From aa245db50c1762c65db9f0a6816f9b70fdc5d6a3 Mon Sep 17 00:00:00 2001 From: Pablo Sabater Date: Mon, 8 Jun 2026 12:14:24 +0200 Subject: [PATCH 01/12] transport-helper: fix memory leak of helper on disconnect disconnect_helper() only frees data inside of the if(data->helper) block [1]. When the transport is disconnected without the helper being fully started, data->name allocated in transport_helper_init() is never freed. Move FREE_AND_NULL(data->name) outside the conditional block so it's always freed on disconnect. [1]: https://lore.kernel.org/git/05fbadbae2184479c87c37675dde7bd79b3e32ab.1716465556.git.ps@pks.im/ Mentored-by: Karthik Nayak Mentored-by: Chandra Pratap Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- transport-helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/transport-helper.c b/transport-helper.c index 04d55572a9..20a6ea8f81 100644 --- a/transport-helper.c +++ b/transport-helper.c @@ -266,9 +266,9 @@ static int disconnect_helper(struct transport *transport) close(data->helper->out); fclose(data->out); res = finish_command(data->helper); - FREE_AND_NULL(data->name); FREE_AND_NULL(data->helper); } + FREE_AND_NULL(data->name); return res; } From 0332ea7eb47cfad5138fadb1c29b9949917ea1be Mon Sep 17 00:00:00 2001 From: Eric Ju Date: Mon, 8 Jun 2026 12:14:25 +0200 Subject: [PATCH 02/12] git-compat-util: add strtoul_ul() with error handling We already have strtoul_ui() and similar functions that provide proper error handling using strtoul from the standard library. However, there isn't currently a variant that returns an unsigned long. This variant is needed in a subsequent commit. Add strtoul_ul() to address this gap, enabling the return of an unsigned long with proper error handling. Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- git-compat-util.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/git-compat-util.h b/git-compat-util.h index 8809776407..4bf569f35c 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -975,6 +975,26 @@ static inline int strtoul_ui(char const *s, int base, unsigned int *result) return 0; } +/* + * Convert a string to an unsigned long using the standard library's strtoul, + * with additional error handling to ensure robustness. + */ +static inline int strtoul_ul(char const *s, int base, unsigned long *result) +{ + unsigned long ul; + char *p; + + errno = 0; + /* negative values would be accepted by strtoul */ + if (strchr(s, '-')) + return -1; + ul = strtoul(s, &p, base); + if (errno || *p || p == s) + return -1; + *result = ul; + return 0; +} + static inline int strtol_i(char const *s, int base, int *result) { long ul; From 0a3e2e9496feb9e9e1da87224ff530c27f9818fa Mon Sep 17 00:00:00 2001 From: Eric Ju Date: Mon, 8 Jun 2026 12:14:26 +0200 Subject: [PATCH 03/12] cat-file: add declaration of variable i inside its for loop Some code used in this series declares variable i and only uses it in a for loop, not in any other logic outside the loop. Change the declaration of i to be inside the for loop for readability. While at it, we also change its type from "int" to "size_t" where the latter makes more sense. Helped-by: Christian Couder Signed-off-by: Eric Ju Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- builtin/cat-file.c | 11 +++-------- fetch-pack.c | 3 +-- 2 files changed, 4 insertions(+), 10 deletions(-) diff --git a/builtin/cat-file.c b/builtin/cat-file.c index fa45f774d7..c060fd4800 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -726,12 +726,10 @@ static void dispatch_calls(struct batch_options *opt, struct queued_cmd *cmd, int nr) { - int i; - if (!opt->buffer_output) die(_("flush is only for --buffer mode")); - for (i = 0; i < nr; i++) + for (size_t i = 0; i < nr; i++) cmd[i].fn(opt, cmd[i].line, output, data); fflush(stdout); @@ -739,9 +737,7 @@ static void dispatch_calls(struct batch_options *opt, static void free_cmds(struct queued_cmd *cmd, size_t *nr) { - size_t i; - - for (i = 0; i < *nr; i++) + for (size_t i = 0; i < *nr; i++) FREE_AND_NULL(cmd[i].line); *nr = 0; @@ -768,7 +764,6 @@ static void batch_objects_command(struct batch_options *opt, size_t alloc = 0, nr = 0; while (strbuf_getdelim_strip_crlf(&input, stdin, opt->input_delim) != EOF) { - int i; const struct parse_cmd *cmd = NULL; const char *p = NULL, *cmd_end; struct queued_cmd call = {0}; @@ -778,7 +773,7 @@ static void batch_objects_command(struct batch_options *opt, if (isspace(*input.buf)) die(_("whitespace before command: '%s'"), input.buf); - for (i = 0; i < ARRAY_SIZE(commands); i++) { + for (size_t i = 0; i < ARRAY_SIZE(commands); i++) { if (!skip_prefix(input.buf, commands[i].name, &cmd_end)) continue; diff --git a/fetch-pack.c b/fetch-pack.c index 120e01f3cf..f13951d154 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -1388,9 +1388,8 @@ static void write_fetch_command_and_capabilities(struct strbuf *req_buf, if (advertise_sid && server_supports_v2("session-id")) packet_buf_write(req_buf, "session-id=%s", trace2_session_id()); if (server_options && server_options->nr) { - int i; ensure_server_supports_v2("server-option"); - for (i = 0; i < server_options->nr; i++) + for (size_t i = 0; i < server_options->nr; i++) packet_buf_write(req_buf, "server-option=%s", server_options->items[i].string); } From ba9b6b1e77a6f99f7b60ec6cdb60273f7533a34c Mon Sep 17 00:00:00 2001 From: Eric Ju Date: Mon, 8 Jun 2026 12:14:27 +0200 Subject: [PATCH 04/12] t1006: split test utility functions into new "lib-cat-file.sh" This refactor extracts utility functions from the cat-file's test script "t1006-cat-file.sh" into a new "lib-cat-file.sh" dedicated library file. The goal is to improve code reuse and readability, enabling future tests to leverage these utilities without duplicating code. Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- t/lib-cat-file.sh | 16 ++++++++++++++++ t/t1006-cat-file.sh | 13 +------------ 2 files changed, 17 insertions(+), 12 deletions(-) create mode 100644 t/lib-cat-file.sh diff --git a/t/lib-cat-file.sh b/t/lib-cat-file.sh new file mode 100644 index 0000000000..44af232d74 --- /dev/null +++ b/t/lib-cat-file.sh @@ -0,0 +1,16 @@ +# Library of git-cat-file related test functions. + +# Print a string without a trailing newline. +echo_without_newline () { + printf '%s' "$*" +} + +# Print a string without newlines and replace them with a NULL character (\0). +echo_without_newline_nul () { + echo_without_newline "$@" | tr '\n' '\0' +} + +# Calculate the length of a string. +strlen () { + echo_without_newline "$1" | wc -c | sed -e 's/^ *//' +} diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh index 8e2c52652c..8360f3bbd9 100755 --- a/t/t1006-cat-file.sh +++ b/t/t1006-cat-file.sh @@ -4,6 +4,7 @@ test_description='git cat-file' . ./test-lib.sh . "$TEST_DIRECTORY/lib-loose.sh" +. "$TEST_DIRECTORY"/lib-cat-file.sh test_cmdmode_usage () { test_expect_code 129 "$@" 2>err && @@ -99,18 +100,6 @@ do ' done -echo_without_newline () { - printf '%s' "$*" -} - -echo_without_newline_nul () { - echo_without_newline "$@" | tr '\n' '\0' -} - -strlen () { - echo_without_newline "$1" | wc -c | sed -e 's/^ *//' -} - run_tests () { type=$1 object_name="$2" From 0ea013ac796efb7a608a12be1b4a88d132d030b1 Mon Sep 17 00:00:00 2001 From: Pablo Sabater Date: Mon, 8 Jun 2026 12:14:28 +0200 Subject: [PATCH 05/12] fetch-pack: move function to connect.c write_fetch_command_and_capabilities will be refactored in a subsequent commit where it will become a more general-purpose function, making it more accessible to additional commands in the future. To move `write_fetch_command_and_capabilities()` to `connect.c`, we need to adjust how `advertise_sid` is managed. Previously in `fetch_pack.c`, `advertise_sid` was a static variable, modified using `repo_config_get_bool()`. In `connect.c`, we now initialize `advertise_sid` at the begining by directly using `repo_config_get_bool()`. This change is safe because: In the original `fetch-pack.c` code, there are only two places that write `advertise_sid`: 1. In function `do_fetch_pack()`: if (!sever_supports("session_id")) advertise_sid = 0; 2. In function `fetch_pack_config()`: repo_config_get_bool("transfer.advertisesid", &advertise_sid); About 1, since `do_fetch_pack()` is only relevant for protocol v1, this assignment can be ignored, as `write_fetch_command_and_capabilities()` is only used in v2. About 2, `repo_config_get_bool()` is from `config.h` and it's an out-of-box dependency of `connect.c`, so we can reuse it directly. Move `write_fetch_command_and_capabilities()` to `connect.c` Helped-by: Jonathan Tan Helped-by: Christian Couder Signed-off-by: Calvin Wan Signed-off-by: Eric Ju Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- connect.c | 34 ++++++++++++++++++++++++++++++++++ connect.h | 4 ++++ fetch-pack.c | 31 ------------------------------- 3 files changed, 38 insertions(+), 31 deletions(-) diff --git a/connect.c b/connect.c index 47e39d2a73..1dced8e632 100644 --- a/connect.c +++ b/connect.c @@ -700,6 +700,40 @@ int server_supports(const char *feature) return !!server_feature_value(feature, NULL); } +void write_fetch_command_and_capabilities(struct strbuf *req_buf, + const struct string_list *server_options) +{ + const char *hash_name; + int advertise_sid; + + repo_config_get_bool(the_repository, "transfer.advertisesid", &advertise_sid); + + ensure_server_supports_v2("fetch"); + packet_buf_write(req_buf, "command=fetch"); + if (server_supports_v2("agent")) + packet_buf_write(req_buf, "agent=%s", git_user_agent_sanitized()); + if (advertise_sid && server_supports_v2("session-id")) + packet_buf_write(req_buf, "session-id=%s", trace2_session_id()); + if (server_options && server_options->nr) { + ensure_server_supports_v2("server-option"); + for (size_t i = 0; i < server_options->nr; i++) + packet_buf_write(req_buf, "server-option=%s", + server_options->items[i].string); + } + + if (server_feature_v2("object-format", &hash_name)) { + const unsigned int hash_algo = hash_algo_by_name(hash_name); + if (hash_algo_by_ptr(the_hash_algo) != hash_algo) + die(_("mismatched algorithms: client %s; server %s"), + the_hash_algo->name, hash_name); + packet_buf_write(req_buf, "object-format=%s", the_hash_algo->name); + } else if (hash_algo_by_ptr(the_hash_algo) != GIT_HASH_SHA1_LEGACY) { + die(_("the server does not support algorithm '%s'"), + the_hash_algo->name); + } + packet_buf_delim(req_buf); +} + static const char *url_scheme_name(enum url_scheme scheme) { switch (scheme) { diff --git a/connect.h b/connect.h index aa482a37fb..c4f6ea4b0a 100644 --- a/connect.h +++ b/connect.h @@ -34,4 +34,8 @@ void check_stateless_delimiter(int stateless_rpc, struct packet_reader *reader, const char *error); +struct string_list; +void write_fetch_command_and_capabilities(struct strbuf *req_buf, + const struct string_list *server_options); + #endif diff --git a/fetch-pack.c b/fetch-pack.c index f13951d154..4a8a70b5f3 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -1376,37 +1376,6 @@ static int add_haves(struct fetch_negotiator *negotiator, return haves_added; } -static void write_fetch_command_and_capabilities(struct strbuf *req_buf, - const struct string_list *server_options) -{ - const char *hash_name; - - ensure_server_supports_v2("fetch"); - packet_buf_write(req_buf, "command=fetch"); - if (server_supports_v2("agent")) - packet_buf_write(req_buf, "agent=%s", git_user_agent_sanitized()); - if (advertise_sid && server_supports_v2("session-id")) - packet_buf_write(req_buf, "session-id=%s", trace2_session_id()); - if (server_options && server_options->nr) { - ensure_server_supports_v2("server-option"); - for (size_t i = 0; i < server_options->nr; i++) - packet_buf_write(req_buf, "server-option=%s", - server_options->items[i].string); - } - - if (server_feature_v2("object-format", &hash_name)) { - int hash_algo = hash_algo_by_name(hash_name); - if (hash_algo_by_ptr(the_hash_algo) != hash_algo) - die(_("mismatched algorithms: client %s; server %s"), - the_hash_algo->name, hash_name); - packet_buf_write(req_buf, "object-format=%s", the_hash_algo->name); - } else if (hash_algo_by_ptr(the_hash_algo) != GIT_HASH_SHA1_LEGACY) { - die(_("the server does not support algorithm '%s'"), - the_hash_algo->name); - } - packet_buf_delim(req_buf); -} - static int send_fetch_request(struct fetch_negotiator *negotiator, int fd_out, struct fetch_pack_args *args, const struct ref *wants, struct oidset *common, From 6dc0d94911e3dcaddfa7bcd718fb7c39ff703763 Mon Sep 17 00:00:00 2001 From: Pablo Sabater Date: Mon, 8 Jun 2026 12:14:29 +0200 Subject: [PATCH 06/12] connect: refactor packet writing Refactor `write_fetch_command_and_capabilities()`, enabling it to serve both fetch and additional commands. In this context, "command" refers to the "operations" supported by Git's wire protocol https://git-scm.com/docs/protocol-v2, such as a Git subcommand (e.g., git-fetch(1)) or a server-side operation like "object-info" as implemented in commit a2ba162 (object-info: support for retrieving object info, 2021-04-20). Refactor the function signature to accept a command instead of the hardcoded "fetch". Helped-by: Jonathan Tan Helped-by: Christian Couder Signed-off-by: Calvin Wan Signed-off-by: Eric Ju Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- connect.c | 10 +++++----- connect.h | 8 ++++++-- fetch-pack.c | 4 ++-- 3 files changed, 13 insertions(+), 9 deletions(-) diff --git a/connect.c b/connect.c index 1dced8e632..78c69d4485 100644 --- a/connect.c +++ b/connect.c @@ -700,16 +700,16 @@ int server_supports(const char *feature) return !!server_feature_value(feature, NULL); } -void write_fetch_command_and_capabilities(struct strbuf *req_buf, - const struct string_list *server_options) +void write_command_and_capabilities(struct strbuf *req_buf, const char *command, + const struct string_list *server_options) { const char *hash_name; int advertise_sid; repo_config_get_bool(the_repository, "transfer.advertisesid", &advertise_sid); - ensure_server_supports_v2("fetch"); - packet_buf_write(req_buf, "command=fetch"); + ensure_server_supports_v2(command); + packet_buf_write(req_buf, "command=%s", command); if (server_supports_v2("agent")) packet_buf_write(req_buf, "agent=%s", git_user_agent_sanitized()); if (advertise_sid && server_supports_v2("session-id")) @@ -727,7 +727,7 @@ void write_fetch_command_and_capabilities(struct strbuf *req_buf, die(_("mismatched algorithms: client %s; server %s"), the_hash_algo->name, hash_name); packet_buf_write(req_buf, "object-format=%s", the_hash_algo->name); - } else if (hash_algo_by_ptr(the_hash_algo) != GIT_HASH_SHA1_LEGACY) { + } else if (hash_algo_by_ptr(the_hash_algo) != GIT_HASH_SHA1) { die(_("the server does not support algorithm '%s'"), the_hash_algo->name); } diff --git a/connect.h b/connect.h index c4f6ea4b0a..8f4c523892 100644 --- a/connect.h +++ b/connect.h @@ -34,8 +34,12 @@ void check_stateless_delimiter(int stateless_rpc, struct packet_reader *reader, const char *error); +/* + * Writes a command along with the requested server capabilities/features into a + * request buffer. + */ struct string_list; -void write_fetch_command_and_capabilities(struct strbuf *req_buf, - const struct string_list *server_options); +void write_command_and_capabilities(struct strbuf *req_buf, const char *command, + const struct string_list *server_options); #endif diff --git a/fetch-pack.c b/fetch-pack.c index 4a8a70b5f3..3d32114907 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -1387,7 +1387,7 @@ static int send_fetch_request(struct fetch_negotiator *negotiator, int fd_out, int done_sent = 0; struct strbuf req_buf = STRBUF_INIT; - write_fetch_command_and_capabilities(&req_buf, args->server_options); + write_command_and_capabilities(&req_buf, "fetch", args->server_options); if (args->use_thin_pack) packet_buf_write(&req_buf, "thin-pack"); @@ -2255,7 +2255,7 @@ void negotiate_using_fetch(const struct oid_array *negotiation_restrict_tips, the_repository, "%d", negotiation_round); strbuf_reset(&req_buf); - write_fetch_command_and_capabilities(&req_buf, server_options); + write_command_and_capabilities(&req_buf, "fetch", server_options); packet_buf_write(&req_buf, "wait-for-done"); From 75a2daeeb19dd67e364c2cd05b454fb58fd09817 Mon Sep 17 00:00:00 2001 From: Calvin Wan Date: Mon, 8 Jun 2026 12:14:30 +0200 Subject: [PATCH 07/12] fetch-pack: move fetch initialization There are some variables initialized at the start of the do_fetch_pack_v2() state machine. Currently, they are initialized in FETCH_CHECK_LOCAL, which is the initial state set at the beginning of the function. However, a subsequent patch will allow for another initial state, while still requiring these initialized variables. Move the initialization to be before the state machine, so that they are set regardless of the initial state. Note that there is no change in behavior, because we're moving code from the beginning of the first state to just before the execution of the state machine. Helped-by: Jonathan Tan Helped-by: Christian Couder Signed-off-by: Calvin Wan Signed-off-by: Eric Ju Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- fetch-pack.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fetch-pack.c b/fetch-pack.c index 3d32114907..cdebd3476f 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -1736,18 +1736,18 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args, reader.me = "fetch-pack"; } + /* v2 supports these by default */ + allow_unadvertised_object_request |= ALLOW_REACHABLE_SHA1; + use_sideband = 2; + if (args->depth > 0 || args->deepen_since || args->deepen_not) + args->deepen = 1; + while (state != FETCH_DONE) { switch (state) { case FETCH_CHECK_LOCAL: sort_ref_list(&ref, ref_compare_name); QSORT(sought, nr_sought, cmp_ref_by_name); - /* v2 supports these by default */ - allow_unadvertised_object_request |= ALLOW_REACHABLE_SHA1; - use_sideband = 2; - if (args->depth > 0 || args->deepen_since || args->deepen_not) - args->deepen = 1; - /* Filter 'ref' by 'sought' and those that aren't local */ mark_complete_and_common_ref(negotiator, args, &ref); filter_refs(args, &ref, sought, nr_sought); From 49d0a8b519a78f78f91fb96a88d109ffc7aef571 Mon Sep 17 00:00:00 2001 From: Calvin Wan Date: Mon, 8 Jun 2026 12:14:31 +0200 Subject: [PATCH 08/12] serve: advertise object-info feature In order for a client to know what object-info components a server can provide, advertise supported object-info features. This will allow a client to decide whether to query the server for object-info or fetch as a fallback. Helped-by: Jonathan Tan Helped-by: Christian Couder Signed-off-by: Calvin Wan Signed-off-by: Eric Ju Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- serve.