@matheusbsbs / matheus-bagliano / commits / c3d59c2e70

rev-list: support delimiting objects with NUL bytes

When walking objects, git-rev-list(1) prints each object entry on a separate line. Some options, such as `--objects`, may print additional information about tree and blob object on the same line in the form: $ git rev-list --objects <rev> <tree/blob oid> SP [<path>] LF Note that in this form the SP is appended regardless of whether the tree or blob object has path information available. Paths containing a newline are also truncated at the newline. Introduce the `-z` option for git-rev-list(1) which reformats the output to use NUL-delimiters between objects and associated info in the following form: $ git rev-list -z --objects <rev> <oid> NUL [path=<path> NUL] In this form, the start of each record is signaled by an OID entry that is all hexidecimal and does not contain any '='. Additional path info from `--objects` is appended to the record as a token/value pair `path=<path>` as-is without any truncation. For now, the `--objects` flag is the only options that can be used in combination with `-z`. In a subsequent commit, NUL-delimited support for other options is added. Other options that do not make sense when used in combination with `-z` are rejected. Signed-off-by: Justin Tobler <jltobler@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Justin Tobler committed Mar 19, 2025 at 13:34 UTC c3d59c2e70c939c39cbeb545b30899d52b650dfc

3 files changed +86 -5

Documentation/rev-list-options.adoc

+21

@@ -361,6 +361,27 @@ ifdef::git-rev-list[]

361 --progress=<header>::

362 Show progress reports on stderr as objects are considered. The

363 `<header>` text will be printed with each progress update.

364 +

365 +-z::

366 + Instead of being newline-delimited, each outputted object and its

367 + accompanying metadata is delimited using NUL bytes. Output is printed

368 + in the following form:

369 ++

370 +-----------------------------------------------------------------------

371 +<OID> NUL [<token>=<value> NUL]...

372 +-----------------------------------------------------------------------

373 ++

374 +Additional object metadata, such as object paths, is printed using the

375 +`<token>=<value>` form. Token values are printed as-is without any

376 +encoding/truncation. An OID entry never contains a '=' character and thus

377 +is used to signal the start of a new object record. Examples:

378 ++

379 +-----------------------------------------------------------------------

380 +<OID> NUL

381 +<OID> NUL path=<path> NUL

382 +-----------------------------------------------------------------------

383 ++

384 +This mode is only compatible with the `--objects` output option.

385 endif::git-rev-list[]

386

387 History Simplification

builtin/rev-list.c

+30 -5

@@ -65,6 +65,7 @@ static const char rev_list_usage[] =

65 " --abbrev-commit\n"

66 " --left-right\n"

67 " --count\n"

68 +" -z\n"

69 " special purpose:\n"

70 " --bisect\n"

71 " --bisect-vars\n"

@@ -97,6 +98,9 @@ static int arg_show_object_names = 1;

99 #define DEFAULT_OIDSET_SIZE (16*1024)

100

101 +static char line_term = '\n';

102 +static char info_term = ' ';

103 +

104 static int show_disk_usage;

105 static off_t total_disk_usage;

106 static int human_readable;

@@ -264,7 +268,7 @@ static void show_commit(struct commit *commit, void *data)

268 if (revs->commit_format == CMIT_FMT_ONELINE)

269 putchar(' ');

270 else if (revs->include_header)

267 - putchar('\n');

271 + putchar(line_term);

272

273 if (revs->verbose_header) {

274 struct strbuf buf = STRBUF_INIT;

@@ -361,12 +365,16 @@ static void show_object(struct object *obj, const char *name, void *cb_data)

365 printf("%s", oid_to_hex(&obj->oid));

366

367 if (arg_show_object_names) {

364 - putchar(' ');

365 - for (const char *p = name; *p && *p != '\n'; p++)

366 - putchar(*p);

368 + if (line_term) {

369 + putchar(info_term);

370 + for (const char *p = name; *p && *p != '\n'; p++)

371 + putchar(*p);

372 + } else if (*name) {

373 + printf("%cpath=%s", info_term, name);

374 + }

375 }

376

369 - putchar('\n');

377 + putchar(line_term);

378 }

379

380 static void show_edge(struct commit *commit)

@@ -642,6 +650,9 @@ int cmd_rev_list(int argc,

650 revs.exclude_promisor_objects = 1;

651 } else if (skip_prefix(arg, "--missing=", &arg)) {

652 parse_missing_action_value(arg);

653 + } else if (!strcmp(arg, "-z")) {

654 + line_term = '\0';

655 + info_term = '\0';

656 }

657 }

658

@@ -757,6 +768,20 @@ int cmd_rev_list(int argc,

768 usage(rev_list_usage);

769

770 }

771 +

772 + /*

773 + * Reject options currently incompatible with -z. For some options, this

774 + * is not an inherent limitation and support may be implemented in the

775 + * future.

776 + */

777 + if (!line_term) {

778 + if (revs.graph || revs.verbose_header || show_disk_usage ||

779 + info.show_timestamp || info.header_prefix || bisect_list ||

780 + use_bitmap_index || revs.edge_hint || revs.left_right ||

781 + revs.cherry_mark || arg_missing_action || revs.boundary)

782 + die(_("-z option used with unsupported option"));

783 + }

784 +

785 if (revs.commit_format != CMIT_FMT_USERFORMAT)

786 revs.include_header = 1;

787 if (revs.commit_format != CMIT_FMT_UNSPECIFIED) {

t/t6000-rev-list-misc.sh

+35

@@ -182,4 +182,39 @@ test_expect_success 'rev-list --unpacked' '

182 test_cmp expect actual

183 '

184

185 +test_expect_success 'rev-list -z' '

186 + test_when_finished rm -rf repo &&

187 +

188 + git init repo &&

189 + test_commit -C repo 1 &&

190 + test_commit -C repo 2 &&

191 +

192 + oid1=$(git -C repo rev-parse HEAD~) &&

193 + oid2=$(git -C repo rev-parse HEAD) &&

194 +

195 + printf "%s\0%s\0" "$oid2" "$oid1" >expect &&

196 + git -C repo rev-list -z HEAD >actual &&

197 +

198 + test_cmp expect actual

199 +'

200 +

201 +test_expect_success 'rev-list -z --objects' '

202 + test_when_finished rm -rf repo &&

203 +

204 + git init repo &&

205 + test_commit -C repo 1 &&

206 + test_commit -C repo 2 &&

207 +

208 + oid1=$(git -C repo rev-parse HEAD:1.t) &&

209 + oid2=$(git -C repo rev-parse HEAD:2.t) &&

210 + path1=1.t &&

211 + path2=2.t &&

212 +

213 + printf "%s\0path=%s\0%s\0path=%s\0" "$oid1" "$path1" "$oid2" "$path2" \

214 + >expect &&

215 + git -C repo rev-list -z --objects HEAD:1.t HEAD:2.t >actual &&

216 +

217 + test_cmp expect actual

218 +'

219 +

220 test_done