From d6b64ed0f3549f56c4d948dc2c0f12abc52fd6c9 Mon Sep 17 00:00:00 2001 From: Matthias Kestenholz Date: Thu, 3 Aug 2006 17:24:35 +0200 Subject: Make git-name-rev a builtin Signed-off-by: Matthias Kestenholz Signed-off-by: Junio C Hamano --- Makefile | 7 +- builtin-name-rev.c | 256 +++++++++++++++++++++++++++++++++++++++++++++++++++++ builtin.h | 1 + git.c | 1 + name-rev.c | 256 ----------------------------------------------------- 5 files changed, 262 insertions(+), 259 deletions(-) create mode 100644 builtin-name-rev.c delete mode 100644 name-rev.c diff --git a/Makefile b/Makefile index 700c77f564..132c9cf012 100644 --- a/Makefile +++ b/Makefile @@ -185,7 +185,7 @@ PROGRAMS = \ git-unpack-objects$X git-update-server-info$X \ git-upload-pack$X git-verify-pack$X \ git-symbolic-ref$X \ - git-name-rev$X git-pack-redundant$X git-var$X \ + git-pack-redundant$X git-var$X \ git-describe$X git-merge-tree$X git-blame$X git-imap-send$X BUILT_INS = git-log$X git-whatchanged$X git-show$X git-update-ref$X \ @@ -198,7 +198,7 @@ BUILT_INS = git-log$X git-whatchanged$X git-show$X git-update-ref$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$X git-prune$X git-mv$X git-prune-packed$X \ - git-repo-config$X + git-repo-config$X git-name-rev$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -255,7 +255,8 @@ BUILTIN_OBJS = \ 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-prune.o \ - builtin-mv.o builtin-prune-packed.o builtin-repo-config.o + builtin-mv.o builtin-prune-packed.o builtin-repo-config.o \ + builtin-name-rev.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-name-rev.c b/builtin-name-rev.c new file mode 100644 index 0000000000..571bba4817 --- /dev/null +++ b/builtin-name-rev.c @@ -0,0 +1,256 @@ +#include +#include "builtin.h" +#include "cache.h" +#include "commit.h" +#include "tag.h" +#include "refs.h" + +static const char name_rev_usage[] = + "git-name-rev [--tags] ( --all | --stdin | committish [committish...] )\n"; + +typedef struct rev_name { + const char *tip_name; + int merge_traversals; + int generation; +} rev_name; + +static long cutoff = LONG_MAX; + +static void name_rev(struct commit *commit, + const char *tip_name, int merge_traversals, int generation, + int deref) +{ + struct rev_name *name = (struct rev_name *)commit->util; + struct commit_list *parents; + int parent_number = 1; + + if (!commit->object.parsed) + parse_commit(commit); + + if (commit->date < cutoff) + return; + + if (deref) { + char *new_name = xmalloc(strlen(tip_name)+3); + strcpy(new_name, tip_name); + strcat(new_name, "^0"); + tip_name = new_name; + + if (generation) + die("generation: %d, but deref?", generation); + } + + if (name == NULL) { + name = xmalloc(sizeof(rev_name)); + commit->util = name; + goto copy_data; + } else if (name->merge_traversals > merge_traversals || + (name->merge_traversals == merge_traversals && + name->generation > generation)) { +copy_data: + name->tip_name = tip_name; + name->merge_traversals = merge_traversals; + name->generation = generation; + } else + return; + + for (parents = commit->parents; + parents; + parents = parents->next, parent_number++) { + if (parent_number > 1) { + char *new_name = xmalloc(strlen(tip_name)+8); + + if (generation > 0) + sprintf(new_name, "%s~%d^%d", tip_name, + generation, parent_number); + else + sprintf(new_name, "%s^%d", tip_name, parent_number); + + name_rev(parents->item, new_name, + merge_traversals + 1 , 0, 0); + } else { + name_rev(parents->item, tip_name, merge_traversals, + generation + 1, 0); + } + } +} + +static int tags_only = 0; + +static int name_ref(const char *path, const unsigned char *sha1) +{ + struct object *o = parse_object(sha1); + int deref = 0; + + if (tags_only && strncmp(path, "refs/tags/", 10)) + return 0; + + while (o && o->type == OBJ_TAG) { + struct tag *t = (struct tag *) o; + if (!t->tagged) + break; /* broken repository */ + o = parse_object(t->tagged->sha1); + deref = 1; + } + if (o && o->type == OBJ_COMMIT) { + struct commit *commit = (struct commit *)o; + + if (!strncmp(path, "refs/heads/", 11)) + path = path + 11; + else if (!strncmp(path, "refs/", 5)) + path = path + 5; + + name_rev(commit, strdup(path), 0, 0, deref); + } + return 0; +} + +/* returns a static buffer */ +static const char* get_rev_name(struct object *o) +{ + static char buffer[1024]; + struct rev_name *n; + struct commit *c; + + if (o->type != OBJ_COMMIT) + return "undefined"; + c = (struct commit *) o; + n = c->util; + if (!n) + return "undefined"; + + if (!n->generation) + return n->tip_name; + + snprintf(buffer, sizeof(buffer), "%s~%d", n->tip_name, n->generation); + + return buffer; +} + +int cmd_name_rev(int argc, const char **argv, const char *prefix) +{ + struct object_array revs = { 0, 0, NULL }; + int as_is = 0, all = 0, transform_stdin = 0; + + git_config(git_default_config); + + if (argc < 2) + usage(name_rev_usage); + + for (--argc, ++argv; argc; --argc, ++argv) { + unsigned char sha1[20]; + struct object *o; + struct commit *commit; + + if (!as_is && (*argv)[0] == '-') { + if (!strcmp(*argv, "--")) { + as_is = 1; + continue; + } else if (!strcmp(*argv, "--tags")) { + tags_only = 1; + continue; + } else if (!strcmp(*argv, "--all")) { + if (argc > 1) + die("Specify either a list, or --all, not both!"); + all = 1; + cutoff = 0; + continue; + } else if (!strcmp(*argv, "--stdin")) { + if (argc > 1) + die("Specify either a list, or --stdin, not both!"); + transform_stdin = 1; + cutoff = 0; + continue; + } + usage(name_rev_usage); + } + + if (get_sha1(*argv, sha1)) { + fprintf(stderr, "Could not get sha1 for %s. Skipping.\n", + *argv); + continue; + } + + o = deref_tag(parse_object(sha1), *argv, 0); + if (!o || o->type != OBJ_COMMIT) { + fprintf(stderr, "Could not get commit for %s. Skipping.\n", + *argv); + continue; + } + + commit = (struct commit *)o; + + if (cutoff > commit->date) + cutoff = commit->date; + + add_object_array((struct object *)commit, *argv, &revs); + } + + for_each_ref(name_ref); + + if (transform_stdin) { + char buffer[2048]; + char *p, *p_start; + + while (!feof(stdin)) { + int forty = 0; + p = fgets(buffer, sizeof(buffer), stdin); + if (!p) + break; + + for (p_start = p; *p; p++) { +#define ishex(x) (isdigit((x)) || ((x) >= 'a' && (x) <= 'f')) + if (!ishex(*p)) + forty = 0; + else if (++forty == 40 && + !ishex(*(p+1))) { + unsigned char sha1[40]; + const char *name = "undefined"; + char c = *(p+1); + + forty = 0; + + *(p+1) = 0; + if (!get_sha1(p - 39, sha1)) { + struct object *o = + lookup_object(sha1); + if (o) + name = get_rev_name(o); + } + *(p+1) = c; + + if (!strcmp(name, "undefined")) + continue; + + fwrite(p_start, p - p_start + 1, 1, + stdout); + printf(" (%s)", name); + p_start = p + 1; + } + } + + /* flush */ + if (p_start != p) + fwrite(p_start, p - p_start, 1, stdout); + } + } else if (all) { + int i, max; + + max = get_max_object_index(); + for (i = 0; i < max; i++) { + struct object * obj = get_indexed_object(i); + if (!obj) + continue; + printf("%s %s\n", sha1_to_hex(obj->sha1), get_rev_name(obj)); + } + } else { + int i; + for (i = 0; i < revs.nr; i++) + printf("%s %s\n", + revs.objects[i].name, + get_rev_name(revs.objects[i].item)); + } + + return 0; +} + diff --git a/builtin.h b/builtin.h index 26ebcaf213..d1d9dc14f9 100644 --- a/builtin.h +++ b/builtin.h @@ -49,6 +49,7 @@ extern int cmd_update_ref(int argc, const char **argv, const char *prefix); extern int cmd_fmt_merge_msg(int argc, const char **argv, const char *prefix); extern int cmd_mv(int argc, const char **argv, const char *prefix); extern int cmd_repo_config(int argc, const char **argv, const char *prefix); +extern int cmd_name_rev(int argc, const char **argv, const char *prefix); extern int cmd_write_tree(int argc, const char **argv, const char *prefix); extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix); diff --git a/git.c b/git.c index 6e72a893b7..501a7815fc 100644 --- a/git.c +++ b/git.c @@ -265,6 +265,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "mv", cmd_mv, NEEDS_PREFIX }, { "prune-packed", cmd_prune_packed, NEEDS_PREFIX }, { "repo-config", cmd_repo_config }, + { "name-rev", cmd_name_rev, NEEDS_PREFIX }, }; int i; diff --git a/name-rev.c b/name-rev.c deleted file mode 100644 index f92f14e32f..0000000000 --- a/name-rev.c +++ /dev/null @@ -1,256 +0,0 @@ -#include -#include "cache.h" -#include "commit.h" -#include "tag.h" -#include "refs.h" - -static const char name_rev_usage[] = - "git-name-rev [--tags] ( --all | --stdin | committish [committish...] )\n"; - -typedef struct rev_name { - const char *tip_name; - int merge_traversals; - int generation; -} rev_name; - -static long cutoff = LONG_MAX; - -static void name_rev(struct commit *commit, - const char *tip_name, int merge_traversals, int generation, - int deref) -{ - struct rev_name *name = (struct rev_name *)commit->util; - struct commit_list *parents; - int parent_number = 1; - - if (!commit->object.parsed) - parse_commit(commit); - - if (commit->date < cutoff) - return; - - if (deref) { - char *new_name = xmalloc(strlen(tip_name)+3); - strcpy(new_name, tip_name); - strcat(new_name, "^0"); - tip_name = new_name; - - if (generation) - die("generation: %d, but deref?", generation); - } - - if (name == NULL) { - name = xmalloc(sizeof(rev_name)); - commit->util = name; - goto copy_data; - } else if (name->merge_traversals > merge_traversals || - (name->merge_traversals == merge_traversals && - name->generation > generation)) { -copy_data: - name->tip_name = tip_name; - name->merge_traversals = merge_traversals; - name->generation = generation; - } else - return; - - for (parents = commit->parents; - parents; - parents = parents->next, parent_number++) { - if (parent_number > 1) { - char *new_name = xmalloc(strlen(tip_name)+8); - - if (generation > 0) - sprintf(new_name, "%s~%d^%d", tip_name, - generation, parent_number); - else - sprintf(new_name, "%s^%d", tip_name, parent_number); - - name_rev(parents->item, new_name, - merge_traversals + 1 , 0, 0); - } else { - name_rev(parents->item, tip_name, merge_traversals, - generation + 1, 0); - } - } -} - -static int tags_only = 0; - -static int name_ref(const char *path, const unsigned char *sha1) -{ - struct object *o = parse_object(sha1); - int deref = 0; - - if (tags_only && strncmp(path, "refs/tags/", 10)) - return 0; - - while (o && o->type == OBJ_TAG) { - struct tag *t = (struct tag *) o; - if (!t->tagged) - break; /* broken repository */ - o = parse_object(t->tagged->sha1); - deref = 1; - } - if (o && o->type == OBJ_COMMIT) { - struct commit *commit = (struct commit *)o; - - if (!strncmp(path, "refs/heads/", 11)) - path = path + 11; - else if (!strncmp(path, "refs/", 5)) - path = path + 5; - - name_rev(commit, strdup(path), 0, 0, deref); - } - return 0; -} - -/* returns a static buffer */ -static const char* get_rev_name(struct object *o) -{ - static char buffer[1024]; - struct rev_name *n; - struct commit *c; - - if (o->type != OBJ_COMMIT) - return "undefined"; - c = (struct commit *) o; - n = c->util; - if (!n) - return "undefined"; - - if (!n->generation) - return n->tip_name; - - snprintf(buffer, sizeof(buffer), "%s~%d", n->tip_name, n->generation); - - return buffer; -} - -int main(int argc, char **argv) -{ - struct object_array revs = { 0, 0, NULL }; - int as_is = 0, all = 0, transform_stdin = 0; - - setup_git_directory(); - git_config(git_default_config); - - if (argc < 2) - usage(name_rev_usage); - - for (--argc, ++argv; argc; --argc, ++argv) { - unsigned char sha1[20]; - struct object *o; - struct commit *commit; - - if (!as_is && (*argv)[0] == '-') { - if (!strcmp(*argv, "--")) { - as_is = 1; - continue; - } else if (!strcmp(*argv, "--tags")) { - tags_only = 1; - continue; - } else if (!strcmp(*argv, "--all")) { - if (argc > 1) - die("Specify either a list, or --all, not both!"); - all = 1; - cutoff = 0; - continue; - } else if (!strcmp(*argv, "--stdin")) { - if (argc > 1) - die("Specify either a list, or --stdin, not both!"); - transform_stdin = 1; - cutoff = 0; - continue; - } - usage(name_rev_usage); - } - - if (get_sha1(*argv, sha1)) { - fprintf(stderr, "Could not get sha1 for %s. Skipping.\n", - *argv); - continue; - } - - o = deref_tag(parse_object(sha1), *argv, 0); - if (!o || o->type != OBJ_COMMIT) { - fprintf(stderr, "Could not get commit for %s. Skipping.\n", - *argv); - continue; - } - - commit = (struct commit *)o; - - if (cutoff > commit->date) - cutoff = commit->date; - - add_object_array((struct object *)commit, *argv, &revs); - } - - for_each_ref(name_ref); - - if (transform_stdin) { - char buffer[2048]; - char *p, *p_start; - - while (!feof(stdin)) { - int forty = 0; - p = fgets(buffer, sizeof(buffer), stdin); - if (!p) - break; - - for (p_start = p; *p; p++) { -#define ishex(x) (isdigit((x)) || ((x) >= 'a' && (x) <= 'f')) - if (!ishex(*p)) - forty = 0; - else if (++forty == 40 && - !ishex(*(p+1))) { - unsigned char sha1[40]; - const char *name = "undefined"; - char c = *(p+1); - - forty = 0; - - *(p+1) = 0; - if (!get_sha1(p - 39, sha1)) { - struct object *o = - lookup_object(sha1); - if (o) - name = get_rev_name(o); - } - *(p+1) = c; - - if (!strcmp(name, "undefined")) - continue; - - fwrite(p_start, p - p_start + 1, 1, - stdout); - printf(" (%s)", name); - p_start = p + 1; - } - } - - /* flush */ - if (p_start != p) - fwrite(p_start, p - p_start, 1, stdout); - } - } else if (all) { - int i, max; - - max = get_max_object_index(); - for (i = 0; i < max; i++) { - struct object * obj = get_indexed_object(i); - if (!obj) - continue; - printf("%s %s\n", sha1_to_hex(obj->sha1), get_rev_name(obj)); - } - } else { - int i; - for (i = 0; i < revs.nr; i++) - printf("%s %s\n", - revs.objects[i].name, - get_rev_name(revs.objects[i].item)); - } - - return 0; -} - -- cgit v1.2.1 From 5d4a60033543e063bc9d77ca957de0187fb58fb3 Mon Sep 17 00:00:00 2001 From: Matthias Kestenholz Date: Thu, 3 Aug 2006 17:24:36 +0200 Subject: Make git-pack-objects a builtin Signed-off-by: Matthias Kestenholz Signed-off-by: Junio C Hamano --- Makefile | 6 +- builtin-pack-objects.c | 1376 ++++++++++++++++++++++++++++++++++++++++++++++++ builtin.h | 1 + git.c | 1 + pack-objects.c | 1376 ------------------------------------------------ 5 files changed, 1381 insertions(+), 1379 deletions(-) create mode 100644 builtin-pack-objects.c delete mode 100644 pack-objects.c diff --git a/Makefile b/Makefile index 132c9cf012..4fd62bcf6d 100644 --- a/Makefile +++ b/Makefile @@ -177,7 +177,7 @@ PROGRAMS = \ git-convert-objects$X git-fetch-pack$X git-fsck-objects$X \ git-hash-object$X git-index-pack$X git-local-fetch$X \ git-merge-base$X \ - git-merge-index$X git-mktag$X git-mktree$X git-pack-objects$X git-patch-id$X \ + git-merge-index$X git-mktag$X git-mktree$X git-patch-id$X \ git-peek-remote$X git-receive-pack$X \ git-send-pack$X git-shell$X \ git-show-index$X git-ssh-fetch$X \ @@ -198,7 +198,7 @@ BUILT_INS = git-log$X git-whatchanged$X git-show$X git-update-ref$X \ git-apply$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-prune$X git-mv$X git-prune-packed$X \ - git-repo-config$X git-name-rev$X + git-repo-config$X git-name-rev$X git-pack-objects$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -256,7 +256,7 @@ BUILTIN_OBJS = \ builtin-cat-file.o builtin-mailsplit.o builtin-stripspace.o \ builtin-update-ref.o builtin-fmt-merge-msg.o builtin-prune.o \ builtin-mv.o builtin-prune-packed.o builtin-repo-config.o \ - builtin-name-rev.o + builtin-name-rev.o builtin-pack-objects.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c new file mode 100644 index 0000000000..2301cd5c0f --- /dev/null +++ b/builtin-pack-objects.c @@ -0,0 +1,1376 @@ +#include "builtin.h" +#include "cache.h" +#include "object.h" +#include "blob.h" +#include "commit.h" +#include "tag.h" +#include "tree.h" +#include "delta.h" +#include "pack.h" +#include "csum-file.h" +#include "tree-walk.h" +#include +#include + +static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list"; + +struct object_entry { + unsigned char sha1[20]; + unsigned long size; /* uncompressed size */ + unsigned long offset; /* offset into the final pack file; + * nonzero if already written. + */ + unsigned int depth; /* delta depth */ + unsigned int delta_limit; /* base adjustment for in-pack delta */ + unsigned int hash; /* name hint hash */ + enum object_type type; + enum object_type in_pack_type; /* could be delta */ + unsigned long delta_size; /* delta data size (uncompressed) */ + struct object_entry *delta; /* delta base object */ + struct packed_git *in_pack; /* already in pack */ + unsigned int in_pack_offset; + struct object_entry *delta_child; /* deltified objects who bases me */ + struct object_entry *delta_sibling; /* other deltified objects who + * uses the same base as me + */ + int preferred_base; /* we do not pack this, but is encouraged to + * be used as the base objectto delta huge + * objects against. + */ +}; + +/* + * Objects we are going to pack are collected in objects array (dynamically + * expanded). nr_objects & nr_alloc controls this array. They are stored + * in the order we see -- typically rev-list --objects order that gives us + * nice "minimum seek" order. + * + * sorted-by-sha ans sorted-by-type are arrays of pointers that point at + * elements in the objects array. The former is used to build the pack + * index (lists object names in the ascending order to help offset lookup), + * and the latter is used to group similar things together by try_delta() + * heuristics. + */ + +static unsigned char object_list_sha1[20]; +static int non_empty = 0; +static int no_reuse_delta = 0; +static int local = 0; +static int incremental = 0; +static struct object_entry **sorted_by_sha, **sorted_by_type; +static struct object_entry *objects = NULL; +static int nr_objects = 0, nr_alloc = 0, nr_result = 0; +static const char *base_name; +static unsigned char pack_file_sha1[20]; +static int progress = 1; +static volatile sig_atomic_t progress_update = 0; +static int window = 10; + +/* + * The object names in objects array are hashed with this hashtable, + * to help looking up the entry by object name. Binary search from + * sorted_by_sha is also possible but this was easier to code and faster. + * This hashtable is built after all the objects are seen. + */ +static int *object_ix = NULL; +static int object_ix_hashsz = 0; + +/* + * Pack index for existing packs give us easy access to the offsets into + * corresponding pack file where each object's data starts, but the entries + * do not store the size of the compressed representation (uncompressed + * size is easily available by examining the pack entry header). We build + * a hashtable of existing packs (pack_revindex), and keep reverse index + * here -- pack index file is sorted by object name mapping to offset; this + * pack_revindex[].revindex array is an ordered list of offsets, so if you + * know the offset of an object, next offset is where its packed + * representation ends. + */ +struct pack_revindex { + struct packed_git *p; + unsigned long *revindex; +} *pack_revindex = NULL; +static int pack_revindex_hashsz = 0; + +/* + * stats + */ +static int written = 0; +static int written_delta = 0; +static int reused = 0; +static int reused_delta = 0; + +static int pack_revindex_ix(struct packed_git *p) +{ + unsigned long ui = (unsigned long)p; + int i; + + ui = ui ^ (ui >> 16); /* defeat structure alignment */ + i = (int)(ui % pack_revindex_hashsz); + while (pack_revindex[i].p) { + if (pack_revindex[i].p == p) + return i; + if (++i == pack_revindex_hashsz) + i = 0; + } + return -1 - i; +} + +static void prepare_pack_ix(void) +{ + int num; + struct packed_git *p; + for (num = 0, p = packed_git; p; p = p->next) + num++; + if (!num) + return; + pack_revindex_hashsz = num * 11; + pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz); + for (p = packed_git; p; p = p->next) { + num = pack_revindex_ix(p); + num = - 1 - num; + pack_revindex[num].p = p; + } + /* revindex elements are lazily initialized */ +} + +static int cmp_offset(const void *a_, const void *b_) +{ + unsigned long a = *(unsigned long *) a_; + unsigned long b = *(unsigned long *) b_; + if (a < b) + return -1; + else if (a == b) + return 0; + else + return 1; +} + +/* + * Ordered list of offsets of objects in the pack. + */ +static void prepare_pack_revindex(struct pack_revindex *rix) +{ + struct packed_git *p = rix->p; + int num_ent = num_packed_objects(p); + int i; + void *index = p->index_base + 256; + + rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1)); + for (i = 0; i < num_ent; i++) { + unsigned int hl = *((unsigned int *)((char *) index + 24*i)); + rix->revindex[i] = ntohl(hl); + } + /* This knows the pack format -- the 20-byte trailer + * follows immediately after the last object data. + */ + rix->revindex[num_ent] = p->pack_size - 20; + qsort(rix->revindex, num_ent, sizeof(unsigned long), cmp_offset); +} + +static unsigned long find_packed_object_size(struct packed_git *p, + unsigned long ofs) +{ + int num; + int lo, hi; + struct pack_revindex *rix; + unsigned long *revindex; + num = pack_revindex_ix(p); + if (num < 0) + die("internal error: pack revindex uninitialized"); + rix = &pack_revindex[num]; + if (!rix->revindex) + prepare_pack_revindex(rix); + revindex = rix->revindex; + lo = 0; + hi = num_packed_objects(p) + 1; + do { + int mi = (lo + hi) / 2; + if (revindex[mi] == ofs) { + return revindex[mi+1] - ofs; + } + else if (ofs < revindex[mi]) + hi = mi; + else + lo = mi + 1; + } while (lo < hi); + die("internal error: pack revindex corrupt"); +} + +static void *delta_against(void *buf, unsigned long size, struct object_entry *entry) +{ + unsigned long othersize, delta_size; + char type[10]; + void *otherbuf = read_sha1_file(entry->delta->sha1, type, &othersize); + void *delta_buf; + + if (!otherbuf) + die("unable to read %s", sha1_to_hex(entry->delta->sha1)); + delta_buf = diff_delta(otherbuf, othersize, + buf, size, &delta_size, 0); + if (!delta_buf || delta_size != entry->delta_size) + die("delta size changed"); + free(buf); + free(otherbuf); + return delta_buf; +} + +/* + * The per-object header is a pretty dense thing, which is + * - first byte: low four bits are "size", then three bits of "type", + * and the high bit is "size continues". + * - each byte afterwards: low seven bits are size continuation, + * with the high bit being "size continues" + */ +static int encode_header(enum object_type type, unsigned long size, unsigned char *hdr) +{ + int n = 1; + unsigned char c; + + if (type < OBJ_COMMIT || type > OBJ_DELTA) + die("bad type %d", type); + + c = (type << 4) | (size & 15); + size >>= 4; + while (size) { + *hdr++ = c | 0x80; + c = size & 0x7f; + size >>= 7; + n++; + } + *hdr = c; + return n; +} + +static unsigned long write_object(struct sha1file *f, + struct object_entry *entry) +{ + unsigned long size; + char type[10]; + void *buf; + unsigned char header[10]; + unsigned hdrlen, datalen; + enum object_type obj_type; + int to_reuse = 0; + + if (entry->preferred_base) + return 0; + + obj_type = entry->type; + if (! entry->in_pack) + to_reuse = 0; /* can't reuse what we don't have */ + else if (obj_type == OBJ_DELTA) + to_reuse = 1; /* check_object() decided it for us */ + else if (obj_type != entry->in_pack_type) + to_reuse = 0; /* pack has delta which is unusable */ + else if (entry->delta) + to_reuse = 0; /* we want to pack afresh */ + else + to_reuse = 1; /* we have it in-pack undeltified, + * and we do not need to deltify it. + */ + + if (! to_reuse) { + buf = read_sha1_file(entry->sha1, type, &size); + if (!buf) + die("unable to read %s", sha1_to_hex(entry->sha1)); + if (size != entry->size) + die("object %s size inconsistency (%lu vs %lu)", + sha1_to_hex(entry->sha1), size, entry->size); + if (entry->delta) { + buf = delta_against(buf, size, entry); + size = entry->delta_size; + obj_type = OBJ_DELTA; + } + /* + * The object header is a byte of 'type' followed by zero or + * more bytes of length. For deltas, the 20 bytes of delta + * sha1 follows that. + */ + hdrlen = encode_header(obj_type, size, header); + sha1write(f, header, hdrlen); + + if (entry->delta) { + sha1write(f, entry->delta, 20); + hdrlen += 20; + } + datalen = sha1write_compressed(f, buf, size); + free(buf); + } + else { + struct packed_git *p = entry->in_pack; + use_packed_git(p); + + datalen = find_packed_object_size(p, entry->in_pack_offset); + buf = (char *) p->pack_base + entry->in_pack_offset; + sha1write(f, buf, datalen); + unuse_packed_git(p); + hdrlen = 0; /* not really */ + if (obj_type == OBJ_DELTA) + reused_delta++; + reused++; + } + if (obj_type == OBJ_DELTA) + written_delta++; + written++; + return hdrlen + datalen; +} + +static unsigned long write_one(struct sha1file *f, + struct object_entry *e, + unsigned long offset) +{ + if (e->offset) + /* offset starts from header size and cannot be zero + * if it is written already. + */ + return offset; + e->offset = offset; + offset += write_object(f, e); + /* if we are deltified, write out its base object. */ + if (e->delta) + offset = write_one(f, e->delta, offset); + return offset; +} + +static void write_pack_file(void) +{ + int i; + struct sha1file *f; + unsigned long offset; + struct pack_header hdr; + unsigned last_percent = 999; + int do_progress = 0; + + if (!base_name) + f = sha1fd(1, ""); + else { + f = sha1create("%s-%s.%s", base_name, + sha1_to_hex(object_list_sha1), "pack"); + do_progress = progress; + } + if (do_progress) + fprintf(stderr, "Writing %d objects.\n", nr_result); + + hdr.hdr_signature = htonl(PACK_SIGNATURE); + hdr.hdr_version = htonl(PACK_VERSION); + hdr.hdr_entries = htonl(nr_result); + sha1write(f, &hdr, sizeof(hdr)); + offset = sizeof(hdr); + if (!nr_result) + goto done; + for (i = 0; i < nr_objects; i++) { + offset = write_one(f, objects + i, offset); + if (do_progress) { + unsigned percent = written * 100 / nr_result; + if (progress_update || percent != last_percent) { + fprintf(stderr, "%4u%% (%u/%u) done\r", + percent, written, nr_result); + progress_update = 0; + last_percent = percent; + } + } + } + if (do_progress) + fputc('\n', stderr); + done: + sha1close(f, pack_file_sha1, 1); +} + +static void write_index_file(void) +{ + int i; + struct sha1file *f = sha1create("%s-%s.%s", base_name, + sha1_to_hex(object_list_sha1), "idx"); + struct object_entry **list = sorted_by_sha; + struct object_entry **last = list + nr_result; + unsigned int array[256]; + + /* + * Write the first-level table (the list is sorted, + * but we use a 256-entry lookup to be able to avoid + * having to do eight extra binary search iterations). + */ + for (i = 0; i < 256; i++) { + struct object_entry **next = list; + while (next < last) { + struct object_entry *entry = *next; + if (entry->sha1[0] != i) + break; + next++; + } + array[i] = htonl(next - sorted_by_sha); + list = next; + } + sha1write(f, array, 256 * sizeof(int)); + + /* + * Write the actual SHA1 entries.. + */ + list = sorted_by_sha; + for (i = 0; i < nr_result; i++) { + struct object_entry *entry = *list++; + unsigned int offset = htonl(entry->offset); + sha1write(f, &offset, 4); + sha1write(f, entry->sha1, 20); + } + sha1write(f, pack_file_sha1, 20); + sha1close(f, NULL, 1); +} + +static int locate_object_entry_hash(const unsigned char *sha1) +{ + int i; + unsigned int ui; + memcpy(&ui, sha1, sizeof(unsigned int)); + i = ui % object_ix_hashsz; + while (0 < object_ix[i]) { + if (!memcmp(sha1, objects[object_ix[i]-1].sha1, 20)) + return i; + if (++i == object_ix_hashsz) + i = 0; + } + return -1 - i; +} + +static struct object_entry *locate_object_entry(const unsigned char *sha1) +{ + int i; + + if (!object_ix_hashsz) + return NULL; + + i = locate_object_entry_hash(sha1); + if (0 <= i) + return &objects[object_ix[i]-1]; + return NULL; +} + +static void rehash_objects(void) +{ + int i; + struct object_entry *oe; + + object_ix_hashsz = nr_objects * 3; + if (object_ix_hashsz < 1024) + object_ix_hashsz = 1024; + object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz); + memset(object_ix, 0, sizeof(int) * object_ix_hashsz); + for (i = 0, oe = objects; i < nr_objects; i++, oe++) { + int ix = locate_object_entry_hash(oe->sha1); + if (0 <= ix) + continue; + ix = -1 - ix; + object_ix[ix] = i + 1; + } +} + +static unsigned name_hash(const char *name) +{ + unsigned char c; + unsigned hash = 0; + + /* + * This effectively just creates a sortable number from the + * last sixteen non-whitespace characters. Last characters + * count "most", so things that end in ".c" sort together. + */ + while ((c = *name++) != 0) { + if (isspace(c)) + continue; + hash = (hash >> 2) + (c << 24); + } + return hash; +} + +static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclude) +{ + unsigned int idx = nr_objects; + struct object_entry *entry; + struct packed_git *p; + unsigned int found_offset = 0; + struct packed_git *found_pack = NULL; + int ix, status = 0; + + if (!exclude) { + for (p = packed_git; p; p = p->next) { + struct pack_entry e; + if (find_pack_entry_one(sha1, &e, p)) { + if (incremental) + return 0; + if (local && !p->pack_local) + return 0; + if (!found_pack) { + found_offset = e.offset; + found_pack = e.p; + } + } + } + } + if ((entry = locate_object_entry(sha1)) != NULL) + goto already_added; + + if (idx >= nr_alloc) { + unsigned int needed = (idx + 1024) * 3 / 2; + objects = xrealloc(objects, needed * sizeof(*entry)); + nr_alloc = needed; + } + entry = objects + idx; + nr_objects = idx + 1; + memset(entry, 0, sizeof(*entry)); + memcpy(entry->sha1, sha1, 20); + entry->hash = hash; + + if (object_ix_hashsz * 3 <= nr_objects * 4) + rehash_objects(); + else { + ix = locate_object_entry_hash(entry->sha1); + if (0 <= ix) + die("internal error in object hashing."); + object_ix[-1 - ix] = idx + 1; + } + status = 1; + + already_added: + if (progress_update) { + fprintf(stderr, "Counting objects...%d\r", nr_objects); + progress_update = 0; + } + if (exclude) + entry->preferred_base = 1; + else { + if (found_pack) { + entry->in_pack = found_pack; + entry->in_pack_offset = found_offset; + } + } + return status; +} + +struct pbase_tree_cache { + unsigned char sha1[20]; + int ref; + int temporary; + void *tree_data; + unsigned long tree_size; +}; + +static struct pbase_tree_cache *(pbase_tree_cache[256]); +static int pbase_tree_cache_ix(const unsigned char *sha1) +{ + return sha1[0] % ARRAY_SIZE(pbase_tree_cache); +} +static int pbase_tree_cache_ix_incr(int ix) +{ + return (ix+1) % ARRAY_SIZE(pbase_tree_cache); +} + +static struct pbase_tree { + struct pbase_tree *next; + /* This is a phony "cache" entry; we are not + * going to evict it nor find it through _get() + * mechanism -- this is for the toplevel node that + * would almost always change with any commit. + */ + struct pbase_tree_cache pcache; +} *pbase_tree; + +static struct pbase_tree_cache *pbase_tree_get(const unsigned char *sha1) +{ + struct pbase_tree_cache *ent, *nent; + void *data; + unsigned long size; + char type[20]; + int neigh; + int my_ix = pbase_tree_cache_ix(sha1); + int available_ix = -1; + + /* pbase-tree-cache acts as a limited hashtable. + * your object will be found at your index or within a few + * slots after that slot if it is cached. + */ + for (neigh = 0; neigh < 8; neigh++) { + ent = pbase_tree_cache[my_ix]; + if (ent && !memcmp(ent->sha1, sha1, 20)) { + ent->ref++; + return ent; + } + else if (((available_ix < 0) && (!ent || !ent->ref)) || + ((0 <= available_ix) && + (!ent && pbase_tree_cache[available_ix]))) + available_ix = my_ix; + if (!ent) + break; + my_ix = pbase_tree_cache_ix_incr(my_ix); + } + + /* Did not find one. Either we got a bogus request or + * we need to read and perhaps cache. + */ + data = read_sha1_file(sha1, type, &size); + if (!data) + return NULL; + if (strcmp(type, tree_type)) { + free(data); + return NULL; + } + + /* We need to either cache or return a throwaway copy */ + + if (available_ix < 0) + ent = NULL; + else { + ent = pbase_tree_cache[available_ix]; + my_ix = available_ix; + } + + if (!ent) { + nent = xmalloc(sizeof(*nent)); + nent->temporary = (available_ix < 0); + } + else { + /* evict and reuse */ + free(ent->tree_data); + nent = ent; + } + memcpy(nent->sha1, sha1, 20); + nent->tree_data = data; + nent->tree_size = size; + nent->ref = 1; + if (!nent->temporary) + pbase_tree_cache[my_ix] = nent; + return nent; +} + +static void pbase_tree_put(struct pbase_tree_cache *cache) +{ + if (!cache->temporary) { + cache->ref--; + return; + } + free(cache->tree_data); + free(cache); +} + +static int name_cmp_len(const char *name) +{ + int i; + for (i = 0; name[i] && name[i] != '\n' && name[i] != '/'; i++) + ; + return i; +} + +static void add_pbase_object(struct tree_desc *tree, + const char *name, + int cmplen, + const char *fullname) +{ + struct name_entry entry; + + while (tree_entry(tree,&entry)) { + unsigned long size; + char type[20]; + + if (entry.pathlen != cmplen || + memcmp(entry.path, name, cmplen) || + !has_sha1_file(entry.sha1) || + sha1_object_info(entry.sha1, type, &size)) + continue; + if (name[cmplen] != '/') { + unsigned hash = name_hash(fullname); + add_object_entry(entry.sha1, hash, 1); + return; + } + if (!strcmp(type, tree_type)) { + struct tree_desc sub; + struct pbase_tree_cache *tree; + const char *down = name+cmplen+1; + int downlen = name_cmp_len(down); + + tree = pbase_tree_get(entry.sha1); + if (!tree) + return; + sub.buf = tree->tree_data; + sub.size = tree->tree_size; + + add_pbase_object(&sub, down, downlen, fullname); + pbase_tree_put(tree); + } + } +} + +static unsigned *done_pbase_paths; +static int done_pbase_paths_num; +static int done_pbase_paths_alloc; +static int done_pbase_path_pos(unsigned hash) +{ + int lo = 0; + int hi = done_pbase_paths_num; + while (lo < hi) { + int mi = (hi + lo) / 2; + if (done_pbase_paths[mi] == hash) + return mi; + if (done_pbase_paths[mi] < hash) + hi = mi; + else + lo = mi + 1; + } + return -lo-1; +} + +static int check_pbase_path(unsigned hash) +{ + int pos = (!done_pbase_paths) ? -1 : done_pbase_path_pos(hash); + if (0 <= pos) + return 1; + pos = -pos - 1; + if (done_pbase_paths_alloc <= done_pbase_paths_num) { + done_pbase_paths_alloc = alloc_nr(done_pbase_paths_alloc); + done_pbase_paths = xrealloc(done_pbase_paths, + done_pbase_paths_alloc * + sizeof(unsigned)); + } + done_pbase_paths_num++; + if (pos < done_pbase_paths_num) + memmove(done_pbase_paths + pos + 1, + done_pbase_paths + pos, + (done_pbase_paths_num - pos - 1) * sizeof(unsigned)); + done_pbase_paths[pos] = hash; + return 0; +} + +static void add_preferred_base_object(char *name, unsigned hash) +{ + struct pbase_tree *it; + int cmplen = name_cmp_len(name); + + if (check_pbase_path(hash)) + return; + + for (it = pbase_tree; it; it = it->next) { + if (cmplen == 0) { + hash = name_hash(""); + add_object_entry(it->pcache.sha1, hash, 1); + } + else { + struct tree_desc tree; + tree.buf = it->pcache.tree_data; + tree.size = it->pcache.tree_size; + add_pbase_object(&tree, name, cmplen, name); + } + } +} + +static void add_preferred_base(unsigned char *sha1) +{ + struct pbase_tree *it; + void *data; + unsigned long size; + unsigned char tree_sha1[20]; + + data = read_object_with_reference(sha1, tree_type, &size, tree_sha1); + if (!data) + return; + + for (it = pbase_tree; it; it = it->next) { + if (!memcmp(it->pcache.sha1, tree_sha1, 20)) { + free(data); + return; + } + } + + it = xcalloc(1, sizeof(*it)); + it->next = pbase_tree; + pbase_tree = it; + + memcpy(it->pcache.sha1, tree_sha1, 20); + it->pcache.tree_data = data; + it->pcache.tree_size = size; +} + +static void check_object(struct object_entry *entry) +{ + char type[20]; + + if (entry->in_pack && !entry->preferred_base) { + unsigned char base[20]; + unsigned long size; + struct object_entry *base_entry; + + /* We want in_pack_type even if we do not reuse delta. + * There is no point not reusing non-delta representations. + */ + check_reuse_pack_delta(entry->in_pack, + entry->in_pack_offset, + base, &size, + &entry->in_pack_type); + + /* Check if it is delta, and the base is also an object + * we are going to pack. If so we will reuse the existing + * delta. + */ + if (!no_reuse_delta && + entry->in_pack_type == OBJ_DELTA && + (base_entry = locate_object_entry(base)) && + (!base_entry->preferred_base)) { + + /* Depth value does not matter - find_deltas() + * will never consider reused delta as the + * base object to deltify other objects + * against, in order to avoid circular deltas. + */ + + /* uncompressed size of the delta data */ + entry->size = entry->delta_size = size; + entry->delta = base_entry; + entry->type = OBJ_DELTA; + + entry->delta_sibling = base_entry->delta_child; + base_entry->delta_child = entry; + + return; + } + /* Otherwise we would do the usual */ + } + + if (sha1_object_info(entry->sha1, type, &entry->size)) + die("unable to get type of object %s", + sha1_to_hex(entry->sha1)); + + if (!strcmp(type, commit_type)) { + entry->type = OBJ_COMMIT; + } else if (!strcmp(type, tree_type)) { + entry->type = OBJ_TREE; + } else if (!strcmp(type, blob_type)) { + entry->type = OBJ_BLOB; + } else if (!strcmp(type, tag_type)) { + entry->type = OBJ_TAG; + } else + die("unable to pack object %s of type %s", + sha1_to_hex(entry->sha1), type); +} + +static unsigned int check_delta_limit(struct object_entry *me, unsigned int n) +{ + struct object_entry *child = me->delta_child; + unsigned int m = n; + while (child) { + unsigned int c = check_delta_limit(child, n + 1); + if (m < c) + m = c; + child = child->delta_sibling; + } + return m; +} + +static void get_object_details(void) +{ + int i; + struct object_entry *entry; + + prepare_pack_ix(); + for (i = 0, entry = objects; i < nr_objects; i++, entry++) + check_object(entry); + + if (nr_objects == nr_result) { + /* + * Depth of objects that depend on the entry -- this + * is subtracted from depth-max to break too deep + * delta chain because of delta data reusing. + * However, we loosen this restriction when we know we + * are creating a thin pack -- it will have to be + * expanded on the other end anyway, so do not + * artificially cut the delta chain and let it go as + * deep as it wants. + */ + for (i = 0, entry = objects; i < nr_objects; i++, entry++) + if (!entry->delta && entry->delta_child) + entry->delta_limit = + check_delta_limit(entry, 1); + } +} + +typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *); + +static entry_sort_t current_sort; + +static int sort_comparator(const void *_a, const void *_b) +{ + struct object_entry *a = *(struct object_entry **)_a; + struct object_entry *b = *(struct object_entry **)_b; + return current_sort(a,b); +} + +static struct object_entry **create_sorted_list(entry_sort_t sort) +{ + struct object_entry **list = xmalloc(nr_objects * sizeof(struct object_entry *)); + int i; + + for (i = 0; i < nr_objects; i++) + list[i] = objects + i; + current_sort = sort; + qsort(list, nr_objects, sizeof(struct object_entry *), sort_comparator); + return list; +} + +static int sha1_sort(const struct object_entry *a, const struct object_entry *b) +{ + return memcmp(a->sha1, b->sha1, 20); +} + +static struct object_entry **create_final_object_list(void) +{ + struct object_entry **list; + int i, j; + + for (i = nr_result = 0; i < nr_objects; i++) + if (!objects[i].preferred_base) + nr_result++; + list = xmalloc(nr_result * sizeof(struct object_entry *)); + for (i = j = 0; i < nr_objects; i++) { + if (!objects[i].preferred_base) + list[j++] = objects + i; + } + current_sort = sha1_sort; + qsort(list, nr_result, sizeof(struct object_entry *), sort_comparator); + return list; +} + +static int type_size_sort(const struct object_entry *a, const struct object_entry *b) +{ + if (a->type < b->type) + return -1; + if (a->type > b->type) + return 1; + if (a->hash < b->hash) + return -1; + if (a->hash > b->hash) + return 1; + if (a->preferred_base < b->preferred_base) + return -1; + if (a->preferred_base > b->preferred_base) + return 1; + if (a->size < b->size) + return -1; + if (a->size > b->size) + return 1; + return a < b ? -1 : (a > b); +} + +struct unpacked { + struct object_entry *entry; + void *data; + struct delta_index *index; +}; + +/* + * We search for deltas _backwards_ in a list sorted by type and + * by size, so that we see progressively smaller and smaller files. + * That's because we prefer deltas to be from the bigger file + * to the smaller - deletes are potentially cheaper, but perhaps + * more importantly, the bigger file is likely the more recent + * one. + */ +static int try_delta(struct unpacked *trg, struct unpacked *src, + unsigned max_depth) +{ + struct object_entry *trg_entry = trg->entry; + struct object_entry *src_entry = src->entry; + unsigned long trg_size, src_size, delta_size, sizediff, max_size, sz; + char type[10]; + void *delta_buf; + + /* Don't bother doing diffs between different types */ + if (trg_entry->type != src_entry->type) + return -1; + + /* We do not compute delta to *create* objects we are not + * going to pack. + */ + if (trg_entry->preferred_base) + return -1; + + /* + * We do not bother to try a delta that we discarded + * on an earlier try, but only when reusing delta data. + */ + if (!no_reuse_delta && trg_entry->in_pack && + trg_entry->in_pack == src_entry->in_pack) + return 0; + + /* + * If the current object is at pack edge, take the depth the + * objects that depend on the current object into account -- + * otherwise they would become too deep. + */ + if (trg_entry->delta_child) { + if (max_depth <= trg_entry->delta_limit) + return 0; + max_depth -= trg_entry->delta_limit; + } + if (src_entry->depth >= max_depth) + return 0; + + /* Now some size filtering heuristics. */ + trg_size = trg_entry->size; + max_size = trg_size/2 - 20; + max_size = max_size * (max_depth - src_entry->depth) / max_depth; + if (max_size == 0) + return 0; + if (trg_entry->delta && trg_entry->delta_size <= max_size) + max_size = trg_entry->delta_size-1; + src_size = src_entry->size; + sizediff = src_size < trg_size ? trg_size - src_size : 0; + if (sizediff >= max_size) + return 0; + + /* Load data if not already done */ + if (!trg->data) { + trg->data = read_sha1_file(trg_entry->sha1, type, &sz); + if (sz != trg_size) + die("object %s inconsistent object length (%lu vs %lu)", + sha1_to_hex(trg_entry->sha1), sz, trg_size); + } + if (!src->data) { + src->data = read_sha1_file(src_entry->sha1, type, &sz); + if (sz != src_size) + die("object %s inconsistent object length (%lu vs %lu)", + sha1_to_hex(src_entry->sha1), sz, src_size); + } + if (!src->index) { + src->index = create_delta_index(src->data, src_size); + if (!src->index) + die("out of memory"); + } + + delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size); + if (!delta_buf) + return 0; + + trg_entry->delta = src_entry; + trg_entry->delta_size = delta_size; + trg_entry->depth = src_entry->depth + 1; + free(delta_buf); + return 1; +} + +static void progress_interval(int signum) +{ + progress_update = 1; +} + +static void find_deltas(struct object_entry **list, int window, int depth) +{ + int i, idx; + unsigned int array_size = window * sizeof(struct unpacked); + struct unpacked *array = xmalloc(array_size); + unsigned processed = 0; + unsigned last_percent = 999; + + memset(array, 0, array_size); + i = nr_objects; + idx = 0; + if (progress) + fprintf(stderr, "Deltifying %d objects.