From 255f04d604dbb331933c2354b5d15ed6715e7d6a Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:25 -0700 Subject: [PATCH 01/14] convert: quote filter names in error messages Git filter driver commands with spaces (e.g. `filter.sh foo`) are hard to read in error messages. Quote them to improve the readability. Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- convert.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/convert.c b/convert.c index 077f5e601e..986c23975b 100644 --- a/convert.c +++ b/convert.c @@ -412,7 +412,7 @@ static int filter_buffer_or_fd(int in, int out, void *data) child_process.out = out; if (start_command(&child_process)) - return error("cannot fork to run external filter %s", params->cmd); + return error("cannot fork to run external filter '%s'", params->cmd); sigchain_push(SIGPIPE, SIG_IGN); @@ -430,13 +430,13 @@ static int filter_buffer_or_fd(int in, int out, void *data) if (close(child_process.in)) write_err = 1; if (write_err) - error("cannot feed the input to external filter %s", params->cmd); + error("cannot feed the input to external filter '%s'", params->cmd); sigchain_pop(SIGPIPE); status = finish_command(&child_process); if (status) - error("external filter %s failed %d", params->cmd, status); + error("external filter '%s' failed %d", params->cmd, status); strbuf_release(&cmd); return (write_err || status); @@ -477,15 +477,15 @@ static int apply_filter(const char *path, const char *src, size_t len, int fd, return 0; /* error was already reported */ if (strbuf_read(&nbuf, async.out, len) < 0) { - error("read from external filter %s failed", cmd); + error("read from external filter '%s' failed", cmd); ret = 0; } if (close(async.out)) { - error("read from external filter %s failed", cmd); + error("read from external filter '%s' failed", cmd); ret = 0; } if (finish_async(&async)) { - error("external filter %s failed", cmd); + error("external filter '%s' failed", cmd); ret = 0; } From ed54970324ec0be0f11e1c2af100ea8b1c01a05a Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:26 -0700 Subject: [PATCH 02/14] convert: modernize tests Use `test_config` to set the config, check that files are empty with `test_must_be_empty`, compare files with `test_cmp`, and remove spaces after ">" and "<". Please note that the "rot13" filter configured in "setup" keeps using `git config` instead of `test_config` because subsequent tests might depend on it. Reviewed-by: Stefan Beller Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- t/t0021-conversion.sh | 58 +++++++++++++++++++++---------------------- 1 file changed, 29 insertions(+), 29 deletions(-) diff --git a/t/t0021-conversion.sh b/t/t0021-conversion.sh index e799e59544..dc509381c9 100755 --- a/t/t0021-conversion.sh +++ b/t/t0021-conversion.sh @@ -38,8 +38,8 @@ script='s/^\$Id: \([0-9a-f]*\) \$/\1/p' test_expect_success check ' - cmp test.o test && - cmp test.o test.t && + test_cmp test.o test && + test_cmp test.o test.t && # ident should be stripped in the repository git diff --raw --exit-code :test :test.i && @@ -47,10 +47,10 @@ test_expect_success check ' embedded=$(sed -ne "$script" test.i) && test "z$id" = "z$embedded" && - git cat-file blob :test.t > test.r && + git cat-file blob :test.t >test.r && - ./rot13.sh < test.o > test.t && - cmp test.r test.t + ./rot13.sh test.t && + test_cmp test.r test.t ' # If an expanded ident ever gets into the repository, we want to make sure that @@ -130,7 +130,7 @@ test_expect_success 'filter shell-escaped filenames' ' # delete the files and check them out again, using a smudge filter # that will count the args and echo the command-line back to us - git config filter.argc.smudge "sh ./argc.sh %f" && + test_config filter.argc.smudge "sh ./argc.sh %f" && rm "$normal" "$special" && git checkout -- "$normal" "$special" && @@ -141,7 +141,7 @@ test_expect_success 'filter shell-escaped filenames' ' test_cmp expect "$special" && # do the same thing, but with more args in the filter expression - git config filter.argc.smudge "sh ./argc.sh %f --my-extra-arg" && + test_config filter.argc.smudge "sh ./argc.sh %f --my-extra-arg" && rm "$normal" "$special" && git checkout -- "$normal" "$special" && @@ -154,9 +154,9 @@ test_expect_success 'filter shell-escaped filenames' ' ' test_expect_success 'required filter should filter data' ' - git config filter.required.smudge ./rot13.sh && - git config filter.required.clean ./rot13.sh && - git config filter.required.required true && + test_config filter.required.smudge ./rot13.sh && + test_config filter.required.clean ./rot13.sh && + test_config filter.required.required true && echo "*.r filter=required" >.gitattributes && @@ -165,17 +165,17 @@ test_expect_success 'required filter should filter data' ' rm -f test.r && git checkout -- test.r && - cmp test.o test.r && + test_cmp test.o test.r && ./rot13.sh expected && git cat-file blob :test.r >actual && - cmp expected actual + test_cmp expected actual ' test_expect_success 'required filter smudge failure' ' - git config filter.failsmudge.smudge false && - git config filter.failsmudge.clean cat && - git config filter.failsmudge.required true && + test_config filter.failsmudge.smudge false && + test_config filter.failsmudge.clean cat && + test_config filter.failsmudge.required true && echo "*.fs filter=failsmudge" >.gitattributes && @@ -186,9 +186,9 @@ test_expect_success 'required filter smudge failure' ' ' test_expect_success 'required filter clean failure' ' - git config filter.failclean.smudge cat && - git config filter.failclean.clean false && - git config filter.failclean.required true && + test_config filter.failclean.smudge cat && + test_config filter.failclean.clean false && + test_config filter.failclean.required true && echo "*.fc filter=failclean" >.gitattributes && @@ -197,8 +197,8 @@ test_expect_success 'required filter clean failure' ' ' test_expect_success 'filtering large input to small output should use little memory' ' - git config filter.devnull.clean "cat >/dev/null" && - git config filter.devnull.required true && + test_config filter.devnull.clean "cat >/dev/null" && + test_config filter.devnull.required true && for i in $(test_seq 1 30); do printf "%1048576d" 1; done >30MB && echo "30MB filter=devnull" >.gitattributes && GIT_MMAP_LIMIT=1m GIT_ALLOC_LIMIT=1m git add 30MB @@ -207,7 +207,7 @@ test_expect_success 'filtering large input to small output should use little mem test_expect_success 'filter that does not read is fine' ' test-genrandom foo $((128 * 1024 + 1)) >big && echo "big filter=epipe" >.gitattributes && - git config filter.epipe.clean "echo xyzzy" && + test_config filter.epipe.clean "echo xyzzy" && git add big && git cat-file blob :big >actual && echo xyzzy >expect && @@ -215,20 +215,20 @@ test_expect_success 'filter that does not read is fine' ' ' test_expect_success EXPENSIVE 'filter large file' ' - git config filter.largefile.smudge cat && - git config filter.largefile.clean cat && + test_config filter.largefile.smudge cat && + test_config filter.largefile.clean cat && for i in $(test_seq 1 2048); do printf "%1048576d" 1; done >2GB && echo "2GB filter=largefile" >.gitattributes && git add 2GB 2>err && - ! test -s err && + test_must_be_empty err && rm -f 2GB && git checkout -- 2GB 2>err && - ! test -s err + test_must_be_empty err ' test_expect_success "filter: clean empty file" ' - git config filter.in-repo-header.clean "echo cleaned && cat" && - git config filter.in-repo-header.smudge "sed 1d" && + test_config filter.in-repo-header.clean "echo cleaned && cat" && + test_config filter.in-repo-header.smudge "sed 1d" && echo "empty-in-worktree filter=in-repo-header" >>.gitattributes && >empty-in-worktree && @@ -240,8 +240,8 @@ test_expect_success "filter: clean empty file" ' ' test_expect_success "filter: smudge empty file" ' - git config filter.empty-in-repo.clean "cat >/dev/null" && - git config filter.empty-in-repo.smudge "echo smudged && cat" && + test_config filter.empty-in-repo.clean "cat >/dev/null" && + test_config filter.empty-in-repo.smudge "echo smudged && cat" && echo "empty-in-repo filter=empty-in-repo" >>.gitattributes && echo dead data walking >empty-in-repo && From b992fe104ecde5a362a31d610de96518f398d5c0 Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:27 -0700 Subject: [PATCH 03/14] run-command: move check_pipe() from write_or_die to run_command Move check_pipe() to run_command and make it public. This is necessary to call the function from pkt-line in a subsequent patch. While at it, make async_exit() static to run_command.c as it is no longer used from outside. Signed-off-by: Lars Schneider Signed-off-by: Ramsay Jones Signed-off-by: Junio C Hamano --- run-command.c | 17 +++++++++++++++-- run-command.h | 2 +- write_or_die.c | 13 ------------- 3 files changed, 16 insertions(+), 16 deletions(-) diff --git a/run-command.c b/run-command.c index 5a4dbb66d7..326936273d 100644 --- a/run-command.c +++ b/run-command.c @@ -634,7 +634,7 @@ int in_async(void) return !pthread_equal(main_thread, pthread_self()); } -void NORETURN async_exit(int code) +static void NORETURN async_exit(int code) { pthread_exit((void *)(intptr_t)code); } @@ -684,13 +684,26 @@ int in_async(void) return process_is_async; } -void NORETURN async_exit(int code) +static void NORETURN async_exit(int code) { exit(code); } #endif +void check_pipe(int err) +{ + if (err == EPIPE) { + if (in_async()) + async_exit(141); + + signal(SIGPIPE, SIG_DFL); + raise(SIGPIPE); + /* Should never happen, but just in case... */ + exit(141); + } +} + int start_async(struct async *async) { int need_in, need_out; diff --git a/run-command.h b/run-command.h index 50666497ae..cf29a3195a 100644 --- a/run-command.h +++ b/run-command.h @@ -139,7 +139,7 @@ struct async { int start_async(struct async *async); int finish_async(struct async *async); int in_async(void); -void NORETURN async_exit(int code); +void check_pipe(int err); /** * This callback should initialize the child process and preload the diff --git a/write_or_die.c b/write_or_die.c index 073443247a..eab8c8d0b9 100644 --- a/write_or_die.c +++ b/write_or_die.c @@ -1,19 +1,6 @@ #include "cache.h" #include "run-command.h" -static void check_pipe(int err) -{ - if (err == EPIPE) { - if (in_async()) - async_exit(141); - - signal(SIGPIPE, SIG_DFL); - raise(SIGPIPE); - /* Should never happen, but just in case... */ - exit(141); - } -} - /* * Some cases use stdio, but want to flush after the write * to get