage,
PARSE_OPT_KEEP_DASHDASH);
if (opts.show_progress < 0) {
if (opts.quiet)
opts.show_progress = 0;
else
opts.show_progress = isatty(2);
}
if (conflict_style) {
opts.merge = 1; /* implied */
git_xmerge_config("merge.conflictstyle", conflict_style, NULL);
}
if ((!!opts.new_branch + !!opts.new_branch_force + !!opts.new_orphan_branch) > 1)
die(_("-b, -B and --orphan are mutually exclusive"));
/*
* From here on, new_branch will contain the branch to be checked out,
* and new_branch_force and new_orphan_branch will tell us which one of
* -b/-B/--orphan is being used.
*/
if (opts.new_branch_force)
opts.new_branch = opts.new_branch_force;
if (opts.new_orphan_branch)
opts.new_branch = opts.new_orphan_branch;
/* --track without -b/-B/--orphan should DWIM */
if (opts.track != BRANCH_TRACK_UNSPECIFIED && !opts.new_branch) {
const char *argv0 = argv[0];
if (!argc || !strcmp(argv0, "--"))
die (_("--track needs a branch name"));
skip_prefix(argv0, "refs/", &argv0);
skip_prefix(argv0, "remotes/", &argv0);
argv0 = strchr(argv0, '/');
if (!argv0 || !argv0[1])
die (_("Missing branch name; try -b"));
opts.new_branch = argv0 + 1;
}
/*
* Extract branch name from command line arguments, so
* all that is left is pathspecs.
*
* Handle
*
* 1) git checkout <tree> -- [<paths>]
* 2) git checkout -- [<paths>]
* 3) git checkout <something> [<paths>]
*
* including "last branch" syntax and DWIM-ery for names of
* remote branches, erroring out for invalid or ambiguous cases.
*/
if (argc) {
struct object_id rev;
int dwim_ok =
!opts.patch_mode &&
dwim_new_local_branch &&
opts.track == BRANCH_TRACK_UNSPECIFIED &&
!opts.new_branch;
int n = parse_branchname_arg(argc, argv, dwim_ok,
&new_branch_info, &opts, &rev);
argv += n;
argc -= n;
}
if (argc) {
parse_pathspec(&opts.pathspec, 0,
opts.patch_mode ? PATHSPEC_PREFIX_ORIGIN : 0,
prefix, argv);
if (!opts.pathspec.nr)
die(_("invalid path specification"));
/*
* Try to give more helpful suggestion.
* new_branch && argc > 1 will be caught later.
*/
if (opts.new_branch && argc == 1)
usability: don't ask questions if no reply is required There has been a bug report by a corporate user that stated that "spelling mistake of stash followed by a yes prints character 'y' infinite times." This analysis was false. When the spelling of a command contains errors, the git program tries to help the user by providing candidates which are close to the unexisting command. E.g Git prints the following: git: 'stahs' is not a git command. See 'git --help'. Did you mean this? stash and then exits. The problem with this hint is that it is not formally indicated as an hint and the user is in fact encouraged to reply to the question, whereas the Git command is already finished. The user was unlucky enough that it was the command he was looking for, and replied "yes" on the command line, effectively launching the `yes` program. The initial error is that the Git programs, when launched in command-line mode (without interaction) must not ask questions, because these questions would normally require a user input as a reply that they won't handle indeed. That's a source of confusion on UX level. To improve the general usability of the Git suite, the following rule was applied: if the sentence * appears in a non-interactive session * is printed last before exit * is a question addressing the user ("you") the sentence is turned into affirmative and proposes the option. The basic rewording of the question sentences has been extended to other spots found in the source. Requested at https://github.com/git/git-scm.com/issues/999 by rpai1 Signed-off-by: Jean-Noel Avila <jn.avila@free.fr> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-11 20:06:32 +08:00
die(_("'%s' is not a commit and a branch '%s' cannot be created from it"),
argv[0], opts.new_branch);
if (opts.force_detach)
die(_("git checkout: --detach does not take a path argument '%s'"),
argv[0]);
if (1 < !!opts.writeout_stage + !!opts.force + !!opts.merge)
die(_("git checkout: --ours/--theirs, --force and --merge are incompatible when\n"
"checking out of the index."));
}
if (opts.new_branch) {
struct strbuf buf = STRBUF_INIT;
if (opts.new_branch_force)
opts.branch_exists = validate_branchname(opts.new_branch, &buf);
else
opts.branch_exists =
validate_new_branchname(opts.new_branch, &buf, 0);
strbuf_release(&buf);
}
UNLEAK(opts);
if (opts.patch_mode || opts.pathspec.nr)
return checkout_paths(&opts, new_branch_info.name);
else
return checkout_branch(&opts, &new_branch_info);
}