Merge branch 'rs/archive-with-internal-gzip'

Teach "git archive" to (optionally and then by default) avoid
spawning an external "gzip" process when creating ".tar.gz" (and
".tgz") archives.

* rs/archive-with-internal-gzip:
  archive-tar: use internal gzip by default
  archive-tar: use OS_CODE 3 (Unix) for internal gzip
  archive-tar: add internal gzip implementation
  archive-tar: factor out write_block()
  archive: rename archiver data field to filter_command
  archive: update format documentation

4 files changed, 100 insertions, 28 deletions

diff --git a/Documentation/git-archive.txt b/Documentation/git-archive.txt
index 56989a2f34..60c040988b 100644
--- a/Documentation/git-archive.txt
+++ b/Documentation/git-archive.txt
@@ -34,10 +34,12 @@ OPTIONS
 -------
 
 --format=<fmt>::
-	Format of the resulting archive: 'tar' or 'zip'. If this option
+	Format of the resulting archive. Possible values are `tar`,
+	`zip`, `tar.gz`, `tgz`, and any format defined using the
+	configuration option `tar.<format>.command`. If `--format`
 	is not given, and the output file is specified, the format is
-	inferred from the filename if possible (e.g. writing to "foo.zip"
-	makes the output to be in the zip format). Otherwise the output
+	inferred from the filename if possible (e.g. writing to `foo.zip`
+	makes the output to be in the `zip` format). Otherwise the output
 	format is `tar`.
 
 -l::
@@ -143,17 +145,16 @@ tar.<format>.command::
 	is executed using the shell with the generated tar file on its
 	standard input, and should produce the final output on its
 	standard output. Any compression-level options will be passed
-	to the command (e.g., "-9"). An output file with the same
-	extension as `<format>` will be use this format if no other
-	format is given.
+	to the command (e.g., `-9`).
 +
-The "tar.gz" and "tgz" formats are defined automatically and default to
-`gzip -cn`. You may override them with custom commands.
+The `tar.gz` and `tgz` formats are defined automatically and use the
+magic command `git archive gzip` by default, which invokes an internal
+implementation of gzip.
 
 tar.<format>.remote::
-	If true, enable `<format>` for use by remote clients via
+	If true, enable the format for use by remote clients via
 	linkgit:git-upload-archive[1]. Defaults to false for
-	user-defined formats, but true for the "tar.gz" and "tgz"
+	user-defined formats, but true for the `tar.gz` and `tgz`
 	formats.
 
 [[ATTRIBUTES]]
diff --git a/archive-tar.c b/archive-tar.c
index 042feb66d2..3d77e0f750 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -38,11 +38,18 @@ static int write_tar_filter_archive(const struct archiver *ar,
 #define USTAR_MAX_MTIME 077777777777ULL
 #endif
 
+static void tar_write_block(const void *buf)
+{
+	write_or_die(1, buf, BLOCKSIZE);
+}
+
+static void (*write_block)(const void *) = tar_write_block;
+
 /* writes out the whole block, but only if it is full */
 static void write_if_needed(void)
 {
 	if (offset == BLOCKSIZE) {
-		write_or_die(1, block, BLOCKSIZE);
+		write_block(block);
 		offset = 0;
 	}
 }
@@ -66,7 +73,7 @@ static void do_write_blocked(const void *data, unsigned long size)
 		write_if_needed();
 	}
 	while (size >= BLOCKSIZE) {
-		write_or_die(1, buf, BLOCKSIZE);
+		write_block(buf);
 		size -= BLOCKSIZE;
 		buf += BLOCKSIZE;
 	}
@@ -101,10 +108,10 @@ static void write_trailer(void)
 {
 	int tail = BLOCKSIZE - offset;
 	memset(block + offset, 0, tail);
-	write_or_die(1, block, BLOCKSIZE);
+	write_block(block);
 	if (tail < 2 * RECORDSIZE) {
 		memset(block, 0, offset);
-		write_or_die(1, block, BLOCKSIZE);
+		write_block(block);
 	}
 }
 
@@ -383,8 +390,8 @@ static int tar_filter_config(const char *var, const char *value, void *data)
 	if (!strcmp(type, "command")) {
 		if (!value)
 			return config_error_nonbool(var);
-		free(ar->data);
-		ar->data = xstrdup(value);
+		free(ar->filter_command);
+		ar->filter_command = xstrdup(value);
 		return 0;
 	}
 	if (!strcmp(type, "remote")) {
@@ -425,17 +432,65 @@ static int write_tar_archive(const struct archiver *ar,
 	return err;
 }
 
+static git_zstream gzstream;
+static unsigned char outbuf[16384];
+
+static void tgz_deflate(int flush)
+{
+	while (gzstream.avail_in || flush == Z_FINISH) {
+		int status = git_deflate(&gzstream, flush);
+		if (!gzstream.avail_out || status == Z_STREAM_END) {
+			write_or_die(1, outbuf, gzstream.next_out - outbuf);
+			gzstream.next_out = outbuf;
+			gzstream.avail_out = sizeof(outbuf);
+			if (status == Z_STREAM_END)
+				break;
+		}
+		if (status != Z_OK && status != Z_BUF_ERROR)
+			die(_("deflate error (%d)"), status);
+	}
+}
+
+static void tgz_write_block(const void *data)
+{
+	gzstream.next_in = (void *)data;
+	gzstream.avail_in = BLOCKSIZE;
+	tgz_deflate(Z_NO_FLUSH);
+}
+
+static const char internal_gzip_command[] = "git archive gzip";
+
 static int write_tar_filter_archive(const struct archiver *ar,
 				    struct archiver_args *args)
 {
+#if ZLIB_VERNUM >= 0x1221
+	struct gz_header_s gzhead = { .os = 3 }; /* Unix, for reproducibility */
+#endif
 	struct strbuf cmd = STRBUF_INIT;
 	struct child_process filter = CHILD_PROCESS_INIT;
 	int r;
 