error handling (and to get better interactive From ac2fbaa674ce3d5b5faf6a83f88cc4af1654f9cd Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:28 -0700 Subject: [PATCH 04/14] run-command: add clean_on_exit_handler Some processes might want to perform cleanup tasks before Git kills them due to the 'clean_on_exit' flag. Let's give them an interface for doing this. The feature is used in a subsequent patch. Please note, that the cleanup callback is not executed if Git dies of a signal. The reason is that only "async-signal-safe" functions would be allowed to be call in that case. Since we cannot control what functions the callback will use, we will not support the case. See 507d7804 for more details. Helped-by: Johannes Sixt Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- run-command.c | 22 ++++++++++++++++++---- run-command.h | 2 ++ 2 files changed, 20 insertions(+), 4 deletions(-) diff --git a/run-command.c b/run-command.c index 326936273d..ca905a9e80 100644 --- a/run-command.c +++ b/run-command.c @@ -21,6 +21,7 @@ void child_process_clear(struct child_process *child) struct child_to_clean { pid_t pid; + struct child_process *process; struct child_to_clean *next; }; static struct child_to_clean *children_to_clean; @@ -31,6 +32,18 @@ static void cleanup_children(int sig, int in_signal) while (children_to_clean) { struct child_to_clean *p = children_to_clean; children_to_clean = p->next; + + if (p->process && !in_signal) { + struct child_process *process = p->process; + if (process->clean_on_exit_handler) { + trace_printf( + "trace: run_command: running exit handler for pid %" + PRIuMAX, (uintmax_t)p->pid + ); + process->clean_on_exit_handler(process); + } + } + kill(p->pid, sig); if (!in_signal) free(p); @@ -49,10 +62,11 @@ static void cleanup_children_on_exit(void) cleanup_children(SIGTERM, 0); } -static void mark_child_for_cleanup(pid_t pid) +static void mark_child_for_cleanup(pid_t pid, struct child_process *process) { struct child_to_clean *p = xmalloc(sizeof(*p)); p->pid = pid; + p->process = process; p->next = children_to_clean; children_to_clean = p; @@ -422,7 +436,7 @@ fail_pipe: if (cmd->pid < 0) error_errno("cannot fork() for %s", cmd->argv[0]); else if (cmd->clean_on_exit) - mark_child_for_cleanup(cmd->pid); + mark_child_for_cleanup(cmd->pid, cmd); /* * Wait for child's execvp. If the execvp succeeds (or if fork() @@ -483,7 +497,7 @@ fail_pipe: if (cmd->pid < 0 && (!cmd->silent_exec_failure || errno != ENOENT)) error_errno("cannot spawn %s", cmd->argv[0]); if (cmd->clean_on_exit && cmd->pid >= 0) - mark_child_for_cleanup(cmd->pid); + mark_child_for_cleanup(cmd->pid, cmd); argv_array_clear(&nargv); cmd->argv = sargv; @@ -765,7 +779,7 @@ int start_async(struct async *async) exit(!!async->proc(proc_in, proc_out, async->data)); } - mark_child_for_cleanup(async->pid); + mark_child_for_cleanup(async->pid, NULL); if (need_in) close(fdin[0]); diff --git a/run-command.h b/run-command.h index cf29a3195a..dd1c78c28d 100644 --- a/run-command.h +++ b/run-command.h @@ -43,6 +43,8 @@ struct child_process { unsigned stdout_to_stderr:1; unsigned use_shell:1; unsigned clean_on_exit:1; + void (*clean_on_exit_handler)(struct child_process *process); + void *clean_on_exit_handler_cbdata; }; #define CHILD_PROCESS_INIT { NULL, ARGV_ARRAY_INIT, ARGV_ARRAY_INIT } From 81c634e94f2fef0cec295f7554080c82bd6aeeb7 Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:29 -0700 Subject: [PATCH 05/14] pkt-line: rename packet_write() to packet_write_fmt() packet_write() should be called packet_write_fmt() because it is a printf-like function that takes a format string as first parameter. packet_write_fmt() should be used for text strings only. Arbitrary binary data should use a new packet_write() function that is introduced in a subsequent patch. Suggested-by: Junio C Hamano Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- builtin/archive.c | 4 ++-- builtin/receive-pack.c | 4 ++-- builtin/remote-ext.c | 4 ++-- builtin/upload-archive.c | 4 ++-- connect.c | 2 +- daemon.c | 2 +- http-backend.c | 2 +- pkt-line.c | 2 +- pkt-line.h | 2 +- shallow.c | 2 +- upload-pack.c | 30 +++++++++++++++--------------- 11 files changed, 29 insertions(+), 29 deletions(-) diff --git a/builtin/archive.c b/builtin/archive.c index a1e3b940c2..49f491413a 100644 --- a/builtin/archive.c +++ b/builtin/archive.c @@ -47,10 +47,10 @@ static int run_remote_archiver(int argc, const char **argv, if (name_hint) { const char *format = archive_format_from_filename(name_hint); if (format) - packet_write(fd[1], "argument --format=%s\n", format); + packet_write_fmt(fd[1], "argument --format=%s\n", format); } for (i = 1; i < argc; i++) - packet_write(fd[1], "argument %s\n", argv[i]); + packet_write_fmt(fd[1], "argument %s\n", argv[i]); packet_flush(fd[1]); buf = packet_read_line(fd[0], NULL); diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c index f1ce05ce28..173d081647 100644 --- a/builtin/receive-pack.c +++ b/builtin/receive-pack.c @@ -224,7 +224,7 @@ static int receive_pack_config(const char *var, const char *value, void *cb) static void show_ref(const char *path, const unsigned char *sha1) { if (sent_capabilities) { - packet_write(1, "%s %s\n", sha1_to_hex(sha1), path); + packet_write_fmt(1, "%s %s\n", sha1_to_hex(sha1), path); } else { struct strbuf cap = STRBUF_INIT; @@ -239,7 +239,7 @@ static void show_ref(const char *path, const unsigned char *sha1) if (advertise_push_options) strbuf_addstr(&cap, " push-options"); strbuf_addf(&cap, " agent=%s", git_user_agent_sanitized()); - packet_write(1, "%s %s%c%s\n", + packet_write_fmt(1, "%s %s%c%s\n", sha1_to_hex(sha1), path, 0, cap.buf); strbuf_release(&cap); sent_capabilities = 1; diff --git a/builtin/remote-ext.c b/builtin/remote-ext.c index 88eb8f9013..11b48bfb41 100644 --- a/builtin/remote-ext.c +++ b/builtin/remote-ext.c @@ -128,9 +128,9 @@ static void send_git_request(int stdin_fd, const char *serv, const char *repo, const char *vhost) { if (!vhost) - packet_write(stdin_fd, "%s %s%c", serv, repo, 0); + packet_write_fmt(stdin_fd, "%s %s%c", serv, repo, 0); else - packet_write(stdin_fd, "%s %s%chost=%s%c", serv, repo, 0, + packet_write_fmt(stdin_fd, "%s %s%chost=%s%c", serv, repo, 0, vhost, 0); } diff --git a/builtin/upload-archive.c b/builtin/upload-archive.c index 2caedf1849..dc872f6a94 100644 --- a/builtin/upload-archive.c +++ b/builtin/upload-archive.c @@ -88,11 +88,11 @@ int cmd_upload_archive(int argc, const char **argv, const char *prefix) writer.git_cmd = 1; if (start_command(&writer)) { int err = errno; - packet_write(1, "NACK unable to spawn subprocess\n"); + packet_write_fmt(1, "NACK unable to spawn subprocess\n"); die("upload-archive: %s", strerror(err)); } - packet_write(1, "ACK\n"); + packet_write_fmt(1, "ACK\n"); packet_flush(1); while (1) { diff --git a/connect.c b/connect.c index 722dc3fc54..5330d9c162 100644 --- a/connect.c +++ b/connect.c @@ -730,7 +730,7 @@ struct child_process *git_connect(int fd[2], const char *url, * Note: Do not add any other headers here! Doing so * will cause older git-daemon servers to crash. */ - packet_write(fd[1], + packet_write_fmt(fd[1], "%s %s%chost=%s%c", prog, path, 0, target_host, 0); diff --git a/daemon.c b/daemon.c index 425aad0507..afce1b9b7f 100644 --- a/daemon.c +++ b/daemon.c @@ -281,7 +281,7 @@ static int daemon_error(const char *dir, const char *msg) { if (!informative_errors) msg = "access denied or repository not exported"; - packet_write(1, "ERR %s: %s", msg, dir); + packet_write_fmt(1, "ERR %s: %s", msg, dir); return -1; } diff --git a/http-backend.c b/http-backend.c index adc8c8c3da..eef0a361f4 100644 --- a/http-backend.c +++ b/http-backend.c @@ -464,7 +464,7 @@ static void get_info_refs(struct strbuf *hdr, char *arg) hdr_str(hdr, content_type, buf.buf); end_headers(hdr); - packet_write(1, "# service=git-%s\n", svc->name); + packet_write_fmt(1, "# service=git-%s\n", svc->name); packet_flush(1); argv[0] = svc->name; diff --git a/pkt-line.c b/pkt-line.c index 30489c60b1..eeb8046aca 100644 --- a/pkt-line.c +++ b/pkt-line.c @@ -118,7 +118,7 @@ static void format_packet(struct strbuf *out, const char *fmt, va_list args) packet_trace(out->buf + orig_len + 4, n - 4, 1); } -void packet_write(int fd, const char *fmt, ...) +void packet_write_fmt(int fd, const char *fmt, ...) { static struct strbuf buf = STRBUF_INIT; va_list args; diff --git a/pkt-line.h b/pkt-line.h index 3cb9d91baa..1902fb37bb 100644 --- a/pkt-line.h +++ b/pkt-line.h @@ -20,7 +20,7 @@ * side can't, we stay with pure read/write interfaces. */ void packet_flush(int fd); -void packet_write(int fd, const char *fmt, ...) __attribute__((format (printf, 2, 3))); +void packet_write_fmt(int fd, const char *fmt, ...) __attribute__((format (printf, 2, 3))); void packet_buf_flush(struct strbuf *buf); void packet_buf_write(struct strbuf *buf, const char *fmt, ...) __attribute__((format (printf, 2, 3))); diff --git a/shallow.c b/shallow.c index 54e2db7334..d666e24f12 100644 --- a/shallow.c +++ b/shallow.c @@ -260,7 +260,7 @@ static int advertise_shallow_grafts_cb(const struct commit_graft *graft, void *c { int fd = *(int *)cb; if (graft->nr_parent == -1) - packet_write(fd, "shallow %s\n", oid_to_hex(&graft->oid)); + packet_write_fmt(fd, "shallow %s\n", oid_to_hex(&graft->oid)); return 0; } diff --git a/upload-pack.c b/upload-pack.c index ca7f941780..cd47de69ab 100644 --- a/upload-pack.c +++ b/upload-pack.c @@ -393,13 +393,13 @@ static int get_common_commits(void) if (multi_ack == 2 && got_common && !got_other && ok_to_give_up()) { sent_ready = 1; - packet_write(1, "ACK %s ready\n", last_hex); + packet_write_fmt(1, "ACK %s ready\n", last_hex); } if (have_obj.nr == 0 || multi_ack) - packet_write(1, "NAK\n"); + packet_write_fmt(1, "NAK\n"); if (no_done && sent_ready) { - packet_write(1, "ACK %s\n", last_hex); + packet_write_fmt(1, "ACK %s\n", last_hex); return 0; } if (stateless_rpc) @@ -416,20 +416,20 @@ static int get_common_commits(void) const char *hex = sha1_to_hex(sha1); if (multi_ack == 2) { sent_ready = 1; - packet_write(1, "ACK %s ready\n", hex); + packet_write_fmt(1, "ACK %s ready\n", hex); } else - packet_write(1, "ACK %s continue\n", hex); + packet_write_fmt(1, "ACK %s continue\n", hex); } break; default: got_common = 1; memcpy(last_hex, sha1_to_hex(sha1), 41); if (multi_ack == 2) - packet_write(1, "ACK %s common\n", last_hex); + packet_write_fmt(1, "ACK %s common\n", last_hex); else if (multi_ack) - packet_write(1, "ACK %s continue\n", last_hex); + packet_write_fmt(1, "ACK %s continue\n", last_hex); else if (have_obj.nr == 1) - packet_write(1, "ACK %s\n", last_hex); + packet_write_fmt(1, "ACK %s\n", last_hex); break; } continue; @@ -437,10 +437,10 @@ static int get_common_commits(void) if (!strcmp(line, "done")) { if (have_obj.nr > 0) { if (multi_ack) - packet_write(1, "ACK %s\n", last_hex); + packet_write_fmt(1, "ACK %s\n", last_hex); return 0; } - packet_write(1, "NAK\n"); + packet_write_fmt(1, "NAK\n"); return -1; } die("git upload-pack: expected SHA1 list, got '%s'", line); @@ -650,7 +650,7 @@ static void receive_needs(void) while (result) { struct object *object = &result->item->object; if (!