svn import: Add direct HTTP access

[git.git] / git-svnimport.perl

diff --git a/git-svnimport.perl b/git-svnimport.perl
index f9318c8..2f89c31 100755 (executable)
--- a/git-svnimport.perl
+++ b/git-svnimport.perl
@@ -5,8 +5,7 @@
 #
 # The basic idea is to pull and analyze SVN changes.
 #
-# Checking out the files is done by a single long-running CVS connection
-# / server process.
+# Checking out the files is done by a single long-running SVN connection.
 #
 # The head revision is on branch "origin" by default.
 # You can change that with the '-o' option.
@@ -26,49 +25,40 @@ use IPC::Open2;
 use SVN::Core;
 use SVN::Ra;
 
-die "Need CVN:COre 1.2.1 or better" if $SVN::Core::VERSION lt "1.2.1";
+die "Need CVN:Core 1.2.1 or better" if $SVN::Core::VERSION lt "1.2.1";
 
 $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_s,$opt_l);
+our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T,$opt_b,$opt_s,$opt_l,$opt_d,$opt_D);
 
 sub usage() {
        print STDERR <<END;
 Usage: ${\basename $0}     # fetch/update GIT from CVS
        [-o branch-for-HEAD] [-h] [-v] [-l max_num_changes]
        [-C GIT_repository] [-t tagname] [-T trunkname] [-b branchname]
-       [-i] [-u] [-s start_chg] [-m] [-M regex] [SVN_URL]
+       [-d|-D] [-i] [-u] [-s start_chg] [-m] [-M regex] [SVN_URL]
 END
        exit(1);
 }
 
-getopts("b:C:hil:mM:o:s:t:T:uv") or usage();
+getopts("b:C:dDhil:mM:o:s:t:T:uv") or usage();
 usage if $opt_h;
 
 my $tag_name = $opt_t || "tags";
 my $trunk_name = $opt_T || "trunk";
 my $branch_name = $opt_b || "branches";
 
-@ARGV <= 1 or usage();
+@ARGV == 1 or @ARGV == 2 or usage();
 
 $opt_o ||= "origin";
+$opt_s ||= 1;
 $opt_l = 100 unless defined $opt_l;
 my $git_tree = $opt_C;
 $git_tree ||= ".";
 
-my $cvs_tree;
-if ($#ARGV == 0) {
-       $cvs_tree = $ARGV[0];
-} elsif (-f 'CVS/Repository') {
-       open my $f, '<', 'CVS/Repository' or 
-           die 'Failed to open CVS/Repository';
-       $cvs_tree = <$f>;
-       chomp $cvs_tree;
-       close $f;
-} else {
-       usage();
-}
+my $svn_url = $ARGV[0];
+my $svn_dir = $ARGV[1];
 
 our @mergerx = ();
 if ($opt_m) {
@@ -117,30 +107,44 @@ sub conn {
 
 sub file {
        my($self,$path,$rev) = @_;
-       my $res;
 
        my ($fh, $name) = tempfile('gitsvn.XXXXXX', 
                    DIR => File::Spec->tmpdir(), UNLINK => 1);
 
        print "... $rev $path ...\n" if $opt_v;
        eval { $self->{'svn'}->get_file($path,$rev,$fh); };
-       if ($@ and $@ !~ /Attempted to get checksum/) {
-           # retry
-           $self->conn();
-               eval { $self->{'svn'}->get_file($path,$rev,$fh); };
-       };
-       return () if $@ and $@ !~ /Attempted to get checksum/;
-       die $@ if $@;
+       if($@) {
+               return undef if $@ =~ /Attempted to get checksum/;
+               die $@;
+       }
        close ($fh);
 
-       return ($name, $res);
+       return $name;
 }
 
-
 package main;
+use URI;
 
-my $svn = SVNconn->new($cvs_tree);
+my $svn = $svn_url;
+$svn .= "/$svn_dir" if defined $svn_dir;
+$svn = SVNconn->new($svn);
 
+my $lwp_ua;
+if($opt_d or $opt_D) {
+       $svn_url = URI->new($svn_url)->canonical;
+       if($opt_D) {
+               $svn_dir =~ s#/*$#/#;
+       } else {
+               $svn_dir = "";
+       }
+       if ($svn_url->scheme eq "http") {
+               use LWP::UserAgent;
+               $lwp_ua = LWP::UserAgent->new(keep_alive => 1, requests_redirectable => []);
+       } else {
+               print STDERR "Warning: not HTTP; turning off direct file access\n";
+               $opt_d=0;
+       }
+}
 
 sub pdate($) {
        my($d) = @_;
@@ -193,7 +197,7 @@ $ENV{GIT_INDEX_FILE} = $git_index;
 my $maxnum = 0;
 my $last_rev = "";
 my $last_branch;
-my $current_rev = $opt_s ? ($opt_s-1) : 0;
+my $current_rev = $opt_s-1;
 unless(-d $git_dir) {
        system("git-init-db");
        die "Cannot init the GIT db at $git_tree: $?\n" if $?;
@@ -254,25 +258,6 @@ EOM
 
 open BRANCHES,">>", "$git_dir/svn2git";
 
-
-## cvsps output:
-#---------------------
-#PatchSet 314
-#Date: 1999/09/18 13:03:59
-#Author: wkoch
-#Branch: STABLE-BRANCH-1-0
-#Ancestor branch: HEAD
-#Tag: (none)
-#Log:
-#    See ChangeLog: Sat Sep 18 13:03:28 CEST 1999  Werner Koch
-#Members:
-#      README:1.57->1.57.2.1
-#      VERSION:1.96->1.96.2.1
-#
-#---------------------
-
-my $state = 0;
-
 sub get_file($$$) {
        my($rev,$branch,$path) = @_;
 
@@ -288,8 +273,30 @@ sub get_file($$$) {
        }
 
        # now get it
-       my ($name, $res) = eval { $svn->file($svnpath,$rev); };
-       return () unless defined $name;
+       my $name;
+       if($opt_d) {
+               my($req,$res);
+
+               # /svn/!svn/bc/2/django/trunk/django-docs/build.py
+               my $url=$svn_url->clone();
+               $url->path($url->path."/!svn/bc/$rev/$svn_dir$svnpath");
+               print "Fetching $url...\n" if $opt_v;
+               $req = HTTP::Request->new(GET => $url);
+               $res = $lwp_ua->request($req);
+               if ($res->is_success) {
+                       my $fh;
+                       ($fh, $name) = tempfile('gitsvn.XXXXXX', 
+                       DIR => File::Spec->tmpdir(), UNLINK => 1);
+                       print $fh $res->content;
+                       close($fh) or die "Could not write $name: $!\n";
+               } else {
+                       return undef if $res->code == 301; # directory?
+                       die $res->status_line." at $url\n";
+               }
+       } else {
+               $name = $svn->file($svnpath,$rev);
+               return undef unless defined $name;
+       }
 
        open my $F, '-|', "git-hash-object", "-w", $name
                or die "Cannot create object: $!\n";