-	if (!ar->data)
+	if (!ar->filter_command)
 		BUG("tar-filter archiver called with no filter defined");
 
-	strbuf_addstr(&cmd, ar->data);
+	if (!strcmp(ar->filter_command, internal_gzip_command)) {
+		write_block = tgz_write_block;
+		git_deflate_init_gzip(&gzstream, args->compression_level);
+#if ZLIB_VERNUM >= 0x1221
+		if (deflateSetHeader(&gzstream.z, &gzhead) != Z_OK)
+			BUG("deflateSetHeader() called too late");
+#endif
+		gzstream.next_out = outbuf;
+		gzstream.avail_out = sizeof(outbuf);
+
+		r = write_tar_archive(ar, args);
+
+		tgz_deflate(Z_FINISH);
+		git_deflate_end(&gzstream);
+		return r;
+	}
+
+	strbuf_addstr(&cmd, ar->filter_command);
 	if (args->compression_level >= 0)
 		strbuf_addf(&cmd, " -%d", args->compression_level);
 
@@ -471,14 +526,14 @@ void init_tar_archiver(void)
 	int i;
 	register_archiver(&tar_archiver);
 
-	tar_filter_config("tar.tgz.command", "gzip -cn", NULL);
+	tar_filter_config("tar.tgz.command", internal_gzip_command, NULL);
 	tar_filter_config("tar.tgz.remote", "true", NULL);
-	tar_filter_config("tar.tar.gz.command", "gzip -cn", NULL);
+	tar_filter_config("tar.tar.gz.command", internal_gzip_command, NULL);
 	tar_filter_config("tar.tar.gz.remote", "true", NULL);
 	git_config(git_tar_config, NULL);
 	for (i = 0; i < nr_tar_filters; i++) {
 		/* omit any filters that never had a command configured */
-		if (tar_filters[i]->data)
+		if (tar_filters[i]->filter_command)
 			register_archiver(tar_filters[i]);
 	}
 }
diff --git a/archive.h b/archive.h
index 49fab71aaf..08bed3ed3a 100644
--- a/archive.h
+++ b/archive.h
@@ -43,7 +43,7 @@ struct archiver {
 	const char *name;
 	int (*write_archive)(const struct archiver *, struct archiver_args *);
 	unsigned flags;
-	void *data;
+	char *filter_command;
 };
 void register_archiver(struct archiver *);
 
diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh
index 7f8d2ab0a7..1a68e89a55 100755
--- a/t/t5000-tar-tree.sh
+++ b/t/t5000-tar-tree.sh
@@ -339,21 +339,21 @@ test_expect_success 'only enabled filters are available remotely' '
 	test_cmp_bin remote.bar config.bar
 '
 
-test_expect_success GZIP 'git archive --format=tgz' '
+test_expect_success 'git archive --format=tgz' '
 	git archive --format=tgz HEAD >j.tgz
 '
 
-test_expect_success GZIP 'git archive --format=tar.gz' '
+test_expect_success 'git archive --format=tar.gz' '
 	git archive --format=tar.gz HEAD >j1.tar.gz &&
 	test_cmp_bin j.tgz j1.tar.gz
 '
 
-test_expect_success GZIP 'infer tgz from .tgz filename' '
+test_expect_success 'infer tgz from .tgz filename' '
 	git archive --output=j2.tgz HEAD &&
 	test_cmp_bin j.tgz j2.tgz
 '
 
-test_expect_success GZIP 'infer tgz from .tar.gz filename' '
+test_expect_success 'infer tgz from .tar.gz filename' '
 	git archive --output=j3.tar.gz HEAD &&
 	test_cmp_bin j.tgz j3.tar.gz
 '
@@ -363,17 +363,33 @@ test_expect_success GZIP 'extract tgz file' '
 	test_cmp_bin b.tar j.tar
 '
 
-test_expect_success GZIP 'remote tar.gz is allowed by default' '
+test_expect_success 'remote tar.gz is allowed by default' '
 	git archive --remote=. --format=tar.gz HEAD >remote.tar.gz &&
 	test_cmp_bin j.tgz remote.tar.gz
 '
 
-test_expect_success GZIP 'remote tar.gz can be disabled' '
+test_expect_success 'remote tar.gz can be disabled' '
 	git config tar.tar.gz.remote false &&
 	test_must_fail git archive --remote=. --format=tar.gz HEAD \
 		>remote.tar.gz
 '
 
+test_expect_success GZIP 'git archive --format=tgz (external gzip)' '
+	test_config tar.tgz.command "gzip -cn" &&
+	git archive --format=tgz HEAD >external_gzip.tgz
+'
+
+test_expect_success GZIP 'git archive --format=tar.gz (external gzip)' '
+	test_config tar.tar.gz.command "gzip -cn" &&
+	git archive --format=tar.gz HEAD >external_gzip.tar.gz &&
+	test_cmp_bin external_gzip.tgz external_gzip.tar.gz
+'
+
+test_expect_success GZIP 'extract tgz file (external gzip)' '
+	gzip -d -c <external_gzip.tgz >external_gzip.tar &&
+	test_cmp_bin b.tar external_gzip.tar
+'
+
 test_expect_success 'archive and :(glob)' '
 	git archive -v HEAD -- ":(glob)**/sh" >/dev/null 2>actual &&
 	cat >expect <<EOF &&