use strict;
use warnings;
use Getopt::Std;
+use File::Copy;
use File::Spec;
use File::Temp qw(tempfile);
use File::Path qw(mkpath);
$ENV{'TZ'}="UTC";
our($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_A,$opt_s,$opt_l,$opt_d,$opt_D);
+ $opt_b,$opt_r,$opt_I,$opt_A,$opt_s,$opt_l,$opt_d,$opt_D,$opt_S,$opt_F,
+ $opt_P,$opt_R);
sub usage() {
print STDERR <<END;
Usage: ${\basename $0} # fetch/update GIT from SVN
- [-o branch-for-HEAD] [-h] [-v] [-l max_rev]
+ [-o branch-for-HEAD] [-h] [-v] [-l max_rev] [-R repack_each_revs]
[-C GIT_repository] [-t tagname] [-T trunkname] [-b branchname]
[-d|-D] [-i] [-u] [-r] [-I ignorefilename] [-s start_chg]
- [-m] [-M regex] [-A author_file] [SVN_URL]
+ [-m] [-M regex] [-A author_file] [-S] [-F] [-P project_name] [SVN_URL]
END
exit(1);
}
-getopts("A:b:C:dDhiI:l:mM:o:rs:t:T:uv") or usage();
+getopts("A:b:C:dDFhiI:l:mM:o:rs:t:T:SP:R: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";
+my $project_name = $opt_P || "";
+$project_name = "/" . $project_name if ($project_name);
+my $repack_after = $opt_R || 1000;
@ARGV == 1 or @ARGV == 2 or usage();
our @mergerx = ();
if ($opt_m) {
- @mergerx = ( qr/\W(?:from|of|merge|merging|merged) (\w+)/i );
+ my $branch_esc = quotemeta ($branch_name);
+ my $trunk_esc = quotemeta ($trunk_name);
+ @mergerx =
+ (
+ qr!\b(?:merg(?:ed?|ing))\b.*?\b((?:(?<=$branch_esc/)[\w\.\-]+)|(?:$trunk_esc))\b!i,
+ qr!\b(?:from|of)\W+((?:(?<=$branch_esc/)[\w\.\-]+)|(?:$trunk_esc))\b!i,
+ qr!\b(?:from|of)\W+(?:the )?([\w\.\-]+)[-\s]branch\b!i
+ );
}
if ($opt_M) {
- push (@mergerx, qr/$opt_M/);
+ unshift (@mergerx, qr/$opt_M/);
}
+# Absolutize filename now, since we will have chdir'ed by the time we
+# get around to opening it.
+$opt_A = File::Spec->rel2abs($opt_A) if $opt_A;
+
our %users = ();
-if ($opt_A) {
- die "Cannot open $opt_A\n" unless -f $opt_A;
- open(my $authors,$opt_A);
+our $users_file = undef;
+sub read_users($) {
+ $users_file = File::Spec->rel2abs(@_);
+ die "Cannot open $users_file\n" unless -f $users_file;
+ open(my $authors,$users_file);
while(<$authors>) {
chomp;
- next unless /^(\S+)\s+(.+?)\s+<(\S+)>$/;
+ next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/;
(my $user,my $name,my $email) = ($1,$2,$3);
$users{$user} = [$name,$email];
}
use File::Spec;
use File::Temp qw(tempfile);
use POSIX qw(strftime dup2);
+use Fcntl qw(SEEK_SET);
sub new {
my($what,$repo) = @_;
print "... $rev $path ...\n" if $opt_v;
my (undef, $properties);
+ my $pool = SVN::Pool->new();
+ $path =~ s#^/*##;
eval { (undef, $properties)
- = $self->{'svn'}->get_file($path,$rev,$fh); };
+ = $self->{'svn'}->get_file($path,$rev,$fh,$pool); };
+ $pool->clear;
if($@) {
return undef if $@ =~ /Attempted to get checksum/;
die $@;
}
my $mode;
if (exists $properties->{'svn:executable'}) {
- $mode = '0755';
+ $mode = '100755';
+ } elsif (exists $properties->{'svn:special'}) {
+ my ($special_content, $filesize);
+ $filesize = tell $fh;
+ seek $fh, 0, SEEK_SET;
+ read $fh, $special_content, $filesize;
+ if ($special_content =~ s/^link //) {
+ $mode = '120000';
+ seek $fh, 0, SEEK_SET;
+ truncate $fh, 0;
+ print $fh $special_content;
+ } else {
+ die "unexpected svn:special file encountered";
+ }
} else {
- $mode = '0644';
+ $mode = '100644';
}
close ($fh);
my($self,$path,$rev) = @_;
print "... $rev $path ...\n" if $opt_v;