(object->flags & (CLIENT_SHALLOW|NOT_SHALLOW))) { - packet_write(1, "shallow %s", + packet_write_fmt(1, "shallow %s", oid_to_hex(&object->oid)); register_shallow(object->oid.hash); shallow_nr++; @@ -662,7 +662,7 @@ static void receive_needs(void) struct object *object = shallows.objects[i].item; if (object->flags & NOT_SHALLOW) { struct commit_list *parents; - packet_write(1, "unshallow %s", + packet_write_fmt(1, "unshallow %s", oid_to_hex(&object->oid)); object->flags &= ~CLIENT_SHALLOW; /* make sure the real parents are parsed */ @@ -741,7 +741,7 @@ static int send_ref(const char *refname, const struct object_id *oid, struct strbuf symref_info = STRBUF_INIT; format_symref_info(&symref_info, cb_data); - packet_write(1, "%s %s%c%s%s%s%s%s agent=%s\n", + packet_write_fmt(1, "%s %s%c%s%s%s%s%s agent=%s\n", oid_to_hex(oid), refname_nons, 0, capabilities, (allow_unadvertised_object_request & ALLOW_TIP_SHA1) ? @@ -753,11 +753,11 @@ static int send_ref(const char *refname, const struct object_id *oid, git_user_agent_sanitized()); strbuf_release(&symref_info); } else { - packet_write(1, "%s %s\n", oid_to_hex(oid), refname_nons); + packet_write_fmt(1, "%s %s\n", oid_to_hex(oid), refname_nons); } capabilities = NULL; if (!peel_ref(refname, peeled.hash)) - packet_write(1, "%s %s^{}\n", oid_to_hex(&peeled), refname_nons); + packet_write_fmt(1, "%s %s^{}\n", oid_to_hex(&peeled), refname_nons); return 0; } From 2f60bdd1a83f14ceee75da309974b0401fa5b019 Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:30 -0700 Subject: [PATCH 06/14] pkt-line: extract set_packet_header() Extracted set_packet_header() function converts an integer to a 4 byte hex string. Make this function locally available so that other pkt-line functions could use it. Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- pkt-line.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/pkt-line.c b/pkt-line.c index eeb8046aca..116ef52c2d 100644 --- a/pkt-line.c +++ b/pkt-line.c @@ -97,10 +97,20 @@ void packet_buf_flush(struct strbuf *buf) strbuf_add(buf, "0000", 4); } -#define hex(a) (hexchar[(a) & 15]) -static void format_packet(struct strbuf *out, const char *fmt, va_list args) +static void set_packet_header(char *buf, const int size) { static char hexchar[] = "0123456789abcdef"; + + #define hex(a) (hexchar[(a) & 15]) + buf[0] = hex(size >> 12); + buf[1] = hex(size >> 8); + buf[2] = hex(size >> 4); + buf[3] = hex(size); + #undef hex +} + +static void format_packet(struct strbuf *out, const char *fmt, va_list args) +{ size_t orig_len, n; orig_len = out->len; @@ -111,10 +121,7 @@ static void format_packet(struct strbuf *out, const char *fmt, va_list args) if (n > LARGE_PACKET_MAX) die("protocol error: impossibly long line"); - out->buf[orig_len + 0] = hex(n >> 12); - out->buf[orig_len + 1] = hex(n >> 8); - out->buf[orig_len + 2] = hex(n >> 4); - out->buf[orig_len + 3] = hex(n); + set_packet_header(&out->buf[orig_len], n); packet_trace(out->buf + orig_len + 4, n - 4, 1); } From 70428d1a5209f8c9996e9a4e0cc2f7aa0f83f3e8 Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:31 -0700 Subject: [PATCH 07/14] pkt-line: add packet_write_fmt_gently() packet_write_fmt() would die in case of a write error even though for some callers an error would be acceptable. Add packet_write_fmt_gently() which writes a formatted pkt-line like packet_write_fmt() but does not die in case of an error. The function is used in a subsequent patch. Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- pkt-line.c | 34 ++++++++++++++++++++++++++++++---- pkt-line.h | 1 + 2 files changed, 31 insertions(+), 4 deletions(-) diff --git a/pkt-line.c b/pkt-line.c index 116ef52c2d..3288ff07d5 100644 --- a/pkt-line.c +++ b/pkt-line.c @@ -125,16 +125,42 @@ static void format_packet(struct strbuf *out, const char *fmt, va_list args) packet_trace(out->buf + orig_len + 4, n - 4, 1); } +static int packet_write_fmt_1(int fd, int gently, + const char *fmt, va_list args) +{ + struct strbuf buf = STRBUF_INIT; + ssize_t count; + + format_packet(&buf, fmt, args); + count = write_in_full(fd, buf.buf, buf.len); + if (count == buf.len) + return 0; + + if (!gently) { + check_pipe(errno); + die_errno("packet write with format failed"); + } + return error("packet write with format failed"); +} + void packet_write_fmt(int fd, const char *fmt, ...) { - static struct strbuf buf = STRBUF_INIT; va_list args; - strbuf_reset(&buf); va_start(args, fmt); - format_packet(&buf, fmt, args); + packet_write_fmt_1(fd, 0, fmt, args); va_end(args); - write_or_die(fd, buf.buf, buf.len); +} + +int packet_write_fmt_gently(int fd, const char *fmt, ...) +{ + int status; + va_list args; + + va_start(args, fmt); + status = packet_write_fmt_1(fd, 1, fmt, args); + va_end(args); + return status; } void packet_buf_write(struct strbuf *buf, const char *fmt, ...) diff --git a/pkt-line.h b/pkt-line.h index 1902fb37bb..3caea77725 100644 --- a/pkt-line.h +++ b/pkt-line.h @@ -23,6 +23,7 @@ void packet_flush(int fd); void packet_write_fmt(int fd, const char *fmt, ...) __attribute__((format (printf, 2, 3))); void packet_buf_flush(struct strbuf *buf); void packet_buf_write(struct strbuf *buf, const char *fmt, ...) __attribute__((format (printf, 2, 3))); +int packet_write_fmt_gently(int fd, const char *fmt, ...) __attribute__((format (printf, 2, 3))); /* * Read a packetized line into the buffer, which must be at least size bytes From 038ce90f2ff91587f2d61993f5c4c23d6fdca144 Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:32 -0700 Subject: [PATCH 08/14] pkt-line: add packet_flush_gently() packet_flush() would die in case of a write error even though for some callers an error would be acceptable. Add packet_flush_gently() which writes a pkt-line flush packet like packet_flush() but does not die in case of an error. The function is used in a subsequent patch. Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- pkt-line.c | 8 ++++++++ pkt-line.h | 1 + 2 files changed, 9 insertions(+) diff --git a/pkt-line.c b/pkt-line.c index 3288ff07d5..62b89dbe3e 100644 --- a/pkt-line.c +++ b/pkt-line.c @@ -91,6 +91,14 @@ void packet_flush(int fd) write_or_die(fd, "0000", 4); } +int packet_flush_gently(int fd) +{ + packet_trace("0000", 4, 1); + if (write_in_full(fd, "0000", 4) == 4) + return 0; + return error("flush packet write failed"); +} + void packet_buf_flush(struct strbuf *buf) { packet_trace("0000", 4, 1); diff --git a/pkt-line.h b/pkt-line.h index 3caea77725..3fa089948f 100644 --- a/pkt-line.h +++ b/pkt-line.h @@ -23,6 +23,7 @@ void packet_flush(int fd); void packet_write_fmt(int fd, const char *fmt, ...) __attribute__((format (printf, 2, 3))); void packet_buf_flush(struct strbuf *buf); void packet_buf_write(struct strbuf *buf, const char *fmt, ...) __attribute__((format (printf, 2, 3))); +int packet_flush_gently(int fd); int packet_write_fmt_gently(int fd, const char *fmt, ...) __attribute__((format (printf, 2, 3))); /* From edfb780cd4fe73474583016055542f5686d3d98d Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:33 -0700 Subject: [PATCH 09/14] pkt-line: add packet_write_gently() packet_write_fmt_gently() uses format_packet() which lets the caller only send string data via "%s". That means it cannot be used for arbitrary data that may contain NULs. Add packet_write_gently() which writes arbitrary data and does not die in case of an error. The function is used by other pkt-line functions in a subsequent patch. Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- pkt-line.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/pkt-line.c b/pkt-line.c index 62b89dbe3e..fef1059a68 100644 --- a/pkt-line.c +++ b/pkt-line.c @@ -171,6 +171,23 @@ int packet_write_fmt_gently(int fd, const char *fmt, ...) return status; } +static int packet_write_gently(const int fd_out, const char *buf, size_t size) +{ + static char packet_write_buffer[LARGE_PACKET_MAX]; + size_t packet_size; + + if (size > sizeof(packet_write_buffer) - 4) + return error("packet write failed - data exceeds max packet size"); + + packet_trace(buf, size, 1); + packet_size = size + 4; + set_packet_header(packet_write_buffer, packet_size); + memcpy(packet_write_buffer + 4, buf, size); + if (write_in_full(fd_out, packet_write_buffer, packet_size) == packet_size) + return 0; + return error("packet write failed"); +} + void packet_buf_write(struct strbuf *buf, const char *fmt, ...) { va_list args; From bb643d8bf872c416b7445e728e2675ac6490fe1d Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:34 -0700 Subject: [PATCH 10/14] pkt-line: add functions to read/write flush terminated packet streams write_packetized_from_fd() and write_packetized_from_buf() write a stream of packets. All content packets use the maximal packet size except for the last one. After the last content packet a `flush` control packet is written. read_packetized_to_strbuf() reads arbitrary sized packets until it detects a `flush` packet. Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- pkt-line.