\n", nr_result); + + while (--i >= 0) { + struct object_entry *entry = list[i]; + struct unpacked *n = array + idx; + int j; + + if (!entry->preferred_base) + processed++; + + if (progress) { + unsigned percent = processed * 100 / nr_result; + if (percent != last_percent || progress_update) { + fprintf(stderr, "%4u%% (%u/%u) done\r", + percent, processed, nr_result); + progress_update = 0; + last_percent = percent; + } + } + + if (entry->delta) + /* This happens if we decided to reuse existing + * delta from a pack. "!no_reuse_delta &&" is implied. + */ + continue; + + if (entry->size < 50) + continue; + free_delta_index(n->index); + n->index = NULL; + free(n->data); + n->data = NULL; + n->entry = entry; + + j = window; + while (--j > 0) { + unsigned int other_idx = idx + j; + struct unpacked *m; + if (other_idx >= window) + other_idx -= window; + m = array + other_idx; + if (!m->entry) + break; + if (try_delta(n, m, depth) < 0) + break; + } + /* if we made n a delta, and if n is already at max + * depth, leaving it in the window is pointless. we + * should evict it first. + */ + if (entry->delta && depth <= entry->depth) + continue; + + idx++; + if (idx >= window) + idx = 0; + } + + if (progress) + fputc('\n', stderr); + + for (i = 0; i < window; ++i) { + free_delta_index(array[i].index); + free(array[i].data); + } + free(array); +} + +static void prepare_pack(int window, int depth) +{ + get_object_details(); + sorted_by_type = create_sorted_list(type_size_sort); + if (window && depth) + find_deltas(sorted_by_type, window+1, depth); +} + +static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout) +{ + static const char cache[] = "pack-cache/pack-%s.%s"; + char *cached_pack, *cached_idx; + int ifd, ofd, ifd_ix = -1; + + cached_pack = git_path(cache, sha1_to_hex(sha1), "pack"); + ifd = open(cached_pack, O_RDONLY); + if (ifd < 0) + return 0; + + if (!pack_to_stdout) { + cached_idx = git_path(cache, sha1_to_hex(sha1), "idx"); + ifd_ix = open(cached_idx, O_RDONLY); + if (ifd_ix < 0) { + close(ifd); + return 0; + } + } + + if (progress) + fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects, + sha1_to_hex(sha1)); + + if (pack_to_stdout) { + if (copy_fd(ifd, 1)) + exit(1); + close(ifd); + } + else { + char name[PATH_MAX]; + snprintf(name, sizeof(name), + "%s-%s.%s", base_name, sha1_to_hex(sha1), "pack"); + ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666); + if (ofd < 0) + die("unable to open %s (%s)", name, strerror(errno)); + if (copy_fd(ifd, ofd)) + exit(1); + close(ifd); + + snprintf(name, sizeof(name), + "%s-%s.%s", base_name, sha1_to_hex(sha1), "idx"); + ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666); + if (ofd < 0) + die("unable to open %s (%s)", name, strerror(errno)); + if (copy_fd(ifd_ix, ofd)) + exit(1); + close(ifd_ix); + puts(sha1_to_hex(sha1)); + } + + return 1; +} + +static void setup_progress_signal(void) +{ + struct sigaction sa; + struct itimerval v; + + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = progress_interval; + sigemptyset(&sa.sa_mask); + sa.sa_flags = SA_RESTART; + sigaction(SIGALRM, &sa, NULL); + + v.it_interval.tv_sec = 1; + v.it_interval.tv_usec = 0; + v.it_value = v.it_interval; + setitimer(ITIMER_REAL, &v, NULL); +} + +static int git_pack_config(const char *k, const char *v) +{ + if(!strcmp(k, "pack.window")) { + window = git_config_int(k, v); + return 0; + } + return git_default_config(k, v); +} + +int cmd_pack_objects(int argc, const char **argv, const char *prefix) +{ + SHA_CTX ctx; + char line[40 + 1 + PATH_MAX + 2]; + int depth = 10, pack_to_stdout = 0; + struct object_entry **list; + int num_preferred_base = 0; + int i; + + git_config(git_pack_config); + + progress = isatty(2); + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + + if (*arg == '-') { + if (!strcmp("--non-empty", arg)) { + non_empty = 1; + continue; + } + if (!strcmp("--local", arg)) { + local = 1; + continue; + } + if (!strcmp("--progress", arg)) { + progress = 1; + continue; + } + if (!strcmp("--incremental", arg)) { + incremental = 1; + continue; + } + if (!strncmp("--window=", arg, 9)) { + char *end; + window = strtoul(arg+9, &end, 0); + if (!arg[9] || *end) + usage(pack_usage); + continue; + } + if (!strncmp("--depth=", arg, 8)) { + char *end; + depth = strtoul(arg+8, &end, 0); + if (!arg[8] || *end) + usage(pack_usage); + continue; + } + if (!strcmp("--progress", arg)) { + progress = 1; + continue; + } + if (!strcmp("-q", arg)) { + progress = 0; + continue; + } + if (!strcmp("--no-reuse-delta", arg)) { + no_reuse_delta = 1; + continue; + } + if (!strcmp("--stdout", arg)) { + pack_to_stdout = 1; + continue; + } + usage(pack_usage); + } + if (base_name) + usage(pack_usage); + base_name = arg; + } + + if (pack_to_stdout != !base_name) + usage(pack_usage); + + prepare_packed_git(); + + if (progress) { + fprintf(stderr, "Generating pack...\n"); + setup_progress_signal(); + } + + for (;;) { + unsigned char sha1[20]; + unsigned hash; + + if (!fgets(line, sizeof(line), stdin)) { + if (feof(stdin)) + break; + if (!ferror(stdin)) + die("fgets returned NULL, not EOF, not error!"); + if (errno != EINTR) + die("fgets: %s", strerror(errno)); + clearerr(stdin); + continue; + } + + if (line[0] == '-') { + if (get_sha1_hex(line+1, sha1)) + die("expected edge sha1, got garbage:\n %s", + line+1); + if (num_preferred_base++ < window) + add_preferred_base(sha1); + continue; + } + if (get_sha1_hex(line, sha1)) + die("expected sha1, got garbage:\n %s", line); + hash = name_hash(line+41); + add_preferred_base_object(line+41, hash); + add_object_entry(sha1, hash, 0); + } + if (progress) + fprintf(stderr, "Done counting %d objects.\n", nr_objects); + sorted_by_sha = create_final_object_list(); + if (non_empty && !nr_result) + return 0; + + SHA1_Init(&ctx); + list = sorted_by_sha; + for (i = 0; i < nr_result; i++) { + struct object_entry *entry = *list++; + SHA1_Update(&ctx, entry->sha1, 20); + } + SHA1_Final(object_list_sha1, &ctx); + if (progress && (nr_objects != nr_result)) + fprintf(stderr, "Result has %d objects.\n", nr_result); + + if (reuse_cached_pack(object_list_sha1, pack_to_stdout)) + ; + else { + if (nr_result) + prepare_pack(window, depth); + if (progress && pack_to_stdout) { + /* the other end usually displays progress itself */ + struct itimerval v = {{0,},}; + setitimer(ITIMER_REAL, &v, NULL); + signal(SIGALRM, SIG_IGN ); + progress_update = 0; + } + write_pack_file(); + if (!pack_to_stdout) { + write_index_file(); + puts(sha1_to_hex(object_list_sha1)); + } + } + if (progress) + fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n", + nr_result, written, written_delta, reused, reused_delta); + return 0; +} diff --git a/builtin.h b/builtin.h index d1d9dc14f9..bc57a04c05 100644 --- a/builtin.h +++ b/builtin.h @@ -50,6 +50,7 @@ extern int cmd_fmt_merge_msg(int argc, const char **argv, const char *prefix); extern int cmd_mv(int argc, const char **argv, const char *prefix); extern int cmd_repo_config(int argc, const char **argv, const char *prefix); extern int cmd_name_rev(int argc, const char **argv, const char *prefix); +extern int cmd_pack_objects(int argc, const char **argv, const char *prefix); extern int cmd_write_tree(int argc, const char **argv, const char *prefix); extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix); diff --git a/git.c b/git.c index 501a7815fc..5d58946f41 100644 --- a/git.c +++ b/git.c @@ -266,6 +266,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "prune-packed", cmd_prune_packed, NEEDS_PREFIX }, { "repo-config", cmd_repo_config }, { "name-rev", cmd_name_rev, NEEDS_PREFIX }, + { "pack-objects", cmd_pack_objects, NEEDS_PREFIX }, }; int i; diff --git a/pack-objects.c b/pack-objects.c deleted file mode 100644 index 861c7f08ff..0000000000 --- a/pack-objects.c +++ /dev/null @@ -1,1376 +0,0 @@ -#include "cache.h" -#include "object.h" -#include "blob.h" -#include "commit.h" -#include "tag.h" -#include "tree.h" -#include "delta.h" -#include "pack.h" -#include "csum-file.h" -#include "tree-walk.h" -#include -#include - -static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list"; - -struct object_entry { - unsigned char sha1[20]; - unsigned long size; /* uncompressed size */ - unsigned long offset; /* offset into the final pack file; - * nonzero if already written. - */ - unsigned int depth; /* delta depth */ - unsigned int delta_limit; /* base adjustment for in-pack delta */ - unsigned int hash; /* name hint hash */ - enum object_type type; - enum object_type in_pack_type; /* could be delta */ - unsigned long delta_size; /* delta data size (uncompressed) */ - struct object_entry *delta; /* delta base object */ - struct packed_git *in_pack; /* already in pack */ - unsigned int in_pack_offset; - struct object_entry *delta_child; /* deltified objects who bases me */ - struct object_entry *delta_sibling; /* other deltified objects who - * uses the same base as me - */ - int preferred_base; /* we do not pack this, but is encouraged to - * be used as the base objectto delta huge - * objects against. - */ -}; - -/* - * Objects we are going to pack are collected in objects array (dynamically - * expanded). nr_objects & nr_alloc controls this array. They are stored - * in the order we see -- typically rev-list --objects order that gives us - * nice "minimum seek" order. - * - * sorted-by-sha ans sorted-by-type are arrays of pointers that point at - * elements in the objects array. The former is used to build the pack - * index (lists object names in the ascending order to help offset lookup), - * and the latter is used to group similar things together by try_delta() - * heuristics. - */ - -static unsigned char object_list_sha1[20]; -static int non_empty = 0; -static int no_reuse_delta = 0; -static int local = 0; -static int incremental = 0; -static struct object_entry **sorted_by_sha, **sorted_by_type; -static struct object_entry *objects = NULL; -static int nr_objects = 0, nr_alloc = 0, nr_result = 0; -static const char *base_name; -static unsigned char pack_file_sha1[20]; -static int progress = 1; -static volatile sig_atomic_t progress_update = 0; -static int window = 10; - -/* - * The object names in objects array are hashed with this hashtable, - * to help looking up the entry by object name. Binary search from - * sorted_by_sha is also possible but this was easier to code and faster. - * This hashtable is built after all the objects are seen. - */ -static int *object_ix = NULL; -static int object_ix_hashsz = 0; - -/* - * Pack index for existing packs give us easy access to the offsets into - * corresponding pack file where each object's data starts, but the entries - * do not store the size of the compressed representation (uncompressed - * size is easily available by examining the pack entry header). We build - * a hashtable of existing packs (pack_revindex), and keep reverse index - * here -- pack index file is sorted by object name mapping to offset; this - * pack_revindex[].revindex array is an ordered list of offsets, so if you - * know the offset of an object, next offset is where its packed - * representation ends. - */ -struct pack_revindex { - struct packed_git *p; - unsigned long *revindex; -} *pack_revindex = NULL; -static int pack_revindex_hashsz = 0; - -/* - * stats - */ -static int written = 0; -static int written_delta = 0; -static int reused = 0; -static int reused_delta = 0; - -static int pack_revindex_ix(struct packed_git *p) -{ - unsigned long ui = (unsigned long)p; - int i; - - ui = ui ^ (ui >> 16); /* defeat structure alignment */ - i = (int)(ui % pack_revindex_hashsz); - while (pack_revindex[i].p) { - if (pack_revindex[i].p == p) - return i; - if (++i == pack_revindex_hashsz) - i = 0; - } - return -1 - i; -} - -static void prepare_pack_ix(void) -{ - int num; - struct packed_git *p; - for (num = 0, p = packed_git; p; p = p->next) - num++; - if (!num) - return; - pack_revindex_hashsz = num * 11; - pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz); - for (p = packed_git; p; p = p->next) { - num = pack_revindex_ix(p); - num = - 1 - num; - pack_revindex[num].p = p; - } - /* revindex elements are lazily initialized */ -} - -static int cmp_offset(const void *a_, const void *b_) -{ - unsigned long a = *(unsigned long *) a_; - unsigned long b = *(unsigned long *) b_; - if (a < b) - return -1; - else if (a == b) - return 0; - else - return 1; -} - -/* - * Ordered list of offsets of objects in the pack. - */ -static void prepare_pack_revindex(struct pack_revindex *rix) -{ - struct packed_git *p = rix->p; - int num_ent = num_packed_objects(p); - int i; - void *index = p->index_base + 256; - - rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1)); - for (i = 0; i < num_ent; i++) { - unsigned int hl = *((unsigned int *)((char *) index + 24*i)); - rix->revindex[i] = ntohl(hl); - } - /* This knows the pack format -- the 20-byte trailer - * follows immediately after the last object data. - */ - rix->revindex[num_ent] = p->pack_size - 20; - qsort(rix->revindex, num_ent, sizeof(unsigned long), cmp_offset); -} - -static unsigned long find_packed_object_size(struct packed_git *p, - unsigned long ofs) -{ - int num; - int lo, hi; - struct pack_revindex *rix; - unsigned long *revindex; - num = pack_revindex_ix(p); - if (num < 0) - die("internal error: pack revindex uninitialized"); - rix = &pack_revindex[num]; - if (!rix->revindex) - prepare_pack_revindex(rix); - revindex = rix->revindex; - lo = 0; - hi = num_packed_objects(p) + 1; - do { - int mi = (lo + hi) / 2; - if (revindex[mi] == ofs) { - return revindex[mi+1] - ofs; - } - else if (ofs < revindex[mi]) - hi = mi; - else - lo = mi + 1; - } while (lo < hi); - die("internal error: pack revindex corrupt"); -} - -static void *delta_against(void *buf, unsigned long size, struct object_entry *entry) -{ - unsigned long othersize, delta_size; - char type[10]; - void *otherbuf = read_sha1_file(entry->delta->sha1, type, &othersize); - void *delta_buf; - - if (!otherbuf) - die("unable to read %s", sha1_to_hex(entry->delta->sha1)); - delta_buf = diff_delta(otherbuf, othersize, - buf, size, &delta_size, 0); - if (!delta_buf || delta_size != entry->delta_size) - die("delta size changed"); - free(buf); - free(otherbuf); - return delta_buf; -} - -/* - * The per-object header is a pretty dense thing, which is - * - first byte: low four bits are "size", then three bits of "type", - * and the high bit is "size continues". - * - each byte afterwards: low seven bits are size continuation, - * with the high bit being "size continues" - */ -static int encode_header(enum object_type type, unsigned long size, unsigned char *hdr) -{ - int n = 1; - unsigned char c; - - if (type < OBJ_COMMIT || type > OBJ_DELTA) - die("bad type %d", type); - - c = (type << 4) | (size & 15); - size >>= 4; - while (size) { - *hdr++ = c | 0x80; - c = size & 0x7f; - size >>= 7; - n++; - } - *hdr = c; - return n; -} - -static unsigned long write_object(struct sha1file *f, - struct object_entry *entry) -{ - unsigned long size; - char type[10]; - void *buf; - unsigned char header[10]; - unsigned hdrlen, datalen; - enum object_type obj_type; - int to_reuse = 0; - - if (entry->preferred_base) - return 0; - - obj_type = entry->type; - if (! entry->in_pack) - to_reuse = 0; /* can't reuse what we don't have */ - else if (obj_type == OBJ_DELTA) - to_reuse = 1; /* check_object() decided it for us */ - else if (obj_type != entry->in_pack_type) - to_reuse = 0; /* pack has delta which is unusable */ - else if (entry->delta) - to_reuse = 0; /* we want to pack afresh */ - else - to_reuse = 1; /* we have it in-pack undeltified, - * and we do not need to deltify it. - */ - - if (! to_reuse) { - buf = read_sha1_file(entry->sha1, type, &size); - if (!buf) - die("unable to read %s", sha1_to_hex(entry->sha1)); - if (size != entry->size) - die("object %s size inconsistency (%lu vs %lu)", - sha1_to_hex(entry->sha1), size, entry->size); - if (entry->delta) { - buf = delta_against(buf, size, entry); - size = entry->delta_size; - obj_type = OBJ_DELTA; - } - /* - * The object header is a byte of 'type' followed by zero or - * more bytes of length. For deltas, the 20 bytes of delta - * sha1 follows that. - */ - hdrlen = encode_header(obj_type, size, header); - sha1write(f, header, hdrlen); - - if (entry->delta) { - sha1write(f, entry->delta, 20); - hdrlen += 20; - } - datalen = sha1write_compressed(f, buf, size); - free(buf); - } - else { - struct packed_git *p = entry->in_pack; - use_packed_git(p); - - datalen = find_packed_object_size(p, entry->in_pack_offset); - buf = (char *) p->pack_base + entry->in_pack_offset; - sha1write(f, buf, datalen); - unuse_packed_git(p); - hdrlen = 0; /* not really */ - if (obj_type == OBJ_DELTA) - reused_delta++; - reused++; - } - if (obj_type == OBJ_DELTA) - written_delta++; - written++; - return hdrlen + datalen; -} - -static unsigned long write_one(struct sha1file *f, - struct object_entry *e, - unsigned long offset) -{ - if (e->offset) - /* offset starts from header size and cannot be zero - * if it is written already. - */ - return offset; - e->offset = offset; - offset += write_object(f, e); - /* if we are deltified, write out its base object. */ - if (e->delta) - offset = write_one(f, e->delta, offset); - return offset; -} - -static void write_pack_file(void) -{ - int i; - struct sha1file *f; - unsigned long offset; - struct pack_header hdr; - unsigned last_percent = 999; - int do_progress = 0; - - if (!base_name) - f = sha1fd(1, ""); - else { - f = sha1create("%s-%s.%s", base_name, - sha1_to_hex(object_list_sha1), "pack"); - do_progress = progress; - } - if (do_progress) - fprintf(stderr, "Writing %d objects.\n", nr_result); - - hdr.hdr_signature = htonl(PACK_SIGNATURE); - hdr.hdr_version = htonl(PACK_VERSION); - hdr.hdr_entries = htonl(nr_result); - sha1write(f, &hdr, sizeof(hdr)); - offset = sizeof(hdr); - if (!nr_result) - goto done; - for (i = 0; i < nr_objects; i++) { - offset = write_one(f, objects + i, offset); - if (do_progress) { - unsigned percent = written * 100 / nr_result; - if (progress_update || percent != last_percent) { - fprintf(stderr, "%4u%% (%u/%u) done\r", - percent, written, nr_result); - progress_update = 0; - last_percent = percent; - } - } - } - if (do_progress) - fputc('\n', stderr); - done: - sha1close(f, pack_file_sha1, 1); -} - -static void write_index_file(void) -{ - int i; - struct sha1file *f = sha1create("%s-%s.