@matheusbsbs / matheus-bagliano / commits / db9d67f2e9

builtin/cat-file.c: support NUL-delimited input with `-z`

When callers are using `cat-file` via one of the stdin-driven `--batch` modes, all input is newline-delimited. This presents a problem when callers wish to ask about, e.g. tree-entries that have a newline character present in their filename. To support this niche scenario, introduce a new `-z` mode to the `--batch`, `--batch-check`, and `--batch-command` suite of options that instructs `cat-file` to treat its input as NUL-delimited, allowing the individual commands themselves to have newlines present. The refactoring here is slightly unfortunate, since we turn loops like: while (strbuf_getline(&buf, stdin) != EOF) into: while (1) { int ret; if (opt->nul_terminated) ret = strbuf_getline_nul(&input, stdin); else ret = strbuf_getline(&input, stdin); if (ret == EOF) break; } It's tempting to think that we could use `strbuf_getwholeline()` and specify either `\n` or `\0` as the terminating character. But for input on platforms that include a CR character preceeding the LF, this wouldn't quite be the same, since `strbuf_getline(...)` will trim any trailing CR, while `strbuf_getwholeline(&buf, stdin, '\n')` will not. In the future, we could clean this up further by introducing a variant of `strbuf_getwholeline()` that addresses the aforementioned gap, but that approach felt too heavy-handed for this pair of uses. Some tests are added in t1006 to ensure that `cat-file` produces the same output in `--batch`, `--batch-check`, and `--batch-command` modes with and without the new `-z` option. Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Taylor Blau committed Jul 22, 2022 at 19:29 UTC db9d67f2e9c9ea389f5558d6a168460d51631769

3 files changed +72 -5

Documentation/git-cat-file.txt

+6 -1

@@ -14,7 +14,7 @@ SYNOPSIS

14 'git cat-file' (-t | -s) [--allow-unknown-type] <object>

15 'git cat-file' (--batch | --batch-check | --batch-command) [--batch-all-objects]

16 [--buffer] [--follow-symlinks] [--unordered]

17 - [--textconv | --filters]

17 + [--textconv | --filters] [-z]

18 'git cat-file' (--textconv | --filters)

19 [<rev>:<path|tree-ish> | --path=<path|tree-ish> <rev>]

@@ -207,6 +207,11 @@ respectively print:

207 /etc/passwd

208 --

209

210 +-z::

211 + Only meaningful with `--batch`, `--batch-check`, or

212 + `--batch-command`; input is NUL-delimited instead of

213 + newline-delimited.

214 +

215

216 OUTPUT

217 ------

builtin/cat-file.c

+25 -3

@@ -31,6 +31,7 @@ struct batch_options {

31 int all_objects;

32 int unordered;

33 int transform_mode; /* may be 'w' or 'c' for --filters or --textconv */

34 + int nul_terminated;

35 const char *format;

36 };

@@ -614,12 +615,20 @@ static void batch_objects_command(struct batch_options *opt,

615 struct queued_cmd *queued_cmd = NULL;

616 size_t alloc = 0, nr = 0;

617

617 - while (!strbuf_getline(&input, stdin)) {

618 - int i;

618 + while (1) {

619 + int i, ret;

620 const struct parse_cmd *cmd = NULL;

621 const char *p = NULL, *cmd_end;

622 struct queued_cmd call = {0};

623

624 + if (opt->nul_terminated)

625 + ret = strbuf_getline_nul(&input, stdin);

626 + else

627 + ret = strbuf_getline(&input, stdin);

628 +

629 + if (ret)

630 + break;

631 +

632 if (!input.len)

633 die(_("empty command in input"));

634 if (isspace(*input.buf))

@@ -763,7 +772,16 @@ static int batch_objects(struct batch_options *opt)

772 goto cleanup;

773 }

774

766 - while (strbuf_getline(&input, stdin) != EOF) {

775 + while (1) {

776 + int ret;

777 + if (opt->nul_terminated)

778 + ret = strbuf_getline_nul(&input, stdin);

779 + else

780 + ret = strbuf_getline(&input, stdin);

781 +

782 + if (ret == EOF)

783 + break;

784 +

785 if (data.split_on_whitespace) {

786 /*

787 * Split at first whitespace, tying off the beginning

@@ -866,6 +884,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)