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ pkt-line.h | 8 ++++++ 2 files changed, 80 insertions(+) diff --git a/pkt-line.c b/pkt-line.c index fef1059a68..d4b6bfe076 100644 --- a/pkt-line.c +++ b/pkt-line.c @@ -197,6 +197,46 @@ void packet_buf_write(struct strbuf *buf, const char *fmt, ...) va_end(args); } +int write_packetized_from_fd(int fd_in, int fd_out) +{ + static char buf[LARGE_PACKET_DATA_MAX]; + int err = 0; + ssize_t bytes_to_write; + + while (!err) { + bytes_to_write = xread(fd_in, buf, sizeof(buf)); + if (bytes_to_write < 0) + return COPY_READ_ERROR; + if (bytes_to_write == 0) + break; + err = packet_write_gently(fd_out, buf, bytes_to_write); + } + if (!err) + err = packet_flush_gently(fd_out); + return err; +} + +int write_packetized_from_buf(const char *src_in, size_t len, int fd_out) +{ + int err = 0; + size_t bytes_written = 0; + size_t bytes_to_write; + + while (!err) { + if ((len - bytes_written) > LARGE_PACKET_DATA_MAX) + bytes_to_write = LARGE_PACKET_DATA_MAX; + else + bytes_to_write = len - bytes_written; + if (bytes_to_write == 0) + break; + err = packet_write_gently(fd_out, src_in + bytes_written, bytes_to_write); + bytes_written += bytes_to_write; + } + if (!err) + err = packet_flush_gently(fd_out); + return err; +} + static int get_packet_data(int fd, char **src_buf, size_t *src_size, void *dst, unsigned size, int options) { @@ -287,3 +327,35 @@ char *packet_read_line_buf(char **src, size_t *src_len, int *dst_len) { return packet_read_line_generic(-1, src, src_len, dst_len); } + +ssize_t read_packetized_to_strbuf(int fd_in, struct strbuf *sb_out) +{ + int packet_len; + + size_t orig_len = sb_out->len; + size_t orig_alloc = sb_out->alloc; + + for (;;) { + strbuf_grow(sb_out, LARGE_PACKET_DATA_MAX); + packet_len = packet_read(fd_in, NULL, NULL, + /* strbuf_grow() above always allocates one extra byte to + * store a '\0' at the end of the string. packet_read() + * writes a '\0' extra byte at the end, too. Let it know + * that there is already room for the extra byte. + */ + sb_out->buf + sb_out->len, LARGE_PACKET_DATA_MAX+1, + PACKET_READ_GENTLE_ON_EOF); + if (packet_len <= 0) + break; + sb_out->len += packet_len; + } + + if (packet_len < 0) { + if (orig_alloc == 0) + strbuf_release(sb_out); + else + strbuf_setlen(sb_out, orig_len); + return packet_len; + } + return sb_out->len - orig_len; +} diff --git a/pkt-line.h b/pkt-line.h index 3fa089948f..18eac64830 100644 --- a/pkt-line.h +++ b/pkt-line.h @@ -25,6 +25,8 @@ void packet_buf_flush(struct strbuf *buf); void packet_buf_write(struct strbuf *buf, const char *fmt, ...) __attribute__((format (printf, 2, 3))); int packet_flush_gently(int fd); int packet_write_fmt_gently(int fd, const char *fmt, ...) __attribute__((format (printf, 2, 3))); +int write_packetized_from_fd(int fd_in, int fd_out); +int write_packetized_from_buf(const char *src_in, size_t len, int fd_out); /* * Read a packetized line into the buffer, which must be at least size bytes @@ -77,8 +79,14 @@ char *packet_read_line(int fd, int *size); */ char *packet_read_line_buf(char **src_buf, size_t *src_len, int *size); +/* + * Reads a stream of variable sized packets until a flush packet is detected. + */ +ssize_t read_packetized_to_strbuf(int fd_in, struct strbuf *sb_out); + #define DEFAULT_PACKET_MAX 1000 #define LARGE_PACKET_MAX 65520 +#define LARGE_PACKET_DATA_MAX (LARGE_PACKET_MAX - 4) extern char packet_buffer[LARGE_PACKET_MAX]; #endif From b84be553548b6d493d6eff728f3e11b5b5f9a254 Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:35 -0700 Subject: [PATCH 11/14] convert: make apply_filter() adhere to standard Git error handling apply_filter() returns a boolean that tells the caller if it "did convert or did not convert". The variable `ret` was used throughout the function to track errors whereas `1` denoted success and `0` failure. This is unusual for the Git source where `0` denotes success. Rename the variable and flip its value to make the function easier readable for Git developers. Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- convert.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/convert.c b/convert.c index 986c23975b..597f561e62 100644 --- a/convert.c +++ b/convert.c @@ -451,7 +451,7 @@ static int apply_filter(const char *path, const char *src, size_t len, int fd, * * (child --> cmd) --> us */ - int ret = 1; + int err = 0; struct strbuf nbuf = STRBUF_INIT; struct async async; struct filter_params params; @@ -477,23 +477,20 @@ static int apply_filter(const char *path, const char *src, size_t len, int fd, return 0; /* error was already reported */ if (strbuf_read(&nbuf, async.out, len) < 0) { - error("read from external filter '%s' failed", cmd); - ret = 0; + err = error("read from external filter '%s' failed", cmd); } if (close(async.out)) { - error("read from external filter '%s' failed", cmd); - ret = 0; + err = error("read from external filter '%s' failed", cmd); } if (finish_async(&async)) { - error("external filter '%s' failed", cmd); - ret = 0; + err = error("external filter '%s' failed", cmd); } - if (ret) { + if (!err) { strbuf_swap(dst, &nbuf); } strbuf_release(&nbuf); - return ret; + return !err; } static struct convert_driver { From 234fa07e066d6bc0728c3d9b92686c69a811e5ac Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:36 -0700 Subject: [PATCH 12/14] convert: prepare filter..process option Refactor the existing 'single shot filter mechanism' and prepare the new 'long running filter mechanism'. Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- convert.c | 60 +++++++++++++++++++++++++++++++------------------------ 1 file changed, 34 insertions(+), 26 deletions(-) diff --git a/convert.c b/convert.c index 597f561e62..71e11ffb9a 100644 --- a/convert.c +++ b/convert.c @@ -442,7 +442,7 @@ static int filter_buffer_or_fd(int in, int out, void *data) return (write_err || status); } -static int apply_filter(const char *path, const char *src, size_t len, int fd, +static int apply_single_file_filter(const char *path, const char *src, size_t len, int fd, struct strbuf *dst, const char *cmd) { /* @@ -456,12 +456,6 @@ static int apply_filter(const char *path, const char *src, size_t len, int fd, struct async async; struct filter_params params; - if (!cmd || !*cmd) - return 0; - - if (!dst) - return 1; - memset(&async, 0, sizeof(async)); async.proc = filter_buffer_or_fd; async.data = ¶ms; @@ -493,6 +487,9 @@ static int apply_filter(const char *path, const char *src, size_t len, int fd, return !err; } +#define CAP_CLEAN (1u<<0) +#define CAP_SMUDGE (1u<<1) + static struct convert_driver { const char *name; struct convert_driver *next; @@ -501,6 +498,29 @@ static struct convert_driver { int required; } *user_convert, **user_convert_tail; +static int apply_filter(const char *path, const char *src, size_t len, + int fd, struct strbuf *dst, struct convert_driver *drv, + const unsigned int wanted_capability) +{ + const char *cmd = NULL; + + if (!drv) + return 0; + + if (!dst) + return 1; + + if ((CAP_CLEAN & wanted_capability) && drv->clean) + cmd = drv->clean; + else if ((CAP_SMUDGE & wanted_capability) && drv->smudge) + cmd = drv->smudge; + + if (cmd && *cmd) + return apply_single_file_filter(path, src, len, fd, dst, cmd); + + return 0; +} + static int read_convert_config(const char *var, const char *value, void *cb) { const char *key, *name; @@ -839,7 +859,7 @@ int would_convert_to_git_filter_fd(const char *path) if (!ca.drv->required) return 0; - return apply_filter(path, NULL, 0, -1, NULL, ca.drv->clean); + return apply_filter(path, NULL, 0, -1, NULL, ca.drv, CAP_CLEAN); } const char *get_convert_attr_ascii(const char *path) @@ -872,18 +892,12 @@ int convert_to_git(const char *path, const char *src, size_t len, struct strbuf *dst, enum safe_crlf checksafe) { int ret = 0; - const char *filter = NULL; - int required = 0; struct conv_attrs ca; convert_attrs(&ca, path); - if (ca.drv) { - filter = ca.drv->clean; - required = ca.drv->required; - } - ret |= apply_filter(path, src, len, -1, dst, filter); - if (!ret && required) + ret |= apply_filter(path, src, len, -1, dst, ca.drv, CAP_CLEAN); + if (!ret && ca.drv && ca.drv->required) die("%s: clean filter '%s' failed", path, ca.drv->name); if (ret && dst) { @@ -907,7 +921,7 @@ void convert_to_git_filter_fd(const char *path, int fd, struct strbuf *dst, assert(ca.drv); assert(ca.drv->clean); - if (!apply_filter(path, NULL, 0, fd, dst, ca.drv->clean)) + if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN)) die("%s: clean filter '%s' failed", path, ca.drv->name); crlf_to_git(path, dst->buf, dst->len, dst, ca.crlf_action, checksafe); @@ -919,15 +933,9 @@ static int convert_to_working_tree_internal(const char *path, const char *src, int normalizing) { int ret = 0, ret_filter = 0; - const char *filter = NULL; - int required = 0; struct conv_attrs ca; convert_attrs(&ca, path); - if (ca.drv) { - filter = ca.drv->smudge; - required = ca.drv->required; - } ret |= ident_to_worktree(path, src, len, dst, ca.ident); if (ret) { @@ -938,7 +946,7 @@ static int convert_to_working_tree_internal(const char *path, const char *src, * CRLF conversion can be skipped if normalizing, unless there * is a smudge filter. The filter might expect CRLFs. */ - if (filter || !normalizing) { + if ((ca.drv && ca.drv->smudge) || !normalizing) { ret |= crlf_to_worktree(path, src, len, dst, ca.crlf_action); if (ret) { src = dst->buf; @@ -946,8 +954,8 @@ static int convert_to_working_tree_internal(const char *path, const char *src, } } - ret_filter = apply_filter(path, src, len, -1, dst, filter); - if (!ret_filter && required) + ret_filter = apply_filter(path, src, len, -1, dst, ca.drv, CAP_SMUDGE); + if (!ret_filter && ca.drv && ca.drv->required) die("%s: smudge filter %s failed", path, ca.drv->name); return ret | ret_filter; From edcc85814c87ebd7f3b1b7d3979fac3dfb84d308 Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:37 -0700 Subject: [PATCH 13/14] convert: add filter..process option Git's clean/smudge mechanism invokes an external filter process for every single blob that is affected by a filter. If Git filters a lot of blobs then the startup time of the external filter processes can become a significant part of the overall Git execution time. In a preliminary performance test this developer used a clean/smudge filter written in golang to filter 12,000 files. This process took 364s with the existing filter mechanism and 5s with the new mechanism. See details here: https://github.com/github/git-lfs/pull/1382 This patch adds the `filter..process` string option which, if used, keeps the external filter process running and processes all blobs with the packet format (pkt-line) based protocol over standard input and standard output. The full protocol is explained in detail in `Documentation/gitattributes.txt`. A few key decisions: * The long running filter process is referred to as filter protocol version 2 because the existing single shot filter invocation is considered version 1. * Git sends a welcome message and expects a response right after the external filter process has started. This ensures that Git will not hang if a version 1 filter is incorrectly used with the filter..process option for version 2 filters. In addition, Git