%s", base_name, - sha1_to_hex(object_list_sha1), "idx"); - struct object_entry **list = sorted_by_sha; - struct object_entry **last = list + nr_result; - unsigned int array[256]; - - /* - * Write the first-level table (the list is sorted, - * but we use a 256-entry lookup to be able to avoid - * having to do eight extra binary search iterations). - */ - for (i = 0; i < 256; i++) { - struct object_entry **next = list; - while (next < last) { - struct object_entry *entry = *next; - if (entry->sha1[0] != i) - break; - next++; - } - array[i] = htonl(next - sorted_by_sha); - list = next; - } - sha1write(f, array, 256 * sizeof(int)); - - /* - * Write the actual SHA1 entries.. - */ - list = sorted_by_sha; - for (i = 0; i < nr_result; i++) { - struct object_entry *entry = *list++; - unsigned int offset = htonl(entry->offset); - sha1write(f, &offset, 4); - sha1write(f, entry->sha1, 20); - } - sha1write(f, pack_file_sha1, 20); - sha1close(f, NULL, 1); -} - -static int locate_object_entry_hash(const unsigned char *sha1) -{ - int i; - unsigned int ui; - memcpy(&ui, sha1, sizeof(unsigned int)); - i = ui % object_ix_hashsz; - while (0 < object_ix[i]) { - if (!memcmp(sha1, objects[object_ix[i]-1].sha1, 20)) - return i; - if (++i == object_ix_hashsz) - i = 0; - } - return -1 - i; -} - -static struct object_entry *locate_object_entry(const unsigned char *sha1) -{ - int i; - - if (!object_ix_hashsz) - return NULL; - - i = locate_object_entry_hash(sha1); - if (0 <= i) - return &objects[object_ix[i]-1]; - return NULL; -} - -static void rehash_objects(void) -{ - int i; - struct object_entry *oe; - - object_ix_hashsz = nr_objects * 3; - if (object_ix_hashsz < 1024) - object_ix_hashsz = 1024; - object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz); - memset(object_ix, 0, sizeof(int) * object_ix_hashsz); - for (i = 0, oe = objects; i < nr_objects; i++, oe++) { - int ix = locate_object_entry_hash(oe->sha1); - if (0 <= ix) - continue; - ix = -1 - ix; - object_ix[ix] = i + 1; - } -} - -static unsigned name_hash(const char *name) -{ - unsigned char c; - unsigned hash = 0; - - /* - * This effectively just creates a sortable number from the - * last sixteen non-whitespace characters. Last characters - * count "most", so things that end in ".c" sort together. - */ - while ((c = *name++) != 0) { - if (isspace(c)) - continue; - hash = (hash >> 2) + (c << 24); - } - return hash; -} - -static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclude) -{ - unsigned int idx = nr_objects; - struct object_entry *entry; - struct packed_git *p; - unsigned int found_offset = 0; - struct packed_git *found_pack = NULL; - int ix, status = 0; - - if (!exclude) { - for (p = packed_git; p; p = p->next) { - struct pack_entry e; - if (find_pack_entry_one(sha1, &e, p)) { - if (incremental) - return 0; - if (local && !p->pack_local) - return 0; - if (!found_pack) { - found_offset = e.offset; - found_pack = e.p; - } - } - } - } - if ((entry = locate_object_entry(sha1)) != NULL) - goto already_added; - - if (idx >= nr_alloc) { - unsigned int needed = (idx + 1024) * 3 / 2; - objects = xrealloc(objects, needed * sizeof(*entry)); - nr_alloc = needed; - } - entry = objects + idx; - nr_objects = idx + 1; - memset(entry, 0, sizeof(*entry)); - memcpy(entry->sha1, sha1, 20); - entry->hash = hash; - - if (object_ix_hashsz * 3 <= nr_objects * 4) - rehash_objects(); - else { - ix = locate_object_entry_hash(entry->sha1); - if (0 <= ix) - die("internal error in object hashing."); - object_ix[-1 - ix] = idx + 1; - } - status = 1; - - already_added: - if (progress_update) { - fprintf(stderr, "Counting objects...%d\r", nr_objects); - progress_update = 0; - } - if (exclude) - entry->preferred_base = 1; - else { - if (found_pack) { - entry->in_pack = found_pack; - entry->in_pack_offset = found_offset; - } - } - return status; -} - -struct pbase_tree_cache { - unsigned char sha1[20]; - int ref; - int temporary; - void *tree_data; - unsigned long tree_size; -}; - -static struct pbase_tree_cache *(pbase_tree_cache[256]); -static int pbase_tree_cache_ix(const unsigned char *sha1) -{ - return sha1[0] % ARRAY_SIZE(pbase_tree_cache); -} -static int pbase_tree_cache_ix_incr(int ix) -{ - return (ix+1) % ARRAY_SIZE(pbase_tree_cache); -} - -static struct pbase_tree { - struct pbase_tree *next; - /* This is a phony "cache" entry; we are not - * going to evict it nor find it through _get() - * mechanism -- this is for the toplevel node that - * would almost always change with any commit. - */ - struct pbase_tree_cache pcache; -} *pbase_tree; - -static struct pbase_tree_cache *pbase_tree_get(const unsigned char *sha1) -{ - struct pbase_tree_cache *ent, *nent; - void *data; - unsigned long size; - char type[20]; - int neigh; - int my_ix = pbase_tree_cache_ix(sha1); - int available_ix = -1; - - /* pbase-tree-cache acts as a limited hashtable. - * your object will be found at your index or within a few - * slots after that slot if it is cached. - */ - for (neigh = 0; neigh < 8; neigh++) { - ent = pbase_tree_cache[my_ix]; - if (ent && !memcmp(ent->sha1, sha1, 20)) { - ent->ref++; - return ent; - } - else if (((available_ix < 0) && (!ent || !ent->ref)) || - ((0 <= available_ix) && - (!ent && pbase_tree_cache[available_ix]))) - available_ix = my_ix; - if (!ent) - break; - my_ix = pbase_tree_cache_ix_incr(my_ix); - } - - /* Did not find one. Either we got a bogus request or - * we need to read and perhaps cache. - */ - data = read_sha1_file(sha1, type, &size); - if (!data) - return NULL; - if (strcmp(type, tree_type)) { - free(data); - return NULL; - } - - /* We need to either cache or return a throwaway copy */ - - if (available_ix < 0) - ent = NULL; - else { - ent = pbase_tree_cache[available_ix]; - my_ix = available_ix; - } - - if (!ent) { - nent = xmalloc(sizeof(*nent)); - nent->temporary = (available_ix < 0); - } - else { - /* evict and reuse */ - free(ent->tree_data); - nent = ent; - } - memcpy(nent->sha1, sha1, 20); - nent->tree_data = data; - nent->tree_size = size; - nent->ref = 1; - if (!nent->temporary) - pbase_tree_cache[my_ix] = nent; - return nent; -} - -static void pbase_tree_put(struct pbase_tree_cache *cache) -{ - if (!cache->temporary) { - cache->ref--; - return; - } - free(cache->tree_data); - free(cache); -} - -static int name_cmp_len(const char *name) -{ - int i; - for (i = 0; name[i] && name[i] != '\n' && name[i] != '/'; i++) - ; - return i; -} - -static void add_pbase_object(struct tree_desc *tree, - const char *name, - int cmplen, - const char *fullname) -{ - struct name_entry entry; - - while (tree_entry(tree,&entry)) { - unsigned long size; - char type[20]; - - if (entry.pathlen != cmplen || - memcmp(entry.path, name, cmplen) || - !has_sha1_file(entry.sha1) || - sha1_object_info(entry.sha1, type, &size)) - continue; - if (name[cmplen] != '/') { - unsigned hash = name_hash(fullname); - add_object_entry(entry.sha1, hash, 1); - return; - } - if (!strcmp(type, tree_type)) { - struct tree_desc sub; - struct pbase_tree_cache *tree; - const char *down = name+cmplen+1; - int downlen = name_cmp_len(down); - - tree = pbase_tree_get(entry.sha1); - if (!tree) - return; - sub.buf = tree->tree_data; - sub.size = tree->tree_size; - - add_pbase_object(&sub, down, downlen, fullname); - pbase_tree_put(tree); - } - } -} - -static unsigned *done_pbase_paths; -static int done_pbase_paths_num; -static int done_pbase_paths_alloc; -static int done_pbase_path_pos(unsigned hash) -{ - int lo = 0; - int hi = done_pbase_paths_num; - while (lo < hi) { - int mi = (hi + lo) / 2; - if (done_pbase_paths[mi] == hash) - return mi; - if (done_pbase_paths[mi] < hash) - hi = mi; - else - lo = mi + 1; - } - return -lo-1; -} - -static int check_pbase_path(unsigned hash) -{ - int pos = (!done_pbase_paths) ? -1 : done_pbase_path_pos(hash); - if (0 <= pos) - return 1; - pos = -pos - 1; - if (done_pbase_paths_alloc <= done_pbase_paths_num) { - done_pbase_paths_alloc = alloc_nr(done_pbase_paths_alloc); - done_pbase_paths = xrealloc(done_pbase_paths, - done_pbase_paths_alloc * - sizeof(unsigned)); - } - done_pbase_paths_num++; - if (pos < done_pbase_paths_num) - memmove(done_pbase_paths + pos + 1, - done_pbase_paths + pos, - (done_pbase_paths_num - pos - 1) * sizeof(unsigned)); - done_pbase_paths[pos] = hash; - return 0; -} - -static void add_preferred_base_object(char *name, unsigned hash) -{ - struct pbase_tree *it; - int cmplen = name_cmp_len(name); - - if (check_pbase_path(hash)) - return; - - for (it = pbase_tree; it; it = it->next) { - if (cmplen == 0) { - hash = name_hash(""); - add_object_entry(it->pcache.sha1, hash, 1); - } - else { - struct tree_desc tree; - tree.buf = it->pcache.tree_data; - tree.size = it->pcache.tree_size; - add_pbase_object(&tree, name, cmplen, name); - } - } -} - -static void add_preferred_base(unsigned char *sha1) -{ - struct pbase_tree *it; - void *data; - unsigned long size; - unsigned char tree_sha1[20]; - - data = read_object_with_reference(sha1, tree_type, &size, tree_sha1); - if (!data) - return; - - for (it = pbase_tree; it; it = it->next) { - if (!memcmp(it->pcache.sha1, tree_sha1, 20)) { - free(data); - return; - } - } - - it = xcalloc(1, sizeof(*it)); - it->next = pbase_tree; - pbase_tree = it; - - memcpy(it->pcache.sha1, tree_sha1, 20); - it->pcache.tree_data = data; - it->pcache.tree_size = size; -} - -static void check_object(struct object_entry *entry) -{ - char type[20]; - - if (entry->in_pack && !entry->preferred_base) { - unsigned char base[20]; - unsigned long size; - struct object_entry *base_entry; - - /* We want in_pack_type even if we do not reuse delta. - * There is no point not reusing non-delta representations. - */ - check_reuse_pack_delta(entry->in_pack, - entry->in_pack_offset, - base, &size, - &entry->in_pack_type); - - /* Check if it is delta, and the base is also an object - * we are going to pack. If so we will reuse the existing - * delta. - */ - if (!no_reuse_delta && - entry->in_pack_type == OBJ_DELTA && - (base_entry = locate_object_entry(base)) && - (!base_entry->preferred_base)) { - - /* Depth value does not matter - find_deltas() - * will never consider reused delta as the - * base object to deltify other objects - * against, in order to avoid circular deltas. - */ - - /* uncompressed size of the delta data */ - entry->size = entry->delta_size = size; - entry->delta = base_entry; - entry->type = OBJ_DELTA; - - entry->delta_sibling = base_entry->delta_child; - base_entry->delta_child = entry; - - return; - } - /* Otherwise we would do the usual */ - } - - if (sha1_object_info(entry->sha1, type, &entry->size)) - die("unable to get type of object %s", - sha1_to_hex(entry->sha1)); - - if (!strcmp(type, commit_type)) { - entry->type = OBJ_COMMIT; - } else if (!strcmp(type, tree_type)) { - entry->type = OBJ_TREE; - } else if (!strcmp(type, blob_type)) { - entry->type = OBJ_BLOB; - } else if (!strcmp(type, tag_type)) { - entry->type = OBJ_TAG; - } else - die("unable to pack object %s of type %s", - sha1_to_hex(entry->sha1), type); -} - -static unsigned int check_delta_limit(struct object_entry *me, unsigned int n) -{ - struct object_entry *child = me->delta_child; - unsigned int m = n; - while (child) { - unsigned int c = check_delta_limit(child, n + 1); - if (m < c) - m = c; - child = child->delta_sibling; - } - return m; -} - -static void get_object_details(void) -{ - int i; - struct object_entry *entry; - - prepare_pack_ix(); - for (i = 0, entry = objects; i < nr_objects; i++, entry++) - check_object(entry); - - if (nr_objects == nr_result) { - /* - * Depth of objects that depend on the entry -- this - * is subtracted from depth-max to break too deep - * delta chain because of delta data reusing. - * However, we loosen this restriction when we know we - * are creating a thin pack -- it will have to be - * expanded on the other end anyway, so do not - * artificially cut the delta chain and let it go as - * deep as it wants. - */ - for (i = 0, entry = objects; i < nr_objects; i++, entry++) - if (!entry->delta && entry->delta_child) - entry->delta_limit = - check_delta_limit(entry, 1); - } -} - -typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *); - -static entry_sort_t current_sort; - -static int sort_comparator(const void *_a, const void *_b) -{ - struct object_entry *a = *(struct object_entry **)_a; - struct object_entry *b = *(struct object_entry **)_b; - return current_sort(a,b); -} - -static struct object_entry **create_sorted_list(entry_sort_t sort) -{ - struct object_entry **list = xmalloc(nr_objects * sizeof(struct object_entry *)); - int i; - - for (i = 0; i < nr_objects; i++) - list[i] = objects + i; - current_sort = sort; - qsort(list, nr_objects, sizeof(struct object_entry *), sort_comparator); - return list; -} - -static int sha1_sort(const struct object_entry *a, const struct object_entry *b) -{ - return memcmp(a->sha1, b->sha1, 20); -} - -static struct object_entry **create_final_object_list(void) -{ - struct object_entry **list; - int i, j; - - for (i = nr_result = 0; i < nr_objects; i++) - if (!objects[i].preferred_base) - nr_result++; - list = xmalloc(nr_result * sizeof(struct object_entry *)); - for (i = j = 0; i < nr_objects; i++) { - if (!objects[i].preferred_base) - list[j++] = objects + i; - } - current_sort = sha1_sort; - qsort(list, nr_result, sizeof(struct object_entry *), sort_comparator); - return list; -} - -static int type_size_sort(const struct object_entry *a, const struct object_entry *b) -{ - if (a->type < b->type) - return -1; - if (a->type > b->type) - return 1; - if (a->hash < b->hash) - return -1; - if (a->hash > b->hash) - return 1; - if (a->preferred_base < b->preferred_base) - return -1; - if (a->preferred_base > b->preferred_base) - return 1; - if (a->size < b->size) - return -1; - if (a->size > b->size) - return 1; - return a < b ? -1 : (a > b); -} - -struct unpacked { - struct object_entry *entry; - void *data; - struct delta_index *index; -}; - -/* - * We search for deltas _backwards_ in a list sorted by type and - * by size, so that we see progressively smaller and smaller files. - * That's because we prefer deltas to be from the bigger file - * to the smaller - deletes are potentially cheaper, but perhaps - * more importantly, the bigger file is likely the more recent - * one. - */ -static int try_delta(struct unpacked *trg, struct unpacked *src, - unsigned max_depth) -{ - struct object_entry *trg_entry = trg->entry; - struct object_entry *src_entry = src->entry; - unsigned long trg_size, src_size, delta_size, sizediff, max_size, sz; - char type[10]; - void *delta_buf; - - /* Don't bother doing diffs between different types */ - if (trg_entry->type != src_entry->type) - return -1; - - /* We do not compute delta to *create* objects we are not - * going to pack. - */ - if (trg_entry->preferred_base) - return -1; - - /* - * We do not bother to try a delta that we discarded - * on an earlier try, but only when reusing delta data. - */ - if (!no_reuse_delta && trg_entry->in_pack && - trg_entry->in_pack == src_entry->in_pack) - return 0; - - /* - * If the current object is at pack edge, take the depth the - * objects that depend on the current object into account -- - * otherwise they would become too deep. - */ - if (trg_entry->delta_child) { - if (max_depth <= trg_entry->delta_limit) - return 0; - max_depth -= trg_entry->delta_limit; - } - if (src_entry->depth >= max_depth) - return 0; - - /* Now some size filtering heuristics. */ - trg_size = trg_entry->size; - max_size = trg_size/2 - 20; - max_size = max_size * (max_depth - src_entry->depth) / max_depth; - if (max_size == 0) - return 0; - if (trg_entry->delta && trg_entry->delta_size <= max_size) - max_size = trg_entry->delta_size-1; - src_size = src_entry->size; - sizediff = src_size < trg_size ? trg_size - src_size : 0; - if (sizediff >= max_size) - return 0; - - /* Load data if not already done */ - if (!trg->data) { - trg->data = read_sha1_file(trg_entry->sha1, type, &sz); - if (sz != trg_size) - die("object %s inconsistent object length (%lu vs %lu)", - sha1_to_hex(trg_entry->sha1), sz, trg_size); - } - if (!src->data) { - src->data = read_sha1_file(src_entry->sha1, type, &sz); - if (sz != src_size) - die("object %s inconsistent object length (%lu vs %lu)", - sha1_to_hex(src_entry->sha1), sz, src_size); - } - if (!src->index) { - src->index = create_delta_index(src->data, src_size); - if (!src->index) - die("out of memory"); - } - - delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size); - if (!delta_buf) - return 0; - - trg_entry->delta = src_entry; - trg_entry->delta_size = delta_size; - trg_entry->depth = src_entry->depth + 1; - free(delta_buf); - return 1; -} - -static void progress_interval(int signum) -{ - progress_update = 1; -} - -static void find_deltas(struct object_entry **list, int window, int depth) -{ - int i, idx; - unsigned int array_size = window * sizeof(struct unpacked); - struct unpacked *array = xmalloc(array_size); - unsigned processed = 0; - unsigned last_percent = 999; - - memset(array, 0, array_size); - i = nr_objects; - idx = 0; - if (progress) - fprintf(stderr, "Deltifying %d objects.\n", nr_result); - - while (--i >= 0) { - struct object_entry *entry = list[i]; - struct unpacked *n = array + idx; - int j; - - if (!entry->preferred_base) - processed++; - - if (progress) { - unsigned percent = processed * 100 / nr_result; - if (percent != last_percent || progress_update) { - fprintf(stderr, "%4u%% (%u/%u) done\r", - percent, processed, nr_result); - progress_update = 0; - last_percent = percent; - } - } - - if (entry->delta) - /* This happens if we decided to reuse existing - * delta from a pack. "!no_reuse_delta &&" is implied. - */ - continue; - - if (entry->size < 50) - continue; - free_delta_index(n->index); - n->index = NULL; - free(n->data); - n->data = NULL; - n->entry = entry; - - j = window; - while (--j > 0) { - unsigned int other_idx = idx + j; - struct unpacked *m; - if (other_idx >= window) - other_idx -= window; - m = array + other_idx; - if (!m->entry) - break; - if (try_delta(n, m, depth) < 0) - break; - } - /* if we made n a delta, and if n is already at max - * depth, leaving it in the window is pointless. we - * should evict it first. - */ - if (entry->delta && depth <= entry->depth) - continue; - - idx++; - if (idx >= window) - idx = 0; - } - - if (progress) - fputc('\n', stderr); - - for (i = 0; i < window; ++i) { - free_delta_index(array[i].index); - free(array[i].data); - } - free(array); -} - -static void prepare_pack(int window, int depth) -{ - get_object_details(); - sorted_by_type = create_sorted_list(type_size_sort); - if (window && depth) - find_deltas(sorted_by_type, window+1, depth); -} - -static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout) -{ - static const char cache[] = "pack-cache/pack-%s.%s"; - char *cached_pack, *cached_idx; - int ifd, ofd, ifd_ix = -1; - - cached_pack = git_path(cache, sha1_to_hex(sha1), "pack"); - ifd = open(cached_pack, O_RDONLY); - if (ifd < 0) - return 0; - - if (!pack_to_stdout) { - cached_idx = git_path(cache, sha1_to_hex(sha1), "idx"); - ifd_ix = open(cached_idx, O_RDONLY); - if (ifd_ix < 0) { - close(ifd); - return 0; - } - } - - if (progress) - fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects, - sha1_to_hex(sha1)); - - if (pack_to_stdout) { - if (copy_fd(ifd, 1)) - exit(1); - close(ifd); - } - else { - char name[PATH_MAX]; - snprintf(name, sizeof(name), - "%s-%s.%s", base_name, sha1_to_hex(sha1), "pack"); - ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666); - if (ofd < 0) - die("unable to open %s (%s)", name, strerror(errno)); - if (copy_fd(ifd, ofd)) - exit(1); - close(ifd); - - snprintf(name, sizeof(name), - "%s-%s.%s", base_name, sha1_to_hex(sha1), "idx"); - ofd = open(name, O_CREAT | O_EXCL | O_WRONLY, 0666); - if (ofd < 0) - die("unable to open %s (%s)", name, strerror(errno)); - if (copy_fd(ifd_ix, ofd)) - exit(1); - close(ifd_ix); - puts(sha1_to_hex(sha1)); - } - - return 1; -} - -static void setup_progress_signal(void) -{ - struct sigaction sa; - struct itimerval v; - - memset(&sa, 0, sizeof(sa)); - sa.sa_handler = progress_interval; - sigemptyset(&sa.sa_mask); - sa.sa_flags = SA_RESTART; - sigaction(SIGALRM, &sa, NULL); - - v.it_interval.tv_sec = 1; - v.it_interval.tv_usec = 0; - v.it_value = v.it_interval; - setitimer(ITIMER_REAL, &v, NULL); -} - -static int git_pack_config(const char *k, const char *v) -{ - if(!strcmp(k, "pack.window")) { - window = git_config_int(k, v); - return 0; - } - return git_default_config(k, v); -} - -int main(int argc, char **argv) -{ - SHA_CTX ctx; - char line[40 + 1 + PATH_MAX + 2]; - int depth = 10, pack_to_stdout = 0; - struct object_entry **list; - int num_preferred_base = 0; - int i; - - setup_git_directory(); - git_config(git_pack_config); - - progress = isatty(2); - for (i = 1; i < argc; i++) { - const char *arg = argv[i]; - - if (*arg == '-') { - if (!strcmp("--non-empty", arg)) { - non_empty = 1; - continue; - } - if (!strcmp("--local", arg)) { - local = 1; - continue; - } - if (!strcmp("--progress", arg)) { - progress = 1; - continue; - } - if (!strcmp("--incremental", arg)) { - incremental = 1; - continue; - } - if (!strncmp("--window=", arg, 9)) { - char *end; - window = strtoul(arg+9, &end, 0); - if (!arg[9] || *end) - usage(pack_usage); - continue; - } - if (!strncmp("--depth=", arg, 8)) { - char *end; - depth = strtoul(arg+8, &end, 0); - if (!arg[8] || *end) - usage(pack_usage); - continue; - } - if (!strcmp("--progress", arg)) { - progress = 1; - continue; - } - if (!strcmp("-q", arg)) { - progress = 0; - continue; - } - if (!strcmp("--no-reuse-delta", arg)) { - no_reuse_delta = 1; - continue; - } - if (!strcmp("--stdout", arg)) { - pack_to_stdout = 1; - continue; - } - usage(pack_usage); - } - if (base_name) - usage(pack_usage); - base_name = arg; - } - - if (pack_to_stdout != !base_name) - usage(pack_usage); - - prepare_packed_git(); - - if (progress) { - fprintf(stderr, "Generating pack...