+ $path =~ s#^/*##;
my (undef,undef,$properties)
= $self->{'svn'}->get_dir($path,$rev,undef);
if (exists $properties->{'svn:ignore'}) {
}
}
+sub dir_list {
+ my($self,$path,$rev) = @_;
+ $path =~ s#^/*##;
+ my ($dirents,undef,$properties)
+ = $self->{'svn'}->get_dir($path,$rev,undef);
+ return $dirents;
+}
+
package main;
use URI;
my $last_branch;
my $current_rev = $opt_s || 1;
unless(-d $git_dir) {
- system("git-init-db");
+ system("git-init");
die "Cannot init the GIT db at $git_tree: $?\n" if $?;
system("git-read-tree");
die "Cannot init an empty tree: $?\n" if $?;
-d $git_dir
or die "Could not create git subdir ($git_dir).\n";
+my $default_authors = "$git_dir/svn-authors";
+if ($opt_A) {
+ read_users($opt_A);
+ copy($opt_A,$default_authors) or die "Copy failed: $!";
+} else {
+ read_users($default_authors) if -f $default_authors;
+}
+
open BRANCHES,">>", "$git_dir/svn2git";
-sub node_kind($$$) {
- my ($branch, $path, $revision) = @_;
+sub node_kind($$) {
+ my ($svnpath, $revision) = @_;
my $pool=SVN::Pool->new;
- my $kind = $svn->{'svn'}->check_path(revert_split_path($branch,$path),$revision,$pool);
+ $svnpath =~ s#^/*##;
+ my $kind = $svn->{'svn'}->check_path($svnpath,$revision,$pool);
$pool->clear;
return $kind;
}
-sub revert_split_path($$) {
- my($branch,$path) = @_;
-
- my $svnpath;
- $path = "" if $path eq "/"; # this should not happen, but ...
- if($branch eq "/") {
- $svnpath = "$trunk_name/$path";
- } elsif($branch =~ m#^/#) {
- $svnpath = "$tag_name$branch/$path";
- } else {
- $svnpath = "$branch_name/$branch/$path";
- }
-
- $svnpath =~ s#/+$##;
- return $svnpath;
-}
-
sub get_file($$$) {
- my($rev,$branch,$path) = @_;
-
- my $svnpath = revert_split_path($branch,$path);
+ my($svnpath,$rev,$path) = @_;
# now get it
my ($name,$mode);
}
sub get_ignore($$$$$) {
- my($new,$old,$rev,$branch,$path) = @_;
+ my($new,$old,$rev,$path,$svnpath) = @_;
return unless $opt_I;
- my $svnpath = revert_split_path($branch,$path);
my $name = $svn->ignore("$svnpath",$rev);
if ($path eq '/') {
$path = $opt_I;
close $F;
unlink $name;
push(@$new,['0644',$sha,$path]);
- } else {
+ } elsif (defined $old) {
push(@$old,$path);
}
}
+sub project_path($$)
+{
+ my ($path, $project) = @_;
+
+ $path = "/".$path unless ($path =~ m#^\/#) ;
+ return $1 if ($path =~ m#^$project\/(.*)$#);
+
+ $path =~ s#\.#\\\.#g;
+ $path =~ s#\+#\\\+#g;
+ return "/" if ($project =~ m#^$path.*$#);
+
+ return undef;
+}
+
sub split_path($$) {
my($rev,$path) = @_;
my $branch;
print STDERR "$rev: Unrecognized path: $path\n" unless (defined $no_error{$path});
return ()
}
- $path = "/" if $path eq "";
+ if ($path eq "") {
+ $path = "/";
+ } elsif ($project_name) {
+ $path = project_path($path, $project_name);
+ }
return ($branch,$path);
}
return $therev;
}
+sub expand_svndir($$$);
+
+sub expand_svndir($$$)
+{
+ my ($svnpath, $rev, $path) = @_;
+ my @list;
+ get_ignore(\@list, undef, $rev, $path, $svnpath);
+ my $dirents = $svn->dir_list($svnpath, $rev);
+ foreach my $p(keys %$dirents) {
+ my $kind = node_kind($svnpath.'/'.$p, $rev);
+ if ($kind eq $SVN::Node::file) {
+ my $f = get_file($svnpath.'/'.$p, $rev, $path.'/'.$p);
+ push(@list, $f) if $f;
+ } elsif ($kind eq $SVN::Node::dir) {
+ push(@list,
+ expand_svndir($svnpath.'/'.$p, $rev, $path.'/'.$p));
+ }
+ }
+ return @list;
