From ba84a797e76c27932e0b317c7ce54925e81093f7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 6 Jul 2006 10:16:22 -0700 Subject: builtin "git prune" This actually removes the objects to be pruned, unless you specify "-n" (at which point it will just tell you which files it would prune). This doesn't do the pack-file pruning that the shell-script used to do, but if somebody really wants to, they could add it easily enough. I wonder how useful it is, though, considering that "git repack -a -d" is just a lot more efficient and generates a better end result. Signed-off-by: Linus Torvalds Signed-off-by: Junio C Hamano diff --git a/Makefile b/Makefile index 588d925..04804c8 100644 --- a/Makefile +++ b/Makefile @@ -120,7 +120,7 @@ SCRIPT_SH = \ git-fetch.sh \ git-ls-remote.sh \ git-merge-one-file.sh git-parse-remote.sh \ - git-prune.sh git-pull.sh git-rebase.sh \ + git-pull.sh git-rebase.sh \ git-repack.sh git-request-pull.sh git-reset.sh \ git-resolve.sh git-revert.sh git-sh-setup.sh \ git-tag.sh git-verify-tag.sh \ @@ -174,7 +174,7 @@ BUILT_INS = git-log$X git-whatchanged$X git-show$X git-update-ref$X \ git-read-tree$X git-commit-tree$X git-write-tree$X \ git-apply$X git-show-branch$X git-diff-files$X git-update-index$X \ git-diff-index$X git-diff-stages$X git-diff-tree$X git-cat-file$X \ - git-fmt-merge-msg$X + git-fmt-merge-msg$X git-prune$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -230,7 +230,7 @@ BUILTIN_OBJS = \ builtin-apply.o builtin-show-branch.o builtin-diff-files.o \ builtin-diff-index.o builtin-diff-stages.o builtin-diff-tree.o \ builtin-cat-file.o builtin-mailsplit.o builtin-stripspace.o \ - builtin-update-ref.o builtin-fmt-merge-msg.o + builtin-update-ref.o builtin-fmt-merge-msg.o builtin-prune.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-prune.c b/builtin-prune.c new file mode 100644 index 0000000..ebdecee --- /dev/null +++ b/builtin-prune.c @@ -0,0 +1,259 @@ +#include "cache.h" +#include "refs.h" +#include "tag.h" +#include "commit.h" +#include "tree.h" +#include "blob.h" +#include "tree-walk.h" +#include "diff.h" +#include "revision.h" +#include "builtin.h" +#include "cache-tree.h" + +static const char prune_usage[] = "git prune [-n]"; +static int show_only = 0; +static struct rev_info revs; + +static int prune_object(char *path, const char *filename, const unsigned char *sha1) +{ + if (show_only) { + printf("would prune %s/%s\n", path, filename); + return 0; + } + unlink(mkpath("%s/%s", path, filename)); + rmdir(path); + return 0; +} + +static int prune_dir(int i, char *path) +{ + DIR *dir = opendir(path); + struct dirent *de; + + if (!dir) + return 0; + + while ((de = readdir(dir)) != NULL) { + char name[100]; + unsigned char sha1[20]; + int len = strlen(de->d_name); + + switch (len) { + case 2: + if (de->d_name[1] != '.') + break; + case 1: + if (de->d_name[0] != '.') + break; + continue; + case 38: + sprintf(name, "%02x", i); + memcpy(name+2, de->d_name, len+1); + if (get_sha1_hex(name, sha1) < 0) + break; + + /* + * Do we know about this object? + * It must have been reachable + */ + if (lookup_object(sha1)) + continue; + + prune_object(path, de->d_name, sha1); + continue; + } + fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name); + } + closedir(dir); + return 0; +} + +static void prune_object_dir(const char *path) +{ + int i; + for (i = 0; i < 256; i++) { + static char dir[4096]; + sprintf(dir, "%s/%02x", path, i); + prune_dir(i, dir); + } +} + +static void process_blob(struct blob *blob, + struct object_array *p, + struct name_path *path, + const char *name) +{ + struct object *obj = &blob->object; + + if (obj->flags & SEEN) + return; + obj->flags |= SEEN; + /* Nothing to do, really .. The blob lookup was the important part */ +} + +static void process_tree(struct tree *tree, + struct object_array *p, + struct name_path *path, + const char *name) +{ + struct object *obj = &tree->object; + struct tree_desc desc; + struct name_entry entry; + struct name_path me; + + if (obj->flags & SEEN) + return; + obj->flags |= SEEN; + if (parse_tree(tree) < 0) + die("bad tree object %s", sha1_to_hex(obj->sha1)); + name = strdup(name); + add_object(obj, p, path, name); + me.up = path; + me.elem = name; + me.elem_len = strlen(name); + + desc.buf = tree->buffer; + desc.size = tree->size; + + while (tree_entry(&desc, &entry)) { + if (S_ISDIR(entry.mode)) + process_tree(lookup_tree(entry.sha1), p, &me, entry.path); + else + process_blob(lookup_blob(entry.sha1), p, &me, entry.path); + } + free(tree->buffer); + tree->buffer = NULL; +} + +static void process_tag(struct tag *tag, struct object_array *p, const char *name) +{ + struct object *obj = &tag->object; + struct name_path me; + + if (obj->flags & SEEN) + return; + obj->flags |= SEEN; + + me.up = NULL; + me.elem = "tag:/"; + me.elem_len = 5; + + if (parse_tag(tag) < 0) + die("bad tag object %s", sha1_to_hex(obj->sha1)); + add_object(tag->tagged, p, NULL, name); +} + +static void walk_commit_list(struct rev_info *revs) +{ + int i; + struct commit *commit; + struct object_array objects = { 0, 0, NULL }; + + /* Walk all commits, process their trees */ + while ((commit = get_revision(revs)) != NULL) + process_tree(commit->tree, &objects, NULL, ""); + + /* Then walk all the pending objects, recursively processing them too */ + for (i = 0; i < revs->pending.nr; i++) { + struct object_array_entry *pending = revs->pending.objects + i; + struct object *obj = pending->item; + const char *name = pending->name; + if (obj->type == TYPE_TAG) { + process_tag((struct tag *) obj, &objects, name); + continue; + } + if (obj->type == TYPE_TREE) { + process_tree((struct tree *)obj, &objects, NULL, name); + continue; + } + if (obj->type == TYPE_BLOB) { + process_blob((struct blob *)obj, &objects, NULL, name); + continue; + } + die("unknown pending object %s (%s)", sha1_to_hex(obj->sha1), name); + } +} + +static int add_one_ref(const char *path, const unsigned char *sha1) +{ + struct object *object = parse_object(sha1); + if (!object) + die("bad object ref: %s:%s", path, sha1_to_hex(sha1)); + add_pending_object(&revs, object, ""); + return 0; +} + +static void add_one_tree(const unsigned char *sha1) +{ + struct tree *tree = lookup_tree(sha1); + add_pending_object(&revs, &tree->object, ""); +} + +static void add_cache_tree(struct cache_tree *it) +{ + int i; + + if (it->entry_count >= 0) + add_one_tree(it->sha1); + for (i = 0; i < it->subtree_nr; i++) + add_cache_tree(it->down[i]->cache_tree); +} + +static void add_cache_refs(void) +{ + int i; + + read_cache(); + for (i = 0; i < active_nr; i++) { + lookup_blob(active_cache[i]->sha1); + /* + * We could add the blobs to the pending list, but quite + * frankly, we don't care. Once we've looked them up, and + * added them as objects, we've really done everything + * there is to do for a blob + */ + } + if (active_cache_tree) + add_cache_tree(active_cache_tree); +} + +int cmd_prune(int argc, const char **argv, char **envp) +{ + int i; + + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + if (!strcmp(arg, "-n")) { + show_only = 1; + continue; + } + usage(prune_usage); + } + + /* + * Set up revision parsing, and mark us as being interested + * in all object types, not just commits. + */ + init_revisions(&revs); + revs.tag_objects = 1; + revs.blob_objects = 1; + revs.tree_objects = 1; + + /* Add all external refs */ + for_each_ref(add_one_ref); + + /* Add all refs from the index file */ + add_cache_refs(); + + /* + * Set up the revision walk - this will move all commits + * from the pending list to the commit walking list. + */ + prepare_revision_walk(&revs); + + walk_commit_list(&revs); + + prune_object_dir(get_object_directory()); + + return 0; +} diff --git a/builtin.h b/builtin.h index d9e5483..5339d86 100644 --- a/builtin.h +++ b/builtin.h @@ -25,6 +25,8 @@ extern int cmd_diff(int argc, const char **argv, char **envp); extern int cmd_format_patch(int argc, const char **argv, char **envp); extern int cmd_count_objects(int argc, const char **argv, char **envp); +extern int cmd_prune(int argc, const char **argv, char **envp); + extern int cmd_push(int argc, const char **argv, char **envp); extern int cmd_grep(int argc, const char **argv, char **envp); extern int cmd_rm(int argc, const char **argv, char **envp); diff --git a/git-prune.sh b/git-prune.sh deleted file mode 100755 index c5a5d29..0000000 --- a/git-prune.sh +++ /dev/null @@ -1,44 +0,0 @@ -#!/bin/sh - -USAGE='[-n] [--] [...]' -. git-sh-setup - -dryrun= -echo= -while case "$#" in 0) break ;; esac -do - case "$1" in - -n) dryrun=-n echo=echo ;; - --) break ;; - -*) usage ;; - *) break ;; - esac - shift; -done - -sync -case "$#" in -0) git-fsck-objects --full --cache --unreachable ;; -*) git-fsck-objects --full --cache --unreachable $(git-rev-parse --all) "$@" ;; -esac | - -sed -ne '/unreachable /{ - s/unreachable [^ ][^ ]* // - s|\(..\)|\1/|p -}' | { - cd "$GIT_OBJECT_DIRECTORY" || exit - xargs $echo rm -f - rmdir 2>/dev/null [0-9a-f][0-9a-f] -} - -git-prune-packed $dryrun - -if redundant=$(git-pack-redundant --all 2>/dev/null) && test "" != "$redundant" -then - if test "" = "$dryrun" - then - echo "$redundant" | xargs rm -f - else - echo rm -f "$redundant" - fi -fi diff --git a/git.c b/git.c index 2567301..16e37e5 100644 --- a/git.c +++ b/git.c @@ -188,7 +188,8 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "stripspace", cmd_stripspace }, { "update-index", cmd_update_index }, { "update-ref", cmd_update_ref }, - { "fmt-merge-msg", cmd_fmt_merge_msg } + { "fmt-merge-msg", cmd_fmt_merge_msg }, + { "prune", cmd_prune }, }; int i; -- cgit v0.10.2-6-g49f6