can detect this kind of error and warn the user. * The status of a filter operation (e.g. "success" or "error) is set before the actual response and (if necessary!) re-set after the response. The advantage of this two step status response is that if the filter detects an error early, then the filter can communicate this and Git does not even need to create structures to read the response. * All status responses are pkt-line lists terminated with a flush packet. This allows us to send other status fields with the same protocol in the future. Helped-by: Martin-Louis Bright Reviewed-by: Jakub Narebski Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- Documentation/gitattributes.txt | 155 ++++++++++- convert.c | 301 +++++++++++++++++++++- t/t0021-conversion.sh | 444 +++++++++++++++++++++++++++++++- t/t0021/rot13-filter.pl | 192 ++++++++++++++ 4 files changed, 1082 insertions(+), 10 deletions(-) create mode 100755 t/t0021/rot13-filter.pl diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt index 7aff940202..3f4d1edb1f 100644 --- a/Documentation/gitattributes.txt +++ b/Documentation/gitattributes.txt @@ -293,7 +293,15 @@ checkout, when the `smudge` command is specified, the command is fed the blob object from its standard input, and its standard output is used to update the worktree file. Similarly, the `clean` command is used to convert the contents of worktree file -upon checkin. +upon checkin. By default these commands process only a single +blob and terminate. If a long running `process` filter is used +in place of `clean` and/or `smudge` filters, then Git can process +all blobs with a single filter command invocation for the entire +life of a single Git command, for example `git add --all`. If a +long running `process` filter is configured then it always takes +precedence over a configured single blob filter. See section +below for the description of the protocol used to communicate with +a `process` filter. One use of the content filtering is to massage the content into a shape that is more convenient for the platform, filesystem, and the user to use. @@ -373,6 +381,151 @@ not exist, or may have different contents. So, smudge and clean commands should not try to access the file on disk, but only act as filters on the content provided to them on standard input. +Long Running Filter Process +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +If the filter command (a string value) is defined via +`filter..process` then Git can process all blobs with a +single filter invocation for the entire life of a single Git +command. This is achieved by using a packet format (pkt-line, +see technical/protocol-common.txt) based protocol over standard +input and standard output as follows. All packets, except for the +"*CONTENT" packets and the "0000" flush packet, are considered +text and therefore are terminated by a LF. + +Git starts the filter when it encounters the first file +that needs to be cleaned or smudged. After the filter started +Git sends a welcome message ("git-filter-client"), a list of supported +protocol version numbers, and a flush packet. Git expects to read a welcome +response message ("git-filter-server"), exactly one protocol version number +from the previously sent list, and a flush packet. All further +communication will be based on the selected version. The remaining +protocol description below documents "version=2". Please note that +"version=42" in the example below does not exist and is only there +to illustrate how the protocol would look like with more than one +version. + +After the version negotiation Git sends a list of all capabilities that +it supports and a flush packet. Git expects to read a list of desired +capabilities, which must be a subset of the supported capabilities list, +and a flush packet as response: +------------------------ +packet: git> git-filter-client +packet: git> version=2 +packet: git> version=42 +packet: git> 0000 +packet: git< git-filter-server +packet: git< version=2 +packet: git< 0000 +packet: git> capability=clean +packet: git> capability=smudge +packet: git> capability=not-yet-invented +packet: git> 0000 +packet: git< capability=clean +packet: git< capability=smudge +packet: git< 0000 +------------------------ +Supported filter capabilities in version 2 are "clean" and +"smudge". + +Afterwards Git sends a list of "key=value" pairs terminated with +a flush packet. The list will contain at least the filter command +(based on the supported capabilities) and the pathname of the file +to filter relative to the repository root. Right after the flush packet +Git sends the content split in zero or more pkt-line packets and a +flush packet to terminate content. Please note, that the filter +must not send any response before it received the content and the +final flush packet. +------------------------ +packet: git> command=smudge +packet: git> pathname=path/testfile.dat +packet: git> 0000 +packet: git> CONTENT +packet: git> 0000 +------------------------ + +The filter is expected to respond with a list of "key=value" pairs +terminated with a flush packet. If the filter does not experience +problems then the list must contain a "success" status. Right after +these packets the filter is expected to send the content in zero +or more pkt-line packets and a flush packet at the end. Finally, a +second list of "key=value" pairs terminated with a flush packet +is expected. The filter can change the status in the second list +or keep the status as is with an empty list. Please note that the +empty list must be terminated with a flush packet regardless. + +------------------------ +packet: git< status=success +packet: git< 0000 +packet: git< SMUDGED_CONTENT +packet: git< 0000 +packet: git< 0000 # empty list, keep "status=success" unchanged! +------------------------ + +If the result content is empty then the filter is expected to respond +with a "success" status and a flush packet to signal the empty content. +------------------------ +packet: git< status=success +packet: git< 0000 +packet: git< 0000 # empty content! +packet: git< 0000 # empty list, keep "status=success" unchanged! +------------------------ + +In case the filter cannot or does not want to process the content, +it is expected to respond with an "error" status. +------------------------ +packet: git< status=error +packet: git< 0000 +------------------------ + +If the filter experiences an error during processing, then it can +send the status "error" after the content was (partially or +completely) sent. +------------------------ +packet: git< status=success +packet: git< 0000 +packet: git< HALF_WRITTEN_ERRONEOUS_CONTENT +packet: git< 0000 +packet: git< status=error +packet: git< 0000 +------------------------ + +In case the filter cannot or does not want to process the content +as well as any future content for the lifetime of the Git process, +then it is expected to respond with an "abort" status at any point +in the protocol. +------------------------ +packet: git< status=abort +packet: git< 0000 +------------------------ + +Git neither stops nor restarts the filter process in case the +"error"/"abort" status is set. However, Git sets its exit code +according to the `filter..required` flag, mimicking the +behavior of the `filter..clean` / `filter..smudge` +mechanism. + +If the filter dies during the communication or does not adhere to +the protocol then Git will stop the filter process and restart it +with the next file that needs to be processed. Depending on the +`filter..required` flag Git will interpret that as error. + +After the filter has processed a blob it is expected to wait for +the next "key=value" list containing a command. Git will close +the command pipe on exit. The filter is expected to detect EOF +and exit gracefully on its own. Git will wait until the filter +process has stopped. + +If you develop your own long running filter +process then the `GIT_TRACE_PACKET` environment variables can be +very helpful for debugging (see linkgit:git[1]). + +Please note that you cannot use an existing `filter..clean` +or `filter..smudge` command with `filter..process` +because the former two use a different inter process communication +protocol than the latter one. + + Interaction between checkin/checkout attributes ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ diff --git a/convert.c b/convert.c index 71e11ffb9a..bc242276ff 100644 --- a/convert.c +++ b/convert.c @@ -3,6 +3,7 @@ #include "run-command.h" #include "quote.h" #include "sigchain.h" +#include "pkt-line.h" /* * convert.c - convert a file when checking it out and checking it in. @@ -490,11 +491,293 @@ static int apply_single_file_filter(const char *path, const char *src, size_t le #define CAP_CLEAN (1u<<0) #define CAP_SMUDGE (1u<<1) +struct cmd2process { + struct hashmap_entry ent; /* must be the first member! */ + unsigned int supported_capabilities; + const char *cmd; + struct child_process process; +}; + +static int cmd_process_map_initialized; +static struct hashmap cmd_process_map; + +static int cmd2process_cmp(const struct cmd2process *e1, + const struct cmd2process *e2, + const void *unused) +{ + return strcmp(e1->cmd, e2->cmd); +} + +static struct cmd2process *find_multi_file_filter_entry(struct hashmap *hashmap, const char *cmd) +{ + struct cmd2process key; + hashmap_entry_init(&key, strhash(cmd)); + key.cmd = cmd; + return hashmap_get(hashmap, &key, NULL); +} + +static int packet_write_list(int fd, const char *line, ...) +{ + va_list args; + int err; + va_start(args, line); + for (;;) { + if (!line) + break; + if (strlen(line) > LARGE_PACKET_DATA_MAX) + return -1; + err = packet_write_fmt_gently(fd, "%s\n", line); + if (err) + return err; + line = va_arg(args, const char*); + } + va_end(args); + return packet_flush_gently(fd); +} + +static void read_multi_file_filter_status(int fd, struct strbuf *status) +{ + struct strbuf **pair; + char *line; + for (;;) { + line = packet_read_line(fd, NULL); + if (!line) + break; + pair = strbuf_split_str(line, '=', 2); + if (pair[0] && pair[0]->len && pair[1]) { + /* the last "status=" line wins */ + if (!strcmp(pair[0]->buf, "status=")) { + strbuf_reset(status); + strbuf_addbuf(status, pair[1]); + } + } + strbuf_list_free(pair); + } +} + +static void kill_multi_file_filter(struct hashmap *hashmap, struct cmd2process *entry) +{ + if (!entry) + return; + + entry->process.clean_on_exit = 0; + kill(entry->process.pid, SIGTERM); + finish_command(&entry->process); + + hashmap_remove(hashmap, entry, NULL); + free(entry); +} + +static void stop_multi_file_filter(struct child_process *process) +{ + sigchain_push(SIGPIPE, SIG_IGN); + /* Closing the pipe signals the filter to initiate a shutdown. */ + close(process->in); + close(process->out); + sigchain_pop(SIGPIPE); + /* Finish command will wait until the shutdown is complete. */ + finish_command(process); +} + +static struct cmd2process *start_multi_file_filter(struct hashmap *hashmap, const char *cmd) +{ + int err; + struct cmd2process *entry; + struct child_process *process; + const char *argv[] = { cmd, NULL }; + struct string_list cap_list = STRING_LIST_INIT_NODUP; + char *cap_buf; + const char *cap_name; + + entry = xmalloc(sizeof(*entry)); + entry->cmd = cmd; + entry->supported_capabilities = 0; + process = &entry->process; + + child_process_init(process); + process->argv = argv; + process->use_shell = 1; + process->in = -1; + process->out = -1; + process->clean_on_exit = 1; + process->clean_on_exit_handler = stop_multi_file_filter; + + if (start_command(process)) { + error("cannot fork to run external filter '%s'", cmd); + return NULL; + } + + hashmap_entry_init(entry, strhash(cmd)); + + sigchain_push(SIGPIPE, SIG_IGN); + + err = packet_write_list(process->in, "git-filter-client", "version=2", NULL); + if (err) + goto done; + + err = strcmp(packet_read_line(process->out, NULL), "git-filter-server"); + if (err) { + error("external filter '%s' does not support filter protocol version 2", cmd); + goto done; + } + err = strcmp(packet_read_line(process->out, NULL), "version=2"); + if (err) + goto done; + err = packet_read_line(process->out, NULL) != NULL; + if (err) + goto done; + + err = packet_write_list(process->in, "capability=clean", "capability=smudge", NULL); + + for (;;) { + cap_buf = packet_read_line(process->out, NULL); + if (!cap_buf) + break; + string_list_split_in_place(&cap_list, cap_buf, '=', 1); + + if (cap_list.nr != 2 || strcmp(cap_list.items[0].string, "capability")) + continue; + + cap_name = cap_list.items[1].string; + if (!strcmp(cap_name, "clean")) { + entry->supported_capabilities |= CAP_CLEAN; + } else if (!strcmp(cap_name, "smudge")) { + entry->supported_capabilities |= CAP_SMUDGE; + } else { + warning( + "external filter '%s' requested unsupported filter capability '%s'", + cmd, cap_name + ); + } + + string_list_clear(&cap_list, 0); + } + +done: + sigchain_pop(SIGPIPE); + + if (err || errno == EPIPE) { + error("initialization for external filter '%s' failed", cmd); + kill_multi_file_filter(hashmap, entry); + return NULL; + } + + hashmap_add(hashmap, entry); + return entry; +} + +static int apply_multi_file_filter(const char *path, const char *src, size_t len, + int fd, struct strbuf *dst, const char *cmd, + const unsigned int wanted_capability) +{ + int err; + struct cmd2process *entry; + struct child_process *process; + struct strbuf nbuf = STRBUF_INIT; + struct strbuf filter_status = STRBUF_INIT; + const char *filter_type; + + if (!cmd_process_map_initialized) { + cmd_process_map_initialized = 1; + hashmap_init(&cmd_process_map, (hashmap_cmp_fn) cmd2process_cmp, 0); + entry = NULL; + } else { + entry = find_multi_file_filter_entry(&cmd_process_map, cmd); + } + + fflush(NULL); + + if (!entry) { + entry = start_multi_file_filter(&cmd_process_map, cmd); + if (!entry) + return 0; + } + process = &entry->process; + + if (!(wanted_capability & entry->supported_capabilities)) + return 0; + + if (CAP_CLEAN & wanted_capability) + filter_type = "clean"; + else if (CAP_SMUDGE & wanted_capability) + filter_type = "smudge"; + else + die("unexpected filter type"); + + sigchain_push(SIGPIPE, SIG_IGN); + + assert(strlen(filter_type) < LARGE_PACKET_DATA_MAX - strlen("command=\n")); + err = packet_write_fmt_gently(process->in, "command=%s\n", filter_type); + if (err) + goto done; + + err = strlen(path) > LARGE_PACKET_DATA_MAX - strlen("pathname=\n"); + if (err) { + error("path name too long for external filter"); + goto done; + } + + err = packet_write_fmt_gently(process->in, "pathname=%s\n", path); + if (err) + goto done; + + err = packet_flush_gently(process->in); + if (err) + goto done; + + if (fd >= 0) + err = write_packetized_from_fd(fd, process->in); + else + err = write_packetized_from_buf(src, len, process->in); + if (err) + goto done; + + read_multi_file_filter_status(process->out, &filter_status); + err = strcmp(filter_status.buf, "success"); + if (err) + goto done; + + err = read_packetized_to_strbuf(process->out, &nbuf) < 0; + if (err) + goto done; + + read_multi_file_filter_status(process->out, &filter_status); + err = strcmp(filter_status.buf, "success"); + +done: + sigchain_pop(SIGPIPE); + + if (err || errno == EPIPE) { + if (!strcmp(filter_status.buf, "error")) { + /* The filter signaled a problem with the file. */ + } else if (!strcmp(filter_status.buf, "abort")) { + /* + * The filter signaled a permanent problem. Don't try to filter + * files with the same command for the lifetime of the current + * Git process. + */ + entry->supported_capabilities &= ~wanted_capability; + } else { + /* + * Something went wrong with the protocol filter. + * Force shutdown and restart if another blob requires filtering. + */ + error("external filter '%s' failed", cmd); + kill_multi_file_filter(&cmd_process_map, entry); + } + } else { + strbuf_swap(dst, &nbuf); + } + strbuf_release(&nbuf); + return !err; +} + static struct convert_driver { const char *name; struct convert_driver *next; const char *smudge; const char *clean; + const char *process; int required; } *user_convert, **user_convert_tail; @@ -510,13 +793,15 @@ static int apply_filter(const char *path, const char *src, size_t len, if (!dst) return 1; - if ((CAP_CLEAN & wanted_capability) && drv->clean) + if ((CAP_CLEAN & wanted_capability) && !drv->process && drv->clean) cmd = drv->clean; - else if ((CAP_SMUDGE & wanted_capability) && drv->smudge) + else if ((CAP_SMUDGE & wanted_capability) && !drv->process && drv->smudge) cmd = drv->smudge; if (cmd && *cmd) return apply_single_file_filter(path, src, len, fd, dst, cmd); + else if (drv->process && *drv->process) + return apply_multi_file_filter(path, src, len, fd, dst, drv->process, wanted_capability); return 0; } @@ -558,6 +843,9 @@ static int read_convert_config(const char *var, const char *value, void *cb) if (!strcmp("clean", key)) return git_config_string(&drv->clean, var, value); + if (!strcmp("process", key)) + return git_config_string(&drv->process, var, value); + if (!strcmp("required", key)) { drv->required = git_config_bool(var, value); return 0; @@ -919,7 +1207,7 @@ void convert_to_git_filter_fd(const char *path, int fd, struct strbuf *dst, convert_attrs(&ca, path); assert(ca.drv); - assert(ca.drv->clean); + assert(ca.drv->clean || ca.drv->process); if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN)) die("%s: clean filter '%s' failed", path, ca.drv->name); @@ -944,9 +1232,10 @@ static int convert_to_working_tree_internal(const char *path, const char *src, } /* * CRLF conversion can be skipped if normalizing, unless there - * is a smudge filter. The filter might expect CRLFs. + * is a smudge or process filter (even if the process filter doesn't + * support smudge). The filters might expect CRLFs. */ - if ((ca.drv && ca.drv->smudge) || !normalizing) { + if ((ca.drv && (ca.drv->smudge || ca.drv->process)) || !normalizing) { ret |= crlf_to_worktree(path, src, len, dst, ca.crlf_action); if (ret) { src = dst->buf; @@ -1407,7 +1696,7 @@ struct stream_filter *get_stream_filter(const char *path, const unsigned char *s struct stream_filter *filter = NULL; convert_attrs(&ca, path); - if (ca.drv && (ca.drv->smudge || ca.drv->clean)) + if (ca.drv && (ca.drv->process || ca.drv->smudge || ca.drv->clean)) return NULL; if (ca.crlf_action == CRLF_AUTO || ca.crlf_action == CRLF_AUTO_CRLF) diff --git a/t/t0021-conversion.sh b/t/t0021-conversion.sh index dc509381c9..a20b9f58e3 100755 --- a/t/t0021-conversion.sh +++ b/t/t0021-conversion.sh @@ -4,13 +4,72 @@ test_description='blob conversion via gitattributes' . ./test-lib.sh -cat <rot13.sh +TEST_ROOT="$(pwd)" + +cat <"$TEST_ROOT/rot13.sh" #!$SHELL_PATH tr \ 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ' \ 'nopqrstuvwxyzabcdefghijklmNOPQRSTUVWXYZABCDEFGHIJKLM' EOF -chmod +x rot13.sh +chmod +x "$TEST_ROOT/rot13.sh" + +generate_random_characters () { + LEN=$1 + NAME=$2 + test-genrandom some-seed $LEN | + perl -pe "s/./chr((ord($&) % 26) + ord('a'))/sge" >"$TEST_ROOT/$NAME" +} + +file_size () { + cat "$1" | wc -c | sed "s/^[ ]*//" +} + +filter_git () { + rm -f rot13-filter.log && + git "$@" 2>git-stderr.log && + rm -f git-stderr.log +} + +# Compare two files and ensure that `clean` and `smudge` respectively are +# called at least once if specified in the `expect` file. The actual +# invocation count is not relevant because their number can vary. +# c.f. http://public-inbox.org/git/xmqqshv18i8i.fsf@gitster.mtv.corp.google.com/ +test_cmp_count () { + expect=$1 + actual=$2 + for FILE in "$expect" "$actual" + do + sort "$FILE" | uniq -c | sed "s/^[ ]*//" | + sed "s/^\([0-9]\) IN: clean/x IN: clean/" | + sed "s/^\([0-9]\) IN: smudge/x IN: smudge/" >"$FILE.tmp" && + mv "$FILE.tmp" "$FILE" + done && + test_cmp "$expect" "$actual" +} + +# Compare two files but exclude all `clean` invocations because Git can +# call `clean` zero or more times. +# c.f. http://public-inbox.org/git/xmqqshv18i8i.fsf@gitster.mtv.corp.google.com/ +test_cmp_exclude_clean () { + expect=$1 + actual=$2 + for FILE in "$expect" "$actual" + do + grep -v "IN: clean" "$FILE" >"$FILE.tmp" && + mv "$FILE.tmp" "$FILE" + done && + test_cmp "$expect" "$actual" +} + +# Check that the contents of two files are equal and that their rot13 version +# is equal to the committed content. +test_cmp_committed_rot13 () { + test_cmp "$1" "$2" && + "$TEST_ROOT/rot13.sh" <"$1" >expected && + git cat-file blob :"$2" >actual && + test_cmp expected actual +} test_expect_success setup ' git config filter.rot13.smudge ./rot13.sh && @@ -31,7 +90,10 @@ test_expect_success setup ' cat test >test.i && git add test test.t test.i && rm -f test test.t test.i && - git checkout -- test test.t test.i + git checkout -- test test.t test.i && + + echo "content-test2" >test2.o && + echo "content-test3 - filename with special characters" >"test3 '\''sq'\'',\$x.o" ' script='s/^\$Id: \([0-9a-f]*\) \$/\1/p' @@ -279,4 +341,380 @@ test_expect_success 'diff does not reuse worktree files that need cleaning' ' test_line_count = 0 count ' +test_expect_success PERL 'required process filter should filter data' ' + test_config_global filter.protocol.process "$TEST_DIRECTORY/t0021/rot13-filter.pl clean smudge" && + test_config_global filter.protocol.required true && + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + + echo "git-stderr.log" >.gitignore && + echo "*.r filter=protocol" >.gitattributes && + git add . && + git commit . -m "test commit 1" && + git branch empty-branch && + + cp "$TEST_ROOT/test.o" test.r && + cp "$TEST_ROOT/test2.o" test2.r && + mkdir testsubdir && + cp "$TEST_ROOT/test3 '\''sq'\'',\$x.o" "testsubdir/test3 '\''sq'\'',\$x.r" && + >test4-empty.r && + + S=$(file_size test.r) && + S2=$(file_size test2.r) && + S3=$(file_size "testsubdir/test3 '\''sq'\'',\$x.r") && + + filter_git add . && + cat >expected.log <<-EOF && + START + init handshake complete + IN: clean test.r $S [OK] -- OUT: $S . [OK] + IN: clean test2.r $S2 [OK] -- OUT: $S2 . [OK] + IN: clean test4-empty.r 0 [OK] -- OUT: 0 [OK] + IN: clean testsubdir/test3 '\''sq'\'',\$x.r $S3 [OK] -- OUT: $S3 . [OK] + STOP + EOF + test_cmp_count expected.log rot13-filter.log && + + filter_git commit . -m "test commit 2" && + cat >expected.log <<-EOF && + START + init handshake complete + IN: clean test.r $S [OK] -- OUT: $S . [OK] + IN: clean test2.r $S2 [OK] -- OUT: $S2 . [OK] + IN: clean test4-empty.r 0 [OK] -- OUT: 0 [OK] + IN: clean testsubdir/test3 '\''sq'\'',\$x.r $S3 [OK] -- OUT: $S3 . [OK] + IN: clean test.r $S [OK] -- OUT: $S . [OK] + IN: clean test2.r $S2 [OK] -- OUT: $S2 . [OK] + IN: clean test4-empty.r 0 [OK] -- OUT: 0 [OK] + IN: clean testsubdir/test3 '\''sq'\'',\$x.r $S3 [OK] -- OUT: $S3 . [OK] + STOP + EOF + test_cmp_count expected.log rot13-filter.log && + + rm -f test2.r "testsubdir/test3 '\''sq'\'',\$x.r" && + + filter_git checkout --quiet --no-progress . && + cat >expected.log <<-EOF && + START + init handshake complete + IN: smudge test2.r $S2 [OK] -- OUT: $S2 . [OK] + IN: smudge testsubdir/test3 '\''sq'\'',\$x.r $S3 [OK] -- OUT: $S3 . [OK] + STOP + EOF + test_cmp_exclude_clean expected.log rot13-filter.log && + + filter_git checkout --quiet --no-progress empty-branch && + cat >expected.log <<-EOF && + START + init handshake complete + IN: clean test.r $S [OK] -- OUT: $S . [OK] + STOP + EOF + test_cmp_exclude_clean expected.log rot13-filter.log && + + filter_git checkout --quiet --no-progress master && + cat >expected.log <<-EOF && + START + init handshake complete + IN: smudge test.r $S [OK] -- OUT: $S . [OK] + IN: smudge test2.r $S2 [OK] -- OUT: $S2 . [OK] + IN: smudge test4-empty.r 0 [OK] -- OUT: 0 [OK] + IN: smudge testsubdir/test3 '\''sq'\'',\$x.r $S3 [OK] -- OUT: $S3 . [OK] + STOP + EOF + test_cmp_exclude_clean expected.log rot13-filter.log && + + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test.r && + test_cmp_committed_rot13 "$TEST_ROOT/test2.o" test2.r && + test_cmp_committed_rot13 "$TEST_ROOT/test3 '\''sq'\'',\$x.o" "testsubdir/test3 '\''sq'\'',\$x.r" + ) +' + +test_expect_success PERL 'required process filter takes precedence' ' + test_config_global filter.protocol.clean false && + test_config_global filter.protocol.process "$TEST_DIRECTORY/t0021/rot13-filter.pl clean" && + test_config_global filter.protocol.required true && + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + + echo "*.r filter=protocol" >.gitattributes && + cp "$TEST_ROOT/test.o" test.r && + S=$(file_size test.r) && + + # Check that the process filter is invoked here + filter_git add . && + cat >expected.log <<-EOF && + START + init handshake complete + IN: clean test.r $S [OK] -- OUT: $S . [OK] + STOP + EOF + test_cmp_count expected.log rot13-filter.log + ) +' + +test_expect_success PERL 'required process filter should be used only for "clean" operation only' ' + test_config_global filter.protocol.process "$TEST_DIRECTORY/t0021/rot13-filter.pl clean" && + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + + echo "*.r filter=protocol" >.gitattributes && + cp "$TEST_ROOT/test.o" test.r && + S=$(file_size test.r) && + + filter_git add . && + cat >expected.log <<-EOF && + START + init handshake complete + IN: clean test.r $S [OK] -- OUT: $S . [OK] + STOP + EOF + test_cmp_count expected.log rot13-filter.log && + + rm test.r && + + filter_git checkout --quiet --no-progress . && + # If the filter would be used for "smudge", too, we would see + # "IN: smudge test.r 57 [OK] -- OUT: 57 . [OK]" here + cat >expected.log <<-EOF && + START + init handshake complete + STOP + EOF + test_cmp_exclude_clean expected.log rot13-filter.log + ) +' + +test_expect_success PERL 'required process filter should process multiple packets' ' + test_config_global filter.protocol.process "$TEST_DIRECTORY/t0021/rot13-filter.pl clean smudge" && + test_config_global filter.protocol.required true && + + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + + # Generate data requiring 1, 2, 3 packets + S=65516 && # PKTLINE_DATA_MAXLEN -> Maximal size of a packet + generate_random_characters $(($S )) 1pkt_1__.file && + generate_random_characters $(($S +1)) 2pkt_1+1.file && + generate_random_characters $(($S*2-1)) 2pkt_2-1.file && + generate_random_characters $(($S*2 )) 2pkt_2__.file && + generate_random_characters $(($S*2+1)) 3pkt_2+1.file && + + for FILE in "$TEST_ROOT"/*.file + do + cp "$FILE" . && + "$TEST_ROOT/rot13.sh" <"$FILE" >"$FILE.rot13" + done && + + echo "*.file filter=protocol" >.gitattributes && + filter_git add *.file .gitattributes && + cat >expected.log <<-EOF && + START + init handshake complete + IN: clean 1pkt_1__.file $(($S )) [OK] -- OUT: $(($S )) . [OK] + IN: clean 2pkt_1+1.file $(($S +1)) [OK] -- OUT: $(($S +1)) .. [OK] + IN: clean 2pkt_2-1.file $(($S*2-1)) [OK] -- OUT: $(($S*2-1)) .. [OK] + IN: clean 2pkt_2__.file $(($S*2 )) [OK] -- OUT: $(($S*2 )) .. [OK] + IN: clean 3pkt_2+1.file $(($S*2+1)) [OK] -- OUT: $(($S*2+1)) ... [OK] + STOP + EOF + test_cmp_count expected.log rot13-filter.log && + + rm -f *.file && + + filter_git checkout --quiet --no-progress -- *.file && + cat >expected.log <<-EOF && + START + init handshake complete + IN: smudge 1pkt_1__.file $(($S )) [OK] -- OUT: $(($S )) . [OK] + IN: smudge 2pkt_1+1.file $(($S +1)) [OK] -- OUT: $(($S +1)) .. [OK] + IN: smudge 2pkt_2-1.file $(($S*2-1)) [OK] -- OUT: $(($S*2-1)) .. [OK] + IN: smudge 2pkt_2__.file $(($S*2 )) [OK] -- OUT: $(($S*2 )) .. [OK] + IN: smudge 3pkt_2+1.file $(($S*2+1)) [OK] -- OUT: $(($S*2+1)) ... [OK] + STOP + EOF + test_cmp_exclude_clean expected.log rot13-filter.log && + + for FILE in *.file + do + test_cmp_committed_rot13 "$TEST_ROOT/$FILE" $FILE + done + ) +' + +test_expect_success PERL 'required process filter with clean error should fail' ' + test_config_global filter.protocol.process "$TEST_DIRECTORY/t0021/rot13-filter.pl clean smudge" && + test_config_global filter.protocol.required true && + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + + echo "*.r filter=protocol" >.gitattributes && + + cp "$TEST_ROOT/test.o" test.r && + echo "this is going to fail" >clean-write-fail.r && + echo "content-test3-subdir" >test3.r && + + test_must_fail git add . + ) +' + +test_expect_success PERL 'process filter should restart after unexpected write failure' ' + test_config_global filter.protocol.process "$TEST_DIRECTORY/t0021/rot13-filter.pl clean smudge" && + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + + echo "*.r filter=protocol" >.gitattributes && + + cp "$TEST_ROOT/test.o" test.r && + cp "$TEST_ROOT/test2.o" test2.r && + echo "this is going to fail" >smudge-write-fail.o && + cp smudge-write-fail.o smudge-write-fail.r && + + S=$(file_size test.r) && + S2=$(file_size test2.r) && + SF=$(file_size smudge-write-fail.r) && + + git add . && + rm -f *.r && + + rm -f rot13-filter.log && + git checkout --quiet --no-progress . 2>git-stderr.log && + + grep "smudge write error at" git-stderr.log && + grep "error: external filter" git-stderr.log && + + cat >expected.log <<-EOF && + START + init handshake complete + IN: smudge smudge-write-fail.r $SF [OK] -- OUT: $SF [WRITE FAIL] + START + init handshake complete + IN: smudge test.r $S [OK] -- OUT: $S . [OK] + IN: smudge test2.r $S2 [OK] -- OUT: $S2 . [OK] + STOP + EOF + test_cmp_exclude_clean expected.log rot13-filter.log && + + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test.r && + test_cmp_committed_rot13 "$TEST_ROOT/test2.o" test2.r && + + # Smudge failed + ! test_cmp smudge-write-fail.o smudge-write-fail.r && + "$TEST_ROOT/rot13.sh" expected && + git cat-file blob :smudge-write-fail.r >actual && + test_cmp expected actual + ) +' + +test_expect_success PERL 'process filter should not be restarted if it signals an error' ' + test_config_global filter.protocol.process "$TEST_DIRECTORY/t0021/rot13-filter.pl clean smudge" && + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + + echo "*.r filter=protocol" >.gitattributes && + + cp "$TEST_ROOT/test.o" test.r && + cp "$TEST_ROOT/test2.o" test2.r && + echo "this will cause an error" >error.o && + cp error.o error.r && + + S=$(file_size test.r) && + S2=$(file_size test2.r) && + SE=$(file_size error.r) && + + git add . && + rm -f *.r && + + filter_git checkout --quiet --no-progress . && + cat >expected.log <<-EOF && + START + init handshake complete + IN: smudge error.r $SE [OK] -- OUT: 0 [ERROR] + IN: smudge test.r $S [OK] -- OUT: $S . [OK] + IN: smudge test2.r $S2 [OK] -- OUT: $S2 . [OK] + STOP + EOF + test_cmp_exclude_clean expected.log rot13-filter.log && + + test_cmp_committed_rot13 "$TEST_ROOT/test.o" test.r && + test_cmp_committed_rot13 "$TEST_ROOT/test2.o" test2.r && + test_cmp error.o error.r + ) +' + +test_expect_success PERL 'process filter abort stops processing of all further files' ' + test_config_global filter.protocol.process "$TEST_DIRECTORY/t0021/rot13-filter.pl clean smudge" && + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + + echo "*.r filter=protocol" >.gitattributes && + + cp "$TEST_ROOT/test.o" test.r && + cp "$TEST_ROOT/test2.o" test2.r && + echo "error this blob and all future blobs" >abort.o && + cp abort.o abort.r && + + SA=$(file_size abort.r) && + + git add . && + rm -f *.r && + + # Note: This test assumes that Git filters files in alphabetical + # order ("abort.r" before "test.r"). + filter_git checkout --quiet --no-progress . && + cat >expected.log <<-EOF && + START + init handshake complete + IN: smudge abort.r $SA [OK] -- OUT: 0 [ABORT] + STOP + EOF + test_cmp_exclude_clean expected.log rot13-filter.log && + + test_cmp "$TEST_ROOT/test.o" test.r && + test_cmp "$TEST_ROOT/test2.o" test2.r && + test_cmp abort.o abort.r + ) +' + +test_expect_success PERL 'invalid process filter must fail (and not hang!)' ' + test_config_global filter.protocol.process cat && + test_config_global filter.protocol.required true && + rm -rf repo && + mkdir repo && + ( + cd repo && + git init && + + echo "*.r filter=protocol" >.gitattributes && + + cp "$TEST_ROOT/test.o" test.r && + test_must_fail git add . 