X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;ds=sidebyside;f=git-cvsimport.perl;h=c5bf2d19cda6104f4fa9ade7c1407bb6ab8b5d1e;hb=a990999e0df3d0518a2fef60feb1ec269e36ada6;hp=50f5d9642a17eef42d9a28e36201a808e655f54f;hpb=061303f0b50a648db8e0af23791fc56181f6bf93;p=git.git diff --git a/git-cvsimport.perl b/git-cvsimport.perl index 50f5d9642..c5bf2d19c 100755 --- a/git-cvsimport.perl +++ b/git-cvsimport.perl @@ -29,7 +29,7 @@ use IPC::Open2; $SIG{'PIPE'}="IGNORE"; $ENV{'TZ'}="UTC"; -our($opt_h,$opt_o,$opt_v,$opt_k,$opt_u,$opt_d,$opt_p,$opt_C,$opt_z,$opt_i,$opt_P, $opt_s,$opt_m,$opt_M,$opt_A,$opt_S,$opt_L); +our ($opt_h,$opt_o,$opt_v,$opt_k,$opt_u,$opt_d,$opt_p,$opt_C,$opt_z,$opt_i,$opt_P, $opt_s,$opt_m,$opt_M,$opt_A,$opt_S,$opt_L); my (%conv_author_name, %conv_author_email); sub usage() { @@ -90,15 +90,15 @@ usage if $opt_h; @ARGV <= 1 or usage(); -if($opt_d) { +if ($opt_d) { $ENV{"CVSROOT"} = $opt_d; -} elsif(-f 'CVS/Root') { +} elsif (-f 'CVS/Root') { open my $f, '<', 'CVS/Root' or die 'Failed to open CVS/Root'; $opt_d = <$f>; chomp $opt_d; close $f; $ENV{"CVSROOT"} = $opt_d; -} elsif($ENV{"CVSROOT"}) { +} elsif ($ENV{"CVSROOT"}) { $opt_d = $ENV{"CVSROOT"}; } else { die "CVSROOT needs to be set"; @@ -141,7 +141,7 @@ use File::Temp qw(tempfile); use POSIX qw(strftime dup2); sub new { - my($what,$repo,$subdir) = @_; + my ($what,$repo,$subdir) = @_; $what=ref($what) if ref($what); my $self = {}; @@ -161,24 +161,38 @@ sub new { sub conn { my $self = shift; my $repo = $self->{'fullrep'}; - if($repo =~ s/^:pserver:(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?//) { - my($user,$pass,$serv,$port) = ($1,$2,$3,$4); + if ($repo =~ s/^:pserver(?:([^:]*)):(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?//) { + my ($param,$user,$pass,$serv,$port) = ($1,$2,$3,$4,$5); + + my ($proxyhost,$proxyport); + if ($param && ($param =~ m/proxy=([^;]+)/)) { + $proxyhost = $1; + # Default proxyport, if not specified, is 8080. + $proxyport = 8080; + if ($ENV{"CVS_PROXY_PORT"}) { + $proxyport = $ENV{"CVS_PROXY_PORT"}; + } + if ($param =~ m/proxyport=([^;]+)/) { + $proxyport = $1; + } + } + $user="anonymous" unless defined $user; my $rr2 = "-"; - unless($port) { + unless ($port) { $rr2 = ":pserver:$user\@$serv:$repo"; $port=2401; } my $rr = ":pserver:$user\@$serv:$port$repo"; - unless($pass) { + unless ($pass) { open(H,$ENV{'HOME'}."/.cvspass") and do { # :pserver:cvs@mea.tmt.tele.fi:/cvsroot/zmailer Ah) { + while () { chomp; s/^\/\d+\s+//; my ($w,$p) = split(/\s/,$_,2); - if($w eq $rr or $w eq $rr2) { + if ($w eq $rr or $w eq $rr2) { $pass = $p; last; } @@ -187,15 +201,45 @@ sub conn { } $pass="A" unless $pass; - my $s = IO::Socket::INET->new(PeerHost => $serv, PeerPort => $port); - die "Socket to $serv: $!\n" unless defined $s; + my ($s, $rep); + if ($proxyhost) { + + # Use a HTTP Proxy. Only works for HTTP proxies that + # don't require user authentication + # + # See: http://www.ietf.org/rfc/rfc2817.txt + + $s = IO::Socket::INET->new(PeerHost => $proxyhost, PeerPort => $proxyport); + die "Socket to $proxyhost: $!