Merge branch 'mr/gitweb-snapshot'

* mr/gitweb-snapshot:
  t/gitweb-lib: Split HTTP response with non-GNU sed
  gitweb: Smarter snapshot names
  gitweb: Document current snapshot rules via new tests
  t/gitweb-lib.sh: Split gitweb output into headers and body
  gitweb: check given hash before trying to create snapshot

4 files changed, 234 insertions, 19 deletions

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index 681e63509..f94536c68 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -2020,16 +2020,27 @@ sub quote_command {
 
 # get HEAD ref of given project as hash
 sub git_get_head_hash {
-	my $project = shift;
+	return git_get_full_hash(shift, 'HEAD');
+}
+
+sub git_get_full_hash {
+	return git_get_hash(@_);
+}
+
+sub git_get_short_hash {
+	return git_get_hash(@_, '--short=7');
+}
+
+sub git_get_hash {
+	my ($project, $hash, @options) = @_;
 	my $o_git_dir = $git_dir;
 	my $retval = undef;
 	$git_dir = "$projectroot/$project";
-	if (open my $fd, "-|", git_cmd(), "rev-parse", "--verify", "HEAD") {
-		my $head = <$fd>;
+	if (open my $fd, '-|', git_cmd(), 'rev-parse',
+	    '--verify', '-q', @options, $hash) {
+		$retval = <$fd>;
+		chomp $retval if defined $retval;
 		close $fd;
-		if (defined $head && $head =~ /^([0-9a-fA-F]{40})$/) {
-			$retval = $1;
-		}
 	}
 	if (defined $o_git_dir) {
 		$git_dir = $o_git_dir;
@@ -5285,6 +5296,43 @@ sub git_tree {
 	git_footer_html();
 }
 
+sub snapshot_name {
+	my ($project, $hash) = @_;
+
+	# path/to/project.git  -> project
+	# path/to/project/.git -> project
+	my $name = to_utf8($project);
+	$name =~ s,([^/])/*\.git$,$1,;
+	$name = basename($name);
+	# sanitize name
+	$name =~ s/[[:cntrl:]]/?/g;
+
+	my $ver = $hash;
+	if ($hash =~ /^[0-9a-fA-F]+$/) {
+		# shorten SHA-1 hash
+		my $full_hash = git_get_full_hash($project, $hash);
+		if ($full_hash =~ /^$hash/ && length($hash) > 7) {
+			$ver = git_get_short_hash($project, $hash);
+		}
+	} elsif ($hash =~ m!^refs/tags/(.*)$!) {
+		# tags don't need shortened SHA-1 hash
+		$ver = $1;
+	} else {
+		# branches and other need shortened SHA-1 hash
+		if ($hash =~ m!^refs/(?:heads|remotes)/(.*)$!) {
+			$ver = $1;
+		}
+		$ver .= '-' . git_get_short_hash($project, $hash);
+	}
+	# in case of hierarchical branch names
+	$ver =~ s!/!.!g;
+
+	# name = project-version_string
+	$name = "$name-$ver";
+
+	return wantarray ? ($name, $name) : $name;
+}
+
 sub git_snapshot {
 	my $format = $input_params{'snapshot_format'};
 	if (!@snapshot_fmts) {
@@ -5302,28 +5350,27 @@ sub git_snapshot {
 		die_error(403, "Unsupported snapshot format");
 	}
 
-	if (!defined $hash) {
-		$hash = git_get_head_hash($project);
+	my $type = git_get_type("$hash^{}");
+	if (!$type) {
+		die_error(404, 'Object does not exist');
+	}  elsif ($type eq 'blob') {
+		die_error(400, 'Object is not a tree-ish');
 	}
 
-	my $name = $project;
-	$name =~ s,([^/])/*\.git$,$1,;
-	$name = basename($name);
-	my $filename = to_utf8($name);
-	$name =~ s/\047/\047\\\047\047/g;
-	my $cmd;
-	$filename .= "-$hash$known_snapshot_formats{$format}{'suffix'}";
-	$cmd = quote_command(
+	my ($name, $prefix) = snapshot_name($project, $hash);
+	my $filename = "$name$known_snapshot_formats{$format}{'suffix'}";
+	my $cmd = quote_command(
 		git_cmd(), 'archive',
 		"--format=$known_snapshot_formats{$format}{'format'}",
-		"--prefix=$name/", $hash);
+		"--prefix=$prefix/", $hash);
 	if (exists $known_snapshot_formats{$format}{'compressor'}) {
 		$cmd .= ' | ' . quote_command(@{$known_snapshot_formats{$format}{'compressor'}});
 	}
 