+}
+
sub copy_path($$$$$$$$) {
# Somebody copied a whole subdirectory.
# We need to find the index entries from the old version which the
my($newrev,$newbranch,$path,$oldpath,$rev,$node_kind,$new,$parents) = @_;
my($srcbranch,$srcpath) = split_path($rev,$oldpath);
- unless(defined $srcbranch) {
- print "Path not found when copying from $oldpath @ $rev\n";
+ unless(defined $srcbranch && defined $srcpath) {
+ print "Path not found when copying from $oldpath @ $rev.\n".
+ "Will try to copy from original SVN location...\n"
+ if $opt_v;
+ push (@$new, expand_svndir($oldpath, $rev, $path));
return;
}
my $therev = branch_rev($srcbranch, $rev);
}
print "$newrev:$newbranch:$path: copying from $srcbranch:$srcpath @ $rev\n" if $opt_v;
if ($node_kind eq $SVN::Node::dir) {
- $srcpath =~ s#/*$#/#;
+ $srcpath =~ s#/*$#/#;
}
my $pid = open my $f,'-|';
sub commit {
my($branch, $changed_paths, $revision, $author, $date, $message) = @_;
- my($author_name,$author_email,$dest);
+ my($committer_name,$committer_email,$dest);
+ my($author_name,$author_email);
my(@old,@new,@parents);
- if (not defined $author) {
- $author_name = $author_email = "unknown";
- } elsif ($opt_A) {
- die "User $author is not listed in $opt_A\n"
+ if (not defined $author or $author eq "") {
+ $committer_name = $committer_email = "unknown";
+ } elsif (defined $users_file) {
+ die "User $author is not listed in $users_file\n"
unless exists $users{$author};
- ($author_name,$author_email) = @{$users{$author}};
+ ($committer_name,$committer_email) = @{$users{$author}};
} elsif ($author =~ /^(.*?)\s+<(.*)>$/) {
- ($author_name, $author_email) = ($1, $2);
+ ($committer_name, $committer_email) = ($1, $2);
} else {
$author =~ s/^<(.*)>$/$1/;
- $author_name = $author_email = $author;
+ $committer_name = $committer_email = $author;
}
+
+ if ($opt_F && $message =~ /From:\s+(.*?)\s+<(.*)>\s*\n/) {
+ ($author_name, $author_email) = ($1, $2);
+ print "Author from From: $1 <$2>\n" if ($opt_v);;
+ } elsif ($opt_S && $message =~ /Signed-off-by:\s+(.*?)\s+<(.*)>\s*\n/) {
+ ($author_name, $author_email) = ($1, $2);
+ print "Author from Signed-off-by: $1 <$2>\n" if ($opt_v);;
+ } else {
+ $author_name = $committer_name;
+ $author_email = $committer_email;
+ }
+
$date = pdate($date);
my $tag;
if(defined $oldpath) {
my $p;
($parent,$p) = split_path($revision,$oldpath);
- if($parent eq "/") {
- $parent = $opt_o;
- } else {
- $parent =~ s#^/##; # if it's a tag
+ if(defined $parent) {
+ if($parent eq "/") {
+ $parent = $opt_o;
+ } else {
+ $parent =~ s#^/##; # if it's a tag
+ }
}
} else {
$parent = undef;
push(@old,$path); # remove any old stuff
}
if(($action->[0] eq "A") || ($action->[0] eq "R")) {
- my $node_kind = node_kind($branch,$path,$revision);
- if($action->[1]) {
- copy_path($revision,$branch,$path,$action->[1],$action->[2],$node_kind,\@new,\@parents);
- } elsif ($node_kind eq $SVN::Node::file) {
- my $f = get_file($revision,$branch,$path);
+ my $node_kind = node_kind($action->[3], $revision);