\n" unless defined $s; + $s->write("CONNECT $serv:$port HTTP/1.1\r\nHost: $serv:$port\r\n\r\n") + or die "Write to $proxyhost: $!\n"; + $s->flush(); + + $rep = <$s>; + + # The answer should look like 'HTTP/1.x 2yy ....' + if (!($rep =~ m#^HTTP/1\.. 2[0-9][0-9]#)) { + die "Proxy connect: $rep\n"; + } + # Skip up to the empty line of the proxy server output + # including the response headers. + while ($rep = <$s>) { + last if (!defined $rep || + $rep eq "\n" || + $rep eq "\r\n"); + } + } else { + $s = IO::Socket::INET->new(PeerHost => $serv, PeerPort => $port); + die "Socket to $serv: $!\n" unless defined $s; + } + $s->write("BEGIN AUTH REQUEST\n$repo\n$user\n$pass\nEND AUTH REQUEST\n") or die "Write to $serv: $!\n"; $s->flush(); - my $rep = <$s>; + $rep = <$s>; - if($rep ne "I LOVE YOU\n") { + if ($rep ne "I LOVE YOU\n") { $rep="" unless $rep; die "AuthReply: $rep\n"; } @@ -227,7 +271,7 @@ sub conn { } } - unless($pid) { + unless ($pid) { $pr->writer(); $pw->reader(); dup2($pw->fileno(),0); @@ -250,7 +294,7 @@ sub conn { $self->{'socketo'}->flush(); chomp(my $rep=$self->readline()); - if($rep !~ s/^Valid-requests\s*//) { + if ($rep !~ s/^Valid-requests\s*//) { $rep="" unless $rep; die "Expected Valid-requests from server, but got: $rep\n"; } @@ -262,14 +306,14 @@ sub conn { } sub readline { - my($self) = @_; + my ($self) = @_; return $self->{'socketi'}->getline(); } sub _file { # Request a file with a given revision. # Trial and error says this is a good way to do it. :-/ - my($self,$fn,$rev) = @_; + my ($self,$fn,$rev) = @_; $self->{'socketo'}->write("Argument -N\n") or return undef; $self->{'socketo'}->write("Argument -P\n") or return undef; # -kk: Linus' version doesn't use it - defaults to off @@ -291,12 +335,12 @@ sub _file { sub _line { # Read a line from the server. # ... except that 'line' may be an entire file. ;-) - my($self, $fh) = @_; + my ($self, $fh) = @_; die "Not in lines" unless defined $self->{'lines'}; my $line; my $res=0; - while(defined($line = $self->readline())) { + while (defined($line = $self->readline())) { # M U gnupg-cvs-rep/AUTHORS # Updated gnupg-cvs-rep/ # /daten/src/rsync/gnupg-cvs-rep/AUTHORS @@ -305,7 +349,7 @@ sub _line { # 0 # ok - if($line =~ s/^(?:Created|Updated) //) { + if ($line =~ s/^(?:Created|Updated) //) { $line = $self->readline(); # path $line = $self->readline(); # Entries line my $mode = $self->readline(); chomp $mode; @@ -316,12 +360,12 @@ sub _line { die "Duh: Filesize $cnt" if $cnt !~ /^\d+$/; $line=""; $res = $self->_fetchfile($fh, $cnt); - } elsif($line =~ s/^ //) { + } elsif ($line =~ s/^ //) { print $fh $line; $res += length($line); - } elsif($line =~ /^M\b/) { + } elsif ($line =~ /^M\b/) { # output, do nothing - } elsif($line =~ /^Mbinary\b/) { + } elsif ($line =~ /^Mbinary\b/) { my $cnt; die "EOF from server after 'Mbinary'" unless defined ($cnt = $self->readline()); chomp $cnt; @@ -330,12 +374,12 @@ sub _line { $res += $self->_fetchfile($fh, $cnt); } else { chomp $line; - if($line eq "ok") { + if ($line eq "ok") { # print STDERR "S: ok (".length($res).")