2>git-stderr.log && + grep "does not support filter protocol version" git-stderr.log + ) +' + test_done diff --git a/t/t0021/rot13-filter.pl b/t/t0021/rot13-filter.pl new file mode 100755 index 0000000000..ae4c50f5c5 --- /dev/null +++ b/t/t0021/rot13-filter.pl @@ -0,0 +1,192 @@ +#!/usr/bin/perl +# +# Example implementation for the Git filter protocol version 2 +# See Documentation/gitattributes.txt, section "Filter Protocol" +# +# The script takes the list of supported protocol capabilities as +# arguments ("clean", "smudge", etc). +# +# This implementation supports special test cases: +# (1) If data with the pathname "clean-write-fail.r" is processed with +# a "clean" operation then the write operation will die. +# (2) If data with the pathname "smudge-write-fail.r" is processed with +# a "smudge" operation then the write operation will die. +# (3) If data with the pathname "error.r" is processed with any +# operation then the filter signals that it cannot or does not want +# to process the file. +# (4) If data with the pathname "abort.r" is processed with any +# operation then the filter signals that it cannot or does not want +# to process the file and any file after that is processed with the +# same command. +# + +use strict; +use warnings; + +my $MAX_PACKET_CONTENT_SIZE = 65516; +my @capabilities = @ARGV; + +open my $debug, ">>", "rot13-filter.log" or die "cannot open log file: $!"; + +sub rot13 { + my $str = shift; + $str =~ y/A-Za-z/N-ZA-Mn-za-m/; + return $str; +} + +sub packet_bin_read { + my $buffer; + my $bytes_read = read STDIN, $buffer, 4; + if ( $bytes_read == 0 ) { + # EOF - Git stopped talking to us! + print $debug "STOP\n"; + exit(); + } + elsif ( $bytes_read != 4 ) { + die "invalid packet: '$buffer'"; + } + my $pkt_size = hex($buffer); + if ( $pkt_size == 0 ) { + return ( 1, "" ); + } + elsif ( $pkt_size > 4 ) { + my $content_size = $pkt_size - 4; + $bytes_read = read STDIN, $buffer, $content_size; + if ( $bytes_read != $content_size ) { + die "invalid packet ($content_size bytes expected; $bytes_read bytes read)"; + } + return ( 0, $buffer ); + } + else { + die "invalid packet size: $pkt_size"; + } +} + +sub packet_txt_read { + my ( $res, $buf ) = packet_bin_read(); + unless ( $buf =~ s/\n$// ) { + die "A non-binary line MUST be terminated by an LF."; + } + return ( $res, $buf ); +} + +sub packet_bin_write { + my $buf = shift; + print STDOUT sprintf( "%04x", length($buf) + 4 ); + print STDOUT $buf; + STDOUT->flush(); +} + +sub packet_txt_write { + packet_bin_write( $_[0] . "\n" ); +} + +sub packet_flush { + print STDOUT sprintf( "%04x", 0 ); + STDOUT->flush(); +} + +print $debug "START\n"; +$debug->flush(); + +( packet_txt_read() eq ( 0, "git-filter-client" ) ) || die "bad initialize"; +( packet_txt_read() eq ( 0, "version=2" ) ) || die "bad version"; +( packet_bin_read() eq ( 1, "" ) ) || die "bad version end"; + +packet_txt_write("git-filter-server"); +packet_txt_write("version=2"); +packet_flush(); + +( packet_txt_read() eq ( 0, "capability=clean" ) ) || die "bad capability"; +( packet_txt_read() eq ( 0, "capability=smudge" ) ) || die "bad capability"; +( packet_bin_read() eq ( 1, "" ) ) || die "bad capability end"; + +foreach (@capabilities) { + packet_txt_write( "capability=" . $_ ); +} +packet_flush(); +print $debug "init handshake complete\n"; +$debug->flush(); + +while (1) { + my ($command) = packet_txt_read() =~ /^command=([^=]+)$/; + print $debug "IN: $command"; + $debug->flush(); + + my ($pathname) = packet_txt_read() =~ /^pathname=([^=]+)$/; + print $debug " $pathname"; + $debug->flush(); + + # Flush + packet_bin_read(); + + my $input = ""; + { + binmode(STDIN); + my $buffer; + my $done = 0; + while ( !$done ) { + ( $done, $buffer ) = packet_bin_read(); + $input .= $buffer; + } + print $debug " " . length($input) . " [OK] -- "; + $debug->flush(); + } + + my $output; + if ( $pathname eq "error.r" or $pathname eq "abort.r" ) { + $output = ""; + } + elsif ( $command eq "clean" and grep( /^clean$/, @capabilities ) ) { + $output = rot13($input); + } + elsif ( $command eq "smudge" and grep( /^smudge$/, @capabilities ) ) { + $output = rot13($input); + } + else { + die "bad command '$command'"; + } + + print $debug "OUT: " . length($output) . " "; + $debug->flush(); + + if ( $pathname eq "error.r" ) { + print $debug "[ERROR]\n"; + $debug->flush(); + packet_txt_write("status=error"); + packet_flush(); + } + elsif ( $pathname eq "abort.r" ) { + print $debug "[ABORT]\n"; + $debug->flush(); + packet_txt_write("status=abort"); + packet_flush(); + } + else { + packet_txt_write("status=success"); + packet_flush(); + + if ( $pathname eq "${command}-write-fail.r" ) { + print $debug "[WRITE FAIL]\n"; + $debug->flush(); + die "${command} write error"; + } + + while ( length($output) > 0 ) { + my $packet = substr( $output, 0, $MAX_PACKET_CONTENT_SIZE ); + packet_bin_write($packet); + # dots represent the number of packets + print $debug "."; + if ( length($output) > $MAX_PACKET_CONTENT_SIZE ) { + $output = substr( $output, $MAX_PACKET_CONTENT_SIZE ); + } + else { + $output = ""; + } + } + packet_flush(); + print $debug " [OK]\n"; + $debug->flush(); + packet_flush(); + } +} From 0f71fa273fc6c352a266894f1f757c5950230d9b Mon Sep 17 00:00:00 2001 From: Lars Schneider Date: Sun, 16 Oct 2016 16:20:38 -0700 Subject: [PATCH 14/14] contrib/long-running-filter: add long running filter example Add a simple pass-thru filter as example implementation for the Git filter protocol version 2. See Documentation/gitattributes.txt, section "Filter Protocol" for more info. Signed-off-by: Lars Schneider Signed-off-by: Junio C Hamano --- Documentation/gitattributes.txt | 4 +- contrib/long-running-filter/example.pl | 128 +++++++++++++++++++++++++ 2 files changed, 131 insertions(+), 1 deletion(-) create mode 100755 contrib/long-running-filter/example.pl diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt index 3f4d1edb1f..976243a63e 100644 --- a/Documentation/gitattributes.txt +++ b/Documentation/gitattributes.txt @@ -516,7 +516,9 @@ the command pipe on exit. The filter is expected to detect EOF and exit gracefully on its own. Git will wait until the filter process has stopped. -If you develop your own long running filter +A long running filter demo implementation can be found in +`contrib/long-running-filter/example.pl` located in the Git +core repository. If you develop your own long running filter process then the `GIT_TRACE_PACKET` environment variables can be very helpful for debugging (see linkgit:git[1]). diff --git a/contrib/long-running-filter/example.pl b/contrib/long-running-filter/example.pl new file mode 100755 index 0000000000..39457055a5 --- /dev/null +++ b/contrib/long-running-filter/example.pl @@ -0,0 +1,128 @@ +#!/usr/bin/perl +# +# Example implementation for the Git filter protocol version 2 +# See Documentation/gitattributes.txt, section "Filter Protocol" +# +# Please note, this pass-thru filter is a minimal skeleton. No proper +# error handling was implemented. +# + +use strict; +use warnings; + +my $MAX_PACKET_CONTENT_SIZE = 65516; + +sub packet_bin_read { + my $buffer; + my $bytes_read = read STDIN, $buffer, 4; + if ( $bytes_read == 0 ) { + + # EOF - Git stopped talking to us! + exit(); + } + elsif ( $bytes_read != 4 ) { + die "invalid packet: '$buffer'"; + } + my $pkt_size = hex($buffer); + if ( $pkt_size == 0 ) { + return ( 1, "" ); + } + elsif ( $pkt_size > 4 ) { + my $content_size = $pkt_size - 4; + $bytes_read = read STDIN, $buffer, $content_size; + if ( $bytes_read != $content_size ) { + die "invalid packet ($content_size bytes expected; $bytes_read bytes read)"; + } + return ( 0, $buffer ); + } + else { + die "invalid packet size: $pkt_size"; + } +} + +sub packet_txt_read { + my ( $res, $buf ) = packet_bin_read(); + unless ( $buf =~ s/\n$// ) { + die "A non-binary line MUST be terminated by an LF."; + } + return ( $res, $buf ); +} + +sub packet_bin_write { + my $buf = shift; + print STDOUT sprintf( "%04x", length($buf) + 4 ); + print STDOUT $buf; + STDOUT->flush(); +} + +sub packet_txt_write { + packet_bin_write( $_[0] . "\n" ); +} + +sub packet_flush { + print STDOUT sprintf( "%04x", 0 ); + STDOUT->flush(); +} + +( packet_txt_read() eq ( 0, "git-filter-client" ) ) || die "bad initialize"; +( packet_txt_read() eq ( 0, "version=2" ) ) || die "bad version"; +( packet_bin_read() eq ( 1, "" ) ) || die "bad version end"; + +packet_txt_write("git-filter-server"); +packet_txt_write("version=2"); +packet_flush(); + +( packet_txt_read() eq ( 0, "capability=clean" ) ) || die "bad capability"; +( packet_txt_read() eq ( 0, "capability=smudge" ) ) || die "bad capability"; +( packet_bin_read() eq ( 1, "" ) ) || die "bad capability end"; + +packet_txt_write("capability=clean"); +packet_txt_write("capability=smudge"); +packet_flush(); + +while (1) { + my ($command) = packet_txt_read() =~ /^command=([^=]+)$/; + my ($pathname) = packet_txt_read() =~ /^pathname=([^=]+)$/; + + packet_bin_read(); + + my $input = ""; + { + binmode(STDIN); + my $buffer; + my $done = 0; + while ( !$done ) { + ( $done, $buffer ) = packet_bin_read(); + $input .= $buffer; + } + } + + my $output; + if ( $command eq "clean" ) { + ### Perform clean here ### + $output = $input; + } + elsif ( $command eq "smudge" ) { + ### Perform smudge here ### + $output = $input; + } + else { + die "bad command '$command'"; + } + + packet_txt_write("status=success"); + packet_flush(); + while ( length($output) > 0 ) { + my $packet = substr( $output, 0, $MAX_PACKET_CONTENT_SIZE ); + packet_bin_write($packet); + if ( length($output) > $MAX_PACKET_CONTENT_SIZE ) { + $output = substr( $output, $MAX_PACKET_CONTENT_SIZE ); + } + else { + $output = ""; + } + } + packet_flush(); # flush content! + packet_flush(); # empty list, keep "status=success" unchanged! + +}