From c7162c1db6fef6527eafb8829d60cf26b02b0108 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Tue, 23 May 2006 18:34:24 -0700 Subject: [PATCH 01/25] git-svn: t0000: add -f flag to checkout Some changes to the latest git.git made this test croak. So we'll always just force everything when using a new branch. Signed-off-by: Eric Wong --- contrib/git-svn/t/t0000-contrib-git-svn.sh | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/contrib/git-svn/t/t0000-contrib-git-svn.sh b/contrib/git-svn/t/t0000-contrib-git-svn.sh index 8b3a0d9029..a07fbad68b 100644 --- a/contrib/git-svn/t/t0000-contrib-git-svn.sh +++ b/contrib/git-svn/t/t0000-contrib-git-svn.sh @@ -32,7 +32,7 @@ test_expect_success \ name='try a deep --rmdir with a commit' -git checkout -b mybranch remotes/git-svn +git checkout -f -b mybranch remotes/git-svn mv dir/a/b/c/d/e/file dir/file cp dir/file file git update-index --add --remove dir/a/b/c/d/e/file dir/file file @@ -58,7 +58,7 @@ test_expect_code 1 "$name" \ name='detect node change from directory to file #1' rm -rf dir $GIT_DIR/index -git checkout -b mybranch2 remotes/git-svn +git checkout -f -b mybranch2 remotes/git-svn mv bar/zzz zzz rm -rf bar mv zzz bar @@ -73,7 +73,7 @@ test_expect_code 1 "$name" \ name='detect node change from file to directory #2' rm -f $GIT_DIR/index -git checkout -b mybranch3 remotes/git-svn +git checkout -f -b mybranch3 remotes/git-svn rm bar/zzz git-update-index --remove bar/zzz mkdir bar/zzz @@ -88,7 +88,7 @@ test_expect_code 1 "$name" \ name='detect node change from directory to file #2' rm -f $GIT_DIR/index -git checkout -b mybranch4 remotes/git-svn +git checkout -f -b mybranch4 remotes/git-svn rm -rf dir git update-index --remove -- dir/file touch dir @@ -103,7 +103,7 @@ test_expect_code 1 "$name" \ name='remove executable bit from a file' rm -f $GIT_DIR/index -git checkout -b mybranch5 remotes/git-svn +git checkout -f -b mybranch5 remotes/git-svn chmod -x exec.sh git update-index exec.sh git commit -m "$name" From 8a97e368882afbc2bdc030214339bed54ed6545c Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Sun, 28 May 2006 15:23:56 -0700 Subject: [PATCH 02/25] git-svn: fix handling of filenames with embedded '@' svn has trouble parsing files with embedded '@' characters. For example, svn propget svn:keywords foo@bar.c svn: Syntax error parsing revision 'bar.c' I asked about this on #svn and the workaround suggested was to append an explicit revision specifier: svn propget svn:keywords foo@bar.c@BASE This patch appends '@BASE' to the filename in all calls to 'svn propget'. Patch originally by Seth Falcon Seth: signoff? [ew: Made to work with older svn that don't support peg revisions] Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index aac877974d..7ed11ef0a5 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -34,7 +34,7 @@ my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, $_find_copies_harder, $_l, $_version, $_upgrade, $_authors); my (@_branch_from, %tree_map, %users); -my $_svn_co_url_revs; +my ($_svn_co_url_revs, $_svn_pg_peg_revs); my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext, 'branch|b=s' => \@_branch_from, @@ -336,7 +336,7 @@ sub show_ignore { my %ign; File::Find::find({wanted=>sub{if(lstat $_ && -d _ && -d "$_/.svn"){ s#^\./##; - @{$ign{$_}} = safe_qx(qw(svn propget svn:ignore),$_); + @{$ign{$_}} = svn_propget_base('svn:ignore', $_); }}, no_chdir=>1},'.'); print "\n# /\n"; @@ -859,7 +859,7 @@ sub svn_info { sub eol_cp { my ($from, $to) = @_; - my $es = safe_qx(qw/svn propget svn:eol-style/, $to); + my $es = svn_propget_base('svn:eol-style', $to); open my $rfd, '<', $from or croak $!; binmode $rfd or croak $!; open my $wfd, '>', $to or croak $!; @@ -897,7 +897,7 @@ sub do_update_index { while (my $x = <$p>) { chomp $x; if (!$no_text_base && lstat $x && ! -l _ && - safe_qx(qw/svn propget svn:keywords/,$x)) { + svn_propget_base('svn:keywords', $x)) { my $mode = -x _ ? 0755 : 0644; my ($v,$d,$f) = File::Spec->splitpath($x); my $tb = File::Spec->catfile($d, '.svn', 'tmp', @@ -1135,6 +1135,9 @@ sub svn_compat_check { if (grep /usage: checkout URL\[\@REV\]/,@co_help) { $_svn_co_url_revs = 1; } + if (grep /\[TARGET\[\@REV\]\.\.\.