+	$filename =~ s/(["\\])/\\$1/g;
 	print $cgi->header(
 		-type => $known_snapshot_formats{$format}{'type'},
-		-content_disposition => 'inline; filename="' . "$filename" . '"',
+		-content_disposition => 'inline; filename="' . $filename . '"',
 		-status => '200 OK');
 
 	open my $fd, "-|", $cmd
diff --git a/t/gitweb-lib.sh b/t/gitweb-lib.sh
index 845253274..76d8b7b80 100644
--- a/t/gitweb-lib.sh
+++ b/t/gitweb-lib.sh
@@ -52,10 +52,24 @@ gitweb_run () {
 	rm -f gitweb.log &&
 	perl -- "$SCRIPT_NAME" \
 		>gitweb.output 2>gitweb.log &&
+	perl -w -e '
+		open O, ">gitweb.headers";
+		while (<>) {
+			print O;
+			last if (/^\r$/ || /^$/);
+		}
+		open O, ">gitweb.body";
+		while (<>) {
+			print O;
+		}
+		close O;
+	' gitweb.output &&
 	if grep '^[[]' gitweb.log >/dev/null 2>&1; then false; else true; fi
 
 	# gitweb.log is left for debugging
-	# gitweb.output is used to parse http output
+	# gitweb.output is used to parse HTTP output
+	# gitweb.headers contains only HTTP headers
+	# gitweb.body contains body of message, without headers
 }
 
 . ./test-lib.sh
diff --git a/t/t9501-gitweb-standalone-http-status.sh b/t/t9501-gitweb-standalone-http-status.sh
index d0ff21d42..0688a57e1 100755
--- a/t/t9501-gitweb-standalone-http-status.sh
+++ b/t/t9501-gitweb-standalone-http-status.sh
@@ -75,4 +75,43 @@ test_expect_success \
 test_debug 'cat gitweb.output'
 