\n"); - setup_progress_signal(); - } - - for (;;) { - unsigned char sha1[20]; - unsigned hash; - - if (!fgets(line, sizeof(line), stdin)) { - if (feof(stdin)) - break; - if (!ferror(stdin)) - die("fgets returned NULL, not EOF, not error!"); - if (errno != EINTR) - die("fgets: %s", strerror(errno)); - clearerr(stdin); - continue; - } - - if (line[0] == '-') { - if (get_sha1_hex(line+1, sha1)) - die("expected edge sha1, got garbage:\n %s", - line+1); - if (num_preferred_base++ < window) - add_preferred_base(sha1); - continue; - } - if (get_sha1_hex(line, sha1)) - die("expected sha1, got garbage:\n %s", line); - hash = name_hash(line+41); - add_preferred_base_object(line+41, hash); - add_object_entry(sha1, hash, 0); - } - if (progress) - fprintf(stderr, "Done counting %d objects.\n", nr_objects); - sorted_by_sha = create_final_object_list(); - if (non_empty && !nr_result) - return 0; - - SHA1_Init(&ctx); - list = sorted_by_sha; - for (i = 0; i < nr_result; i++) { - struct object_entry *entry = *list++; - SHA1_Update(&ctx, entry->sha1, 20); - } - SHA1_Final(object_list_sha1, &ctx); - if (progress && (nr_objects != nr_result)) - fprintf(stderr, "Result has %d objects.\n", nr_result); - - if (reuse_cached_pack(object_list_sha1, pack_to_stdout)) - ; - else { - if (nr_result) - prepare_pack(window, depth); - if (progress && pack_to_stdout) { - /* the other end usually displays progress itself */ - struct itimerval v = {{0,},}; - setitimer(ITIMER_REAL, &v, NULL); - signal(SIGALRM, SIG_IGN ); - progress_update = 0; - } - write_pack_file(); - if (!pack_to_stdout) { - write_index_file(); - puts(sha1_to_hex(object_list_sha1)); - } - } - if (progress) - fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n", - nr_result, written, written_delta, reused, reused_delta); - return 0; -} -- cgit v1.2.1 From 6441363079d85cf17aee21b8925e9745c8abda16 Mon Sep 17 00:00:00 2001 From: Matthias Kestenholz Date: Thu, 3 Aug 2006 17:24:37 +0200 Subject: Make git-unpack-objects a builtin Signed-off-by: Matthias Kestenholz Signed-off-by: Junio C Hamano --- Makefile | 7 +- builtin-unpack-objects.c | 310 ++++++++++++++++++++++++++++++++++++++++++++++ builtin.h | 1 + git.c | 1 + unpack-objects.c | 311 ----------------------------------------------- 5 files changed, 316 insertions(+), 314 deletions(-) create mode 100644 builtin-unpack-objects.c delete mode 100644 unpack-objects.c diff --git a/Makefile b/Makefile index 4fd62bcf6d..b108a8aa7a 100644 --- a/Makefile +++ b/Makefile @@ -182,7 +182,7 @@ PROGRAMS = \ git-send-pack$X git-shell$X \ git-show-index$X git-ssh-fetch$X \ git-ssh-upload$X git-unpack-file$X \ - git-unpack-objects$X git-update-server-info$X \ + git-update-server-info$X \ git-upload-pack$X git-verify-pack$X \ git-symbolic-ref$X \ git-pack-redundant$X git-var$X \ @@ -198,7 +198,8 @@ BUILT_INS = git-log$X git-whatchanged$X git-show$X git-update-ref$X \ git-apply$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-prune$X git-mv$X git-prune-packed$X \ - git-repo-config$X git-name-rev$X git-pack-objects$X + git-repo-config$X git-name-rev$X git-pack-objects$X \ + git-unpack-objects$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -256,7 +257,7 @@ BUILTIN_OBJS = \ builtin-cat-file.o builtin-mailsplit.o builtin-stripspace.o \ builtin-update-ref.o builtin-fmt-merge-msg.o builtin-prune.o \ builtin-mv.o builtin-prune-packed.o builtin-repo-config.o \ - builtin-name-rev.o builtin-pack-objects.o + builtin-name-rev.o builtin-pack-objects.o builtin-unpack-objects.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-unpack-objects.c b/builtin-unpack-objects.c new file mode 100644 index 0000000000..09d264d9f2 --- /dev/null +++ b/builtin-unpack-objects.c @@ -0,0 +1,310 @@ +#include "builtin.h" +#include "cache.h" +#include "object.h" +#include "delta.h" +#include "pack.h" +#include "blob.h" +#include "commit.h" +#include "tag.h" +#include "tree.h" + +#include + +static int dry_run, quiet; +static const char unpack_usage[] = "git-unpack-objects [-n] [-q] < pack-file"; + +/* We always read in 4kB chunks. */ +static unsigned char buffer[4096]; +static unsigned long offset, len, eof; +static SHA_CTX ctx; + +/* + * Make sure at least "min" bytes are available in the buffer, and + * return the pointer to the buffer. + */ +static void * fill(int min) +{ + if (min <= len) + return buffer + offset; + if (eof) + die("unable to fill input"); + if (min > sizeof(buffer)) + die("cannot fill %d bytes", min); + if (offset) { + SHA1_Update(&ctx, buffer, offset); + memcpy(buffer, buffer + offset, len); + offset = 0; + } + do { + int ret = xread(0, buffer + len, sizeof(buffer) - len); + if (ret <= 0) { + if (!ret) + die("early EOF"); + die("read error on input: %s", strerror(errno)); + } + len += ret; + } while (len < min); + return buffer; +} + +static void use(int bytes) +{ + if (bytes > len) + die("used more bytes than were available"); + len -= bytes; + offset += bytes; +} + +static void *get_data(unsigned long size) +{ + z_stream stream; + void *buf = xmalloc(size); + + memset(&stream, 0, sizeof(stream)); + + stream.next_out = buf; + stream.avail_out = size; + stream.next_in = fill(1); + stream.avail_in = len; + inflateInit(&stream); + + for (;;) { + int ret = inflate(&stream, 0); + use(len - stream.avail_in); + if (stream.total_out == size && ret == Z_STREAM_END) + break; + if (ret != Z_OK) + die("inflate returned %d\n", ret); + stream.next_in = fill(1); + stream.avail_in = len; + } + inflateEnd(&stream); + return buf; +} + +struct delta_info { + unsigned char base_sha1[20]; + unsigned long size; + void *delta; + struct delta_info *next; +}; + +static struct delta_info *delta_list; + +static void add_delta_to_list(unsigned char *base_sha1, void *delta, unsigned long size) +{ + struct delta_info *info = xmalloc(sizeof(*info)); + + memcpy(info->base_sha1, base_sha1, 20); + info->size = size; + info->delta = delta; + info->next = delta_list; + delta_list = info; +} + +static void added_object(unsigned char *sha1, const char *type, void *data, unsigned long size); + +static void write_object(void *buf, unsigned long size, const char *type) +{ + unsigned char sha1[20]; + if (write_sha1_file(buf, size, type, sha1) < 0) + die("failed to write object"); + added_object(sha1, type, buf, size); +} + +static int resolve_delta(const char *type, + void *base, unsigned long base_size, + void *delta, unsigned long delta_size) +{ + void *result; + unsigned long result_size; + + result = patch_delta(base, base_size, + delta, delta_size, + &result_size); + if (!result) + die("failed to apply delta"); + free(delta); + write_object(result, result_size, type); + free(result); + return 0; +} + +static void added_object(unsigned char *sha1, const char *type, void *data, unsigned long size) +{ + struct delta_info **p = &delta_list; + struct delta_info *info; + + while ((info = *p) != NULL) { + if (!memcmp(info->base_sha1, sha1, 20)) { + *p = info->next; + p = &delta_list; + resolve_delta(type, data, size, info->delta, info->size); + free(info); + continue; + } + p = &info->next; + } +} + +static int unpack_non_delta_entry(enum object_type kind, unsigned long size) +{ + void *buf = get_data(size); + const char *type; + + switch (kind) { + case OBJ_COMMIT: type = commit_type; break; + case OBJ_TREE: type = tree_type; break; + case OBJ_BLOB: type = blob_type; break; + case OBJ_TAG: type = tag_type; break; + default: die("bad type %d", kind); + } + if (!dry_run) + write_object(buf, size, type); + free(buf); + return 0; +} + +static int unpack_delta_entry(unsigned long delta_size) +{ + void *delta_data, *base; + unsigned long base_size; + char type[20]; + unsigned char base_sha1[20]; + int result; + + memcpy(base_sha1, fill(20), 20); + use(20); + + delta_data = get_data(delta_size); + if (dry_run) { + free(delta_data); + return 0; + } + + if (!has_sha1_file(base_sha1)) { + add_delta_to_list(base_sha1, delta_data, delta_size); + return 0; + } + base = read_sha1_file(base_sha1, type, &base_size); + if (!base) + die("failed to read delta-pack base object %s", sha1_to_hex(base_sha1)); + result = resolve_delta(type, base, base_size, delta_data, delta_size); + free(base); + return result; +} + +static void unpack_one(unsigned nr, unsigned total) +{ + unsigned shift; + unsigned char *pack, c; + unsigned long size; + enum object_type type; + + pack = fill(1); + c = *pack; + use(1); + type = (c >> 4) & 7; + size = (c & 15); + shift = 4; + while (c & 0x80) { + pack = fill(1); + c = *pack++; + use(1); + size += (c & 0x7f) << shift; + shift += 7; + } + if (!quiet) { + static unsigned long last_sec; + static unsigned last_percent; + struct timeval now; + unsigned percentage = (nr * 100) / total; + + gettimeofday(&now, NULL); + if (percentage != last_percent || now.tv_sec != last_sec) { + last_sec = now.tv_sec; + last_percent = percentage; + fprintf(stderr, "%4u%% (%u/%u) done\r", percentage, nr, total); + } + } + switch (type) { + case OBJ_COMMIT: + case OBJ_TREE: + case OBJ_BLOB: + case OBJ_TAG: + unpack_non_delta_entry(type, size); + return; + case OBJ_DELTA: + unpack_delta_entry(size); + return; + default: + die("bad object type %d", type); + } +} + +static void unpack_all(void) +{ + int i; + struct pack_header *hdr = fill(sizeof(struct pack_header)); + unsigned nr_objects = ntohl(hdr->hdr_entries); + + if (ntohl(hdr->hdr_signature) != PACK_SIGNATURE) + die("bad pack file"); + if (!pack_version_ok(hdr->hdr_version)) + die("unknown pack file version %d", ntohl(hdr->hdr_version)); + fprintf(stderr, "Unpacking %d objects\n", nr_objects); + + use(sizeof(struct pack_header)); + for (i = 0; i < nr_objects; i++) + unpack_one(i+1, nr_objects); + if (delta_list) + die("unresolved deltas left after unpacking"); +} + +int cmd_unpack_objects(int argc, const char **argv, const char *prefix) +{ + int i; + unsigned char sha1[20]; + + quiet = !isatty(2); + + for (i = 1 ; i < argc; i++) { + const char *arg = argv[i]; + + if (*arg == '-') { + if (!strcmp(arg, "-n")) { + dry_run = 1; + continue; + } + if (!strcmp(arg, "-q")) { + quiet = 1; + continue; + } + usage(unpack_usage); + } + + /* We don't take any non-flag arguments now.. Maybe some day */ + usage(unpack_usage); + } + SHA1_Init(&ctx); + unpack_all(); + SHA1_Update(&ctx, buffer, offset); + SHA1_Final(sha1, &ctx); + if (memcmp(fill(20), sha1, 20)) + die("final sha1 did not match"); + use(20); + + /* Write the last part of the buffer to stdout */ + while (len) { + int ret = xwrite(1, buffer + offset, len); + if (ret <= 0) + break; + len -= ret; + offset += ret; + } + + /* All done */ + if (!quiet) + fprintf(stderr, "\n"); + return 0; +} diff --git a/builtin.h b/builtin.h index bc57a04c05..af73c3c19e 100644 --- a/builtin.h +++ b/builtin.h @@ -51,6 +51,7 @@ extern int cmd_mv(int argc, const char **argv, const char *prefix); extern int cmd_repo_config(int argc, const char **argv, const char *prefix); extern int cmd_name_rev(int argc, const char **argv, const char *prefix); extern int cmd_pack_objects(int argc, const char **argv, const char *prefix); +extern int cmd_unpack_objects(int argc, const char **argv, const char *prefix); extern int cmd_write_tree(int argc, const char **argv, const char *prefix); extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix); diff --git a/git.c b/git.c index 5d58946f41..7c3a7f8fd1 100644 --- a/git.c +++ b/git.c @@ -267,6 +267,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "repo-config", cmd_repo_config }, { "name-rev", cmd_name_rev, NEEDS_PREFIX }, { "pack-objects", cmd_pack_objects, NEEDS_PREFIX }, + { "unpack-objects", cmd_unpack_objects, NEEDS_PREFIX }, }; int i; diff --git a/unpack-objects.c b/unpack-objects.c deleted file mode 100644 index 48c1ee7968..0000000000 --- a/unpack-objects.c +++ /dev/null @@ -1,311 +0,0 @@ -#include "cache.h" -#include "object.h" -#include "delta.h" -#include "pack.h" -#include "blob.h" -#include "commit.h" -#include "tag.h" -#include "tree.h" - -#include - -static int dry_run, quiet; -static const char unpack_usage[] = "git-unpack-objects [-n] [-q] < pack-file"; - -/* We always read in 4kB chunks. */ -static unsigned char buffer[4096]; -static unsigned long offset, len, eof; -static SHA_CTX ctx; - -/* - * Make sure at least "min" bytes are available in the buffer, and - * return the pointer to the buffer. - */ -static void * fill(int min) -{ - if (min <= len) - return buffer + offset; - if (eof) - die("unable to fill input"); - if (min > sizeof(buffer)) - die("cannot fill %d bytes", min); - if (offset) { - SHA1_Update(&ctx, buffer, offset); - memcpy(buffer, buffer + offset, len); - offset = 0; - } - do { - int ret = xread(0, buffer + len, sizeof(buffer) - len); - if (ret <= 0) { - if (!ret) - die("early EOF"); - die("read error on input: %s", strerror(errno)); - } - len += ret; - } while (len < min); - return buffer; -} - -static void use(int bytes) -{ - if (bytes > len) - die("used more bytes than were available"); - len -= bytes; - offset += bytes; -} - -static void *get_data(unsigned long size) -{ - z_stream stream; - void *buf = xmalloc(size); - - memset(&stream, 0, sizeof(stream)); - - stream.next_out = buf; - stream.avail_out = size; - stream.next_in = fill(1); - stream.avail_in = len; - inflateInit(&stream); - - for (;;) { - int ret = inflate(&stream, 0); - use(len - stream.avail_in); - if (stream.total_out == size && ret == Z_STREAM_END) - break; - if (ret != Z_OK) - die("inflate returned %d\n", ret); - stream.next_in = fill(1); - stream.avail_in = len; - } - inflateEnd(&stream); - return buf; -} - -struct delta_info { - unsigned char base_sha1[20]; - unsigned long size; - void *delta; - struct delta_info *next; -}; - -static struct delta_info *delta_list; - -static void add_delta_to_list(unsigned char *base_sha1, void *delta, unsigned long size) -{ - struct delta_info *info = xmalloc(sizeof(*info)); - - memcpy(info->base_sha1, base_sha1, 20); - info->size = size; - info->delta = delta; - info->next = delta_list; - delta_list = info; -} - -static void added_object(unsigned char *sha1, const char *type, void *data, unsigned long size); - -static void write_object(void *buf, unsigned long size, const char *type) -{ - unsigned char sha1[20]; - if (write_sha1_file(buf, size, type, sha1) < 0) - die("failed to write object"); - added_object(sha1, type, buf, size); -} - -static int resolve_delta(const char *type, - void *base, unsigned long base_size, - void *delta, unsigned long delta_size) -{ - void *result; - unsigned long result_size; - - result = patch_delta(base, base_size, - delta, delta_size, - &result_size); - if (!result) - die("failed to apply delta"); - free(delta); - write_object(result, result_size, type); - free(result); - return 0; -} - -static void added_object(unsigned char *sha1, const char *type, void *data, unsigned long size) -{ - struct delta_info **p = &delta_list; - struct delta_info *info; - - while ((info = *p) != NULL) { - if (!memcmp(info->base_sha1, sha1, 20)) { - *p = info->next; - p = &delta_list; - resolve_delta(type, data, size, info->delta, info->size); - free(info); - continue; - } - p = &info->next; - } -} - -static int unpack_non_delta_entry(enum object_type kind, unsigned long size) -{ - void *buf = get_data(size); - const char *type; - - switch (kind) { - case OBJ_COMMIT: type = commit_type; break; - case OBJ_TREE: type = tree_type; break; - case OBJ_BLOB: type = blob_type; break; - case OBJ_TAG: type = tag_type; break; - default: die("bad type %d", kind); - } - if (!dry_run) - write_object(buf, size, type); - free(buf); - return 0; -} - -static int unpack_delta_entry(unsigned long delta_size) -{ - void *delta_data, *base; - unsigned long base_size; - char type[20]; - unsigned char base_sha1[20]; - int result; - - memcpy(base_sha1, fill(20), 20); - use(20); - - delta_data = get_data(delta_size); - if (dry_run) { - free(delta_data); - return 0; - } - - if (!has_sha1_file(base_sha1)) { - add_delta_to_list(base_sha1, delta_data, delta_size); - return 0; - } - base = read_sha1_file(base_sha1, type, &base_size); - if (!base) - die("failed to read delta-pack base object %s", sha1_to_hex(base_sha1)); - result = resolve_delta(type, base, base_size, delta_data, delta_size); - free(base); - return result; -} - -static void unpack_one(unsigned nr, unsigned total) -{ - unsigned shift; - unsigned char *pack, c; - unsigned long size; - enum object_type type; - - pack = fill(1); - c = *pack; - use(1); - type = (c >> 4) & 7; - size = (c & 15); - shift = 4; - while (c & 0x80) { - pack = fill(1); - c = *pack++; - use(1); - size += (c & 0x7f) << shift; - shift += 7; - } - if (!quiet) { - static unsigned long last_sec; - static unsigned last_percent; - struct timeval now; - unsigned percentage = (nr * 100) / total; - - gettimeofday(&now, NULL); - if (percentage != last_percent || now.tv_sec != last_sec) { - last_sec = now.tv_sec; - last_percent = percentage; - fprintf(stderr, "%4u%% (%u/%u) done\r", percentage, nr, total); - } - } - switch (type) { - case OBJ_COMMIT: - case OBJ_TREE: - case OBJ_BLOB: - case OBJ_TAG: - unpack_non_delta_entry(type, size); - return; - case OBJ_DELTA: - unpack_delta_entry(size); - return; - default: - die("bad object type %d", type); - } -} - -static void unpack_all(void) -{ - int i; - struct pack_header *hdr = fill(sizeof(struct pack_header)); - unsigned nr_objects = ntohl(hdr->hdr_entries); - - if (ntohl(hdr->hdr_signature) != PACK_SIGNATURE) - die("bad pack file"); - if (!pack_version_ok(hdr->hdr_version)) - die("unknown pack file version %d", ntohl(hdr->hdr_version)); - fprintf(stderr, "Unpacking %d objects\n", nr_objects); - - use(sizeof(struct pack_header)); - for (i = 0; i < nr_objects; i++) - unpack_one(i+1, nr_objects); - if (delta_list) - die("unresolved deltas left after unpacking"); -} - -int main(int argc, char **argv) -{ - int i; - unsigned char sha1[20]; - - setup_git_directory(); - - quiet = !isatty(2); - - for (i = 1 ; i < argc; i++) { - const char *arg = argv[i]; - - if (*arg == '-') { - if (!strcmp(arg, "-n")) { - dry_run = 1; - continue; - } - if (!strcmp(arg, "-q")) { - quiet = 1; - continue; - } - usage(unpack_usage); - } - - /* We don't take any non-flag arguments now.. Maybe some day */ - usage(unpack_usage); - } - SHA1_Init(&ctx); - unpack_all(); - SHA1_Update(&ctx, buffer, offset); - SHA1_Final(sha1, &ctx); - if (memcmp(fill(20), sha1, 20)) - die("final sha1 did not match"); - use(20); - - /* Write the last part of the buffer to stdout */ - while (len) { - int ret = xwrite(1, buffer + offset, len); - if (ret <= 0) - break; - len -= ret; - offset += ret; - } - - /* All done */ - if (!quiet) - fprintf(stderr, "\n"); - return 0; -} -- cgit v1.2.1 From 640ce1052bbd6a8f1dd4d58beaa521d7592a0f02 Mon Sep 17 00:00:00 2001 From: Matthias Kestenholz Date: Thu, 3 Aug 2006 17:24:38 +0200 Subject: Make git-symbolic-ref a builtin Signed-off-by: Matthias Kestenholz Signed-off-by: Junio C Hamano --- Makefile | 6 +++--- builtin-symbolic-ref.c | 35 +++++++++++++++++++++++++++++++++++ builtin.h | 1 + git.c | 1 + symbolic-ref.c | 35 ----------------------------------- 5 files changed, 40 insertions(+), 38 deletions(-) create mode 100644 builtin-symbolic-ref.c delete mode 100644 symbolic-ref.c diff --git a/Makefile b/Makefile index b108a8aa7a..db59e00ede 100644 --- a/Makefile +++ b/Makefile @@ -184,7 +184,6 @@ PROGRAMS = \ git-ssh-upload$X git-unpack-file$X \ git-update-server-info$X \ git-upload-pack$X git-verify-pack$X \ - git-symbolic-ref$X \ git-pack-redundant$X git-var$X \ git-describe$X git-merge-tree$X git-blame$X git-imap-send$X @@ -199,7 +198,7 @@ BUILT_INS = git-log$X git-whatchanged$X git-show$X git-update-ref$X \ git-diff-index$X git-diff-stages$X git-diff-tree$X git-cat-file$X \ git-fmt-merge-msg$X git-prune$X git-mv$X git-prune-packed$X \ git-repo-config$X git-name-rev$X git-pack-objects$X \ - git-unpack-objects$X + git-unpack-objects$X git-symbolic-ref$X # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -257,7 +256,8 @@ BUILTIN_OBJS = \ builtin-cat-file.o builtin-mailsplit.o builtin-stripspace.o \ builtin-update-ref.o builtin-fmt-merge-msg.o builtin-prune.o \ builtin-mv.o builtin-prune-packed.o builtin-repo-config.o \ - builtin-name-rev.o builtin-pack-objects.o builtin-unpack-objects.o + builtin-name-rev.o builtin-pack-objects.o builtin-unpack-objects.o \ + builtin-symbolic-ref.