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/serve.c b/serve.c index 49a6e39b1d..2b07d922b3 100644 --- a/serve.c +++ b/serve.c @@ -89,7 +89,7 @@ static void session_id_receive(struct repository *r UNUSED, trace2_data_string("transfer", NULL, "client-sid", client_sid); } -static int object_info_advertise(struct repository *r, struct strbuf *value UNUSED) +static int object_info_advertise(struct repository *r, struct strbuf *value) { if (advertise_object_info == -1 && repo_config_get_bool(r, "transfer.advertiseobjectinfo", @@ -97,6 +97,9 @@ static int object_info_advertise(struct repository *r, struct strbuf *value UNUS /* disabled by default */ advertise_object_info = 0; } + /* Currently only size is supported */ + if (value && advertise_object_info) + strbuf_addstr(value, "size"); return advertise_object_info; } From 7568f84d86596a2cedb3fa0f8f2b825b3b55db18 Mon Sep 17 00:00:00 2001 From: Calvin Wan Date: Mon, 8 Jun 2026 12:14:32 +0200 Subject: [PATCH 09/12] transport: add client support for object-info Sometimes, it is beneficial to retrieve information about an object without downloading it entirely. The server-side logic for this functionality was implemented in commit "a2ba162cda (object-info: support for retrieving object info, 2021-04-20)." And the wire format is documented at https://git-scm.com/docs/protocol-v2#_object_info. This commit introduces client functions to interact with the server. Currently, the client supports requesting a list of object IDs with the 'size' feature from a v2 server. If the server does not advertise this feature (i.e., transfer.advertiseobjectinfo is set to false), the client will return an error and exit. Notice that the entire request is written into req_buf before being sent to the remote. This approach follows the pattern used in the `send_fetch_request()` logic within fetch-pack.c. Streaming the request is not addressed in this patch. Helped-by: Jonathan Tan Helped-by: Christian Couder Signed-off-by: Calvin Wan Signed-off-by: Eric Ju Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- Makefile | 1 + fetch-object-info.c | 87 +++++++++++++++++++++++++++++++++++++++++++++ fetch-object-info.h | 22 ++++++++++++ fetch-pack.c | 3 ++ fetch-pack.h | 2 ++ meson.build | 1 + transport-helper.c | 11 ++++-- transport.c | 28 ++++++++++++++- transport.h | 11 ++++++ 9 files changed, 163 insertions(+), 3 deletions(-) create mode 100644 fetch-object-info.c create mode 100644 fetch-object-info.h diff --git a/Makefile b/Makefile index b31ecb0756..45453e03c5 100644 --- a/Makefile +++ b/Makefile @@ -1159,6 +1159,7 @@ LIB_OBJS += ewah/ewah_rlw.o LIB_OBJS += exec-cmd.o LIB_OBJS += fetch-negotiator.o LIB_OBJS += fetch-pack.o +LIB_OBJS += fetch-object-info.o LIB_OBJS += fmt-merge-msg.o LIB_OBJS += fsck.o LIB_OBJS += fsmonitor.o diff --git a/fetch-object-info.c b/fetch-object-info.c new file mode 100644 index 0000000000..51a898430d --- /dev/null +++ b/fetch-object-info.c @@ -0,0 +1,87 @@ +#include "git-compat-util.h" +#include "gettext.h" +#include "hex.h" +#include "pkt-line.h" +#include "connect.h" +#include "oid-array.h" +#include "odb.h" +#include "fetch-object-info.h" +#include "string-list.h" + +/* Sends git-cat-file object-info command and its arguments into the request buffer. */ +static void send_object_info_request(const int fd_out, struct object_info_args *args) +{ + struct strbuf req_buf = STRBUF_INIT; + + write_command_and_capabilities(&req_buf, "object-info", args->server_options); + + if (unsorted_string_list_has_string(args->object_info_options, "size")) + packet_buf_write(&req_buf, "size"); + + if (args->oids) + for (size_t i = 0; i < args->oids->nr; i++) + packet_buf_write(&req_buf, "oid %s", oid_to_hex(&args->oids->oid[i])); + + packet_buf_flush(&req_buf); + if (write_in_full(fd_out, req_buf.buf, req_buf.len) < 0) + die_errno(_("unable to write request to remote")); + + strbuf_release(&req_buf); +} + +int fetch_object_info(const enum protocol_version version, struct object_info_args *args, + struct packet_reader *reader, struct object_info *object_info_data, + const int stateless_rpc, const int fd_out) +{ + int size_index = -1; + + switch (version) { + case protocol_v2: + if (!server_supports_v2("object-info")) + die(_("object-info capability is not enabled on the server")); + send_object_info_request(fd_out, args); + break; + case protocol_v1: + case protocol_v0: + die(_("unsupported protocol version. expected v2")); + case protocol_unknown_version: + BUG("unknown protocol version"); + } + + for (size_t i = 0; i < args->object_info_options->nr; i++) { + if (packet_reader_read(reader) != PACKET_READ_NORMAL) { + check_stateless_delimiter(stateless_rpc, reader, "stateless delimiter expected"); + return -1; + } + + if (!string_list_has_string(args->object_info_options, reader->line)) + return -1; + + if (!strcmp(reader->line, "size")) { + size_index = i; + for (size_t j = 0; j < args->oids->nr; j++) + object_info_data[j].sizep = xcalloc(1, sizeof(*object_info_data[j].sizep)); + } + } + + for (size_t i = 0; packet_reader_read(reader) == PACKET_READ_NORMAL && i < args->oids->nr; i++) { + struct string_list object_info_values = STRING_LIST_INIT_DUP; + + string_list_split(&object_info_values, reader->line, " ", -1); + if (0 <= size_index) { + if (!strcmp(object_info_values.items[1 + size_index].string, "")) + die("object-info: server does not recognize object %s", + object_info_values.items[0].string); + + if (strtoul_ul(object_info_values.items[1 + size_index].string, 10, object_info_data[i].sizep)) + die("object-info: ref %s has invalid size %s", + object_info_values.items[0].string, + object_info_values.items[1 + size_index].string); + } + + string_list_clear(&object_info_values, 0); + } + check_stateless_delimiter(stateless_rpc, reader, "stateless delimiter expected"); + + return 0; +} diff --git a/fetch-object-info.h b/fetch-object-info.h new file mode 100644 index 0000000000..d35284bd6b --- /dev/null +++ b/fetch-object-info.h @@ -0,0 +1,22 @@ +#ifndef FETCH_OBJECT_INFO_H +#define FETCH_OBJECT_INFO_H + +#include "pkt-line.h" +#include "protocol.h" +#include "odb.h" + +struct object_info_args { + struct string_list *object_info_options; + const struct string_list *server_options; + struct oid_array *oids; +}; + +/* + * Sends git-cat-file object-info command into the request buf and read the + * results from packets. + */ +int fetch_object_info(enum protocol_version version, struct object_info_args *args, + struct packet_reader *reader, struct object_info *object_info_data, + int stateless_rpc, int fd_out); + +#endif /* FETCH_OBJECT_INFO_H */ diff --git a/fetch-pack.c b/fetch-pack.c index cdebd3476f..a86c93fc52 100644 --- a/fetch-pack.c +++ b/fetch-pack.c @@ -1742,6 +1742,9 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args, if (args->depth > 0 || args->deepen_since || args->deepen_not) args->deepen = 1; + if (args->object_info) + state = FETCH_SEND_REQUEST; + while (state != FETCH_DONE) { switch (state) { case FETCH_CHECK_LOCAL: diff --git a/fetch-pack.h b/fetch-pack.h index 6d0dec7f41..5a428f11ed 100644 --- a/fetch-pack.h +++ b/fetch-pack.h @@ -16,6 +16,7 @@ struct fetch_pack_args { const struct string_list *deepen_not; struct list_objects_filter_options filter_options; const struct string_list *server_options; + struct object_info *object_info_data; /* * If not NULL, during packfile negotiation, fetch-pack will send "have" @@ -43,6 +44,7 @@ struct fetch_pack_args { unsigned reject_shallow_remote:1; unsigned deepen:1; unsigned refetch:1; + unsigned object_info:1; /* * Indicate that the remote of this request is a promisor remote. The diff --git a/meson.build b/meson.build index 064fe2e2f1..7b7dec5949 100644 --- a/meson.build +++ b/meson.build @@ -347,6 +347,7 @@ libgit_sources = [ 'exec-cmd.c', 'fetch-negotiator.c', 'fetch-pack.c', + 'fetch-object-info.c', 'fmt-merge-msg.c', 'fsck.c', 'fsmonitor.c', diff --git a/transport-helper.c b/transport-helper.c index 20a6ea8f81..4adb73bfbc 100644 --- a/transport-helper.c +++ b/transport-helper.c @@ -727,8 +727,8 @@ static int fetch_refs(struct transport *transport, /* * If we reach here, then the server, the client, and/or the transport - * helper does not support protocol v2. --negotiate-only requires - * protocol v2. + * helper does not support protocol v2. --negotiate-only and cat-file + * remote-object-info require protocol v2. */ if (data->transport_options.acked_commits) { warning(_("--negotiate-only requires protocol v2")); @@ -744,6 +744,13 @@ static int fetch_refs(struct transport *transport, free_refs(dummy); } + /* fail the command explicitly to avoid further commands input. */ + if (transport->smart_options->object_info) + die(_("remote-object-info requires protocol v2")); + + if (!data->get_refs_list_called) + get_refs_list_using_list(transport, 0); + count = 0; for (i = 0; i < nr_heads; i++) if (!(to_fetch[i]->status & REF_STATUS_UPTODATE)) diff --git a/transport.c b/transport.c index 0f5ec30247..7d3246e12b 100644 --- a/transport.c +++ b/transport.c @@ -9,6 +9,7 @@ #include "hook.h" #include "pkt-line.h" #include "fetch-pack.h" +#include "fetch-object-info.h" #include "remote.h" #include "connect.h" #include "send-pack.h" @@ -467,8 +468,33 @@ static int fetch_refs_via_pack(struct transport *transport, args.negotiation_restrict_tips = data->options.negotiation_restrict_tips; args.negotiation_include_tips = data->options.negotiation_include_tips; args.reject_shallow_remote = transport->smart_options->reject_shallow; + args.object_info = transport->smart_options->object_info; - if (!data->finished_handshake) { + if (transport->smart_options->object_info + && transport->smart_options->object_info_oids->nr > 0) { + struct packet_reader reader; + struct object_info_args obj_info_args = { 0 }; + + obj_info_args.server_options = transport->server_options; + obj_info_args.oids = transport->smart_options->object_info_oids; + obj_info_args.object_info_options = transport->smart_options->object_info_options; + string_list_sort(obj_info_args.object_info_options); + + connect_setup(transport, 0); + packet_reader_init(&reader, data->fd[0], NULL, 0, + PACKET_READ_CHOMP_NEWLINE | + PACKET_READ_GENTLE_ON_EOF | + PACKET_READ_DIE_ON_ERR_PACKET); + + data->version = discover_version(&reader); + transport->hash_algo = reader.hash_algo; + + ret = fetch_object_info(data->version, &obj_info_args, &reader, + data->options.object_info_data, transport->stateless_rpc, + data->fd[1]); + goto cleanup; + + } else if (!data->finished_handshake) { int i; int must_list_refs = 0; for (i = 0; i < nr_heads; i++) { diff --git a/transport.h b/transport.h index 7e5867cffa..bd60b10af4 100644 --- a/transport.h +++ b/transport.h @@ -6,6 +6,7 @@ #include "list-objects-filter-options.h" #include "string-list.h" #include "connect.h" +#include "odb.h" struct