 
+# ----------------------------------------------------------------------
+# snapshot hash ids
+
+test_expect_success 'snapshots: good tree-ish id' '
+	gitweb_run "p=.git;a=snapshot;h=master;sf=tgz" &&
+	grep "Status: 200 OK" gitweb.output
+'
+test_debug 'cat gitweb.output'
+
+test_expect_success 'snapshots: bad tree-ish id' '
+	gitweb_run "p=.git;a=snapshot;h=frizzumFrazzum;sf=tgz" &&
+	grep "404 - Object does not exist" gitweb.output
+'
+test_debug 'cat gitweb.output'
+
+test_expect_success 'snapshots: bad tree-ish id (tagged object)' '
+	echo object > tag-object &&
+	git add tag-object &&
+	git commit -m "Object to be tagged" &&
+	git tag tagged-object `git hash-object tag-object` &&
+	gitweb_run "p=.git;a=snapshot;h=tagged-object;sf=tgz" &&
+	grep "400 - Object is not a tree-ish" gitweb.output
+'
+test_debug 'cat gitweb.output'
+
+test_expect_success 'snapshots: good object id' '
+	ID=`git rev-parse --verify HEAD` &&
+	gitweb_run "p=.git;a=snapshot;h=$ID;sf=tgz" &&
+	grep "Status: 200 OK" gitweb.output
+'
+test_debug 'cat gitweb.output'
+
+test_expect_success 'snapshots: bad object id' '
+	gitweb_run "p=.git;a=snapshot;h=abcdef01234;sf=tgz" &&
+	grep "404 - Object does not exist" gitweb.output
+'
+test_debug 'cat gitweb.output'
+
+
 test_done
diff --git a/t/t9502-gitweb-standalone-parse-output.sh b/t/t9502-gitweb-standalone-parse-output.sh
new file mode 100755
index 000000000..dd8389000
--- /dev/null
+++ b/t/t9502-gitweb-standalone-parse-output.sh
@@ -0,0 +1,115 @@
+#!/bin/sh
+#
+# Copyright (c) 2009 Mark Rada
+#
+
+test_description='gitweb as standalone script (parsing script output).
+
+This test runs gitweb (git web interface) as a CGI script from the
+commandline, and checks that it produces the correct output, either
+in the HTTP header or the actual script output.'
+
+
+. ./gitweb-lib.sh
+
+# ----------------------------------------------------------------------
+# snapshot file name and prefix
+
+cat >>gitweb_config.perl <<\EOF
+
+$known_snapshot_formats{'tar'} = {
+	'display' => 'tar',
+	'type' => 'application/x-tar',
+	'suffix' => '.tar',
+	'format' => 'tar',
+};
+
+$feature{'snapshot'}{'default'} = ['tar'];
+EOF
+
+# Call check_snapshot with the arguments "<basename> [<prefix>]"
+#
+# This will check that gitweb HTTP header contains proposed filename
+# as <basename> with '.tar' suffix added, and that generated tarfile
+# (gitweb message body) has <prefix> as prefix for al files in tarfile
+#
+# <prefix> default to <basename>
+check_snapshot () {
+	basename=$1
+	prefix=${2:-"$1"}
+	echo "basename=$basename"
+	grep "filename=.*$basename.tar" gitweb.headers >/dev/null 2>&1 &&
+	"$TAR" tf gitweb.body >file_list &&
+	! grep -v "^$prefix/" file_list
+}
+
+test_expect_success setup '
+	test_commit first foo &&
+	git branch xx/test &&
+	FULL_ID=$(git rev-parse --verify HEAD) &&
+	SHORT_ID=$(git rev-parse --verify --short=7 HEAD)
+'
+test_debug '
+	echo "FULL_ID  = $FULL_ID"
+	echo "SHORT_ID = $SHORT_ID"
+'
+
+test_expect_success 'snapshot: full sha1' '
+	gitweb_run "p=.git;a=snapshot;h=$FULL_ID;sf=tar" &&
+	check_snapshot ".git-$SHORT_ID"
+'
+test_debug 'cat gitweb.headers && cat file_list'
+
+test_expect_success 'snapshot: shortened sha1' '
+	gitweb_run "p=.git;a=snapshot;h=$SHORT_ID;sf=tar" &&
+	check_snapshot ".git-$SHORT_ID"
+'
+test_debug 'cat gitweb.headers && cat file_list'
+
+test_expect_success 'snapshot: almost full sha1' '
+	ID=$(git rev-parse --short=30 HEAD) &&
+	gitweb_run "p=.git;a=snapshot;h=$ID;sf=tar" &&
+	check_snapshot ".git-$SHORT_ID"
+'
+test_debug 'cat gitweb.headers && cat file_list'
+
+test_expect_success 'snapshot: HEAD' '
+	gitweb_run "p=.git;a=snapshot;h=HEAD;sf=tar" &&
+	check_snapshot ".git-HEAD-$SHORT_ID"
+'
+test_debug 'cat gitweb.headers && cat file_list'
+
+test_expect_success 'snapshot: short branch name (master)' '
+	gitweb_run "p=.git;a=snapshot;h=master;sf=tar" &&
+	ID=$(git rev-parse --verify --short=7 master) &&
+	check_snapshot ".git-master-$ID"
+'
+test_debug 'cat gitweb.headers && cat file_list'
+
+test_expect_success 'snapshot: short tag name (first)' '
+	gitweb_run "p=.git;a=snapshot;h=first;sf=tar" &&
+	ID=$(git rev-parse --verify --short=7 first) &&
+	check_snapshot ".git-first-$ID"
+'
+test_debug 'cat gitweb.headers && cat file_list'
+
+test_expect_success 'snapshot: full branch name (refs/heads/master)' '
+	gitweb_run "p=.git;a=snapshot;h=refs/heads/master;sf=tar" &&
+	ID=$(git rev-parse --verify --short=7 master) &&
+	check_snapshot ".git-master-$ID"
+'
+test_debug 'cat gitweb.headers && cat file_list'
+
+test_expect_success 'snapshot: full tag name (refs/tags/first)' '
+	gitweb_run "p=.git;a=snapshot;h=refs/tags/first;sf=tar" &&
+	check_snapshot ".git-first"
+'
+test_debug 'cat gitweb.headers && cat file_list'
+
+test_expect_success 'snapshot: hierarchical branch name (xx/test)' '
+	gitweb_run "p=.git;a=snapshot;h=xx/test;sf=tar" &&
+	! grep "filename=.*/" gitweb.headers
+'
+test_debug 'cat gitweb.headers'
+
+test_done