+ if ($node_kind eq $SVN::Node::file) {
+ my $f = get_file($action->[3],
+ $revision, $path);
if ($f) {
push(@new,$f) if $f;
} else {
print STDERR "$revision: $branch: could not fetch '$opath'\n";
}
} elsif ($node_kind eq $SVN::Node::dir) {
- get_ignore(\@new, \@old, $revision,
- $branch,$path);
+ if($action->[1]) {
+ copy_path($revision, $branch,
+ $path, $action->[1],
+ $action->[2], $node_kind,
+ \@new, \@parents);
+ } else {
+ get_ignore(\@new, \@old, $revision,
+ $path, $action->[3]);
+ }
}
} elsif ($action->[0] eq "D") {
push(@old,$path);
} elsif ($action->[0] eq "M") {
- my $node_kind = node_kind($branch,$path,$revision);
+ my $node_kind = node_kind($action->[3], $revision);
if ($node_kind eq $SVN::Node::file) {
- my $f = get_file($revision,$branch,$path);
+ my $f = get_file($action->[3],
+ $revision, $path);
push(@new,$f) if $f;
} elsif ($node_kind eq $SVN::Node::dir) {
get_ignore(\@new, \@old, $revision,
- $branch,$path);
+ $path, $action->[3]);
}
} else {
die "$revision: unknown action '".$action->[0]."' for $path\n";
"GIT_AUTHOR_NAME=$author_name",
"GIT_AUTHOR_EMAIL=$author_email",
"GIT_AUTHOR_DATE=".strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date)),
- "GIT_COMMITTER_NAME=$author_name",
- "GIT_COMMITTER_EMAIL=$author_email",
+ "GIT_COMMITTER_NAME=$committer_name",
+ "GIT_COMMITTER_EMAIL=$committer_email",
"GIT_COMMITTER_DATE=".strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date)),
"git-commit-tree", $tree,@par);
die "Cannot exec git-commit-tree: $!\n";
print $out ("object $cid\n".
"type commit\n".
"tag $dest\n".
- "tagger $author_name <$author_email>\n") and
+ "tagger $committer_name <$committer_email> 0 +0000\n") and
close($out)
or die "Cannot create tag object $dest: $!\n";
while(my($path,$action) = each %$changed_paths) {
($branch,$path) = split_path($revision,$path);
next if not defined $branch;
+ next if not defined $path;
$done{$branch}{$path} = $action;
}
while(($branch,$changed_paths) = each %done) {
$opt_l = $svn->{'maxrev'} if not defined $opt_l or $opt_l > $svn->{'maxrev'};
-if ($svn->{'maxrev'} < $current_rev) {
+if ($opt_l < $current_rev) {
print "Up to date: no new revisions to fetch!\n" if $opt_v;
unlink("$git_dir/SVN2GIT_HEAD");
exit;
}
-print "Fetching from $current_rev to $opt_l ...\n" if $opt_v;
+print "Processing from $current_rev to $opt_l ...\n" if $opt_v;
+
+my $from_rev;
+my $to_rev = $current_rev - 1;
-my $pool=SVN::Pool->new;
-$svn->{'svn'}->get_log("/",$current_rev,$opt_l,0,1,1,\&commit_all,$pool);
-$pool->clear;
+while ($to_rev < $opt_l) {
+ $from_rev = $to_rev + 1;
+ $to_rev = $from_rev + $repack_after;
+ $to_rev = $opt_l if $opt_l < $to_rev;
+ print "Fetching from $from_rev to $to_rev ...\n" if $opt_v;
+ my $pool=SVN::Pool->new;
+ $svn->{'svn'}->get_log("/",$from_rev,$to_rev,0,1,1,\&commit_all,$pool);
+ $pool->clear;
+ my $pid = fork();
+ die "Fork: $!\n" unless defined $pid;
+ unless($pid) {
+ exec("git-repack", "-d")
+ or die "Cannot repack: $!\n";
+ }
+ waitpid($pid, 0);
+}
unlink($git_index);