\n"; return $res; - } elsif($line =~ s/^E //) { + } elsif ($line =~ s/^E //) { # print STDERR "S: $line\n"; - } elsif($line =~ /^(Remove-entry|Removed) /i) { + } elsif ($line =~ /^(Remove-entry|Removed) /i) { $line = $self->readline(); # filename $line = $self->readline(); # OK chomp $line; @@ -349,7 +393,7 @@ sub _line { return undef; } sub file { - my($self,$fn,$rev) = @_; + my ($self,$fn,$rev) = @_; my $res; my ($fh, $name) = tempfile('gitcvs.XXXXXX', @@ -373,7 +417,7 @@ sub _fetchfile { my ($self, $fh, $cnt) = @_; my $res = 0; my $bufsize = 1024 * 1024; - while($cnt) { + while ($cnt) { if ($bufsize > $cnt) { $bufsize = $cnt; } @@ -394,7 +438,7 @@ my $cvs = CVSconn->new($opt_d, $cvs_tree); sub pdate($) { - my($d) = @_; + my ($d) = @_; m#(\d{2,4})/(\d\d)/(\d\d)\s(\d\d):(\d\d)(?::(\d\d))?# or die "Unparseable date: $d\n"; my $y=$1; $y-=1900 if $y>1900; @@ -402,22 +446,22 @@ sub pdate($) { } sub pmode($) { - my($mode) = @_; + my ($mode) = @_; my $m = 0; my $mm = 0; my $um = 0; for my $x(split(//,$mode)) { - if($x eq ",") { + if ($x eq ",") { $m |= $mm&$um; $mm = 0; $um = 0; - } elsif($x eq "u") { $um |= 0700; - } elsif($x eq "g") { $um |= 0070; - } elsif($x eq "o") { $um |= 0007; - } elsif($x eq "r") { $mm |= 0444; - } elsif($x eq "w") { $mm |= 0222; - } elsif($x eq "x") { $mm |= 0111; - } elsif($x eq "=") { # do nothing + } elsif ($x eq "u") { $um |= 0700; + } elsif ($x eq "g") { $um |= 0070; + } elsif ($x eq "o") { $um |= 0007; + } elsif ($x eq "r") { $mm |= 0444; + } elsif ($x eq "w") { $mm |= 0222; + } elsif ($x eq "x") { $mm |= 0111; + } elsif ($x eq "=") { # do nothing } else { die "Unknown mode: $mode\n"; } } @@ -441,7 +485,7 @@ sub get_headref ($$) { my $git_dir = shift; my $f = "$git_dir/refs/heads/$name"; - if(open(my $fh, $f)) { + if (open(my $fh, $f)) { chomp(my $r = <$fh>); is_sha1($r) or die "Cannot get head id for $name ($r): $!"; return $r; @@ -467,13 +511,8 @@ my $orig_git_index; $orig_git_index = $ENV{GIT_INDEX_FILE} if exists $ENV{GIT_INDEX_FILE}; my %index; # holds filenames of one index per branch -$index{$opt_o} = tmpnam(); - -$ENV{GIT_INDEX_FILE} = $index{$opt_o}; -system("git-read-tree", $opt_o); -die "read-tree failed: $?\n" if $?; -unless(-d $git_dir) { +unless (-d $git_dir) { system("git-init-db"); die "Cannot init the GIT db at $git_tree: $?\n" if $?; system("git-read-tree"); @@ -492,38 +531,25 @@ unless(-d $git_dir) { chomp ($last_branch = ); $last_branch = basename($last_branch); close(F); - unless($last_branch) { + unless ($last_branch) { warn "Cannot read the last branch name: $! -- assuming 'master'\n"; $last_branch = "master"; } $orig_branch = $last_branch; $tip_at_start = `git-rev-parse --verify HEAD`; - # populate index - unless ($index{$last_branch}) { - $index{$last_branch} = tmpnam(); - } - $ENV{GIT_INDEX_FILE} = $index{$last_branch}; - system('git-read-tree', $last_branch); - die "read-tree failed: $?