archimport: add -D <depth> and -a switch
add -D <depth> option to abrowse add -a switch to attempt to auto-register archives at mirrors.sourcecontrol.net (ML: Also removes some std libraries no longer in use) Signed-off-by: Eric Wong <normalperson@yhbt.net> Signed-off-by: Martin Langhoff <martin@catalyst.net.nz>
This commit is contained in:
Eric Wong
Martin Langhoff
parent
1136fb5284
commit
42f44b08bc
@ -53,14 +53,9 @@ and can contain multiple, unrelated branches.
|
|||||||
use strict;
|
use strict;
|
||||||
use warnings;
|
use warnings;
|
||||||
use Getopt::Std;
|
use Getopt::Std;
|
||||||
use File::Spec;
|
use File::Temp qw(tempdir);
|
||||||
use File::Temp qw(tempfile tempdir);
|
|
||||||
use File::Path qw(mkpath rmtree);
|
use File::Path qw(mkpath rmtree);
|
||||||
use File::Basename qw(basename dirname);
|
use File::Basename qw(basename dirname);
|
||||||
use Time::Local;
|
|
||||||
use IO::Socket;
|
|
||||||
use IO::Pipe;
|
|
||||||
use POSIX qw(strftime dup2);
|
|
||||||
use Data::Dumper qw/ Dumper /;
|
use Data::Dumper qw/ Dumper /;
|
||||||
use IPC::Open2;
|
use IPC::Open2;
|
||||||
|
|
||||||
@ -71,27 +66,33 @@ my $git_dir = $ENV{"GIT_DIR"} || ".git";
|
|||||||
$ENV{"GIT_DIR"} = $git_dir;
|
$ENV{"GIT_DIR"} = $git_dir;
|
||||||
my $ptag_dir = "$git_dir/archimport/tags";
|
my $ptag_dir = "$git_dir/archimport/tags";
|
||||||
|
|
||||||
our($opt_h,$opt_v, $opt_T,$opt_t,$opt_o);
|
our($opt_h,$opt_v,$opt_T,$opt_t,$opt_D,$opt_a,$opt_o);
|
||||||
|
|
||||||
sub usage() {
|
sub usage() {
|
||||||
print STDERR <<END;
|
print STDERR <<END;
|
||||||
Usage: ${\basename $0} # fetch/update GIT from Arch
|
Usage: ${\basename $0} # fetch/update GIT from Arch
|
||||||
[ -o ] [ -h ] [ -v ] [ -T ] [ -t tempdir ]
|
[ -o ] [ -h ] [ -v ] [ -T ] [ -a ] [ -D depth ] [ -t tempdir ]
|
||||||
repository/arch-branch [ repository/arch-branch] ...
|
repository/arch-branch [ repository/arch-branch] ...
|
||||||
END
|
END
|
||||||
exit(1);
|
exit(1);
|
||||||
}
|
}
|
||||||
|
|
||||||
getopts("Thvt:") or usage();
|
getopts("Thvat:D:") or usage();
|
||||||
usage if $opt_h;
|
usage if $opt_h;
|
||||||
|
|
||||||
@ARGV >= 1 or usage();
|
@ARGV >= 1 or usage();
|
||||||
my @arch_roots = @ARGV;
|
# $arch_branches:
|
||||||
|
# values associated with keys:
|
||||||
|
# =1 - Arch version / git 'branch' detected via abrowse on a limit
|
||||||
|
# >1 - Arch version / git 'branch' of an auxilliary branch we've merged
|
||||||
|
my %arch_branches = map { $_ => 1 } @ARGV;
|
||||||
|
|
||||||
$ENV{'TMPDIR'} = $opt_t if $opt_t; # $ENV{TMPDIR} will affect tempdir() calls:
|
$ENV{'TMPDIR'} = $opt_t if $opt_t; # $ENV{TMPDIR} will affect tempdir() calls:
|
||||||
my $tmp = tempdir('git-archimport-XXXXXX', TMPDIR => 1, CLEANUP => 1);
|
my $tmp = tempdir('git-archimport-XXXXXX', TMPDIR => 1, CLEANUP => 1);
|
||||||
$opt_v && print "+ Using $tmp as temporary directory\n";
|
$opt_v && print "+ Using $tmp as temporary directory\n";
|
