svnimport: Read author names and emails from a file

Read a file with lines on the form

  username User's Full Name <email@addres.org>

and use "User's Full Name <email@addres.org>" as the GIT author and
committer for Subversion commits made by "username". If encountering a
commit made by a user not in the list, abort.

Signed-off-by: Karl Hasselström <kha@treskal.com>
Signed-off-by: Junio C Hamano <junkio@cox.net>

2 files changed, 32 insertions, 4 deletions

diff --git a/Documentation/git-svnimport.txt b/Documentation/git-svnimport.txt
index c95ff84f6..e0e3a5d4e 100644
--- a/Documentation/git-svnimport.txt
+++ b/Documentation/git-svnimport.txt
@@ -13,7 +13,8 @@ SYNOPSIS
 		[ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev]
 		[ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ]
 		[ -s start_chg ] [ -m ] [ -r ] [ -M regex ]
-		[ -I <ignorefile_name> ] <SVN_repository_URL> [ <path> ]
+		[ -I <ignorefile_name> ] [ -A <author_file> ]
+		<SVN_repository_URL> [ <path> ]
 
 
 DESCRIPTION
@@ -71,6 +72,16 @@ When importing incrementally, you might need to edit the .git/svn2git file.
 	syntaxes are similar enough that using the Subversion patterns
 	directly with "-I .gitignore" will almost always just work.)
 
+-A <author_file>::
+	Read a file with lines on the form
+
+	  username User's Full Name <email@addres.org>
+
+	and use "User's Full Name <email@addres.org>" as the GIT
+	author and committer for Subversion commits made by
+	"username". If encountering a commit made by a user not in the
+	list, abort.
+
 -m::
 	Attempt to detect merges based on the commit message. This option
 	will enable default regexes that try to capture the name source
diff --git a/git-svnimport.perl b/git-svnimport.perl
index 0dd9fab9f..75ce8e068 100755
--- a/git-svnimport.perl
+++ b/git-svnimport.perl
@@ -30,7 +30,7 @@ $SIG{'PIPE'}="IGNORE";
 $ENV{'TZ'}="UTC";
 
 our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T,
-    $opt_b,$opt_r,$opt_I,$opt_s,$opt_l,$opt_d,$opt_D);
+    $opt_b,$opt_r,$opt_I,$opt_A,$opt_s,$opt_l,$opt_d,$opt_D);
 
 sub usage() {
 	print STDERR <<END;
@@ -38,12 +38,12 @@ Usage: ${\basename $0}     # fetch/update GIT from SVN
        [-o branch-for-HEAD] [-h] [-v] [-l max_rev]
        [-C GIT_repository] [-t tagname] [-T trunkname] [-b branchname]
        [-d|-D] [-i] [-u] [-r] [-I ignorefilename] [-s start_chg]
-       [-m] [-M regex] [SVN_URL]
+       [-m] [-M regex] [-A author_file] [SVN_URL]
 END
 	exit(1);
 }
 
-getopts("b:C:dDhiI:l:mM:o:rs:t:T:uv") or usage();
+getopts("A:b:C:dDhiI:l:mM:o:rs:t:T:uv") or usage();
 usage if $opt_h;
 
 my $tag_name = $opt_t || "tags";
@@ -68,6 +68,19 @@ if ($opt_M) {
 	push (@mergerx, qr/$opt_M/);
 }
 
+our %users = ();
+if ($opt_A) {
+	die "Cannot open $opt_A\n" unless -f $opt_A;
+	open(my $authors,$opt_A);
+	while(<$authors>) {
+		chomp;
+		next unless /^(\S+)\s+(.+?)\s+<(\S+)>$/;
+		(my $user,my $name,my $email) = ($1,$2,$3);
+		$users{$user} = [$name,$email];
+	}
+	close($authors);
+}
+
 select(STDERR); $|=1; select(STDOUT);
 
 
@@ -485,6 +498,10 @@ sub commit {
 
 	if (not defined $author) {
 		$author_name = $author_email = "unknown";
+	} elsif ($opt_A) {
+		die "User $author is not listed in $opt_A\n"
+		    unless exists $users{$author};
+		($author_name,$author_email) = @{$users{$author}};
 	} elsif ($author =~ /^(.*?)\s+<(.*)>$/) {
 		($author_name, $author_email) = ($1, $2);
 	} else {