\n" if $?; - # Get the last import timestamps - opendir(D,"$git_dir/refs/heads"); - while(defined(my $head = readdir(D))) { - next if $head =~ /^\./; - open(F,"$git_dir/refs/heads/$head") - or die "Bad head branch: $head: $!\n"; - chomp(my $ftag = ); - close(F); - open(F,"git-cat-file commit $ftag |"); - while() { - next unless /^author\s.*\s(\d+)\s[-+]\d{4}$/; - $branch_date{$head} = $1; - last; - } - close(F); + my $fmt = '($ref, $author) = (%(refname), %(author));'; + open(H, "git-for-each-ref --perl --format='$fmt' refs/heads |") or + die "Cannot run git-for-each-ref: $!\n"; + while (defined(my $entry = )) { + my ($ref, $author); + eval($entry) || die "cannot eval refs list: $@"; + my ($head) = ($ref =~ m|^refs/heads/(.*)|); + $author =~ /^.*\s(\d+)\s[-+]\d{4}$/; + $branch_date{$head} = $1; } - closedir(D); + close(H); } -d $git_dir @@ -546,7 +572,7 @@ unless ($opt_P) { print "Running cvsps...\n" if $opt_v; my $pid = open(CVSPS,"-|"); die "Cannot fork: $!\n" unless defined $pid; - unless($pid) { + unless ($pid) { my @opt; @opt = split(/,/,$opt_p) if defined $opt_p; unshift @opt, '-z', $opt_z if defined $opt_z; @@ -616,13 +642,34 @@ sub write_tree () { return $tree; } -my($patchset,$date,$author_name,$author_email,$branch,$ancestor,$tag,$logmsg); -my(@old,@new,@skipped,%ignorebranch); +my ($patchset,$date,$author_name,$author_email,$branch,$ancestor,$tag,$logmsg); +my (@old,@new,@skipped,%ignorebranch); # commits that cvsps cannot place anywhere... $ignorebranch{'#CVSPS_NO_BRANCH'} = 1; sub commit { + if ($branch eq $opt_o && !$index{branch} && !get_headref($branch, $git_dir)) { + # looks like an initial commit + # use the index primed by git-init-db + $ENV{GIT_INDEX_FILE} = '.git/index'; + $index{$branch} = '.git/index'; + } else { + # use an index per branch to speed up + # imports of projects with many branches + unless ($index{$branch}) { + $index{$branch} = tmpnam(); + $ENV{GIT_INDEX_FILE} = $index{$branch}; + if ($ancestor) { + system("git-read-tree", $ancestor); + } else { + system("git-read-tree", $branch); + } + die "read-tree failed: $?\n" if $?; + } + } + $ENV{GIT_INDEX_FILE} = $index{$branch}; + update_index(@old, @new); @old = @new = (); my $tree = write_tree(); @@ -637,7 +684,7 @@ sub commit { foreach my $rx (@mergerx) { next unless $logmsg =~ $rx && $1; my $mparent = $1 eq 'HEAD' ? $opt_o : $1; - if(my $sha1 = get_headref($mparent, $git_dir)) { + if (my $sha1 = get_headref($mparent, $git_dir)) { push @commit_args, '-p', $mparent; print "Merge parent branch: $mparent\n" if $opt_v; } @@ -678,9 +725,9 @@ sub commit { system("git-update-ref refs/heads/$branch $cid") == 0 or die "Cannot write branch $branch for update: $!\n"; - if($tag) { - my($in, $out) = ('',''); - my($xtag) = $tag; + if ($tag) { + my ($in, $out) = ('',''); + my ($xtag) = $tag; $xtag =~ s/\s+\*\*.*$//; # Remove stuff like ** INVALID ** and ** FUNKY ** $xtag =~ tr/_/\./ if ( $opt_u ); $xtag =~ s/[\/]/$opt_s/g; @@ -715,25 +762,25 @@ sub commit { }; my $commitcount = 1; -while() { +while () { chomp; - if($state == 0 and /^-+$/) { + if ($state == 0 and /^-+$/) { $state = 1; - } elsif($state == 0) { + } elsif ($state == 0) { $state = 1; redo; - } elsif(($state==0 or $state==1) and s/^PatchSet\s+//) { + } elsif (($state==0 or $state==1) and s/^PatchSet\s+//) { $patchset = 0+$_; $state=2; - } elsif($state == 2 and s/^Date:\s+//) { + } elsif ($state == 2 and s/^Date:\s+//) { $date = pdate($_); - unless($date) { + unless ($date) { print STDERR "Could not parse date: $_\n"; $state=0; next; } $state=3; - } elsif($state == 3 and s/^Author:\s+//) { + } elsif ($state == 3 and s/^Author:\s+//) { s/\s+$//; if (/^(.*?)\s+<(.*)>/) { ($author_name, $author_email) = ($1, $2); @@ -744,34 +791,34 @@ while() { $author_name = $author_email = $_; } $state = 4; - } elsif($state == 4 and s/^Branch:\s+//) { + } elsif ($state == 4 and s/^Branch:\s+//) { s/\s+$//; s/[\/]/$opt_s/g; $branch = $_; $state = 5; - } elsif($state == 5 and s/^Ancestor branch:\s+//) { + } elsif ($state == 5 and s/^Ancestor branch:\s+//) { s/\s+$//; $ancestor = $_; $ancestor = $opt_o if $ancestor eq "HEAD"; $state = 6; - } elsif($state == 5) { + } elsif ($state == 5) { $ancestor = undef; $state = 6; redo; - } elsif($state == 6 and s/^Tag:\s+//) { + } elsif ($state == 6 and s/^Tag:\s+//) { s/\s+$//; - if($_ eq "(none)") { + if ($_ eq "(none)") { $tag = undef; } else { $tag = $_; } $state = 7; - } elsif($state == 7 and /^Log:/) { + } elsif ($state == 7 and /^Log:/) { $logmsg = ""; $state = 8; - } elsif($state == 8 and /^Members:/) { + } elsif ($state == 8 and /^Members:/) { $branch = $opt_o if $branch eq "HEAD"; - if(defined $branch_date{$branch} and $branch_date{$branch} >= $date) { + if (defined $branch_date{$branch} and $branch_date{$branch} >= $date) { # skip print "skip patchset $patchset: $date before $branch_date{$branch}\n" if $opt_v; $state = 11; @@ -782,17 +829,17 @@ while() { $state = 11; next; } - if($ancestor) { - if($ancestor eq $branch) { + if ($ancestor) { + if ($ancestor eq $branch) { print STDERR "Branch $branch erroneously stems from itself -- changed ancestor to $opt_o\n"; $ancestor = $opt_o; } - if(-f "$git_dir/refs/heads/$branch") { + if (-f "$git_dir/refs/heads/$branch") { print STDERR "Branch $branch already exists!\n"; $state=11; next; } - unless(open(H,"$git_dir/refs/heads/$ancestor")) { + unless (open(H,"$git_dir/refs/heads/$ancestor")) { print STDERR "Branch $ancestor does not exist!\n"; $ignorebranch{$branch} = 1; $state=11; @@ -800,7 +847,7 @@ while() { } chomp(my $id = ); close(H); - unless(open(H,"> $git_dir/refs/heads/$branch")) { + unless (open(H,"> $git_dir/refs/heads/$branch")) { print STDERR "Could not create branch $branch: $!\n"; $ignorebranch{$branch} = 1; $state=11; @@ -811,35 +858,11 @@ while() { close(H) or die "Could not write branch $branch: $!"; } - if(($ancestor || $branch) ne $last_branch) { - print "Switching from $last_branch to $branch\n" if $opt_v; - unless ($index{$branch}) { - $index{$branch} = tmpnam(); - $ENV{GIT_INDEX_FILE} = $index{$branch}; - system("git-read-tree", $branch); - die "read-tree failed: $?\n" if $?; - } - # just in case - $ENV{GIT_INDEX_FILE} = $index{$branch}; - if ($ancestor) { - print "have ancestor $ancestor" if $opt_v; - system("git-read-tree", $ancestor); - die "read-tree failed: $?\n" if $?; - } - } else { - # just in case - unless ($index{$branch}) { - $index{$branch} = tmpnam(); - $ENV{GIT_INDEX_FILE} = $index{$branch}; - system("git-read-tree", $branch); - die "read-tree failed: $?\n" if $?; - } - } $last_branch = $branch if $branch ne $last_branch; $state = 9; - } elsif($state == 8) { + } elsif ($state == 8) { $logmsg .= "$_\n"; - } elsif($state == 9 and /^\s+(.+?):(INITIAL|\d+(?:\.\d+)+)->(\d+(?:\.\d+)+)\s*$/) { + } elsif ($state == 9 and /^\s+(.+?):(INITIAL|\d+(?:\.\d+)+)->(\d+(?:\.\d+)+)\s*$/) { # VERSION:1.96->1.96.2.1 my $init = ($2 eq "INITIAL"); my $fn = $1; @@ -852,7 +875,7 @@ while() { } print "Fetching $fn v $rev\n" if $opt_v; my ($tmpname, $size) = $cvs->file($fn,$rev); - if($size == -1) { + if ($size == -1) { push(@old,$fn); print "Drop $fn\n" if $opt_v; } else { @@ -870,14 +893,14 @@ while() { push(@new,[$mode, $sha, $fn]); # may be resurrected! } unlink($tmpname); - } elsif($state == 9 and /^\s+(.+?):\d+(?:\.\d+)+->(\d+(?:\.\d+)+)\(DEAD\)\s*$/) { + } elsif ($state == 9 and /^\s+(.+?):\d+(?:\.\d+)+->(\d+(?:\.\d+)+)\(DEAD\)\s*$/) { my $fn = $1; $fn =~ s#^/+##; push(@old,$fn); print "Delete $fn\n" if $opt_v; - } elsif($state == 9 and /^\s*$/) { + } elsif ($state == 9 and /^\s*$/) { $state = 10; - } elsif(($state == 9 or $state == 10) and /^-+$/) { + } elsif (($state == 9 or $state == 10) and /^-+$/) { $commitcount++; if ($opt_L && $commitcount > $opt_L) { last; @@ -887,18 +910,30 @@ while() { system("git repack -a -d"); } $state = 1; - } elsif($state == 11 and /^-+$/) { + } elsif ($state == 11 and /^-+$/) { $state = 1; - } elsif(/^-+$/) { # end of unknown-line processing + } elsif (/^-+$/) { # end of unknown-line processing $state = 1; - } elsif($state != 11) { # ignore stuff when skipping + } elsif ($state != 11) { # ignore stuff when skipping print "* UNKNOWN LINE * $_\n"; } } commit() if $branch and $state != 11; +# The heuristic of repacking every 1024 commits can leave a +# lot of unpacked data. If there is more than 1MB worth of +# not-packed objects, repack once more. +my $line = `git-count-objects`; +if ($line =~ /^(\d+) objects, (\d+) kilobytes$/) { + my ($n_objects, $kb) = ($1, $2); + 1024 < $kb + and system("git repack -a -d"); +} + foreach my $git_index (values %index) { - unlink($git_index); + if ($git_index ne '.git/index') { + unlink($git_index); + } } if (defined $orig_git_index) { @@ -908,7 +943,7 @@ if (defined $orig_git_index) { } # Now switch back to the branch we were in before all of this happened -if($orig_branch) { +if ($orig_branch) { print "DONE.\n" if $opt_v; if ($opt_i) { exit 0;