||||||
|
|
||||||
|
my %reachable = (); # Arch repositories we can access
|
||||||
|
my %unreachable = (); # Arch repositories we can't access :<
|
||||||
my @psets = (); # the collection
|
my @psets = (); # the collection
|
||||||
my %psets = (); # the collection, by name
|
my %psets = (); # the collection, by name
|
||||||
|
|
||||||
@ -99,96 +100,112 @@ my %rptags = (); # my reverse private tags
|
|||||||
# to map a SHA1 to a commitid
|
# to map a SHA1 to a commitid
|
||||||
my $TLA = $ENV{'ARCH_CLIENT'} || 'tla';
|
my $TLA = $ENV{'ARCH_CLIENT'} || 'tla';
|
||||||
|
|
||||||
foreach my $root (@arch_roots) {
|
sub do_abrowse {
|
||||||
my ($arepo, $abranch) = split(m!/!, $root);
|
my $stage = shift;
|
||||||
open ABROWSE, "tla abrowse -f -A $arepo --desc --merges $abranch |"
|
while (my ($limit, $level) = each %arch_branches) {
|
||||||
or die "Problems with tla abrowse: $!";
|
next unless $level == $stage;
|
||||||
|
|
||||||
my %ps = (); # the current one
|
open ABROWSE, "$TLA abrowse -fkD --merges $limit |"
|
||||||
my $mode = '';
|
or die "Problems with tla abrowse: $!";
|
||||||
my $lastseen = '';
|
|
||||||
|
|
||||||
while (<ABROWSE>) {
|
my %ps = (); # the current one
|
||||||
chomp;
|
my $lastseen = '';
|
||||||
|
|
||||||
# first record padded w 8 spaces
|
while (<ABROWSE>) {
|
||||||
if (s/^\s{8}\b//) {
|
chomp;
|
||||||
|
|
||||||
# store the record we just captured
|
# first record padded w 8 spaces
|
||||||
if (%ps) {
|
if (s/^\s{8}\b//) {
|
||||||
my %temp = %ps; # break references
|
my ($id, $type) = split(m/\s+/, $_, 2);
|
||||||
push (@psets, \%temp);
|
|
||||||
$psets{$temp{id}} = \%temp;
|
|
||||||
%ps = ();
|
|
||||||
}
|
|
||||||
|
|
||||||
my ($id, $type) = split(m/\s{3}/, $_);
|
my %last_ps;
|
||||||
$ps{id} = $id;
|
# store the record we just captured
|
||||||
$ps{repo} = $arepo;
|
if (%ps && !exists $psets{ $ps{id} }) {
|
||||||
|
%last_ps = %ps; # break references
|
||||||
# deal with types
|
push (@psets, \%last_ps);
|
||||||
if ($type =~ m/^\(simple changeset\)/) {
|
$psets{ $last_ps{id} } = \%last_ps;
|
||||||
$ps{type} = 's';
|
|
||||||
} elsif ($type eq '(initial import)') {
|
|
||||||
$ps{type} = 'i';
|
|
||||||
} elsif ($type =~ m/^\(tag revision of (.+)\)/) {
|
|
||||||
$ps{type} = 't';
|
|
||||||
$ps{tag} = $1;
|
|
||||||
} else {
|
|
||||||
warn "Unknown type $type";
|
|
||||||
}
|
|
||||||
$lastseen = 'id';
|
|
||||||
}
|
|
||||||
|
|
||||||
if (s/^\s{10}//) {
|
|
||||||
# 10 leading spaces or more
|
|
||||||
# indicate commit metadata
|
|
||||||
|
|
||||||
# date & author
|
|
||||||
if ($lastseen eq 'id' && m/^\d{4}-\d{2}-\d{2}/) {
|
|
||||||
|
|
||||||
my ($date, $authoremail) = split(m/\s{2,}/, $_);
|
|
||||||
$ps{date} = $date;
|
|
||||||
$ps{date} =~ s/\bGMT$//; # strip off trailign GMT
|
|
||||||
if ($ps{date} =~ m/\b\w+$/) {
|
|
||||||
warn 'Arch dates not in GMT?! - imported dates will be wrong';
|
|
||||||
}
|
}
|
||||||
|
|
||||||
