version: include version information for tarballs from git

Embed the git commit hash as well as the tag information for tarballs
produced by 'git archive' (this includes the Github tarball). Example:

    TShark (Wireshark) 3.0.1 (Git commit ea351cd)

Note that the embedded git ref names can include branch information, see
for example `git log -n1 -s --format=%D v3.0.1`:

    tag: wireshark-3.0.1, tag: v3.0.1
    HEAD -> bug/15544, tag: v99.99
    HEAD, origin/master, origin/HEAD, master

Thus, when creating release tarballs, I would recommend using the above
command to see whether unnecessary branch information is present. If so,
create a new post-release commit first on the same branch. This way, the
release tarballs should be reproducible.

While at it, increase the commit abbreviation length from 8 to 12.
Currently git describe abbreviates to 10 by default. The default length
is at minimum 7 and is dependent on the number of objects:

    git count-objects -v | perl -lne 'print int(log($1)/log(2)/2)+1 if /^in-pack: (\d+)/'

Bug: 15544
Change-Id: Ifd1ed636b69f7687a7272775686f51387040a596
Reviewed-on: https://code.wireshark.org/review/33214
Petri-Dish: Peter Wu <peter@lekensteyn.nl>
Tested-by: Petri Dish Buildbot
Reviewed-by: Dario Lombardo <lomato@gmail.com>
Reviewed-by: Alexis La Goutte <alexis.lagoutte@gmail.com>

.gitattributes

@@ -5,3 +5,4 @@
 .gitattributes              export-ignore
 .gitignore                  export-ignore
 .gitreview                  export-ignore
+tools/make-version.pl       export-subst

tools/make-version.pl

@@ -80,17 +80,36 @@ sub read_repo_info {
 	my $do_hack = 1;
 	my $info_source = "Unknown";
 	my $is_git_repo = 0;
+	my $git_abbrev_length = 12;
 	my $git_cdir;
 	my $vcs_tag;
 	my $repo_branch = "unknown";
 	my $info_cmd = "";
 
+	# Tarball produced by 'git archive' will have the $Format string
+	# substituted due to the use of 'export-subst' in .gitattributes.
+	my $git_archive_commit = '$Format:%H$';
+	my @git_refs = split(/, /, '$Format:%D$');
+	if (substr($git_archive_commit, 0, 1) eq '$') {
+		# If $Format is still present, then this is not a git archive.
+		$git_archive_commit = undef;
+	} else {
+		foreach my $git_ref (@git_refs) {
+			if ($git_ref =~ /^tag: (v[1-9].+)/) {
+				$vcs_tag = $1;
+				$is_tagged = 1;
+			}
+		}
+	}
+
 	$package_string = $untagged_version_extra;
 
 	# For tarball releases, do not invoke git at all and instead rely on
 	# versioning information that was provided at tarball creation time.
 	if ($git_description) {
 		$info_source = "Forced via command line flag";
+	} elsif ($git_archive_commit) {
+		$info_source = "git archive";
 	} elsif (-e "$src_dir/.git" && ! -d "$src_dir/.git/svn") {
 		$info_source = "Command line (git)";
 		$git_client = 1;
@@ -148,6 +167,10 @@ sub read_repo_info {
 		$do_hack = 0;
 		# Assume format like v2.3.0rc0-1342-g7bdcf75
 		$commit_id = ($git_description =~ /([0-9a-f]+)$/)[0];
+	} elsif ($git_archive_commit) {
+		$do_hack = 0;
+		# Assume a full commit hash, abbreviate it.
+		$commit_id = substr($git_archive_commit, 0, $git_abbrev_length);
 	} elsif ($git_client) {
 		eval {
 			use warnings "all";
@@ -159,7 +182,7 @@ sub read_repo_info {
 			}
 
 			# Commits since last annotated tag.
-			chomp($line = qx{git --git-dir="$src_dir"/.git describe --abbrev=8 --long --always --match "v[1-9]*"});
+			chomp($line = qx{git --git-dir="$src_dir"/.git describe --abbrev=$git_abbrev_length --long --always --match "v[1-9]*"});
 			if ($? == 0 && length($line) > 1) {
 				my @parts = split(/-/, $line);
 				$git_description = $line;
@@ -577,6 +600,10 @@ sub new_version_h
 		return "#define VCSVERSION \"$line-$vcs_name-$num_commits\"\n";
 	}
 
+	if ($commit_id) {
+		return "#define VCSVERSION \"$vcs_name commit $commit_id\"\n";
+	}
+
 	return "#define VCSVERSION \"$vcs_name Rev Unknown from unknown\"\n";
 }