884 N_("like --batch, but don't emit <contents>"),

885 PARSE_OPT_OPTARG | PARSE_OPT_NONEG,

886 batch_option_callback),

887 + OPT_BOOL('z', NULL, &batch.nul_terminated, N_("stdin is NUL-terminated")),

888 OPT_CALLBACK_F(0, "batch-command", &batch, N_("format"),

889 N_("read commands from stdin"),

890 PARSE_OPT_OPTARG | PARSE_OPT_NONEG,

@@ -921,6 +940,9 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)

940 else if (batch.all_objects)

941 usage_msg_optf(_("'%s' requires a batch mode"), usage, options,

942 "--batch-all-objects");

943 + else if (batch.nul_terminated)

944 + usage_msg_optf(_("'%s' requires a batch mode"), usage, options,

945 + "-z");

946

947 /* Batch defaults */

948 if (batch.buffer_output < 0)

t/t1006-cat-file.sh

+41 -1

@@ -88,7 +88,8 @@ done

89 for opt in --buffer \

90 --follow-symlinks \

91 - --batch-all-objects

91 + --batch-all-objects \

92 + -z

93 do

94 test_expect_success "usage: bad option combination: $opt without batch mode" '

95 test_incompatible_usage git cat-file $opt &&

@@ -100,6 +101,10 @@ echo_without_newline () {

101 printf '%s' "$*"

102 }

103

104 +echo_without_newline_nul () {

105 + echo_without_newline "$@" | tr '\n' '\0'

106 +}

107 +

108 strlen () {

109 echo_without_newline "$1" | wc -c | sed -e 's/^ *//'

110 }

@@ -398,6 +403,12 @@ test_expect_success '--batch with multiple sha1s gives correct format' '

403 test "$(maybe_remove_timestamp "$batch_output" 1)" = "$(maybe_remove_timestamp "$(echo_without_newline "$batch_input" | git cat-file --batch)" 1)"

404 '

405

406 +test_expect_success '--batch, -z with multiple sha1s gives correct format' '

407 + echo_without_newline_nul "$batch_input" >in &&

408 + test "$(maybe_remove_timestamp "$batch_output" 1)" = \

409 + "$(maybe_remove_timestamp "$(git cat-file --batch -z <in)" 1)"

410 +'

411 +

412 batch_check_input="$hello_sha1

413 $tree_sha1

414 $commit_sha1

@@ -418,6 +429,24 @@ test_expect_success "--batch-check with multiple sha1s gives correct format" '

429 "$(echo_without_newline "$batch_check_input" | git cat-file --batch-check)"

430 '

431

432 +test_expect_success "--batch-check, -z with multiple sha1s gives correct format" '

433 + echo_without_newline_nul "$batch_check_input" >in &&

434 + test "$batch_check_output" = "$(git cat-file --batch-check -z <in)"

435 +'

436 +

437 +test_expect_success FUNNYNAMES '--batch-check, -z with newline in input' '

438 + touch -- "newline${LF}embedded" &&

439 + git add -- "newline${LF}embedded" &&

440 + git commit -m "file with newline embedded" &&

441 + test_tick &&

442 +

443 + printf "HEAD:newline${LF}embedded" >in &&

444 + git cat-file --batch-check -z <in >actual &&

445 +

446 + echo "$(git rev-parse "HEAD:newline${LF}embedded") blob 0" >expect &&

447 + test_cmp expect actual

448 +'

449 +

450 batch_command_multiple_info="info $hello_sha1

451 info $tree_sha1

452 info $commit_sha1

@@ -436,6 +465,11 @@ test_expect_success '--batch-command with multiple info calls gives correct form

465 echo "$batch_command_multiple_info" >in &&

466 git cat-file --batch-command --buffer <in >actual &&

467

468 + test_cmp expect actual &&

469 +

470 + echo "$batch_command_multiple_info" | tr "\n" "\0" >in &&

471 + git cat-file --batch-command --buffer -z <in >actual &&

472 +

473 test_cmp expect actual

474 '

475

@@ -459,6 +493,12 @@ test_expect_success '--batch-command with multiple command calls gives correct f

493 echo "$batch_command_multiple_contents" >in &&

494 git cat-file --batch-command --buffer <in >actual_raw &&

495

496 + remove_timestamp <actual_raw >actual &&

497 + test_cmp expect actual &&

498 +

499 + echo "$batch_command_multiple_contents" | tr "\n" "\0" >in &&

500 + git cat-file --batch-command --buffer -z <in >actual_raw &&

501 +

502 remove_timestamp <actual_raw >actual &&

503 test_cmp expect actual

504 '