$authoremail =~ m/^(.+)\s(\S+)$/;
|
my $branch = extract_versionname($id);
|
||||||
$ps{author} = $1;
|
%ps = ( id => $id, branch => $branch );
|
||||||
$ps{email} = $2;
|
if (%last_ps && ($last_ps{branch} eq $branch)) {
|
||||||
|
$ps{parent_id} = $last_ps{id};
|
||||||
|
}
|
||||||
|
|
||||||
$lastseen = 'date';
|
$arch_branches{$branch} = 1;
|
||||||
|
$lastseen = 'id';
|
||||||
|
|
||||||
} elsif ($lastseen eq 'date') {
|
# deal with types (should work with baz or tla):
|
||||||
# the only hint is position
|
if ($type =~ m/\(.*changeset\)/) {
|
||||||
# subject is after date
|
$ps{type} = 's';
|
||||||
$ps{subj} = $_;
|
} elsif ($type =~ /\(.*import\)/) {
|
||||||
$lastseen = 'subj';
|
$ps{type} = 'i';
|
||||||
|
} elsif ($type =~ m/\(tag.*\)/) {
|
||||||
|
$ps{type} = 't';
|
||||||
|
# read which revision we've tagged when we parse the log
|
||||||
|
#$ps{tag} = $1;
|
||||||
|
} else {
|
||||||
|
warn "Unknown type $type";
|
||||||
|
}
|
||||||
|
|
||||||
} elsif ($lastseen eq 'subj' && $_ eq 'merges in:') {
|
$arch_branches{$branch} = 1;
|
||||||
$ps{merges} = [];
|
$lastseen = 'id';
|
||||||
$lastseen = 'merges';
|
} elsif (s/^\s{10}//) {
|
||||||
|
# 10 leading spaces or more
|
||||||
|
# indicate commit metadata
|
||||||
|
|
||||||
} elsif ($lastseen eq 'merges' && s/^\s{2}//) {
|
# date
|
||||||
push (@{$ps{merges}}, $_);
|
if ($lastseen eq 'id' && m/^(\d{4}-\d\d-\d\d \d\d:\d\d:\d\d)/){
|
||||||
} else {
|
$ps{date} = $1;
|
||||||
warn 'more metadata after merges!?';
|
$lastseen = 'date';
|
||||||
|
} elsif ($_ eq 'merges in:') {
|
||||||
|
$ps{merges} = [];
|
||||||
|
$lastseen = 'merges';
|
||||||
|
} elsif ($lastseen eq 'merges' && s/^\s{2}//) {
|
||||||
|
my $id = $_;
|
||||||
|
push (@{$ps{merges}}, $id);
|
||||||
|
|
||||||
|
# aggressive branch finding:
|
||||||
|
if ($opt_D) {
|
||||||
|
my $branch = extract_versionname($id);
|
||||||
|
my $repo = extract_reponame($branch);
|
||||||
|
|
||||||
|
if (archive_reachable($repo) &&
|
||||||
|
!defined $arch_branches{$branch}) {
|
||||||
|
$arch_branches{$branch} = $stage + 1;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
warn "more metadata after merges!?: $_\n" unless /^\s*$/;
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
if (%ps) {
|
if (%ps && !exists $psets{ $ps{id} }) {
|
||||||
my %temp = %ps; # break references
|
my %temp = %ps; # break references
|
||||||
push (@psets, \%temp);
|
if (@psets && $psets[$#psets]{branch} eq $ps{branch}) {
|
||||||
$psets{ $temp{id} } = \%temp;
|
$temp{parent_id} = $psets[$#psets]{id};
|
||||||
%ps = ();
|
}
|
||||||
|
push (@psets, \%temp);
|
||||||
|
$psets{ $temp{id} } = \%temp;
|
||||||
|
}
|
||||||
|
|
||||||
|
close ABROWSE or die "$TLA abrowse failed on $limit\n";
|
||||||
}
|
}
|
||||||
close ABROWSE;
|
|
||||||
} # end foreach $root
|
} # end foreach $root
|
||||||
|
|
||||||
|
do_abrowse(1);
|
||||||
|
my $depth = 2;
|
||||||
|
$opt_D ||= 0;
|
||||||
|
while ($depth <= $opt_D) {
