diff options
| -rw-r--r-- | .gitignore | 1 | ||||
| -rwxr-xr-x | Documentation/cmd-list.perl | 1 | ||||
| -rw-r--r-- | Documentation/git-bundle.txt | 139 | ||||
| -rw-r--r-- | Makefile | 1 | ||||
| -rw-r--r-- | builtin-bundle.c | 424 | ||||
| -rw-r--r-- | builtin.h | 1 | ||||
| -rwxr-xr-x | git-fetch.sh | 7 | ||||
| -rwxr-xr-x | git-ls-remote.sh | 7 | ||||
| -rw-r--r-- | git.c | 1 | ||||
| -rw-r--r-- | index-pack.c | 3 | ||||
| -rw-r--r-- | revision.c | 2 | ||||
| -rwxr-xr-x | t/t5510-fetch.sh | 28 |
12 files changed, 611 insertions, 4 deletions
diff --git a/.gitignore b/.gitignore index eb8a1f8606..0eaba0a278 100644 --- a/.gitignore +++ b/.gitignore @@ -13,6 +13,7 @@ git-archive git-bisect git-blame git-branch +git-bundle git-cat-file git-check-ref-format git-checkout diff --git a/Documentation/cmd-list.perl b/Documentation/cmd-list.perl index a2d6268e2b..f61c77aa7c 100755 --- a/Documentation/cmd-list.perl +++ b/Documentation/cmd-list.perl @@ -70,6 +70,7 @@ git-archive mainporcelain git-bisect mainporcelain git-blame ancillaryinterrogators git-branch mainporcelain +git-bundle mainporcelain git-cat-file plumbinginterrogators git-checkout-index plumbingmanipulators git-checkout mainporcelain diff --git a/Documentation/git-bundle.txt b/Documentation/git-bundle.txt new file mode 100644 index 0000000000..4ea9e85d5e --- /dev/null +++ b/Documentation/git-bundle.txt @@ -0,0 +1,139 @@ +git-bundle(1) +============= + +NAME +---- +git-bundle - Move objects and refs by archive + + +SYNOPSIS +-------- +'git-bundle' create <file> [git-rev-list args] +'git-bundle' verify <file> +'git-bundle' list-heads <file> [refname...] +'git-bundle' unbundle <file> [refname...] + +DESCRIPTION +----------- + +Some workflows require that one or more branches of development on one +machine be replicated on another machine, but the two machines cannot +be directly connected so the interactive git protocols (git, ssh, +rsync, http) cannot be used. This command provides suport for +git-fetch and git-pull to operate by packaging objects and references +in an archive at the originating machine, then importing those into +another repository using gitlink:git-fetch[1] and gitlink:git-pull[1] +after moving the archive by some means (i.e., by sneakernet). As no +direct connection between repositories exists, the user must specify a +basis for the bundle that is held by the destination repository: the +bundle assumes that all objects in the basis are already in the +destination repository. + +OPTIONS +------- + +create <file>:: + Used to create a bundle named 'file'. This requires the + git-rev-list arguments to define the bundle contents. + +verify <file>:: + Used to check that a bundle file is valid and will apply + cleanly to the current repository. This includes checks on the + bundle format itself as well as checking that the prerequisite + commits exist and are fully linked in the current repository. + git-bundle prints a list of missing commits, if any, and exits + with non-zero status. + +list-heads <file>:: + Lists the references defined in the bundle. If followed by a + list of references, only references matching those given are + printed out. + +unbundle <file>:: + Passes the objects in the bundle to gitlink:git-index-pack[1] + for storage in the repository, then prints the names of all + defined references. If a reflist is given, only references + matching those in the given list are printed. This command is + really plumbing, intended to be called only by + gitlink:git-fetch[1]. + +[git-rev-list-args...]:: + A