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz diff --git a/builtin-symbolic-ref.c b/builtin-symbolic-ref.c new file mode 100644 index 0000000000..b4ec6f28ed --- /dev/null +++ b/builtin-symbolic-ref.c @@ -0,0 +1,35 @@ +#include "builtin.h" +#include "cache.h" + +static const char git_symbolic_ref_usage[] = +"git-symbolic-ref name [ref]"; + +static void check_symref(const char *HEAD) +{ + unsigned char sha1[20]; + const char *git_HEAD = strdup(git_path("%s", HEAD)); + const char *git_refs_heads_master = resolve_ref(git_HEAD, sha1, 0); + if (git_refs_heads_master) { + /* we want to strip the .git/ part */ + int pfxlen = strlen(git_HEAD) - strlen(HEAD); + puts(git_refs_heads_master + pfxlen); + } + else + die("No such ref: %s", HEAD); +} + +int cmd_symbolic_ref(int argc, const char **argv, const char *prefix) +{ + git_config(git_default_config); + switch (argc) { + case 2: + check_symref(argv[1]); + break; + case 3: + create_symref(strdup(git_path("%s", argv[1])), argv[2]); + break; + default: + usage(git_symbolic_ref_usage); + } + return 0; +} diff --git a/builtin.h b/builtin.h index af73c3c19e..b767245c75 100644 --- a/builtin.h +++ b/builtin.h @@ -52,6 +52,7 @@ extern int cmd_repo_config(int argc, const char **argv, const char *prefix); extern int cmd_name_rev(int argc, const char **argv, const char *prefix); extern int cmd_pack_objects(int argc, const char **argv, const char *prefix); extern int cmd_unpack_objects(int argc, const char **argv, const char *prefix); +extern int cmd_symbolic_ref(int argc, const char **argv, const char *prefix); extern int cmd_write_tree(int argc, const char **argv, const char *prefix); extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix); diff --git a/git.c b/git.c index 7c3a7f8fd1..e40e85935c 100644 --- a/git.c +++ b/git.c @@ -268,6 +268,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "name-rev", cmd_name_rev, NEEDS_PREFIX }, { "pack-objects", cmd_pack_objects, NEEDS_PREFIX }, { "unpack-objects", cmd_unpack_objects, NEEDS_PREFIX }, + { "symbolic-ref", cmd_symbolic_ref, NEEDS_PREFIX }, }; int i; diff --git a/symbolic-ref.c b/symbolic-ref.c deleted file mode 100644 index 193c87c174..0000000000 --- a/symbolic-ref.c +++ /dev/null @@ -1,35 +0,0 @@ -#include "cache.h" - -static const char git_symbolic_ref_usage[] = -"git-symbolic-ref name [ref]"; - -static void check_symref(const char *HEAD) -{ - unsigned char sha1[20]; - const char *git_HEAD = strdup(git_path("%s", HEAD)); - const char *git_refs_heads_master = resolve_ref(git_HEAD, sha1, 0); - if (git_refs_heads_master) { - /* we want to strip the .git/ part */ - int pfxlen = strlen(git_HEAD) - strlen(HEAD); - puts(git_refs_heads_master + pfxlen); - } - else - die("No such ref: %s", HEAD); -} - -int main(int argc, const char **argv) -{ - setup_git_directory(); - git_config(git_default_config); - switch (argc) { - case 2: - check_symref(argv[1]); - break; - case 3: - create_symref(strdup(git_path("%s", argv[1])), argv[2]); - break; - default: - usage(git_symbolic_ref_usage); - } - return 0; -} -- cgit v1.2.1 From e414156ab6e7869b29622ee3439e3c91361f5b0e Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Fri, 4 Aug 2006 01:23:19 -0700 Subject: Make git-checkout-index a builtin Signed-off-by: Junio C Hamano --- Makefile | 6 +- builtin-checkout-index.c | 309 ++++++++++++++++++++++++++++++++++++++++++++++ builtin.h | 1 + checkout-index.c | 311 ----------------------------------------------- git.c | 1 + 5 files changed, 315 insertions(+), 313 deletions(-) create mode 100644 builtin-checkout-index.c delete mode 100644 checkout-index.c diff --git a/Makefile b/Makefile index db59e00ede..1a3605b123 100644 --- a/Makefile +++ b/Makefile @@ -173,7 +173,6 @@ SIMPLE_PROGRAMS = \ # ... and all the rest that could be moved out of bindir to gitexecdir PROGRAMS = \ - git-checkout-index$X \ git-convert-objects$X git-fetch-pack$X git-fsck-objects$X \ git-hash-object$X git-index-pack$X git-local-fetch$X \ git-merge-base$X \ @@ -187,7 +186,9 @@ PROGRAMS = \ git-pack-redundant$X git-var$X \ git-describe$X git-merge-tree$X git-blame$X git-imap-send$X -BUILT_INS = git-log$X git-whatchanged$X git-show$X git-update-ref$X \ +BUILT_INS = \ + git-checkout-index$X \ + git-log$X git-whatchanged$X git-show$X git-update-ref$X \ git-count-objects$X git-diff$X git-push$X git-mailsplit$X \ git-grep$X git-add$X git-rm$X git-rev-list$X git-stripspace$X \ git-check-ref-format$X git-rev-parse$X git-mailinfo$X \ @@ -245,6 +246,7 @@ LIB_OBJS = \ alloc.o merge-file.o path-list.o $(DIFF_OBJS) BUILTIN_OBJS = \ + builtin-checkout-index.o \ builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ builtin-grep.o builtin-add.o builtin-rev-list.o builtin-check-ref-format.o \ builtin-rm.o builtin-init-db.o builtin-rev-parse.o \ diff --git a/builtin-checkout-index.c b/builtin-checkout-index.c new file mode 100644 index 0000000000..29ea6fdc62 --- /dev/null +++ b/builtin-checkout-index.c @@ -0,0 +1,309 @@ +/* + * Check-out files from the "current cache directory" + * + * Copyright (C) 2005 Linus Torvalds + * + * Careful: order of argument flags does matter. For example, + * + * git-checkout-index -a -f file.c + * + * Will first check out all files listed in the cache (but not + * overwrite any old ones), and then force-checkout "file.c" a + * second time (ie that one _will_ overwrite any old contents + * with the same filename). + * + * Also, just doing "git-checkout-index" does nothing. You probably + * meant "git-checkout-index -a". And if you want to force it, you + * want "git-checkout-index -f -a". + * + * Intuitiveness is not the goal here. Repeatability is. The + * reason for the "no arguments means no work" thing is that + * from scripts you are supposed to be able to do things like + * + * find . -name '*.h' -print0 | xargs -0 git-checkout-index -f -- + * + * or: + * + * find . -name '*.h' -print0 | git-checkout-index -f -z --stdin + * + * which will force all existing *.h files to be replaced with + * their cached copies. If an empty command line implied "all", + * then this would force-refresh everything in the cache, which + * was not the point. + * + * Oh, and the "--" is just a good idea when you know the rest + * will be filenames. Just so that you wouldn't have a filename + * of "-a" causing problems (not possible in the above example, + * but get used to it in scripting!). + */ +#include "cache.h" +#include "strbuf.h" +#include "quote.h" +#include "cache-tree.h" + +#define CHECKOUT_ALL 4 +static int line_termination = '\n'; +static int checkout_stage; /* default to checkout stage0 */ +static int to_tempfile; +static char topath[4][MAXPATHLEN+1]; + +static struct checkout state; + +static void write_tempfile_record(const char *name, int prefix_length) +{ + int i; + + if (CHECKOUT_ALL == checkout_stage) { + for (i = 1; i < 4; i++) { + if (i > 1) + putchar(' '); + if (topath[i][0]) + fputs(topath[i], stdout); + else + putchar('.'); + } + } else + fputs(topath[checkout_stage], stdout); + + putchar('\t'); + write_name_quoted("", 0, name + prefix_length, + line_termination, stdout); + putchar(line_termination); + + for (i = 0; i < 4; i++) { + topath[i][0] = 0; + } +} + +static int checkout_file(const char *name, int prefix_length) +{ + int namelen = strlen(name); + int pos = cache_name_pos(name, namelen); + int has_same_name = 0; + int did_checkout = 0; + int errs = 0; + + if (pos < 0) + pos = -pos - 1; + + while (pos < active_nr) { + struct cache_entry *ce = active_cache[pos]; + if (ce_namelen(ce) != namelen || + memcmp(ce->name, name, namelen)) + break; + has_same_name = 1; + pos++; + if (ce_stage(ce) != checkout_stage + && (CHECKOUT_ALL != checkout_stage || !ce_stage(ce))) + continue; + did_checkout = 1; + if (checkout_entry(ce, &state, + to_tempfile ? topath[ce_stage(ce)] : NULL) < 0) + errs++; + } + + if (did_checkout) { + if (to_tempfile) + write_tempfile_record(name, prefix_length); + return errs > 0 ? -1 : 0; + } + + if (!state.quiet) { + fprintf(stderr, "git-checkout-index: %s ", name); + if (!has_same_name) + fprintf(stderr, "is not in the cache"); + else if (checkout_stage) + fprintf(stderr, "does not exist at stage %d", + checkout_stage); + else + fprintf(stderr, "is unmerged"); + fputc('\n', stderr); + } + return -1; +} + +static int checkout_all(const char *prefix, int prefix_length) +{ + int i, errs = 0; + struct cache_entry* last_ce = NULL; + + for (i = 0; i < active_nr ; i++) { + struct cache_entry *ce = active_cache[i]; + if (ce_stage(ce) != checkout_stage + && (CHECKOUT_ALL != checkout_stage || !ce_stage(ce))) + continue; + if (prefix && *prefix && + (ce_namelen(ce) <= prefix_length || + memcmp(prefix, ce->name, prefix_length))) + continue; + if (last_ce && to_tempfile) { + if (ce_namelen(last_ce) != ce_namelen(ce) + || memcmp(last_ce->name, ce->name, ce_namelen(ce))) + write_tempfile_record(last_ce->name, prefix_length); + } + if (checkout_entry(ce, &state, + to_tempfile ? topath[ce_stage(ce)] : NULL) < 0) + errs++; + last_ce = ce; + } + if (last_ce && to_tempfile) + write_tempfile_record(last_ce->name, prefix_length); + if (errs) + /* we have already done our error reporting. + * exit with the same code as die(). + */ + exit(128); + return 0; +} + +static const char checkout_cache_usage[] = +"git-checkout-index [-u] [-q] [-a] [-f] [-n] [--stage=[123]|all] [--prefix=] [--temp] [--] ..."; + +static struct lock_file lock_file; + +int cmd_checkout_index(int argc, const char **argv, const char *prefix) +{ + int i; + int newfd = -1; + int all = 0; + int read_from_stdin = 0; + int prefix_length; + + git_config(git_default_config); + state.base_dir = ""; + prefix_length = prefix ? strlen(prefix) : 0; + + if (read_cache() < 0) { + die("invalid cache"); + } + + for (i = 1; i < argc; i++) { + const char *arg = argv[i]; + + if (!strcmp(arg, "--")) { + i++; + break; + } + if (!strcmp(arg, "-a") || !strcmp(arg, "--all")) { + all = 1; + continue; + } + if (!strcmp(arg, "-f") || !strcmp(arg, "--force")) { + state.force = 1; + continue; + } + if (!strcmp(arg, "-q") || !strcmp(arg, "--quiet")) { + state.quiet = 1; + continue; + } + if (!strcmp(arg, "-n") || !strcmp(arg, "--no-create")) { + state.not_new = 1; + continue; + } + if (!strcmp(arg, "-u") || !strcmp(arg, "--index")) { + state.refresh_cache = 1; + if (newfd < 0) + newfd = hold_lock_file_for_update + (&lock_file, get_index_file()); + if (newfd < 0) + die("cannot open index.lock file."); + continue; + } + if (!strcmp(arg, "-z")) { + line_termination = 0; + continue; + } + if (!strcmp(arg, "--stdin")) { + if (i != argc - 1) + die("--stdin must be at the end"); + read_from_stdin = 1; + i++; /* do not consider arg as a file name */ + break; + } + if (!strcmp(arg, "--temp")) { + to_tempfile = 1; + continue; + } + if (!strncmp(arg, "--prefix=", 9)) { + state.base_dir = arg+9; + state.base_dir_len = strlen(state.base_dir); + continue; + } + if (!strncmp(arg, "--stage=", 8)) { + if (!strcmp(arg + 8, "all")) { + to_tempfile = 1; + checkout_stage = CHECKOUT_ALL; + } else { + int ch = arg[8]; + if ('1' <= ch && ch <= '3') + checkout_stage = arg[8] - '0'; + else + die("stage should be between 1 and 3 or all"); + } + continue; + } + if (arg[0] == '-') + usage(checkout_cache_usage); + break; + } + + if (state.base_dir_len || to_tempfile) { + /* when --prefix is specified we do not + * want to update cache. + */ + if (state.refresh_cache) { + close(newfd); newfd = -1; + rollback_lock_file(&lock_file); + } + state.refresh_cache = 0; + } + + /* Check out named files first */ + for ( ; i < argc; i++) { + const char *arg = argv[i]; + const char *p; + + if (all) + die("git-checkout-index: don't mix '--all' and explicit filenames"); + if (read_from_stdin) + die("git-checkout-index: don't mix '--stdin' and explicit filenames"); + p = prefix_path(prefix, prefix_length, arg); + checkout_file(p, prefix_length); + if (p < arg || p > arg + strlen(arg)) + free((char*)p); + } + + if (read_from_stdin) { + struct strbuf buf; + if (all) + die("git-checkout-index: don't mix '--all' and '--stdin'"); + strbuf_init(&buf); + while (1) { + char *path_name; + const char *p; + + read_line(&buf, stdin, line_termination); + if (buf.eof) + break; + if (line_termination && buf.buf[0] == '"') + path_name = unquote_c_style(buf.buf, NULL); + else + path_name = buf.buf; + p = prefix_path(prefix, prefix_length, path_name); + checkout_file(p, prefix_length); + if (p < path_name || p > path_name + strlen(path_name)) + free((char *)p); + if (path_name != buf.buf) + free(path_name); + } + } + + if (all) + checkout_all(prefix, prefix_length); + + if (0 <= newfd && + (write_cache(newfd, active_cache, active_nr) || + close(newfd) || commit_lock_file(&lock_file))) + die("Unable to write new index file"); + return 0; +} diff --git a/builtin.h b/builtin.h index b767245c75..3a24637b11 100644 --- a/builtin.h +++ b/builtin.h @@ -53,6 +53,7 @@ extern int cmd_name_rev(int argc, const char **argv, const char *prefix); extern int cmd_pack_objects(int argc, const char **argv, const char *prefix); extern int cmd_unpack_objects(int argc, const char **argv, const char *prefix); extern int cmd_symbolic_ref(int argc, const char **argv, const char *prefix); +extern int cmd_checkout_index(int argc, const char **argv, const char *prefix); extern int cmd_write_tree(int argc, const char **argv, const char *prefix); extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix); diff --git a/checkout-index.c b/checkout-index.c deleted file mode 100644 index 61152f34b7..0000000000 --- a/checkout-index.c +++ /dev/null @@ -1,311 +0,0 @@ -/* - * Check-out files from the "current cache directory" - * - * Copyright (C) 2005 Linus Torvalds - * - * Careful: order of argument flags does matter. For example, - * - * git-checkout-index -a -f file.c - * - * Will first check out all files listed in the cache (but not - * overwrite any old ones), and then force-checkout "file.c" a - * second time (ie that one _will_ overwrite any old contents - * with the same filename). - * - * Also, just doing "git-checkout-index" does nothing. You probably - * meant "git-checkout-index -a". And if you want to force it, you - * want "git-checkout-index -f -a". - * - * Intuitiveness is not the goal here. Repeatability is. The - * reason for the "no arguments means no work" thing is that - * from scripts you are supposed to be able to do things like - * - * find . -name '*.h' -print0 | xargs -0 git-checkout-index -f -- - * - * or: - * - * find . -name '*.h' -print0 | git-checkout-index -f -z --stdin - * - * which will force all existing *.h files to be replaced with - * their cached copies. If an empty command line implied "all", - * then this would force-refresh everything in the cache, which - * was not the point. - * - * Oh, and the "--" is just a good idea when you know the rest - * will be filenames. Just so that you wouldn't have a filename - * of "-a" causing problems (not possible in the above example, - * but get used to it in scripting!). - */ -#include "cache.h" -#include "strbuf.h" -#include "quote.h" -#include "cache-tree.h" - -#define CHECKOUT_ALL 4 -static const char *prefix; -static int prefix_length; -static int line_termination = '\n'; -static int checkout_stage; /* default to checkout stage0 */ -static int to_tempfile; -static char topath[4][MAXPATHLEN+1]; - -static struct checkout state; - -static void write_tempfile_record (const char *name) -{ - int i; - - if (CHECKOUT_ALL == checkout_stage) { - for (i = 1; i < 4; i++) { - if (i > 1) - putchar(' '); - if (topath[i][0]) - fputs(topath[i], stdout); - else - putchar('.'); - } - } else - fputs(topath[checkout_stage], stdout); - - putchar('\t'); - write_name_quoted("", 0, name + prefix_length, - line_termination, stdout); - putchar(line_termination); - - for (i = 0; i < 4; i++) { - topath[i][0] = 0; - } -} - -static int checkout_file(const char *name) -{ - int namelen = strlen(name); - int pos = cache_name_pos(name, namelen); - int has_same_name = 0; - int did_checkout = 0; - int errs = 0; - - if (pos < 0) - pos = -pos - 1; - - while (pos < active_nr) { - struct cache_entry *ce = active_cache[pos]; - if (ce_namelen(ce) != namelen || - memcmp(ce->name, name, namelen)) - break; - has_same_name = 1; - pos++; - if (ce_stage(ce) != checkout_stage - && (CHECKOUT_ALL != checkout_stage || !ce_stage(ce))) - continue; - did_checkout = 1; - if (checkout_entry(ce, &state, - to_tempfile ? topath[ce_stage(ce)] : NULL) < 0) - errs++; - } - - if (did_checkout) { - if (to_tempfile) - write_tempfile_record(name); - return errs > 0 ? -1 : 0; - } - - if (!state.quiet) { - fprintf(stderr, "git-checkout-index: %s ", name); - if (!has_same_name) - fprintf(stderr, "is not in the cache"); - else if (checkout_stage) - fprintf(stderr, "does not exist at stage %d", - checkout_stage); - else - fprintf(stderr, "is unmerged"); - fputc('\n', stderr); - } - return -1; -} - -static int checkout_all(void) -{ - int i, errs = 0; - struct cache_entry* last_ce = NULL; - - for (i = 0; i < active_nr ; i++) { - struct cache_entry *ce = active_cache[i]; - if (ce_stage(ce) != checkout_stage - && (CHECKOUT_ALL != checkout_stage || !ce_stage(ce))) - continue; - if (prefix && *prefix && - (ce_namelen(ce) <= prefix_length || - memcmp(prefix, ce->name, prefix_length))) - continue; - if (last_ce && to_tempfile) { - if (ce_namelen(last_ce) != ce_namelen(ce) - || memcmp(last_ce->name, ce->name, ce_namelen(ce))) - write_tempfile_record(last_ce->name); - } - if (checkout_entry(ce, &state, - to_tempfile ? topath[ce_stage(ce)] : NULL) < 0) - errs++; - last_ce = ce; - } - if (last_ce && to_tempfile) - write_tempfile_record(last_ce->name); - if (errs) - /* we have already done our error reporting. - * exit with the same code as die(). - */ - exit(128); - return 0; -} - -static const char checkout_cache_usage[] = -"git-checkout-index [-u] [-q] [-a] [-f] [-n] [--stage=[123]|all] [--prefix=] [--temp] [--] ..."; - -static struct lock_file lock_file; - -int main(int argc, char **argv) -{ - int i; - int newfd = -1; - int all = 0; - int read_from_stdin = 0; - - state.base_dir = ""; - prefix = setup_git_directory(); - git_config(git_default_config); - prefix_length = prefix ? strlen(prefix) : 0; - - if (read_cache() < 0) { - die("invalid cache"); - } - - for (i = 1; i < argc; i++) { - const char *arg = argv[i]; - - if (!strcmp(arg, "--")) { - i++; - break; - } - if (!strcmp(arg, "-a") || !strcmp(arg, "--all")) { - all = 1; - continue; - } - if (!strcmp(arg, "-f") || !strcmp(arg, "--force")) { - state.force = 1; - continue; - } - if (!strcmp(arg, "-q") || !strcmp(arg, "--quiet")) { - state.quiet = 1; - continue; - } - if (!strcmp(arg, "-n") || !strcmp(arg, "--no-create")) { - state.not_new = 1; - continue; - } - if (!strcmp(arg, "-u") || !strcmp(arg, "--index")) { - state.refresh_cache = 1; - if (newfd < 0) - newfd = hold_lock_file_for_update - (&lock_file, get_index_file()); - if (newfd < 0) - die("cannot open index.lock file."); - continue; - } - if (!strcmp(arg, "-z")) { - line_termination = 0; - continue; - } - if (!strcmp(arg, "--stdin")) { - if (i != argc - 1) - die("--stdin must be at the end"); - read_from_stdin = 1; - i++; /* do not consider arg as a file name */ - break; - } - if (!strcmp(arg, "--temp")) { - to_tempfile = 1; - continue; - } - if (!strncmp(arg, "--prefix=", 9)) { - state.base_dir = arg+9; - state.base_dir_len = strlen(state.base_dir); - continue; - } - if (!strncmp(arg, "--stage=", 8)) { - if (!strcmp(arg + 8, "all")) { - to_tempfile = 1; - checkout_stage = CHECKOUT_ALL; - } else { - int ch = arg[8]; - if ('1' <= ch && ch <= '3') - checkout_stage = arg[8] - '0'; - else - die("stage should be between 1 and 3 or all"); - } - continue; - } - if (arg[0] == '-') - usage(checkout_cache_usage); - break; - } - - if (state.base_dir_len || to_tempfile) { - /* when --prefix is specified we do not - * want to update cache. - */ - if (state.refresh_cache) { - close(newfd); newfd = -1; - rollback_lock_file(&lock_file); - } - state.refresh_cache = 0; - } - - /* Check out named files first */ - for ( ; i < argc; i++) { - const char *arg = argv[i]; - const char *p; - - if (all) - die("git-checkout-index: don't mix '--all' and explicit filenames"); - if (read_from_stdin) - die("git-checkout-index: don't mix '--stdin' and explicit filenames"); - p = prefix_path(prefix, prefix_length, arg); - checkout_file(p); - if (p < arg || p > arg + strlen(arg)) - free((char*)p); - } - - if (read_from_stdin) { - struct strbuf buf; - if (all) - die("git-checkout-index: don't mix '--all' and '--stdin'"); - strbuf_init(&buf); - while (1) { - char *path_name; - const char *p; - - read_line(&buf, stdin, line_termination); - if (buf.eof) - break; - if (line_termination && buf.buf[0] == '"') - path_name = unquote_c_style(buf.buf, NULL); - else - path_name = buf.buf; - p = prefix_path(prefix, prefix_length, path_name); - checkout_file(p); - if (p < path_name || p > path_name + strlen(path_name)) - free((char *)p); - if (path_name != buf.buf) - free(path_name); - } - } - - if (all) - checkout_all(); - - if (0 <= newfd && - (write_cache(newfd, active_cache, active_nr) || - close(newfd) || commit_lock_file(&lock_file))) - die("Unable to write new index file"); - return 0; -} diff --git a/git.c b/git.c index e40e85935c..07b6d3e9dd 100644 --- a/git.c +++ b/git.c @@ -269,6 +269,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "pack-objects", cmd_pack_objects, NEEDS_PREFIX }, { "unpack-objects", cmd_unpack_objects, NEEDS_PREFIX }, { "symbolic-ref", cmd_symbolic_ref, NEEDS_PREFIX }, + { "checkout-index", cmd_checkout_index, NEEDS_PREFIX }, }; int i; -- cgit v1.2.1 From f754fa9c5480c4556ad268fb5014c4b96cc7b9dc Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Fri, 4 Aug 2006 01:51:04 -0700 Subject: builtins: Makefile clean-up This cleans up the build procedure for