From db9d67f2e9c9ea389f5558d6a168460d51631769 Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Fri, 22 Jul 2022 19:29:05 -0400 Subject: 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 Signed-off-by: Junio C Hamano diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt index 24a811f..3515350 100644 --- a/Documentation/git-cat-file.txt +++ b/Documentation/git-cat-file.txt @@ -14,7 +14,7 @@ SYNOPSIS 'git cat-file' (-t | -s) [--allow-unknown-type] 'git cat-file' (--batch | --batch-check | --batch-command) [--batch-all-objects] [--buffer] [--follow-symlinks] [--unordered] - [--textconv | --filters] + [--textconv | --filters] [-z] 'git cat-file' (--textconv | --filters) [: | --path= ] @@ -207,6 +207,11 @@ respectively print: /etc/passwd -- +-z:: + Only meaningful with `--batch`, `--batch-check`, or + `--batch-command`; input is NUL-delimited instead of + newline-delimited. + OUTPUT ------ diff --git a/builtin/cat-file.c b/builtin/cat-file.c index f42782e..c3602d1 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -31,6 +31,7 @@ struct batch_options { int all_objects; int unordered; int transform_mode; /* may be 'w' or 'c' for --filters or --textconv */ + int nul_terminated; const char *format; }; @@ -614,12 +615,20 @@ static void batch_objects_command(struct batch_options *opt, struct queued_cmd *queued_cmd = NULL; size_t alloc = 0, nr = 0; - while (!strbuf_getline(&input, stdin)) { - int i; + while (1) { + int i, ret; const struct parse_cmd *cmd = NULL; const char *p = NULL, *cmd_end; struct queued_cmd call = {0}; + if (opt->nul_terminated) + ret = strbuf_getline_nul(&input, stdin); + else + ret = strbuf_getline(&input, stdin); + + if (ret) + break; + if (!input.len) die(_("empty command in input")); if (isspace(*input.buf)) @@ -763,7 +772,16 @@ static int batch_objects(struct batch_options *opt) goto cleanup; } - while (strbuf_getline(&input, stdin) != EOF) { + while (1) { + int ret; + if (opt->nul_terminated) + ret = strbuf_getline_nul(&input, stdin); + else + ret = strbuf_getline(&input, stdin); + + if (ret == EOF) + break; + if (data.split_on_whitespace) { /* * Split at first whitespace, tying off the beginning @@ -866,6 +884,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix) N_("like --batch, but don't emit "), PARSE_OPT_OPTARG | PARSE_OPT_NONEG, batch_option_callback), + OPT_BOOL('z', NULL, &batch.nul_terminated, N_("stdin is NUL-terminated")), OPT_CALLBACK_F(0, "batch-command", &batch, N_("format"), N_("read commands from stdin"), PARSE_OPT_OPTARG | PARSE_OPT_NONEG, @@ -921,6 +940,9 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix) else if (batch.all_objects) usage_msg_optf(_("'%s' requires a batch mode"), usage, options, "--batch-all-objects"); + else if (batch.nul_terminated) + usage_msg_optf(_("'%s' requires a batch mode"), usage, options, + "-z"); /* Batch defaults */ if (batch.buffer_output < 0) diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh index 01c0535..23b8942 100755 --- a/t/t1006-cat-file.sh +++ b/t/t1006-cat-file.sh @@ -88,7 +88,8 @@ done for opt in --buffer \ --follow-symlinks \ - --batch-all-objects + --batch-all-objects \ + -z do test_expect_success "usage: bad option combination: $opt without batch mode" ' test_incompatible_usage git cat-file $opt && @@ -100,6 +101,10 @@ echo_without_newline () { printf '%s' "$*" } +echo_without_newline_nul () { + echo_without_newline "$@" | tr '\n' '\0' +} + strlen () { echo_without_newline "$1" | wc -c | sed -e 's/^ *//' } @@ -398,6 +403,12 @@ test_expect_success '--batch with multiple sha1s gives correct format' ' test "$(maybe_remove_timestamp "$batch_output" 1)" = "$(maybe_remove_timestamp "$(echo_without_newline "$batch_input" | git cat-file --batch)" 1)" ' +test_expect_success '--batch, -z with multiple sha1s gives correct format' ' + echo_without_newline_nul "$batch_input" >in && + test "$(maybe_remove_timestamp "$batch_output" 1)" = \ + "$(maybe_remove_timestamp "$(git cat-file --batch -z in && + test "$batch_check_output" = "$(git cat-file --batch-check -z in && + git cat-file --batch-check -z actual && + + echo "$(git rev-parse "HEAD:newline${LF}embedded") blob 0" >expect && + test_cmp expect actual +' + batch_command_multiple_info="info $hello_sha1 info $tree_sha1 info $commit_sha1 @@ -436,6 +465,11 @@ test_expect_success '--batch-command with multiple info calls gives correct form echo "$batch_command_multiple_info" >in && git cat-file --batch-command --buffer actual && + test_cmp expect actual && + + echo "$batch_command_multiple_info" | tr "\n" "\0" >in && + git cat-file --batch-command --buffer -z actual && + test_cmp expect actual ' @@ -460,6 +494,12 @@ test_expect_success '--batch-command with multiple command calls gives correct f git cat-file --batch-command --buffer actual_raw && remove_timestamp actual && + test_cmp expect actual && + + echo "$batch_command_multiple_contents" | tr "\n" "\0" >in && + git cat-file --batch-command --buffer -z actual_raw && + + remove_timestamp actual && test_cmp expect actual ' -- cgit v0.10.2-6-g49f6