|
||||||
|
do_abrowse($depth);
|
||||||
|
$depth++;
|
||||||
|
}
|
||||||
|
|
||||||
## Order patches by time
|
## Order patches by time
|
||||||
|
# FIXME see if we can find a more optimal way to do this by graphing
|
||||||
|
# the ancestry data and walking it, that way we won't have to rely on
|
||||||
|
# client-supplied dates
|
||||||
@psets = sort {$a->{date}.$b->{id} cmp $b->{date}.$b->{id}} @psets;
|
@psets = sort {$a->{date}.$b->{id} cmp $b->{date}.$b->{id}} @psets;
|
||||||
|
|
||||||
#print Dumper \@psets;
|
#print Dumper \@psets;
|
||||||
@ -209,7 +226,7 @@ unless (-d $git_dir) { # initial import
|
|||||||
}
|
}
|
||||||
} else { # progressing an import
|
} else { # progressing an import
|
||||||
# load the rptags
|
# load the rptags
|
||||||
opendir(DIR, "$git_dir/archimport/tags")
|
opendir(DIR, $ptag_dir)
|
||||||
|| die "can't opendir: $!";
|
|| die "can't opendir: $!";
|
||||||
while (my $file = readdir(DIR)) {
|
while (my $file = readdir(DIR)) {
|
||||||
# skip non-interesting-files
|
# skip non-interesting-files
|
||||||
@ -829,6 +846,7 @@ sub find_parents {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@parents = ();
|
@parents = ();
|
||||||
foreach (keys %parents) {
|
foreach (keys %parents) {
|
||||||
push @parents, '-p', ptag($_);
|
push @parents, '-p', ptag($_);
|
||||||
@ -856,6 +874,7 @@ sub commitid2pset {
|
|||||||
return $ps;
|
return $ps;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
# an alterative to `command` that allows input to be passed as an array
|
# an alterative to `command` that allows input to be passed as an array
|
||||||
# to work around shell problems with weird characters in arguments
|
# to work around shell problems with weird characters in arguments
|
||||||
sub safe_pipe_capture {
|
sub safe_pipe_capture {
|
||||||
@ -869,4 +888,30 @@ sub safe_pipe_capture {
|
|||||||
return wantarray ? @output : join('',@output);
|
return wantarray ? @output : join('',@output);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
# `tla logs -rf -d <dir> | head -n1` or `baz tree-id <dir>`
|
||||||
|
sub arch_tree_id {
|
||||||
|
my $dir = shift;
|
||||||
|
chomp( my $ret = (safe_pipe_capture($TLA,'logs','-rf','-d',$dir))[0] );
|
||||||
|
return $ret;
|
||||||
|
}
|
||||||
|
|
||||||
|
sub archive_reachable {
|
||||||
|
my $archive = shift;
|
||||||
|
return 1 if $reachable{$archive};
|
||||||
|
return 0 if $unreachable{$archive};
|
||||||
|
|
||||||
|
if (system "$TLA whereis-archive $archive >/dev/null") {
|
||||||
|
if ($opt_a && (system($TLA,'register-archive',
|
||||||
|
"http://mirrors.sourcecontrol.net/$archive") == 0)) {
|
||||||
|
$reachable{$archive} = 1;
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
print STDERR "Archive is unreachable: $archive\n";
|
||||||
|
$unreachable{$archive} = 1;
|
||||||
|
return 0;
|
||||||
|
} else {
|
||||||
|
$reachable{$archive} = 1;
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user