git_transport_options { unsigned thin : 1; @@ -31,6 +32,12 @@ struct git_transport_options { */ unsigned connectivity_checked:1; + /* + * Transport will attempt to retrieve only object-info. + * If object-info is not supported, the operation will error and exit. + */ + unsigned object_info : 1; + int depth; const char *deepen_since; const struct string_list *deepen_not; @@ -55,6 +62,10 @@ struct git_transport_options { * common commits to this oidset instead of fetching any packfiles. */ struct oidset *acked_commits; + + struct oid_array *object_info_oids; + struct object_info *object_info_data; + struct string_list *object_info_options; }; enum transport_family { From 82b4ab8001daf191c392bfa0cafff793f30740e1 Mon Sep 17 00:00:00 2001 From: Eric Ju Date: Mon, 8 Jun 2026 12:14:33 +0200 Subject: [PATCH 10/12] cat-file: add remote-object-info to batch-command Since the `info` command in `cat-file --batch-command` prints object info for a given object, it is natural to add another command in `cat-file --batch-command` to print object info for a given object from a remote. Add `remote-object-info` to `cat-file --batch-command`. While `info` takes object ids one at a time, this creates overhead when making requests to a server. So `remote-object-info` instead can take multiple object ids at once. The `cat-file --batch-command` command is generally implemented in the following manner: - Receive and parse input from user - Call respective function attached to command - Get object info, print object info In --buffer mode, this changes to: - Receive and parse input from user - Store respective function attached to command in a queue - After flush, loop through commands in queue - Call respective function attached to command - Get object info, print object info Notice how the getting and printing of object info is accomplished one at a time. As described above, this creates a problem for making requests to a server. Therefore, `remote-object-info` is implemented in the following manner: - Receive and parse input from user If command is `remote-object-info`: - Get object info from remote - Loop through and print each object info Else: - Call respective function attached to command - Parse input, get object info, print object info And finally for --buffer mode `remote-object-info`: - Receive and parse input from user - Store respective function attached to command in a queue - After flush, loop through commands in queue: If command is `remote-object-info`: - Get object info from remote - Loop through and print each object info Else: - Call respective function attached to command - Get object info, print object info To summarize, `remote-object-info` gets object info from the remote and then loops through the object info passed in, printing the info. In order for `remote-object-info` to avoid remote communication overhead in the non-buffer mode, the objects are passed in as such: remote-object-info ... rather than remote-object-info remote-object-info ... remote-object-info Helped-by: Jonathan Tan Helped-by: Christian Couder Signed-off-by: Calvin Wan Signed-off-by: Eric Ju Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- Documentation/git-cat-file.adoc | 24 +- builtin/cat-file.c | 128 ++++- object-file.c | 10 + odb.h | 3 + t/meson.build | 1 + t/t1017-cat-file-remote-object-info.sh | 664 +++++++++++++++++++++++++ transport.c | 4 +- 7 files changed, 827 insertions(+), 7 deletions(-) create mode 100755 t/t1017-cat-file-remote-object-info.sh diff --git a/Documentation/git-cat-file.adoc b/Documentation/git-cat-file.adoc index 86b9181599..aba20eb770 100644 --- a/Documentation/git-cat-file.adoc +++ b/Documentation/git-cat-file.adoc @@ -169,6 +169,13 @@ info :: Print object info for object reference ``. This corresponds to the output of `--batch-check`. +remote-object-info ...:: + Print object info for object references `` at specified + `` without downloading objects from the remote. + Raise an error when the `object-info` capability is not supported by the remote. + Raise an error when no object references are provided. + This command may be combined with `--buffer`. + flush:: Used with `--buffer` to execute all preceding commands that were issued since the beginning or since the last flush was issued. When `--buffer` @@ -312,7 +319,8 @@ newline. The available atoms are: The full hex representation of the object name. `objecttype`:: - The type of the object (the same as `cat-file -t` reports). + The type of the object (the same as `cat-file -t` reports). See + `CAVEATS` below. Not supported by `remote-object-info`. `objectmode`:: If the specified object has mode information (such as a tree or @@ -325,13 +333,14 @@ newline. The available atoms are: `objectsize:disk`:: The size, in bytes, that the object takes up on disk. See the - note about on-disk sizes in the `CAVEATS` section below. + note about on-disk sizes in the `CAVEATS` section below. Not + supported by `remote-object-info`. `deltabase`:: If the object is stored as a delta on-disk, this expands to the full hex representation of the delta base object name. Otherwise, expands to the null OID (all zeroes). See `CAVEATS` - below. + below. Not supported by `remote-object-info`. `rest`:: If this atom is used in the output string, input lines are split @@ -341,7 +350,10 @@ newline. The available atoms are: line) are output in place of the `%(rest)` atom. If no format is specified, the default format is `%(objectname) -%(objecttype) %(objectsize)`. +%(objecttype) %(objectsize)`, except for `remote-object-info` commands which use +`%(objectname) %(objectsize)` for now because "%(objecttype)" is not supported yet. +WARNING: When "%(objecttype)" is supported, the default format WILL be unified, so +DO NOT RELY on the current default format to stay the same!!! If `--batch` is specified, or if `--batch-command` is used with the `contents` command, the object information is followed by the object contents (consisting @@ -438,6 +450,10 @@ scripting purposes. CAVEATS ------- +Note that since %(objecttype), %(objectsize:disk) and %(deltabase) are +currently not supported by the `remote-object-info` command, we will raise +an error and exit when they appear in the format string. + Note that the sizes of objects on disk are reported accurately, but care should be taken in drawing conclusions about which refs or objects are responsible for disk usage. The size of a packed non-delta object may be diff --git a/builtin/cat-file.c b/builtin/cat-file.c index c060fd4800..a14cfea815 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -29,6 +29,22 @@ #include "promisor-remote.h" #include "mailmap.h" #include "write-or-die.h" +#include "alias.h" +#include "remote.h" +#include "transport.h" + +/* + * Maximum length for a remote URL. While no universal standard exists, + * 8K is assumed to be a reasonable limit. + */ +#define MAX_REMOTE_URL_LEN (8 * 1024) + +/* Maximum number of objects allowed in a single remote-object-info request. */ +#define MAX_ALLOWED_OBJ_LIMIT 10000 + +/* Maximum input size permitted for the remote-object-info command. */ +#define MAX_REMOTE_OBJ_INFO_LINE \ + (MAX_REMOTE_URL_LEN + MAX_ALLOWED_OBJ_LIMIT * (GIT_MAX_HEXSZ + 1)) enum batch_mode { BATCH_MODE_CONTENTS, @@ -639,6 +655,67 @@ out: object_context_release(&ctx); } +static int get_remote_info(struct batch_options *opt, + int argc, + const char **argv, + struct object_info **remote_object_info, + struct oid_array *object_info_oids) +{ + int retval = 0; + struct remote *remote = NULL; + struct object_id oid; + struct string_list object_info_options = STRING_LIST_INIT_NODUP; + static struct transport *gtransport; + + /* + * Change the format to "%(objectname) %(objectsize)" when + * remote-object-info command is used. Once we start supporting objecttype + * the default format should change to DEFAULT_FORMAT. + */ + if (!opt->format) + opt->format = "%(objectname) %(objectsize)"; + + remote = remote_get(argv[0]); + if (!remote) + die(_("must supply valid remote when using remote-object-info")); + + oid_array_clear(object_info_oids); + for (int i = 1; i < argc; i++) { + if (get_oid_hex(argv[i], &oid)) + die(_("Not a valid object name %s"), argv[i]); + oid_array_append(object_info_oids, &oid); + } + if (!object_info_oids->nr) + die(_("remote-object-info requires objects")); + + gtransport = transport_get(remote, NULL); + + if (!gtransport->smart_options) { + retval = -1; + goto cleanup; + } + + CALLOC_ARRAY(*remote_object_info, object_info_oids->nr); + gtransport->smart_options->object_info = 1; + gtransport->smart_options->object_info_oids = object_info_oids; + + /* 'objectsize' is the only option currently supported */ + if (!strstr(opt->format, "%(objectsize)")) + die(_("%s is currently not supported with remote-object-info"), opt->format); + + string_list_append(&object_info_options, "size"); + + if (object_info_options.nr > 0) { + gtransport->smart_options->object_info_options = &object_info_options; + gtransport->smart_options->object_info_data = *remote_object_info; + retval = transport_fetch_refs(gtransport, NULL); + } +cleanup: + string_list_clear(&object_info_options, 0); + transport_disconnect(gtransport); + return retval; +} + struct object_cb_data { struct batch_options *opt; struct expand_data *expand; @@ -720,6 +797,54 @@ static void parse_cmd_mailmap(struct batch_options *opt UNUSED, load_mailmap(); } +static void parse_cmd_remote_object_info(struct batch_options *opt, + const char *line, struct strbuf *output, + struct expand_data *data) +{ + int count; + const char **argv; + char *line_to_split; + static struct object_info *remote_object_info; + static struct oid_array object_info_oids = OID_ARRAY_INIT; + + if (strlen(line) >= MAX_REMOTE_OBJ_INFO_LINE) + die(_("remote-object-info command too long")); + + line_to_split = xstrdup(line); + count = split_cmdline(line_to_split, &argv); + if (count < 0) + die(_("split remote-object-info command")); + if (count - 1 > MAX_ALLOWED_OBJ_LIMIT) + die(_("remote-object-info supports at most %d objects"), + MAX_ALLOWED_OBJ_LIMIT); + + if (get_remote_info(opt, count, argv, &remote_object_info, + &object_info_oids)) + goto cleanup; + + data->skip_object_info = 1; + for (size_t i = 0; i < object_info_oids.nr; i++) { + data->oid = object_info_oids.oid[i]; + if (remote_object_info[i].sizep) { + /* + * When reaching here, it means remote-object-info can retrieve + * information from server without downloading them. + */ + data->size = *remote_object_info[i].sizep; + opt->batch_mode = BATCH_MODE_INFO; + batch_object_write(argv[i + 1], output, opt, data, NULL, 0); + } + } + data->skip_object_info = 0; + +cleanup: + for (size_t i = 0; i < object_info_oids.nr; i++) + free_object_info_contents(&remote_object_info[i]); + free(line_to_split); + free(argv); + free(remote_object_info); +} + static void dispatch_calls(struct batch_options *opt, struct strbuf *output, struct expand_data *data, @@ -751,8 +876,9 @@ static const struct parse_cmd { } commands[] = { { "contents", parse_cmd_contents, 1 }, { "info", parse_cmd_info, 1 }, - { "flush", NULL, 0 }, { "mailmap", parse_cmd_mailmap, 1 }, + { "remote-object-info", parse_cmd_remote_object_info, 1 }, + { "flush", NULL, 0 }, }; static void batch_objects_command(struct batch_options *opt, diff --git a/object-file.c b/object-file.c index 90f995d000..9608607847 100644 --- a/object-file.c +++ b/object-file.c @@ -2356,3 +2356,13 @@ error: free(st); return -1; } + +void free_object_info_contents(struct object_info *object_info) +{ + if (!object_info) + return; + free(object_info->typep); + free(object_info->sizep); + free(object_info->disk_sizep); + free(object_info->delta_base_oid); +} diff --git a/odb.h b/odb.h index 73553ed5a7..6d643c5cf3 100644 --- a/odb.h +++ b/odb.h @@ -573,4 +573,7 @@ void parse_alternates(const char *string, const char *relative_base, struct strvec *out); +/* Free pointers inside of object_info, but not object_info itself */ +void free_object_info_contents(struct object_info *object_info); + #endif /* ODB_H */ diff --git a/t/meson.build b/t/meson.build index 2af8d01279..3473e477bd 100644 --- a/t/meson.build +++ b/t/meson.build @@ -170,6 +170,7 @@ integration_tests = [ 't1014-read-tree-confusing.sh', 't1015-read-index-unmerged.sh', 't1016-compatObjectFormat.sh', + 't1017-cat-file-remote-object-info.sh', 't1020-subdirectory.sh', 't1022-read-tree-partial-clone.sh', 't1050-large.sh', diff --git a/t/t1017-cat-file-remote-object-info.sh b/t/t1017-cat-file-remote-object-info.sh new file mode 100755 index 0000000000..5c8c07b0cf --- /dev/null +++ b/t/t1017-cat-file-remote-object-info.sh @@ -0,0 +1,664 @@ +#!/bin/sh + +test_description='git cat-file --batch-command with remote-object-info command' + +GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main +export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME + +. ./test-lib.sh +. "$TEST_DIRECTORY"/lib-cat-file.sh + +hello_content="Hello World" +hello_size=$(strlen "$hello_content") +hello_oid=$(echo_without_newline "$hello_content" | git hash-object --stdin) + +# This is how we get 13: +# 13 = + + + , where +# file mode is 100644, which is 6 characters; +# file name is hello, which is 5 characters +# a space is 1 character and a null is 1 character +tree_size=$(($(test_oid rawsz) + 13)) + +commit_message="Initial commit" + +# This is how we get 137: +# 137 = + + + +# + + +# + + +# + +# +# An easier way to calculate is: 1. use `git cat-file commit | wc -c`, +# to get 177, 2. then deduct 40 hex characters to get 137 +commit_size=$(($(test_oid hexsz) + 137)) + +tag_header_without_oid="type blob +tag hellotag +tagger $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL>" +tag_header_without_timestamp="object $hello_oid +$tag_header_without_oid" +tag_description="This is a tag" +tag_content="$tag_header_without_timestamp 0 +0000 + +$tag_description" + +tag_oid=$(echo_without_newline "$tag_content" | git hash-object -t tag --stdin -w) +tag_size=$(strlen "$tag_content") + +set_transport_variables () { + hello_oid=$(echo_without_newline "$hello_content" | git hash-object --stdin) + tree_oid=$(git -C "$1" write-tree) + commit_oid=$(echo_without_newline "$commit_message" | git -C "$1" commit-tree $tree_oid) + tag_oid=$(echo_without_newline "$tag_content" | git -C "$1" hash-object -t tag --stdin -w) + tag_size=$(strlen "$tag_content") +} + +# This section tests --batch-command with remote-object-info command +# Since "%(objecttype)" is currently not supported by the command remote-object-info , +# the filters are set to "%(objectname) %(objectsize)" in some test cases. + +# Test --batch-command remote-object-info with 'git://' transport with +# transfer.advertiseobjectinfo set to true, i.e. server has object-info capability +. "$TEST_DIRECTORY"/lib-git-daemon.sh +start_git_daemon --export-all --enable=receive-pack +daemon_parent=$GIT_DAEMON_DOCUMENT_ROOT_PATH/parent + +test_expect_success 'create repo to be served by git-daemon' ' + git init "$daemon_parent" && + echo_without_newline "$hello_content" > $daemon_parent/hello && + git -C "$daemon_parent" update-index --add hello && + git -C "$daemon_parent" config transfer.advertiseobjectinfo true && + git clone "$GIT_DAEMON_URL/parent" -n "$daemon_parent/daemon_client_empty" +' + +test_expect_success 'batch-command remote-object-info git://' ' + ( + set_transport_variables "$daemon_parent" && + cd "$daemon_parent/daemon_client_empty" && + + # These results prove remote-object-info can get object info from the remote + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + + # These results prove remote-object-info did not download objects from the remote + echo "$hello_oid missing" >>expect && + echo "$tree_oid missing" >>expect && + echo "$commit_oid missing" >>expect && + echo "$tag_oid missing" >>expect && + + git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF && + remote-object-info "$GIT_DAEMON_URL/parent" $hello_oid + remote-object-info "$GIT_DAEMON_URL/parent" $tree_oid + remote-object-info "$GIT_DAEMON_URL/parent" $commit_oid + remote-object-info "$GIT_DAEMON_URL/parent" $tag_oid + info $hello_oid + info $tree_oid + info $commit_oid + info $tag_oid + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command remote-object-info git:// multiple sha1 per line' ' + ( + set_transport_variables "$daemon_parent" && + cd "$daemon_parent/daemon_client_empty" && + + # These results prove remote-object-info can get object info from the remote + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + + # These results prove remote-object-info did not download objects from the remote + echo "$hello_oid missing" >>expect && + echo "$tree_oid missing" >>expect && + echo "$commit_oid missing" >>expect && + echo "$tag_oid missing" >>expect && + + git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF && + remote-object-info "$GIT_DAEMON_URL/parent" $hello_oid $tree_oid $commit_oid $tag_oid + info $hello_oid + info $tree_oid + info $commit_oid + info $tag_oid + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command remote-object-info git:// default filter' ' + ( + set_transport_variables "$daemon_parent" && + cd "$daemon_parent/daemon_client_empty" && + + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + GIT_TRACE_PACKET=1 git cat-file --batch-command >actual <<-EOF && + remote-object-info "$GIT_DAEMON_URL/parent" $hello_oid $tree_oid + remote-object-info "$GIT_DAEMON_URL/parent" $commit_oid $tag_oid + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command --buffer remote-object-info git://' ' + ( + set_transport_variables "$daemon_parent" && + cd "$daemon_parent/daemon_client_empty" && + + # These results prove remote-object-info can get object info from the remote + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + + # These results prove remote-object-info did not download objects from the remote + echo "$hello_oid missing" >>expect && + echo "$tree_oid missing" >>expect && + echo "$commit_oid missing" >>expect && + echo "$tag_oid missing" >>expect && + + git cat-file --batch-command="%(objectname) %(objectsize)" --buffer >actual <<-EOF && + remote-object-info "$GIT_DAEMON_URL/parent" $hello_oid $tree_oid + remote-object-info "$GIT_DAEMON_URL/parent" $commit_oid $tag_oid + info $hello_oid + info $tree_oid + info $commit_oid + info $tag_oid + flush + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command -Z remote-object-info git:// default filter' ' + ( + set_transport_variables "$daemon_parent" && + cd "$daemon_parent/daemon_client_empty" && + + printf "%s\0" "$hello_oid $hello_size" >expect && + printf "%s\0" "$tree_oid $tree_size" >>expect && + printf "%s\0" "$commit_oid $commit_size" >>expect && + printf "%s\0" "$tag_oid $tag_size" >>expect && + + printf "%s\0" "$hello_oid missing" >>expect && + printf "%s\0" "$tree_oid missing" >>expect && + printf "%s\0" "$commit_oid missing" >>expect && + printf "%s\0" "$tag_oid missing" >>expect && + + batch_input="remote-object-info $GIT_DAEMON_URL/parent $hello_oid $tree_oid +remote-object-info $GIT_DAEMON_URL/parent $commit_oid $tag_oid +info $hello_oid +info $tree_oid +info $commit_oid +info $tag_oid +" && + echo_without_newline_nul "$batch_input" >commands_null_delimited && + + git cat-file --batch-command -Z < commands_null_delimited >actual && + test_cmp expect actual + ) +' + +# Test --batch-command remote-object-info with 'git://' and +# transfer.advertiseobjectinfo set to false, i.e. server does not have object-info capability +test_expect_success 'batch-command remote-object-info git:// fails when transfer.advertiseobjectinfo=false' ' + ( + git -C "$daemon_parent" config transfer.advertiseobjectinfo false && + set_transport_variables "$daemon_parent" && + + test_must_fail git cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF && + remote-object-info $GIT_DAEMON_URL/parent $hello_oid $tree_oid $commit_oid $tag_oid + EOF + test_grep "object-info capability is not enabled on the server" err && + + # revert server state back + git -C "$daemon_parent" config transfer.advertiseobjectinfo true + + ) +' + +stop_git_daemon + +# Test --batch-command remote-object-info with 'file://' transport with +# transfer.advertiseobjectinfo set to true, i.e. server has object-info capability +# shellcheck disable=SC2016 +test_expect_success 'create repo to be served by file:// transport' ' + git init server && + git -C server config protocol.version 2 && + git -C server config transfer.advertiseobjectinfo true && + echo_without_newline "$hello_content" > server/hello && + git -C server update-index --add hello && + git clone -n "file://$(pwd)/server" file_client_empty +' + +test_expect_success 'batch-command remote-object-info file://' ' + ( + set_transport_variables "server" && + server_path="$(pwd)/server" && + cd file_client_empty && + + # These results prove remote-object-info can get object info from the remote + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + + # These results prove remote-object-info did not download objects from the remote + echo "$hello_oid missing" >>expect && + echo "$tree_oid missing" >>expect && + echo "$commit_oid missing" >>expect && + echo "$tag_oid missing" >>expect && + + git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF && + remote-object-info "file://${server_path}" $hello_oid + remote-object-info "file://${server_path}" $tree_oid + remote-object-info "file://${server_path}" $commit_oid + remote-object-info "file://${server_path}" $tag_oid + info $hello_oid + info $tree_oid + info $commit_oid + info $tag_oid + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command remote-object-info file:// multiple sha1 per line' ' + ( + set_transport_variables "server" && + server_path="$(pwd)/server" && + cd file_client_empty && + + # These results prove remote-object-info can get object info from the remote + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + + # These results prove remote-object-info did not download objects from the remote + echo "$hello_oid missing" >>expect && + echo "$tree_oid missing" >>expect && + echo "$commit_oid missing" >>expect && + echo "$tag_oid missing" >>expect && + + + git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF && + remote-object-info "file://${server_path}" $hello_oid $tree_oid $commit_oid $tag_oid + info $hello_oid + info $tree_oid + info $commit_oid + info $tag_oid + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command --buffer remote-object-info file://' ' + ( + set_transport_variables "server" && + server_path="$(pwd)/server" && + cd file_client_empty && + + # These results prove remote-object-info can get object info from the remote + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + + # These results prove remote-object-info did not download objects from the remote + echo "$hello_oid missing" >>expect && + echo "$tree_oid missing" >>expect && + echo "$commit_oid missing" >>expect && + echo "$tag_oid missing" >>expect && + + git cat-file --batch-command="%(objectname) %(objectsize)" --buffer >actual <<-EOF && + remote-object-info "file://${server_path}" $hello_oid $tree_oid + remote-object-info "file://${server_path}" $commit_oid $tag_oid + info $hello_oid + info $tree_oid + info $commit_oid + info $tag_oid + flush + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command remote-object-info file:// default filter' ' + ( + set_transport_variables "server" && + server_path="$(pwd)/server" && + cd file_client_empty && + + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + + git cat-file --batch-command >actual <<-EOF && + remote-object-info "file://${server_path}" $hello_oid $tree_oid + remote-object-info "file://${server_path}" $commit_oid $tag_oid + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command -Z remote-object-info file:// default filter' ' + ( + set_transport_variables "server" && + server_path="$(pwd)/server" && + cd file_client_empty && + + printf "%s\0" "$hello_oid $hello_size" >expect && + printf "%s\0" "$tree_oid $tree_size" >>expect && + printf "%s\0" "$commit_oid $commit_size" >>expect && + printf "%s\0" "$tag_oid $tag_size" >>expect && + + printf "%s\0" "$hello_oid missing" >>expect && + printf "%s\0" "$tree_oid missing" >>expect && + printf "%s\0" "$commit_oid missing" >>expect && + printf "%s\0" "$tag_oid missing" >>expect && + + batch_input="remote-object-info \"file://${server_path}\" $hello_oid $tree_oid +remote-object-info \"file://${server_path}\" $commit_oid $tag_oid +info $hello_oid +info $tree_oid +info $commit_oid +info $tag_oid +" && + echo_without_newline_nul "$batch_input" >commands_null_delimited && + + git cat-file --batch-command -Z < commands_null_delimited >actual && + test_cmp expect actual + ) +' + +# Test --batch-command remote-object-info with 'file://' and +# transfer.advertiseobjectinfo set to false, i.e. server does not have object-info capability +test_expect_success 'batch-command remote-object-info file:// fails when transfer.advertiseobjectinfo=false' ' + ( + set_transport_variables "server" && + server_path="$(pwd)/server" && + git -C "${server_path}" config transfer.advertiseobjectinfo false && + + test_must_fail git cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF && + remote-object-info "file://${server_path}" $hello_oid $tree_oid $commit_oid $tag_oid + EOF + test_grep "object-info capability is not enabled on the server" err && + + # revert server state back + git -C "${server_path}" config transfer.advertiseobjectinfo true + ) +' + +# Test --batch-command remote-object-info with 'http://' transport with +# transfer.advertiseobjectinfo set to true, i.e. server has object-info capability + +. "$TEST_DIRECTORY"/lib-httpd.sh +start_httpd + +test_expect_success 'create repo to be served by http:// transport' ' + git init "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" config http.receivepack true && + git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" config transfer.advertiseobjectinfo true && + echo_without_newline "$hello_content" > $HTTPD_DOCUMENT_ROOT_PATH/http_parent/hello && + git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" update-index --add hello && + git clone "$HTTPD_URL/smart/http_parent" -n "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty" +' + +test_expect_success 'batch-command remote-object-info http://' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty" && + + # These results prove remote-object-info can get object info from the remote + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + + # These results prove remote-object-info did not download objects from the remote + echo "$hello_oid missing" >>expect && + echo "$tree_oid missing" >>expect && + echo "$commit_oid missing" >>expect && + echo "$tag_oid missing" >>expect && + + git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid + remote-object-info "$HTTPD_URL/smart/http_parent" $tree_oid + remote-object-info "$HTTPD_URL/smart/http_parent" $commit_oid + remote-object-info "$HTTPD_URL/smart/http_parent" $tag_oid + info $hello_oid + info $tree_oid + info $commit_oid + info $tag_oid + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command remote-object-info http:// one line' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty" && + + # These results prove remote-object-info can get object info from the remote + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + + # These results prove remote-object-info did not download objects from the remote + echo "$hello_oid missing" >>expect && + echo "$tree_oid missing" >>expect && + echo "$commit_oid missing" >>expect && + echo "$tag_oid missing" >>expect && + + git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid $tree_oid $commit_oid $tag_oid + info $hello_oid + info $tree_oid + info $commit_oid + info $tag_oid + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command --buffer remote-object-info http://' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty" && + + # These results prove remote-object-info can get object info from the remote + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + + # These results prove remote-object-info did not download objects from the remote + echo "$hello_oid missing" >>expect && + echo "$tree_oid missing" >>expect && + echo "$commit_oid missing" >>expect && + echo "$tag_oid missing" >>expect && + + git cat-file --batch-command="%(objectname) %(objectsize)" --buffer >actual <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid $tree_oid + remote-object-info "$HTTPD_URL/smart/http_parent" $commit_oid $tag_oid + info $hello_oid + info $tree_oid + info $commit_oid + info $tag_oid + flush + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command remote-object-info http:// default filter' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty" && + + echo "$hello_oid $hello_size" >expect && + echo "$tree_oid $tree_size" >>expect && + echo "$commit_oid $commit_size" >>expect && + echo "$tag_oid $tag_size" >>expect && + + git cat-file --batch-command >actual <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid $tree_oid + remote-object-info "$HTTPD_URL/smart/http_parent" $commit_oid $tag_oid + EOF + test_cmp expect actual + ) +' + +test_expect_success 'batch-command -Z remote-object-info http:// default filter' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty" && + + printf "%s\0" "$hello_oid $hello_size" >expect && + printf "%s\0" "$tree_oid $tree_size" >>expect && + printf "%s\0" "$commit_oid $commit_size" >>expect && + printf "%s\0" "$tag_oid $tag_size" >>expect && + + batch_input="remote-object-info $HTTPD_URL/smart/http_parent $hello_oid $tree_oid +remote-object-info $HTTPD_URL/smart/http_parent $commit_oid $tag_oid +" && + echo_without_newline_nul "$batch_input" >commands_null_delimited && + + git cat-file --batch-command -Z < commands_null_delimited >actual && + test_cmp expect actual + ) +' + +test_expect_success 'remote-object-info fails on unspported filter option (objectsize:disk)' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + + test_must_fail git cat-file --batch-command="%(objectsize:disk)" 2>err <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid + EOF + test_grep "%(objectsize:disk) is currently not supported with remote-object-info" err + ) +' + +test_expect_success 'remote-object-info fails on unspported filter option (deltabase)' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + + test_must_fail git cat-file --batch-command="%(deltabase)" 2>err <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid + EOF + test_grep "%(deltabase) is currently not supported with remote-object-info" err + ) +' + +test_expect_success 'remote-object-info fails on server with legacy protocol' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + + test_must_fail git -c protocol.version=0 cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid + EOF + test_grep "remote-object-info requires protocol v2" err + ) +' + +test_expect_success 'remote-object-info fails on server with legacy protocol with default filter' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + + test_must_fail git -c protocol.version=0 cat-file --batch-command 2>err <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid + EOF + test_grep "remote-object-info requires protocol v2" err + ) +' + +test_expect_success 'remote-object-info fails on malformed OID' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + malformed_object_id="this_id_is_not_valid" && + + test_must_fail git cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $malformed_object_id + EOF + test_grep "Not a valid object name '$malformed_object_id'" err + ) +' + +test_expect_success 'remote-object-info fails on malformed OID with default filter' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + malformed_object_id="this_id_is_not_valid" && + + test_must_fail git cat-file --batch-command 2>err <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $malformed_object_id + EOF + test_grep "Not a valid object name '$malformed_object_id'" err + ) +' + +test_expect_success 'remote-object-info fails on missing OID' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + git clone "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" missing_oid_repo && + test_commit -C missing_oid_repo message1 c.txt && + cd missing_oid_repo && + + object_id=$(git rev-parse message1:c.txt) && + test_must_fail git cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $object_id + EOF + test_grep "object-info: server does not recognize object $object_id" err + ) +' + +test_expect_success 'remote-object-info fails on not providing OID' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + + test_must_fail git cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" + EOF + test_grep "remote-object-info requires objects" err + ) +' + + +# Test --batch-command remote-object-info with 'http://' transport and +# transfer.advertiseobjectinfo set to false, i.e. server does not have object-info capability +test_expect_success 'batch-command remote-object-info http:// fails when transfer.advertiseobjectinfo=false ' ' + ( + set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && + git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" config transfer.advertiseobjectinfo false && + + test_must_fail git cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF && + remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid $tree_oid $commit_oid $tag_oid + EOF + test_grep "object-info capability is not enabled on the server" err && + + # revert server state back + git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" config transfer.advertiseobjectinfo true + ) +' + +# DO NOT add non-httpd-specific tests here, because the last part of this +# test script is only executed when httpd is available and enabled. + +test_done diff --git a/transport.c b/transport.c index 7d3246e12b..81faf8e748 100644 --- a/transport.c +++ b/transport.c @@ -470,8 +470,8 @@ static int fetch_refs_via_pack(struct transport *transport, args.reject_shallow_remote = transport->smart_options->reject_shallow; args.object_info = transport->smart_options->object_info; - if (transport->smart_options->object_info - && transport->smart_options->object_info_oids->nr > 0) { + if (transport->smart_options->object_info && + transport->smart_options->object_info_oids->nr > 0) { struct packet_reader reader; struct object_info_args obj_info_args = { 0 }; From 5b591f977f215abae538eee15daf7fa70c62ce81 Mon Sep 17 00:00:00 2001 From: Pablo Sabater Date: Mon, 8 Jun 2026 12:14:34 +0200 Subject: [PATCH 11/12] cat-file: validate remote atoms with allow_list strstr() is not enough to validate the format placeholders in remote-object-info causing two errors: - Atoms recognized by expand_atom() but the remote doesn't returns 1, but data->type contains garbage causing segfault. - expand_atom() returns 0 for unknown atoms, calling strbuf_expand_bad_format() which ends in die() blocking local queries if the same format is shared. Add an allow_list with the supported atoms at the top of expand_atom(). In remote mode, unsupported atoms return 1 leaving the sb empty, honoring how for-each-ref handles known but inapplicable atoms. As extra safety, initialize data->type to OBJ_BAD and add a NULL check for type_name() so uninitialized data doesn't cause segfault. Update tests that expect previous die() behaviour to expect an empty string and add an explicit test for empty string return on unknown placeholder. Update caveat behaviour documentation. Mentored-by: Karthik Nayak Mentored-by: Chandra Pratap Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- Documentation/git-cat-file.adoc | 5 ++-- builtin/cat-file.c | 41 +++++++++++++++++++++----- t/t1017-cat-file-remote-object-info.sh | 28 +++++++++++++++--- 3 files changed, 60 insertions(+), 14 deletions(-) diff --git a/Documentation/git-cat-file.adoc b/Documentation/git-cat-file.adoc index aba20eb770..3b7a85b383 100644 --- a/Documentation/git-cat-file.adoc +++ b/Documentation/git-cat-file.adoc @@ -451,8 +451,9 @@ CAVEATS ------- Note that since %(objecttype), %(objectsize:disk) and %(deltabase) are -currently not supported by the `remote-object-info` command, we will raise -an error and exit when they appear in the format string. +currently not supported by the `remote-object-info` command, they will +return an empty string for remote queries, matching how `for-each-ref` +behaves for known but inapplicable placeholders. Note that the sizes of objects on disk are reported accurately, but care should be taken in drawing conclusions about which refs or objects are diff --git a/builtin/cat-file.c b/builtin/cat-file.c index a14cfea815..1166a046b4 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -336,8 +336,18 @@ struct expand_data { * optimized out. */ unsigned skip_object_info : 1; + + /* + * Flags about when an object info is being fetched from remote. + */ + unsigned is_remote:1; +}; +#define EXPAND_DATA_INIT { .mode = S_IFINVALID, .type = OBJ_BAD } + +static const char *remote_object_info_atoms[] = { + "objectname", + "objectsize", }; -#define EXPAND_DATA_INIT { .mode = S_IFINVALID } static int is_atom(const char *atom, const char *s, int slen) { @@ -348,14 +358,31 @@ static int is_atom(const char *atom, const char *s, int slen) static int expand_atom(struct strbuf *sb, const char *atom, int len, struct expand_data *data) { + if (data->is_remote) { + size_t i, allowed_nr = ARRAY_SIZE(remote_object_info_atoms); + for (i = 0; i < allowed_nr; i++) + if (is_atom(remote_object_info_atoms[i], atom, len)) + break; + + /* + * On remote, skip unsupported atoms returning an empty sb, + * honoring how for-each-ref handles known but inapplicable + * atoms (e.g. %(tagger)). + */ + if (i == allowed_nr) + return 1; + } + if (is_atom("objectname", atom, len)) { if (!data->mark_query) strbuf_addstr(sb, oid_to_hex(&data->oid)); } else if (is_atom("objecttype", atom, len)) { - if (data->mark_query) + if (data->mark_query) { data->info.typep = &data->type; - else - strbuf_addstr(sb, type_name(data->type)); + } else { + const char *t = type_name(data->type); + strbuf_addstr(sb, t ? t : ""); + } } else if (is_atom("objectsize", atom, len)) { if (data->mark_query) data->info.sizep = &data->size; @@ -699,10 +726,6 @@ static int get_remote_info(struct batch_options *opt, gtransport->smart_options->object_info = 1; gtransport->smart_options->object_info_oids = object_info_oids; - /* 'objectsize' is the only option currently supported */ - if (!strstr(opt->format, "%(objectsize)")) - die(_("%s is currently not supported with remote-object-info"), opt->format); - string_list_append(&object_info_options, "size"); if (object_info_options.nr > 0) { @@ -832,7 +855,9 @@ static void parse_cmd_remote_object_info(struct batch_options *opt, */ data->size = *remote_object_info[i].sizep; opt->batch_mode = BATCH_MODE_INFO; + data->is_remote = 1; batch_object_write(argv[i + 1], output, opt, data, NULL, 0); + data->is_remote = 0; } } data->skip_object_info = 0; diff --git a/t/t1017-cat-file-remote-object-info.sh b/t/t1017-cat-file-remote-object-info.sh index 5c8c07b0cf..0a78aabf3b 100755 --- a/t/t1017-cat-file-remote-object-info.sh +++ b/t/t1017-cat-file-remote-object-info.sh @@ -205,6 +205,22 @@ info $tag_oid ) ' +# This tests depends on %(objecttype) not being supported yet, once supported +# it needs to be