built-in commands by: - generating mostly redundant definition of BUILT_INS from BUILTIN_OBJS in the Makefile, - renaming a few files to make the above possible, and - sorting the built-in command table in git.c. It might be a good idea to binary search (or perfect hash) the built-in command table, but that can be done later when somebody feels like. Signed-off-by: Junio C Hamano --- Makefile | 74 +++++++++------ builtin-count-objects.c | 125 ++++++++++++++++++++++++++ builtin-count.c | 125 -------------------------- builtin-help.c | 234 ------------------------------------------------ builtin.h | 80 ++++++++--------- git.c | 68 +++++++------- help.c | 234 ++++++++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 475 insertions(+), 465 deletions(-) create mode 100644 builtin-count-objects.c delete mode 100644 builtin-count.c delete mode 100644 builtin-help.c create mode 100644 help.c diff --git a/Makefile b/Makefile index 1a3605b123..dc39f72f1e 100644 --- a/Makefile +++ b/Makefile @@ -187,19 +187,9 @@ PROGRAMS = \ git-describe$X git-merge-tree$X git-blame$X git-imap-send$X BUILT_INS = \ - git-checkout-index$X \ - git-log$X git-whatchanged$X git-show$X git-update-ref$X \ - git-count-objects$X git-diff$X git-push$X git-mailsplit$X \ - git-grep$X git-add$X git-rm$X git-rev-list$X git-stripspace$X \ - git-check-ref-format$X git-rev-parse$X git-mailinfo$X \ - git-init-db$X git-tar-tree$X git-upload-tar$X git-format-patch$X \ - git-ls-files$X git-ls-tree$X git-get-tar-commit-id$X \ - git-read-tree$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$X git-prune$X git-mv$X git-prune-packed$X \ - git-repo-config$X git-name-rev$X git-pack-objects$X \ - git-unpack-objects$X git-symbolic-ref$X + git-format-patch$X git-show$X git-whatchanged$X \ + git-get-tar-commit-id$X \ + $(patsubst builtin-%.o,git-%$X,$(BUILTIN_OBJS)) # what 'all' will build and 'install' will install, in gitexecdir ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS) @@ -228,7 +218,7 @@ LIB_H = \ blob.h cache.h commit.h csum-file.h delta.h \ diff.h object.h pack.h pkt-line.h quote.h refs.h \ run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \ - tree-walk.h log-tree.h dir.h path-list.h + tree-walk.h log-tree.h dir.h path-list.h builtin.h DIFF_OBJS = \ diff.o diff-lib.o diffcore-break.o diffcore-order.o \ @@ -243,23 +233,49 @@ LIB_OBJS = \ server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \ tag.o tree.o usage.o config.o environment.o ctype.o copy.o \ fetch-clone.o revision.o pager.o tree-walk.o xdiff-interface.o \ - alloc.o merge-file.o path-list.o $(DIFF_OBJS) + alloc.o merge-file.o path-list.o help.o $(DIFF_OBJS) BUILTIN_OBJS = \ + builtin-add.o \ + builtin-apply.o \ + builtin-cat-file.o \ builtin-checkout-index.o \ - builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ - builtin-grep.o builtin-add.o builtin-rev-list.o builtin-check-ref-format.o \ - builtin-rm.o builtin-init-db.o builtin-rev-parse.o \ - builtin-tar-tree.o builtin-upload-tar.o builtin-update-index.o \ - builtin-ls-files.o builtin-ls-tree.o builtin-write-tree.o \ - builtin-read-tree.o builtin-commit-tree.o builtin-mailinfo.o \ - 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-prune.o \ - builtin-mv.o builtin-prune-packed.o builtin-repo-config.o \ - builtin-name-rev.o builtin-pack-objects.o builtin-unpack-objects.o \ - builtin-symbolic-ref.o + builtin-check-ref-format.o \ + builtin-commit-tree.o \ + builtin-count-objects.o \ + builtin-diff.o \ + builtin-diff-files.o \ + builtin-diff-index.o \ + builtin-diff-stages.o \ + builtin-diff-tree.o \ + builtin-fmt-merge-msg.o \ + builtin-grep.o \ + builtin-init-db.o \ + builtin-log.o \ + builtin-ls-files.o \ + builtin-ls-tree.o \ + builtin-mailinfo.o \ + builtin-mailsplit.o \ + builtin-mv.o \ + builtin-name-rev.o \ + builtin-pack-objects.o \ + builtin-prune.o \ + builtin-prune-packed.o \ + builtin-push.o \ + builtin-read-tree.o \ + builtin-repo-config.o \ + builtin-rev-list.o \ + builtin-rev-parse.o \ + builtin-rm.o \ + builtin-show-branch.o \ + builtin-stripspace.o \ + builtin-symbolic-ref.o \ + builtin-tar-tree.o \ + builtin-unpack-objects.o \ + builtin-update-index.o \ + builtin-update-ref.o \ + builtin-upload-tar.o \ + builtin-write-tree.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) LIBS = $(GITLIBS) -lz @@ -540,7 +556,7 @@ git$X: git.c common-cmds.h $(BUILTIN_OBJS) $(GITLIBS) GIT-CFLAGS $(ALL_CFLAGS) -o $@ $(filter %.c,$^) \ $(BUILTIN_OBJS) $(ALL_LDFLAGS) $(LIBS) -builtin-help.o: common-cmds.h +help.o: common-cmds.h $(BUILT_INS): git$X rm -f $@ && ln git$X $@ diff --git a/builtin-count-objects.c b/builtin-count-objects.c new file mode 100644 index 0000000000..1d3729aa99 --- /dev/null +++ b/builtin-count-objects.c @@ -0,0 +1,125 @@ +/* + * Builtin "git count-objects". + * + * Copyright (c) 2006 Junio C Hamano + */ + +#include "cache.h" +#include "builtin.h" + +static const char count_objects_usage[] = "git-count-objects [-v]"; + +static void count_objects(DIR *d, char *path, int len, int verbose, + unsigned long *loose, + unsigned long *loose_size, + unsigned long *packed_loose, + unsigned long *garbage) +{ + struct dirent *ent; + while ((ent = readdir(d)) != NULL) { + char hex[41]; + unsigned char sha1[20]; + const char *cp; + int bad = 0; + + if ((ent->d_name[0] == '.') && + (ent->d_name[1] == 0 || + ((ent->d_name[1] == '.') && (ent->d_name[2] == 0)))) + continue; + for (cp = ent->d_name; *cp; cp++) { + int ch = *cp; + if (('0' <= ch && ch <= '9') || + ('a' <= ch && ch <= 'f')) + continue; + bad = 1; + break; + } + if (cp - ent->d_name != 38) + bad = 1; + else { + struct stat st; + memcpy(path + len + 3, ent->d_name, 38); + path[len + 2] = '/'; + path[len + 41] = 0; + if (lstat(path, &st) || !S_ISREG(st.st_mode)) + bad = 1; + else + (*loose_size) += st.st_blocks; + } + if (bad) { + if (verbose) { + error("garbage found: %.*s/%s", + len + 2, path, ent->d_name); + (*garbage)++; + } + continue; + } + (*loose)++; + if (!verbose) + continue; + memcpy(hex, path+len, 2); + memcpy(hex+2, ent->d_name, 38); + hex[40] = 0; + if (get_sha1_hex(hex, sha1)) + die("internal error"); + if (has_sha1_pack(sha1)) + (*packed_loose)++; + } +} + +int cmd_count_objects(int ac, const char **av, const char *prefix) +{ + int i; + int verbose = 0; + const char *objdir = get_object_directory(); + int len = strlen(objdir); + char *path = xmalloc(len + 50); + unsigned long loose = 0, packed = 0, packed_loose = 0, garbage = 0; + unsigned long loose_size = 0; + + for (i = 1; i < ac; i++) { + const char *arg = av[i]; + if (*arg != '-') + break; + else if (!strcmp(arg, "-v")) + verbose = 1; + else + usage(count_objects_usage); + } + + /* we do not take arguments other than flags for now */ + if (i < ac) + usage(count_objects_usage); + memcpy(path, objdir, len); + if (len && objdir[len-1] != '/') + path[len++] = '/'; + for (i = 0; i < 256; i++) { + DIR *d; + sprintf(path + len, "%02x", i); + d = opendir(path); + if (!d) + continue; + count_objects(d, path, len, verbose, + &loose, &loose_size, &packed_loose, &garbage); + closedir(d); + } + if (verbose) { + struct packed_git *p; + if (!packed_git) + prepare_packed_git(); + for (p = packed_git; p; p = p->next) { + if (!p->pack_local) + continue; + packed += num_packed_objects(p); + } + printf("count: %lu\n", loose); + printf("size: %lu\n", loose_size / 2); + printf("in-pack: %lu\n", packed); + printf("prune-packable: %lu\n", packed_loose); + printf("garbage: %lu\n", garbage); + } + else + printf("%lu objects, %lu kilobytes\n", + loose, loose_size / 2); + return 0; +} diff --git a/builtin-count.c b/builtin-count.c deleted file mode 100644 index 1d3729aa99..0000000000 --- a/builtin-count.c +++ /dev/null @@ -1,125 +0,0 @@ -/* - * Builtin "git count-objects". - * - * Copyright (c) 2006 Junio C Hamano - */ - -#include "cache.h" -#include "builtin.h" - -static const char count_objects_usage[] = "git-count-objects [-v]"; - -static void count_objects(DIR *d, char *path, int len, int verbose, - unsigned long *loose, - unsigned long *loose_size, - unsigned long *packed_loose, - unsigned long *garbage) -{ - struct dirent *ent; - while ((ent = readdir(d)) != NULL) { - char hex[41]; - unsigned char sha1[20]; - const char *cp; - int bad = 0; - - if ((ent->d_name[0] == '.') && - (ent->d_name[1] == 0 || - ((ent->d_name[1] == '.') && (ent->d_name[2] == 0)))) - continue; - for (cp = ent->d_name; *cp; cp++) { - int ch = *cp; - if (('0' <= ch && ch <= '9') || - ('a' <= ch && ch <= 'f')) - continue; - bad = 1; - break; - } - if (cp - ent->d_name != 38) - bad = 1; - else { - struct stat st; - memcpy(path + len + 3, ent->d_name, 38); - path[len + 2] = '/'; - path[len + 41] = 0; - if (lstat(path, &st) || !S_ISREG(st.st_mode)) - bad = 1; - else - (*loose_size) += st.st_blocks; - } - if (bad) { - if (verbose) { - error("garbage found: %.*s/%s", - len + 2, path, ent->d_name); - (*garbage)++; - } - continue; - } - (*loose)++; - if (!verbose) - continue; - memcpy(hex, path+len, 2); - memcpy(hex+2, ent->d_name, 38); - hex[40] = 0; - if (get_sha1_hex(hex, sha1)) - die("internal error"); - if (has_sha1_pack(sha1)) - (*packed_loose)++; - } -} - -int cmd_count_objects(int ac, const char **av, const char *prefix) -{ - int i; - int verbose = 0; - const char *objdir = get_object_directory(); - int len = strlen(objdir); - char *path = xmalloc(len + 50); - unsigned long loose = 0, packed = 0, packed_loose = 0, garbage = 0; - unsigned long loose_size = 0; - - for (i = 1; i < ac; i++) { - const char *arg = av[i]; - if (*arg != '-') - break; - else if (!strcmp(arg, "-v")) - verbose = 1; - else - usage(count_objects_usage); - } - - /* we do not take arguments other than flags for now */ - if (i < ac) - usage(count_objects_usage); - memcpy(path, objdir, len); - if (len && objdir[len-1] != '/') - path[len++] = '/'; - for (i = 0; i < 256; i++) { - DIR *d; - sprintf(path + len, "%02x", i); - d = opendir(path); - if (!d) - continue; - count_objects(d, path, len, verbose, - &loose, &loose_size, &packed_loose, &garbage); - closedir(d); - } - if (verbose) { - struct packed_git *p; - if (!packed_git) - prepare_packed_git(); - for (p = packed_git; p; p = p->next) { - if (!p->pack_local) - continue; - packed += num_packed_objects(p); - } - printf("count: %lu\n", loose); - printf("size: %lu\n", loose_size / 2); - printf("in-pack: %lu\n", packed); - printf("prune-packable: %lu\n", packed_loose); - printf("garbage: %lu\n", garbage); - } - else - printf("%lu objects, %lu kilobytes\n", - loose, loose_size / 2); - return 0; -} diff --git a/builtin-help.c b/builtin-help.c deleted file mode 100644 index fb731cc934..0000000000 --- a/builtin-help.c +++ /dev/null @@ -1,234 +0,0 @@ -/* - * builtin-help.c - * - * Builtin help-related commands (help, usage, version) - */ -#include -#include "cache.h" -#include "builtin.h" -#include "exec_cmd.h" -#include "common-cmds.h" - - -/* most GUI terminals set COLUMNS (although some don't export it) */ -static int term_columns(void) -{ - char *col_string = getenv("COLUMNS"); - int n_cols = 0; - - if (col_string && (n_cols = atoi(col_string)) > 0) - return n_cols; - -#ifdef TIOCGWINSZ - { - struct winsize ws; - if (!ioctl(1, TIOCGWINSZ, &ws)) { - if (ws.ws_col) - return ws.ws_col; - } - } -#endif - - return 80; -} - -static void oom(void) -{ - fprintf(stderr, "git: out of memory\n"); - exit(1); -} - -static inline void mput_char(char c, unsigned int num) -{ - while(num--) - putchar(c); -} - -static struct cmdname { - size_t len; - char name[1]; -} **cmdname; -static int cmdname_alloc, cmdname_cnt; - -static void add_cmdname(const char *name, int len) -{ - struct cmdname *ent; - if (cmdname_alloc <= cmdname_cnt) { - cmdname_alloc = cmdname_alloc + 200; - cmdname = realloc(cmdname, cmdname_alloc * sizeof(*cmdname)); - if (!cmdname) - oom(); - } - ent = malloc(sizeof(*ent) + len); - if (!ent) - oom(); - ent->len = len; - memcpy(ent->name, name, len); - ent->name[len] = 0; - cmdname[cmdname_cnt++] = ent; -} - -static int cmdname_compare(const void *a_, const void *b_) -{ - struct cmdname *a = *(struct cmdname **)a_; - struct cmdname *b = *(struct cmdname **)b_; - return strcmp(a->name, b->name); -} - -static void pretty_print_string_list(struct cmdname **cmdname, int longest) -{ - int cols = 1, rows; - int space = longest + 1; /* min 1 SP between words */ - int max_cols = term_columns() - 1; /* don't print *on* the edge */ - int i, j; - - if (space < max_cols) - cols = max_cols / space; - rows = (cmdname_cnt + cols - 1) / cols; - - qsort(cmdname, cmdname_cnt, sizeof(*cmdname), cmdname_compare); - - for (i = 0; i < rows; i++) { - printf(" "); - - for (j = 0; j < cols; j++) { - int n = j * rows + i; - int size = space; - if (n >= cmdname_cnt) - break; - if (j == cols-1 || n + rows >= cmdname_cnt) - size = 1; - printf("%-*s", size, cmdname[n]->name); - } - putchar('\n'); - } -} - -static void list_commands(const char *exec_path, const char *pattern) -{ - unsigned int longest = 0; - char path[PATH_MAX]; - int dirlen; - DIR *dir = opendir(exec_path); - struct dirent *de; - - if (!dir) { - fprintf(stderr, "git: '%s': %s\n", exec_path, strerror(errno)); - exit(1); - } - - dirlen = strlen(exec_path); - if (PATH_MAX - 20 < dirlen) { - fprintf(stderr, "git: insanely long exec-path '%s'\n", - exec_path); - exit(1); - } - - memcpy(path, exec_path, dirlen); - path[dirlen++] = '/'; - - while ((de = readdir(dir)) != NULL) { - struct stat st; - int entlen; - - if (strncmp(de->d_name, "git-", 4)) - continue; - strcpy(path+dirlen, de->d_name); - if (stat(path, &st) || /* stat, not lstat */ - !S_ISREG(st.st_mode) || - !(st.st_mode & S_IXUSR)) - continue; - - entlen = strlen(de->d_name); - if (4 < entlen && !strcmp(de->d_name + entlen - 4, ".exe")) - entlen -= 4; - - if (longest < entlen) - longest = entlen; - - add_cmdname(de->d_name + 4, entlen-4); - } - closedir(dir); - - printf("git commands available in '%s'\n", exec_path); - printf("----------------------------"); - mput_char('-', strlen(exec_path)); - putchar('\n'); - pretty_print_string_list(cmdname, longest - 4); - putchar('\n'); -} - -static void list_common_cmds_help(void) -{ - int i, longest = 0; - - for (i = 0; i < ARRAY_SIZE(common_cmds); i++) { - if (longest < strlen(common_cmds[i].name)) - longest = strlen(common_cmds[i].name); - } - - puts("The most commonly used git commands are:"); - for (i = 0; i < ARRAY_SIZE(common_cmds); i++) { - printf(" %s", common_cmds[i].name); - mput_char(' ', longest - strlen(common_cmds[i].name) + 4); - puts(common_cmds[i].help); - } - puts("(use 'git help -a' to get a list of all installed git commands)"); -} - -static void show_man_page(const char *git_cmd) -{ - const char *page; - - if (!strncmp(git_cmd, "git", 3)) - page = git_cmd; - else { - int page_len = strlen(git_cmd) + 4; - char *p = malloc(page_len + 1); - strcpy(p, "git-"); - strcpy(p + 4, git_cmd); - p[page_len] = 0; - page = p; - } - - execlp("man", "man", page, NULL); -} - -void help_unknown_cmd(const char *cmd) -{ - printf("git: '%s' is not a git-command\n\n", cmd); - list_common_cmds_help(); - exit(1); -} - -int cmd_version(int argc, const char **argv, const char *prefix) -{ - printf("git version %s\n", git_version_string); - return 0; -} - -int cmd_help(int argc, const char **argv, const char *prefix) -{ - const char *help_cmd = argc > 1 ? argv[1] : NULL; - const char *exec_path = git_exec_path(); - - if (!help_cmd) { - printf("usage: %s\n\n", git_usage_string); - list_common_cmds_help(); - exit(1); - } - - else if (!strcmp(help_cmd, "--all") || !strcmp(help_cmd, "-a")) { - printf("usage: %s\n\n", git_usage_string); - if(exec_path) - list_commands(exec_path, "git-*"); - exit(1); - } - - else - show_man_page(help_cmd); - - return 0; -} - - diff --git a/builtin.h b/builtin.h index 3a24637b11..c0bdb051bd 100644 --- a/builtin.h +++ b/builtin.h @@ -8,62 +8,56 @@ extern const char git_version_string[]; extern const char git_usage_string[]; extern void help_unknown_cmd(const char *cmd); +extern int mailinfo(FILE *in, FILE *out, int ks, const char *encoding, const char *msg, const char *patch); +extern int split_mbox(const char **mbox, const char *dir, int allow_bare, int nr_prec, int skip); +extern void stripspace(FILE *in, FILE *out); +extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix); -extern int cmd_help(int argc, const char **argv, const char *prefix); -extern int cmd_version(int argc, const char **argv, const char *prefix); - -extern int cmd_whatchanged(int argc, const char **argv, const char *prefix); -extern int cmd_show(int argc, const char **argv, const char *prefix); -extern int cmd_log(int argc, const char **argv, const char *prefix); -extern int cmd_diff(int argc, const char **argv, const char *prefix); -extern int cmd_format_patch(int argc, const char **argv, const char *prefix); -extern int cmd_count_objects(int argc, const char **argv, const char *prefix); - -extern int cmd_prune(int argc, const char **argv, const char *prefix); -extern int cmd_prune_packed(int argc, const char **argv, const char *prefix); - -extern int cmd_push(int argc, const char **argv, const char *prefix); -extern int cmd_grep(int argc, const char **argv, const char *prefix); -extern int cmd_rm(int argc, const char **argv, const char *prefix); extern int cmd_add(int argc, const char **argv, const char *prefix); -extern int cmd_rev_list(int argc, const char **argv, const char *prefix); +extern int cmd_apply(int argc, const char **argv, const char *prefix); +extern int cmd_cat_file(int argc, const char **argv, const char *prefix); +extern int cmd_checkout_index(int argc, const char **argv, const char *prefix); extern int cmd_check_ref_format(int argc, const char **argv, const char *prefix); -extern int cmd_init_db(int argc, const char **argv, const char *prefix); -extern int cmd_tar_tree(int argc, const char **argv, const char *prefix); -extern int cmd_upload_tar(int argc, const char **argv, const char *prefix); -extern int cmd_get_tar_commit_id(int argc, const char **argv, const char *prefix); -extern int cmd_ls_files(int argc, const char **argv, const char *prefix); -extern int cmd_ls_tree(int argc, const char **argv, const char *prefix); -extern int cmd_read_tree(int argc, const char **argv, const char *prefix); extern int cmd_commit_tree(int argc, const char **argv, const char *prefix); -extern int cmd_apply(int argc, const char **argv, const char *prefix); -extern int cmd_show_branch(int argc, const char **argv, const char *prefix); +extern int cmd_count_objects(int argc, const char **argv, const char *prefix); extern int cmd_diff_files(int argc, const char **argv, const char *prefix); extern int cmd_diff_index(int argc, const char **argv, const char *prefix); +extern int cmd_diff(int argc, const char **argv, const char *prefix); extern int cmd_diff_stages(int argc, const char **argv, const char *prefix); extern int cmd_diff_tree(int argc, const char **argv, const char *prefix); -extern int cmd_cat_file(int argc, const char **argv, const char *prefix); -extern int cmd_rev_parse(int argc, const char **argv, const char *prefix); -extern int cmd_update_index(int argc, const char **argv, const char *prefix); -extern int cmd_update_ref(int argc, const char **argv, const char *prefix); extern int cmd_fmt_merge_msg(int argc, const char **argv, const char *prefix); +extern int cmd_format_patch(int argc, const char **argv, const char *prefix); +extern int cmd_get_tar_commit_id(int argc, const char **argv, const char *prefix); +extern int cmd_grep(int argc, const char **argv, const char *prefix); +extern int cmd_help(int argc, const char **argv, const char *prefix); +extern int cmd_init_db(int argc, const char **argv, const char *prefix); +extern int cmd_log(int argc, const char **argv, const char *prefix); +extern int cmd_ls_files(int argc, const char **argv, const char *prefix); +extern int cmd_ls_tree(int argc, const char **argv, const char *prefix); +extern int cmd_mailinfo(int argc, const char **argv, const char *prefix); +extern int cmd_mailsplit(int argc, const char **argv, const char *prefix); extern int cmd_mv(int argc, const char **argv, const char *prefix); -extern int cmd_repo_config(int argc, const char **argv, const char *prefix); extern int cmd_name_rev(int argc, const char **argv, const char *prefix); extern int cmd_pack_objects(int argc, const char **argv, const char *prefix); -extern int cmd_unpack_objects(int argc, const char **argv, const char *prefix); +extern int cmd_prune(int argc, const char **argv, const char *prefix); +extern int cmd_prune_packed(int argc, const char **argv, const char *prefix); +extern int cmd_push(int argc, const char **argv, const char *prefix); +extern int cmd_read_tree(int argc, const char **argv, const char *prefix); +extern int cmd_repo_config(int argc, const char **argv, const char *prefix); +extern int cmd_rev_list(int argc, const char **argv, const char *prefix); +extern int cmd_rev_parse(int argc, const char **argv, const char *prefix); +extern int cmd_rm(int argc, const char **argv, const char *prefix); +extern int cmd_show_branch(int argc, const char **argv, const char *prefix); +extern int cmd_show(int argc, const char **argv, const char *prefix); +extern int cmd_stripspace(int argc, const char **argv, const char *prefix); extern int cmd_symbolic_ref(int argc, const char **argv, const char *prefix); -extern int cmd_checkout_index(int argc, const char **argv, const char *prefix); - +extern int cmd_tar_tree(int argc, const char **argv, const char *prefix); +extern int cmd_unpack_objects(int argc, const char **argv, const char *prefix); +extern int cmd_update_index(int argc, const char **argv, const char *prefix); +extern int cmd_update_ref(int argc, const char **argv, const char *prefix); +extern int cmd_upload_tar(int argc, const char **argv, const char *prefix); +extern int cmd_version(int argc, const char **argv, const char *prefix); +extern int cmd_whatchanged(int argc, const char **argv, const char *prefix); extern int cmd_write_tree(int argc, const char **argv, const char *prefix); -extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix); - -extern int cmd_mailsplit(int argc, const char **argv, const char *prefix); -extern int split_mbox(const char **mbox, const char *dir, int allow_bare, int nr_prec, int skip); -extern int cmd_mailinfo(int argc, const char **argv, const char *prefix); -extern int mailinfo(FILE *in, FILE *out, int ks, const char *encoding, const char *msg, const char *patch); - -extern int cmd_stripspace(int argc, const char **argv, const char *prefix); -extern void stripspace(FILE *in, FILE *out); #endif diff --git a/git.c b/git.c index 07b6d3e9dd..754db1a2ee 100644 --- a/git.c +++ b/git.c @@ -224,52 +224,52 @@ static void handle_internal_command(int argc, const char **argv, char **envp) int (*fn)(int, const char **, const char *); int option; } commands[] = { - { "version", cmd_version }, - { "help", cmd_help }, - { "log", cmd_log, NEEDS_PREFIX | USE_PAGER }, - { "whatchanged", cmd_whatchanged, NEEDS_PREFIX | USE_PAGER }, - { "show", cmd_show, NEEDS_PREFIX | USE_PAGER }, - { "push", cmd_push }, - { "format-patch", cmd_format_patch, NEEDS_PREFIX }, - { "count-objects", cmd_count_objects }, - { "diff", cmd_diff, NEEDS_PREFIX }, - { "grep", cmd_grep, NEEDS_PREFIX }, - { "rm", cmd_rm, NEEDS_PREFIX }, { "add", cmd_add, NEEDS_PREFIX }, - { "rev-list", cmd_rev_list, NEEDS_PREFIX }, - { "init-db", cmd_init_db }, - { "get-tar-commit-id", cmd_get_tar_commit_id }, - { "upload-tar", cmd_upload_tar }, + { "apply", cmd_apply }, + { "cat-file", cmd_cat_file, NEEDS_PREFIX }, + { "checkout-index", cmd_checkout_index, NEEDS_PREFIX }, { "check-ref-format", cmd_check_ref_format }, - { "ls-files", cmd_ls_files, NEEDS_PREFIX }, - { "ls-tree", cmd_ls_tree, NEEDS_PREFIX }, - { "tar-tree", cmd_tar_tree, NEEDS_PREFIX }, - { "read-tree", cmd_read_tree, NEEDS_PREFIX }, { "commit-tree", cmd_commit_tree, NEEDS_PREFIX }, - { "apply", cmd_apply }, - { "show-branch", cmd_show_branch, NEEDS_PREFIX }, + { "count-objects", cmd_count_objects }, + { "diff", cmd_diff, NEEDS_PREFIX }, { "diff-files", cmd_diff_files, NEEDS_PREFIX }, { "diff-index", cmd_diff_index, NEEDS_PREFIX }, { "diff-stages", cmd_diff_stages, NEEDS_PREFIX }, { "diff-tree", cmd_diff_tree, NEEDS_PREFIX }, - { "cat-file", cmd_cat_file, NEEDS_PREFIX }, - { "rev-parse", cmd_rev_parse, NEEDS_PREFIX }, - { "write-tree", cmd_write_tree, NEEDS_PREFIX }, - { "mailsplit", cmd_mailsplit }, - { "mailinfo", cmd_mailinfo }, - { "stripspace", cmd_stripspace }, - { "update-index", cmd_update_index, NEEDS_PREFIX }, - { "update-ref", cmd_update_ref, NEEDS_PREFIX }, { "fmt-merge-msg", cmd_fmt_merge_msg, NEEDS_PREFIX }, - { "prune", cmd_prune, NEEDS_PREFIX }, + { "format-patch", cmd_format_patch, NEEDS_PREFIX }, + { "get-tar-commit-id", cmd_get_tar_commit_id }, + { "grep", cmd_grep, NEEDS_PREFIX }, + { "help", cmd_help }, + { "init-db", cmd_init_db }, + { "log", cmd_log, NEEDS_PREFIX | USE_PAGER }, + { "ls-files", cmd_ls_files, NEEDS_PREFIX }, + { "ls-tree", cmd_ls_tree, NEEDS_PREFIX }, + { "mailinfo", cmd_mailinfo }, + { "mailsplit", cmd_mailsplit }, { "mv", cmd_mv, NEEDS_PREFIX }, - { "prune-packed", cmd_prune_packed, NEEDS_PREFIX }, - { "repo-config", cmd_repo_config }, { "name-rev", cmd_name_rev, NEEDS_PREFIX }, { "pack-objects", cmd_pack_objects, NEEDS_PREFIX }, - { "unpack-objects", cmd_unpack_objects, NEEDS_PREFIX }, + { "prune", cmd_prune, NEEDS_PREFIX }, + { "prune-packed", cmd_prune_packed, NEEDS_PREFIX }, + { "push", cmd_push }, + { "read-tree", cmd_read_tree, NEEDS_PREFIX }, + { "repo-config", cmd_repo_config }, + { "rev-list", cmd_rev_list, NEEDS_PREFIX }, + { "rev-parse", cmd_rev_parse, NEEDS_PREFIX }, + { "rm", cmd_rm, NEEDS_PREFIX }, + { "show-branch", cmd_show_branch, NEEDS_PREFIX }, + { "show", cmd_show, NEEDS_PREFIX | USE_PAGER }, + { "stripspace", cmd_stripspace }, { "symbolic-ref", cmd_symbolic_ref, NEEDS_PREFIX }, - { "checkout-index", cmd_checkout_index, NEEDS_PREFIX }, + { "tar-tree", cmd_tar_tree, NEEDS_PREFIX }, + { "unpack-objects", cmd_unpack_objects, NEEDS_PREFIX }, + { "update-index", cmd_update_index, NEEDS_PREFIX }, + { "update-ref", cmd_update_ref, NEEDS_PREFIX }, + { "upload-tar", cmd_upload_tar }, + { "version", cmd_version }, + { "whatchanged", cmd_whatchanged, NEEDS_PREFIX | USE_PAGER }, + { "write-tree", cmd_write_tree, NEEDS_PREFIX }, }; int i; diff --git a/help.c b/help.c new file mode 100644 index 0000000000..fb731cc934 --- /dev/null +++ b/help.c @@ -0,0 +1,234 @@ +/* + * builtin-help.c + * + * Builtin help-related commands (help, usage, version) + */ +#include +#include "cache.h" +#include "builtin.h" +#include "exec_cmd.h" +#include "common-cmds.h" + + +/* most GUI terminals set COLUMNS (although some don't export it) */ +static int term_columns(void) +{ + char *col_string = getenv("COLUMNS"); + int n_cols = 0; + + if (col_string && (n_cols = atoi(col_string)) > 0) + return n_cols; + +#ifdef TIOCGWINSZ + { + struct winsize ws; + if (!ioctl(1, TIOCGWINSZ, &ws)) { + if (ws.ws_col) + return ws.ws_col; + } + } +#endif + + return 80; +} + +static void oom(void) +{ + fprintf(stderr, "git: out of memory\n"); + exit(1); +} + +static inline void mput_char(char c, unsigned int num) +{ + while(num--) + putchar(c); +} + +static struct cmdname { + size_t len; + char name[1]; +} **cmdname; +static int cmdname_alloc, cmdname_cnt; + +static void add_cmdname(const char *name, int len) +{ + struct cmdname *ent; + if (cmdname_alloc <= cmdname_cnt) { + cmdname_alloc = cmdname_alloc + 200; + cmdname = realloc(cmdname, cmdname_alloc * sizeof(*cmdname)); + if (!cmdname) + oom(); + } + ent = malloc(sizeof(*ent) + len); + if (!ent) + oom(); + ent->len = len; + memcpy(ent->name, name, len); + ent->name[len] = 0; + cmdname[cmdname_cnt++] = ent; +} + +static int cmdname_compare(const void *a_, const void *b_) +{ + struct cmdname *a = *(struct cmdname **)a_; + struct cmdname *b = *(struct cmdname **)b_; + return strcmp(a->name, b->name); +} + +static void pretty_print_string_list(struct cmdname **cmdname, int longest) +{ + int cols = 1, rows; + int space = longest + 1; /* min 1 SP between words */ + int max_cols = term_columns() - 1; /* don't print *on* the edge */ + int i, j; + + if (space < max_cols) + cols = max_cols / space; + rows = (cmdname_cnt + cols - 1) / cols; + + qsort(cmdname, cmdname_cnt, sizeof(*cmdname), cmdname_compare); + + for (i = 0; i < rows; i++) { + printf(" "); + + for (j = 0; j < cols; j++) { + int n = j * rows + i; + int size = space; + if (n >= cmdname_cnt) + break; + if (j == cols-1 || n + rows >= cmdname_cnt) + size = 1; + printf("%-*s", size, cmdname[n]->name); + } + putchar('\n'); + } +} + +static void list_commands(const char *exec_path, const char *pattern) +{ + unsigned int longest = 0; + char path[PATH_MAX]; + int dirlen; + DIR *dir = opendir(exec_path); + struct dirent *de; + + if (!dir) { + fprintf(stderr, "git: '%s': %s\n", exec_path, strerror(errno)); + exit(1); + } + + dirlen = strlen(exec_path); + if (PATH_MAX - 20 < dirlen) { + fprintf(stderr, "git: insanely long exec-path '%s'\n", + exec_path); + exit(1); + } + + memcpy(path, exec_path, dirlen); + path[dirlen++] = '/'; + + while ((de = readdir(dir)) != NULL) { + struct stat st; + int entlen; + + if (strncmp(de->d_name, "git-", 4)) + continue; + strcpy(path+dirlen, de->d_name); + if (stat(path, &st) || /* stat, not lstat */ + !S_ISREG(st.st_mode) || + !(st.st_mode & S_IXUSR)) + continue; + + entlen = strlen(de->d_name); + if (4 < entlen && !strcmp(de->d_name + entlen - 4, ".exe")) + entlen -= 4; + + if (longest < entlen) + longest = entlen; + + add_cmdname(de->d_name + 4, entlen-4); + } + closedir(dir); + + printf("git commands available in '%s'\n", exec_path); + printf("----------------------------"); + mput_char('-', strlen(exec_path)); + putchar('\n'); + pretty_print_string_list(cmdname, longest - 4); + putchar('\n'); +} + +static void list_common_cmds_help(void) +{ + int i, longest = 0; + + for (i = 0; i < ARRAY_SIZE(common_cmds); i++) { + if (longest < strlen(common_cmds[i].name)) + longest = strlen(common_cmds[i].name); + } + + puts("The most commonly used git commands are:"); + for (i = 0; i < ARRAY_SIZE(common_cmds); i++) { + printf(" %s", common_cmds[i].name); + mput_char(' ', longest - strlen(common_cmds[i].name) + 4); + puts(common_cmds[i].help); + } + puts("(use 'git help -a' to get a list of all installed git commands)"); +} + +static void show_man_page(const char *git_cmd) +{ + const char *page; + + if (!strncmp(git_cmd, "git", 3)) + page = git_cmd; + else { + int page_len = strlen(git_cmd) + 4; + char *p = malloc(page_len + 1); + strcpy(p, "git-"); + strcpy(p + 4, git_cmd); + p[page_len] = 0; + page = p; + } + + execlp("man", "man", page, NULL); +} + +void help_unknown_cmd(const char *cmd) +{ + printf("git: '%s' is not a git-command\n\n", cmd); + list_common_cmds_help(); + exit(1); +} + +int cmd_version(int argc, const char **argv, const char *prefix) +{ + printf("git version %s\n", git_version_string); + return 0; +} + +int cmd_help(int argc, const char **argv, const char *prefix) +{ + const char *help_cmd = argc > 1 ? argv[1] : NULL; + const char *exec_path = git_exec_path(); + + if (!help_cmd) { + printf("usage: %s\n\n", git_usage_string); + list_common_cmds_help(); + exit(1); + } + + else if (!strcmp(help_cmd, "--all") || !strcmp(help_cmd, "-a")) { + printf("usage: %s\n\n", git_usage_string); + if(exec_path) + list_commands(exec_path, "git-*"); + exit(1); + } + + else + show_man_page(help_cmd); + + return 0; +} + + -- cgit v1.2.1 From efffea033457eedb90ad63596687564f797f12de Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Fri, 4 Aug 2006 02:04:00 -0700 Subject: git.c: Rename NEEDS_PREFIX to RUN_SETUP As Matthias Kestenholz noted, the flag does not quite mean "needs prefix" -- it is more like "run setup_git_directory() before running this command", so rename it to avoid future confusion. While we are at it, rewrite the definition of options to make it obvious that we are talking about flag bits by using standard (1< --- git.c | 72 +++++++++++++++++++++++++++++++++---------------------------------- 1 file changed, 36 insertions(+), 36 deletions(-) diff --git a/git.c b/git.c index 754db1a2ee..96e596b1a3 100644 --- a/git.c +++ b/git.c @@ -213,8 +213,8 @@ static int handle_alias(int *argcp, const char ***argv) const char git_version_string[] = GIT_VERSION; -#define NEEDS_PREFIX 1 -#define USE_PAGER 2 +#define RUN_SETUP (1<<0) +#define USE_PAGER (1<<1) static void handle_internal_command(int argc, const char **argv, char **envp) { @@ -224,52 +224,52 @@ static void handle_internal_command(int argc, const char **argv, char **envp) int (*fn)(int, const char **, const char *); int option; } commands[] = { - { "add", cmd_add, NEEDS_PREFIX }, + { "add", cmd_add, RUN_SETUP }, { "apply", cmd_apply }, - { "cat-file", cmd_cat_file, NEEDS_PREFIX }, - { "checkout-index", cmd_checkout_index, NEEDS_PREFIX }, + { "cat-file", cmd_cat_file, RUN_SETUP }, + { "checkout-index", cmd_checkout_index, RUN_SETUP }, { "check-ref-format", cmd_check_ref_format }, - { "commit-tree", cmd_commit_tree, NEEDS_PREFIX }, + { "commit-tree", cmd_commit_tree, RUN_SETUP }, { "count-objects", cmd_count_objects }, - { "diff", cmd_diff, NEEDS_PREFIX }, - { "diff-files", cmd_diff_files, NEEDS_PREFIX }, - { "diff-index", cmd_diff_index, NEEDS_PREFIX }, - { "diff-stages", cmd_diff_stages, NEEDS_PREFIX }, - { "diff-tree", cmd_diff_tree, NEEDS_PREFIX }, - { "fmt-merge-msg", cmd_fmt_merge_msg, NEEDS_PREFIX }, - { "format-patch", cmd_format_patch, NEEDS_PREFIX }, + { "diff", cmd_diff, RUN_SETUP }, + { "diff-files", cmd_diff_files, RUN_SETUP }, + { "diff-index", cmd_diff_index, RUN_SETUP }, + { "diff-stages", cmd_diff_stages, RUN_SETUP }, + { "diff-tree", cmd_diff_tree, RUN_SETUP }, + { "fmt-merge-msg", cmd_fmt_merge_msg, RUN_SETUP }, + { "format-patch", cmd_format_patch, RUN_SETUP }, { "get-tar-commit-id", cmd_get_tar_commit_id }, - { "grep", cmd_grep, NEEDS_PREFIX }, + { "grep", cmd_grep, RUN_SETUP }, { "help", cmd_help }, { "init-db", cmd_init_db }, - { "log", cmd_log, NEEDS_PREFIX | USE_PAGER }, - { "ls-files", cmd_ls_files, NEEDS_PREFIX }, - { "ls-tree", cmd_ls_tree, NEEDS_PREFIX }, + { "log", cmd_log, RUN_SETUP | USE_PAGER }, + { "ls-files", cmd_ls_files, RUN_SETUP }, + { "ls-tree", cmd_ls_tree, RUN_SETUP }, { "mailinfo", cmd_mailinfo }, { "mailsplit", cmd_mailsplit }, - { "mv", cmd_mv, NEEDS_PREFIX }, - { "name-rev", cmd_name_rev, NEEDS_PREFIX }, - { "pack-objects", cmd_pack_objects, NEEDS_PREFIX }, - { "prune", cmd_prune, NEEDS_PREFIX }, - { "prune-packed", cmd_prune_packed, NEEDS_PREFIX }, + { "mv", cmd_mv, RUN_SETUP }, + { "name-rev", cmd_name_rev, RUN_SETUP }, + { "pack-objects", cmd_pack_objects, RUN_SETUP }, + { "prune", cmd_prune, RUN_SETUP }, + { "prune-packed", cmd_prune_packed, RUN_SETUP }, { "push", cmd_push }, - { "read-tree", cmd_read_tree, NEEDS_PREFIX }, + { "read-tree", cmd_read_tree, RUN_SETUP }, { "repo-config", cmd_repo_config }, - { "rev-list", cmd_rev_list, NEEDS_PREFIX }, - { "rev-parse", cmd_rev_parse, NEEDS_PREFIX }, - { "rm", cmd_rm, NEEDS_PREFIX }, - { "show-branch", cmd_show_branch, NEEDS_PREFIX }, - { "show", cmd_show, NEEDS_PREFIX | USE_PAGER }, + { "rev-list", cmd_rev_list, RUN_SETUP }, + { "rev-parse", cmd_rev_parse, RUN_SETUP }, + { "rm", cmd_rm, RUN_SETUP }, + { "show-branch", cmd_show_branch, RUN_SETUP }, + { "show", cmd_show, RUN_SETUP | USE_PAGER }, { "stripspace", cmd_stripspace }, - { "symbolic-ref", cmd_symbolic_ref, NEEDS_PREFIX }, - { "tar-tree", cmd_tar_tree, NEEDS_PREFIX }, - { "unpack-objects", cmd_unpack_objects, NEEDS_PREFIX }, - { "update-index", cmd_update_index, NEEDS_PREFIX }, - { "update-ref", cmd_update_ref, NEEDS_PREFIX }, + { "symbolic-ref", cmd_symbolic_ref, RUN_SETUP }, + { "tar-tree", cmd_tar_tree, RUN_SETUP }, + { "unpack-objects", cmd_unpack_objects, RUN_SETUP }, + { "update-index", cmd_update_index, RUN_SETUP }, + { "update-ref", cmd_update_ref, RUN_SETUP }, { "upload-tar", cmd_upload_tar }, { "version", cmd_version }, - { "whatchanged", cmd_whatchanged, NEEDS_PREFIX | USE_PAGER }, - { "write-tree", cmd_write_tree, NEEDS_PREFIX }, + { "whatchanged", cmd_whatchanged, RUN_SETUP | USE_PAGER }, + { "write-tree", cmd_write_tree, RUN_SETUP }, }; int i; @@ -286,7 +286,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp) continue; prefix = NULL; - if (p->option & NEEDS_PREFIX) + if (p->option & RUN_SETUP) prefix = setup_git_directory(); if (p->option & USE_PAGER) setup_pager(); -- cgit v1.2.1 From 2e3ed670eb09feffe847af55db38da3dcecc2a88 Mon Sep 17 00:00:00 2001 From: Rene Scharfe Date: Thu, 10 Aug 2006 17:02:38 +0200 Subject: git-verify-pack: make builtin Convert git-verify-pack to a builtin command. Also rename ac to argc and av to argv for consistancy. Signed-off-by: Rene Scharfe Signed-off-by: Junio C Hamano --- Makefile | 1 + builtin-verify-pack.c | 79 +++++++++++++++++++++++++++++++++++++++++++++++++++ builtin.h | 1 + git.c | 1 + verify-pack.c | 78 -------------------------------------------------- 5 files changed, 82 insertions(+), 78 deletions(-) create mode 100644 builtin-verify-pack.c delete mode 100644 verify-pack.c diff --git a/Makefile b/Makefile index 733fa660d9..a3ba585cee 100644 --- a/Makefile +++ b/Makefile @@ -275,6 +275,7 @@ BUILTIN_OBJS = \ builtin-update-index.o \ builtin-update-ref.o \ builtin-upload-tar.o \ + builtin-verify-pack.o \ builtin-write-tree.o GITLIBS = $(LIB_FILE) $(XDIFF_LIB) diff --git a/builtin-verify-pack.c b/builtin-verify-pack.c new file mode 100644 index 0000000000..d700761e15 --- /dev/null +++ b/builtin-verify-pack.c @@ -0,0 +1,79 @@ +#include "builtin.h" +#include "cache.h" +#include "pack.h" + +static int verify_one_pack(const char *path, int verbose) +{ + char arg[PATH_MAX]; + int len; + struct packed_git *pack; + int err; + + len = strlcpy(arg, path, PATH_MAX); + if (len >= PATH_MAX) + return error("name too long: %s", path); + + /* + * In addition to "foo.idx" we accept "foo.pack" and "foo"; + * normalize these forms to "foo.idx" for add_packed_git(). + */ + if (has_extension(arg, len, ".pack")) { + strcpy(arg + len - 5, ".idx"); + len--; + } else if (!has_extension(arg, len, ".idx")) { + if (len + 4 >= PATH_MAX) + return error("name too long: %s.idx", arg); + strcpy(arg + len, ".idx"); + len += 4; + } + + /* + * add_packed_git() uses our buffer (containing "foo.idx") to + * build the pack filename ("foo.pack"). Make sure it fits. + */ + if (len + 1 >= PATH_MAX) { + arg[len - 4] = '\0'; + return error("name too long: %s.pack", arg); + } + + pack = add_packed_git(arg, len, 1); + if (!pack) + return error("packfile %s not found.", arg); + + err = verify_pack(pack, verbose); + free(pack); + + return err; +} + +static const char verify_pack_usage[] = "git-verify-pack [-v] ..."; + +int cmd_verify_pack(int argc, const char **argv, const char *prefix) +{ + int err = 0; + int verbose = 0; + int no_more_options = 0; + int nothing_done = 1; + + while (1 < argc) { + if (!no_more_options && argv[1][0] == '-') { + if (!strcmp("-v", argv[1])) + verbose = 1; + else if (!strcmp("--", argv[1])) + no_more_options = 1; + else + usage(verify_pack_usage); + } + else { + if (verify_one_pack(argv[1], verbose)) + err = 1; + nothing_done = 0; + } + argc--; argv++; + } + + if (nothing_done) + usage(verify_pack_usage); + + return err; +} diff --git a/builtin.h b/builtin.h index c0bdb051bd..ade58c4a1f 100644 --- a/builtin.h +++ b/builtin.h @@ -59,5 +59,6 @@ extern int cmd_upload_tar(int argc, const char **argv, const char *prefix); extern int cmd_version(int argc, const char **argv, const char *prefix); extern int cmd_whatchanged(int argc, const char **argv, const char *prefix); extern int cmd_write_tree(int argc, const char **argv, const char *prefix); +extern int cmd_verify_pack(int argc, const char **argv, const char *prefix); #endif diff --git a/git.c b/git.c index db0f86790d..5da7787d86 100644 --- a/git.c +++ b/git.c @@ -270,6 +270,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "version", cmd_version }, { "whatchanged", cmd_whatchanged, RUN_SETUP | USE_PAGER }, { "write-tree", cmd_write_tree, RUN_SETUP }, + { "verify-pack", cmd_verify_pack }, }; int i; diff --git a/verify-pack.c b/verify-pack.c deleted file mode 100644 index f440a39678..0000000000 --- a/verify-pack.c +++ /dev/null @@ -1,78 +0,0 @@ -#include "cache.h" -#include "pack.h" - -static int verify_one_pack(const char *path, int verbose) -{ - char arg[PATH_MAX]; - int len; - struct packed_git *pack; - int err; - - len = strlcpy(arg, path, PATH_MAX); - if (len >= PATH_MAX) - return error("name too long: %s", path); - - /* - * In addition to "foo.idx" we accept "foo.pack" and "foo"; - * normalize these forms to "foo.idx" for add_packed_git(). - */ - if (has_extension(arg, len, ".pack")) { - strcpy(arg + len - 5, ".idx"); - len--; - } else if (!has_extension(arg, len, ".idx")) { - if (len + 4 >= PATH_MAX) - return error("name too long: %s.idx", arg); - strcpy(arg + len, ".idx"); - len += 4; - } - - /* - * add_packed_git() uses our buffer (containing "foo.idx") to - * build the pack filename ("foo.pack"). Make sure it fits. - */ - if (len + 1 >= PATH_MAX) { - arg[len - 4] = '\0'; - return error("name too long: %s.pack", arg); - } - - pack = add_packed_git(arg, len, 1); - if (!pack) - return error("packfile %s not found.", arg); - - err = verify_pack(pack, verbose); - free(pack); - - return err; -} - -static const char verify_pack_usage[] = "git-verify-pack [-v] ..."; - -int main(int ac, char **av) -{ - int err = 0; - int verbose = 0; - int no_more_options = 0; - int nothing_done = 1; - - while (1 < ac) { - if (!no_more_options && av[1][0] == '-') { - if (!strcmp("-v", av[1])) - verbose = 1; - else if (!strcmp("--", av[1])) - no_more_options = 1; - else - usage(verify_pack_usage); - } - else { - if (verify_one_pack(av[1], verbose)) - err = 1; - nothing_done = 0; - } - ac--; av++; - } - - if (nothing_done) - usage(verify_pack_usage); - - return err; -} -- cgit v1.2.1