list of arguments, accepatble to git-rev-parse and + git-rev-list, that specify the specific objects and references + to transport. For example, "master~10..master" causes the + current master reference to be packaged along with all objects + added since its 10th ancestor commit. There is no explicit + limit to the number of references and objects that may be + packaged. + + +[refname...]:: + A list of references used to limit the references reported as + available. This is principally of use to git-fetch, which + expects to recieve only those references asked for and not + necessarily everything in the pack (in this case, git-bundle is + acting like gitlink:git-fetch-pack[1]). + +SPECIFYING REFERENCES +--------------------- + +git-bundle will only package references that are shown by +git-show-ref: this includes heads, tags, and remote heads. References +such as master~1 cannot be packaged, but are perfectly suitable for +defining the basis. More than one reference may be packaged, and more +than one basis can be specified. The objects packaged are those not +contained in the union of the given bases. Each basis can be +specified explicitly (e.g., ^master~10), or implicitly (e.g., +master~10..master, master --since=10.days.ago). + +It is very important that the basis used be held by the destination. +It is ok to err on the side of conservatism, causing the bundle file +to contain objects already in the destination as these are ignored +when unpacking at the destination. + +EXAMPLE +------- + +Assume two repositories exist as R1 on machine A, and R2 on machine B. +For whatever reason, direct connection between A and B is not allowed, +but we can move data from A to B via some mechanism (CD, email, etc). +We want to update R2 with developments made on branch master in R1. +We set a tag in R1 (lastR2bundle) after the previous such transport, +and move it afterwards to help build the bundle. + +in R1 on A: +$ git-bundle create mybundle master ^lastR2bundle +$ git tag -f lastR2bundle master + +(move mybundle from A to B by some mechanism) + +in R2 on B: +$ git-bundle verify mybundle +$ git-fetch mybundle refspec + +where refspec is refInBundle:localRef + + +Also, with something like this in your config: + +[remote "bundle"] + url = /home/me/tmp/file.bdl + fetch = refs/heads/*:refs/remotes/origin/* + +You can first sneakernet the bundle file to ~/tmp/file.bdl and +then these commands: + +$ git ls-remote bundle +$ git fetch bundle +$ git pull bundle + +would treat it as if it is talking with a remote side over the +network. + +Author +------ +Written by Mark Levedahl <mdl123@verizon.net> + +GIT +--- +Part of the gitlink:git[7] suite @@ -277,6 +277,7 @@ BUILTIN_OBJS = \ builtin-archive.o \ builtin-blame.o \ builtin-branch.o \ + builtin-bundle.o \ builtin-cat-file.o \ builtin-checkout-index.o \ builtin-check-ref-format.o \ diff --git a/builtin-bundle.c b/builtin-bundle.c new file mode 100644 index 0000000000..d41a413b58 --- /dev/null +++ b/builtin-bundle.c @@ -0,0 +1,424 @@ +#include "cache.h" +#include "object.h" +#include "commit.h" +#include "diff.h" +#include "revision.h" +#include "list-objects.h" +#include "exec_cmd.h" + +/* + * Basic handler for bundle files to connect repositories via sneakernet. + * Invocation must include action. + * This function can create a bundle or provide information on an existing + * bundle supporting git-fetch, git-pull, and git-ls-remote + */ + +static const char *bundle_usage="git-bundle (create <bundle> <git-rev-list args> | verify <bundle> | list-heads <bundle> [refname]... | unbundle <bundle> [refname]... )"; + +static const char bundle_signature[] = "# v2 git bundle\n"; + +struct ref_list { + unsigned int nr, alloc; + struct ref_list_entry { + unsigned char sha1[20]; + char *name; + } *list; +}; + +static void add_to_ref_list(const unsigned char *sha1, const char *name, + struct ref_list *list) +{ + if (list->nr + 1 >= list->alloc) { + list->alloc = alloc_nr(list->nr + 1); + list->list = xrealloc(list->list, + list->alloc * sizeof(list->list[0])); + } + memcpy(list->list[list->nr].sha1, sha1, 20); + list->list[list->nr].name = xstrdup(name); + list->nr++; +} + +struct bundle_header { + struct ref_list prerequisites; + struct ref_list references; +}; + +/* this function returns the length of the string */ +static int read_string(int fd, char *buffer, int size) +{ + int i; + for (i = 0; i < size - 1; i++) { + int count = xread(fd, buffer + i, 1); + if (count < 0) + return error("Read error: %s", strerror(errno)); + if (count == 0) { + i--; + break; + } + if (buffer[i] == '\n') + break; + } + buffer[i + 1] = '\0'; + return i + 1; +} + +/* returns an fd */ +static int read_header(const char *path, struct bundle_header *header) { + char buffer[1024]; + int fd = open(path, O_RDONLY); + + if (fd < 0) + return error("could not open '%s'", path); + if (read_string(fd, buffer, sizeof(buffer)) < 0 || + strcmp(buffer, bundle_signature)) { + close(fd); + return error("'%s' does not look like a v2 bundle file", path); + } + while (read_string(fd, buffer, sizeof(buffer)) > 0 + && buffer[0] != '\n') { + int is_prereq = buffer[0] == '-'; + int offset = is_prereq ? 1 : 0; + int len = strlen(buffer); + unsigned char sha1[20]; + struct ref_list *list = is_prereq ? &header->prerequisites + : &header->references; + char delim; + + if (buffer[len - 1] == '\n') + buffer[len - 1] = '\0'; + if (get_sha1_hex(buffer + offset, sha1)) { + warn("unrecognized header: %s", buffer); + continue; + } + delim = buffer[40 + offset]; + if (!isspace(delim) && (delim != '\0' || !is_prereq)) + die ("invalid header: %s", buffer); + add_to_ref_list(sha1, isspace(delim) ? + buffer + 41 + offset : "", list); + } + return fd; +} + +/* if in && *in >= 0, take that as input file descriptor instead */ +static int fork_with_pipe(const char **argv, int *in, int *out) +{ + int needs_in, needs_out; + int fdin[2], fdout[2], pid; + + needs_in = in && *in < 0; + if (needs_in) { + if (pipe(fdin) < 0) + return error("could not setup pipe"); + *in = fdin[1]; + } + + needs_out = out && *out < 0; + if (needs_out) { + if (pipe(fdout) < 0) + return error("could not setup pipe"); + *out = fdout[0]; + } + + if ((pid = fork()) < 0) { + if (needs_in) { + close(fdin[0]); + close(fdin[1]); + } + if (needs_out) { + close(fdout[0]); + close(fdout[1]); + } + return error("could not fork"); + } + if (!pid) { + if (needs_in) { + dup2(fdin[0], 0); + close(fdin[0]); + close(fdin[1]); + } else if (in) { + dup2(*in, 0); + close(*in); + } + if (needs_out) { + dup2(fdout[1], 1); + close(fdout[0]); + close(fdout[1]); + } else if (out) { + dup2(*out, 1); + close(*out); + } + exit(execv_git_cmd(argv)); + } + if (needs_in) + close(fdin[0]); + else if (in) + close(*in); + if (needs_out) + close(fdout[1]); + else if (out) + close(*out); + return pid; +} + +static int verify_bundle(struct bundle_header *header) +{ + /* + * Do fast check, then if any prereqs are missing then go line by line + * to be verbose about the errors + */ + struct ref_list *p = &header->prerequisites; + struct rev_info revs; + const char *argv[] = {NULL, "--all"}; + struct object_array refs; + struct commit *commit; + int i, ret = 0, req_nr; + const char *message = "Repository lacks these prerequisite commits:"; + + init_revisions(&revs, NULL); + for (i = 0; i < p->nr; i++) { + struct ref_list_entry *e = p->list + i; + struct object *o = parse_object(e->sha1); + if (o) { + o->flags |= BOUNDARY_SHOW; + add_pending_object(&revs, o, e->name); + continue; + } + if (++ret == 1) + error(message); + error("%s %s", sha1_to_hex(e->sha1), e->name); + } + if (revs.pending.nr == 0) + return ret; + req_nr = revs.pending.nr; + setup_revisions(2, argv, &revs, NULL); + + memset(&refs, 0, sizeof(struct object_array)); + for (i = 0; i < revs.pending.nr; i++) { + struct object_array_entry *e = revs.pending.objects + i; + add_object_array(e->item, e->name, &refs); + } + + prepare_revision_walk(&revs); + + i = req_nr; + while (i && (commit = get_revision(&revs))) + if (commit->object.flags & BOUNDARY_SHOW) + i--; + + for (i = 0; i < req_nr; i++) + if (!(refs.objects[i].item->flags & SHOWN)) { + if (++ret == 1) + error(message); + error("%s %s", sha1_to_hex(refs.objects[i].item->sha1), + refs.objects[i].name); + } + + for (i = 0; i < refs.nr; i++) + clear_commit_marks((struct commit *)refs.objects[i].item, -1); + + return ret; +} + +static int list_heads(struct bundle_header *header, int argc, const char **argv) +{ + int i; + struct ref_list *r = &header->references; + + for (i = 0; i < r->nr; i++) { + if (argc > 1) { + int j; + for (j = 1; j < argc; j++) + if (!strcmp(r->list[i].name, argv[j])) + break; + if (j == argc) + continue; + } + printf("%s %s\n", sha1_to_hex(r->list[i].sha1), + r->list[i].name); + } + return 0; +} + +static void show_commit(struct commit *commit) +{ + write_or_die(1, sha1_to_hex(commit->object.sha1), 40); + write_or_die(1, "\n", 1); + if (commit->parents) { + free_commit_list(commit->parents); + commit->parents = NULL; + } +} + +static void show_object(struct object_array_entry *p) +{ + /* An object with name "foo\n0000000..." can be used to + * confuse downstream git-pack-objects very badly. + */ + const char *ep = strchr(p->name, '\n'); + int len = ep ? ep - p->name : strlen(p->name); + write_or_die(1, sha1_to_hex(p->item->sha1), 40); + write_or_die(1, " ", 1); + if (len) + write_or_die(1, p->name, len); + write_or_die(1, "\n", 1); +} + +static int create_bundle(struct bundle_header *header, const char *path, + int argc, const char **argv) +{ + int bundle_fd = -1; + const char **argv_boundary = xmalloc((argc + 4) * sizeof(const char *)); + const char **argv_pack = xmalloc(4 * sizeof(const char *)); + int pid, in, out, i, status; + char buffer[1024]; + struct rev_info revs; + + bundle_fd = (!strcmp(path, "-") ? 1 : + open(path, O_CREAT | O_WRONLY, 0666)); + if (bundle_fd < 0) + return error("Could not write to '%s'", path); + + /* write signature */ + write_or_die(bundle_fd, bundle_signature, strlen(bundle_signature)); + + /* write prerequisites */ + memcpy(argv_boundary + 3, argv + 1, argc * sizeof(const char *)); + argv_boundary[0] = "rev-list"; + argv_boundary[1] = "--boundary"; + argv_boundary[2] = "--pretty=oneline"; + argv_boundary[argc + 2] = NULL; + out = -1; + pid = fork_with_pipe(argv_boundary, NULL, &out); + if (pid < 0) + return -1; + while ((i = read_string(out, buffer, sizeof(buffer))) > 0) + if (buffer[0] == '-') + write_or_die(bundle_fd, buffer, i); + while ((i = waitpid(pid, &status, 0)) < 0) + if (errno != EINTR) + return error("rev-list died"); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + return error("rev-list died %d", WEXITSTATUS(status)); + + /* write references */ + save_commit_buffer = 0; + init_revisions(&revs, NULL); + revs.tag_objects = 1; + revs.tree_objects = 1; + revs.blob_objects = 1; + argc = setup_revisions(argc, argv, &revs, NULL); + if (argc > 1) + return error("unrecognized argument: %s'", argv[1]); + for (i = 0; i < revs.pending.nr; i++) { + struct object_array_entry *e = revs.pending.objects + i; + if (!(e->item->flags & UNINTERESTING)) { + unsigned char sha1[20]; + char *ref; + if (dwim_ref(e->name, strlen(e->name), sha1, &ref) != 1) + continue; + write_or_die(bundle_fd, sha1_to_hex(e->item->sha1), 40); + write_or_die(bundle_fd, " ", 1); + write_or_die(bundle_fd, ref, strlen(ref)); + write_or_die(bundle_fd, "\n", 1); + free(ref); + } + } + + /* end header */ + write_or_die(bundle_fd, "\n", 1); + + /* write pack */ + argv_pack[0] = "pack-objects"; + argv_pack[1] = "--all-progress"; + argv_pack[2] = "--stdout"; + argv_pack[3] = NULL; + in = -1; + out = bundle_fd; + pid = fork_with_pipe(argv_pack, &in, &out); + if (pid < 0) + return error("Could not spawn pack-objects"); + close(1); + dup2(in, 1); + close(in); + prepare_revision_walk(&revs); + traverse_commit_list(&revs, show_commit, show_object); + close(1); + while (waitpid(pid, &status, 0) < 0) + if (errno != EINTR) + return -1; + if (!WIFEXITED(status) || WEXITSTATUS(status)) + return error ("pack-objects died"); + return 0; +} + +static int unbundle(struct bundle_header *header, int bundle_fd, + int argc, const char **argv) +{ + const char *argv_index_pack[] = {"index-pack", "--stdin", NULL}; + int pid, status, dev_null; + + if (verify_bundle(header)) + return -1; + dev_null = open("/dev/null", O_WRONLY); + pid = fork_with_pipe(argv_index_pack, &bundle_fd, &dev_null); + if (pid < 0) + return error("Could not spawn index-pack"); + while (waitpid(pid, &status, 0) < 0) + if (errno != EINTR) + return error("index-pack died"); + if (!WIFEXITED(status) || WEXITSTATUS(status)) + return error("index-pack exited with status %d", + WEXITSTATUS(status)); + return list_heads(header, argc, argv); +} + +int cmd_bundle(int argc, const char **argv, const char *prefix) +{ + struct bundle_header header; + int nongit = 0; + const char *cmd, *bundle_file; + int bundle_fd = -1; + char buffer[PATH_MAX]; + + if (argc < 3) + usage(bundle_usage); + + cmd = argv[1]; + bundle_file = argv[2]; + argc -= 2; + argv += 2; + + prefix = setup_git_directory_gently(&nongit); + if (prefix && bundle_file[0] != '/') { + snprintf(buffer, sizeof(buffer), "%s/%s", prefix, bundle_file); + bundle_file = buffer; + } + + memset(&header, 0, sizeof(header)); + if (strcmp(cmd, "create") && + !(bundle_fd = read_header(bundle_file, &header))) + return 1; + + if (!strcmp(cmd, "verify")) { + close(bundle_fd); + if (verify_bundle(&header)) + return 1; + fprintf(stderr, "%s is okay\n", bundle_file); + return 0; + } + if (!strcmp(cmd, "list-heads")) { + close(bundle_fd); + return !!list_heads(&header, argc, argv); + } + if (!strcmp(cmd, "create")) { + if (nongit) + die("Need a repository to create a bundle."); + return !!create_bundle(&header, bundle_file, argc, argv); + } else if (!strcmp(cmd, "unbundle")) { + if (nongit) + die("Need a repository to unbundle."); + return !!unbundle(&header, bundle_fd, argc, argv); + } else + usage(bundle_usage); +} + @@ -19,6 +19,7 @@ extern int cmd_apply(int argc, const char **argv, const char *prefix); extern int cmd_archive(int argc, const char **argv, const char *prefix); extern int cmd_blame(int argc, const char **argv, const char *prefix); extern int cmd_branch(int argc, const char **argv, const char *prefix); +extern int cmd_bundle(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); diff --git a/git-fetch.sh b/git-fetch.sh index d230995f6e..59bee5db0f 100755 --- a/git-fetch.sh +++ b/git-fetch.sh @@ -386,8 +386,15 @@ fetch_main () { ( : subshell because we muck with IFS IFS=" $LF" ( + if test -f "$remote" ; then + test -n "$shallow_depth" && + die "shallow clone with bundle is not supported" + git-bundle unbundle "$remote" $rref || + echo failed "$remote" + else git-fetch-pack --thin $exec $keep $shallow_depth "$remote" $rref || echo failed "$remote" + fi ) | ( trap ' diff --git a/git-ls-remote.sh b/git-ls-remote.sh index 8ea5c5e816..a6ed99a7c5 100755 --- a/git-ls-remote.sh +++ b/git-ls-remote.sh @@ -89,8 +89,13 @@ rsync://* ) ;; * ) - git-peek-remote $exec "$peek_repo" || + if test -f "$peek_repo" ; then + git bundle list-heads "$peek_repo" || echo "failed slurping" + else + git-peek-remote $exec "$peek_repo" || + echo "failed slurping" + fi ;; esac | sort -t ' ' -k 2 | @@ -229,6 +229,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp) { "archive", cmd_archive }, { "blame", cmd_blame, RUN_SETUP }, { "branch", cmd_branch, RUN_SETUP }, + { "bundle", cmd_bundle }, { "cat-file", cmd_cat_file, RUN_SETUP }, { "checkout-index", cmd_checkout_index, RUN_SETUP }, { "check-ref-format", cmd_check_ref_format }, diff --git a/index-pack.c b/index-pack.c index 9f8f0cad20..cf81a99500 100644 --- a/index-pack.c +++ b/index-pack.c @@ -463,7 +463,8 @@ static void parse_pack_objects(unsigned char *sha1) /* If input_fd is a file, we should have reached its end now. */ if (fstat(input_fd, &st)) die("cannot fstat packfile: %s", strerror(errno)); - if (S_ISREG(st.st_mode) && st.st_size != consumed_bytes) + if (S_ISREG(st.st_mode) && + lseek(input_fd, 0, SEEK_CUR) - input_len != st.st_size) die("pack has junk at the end"); if (!nr_deltas) diff --git a/revision.c b/revision.c index b84c066cba..f5b8ae4f03 100644 --- a/revision.c +++ b/revision.c @@ -482,7 +482,7 @@ static int handle_one_ref(const char *path, const unsigned char *sha1, int flag, struct all_refs_cb *cb = cb_data; struct object *object = get_reference(cb->all_revs, path, sha1, cb->all_flags); - add_pending_object(cb->all_revs, object, ""); + add_pending_object(cb->all_revs, object, path); return 0; } diff --git a/t/t5510-fetch.sh b/t/t5510-fetch.sh index 50c64856f0..fa76662dce 100755 --- a/t/t5510-fetch.sh +++ b/t/t5510-fetch.sh @@ -35,7 +35,9 @@ test_expect_success "clone and setup child repos" ' echo "URL: ../two/.git/" echo "Pull: refs/heads/master:refs/heads/two" echo "Pull: refs/heads/one:refs/heads/one" - } >.git/remotes/two + } >.git/remotes/two && + cd .. && + git clone . bundle ' test_expect_success "fetch test" ' @@ -81,4 +83,28 @@ test_expect_success 'fetch following tags' ' ' +test_expect_success 'create bundle 1' ' + cd "$D" && + echo >file updated again by origin && + git commit -a -m "tip" && + git bundle create bundle1 master^..master +' + +test_expect_success 'create bundle 2' ' + cd "$D" && + git bundle create bundle2 master~2..master +' + +test_expect_failure 'unbundle 1' ' + cd "$D/bundle" && + git checkout -b some-branch && + git fetch "$D/bundle1" master:master +' + +test_expect_success 'unbundle 2' ' + cd "$D/bundle" && + git fetch ../bundle2 master:master && + test "tip" = "$(git log -1 --pretty=oneline master | cut -b42-)" +' + test_done |