updated. +test_expect_success 'unsupported placeholder on remote returns empty string' ' + ( + set_transport_variables "$daemon_parent" && + cd "$daemon_parent/daemon_client_empty" && + + echo "" >expect && + + git cat-file --batch-command="%(objecttype)" >actual <<-EOF && + remote-object-info "$GIT_DAEMON_URL/parent" $hello_oid + EOF + test_cmp expect actual + ) +' + # Test --batch-command remote-object-info with 'git://' and # transfer.advertiseobjectinfo set to false, i.e. server does not have object-info capability test_expect_success 'batch-command remote-object-info git:// fails when transfer.advertiseobjectinfo=false' ' @@ -544,10 +560,12 @@ test_expect_success 'remote-object-info fails on unspported filter option (objec set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && - test_must_fail git cat-file --batch-command="%(objectsize:disk)" 2>err <<-EOF && + echo "$hello_oid " >expect && + + git cat-file --batch-command="%(objectname) %(objectsize:disk)" >actual <<-EOF && remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid EOF - test_grep "%(objectsize:disk) is currently not supported with remote-object-info" err + test_cmp expect actual ) ' @@ -556,10 +574,12 @@ test_expect_success 'remote-object-info fails on unspported filter option (delta set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" && - test_must_fail git cat-file --batch-command="%(deltabase)" 2>err <<-EOF && + echo "" >expect && + + git cat-file --batch-command="%(deltabase)" >actual <<-EOF && remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid EOF - test_grep "%(deltabase) is currently not supported with remote-object-info" err + test_cmp expect actual ) ' From 56f3100adb60b4b7b3f7e75164b826042d085151 Mon Sep 17 00:00:00 2001 From: Pablo Sabater Date: Mon, 8 Jun 2026 12:14:35 +0200 Subject: [PATCH 12/12] cat-file: make remote-object-info allow-list dynamic The static allow-list in expand_atom() is hardcoded to only allow "objectname" and "objectsize" for remote queries. This works because up to this point all servers will either support object-info with name and size or they do not support them at all, but we cannot expect that in a future different servers with different git versions to have the same object-info capabilities. Therefore, the allow_list needs to be dynamic depending on what does the server advertise. The client will now: 1. Request the protocol option that the placeholder refers to (i.e. "size" when "%(objectsize)"). 2. Filters the request in fetch_object_info() dropping any option that the server does not advertise. 3. After the fetching, the options that haven't been dropped are the ones fetched and supported by the server, these supported options are mapped and remote_allowed_atoms is populated with the placeholders. 4. expand_atom() checks remote_allowed_atoms with the same behaviour as the static allow_list had. Move object_info_options out of get_remote_info so the caller which has data can select what options will be requested instead of requesting always size. Move batch_object_write() out so there will always be an output even if all the placeholders are not supported by the server (returns an empty line). Include "type" in the object_info_options so once the server supports it, the clients know already how to request it. Mentored-by: Karthik Nayak Mentored-by: Chandra Pratap Signed-off-by: Pablo Sabater Signed-off-by: Junio C Hamano --- builtin/cat-file.c | 85 +++++++++++++++++++++++++++------------------ fetch-object-info.c | 6 ++++ 2 files changed, 58 insertions(+), 33 deletions(-) diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 1166a046b4..055991b5af 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -341,13 +341,10 @@ struct expand_data { * Flags about when an object info is being fetched from remote. */ unsigned is_remote:1; -}; -#define EXPAND_DATA_INIT { .mode = S_IFINVALID, .type = OBJ_BAD } -static const char *remote_object_info_atoms[] = { - "objectname", - "objectsize", + struct string_list remote_allowed_atoms; }; +#define EXPAND_DATA_INIT { .mode = S_IFINVALID, .type = OBJ_BAD, .remote_allowed_atoms = STRING_LIST_INIT_NODUP } static int is_atom(const char *atom, const char *s, int slen) { @@ -359,17 +356,11 @@ static int expand_atom(struct strbuf *sb, const char *atom, int len, struct expand_data *data) { if (data->is_remote) { - size_t i, allowed_nr = ARRAY_SIZE(remote_object_info_atoms); - for (i = 0; i < allowed_nr; i++) - if (is_atom(remote_object_info_atoms[i], atom, len)) + size_t i; + for (i = 0; i < data->remote_allowed_atoms.nr; i++) + if (is_atom(data->remote_allowed_atoms.items[i].string, atom, len)) break; - - /* - * On remote, skip unsupported atoms returning an empty sb, - * honoring how for-each-ref handles known but inapplicable - * atoms (e.g. %(tagger)). - */ - if (i == allowed_nr) + if (i == data->remote_allowed_atoms.nr) return 1; } @@ -686,12 +677,12 @@ static int get_remote_info(struct batch_options *opt, int argc, const char **argv, struct object_info **remote_object_info, - struct oid_array *object_info_oids) + struct oid_array *object_info_oids, + struct string_list *object_info_options) { int retval = 0; struct remote *remote = NULL; struct object_id oid; - struct string_list object_info_options = STRING_LIST_INIT_NODUP; static struct transport *gtransport; /* @@ -726,15 +717,12 @@ static int get_remote_info(struct batch_options *opt, gtransport->smart_options->object_info = 1; gtransport->smart_options->object_info_oids = object_info_oids; - string_list_append(&object_info_options, "size"); - - if (object_info_options.nr > 0) { - gtransport->smart_options->object_info_options = &object_info_options; + if (object_info_options->nr > 0) { + gtransport->smart_options->object_info_options = object_info_options; gtransport->smart_options->object_info_data = *remote_object_info; retval = transport_fetch_refs(gtransport, NULL); } cleanup: - string_list_clear(&object_info_options, 0); transport_disconnect(gtransport); return retval; } @@ -820,6 +808,21 @@ static void parse_cmd_mailmap(struct batch_options *opt UNUSED, load_mailmap(); } +struct protocol_placeholder_entry { + const char *option; + const char *atom; +}; + +static const struct protocol_placeholder_entry remote_atom_map[] = { + {"size", "objectsize"}, + {"type", "objecttype"}, + /* + * Add new protocol options here. Even if the server doesn't support + * them the allow_list will drop them if the server doesn't advertise + * them. + */ +}; + static void parse_cmd_remote_object_info(struct batch_options *opt, const char *line, struct strbuf *output, struct expand_data *data) @@ -829,6 +832,7 @@ static void parse_cmd_remote_object_info(struct batch_options *opt, char *line_to_split; static struct object_info *remote_object_info; static struct oid_array object_info_oids = OID_ARRAY_INIT; + struct string_list object_info_options = STRING_LIST_INIT_NODUP; if (strlen(line) >= MAX_REMOTE_OBJ_INFO_LINE) die(_("remote-object-info command too long")); @@ -841,30 +845,44 @@ static void parse_cmd_remote_object_info(struct batch_options *opt, die(_("remote-object-info supports at most %d objects"), MAX_ALLOWED_OBJ_LIMIT); + if (data->info.sizep) + string_list_append(&object_info_options, "size"); + if (data->info.typep) + string_list_append(&object_info_options, "type"); + if (get_remote_info(opt, count, argv, &remote_object_info, - &object_info_oids)) + &object_info_oids, &object_info_options)) goto cleanup; + string_list_clear(&data->remote_allowed_atoms, 0); + string_list_append(&data->remote_allowed_atoms, "objectname"); + for (size_t i = 0; i < ARRAY_SIZE(remote_atom_map); i++) + if (unsorted_string_list_has_string(&object_info_options, remote_atom_map[i].option)) + string_list_append(&data->remote_allowed_atoms, + remote_atom_map[i].atom); + data->skip_object_info = 1; for (size_t i = 0; i < object_info_oids.nr; i++) { data->oid = object_info_oids.oid[i]; - if (remote_object_info[i].sizep) { - /* - * When reaching here, it means remote-object-info can retrieve - * information from server without downloading them. - */ + /* + * When reaching here, it means remote-object-info can retrieve + * information from server without downloading them. + */ + if (remote_object_info[i].sizep) data->size = *remote_object_info[i].sizep; - opt->batch_mode = BATCH_MODE_INFO; - data->is_remote = 1; - batch_object_write(argv[i + 1], output, opt, data, NULL, 0); - data->is_remote = 0; - } + if (remote_object_info[i].typep) + data->type = *remote_object_info[i].typep; + opt->batch_mode = BATCH_MODE_INFO; + data->is_remote = 1; + batch_object_write(argv[i + 1], output, opt, data, NULL, 0); + data->is_remote = 0; } data->skip_object_info = 0; cleanup: for (size_t i = 0; i < object_info_oids.nr; i++) free_object_info_contents(&remote_object_info[i]); + string_list_clear(&object_info_options, 0); free(line_to_split); free(argv); free(remote_object_info); @@ -1177,6 +1195,7 @@ static int batch_objects(struct batch_options *opt) cleanup: strbuf_release(&input); strbuf_release(&output); + string_list_clear(&data.remote_allowed_atoms, 0); warn_on_object_refname_ambiguity = save_warning; return retval; } diff --git a/fetch-object-info.c b/fetch-object-info.c index 51a898430d..425929a269 100644 --- a/fetch-object-info.c +++ b/fetch-object-info.c @@ -39,6 +39,12 @@ int fetch_object_info(const enum protocol_version version, struct object_info_ar case protocol_v2: if (!server_supports_v2("object-info")) die(_("object-info capability is not enabled on the server")); + + for (int i = args->object_info_options->nr - 1; i >= 0; i--) + if (!server_supports_feature("object-info", + args->object_info_options->items[i].string, 0)) + unsorted_string_list_delete_item(args->object_info_options, i, 0); + send_object_info_request(fd_out, args); break; case protocol_v1: