git-commit-vandalism/git-cvsimport.perl

1010 lines
26 KiB
Plaintext
Raw Normal View History

2005-06-28 16:48:40 +02:00
#!/usr/bin/perl -w
2005-06-28 16:48:40 +02:00
# This tool is copyright (c) 2005, Matthias Urlichs.
# It is released under the Gnu Public License, version 2.
#
# The basic idea is to aggregate CVS check-ins into related changes.
# Fortunately, "cvsps" does that for us; all we have to do is to parse
# its output.
#
# Checking out the files is done by a single long-running CVS connection
# / server process.
#
# The head revision is on branch "origin" by default.
# You can change that with the '-o' option.
use strict;
use warnings;
use Getopt::Std;
use File::Spec;
use File::Temp qw(tempfile tmpnam);
2005-06-28 16:48:40 +02:00
use File::Path qw(mkpath);
use File::Basename qw(basename dirname);
use Time::Local;
2005-06-28 19:49:19 +02:00
use IO::Socket;
use IO::Pipe;
use POSIX qw(strftime dup2 ENOENT);
use IPC::Open2;
2005-06-28 16:48:40 +02:00
$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, $opt_a, $opt_r);
my (%conv_author_name, %conv_author_email);
2005-06-28 16:48:40 +02:00
sub usage(;$) {
my $msg = shift;
print(STDERR "Error: $msg\n") if $msg;
2005-06-28 16:48:40 +02:00
print STDERR <<END;
2005-06-28 19:49:19 +02:00
Usage: ${\basename $0} # fetch/update GIT from CVS
[-o branch-for-HEAD] [-h] [-v] [-d CVSROOT] [-A author-conv-file]
[-p opts-for-cvsps] [-P file] [-C GIT_repository] [-z fuzz] [-i] [-k]
[-u] [-s subst] [-a] [-m] [-M regex] [-S regex] [-L commitlimit]
[-r remote] [CVS_module]
2005-06-28 16:48:40 +02:00
END
exit(1);
}
sub read_author_info($) {
my ($file) = @_;
my $user;
open my $f, '<', "$file" or die("Failed to open $file: $!\n");
while (<$f>) {
# Expected format is this:
# exon=Andreas Ericsson <ae@op5.se>
if (m/^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/) {
$user = $1;
$conv_author_name{$user} = $2;
$conv_author_email{$user} = $3;
}
# However, we also read from CVSROOT/users format
# to ease migration.
elsif (/^(\w+):(['"]?)(.+?)\2\s*$/) {
my $mapped;
($user, $mapped) = ($1, $3);
if ($mapped =~ /^\s*(.*?)\s*<(.*)>\s*$/) {
$conv_author_name{$user} = $1;
$conv_author_email{$user} = $2;
}
elsif ($mapped =~ /^<?(.*)>?$/) {
$conv_author_name{$user} = $user;
$conv_author_email{$user} = $1;
}
}
# NEEDSWORK: Maybe warn on unrecognized lines?
}
close ($f);
}
sub write_author_info($) {
my ($file) = @_;
open my $f, '>', $file or
die("Failed to open $file for writing: $!");
foreach (keys %conv_author_name) {
print $f "$_=$conv_author_name{$_} <$conv_author_email{$_}>\n";
}
close ($f);
}
# convert getopts specs for use by git config
sub read_repo_config {
# Split the string between characters, unless there is a ':'
# So "abc:de" becomes ["a", "b", "c:", "d", "e"]
my @opts = split(/ *(?!:)/, shift);
foreach my $o (@opts) {
my $key = $o;
$key =~ s/://g;
my $arg = 'git config';
$arg .= ' --bool' if ($o !~ /:$/);
chomp(my $tmp = `$arg --get cvsimport.$key`);
if ($tmp && !($arg =~ /--bool/ && $tmp eq 'false')) {
no strict 'refs';
my $opt_name = "opt_" . $key;
if (!$$opt_name) {
$$opt_name = $tmp;
}
}
}
}
my $opts = "haivmkuo:d:p:r:C:z:s:M:P:A:S:L:";
read_repo_config($opts);
getopts($opts) or usage();
2005-06-28 16:48:40 +02:00
usage if $opt_h;
if (@ARGV == 0) {
chomp(my $module = `git config --get cvsimport.module`);
push(@ARGV, $module) if $? == 0;
}
@ARGV <= 1 or usage("You can't specify more than one CVS module");
2005-06-28 16:48:40 +02:00
if ($opt_d) {
2005-06-28 19:49:19 +02:00
$ENV{"CVSROOT"} = $opt_d;
} 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"}) {
2005-06-28 19:49:19 +02:00
$opt_d = $ENV{"CVSROOT"};
} else {
usage("CVSROOT needs to be set");
2005-06-28 19:49:19 +02:00
}
$opt_s ||= "-";
$opt_a ||= 0;
my $git_tree = $opt_C;
2005-06-28 19:49:19 +02:00
$git_tree ||= ".";
my $remote;
if (defined $opt_r) {
$remote = 'refs/remotes/' . $opt_r;
$opt_o ||= "master";
} else {
$opt_o ||= "origin";
$remote = 'refs/heads';
}
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 $f;
} else {
usage("CVS module has to be specified");
}
our @mergerx = ();
if ($opt_m) {
@mergerx = ( qr/\b(?:from|of|merge|merging|merged) (\w+)/i );
}
if ($opt_M) {
push (@mergerx, qr/$opt_M/);
}
# Remember UTC of our starting time
# we'll want to avoid importing commits
# that are too recent
our $starttime = time();
2005-06-28 16:48:40 +02:00
select(STDERR); $|=1; select(STDOUT);
package CVSconn;
# Basic CVS dialog.
2005-06-28 19:49:19 +02:00
# We're only interested in connecting and downloading, so ...
2005-06-28 16:48:40 +02:00
use File::Spec;
use File::Temp qw(tempfile);
2005-06-28 19:58:40 +02:00
use POSIX qw(strftime dup2);
2005-06-28 16:48:40 +02:00
sub new {
my ($what,$repo,$subdir) = @_;
2005-06-28 16:48:40 +02:00
$what=ref($what) if ref($what);
my $self = {};
$self->{'buffer'} = "";
bless($self,$what);
$repo =~ s#/+$##;
$self->{'fullrep'} = $repo;
$self->conn();
$self->{'subdir'} = $subdir;
$self->{'lines'} = undef;
return $self;
}
sub conn {
my $self = shift;
my $repo = $self->{'fullrep'};
if ($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;
}
}
# if username is not explicit in CVSROOT, then use current user, as cvs would
$user=(getlogin() || $ENV{'LOGNAME'} || $ENV{'USER'} || "anonymous") unless $user;
2005-06-28 19:49:19 +02:00
my $rr2 = "-";
unless ($port) {
2005-06-28 16:48:40 +02:00
$rr2 = ":pserver:$user\@$serv:$repo";
$port=2401;
}
my $rr = ":pserver:$user\@$serv:$port$repo";
unless ($pass) {
2005-06-28 16:48:40 +02:00
open(H,$ENV{'HOME'}."/.cvspass") and do {
# :pserver:cvs@mea.tmt.tele.fi:/cvsroot/zmailer Ah<Z
while (<H>) {
2005-06-28 16:48:40 +02:00
chomp;
s/^\/\d+\s+//;
my ($w,$p) = split(/\s/,$_,2);
if ($w eq $rr or $w eq $rr2) {
2005-06-28 16:48:40 +02:00
$pass = $p;
last;
}
}
};
}
$pass="A" unless $pass;
my ($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;
}
2005-06-28 16:48:40 +02:00
$s->write("BEGIN AUTH REQUEST\n$repo\n$user\n$pass\nEND AUTH REQUEST\n")
or die "Write to $serv: $!\n";
$s->flush();
$rep = <$s>;
2005-06-28 16:48:40 +02:00
if ($rep ne "I LOVE YOU\n") {
2005-06-28 16:48:40 +02:00
$rep="<unknown>" unless $rep;
die "AuthReply: $rep\n";
}
$self->{'socketo'} = $s;
$self->{'socketi'} = $s;
2005-07-03 13:02:06 +02:00
} else { # local or ext: Fork off our own cvs server.
2005-06-28 16:48:40 +02:00
my $pr = IO::Pipe->new();
my $pw = IO::Pipe->new();
my $pid = fork();
die "Fork: $!\n" unless defined $pid;
2005-07-03 12:26:51 +02:00
my $cvs = 'cvs';
$cvs = $ENV{CVS_SERVER} if exists $ENV{CVS_SERVER};
2005-07-03 13:02:06 +02:00
my $rsh = 'rsh';
$rsh = $ENV{CVS_RSH} if exists $ENV{CVS_RSH};
my @cvs = ($cvs, 'server');
my ($local, $user, $host);
$local = $repo =~ s/:local://;
if (!$local) {
$repo =~ s/:ext://;
$local = !($repo =~ s/^(?:([^\@:]+)\@)?([^:]+)://);
($user, $host) = ($1, $2);
}
if (!$local) {
if ($user) {
unshift @cvs, $rsh, '-l', $user, $host;
} else {
unshift @cvs, $rsh, $host;
}
}
unless ($pid) {
2005-06-28 16:48:40 +02:00
$pr->writer();
$pw->reader();
dup2($pw->fileno(),0);
dup2($pr->fileno(),1);
$pr->close();
$pw->close();
2005-07-03 13:02:06 +02:00
exec(@cvs);
2005-06-28 16:48:40 +02:00
}
$pw->writer();
$pr->reader();
$self->{'socketo'} = $pw;
$self->{'socketi'} = $pr;
}
$self->{'socketo'}->write("Root $repo\n");
# Trial and error says that this probably is the minimum set
$self->{'socketo'}->write("Valid-responses ok error Valid-requests Mode M Mbinary E Checked-in Created Updated Merged Removed\n");
2005-06-28 16:48:40 +02:00
$self->{'socketo'}->write("valid-requests\n");
$self->{'socketo'}->flush();
chomp(my $rep=$self->readline());
if ($rep !~ s/^Valid-requests\s*//) {
2005-06-28 16:48:40 +02:00
$rep="<unknown>" unless $rep;
die "Expected Valid-requests from server, but got: $rep\n";
}
chomp(my $res=$self->readline());
die "validReply: $res\n" if $res ne "ok";
$self->{'socketo'}->write("UseUnchanged\n") if $rep =~ /\bUseUnchanged\b/;
$self->{'repo'} = $repo;
}
sub readline {
my ($self) = @_;
2005-06-28 16:48:40 +02:00
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) = @_;
2005-06-28 16:48:40 +02:00
$self->{'socketo'}->write("Argument -N\n") or return undef;
$self->{'socketo'}->write("Argument -P\n") or return undef;
# -kk: Linus' version doesn't use it - defaults to off
if ($opt_k) {
$self->{'socketo'}->write("Argument -kk\n") or return undef;
}
2005-06-28 16:48:40 +02:00
$self->{'socketo'}->write("Argument -r\n") or return undef;
$self->{'socketo'}->write("Argument $rev\n") or return undef;
$self->{'socketo'}->write("Argument --\n") or return undef;
$self->{'socketo'}->write("Argument $self->{'subdir'}/$fn\n") or return undef;
$self->{'socketo'}->write("Directory .\n") or return undef;
$self->{'socketo'}->write("$self->{'repo'}\n") or return undef;
# $self->{'socketo'}->write("Sticky T1.0\n") or return undef;
2005-06-28 16:48:40 +02:00
$self->{'socketo'}->write("co\n") or return undef;
$self->{'socketo'}->flush() or return undef;
$self->{'lines'} = 0;
return 1;
}
sub _line {
# Read a line from the server.
# ... except that 'line' may be an entire file. ;-)
my ($self, $fh) = @_;
2005-06-28 16:48:40 +02:00
die "Not in lines" unless defined $self->{'lines'};
my $line;
my $res=0;
while (defined($line = $self->readline())) {
2005-06-28 16:48:40 +02:00
# M U gnupg-cvs-rep/AUTHORS
# Updated gnupg-cvs-rep/
# /daten/src/rsync/gnupg-cvs-rep/AUTHORS
# /AUTHORS/1.1///T1.1
# u=rw,g=rw,o=rw
# 0
# ok
if ($line =~ s/^(?:Created|Updated) //) {
2005-06-28 16:48:40 +02:00
$line = $self->readline(); # path
$line = $self->readline(); # Entries line
my $mode = $self->readline(); chomp $mode;
$self->{'mode'} = $mode;
defined (my $cnt = $self->readline())
or die "EOF from server after 'Changed'\n";
chomp $cnt;
die "Duh: Filesize $cnt" if $cnt !~ /^\d+$/;
$line="";
$res = $self->_fetchfile($fh, $cnt);
} elsif ($line =~ s/^ //) {
print $fh $line;
$res += length($line);
} elsif ($line =~ /^M\b/) {
2005-06-28 16:48:40 +02:00
# output, do nothing
} elsif ($line =~ /^Mbinary\b/) {
2005-06-28 16:48:40 +02:00
my $cnt;
die "EOF from server after 'Mbinary'" unless defined ($cnt = $self->readline());
chomp $cnt;
die "Duh: Mbinary $cnt" if $cnt !~ /^\d+$/ or $cnt<1;
$line="";
$res += $self->_fetchfile($fh, $cnt);
2005-06-28 16:48:40 +02:00
} else {
chomp $line;
if ($line eq "ok") {
2005-06-28 16:48:40 +02:00
# print STDERR "S: ok (".length($res).")\n";
return $res;
} elsif ($line =~ s/^E //) {
2005-06-28 16:48:40 +02:00
# print STDERR "S: $line\n";
} elsif ($line =~ /^(Remove-entry|Removed) /i) {
$line = $self->readline(); # filename
$line = $self->readline(); # OK
chomp $line;
die "Unknown: $line" if $line ne "ok";
return -1;
2005-06-28 16:48:40 +02:00
} else {
die "Unknown: $line\n";
}
}
}
return undef;
2005-06-28 16:48:40 +02:00
}
sub file {
my ($self,$fn,$rev) = @_;
2005-06-28 16:48:40 +02:00
my $res;
my ($fh, $name) = tempfile('gitcvs.XXXXXX',
DIR => File::Spec->tmpdir(), UNLINK => 1);
$self->_file($fn,$rev) and $res = $self->_line($fh);
if (!defined $res) {
print STDERR "Server has gone away while fetching $fn $rev, retrying...\n";
truncate $fh, 0;
$self->conn();
$self->_file($fn,$rev) or die "No file command send";
$res = $self->_line($fh);
die "Retry failed" unless defined $res;
2005-06-28 16:48:40 +02:00
}
close ($fh);
2005-06-28 16:48:40 +02:00
return ($name, $res);
2005-06-28 16:48:40 +02:00
}
sub _fetchfile {
my ($self, $fh, $cnt) = @_;
my $res = 0;
my $bufsize = 1024 * 1024;
while ($cnt) {
if ($bufsize > $cnt) {
$bufsize = $cnt;
}
my $buf;
my $num = $self->{'socketi'}->read($buf,$bufsize);
die "Server: Filesize $cnt: $num: $!\n" if not defined $num or $num<=0;
print $fh $buf;
$res += $num;
$cnt -= $num;
}
return $res;
}
2005-06-28 16:48:40 +02:00
package main;
2005-06-28 19:49:19 +02:00
my $cvs = CVSconn->new($opt_d, $cvs_tree);
2005-06-28 16:48:40 +02:00
sub pdate($) {
my ($d) = @_;
2005-06-28 16:48:40 +02:00
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;
return timegm($6||0,$5,$4,$3,$2-1,$y);
}
2005-06-28 16:48:40 +02:00
sub pmode($) {
my ($mode) = @_;
2005-06-28 16:48:40 +02:00
my $m = 0;
my $mm = 0;
my $um = 0;
for my $x(split(//,$mode)) {
if ($x eq ",") {
2005-06-28 16:48:40 +02:00
$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
2005-06-28 16:48:40 +02:00
} else { die "Unknown mode: $mode\n";
}
}
$m |= $mm&$um;
return $m;
}
2005-06-28 16:48:40 +02:00
sub getwd() {
my $pwd = `pwd`;
chomp $pwd;
return $pwd;
}
sub is_sha1 {
my $s = shift;
return $s =~ /^[a-f0-9]{40}$/;
}
sub get_headref ($) {
my $name = shift;
my $r = `git rev-parse --verify '$name' 2>/dev/null`;
return undef unless $? == 0;
chomp $r;
return $r;
}
2005-06-28 16:48:40 +02:00
-d $git_tree
or mkdir($git_tree,0777)
or die "Could not create $git_tree: $!";
chdir($git_tree);
2005-06-28 16:48:40 +02:00
my $last_branch = "";
my $orig_branch = "";
2005-06-28 16:48:40 +02:00
my %branch_date;
my $tip_at_start = undef;
2005-06-28 16:48:40 +02:00
my $git_dir = $ENV{"GIT_DIR"} || ".git";
$git_dir = getwd()."/".$git_dir unless $git_dir =~ m#^/#;
$ENV{"GIT_DIR"} = $git_dir;
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
unless (-d $git_dir) {
system("git-init");
2005-06-28 16:48:40 +02:00
die "Cannot init the GIT db at $git_tree: $?\n" if $?;
system("git-read-tree");
die "Cannot init an empty tree: $?\n" if $?;
$last_branch = $opt_o;
$orig_branch = "";
2005-06-28 16:48:40 +02:00
} else {
open(F, "git-symbolic-ref HEAD |") or
die "Cannot run git-symbolic-ref: $!\n";
chomp ($last_branch = <F>);
$last_branch = basename($last_branch);
close(F);
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`;
2005-06-28 16:48:40 +02:00
# Get the last import timestamps
my $fmt = '($ref, $author) = (%(refname), %(author));';
open(H, "git-for-each-ref --perl --format='$fmt' $remote |") or
die "Cannot run git-for-each-ref: $!\n";
while (defined(my $entry = <H>)) {
my ($ref, $author);
eval($entry) || die "cannot eval refs list: $@";
my ($head) = ($ref =~ m|^$remote/(.*)|);
$author =~ /^.*\s(\d+)\s[-+]\d{4}$/;
$branch_date{$head} = $1;
2005-06-28 16:48:40 +02:00
}
close(H);
if (!exists $branch_date{$opt_o}) {
die "Branch '$opt_o' does not exist.\n".
"Either use the correct '-o branch' option,\n".
"or import to a new repository.\n";
}
2005-06-28 16:48:40 +02:00
}
-d $git_dir
or die "Could not create git subdir ($git_dir).\n";
# now we read (and possibly save) author-info as well
-f "$git_dir/cvs-authors" and
read_author_info("$git_dir/cvs-authors");
if ($opt_A) {
read_author_info($opt_A);
write_author_info("$git_dir/cvs-authors");
}
#
# run cvsps into a file unless we are getting
# it passed as a file via $opt_P
#
my $cvspsfile;
unless ($opt_P) {
print "Running cvsps...\n" if $opt_v;
my $pid = open(CVSPS,"-|");
my $cvspsfh;
die "Cannot fork: $!\n" unless defined $pid;
unless ($pid) {
my @opt;
@opt = split(/,/,$opt_p) if defined $opt_p;
unshift @opt, '-z', $opt_z if defined $opt_z;
unshift @opt, '-q' unless defined $opt_v;
unless (defined($opt_p) && $opt_p =~ m/--no-cvs-direct/) {
push @opt, '--cvs-direct';
}
exec("cvsps","--norc",@opt,"-u","-A",'--root',$opt_d,$cvs_tree);
die "Could not start cvsps: $!\n";
}
($cvspsfh, $cvspsfile) = tempfile('gitXXXXXX', SUFFIX => '.cvsps',
DIR => File::Spec->tmpdir());
while (<CVSPS>) {
print $cvspsfh $_;
}
close CVSPS;
$? == 0 or die "git-cvsimport: fatal: cvsps reported error\n";
close $cvspsfh;
} else {
$cvspsfile = $opt_P;
2005-06-28 16:48:40 +02:00
}
open(CVS, "<$cvspsfile") or die $!;
2005-06-28 16:48:40 +02:00
## 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 update_index (\@\@) {
my $old = shift;
my $new = shift;
open(my $fh, '|-', qw(git-update-index -z --index-info))
or die "unable to open git-update-index: $!";
print $fh
(map { "0 0000000000000000000000000000000000000000\t$_\0" }
@$old),
(map { '100' . sprintf('%o', $_->[0]) . " $_->[1]\t$_->[2]\0" }
@$new)
or die "unable to write to git-update-index: $!";
close $fh
or die "unable to write to git-update-index: $!";
$? and die "git-update-index reported error: $?";
}
2005-06-28 16:48:40 +02:00
sub write_tree () {
open(my $fh, '-|', qw(git-write-tree))
or die "unable to open git-write-tree: $!";
chomp(my $tree = <$fh>);
is_sha1($tree)
or die "Cannot get tree id ($tree): $!";
close($fh)
2005-06-28 16:48:40 +02:00
or die "Error running git-write-tree: $?\n";
print "Tree ID $tree\n" if $opt_v;
return $tree;
}
2005-06-28 16:48:40 +02:00
my ($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("$remote/$branch")) {
# looks like an initial commit
# use the index primed by git-init
$ENV{GIT_INDEX_FILE} = "$git_dir/index";
$index{$branch} = "$git_dir/index";
} else {
# use an index per branch to speed up
# imports of projects with many branches
unless ($index{$branch}) {
$index{$branch} = tmpnam();
$ENV{GIT_INDEX_FILE} = $index{$branch};
if ($ancestor) {
system("git-read-tree", "$remote/$ancestor");
} else {
system("git-read-tree", "$remote/$branch");
}
die "read-tree failed: $?\n" if $?;
}
}
$ENV{GIT_INDEX_FILE} = $index{$branch};
update_index(@old, @new);
@old = @new = ();
my $tree = write_tree();
my $parent = get_headref("$remote/$last_branch");
print "Parent ID " . ($parent ? $parent : "(empty)") . "\n" if $opt_v;
my @commit_args;
push @commit_args, ("-p", $parent) if $parent;
# loose detection of merges
# based on the commit msg
foreach my $rx (@mergerx) {
next unless $logmsg =~ $rx && $1;
my $mparent = $1 eq 'HEAD' ? $opt_o : $1;
if (my $sha1 = get_headref("$remote/$mparent")) {
push @commit_args, '-p', "$remote/$mparent";
print "Merge parent branch: $mparent\n" if $opt_v;
}
2005-06-28 16:48:40 +02:00
}
my $commit_date = strftime("+0000 %Y-%m-%d %H:%M:%S",gmtime($date));
$ENV{GIT_AUTHOR_NAME} = $author_name;
$ENV{GIT_AUTHOR_EMAIL} = $author_email;
$ENV{GIT_AUTHOR_DATE} = $commit_date;
$ENV{GIT_COMMITTER_NAME} = $author_name;
$ENV{GIT_COMMITTER_EMAIL} = $author_email;
$ENV{GIT_COMMITTER_DATE} = $commit_date;
my $pid = open2(my $commit_read, my $commit_write,
'git-commit-tree', $tree, @commit_args);
# compatibility with git2cvs
substr($logmsg,32767) = "" if length($logmsg) > 32767;
$logmsg =~ s/[\s\n]+\z//;
if (@skipped) {
$logmsg .= "\n\n\nSKIPPED:\n\t";
$logmsg .= join("\n\t", @skipped) . "\n";
@skipped = ();
}
print($commit_write "$logmsg\n") && close($commit_write)
2005-06-28 16:48:40 +02:00
or die "Error writing to git-commit-tree: $!\n";
2005-06-28 19:49:19 +02:00
print "Committed patch $patchset ($branch $commit_date)\n" if $opt_v;
chomp(my $cid = <$commit_read>);
is_sha1($cid) or die "Cannot get commit id ($cid): $!\n";
2005-06-28 16:48:40 +02:00
print "Commit ID $cid\n" if $opt_v;
close($commit_read);
2005-06-28 19:49:19 +02:00
waitpid($pid,0);
die "Error running git-commit-tree: $?\n" if $?;
2005-06-28 16:48:40 +02:00
system("git-update-ref $remote/$branch $cid") == 0
2005-06-28 16:48:40 +02:00
or die "Cannot write branch $branch for update: $!\n";
if ($tag) {
my ($xtag) = $tag;
$xtag =~ s/\s+\*\*.*$//; # Remove stuff like ** INVALID ** and ** FUNKY **
$xtag =~ tr/_/\./ if ( $opt_u );
$xtag =~ s/[\/]/$opt_s/g;
system('git-tag', '-f', $xtag, $cid) == 0
or die "Cannot create tag $xtag: $!\n";
print "Created tag '$xtag' on '$branch'\n" if $opt_v;
2005-06-28 16:48:40 +02:00
}
};
my $commitcount = 1;
while (<CVS>) {
2005-06-28 16:48:40 +02:00
chomp;
if ($state == 0 and /^-+$/) {
2005-06-28 16:48:40 +02:00
$state = 1;
} elsif ($state == 0) {
2005-06-28 16:48:40 +02:00
$state = 1;
redo;
} elsif (($state==0 or $state==1) and s/^PatchSet\s+//) {
2005-06-28 16:48:40 +02:00
$patchset = 0+$_;
$state=2;
} elsif ($state == 2 and s/^Date:\s+//) {
2005-06-28 16:48:40 +02:00
$date = pdate($_);
unless ($date) {
2005-06-28 16:48:40 +02:00
print STDERR "Could not parse date: $_\n";
$state=0;
next;
}
$state=3;
} elsif ($state == 3 and s/^Author:\s+//) {
2005-06-28 16:48:40 +02:00
s/\s+$//;
if (/^(.*?)\s+<(.*)>/) {
($author_name, $author_email) = ($1, $2);
} elsif ($conv_author_name{$_}) {
$author_name = $conv_author_name{$_};
$author_email = $conv_author_email{$_};
} else {
$author_name = $author_email = $_;
}
2005-06-28 16:48:40 +02:00
$state = 4;
} elsif ($state == 4 and s/^Branch:\s+//) {
2005-06-28 16:48:40 +02:00
s/\s+$//;
tr/_/\./ if ( $opt_u );
s/[\/]/$opt_s/g;
2005-06-28 16:48:40 +02:00
$branch = $_;
$state = 5;
} elsif ($state == 5 and s/^Ancestor branch:\s+//) {
2005-06-28 16:48:40 +02:00
s/\s+$//;
$ancestor = $_;
$ancestor = $opt_o if $ancestor eq "HEAD";
2005-06-28 16:48:40 +02:00
$state = 6;
} elsif ($state == 5) {
2005-06-28 16:48:40 +02:00
$ancestor = undef;
$state = 6;
redo;
} elsif ($state == 6 and s/^Tag:\s+//) {
2005-06-28 16:48:40 +02:00
s/\s+$//;
if ($_ eq "(none)") {
2005-06-28 16:48:40 +02:00
$tag = undef;
} else {
$tag = $_;
}
$state = 7;
} elsif ($state == 7 and /^Log:/) {
2005-06-28 16:48:40 +02:00
$logmsg = "";
$state = 8;
} elsif ($state == 8 and /^Members:/) {
2005-06-28 16:48:40 +02:00
$branch = $opt_o if $branch eq "HEAD";
if (defined $branch_date{$branch} and $branch_date{$branch} >= $date) {
2005-06-28 16:48:40 +02:00
# skip
print "skip patchset $patchset: $date before $branch_date{$branch}\n" if $opt_v;
2005-06-28 16:48:40 +02:00
$state = 11;
next;
}
if (!$opt_a && $starttime - 300 - (defined $opt_z ? $opt_z : 300) <= $date) {
# skip if the commit is too recent
# given that the cvsps default fuzz is 300s, we give ourselves another
# 300s just in case -- this also prevents skipping commits
# due to server clock drift
print "skip patchset $patchset: $date too recent\n" if $opt_v;
$state = 11;
next;
}
if (exists $ignorebranch{$branch}) {
print STDERR "Skipping $branch\n";
$state = 11;
next;
}
if ($ancestor) {
if ($ancestor eq $branch) {
print STDERR "Branch $branch erroneously stems from itself -- changed ancestor to $opt_o\n";
$ancestor = $opt_o;
}
if (defined get_headref("$remote/$branch")) {
2005-06-28 16:48:40 +02:00
print STDERR "Branch $branch already exists!\n";
$state=11;
next;
}
my $id = get_headref("$remote/$ancestor");
if (!$id) {
2005-06-28 16:48:40 +02:00
print STDERR "Branch $ancestor does not exist!\n";
$ignorebranch{$branch} = 1;
2005-06-28 16:48:40 +02:00
$state=11;
next;
}
system(qw(git update-ref -m cvsimport),
"$remote/$branch", $id);
if($? != 0) {
print STDERR "Could not create branch $branch\n";
$ignorebranch{$branch} = 1;
2005-06-28 16:48:40 +02:00
$state=11;
next;
}
}
$last_branch = $branch if $branch ne $last_branch;
2005-06-28 16:48:40 +02:00
$state = 9;
} elsif ($state == 8) {
2005-06-28 16:48:40 +02:00
$logmsg .= "$_\n";
} elsif ($state == 9 and /^\s+(.+?):(INITIAL|\d+(?:\.\d+)+)->(\d+(?:\.\d+)+)\s*$/) {
2005-06-28 16:48:40 +02:00
# VERSION:1.96->1.96.2.1
2005-06-28 19:49:19 +02:00
my $init = ($2 eq "INITIAL");
2005-06-28 16:48:40 +02:00
my $fn = $1;
2005-06-28 19:58:40 +02:00
my $rev = $3;
$fn =~ s#^/+##;
if ($opt_S && $fn =~ m/$opt_S/) {
print "SKIPPING $fn v $rev\n";
push(@skipped, $fn);
next;
}
print "Fetching $fn v $rev\n" if $opt_v;
my ($tmpname, $size) = $cvs->file($fn,$rev);
if ($size == -1) {
push(@old,$fn);
print "Drop $fn\n" if $opt_v;
} else {
print "".($init ? "New" : "Update")." $fn: $size bytes\n" if $opt_v;
my $pid = open(my $F, '-|');
die $! unless defined $pid;
if (!$pid) {
exec("git-hash-object", "-w", $tmpname)
or die "Cannot create object: $!\n";
}
my $sha = <$F>;
chomp $sha;
close $F;
my $mode = pmode($cvs->{'mode'});
push(@new,[$mode, $sha, $fn]); # may be resurrected!
}
unlink($tmpname);
} elsif ($state == 9 and /^\s+(.+?):\d+(?:\.\d+)+->(\d+(?:\.\d+)+)\(DEAD\)\s*$/) {
2005-06-28 19:58:40 +02:00
my $fn = $1;
$fn =~ s#^/+##;
push(@old,$fn);
print "Delete $fn\n" if $opt_v;
} elsif ($state == 9 and /^\s*$/) {
2005-06-28 16:48:40 +02:00
$state = 10;
} elsif (($state == 9 or $state == 10) and /^-+$/) {
$commitcount++;
if ($opt_L && $commitcount > $opt_L) {
last;
}
commit();
if (($commitcount & 1023) == 0) {
system("git repack -a -d");
}
2005-06-28 16:48:40 +02:00
$state = 1;
} elsif ($state == 11 and /^-+$/) {
2005-06-28 16:48:40 +02:00
$state = 1;
} elsif (/^-+$/) { # end of unknown-line processing
2005-06-28 16:48:40 +02:00
$state = 1;
} elsif ($state != 11) { # ignore stuff when skipping
2005-06-28 16:48:40 +02:00
print "* UNKNOWN LINE * $_\n";
}
}
commit() if $branch and $state != 11;
unless ($opt_P) {
unlink($cvspsfile);
}
# 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 $git_index (values %index) {
if ($git_index ne "$git_dir/index") {
unlink($git_index);
}
}
if (defined $orig_git_index) {
$ENV{GIT_INDEX_FILE} = $orig_git_index;
} else {
delete $ENV{GIT_INDEX_FILE};
}
# Now switch back to the branch we were in before all of this happened
if ($orig_branch) {
print "DONE.\n" if $opt_v;
if ($opt_i) {
exit 0;
}
my $tip_at_end = `git-rev-parse --verify HEAD`;
if ($tip_at_start ne $tip_at_end) {
for ($tip_at_start, $tip_at_end) { chomp; }
print "Fetched into the current branch.\n" if $opt_v;
system(qw(git-read-tree -u -m),
$tip_at_start, $tip_at_end);
die "Fast-forward update failed: $?\n" if $?;
}
else {
system(qw(git-merge cvsimport HEAD), "$remote/$opt_o");
die "Could not merge $opt_o into the current branch.\n" if $?;
}
} else {
$orig_branch = "master";
print "DONE; creating $orig_branch branch\n" if $opt_v;
system("git-update-ref", "refs/heads/master", "$remote/$opt_o")
unless defined get_headref('refs/heads/master');
system("git-symbolic-ref", "$remote/HEAD", "$remote/$opt_o")
if ($opt_r && $opt_o ne 'HEAD');
system('git-update-ref', 'HEAD', "$orig_branch");
unless ($opt_i) {
system('git checkout -f');
die "checkout failed: $?\n" if $?;
}
}