\]/, `svn propget -h`) { + $_svn_pg_peg_revs = 1; + } # I really, really hope nobody hits this... unless (grep /stop-on-copy/, (safe_qx(qw(svn log -h)))) { @@ -1214,6 +1217,12 @@ sub load_authors { close $authors or croak $!; } +sub svn_propget_base { + my ($p, $f) = @_; + $f .= '@BASE' if $_svn_pg_peg_revs; + return safe_qx(qw/svn propget/, $p, $f); +} + __END__ Data structures: From 4a393f2b53f0997f79d47793d4c774fa0072887c Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Fri, 9 Jun 2006 23:27:01 -0700 Subject: [PATCH 03/25] git-svn: eol_cp corner-case fixes If we read the maximum size of our buffer into $buf, and the last character is '\015', there's a chance that the character is '\012', which means our regex won't work correctly. At the worst case, this could introduce an extra newline into the code. We'll now read an extra character if we see '\015' is the last character in $buf. We also forgot to recalculate the length of $buf after doing the newline substitution, causing some files to appeare truncated. We'll do that now and force byte semantics in length() for good measure. Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 7ed11ef0a5..8d2e7f74ea 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -866,19 +866,26 @@ sub eol_cp { binmode $wfd or croak $!; my $eol = $EOL{$es} or undef; - if ($eol) { - print "$eol: $from => $to\n"; - } my $buf; + use bytes; while (1) { my ($r, $w, $t); defined($r = sysread($rfd, $buf, 4096)) or croak $!; return unless $r; - $buf =~ s/(?:\015|\012|\015\012)/$eol/gs if $eol; + if ($eol) { + if ($buf =~ /\015$/) { + my $c; + defined($r = sysread($rfd,$c,1)) or croak $!; + $buf .= $c if $r > 0; + } + $buf =~ s/(?:\015\012|\015|\012)/$eol/gs; + $r = length($buf); + } for ($w = 0; $w < $r; $w += $t) { $t = syswrite($wfd, $buf, $r - $w, $w) or croak $!; } } + no bytes; } sub do_update_index { From ce475dfcb5021339d8545a020e8697dd35a1bbea Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Fri, 2 Jun 2006 15:16:41 -0700 Subject: [PATCH 04/25] git-svn: restore original LC_ALL setting (or unset) for commit svn forces UTF-8 for commit messages, and with LC_ALL set to 'C' it is unable to determine encoding of the git commit message. Now we'll just assume the user has set LC_* correctly for the commit message they're using. Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 34 +++++++++++++++++++++++----------- 1 file changed, 23 insertions(+), 11 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 8d2e7f74ea..8bc3d69fdb 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -14,6 +14,7 @@ $GIT_DIR = abs_path($ENV{GIT_DIR} || '.git'); $ENV{GIT_DIR} = $GIT_DIR; +my $LC_ALL = $ENV{LC_ALL}; # make sure the svn binary gives consistent output between locales and TZs: $ENV{TZ} = 'UTC'; $ENV{LC_ALL} = 'C'; @@ -704,23 +705,34 @@ sub svn_commit_tree { my ($oneline) = ($log_msg{msg} =~ /([^\n\r]+)/); print "Committing $commit: $oneline\n"; + if (defined $LC_ALL) { + $ENV{LC_ALL} = $LC_ALL; + } else { + delete $ENV{LC_ALL}; + } my @ci_output = safe_qx(qw(svn commit -F),$commit_msg); - my ($committed) = grep(/^Committed revision \d+\./,@ci_output); + $ENV{LC_ALL} = 'C'; unlink $commit_msg; - defined $committed or croak + my ($committed) = ($ci_output[$#ci_output] =~ /(\d+)/); + if (!defined $committed) { + my $out = join("\n",@ci_output); + print STDERR "W: Trouble parsing \`svn commit' output:\n\n", + $out, "\n\nAssuming English locale..."; + ($committed) = ($out =~ /^Committed revision \d+\./sm); + defined $committed or die " FAILED!\n", "Commit output failed to parse committed revision!\n", - join("\n",@ci_output),"\n"; - my ($rev_committed) = ($committed =~ /^Committed revision (\d+)\./); + print STDERR " OK\n"; + } my @svn_up = qw(svn up); push @svn_up, '--ignore-externals' unless $_no_ignore_ext; - if ($rev_committed == ($svn_rev + 1)) { - push @svn_up, "-r$rev_committed"; + if ($committed == ($svn_rev + 1)) { + push @svn_up, "-r$committed"; sys(@svn_up); my $info = svn_info('.'); my $date = $info->{'Last Changed Date'} or die "Missing date\n"; - if ($info->{'Last Changed Rev'} != $rev_committed) { - croak "$info->{'Last Changed Rev'} != $rev_committed\n" + if ($info->{'Last Changed Rev'} != $committed) { + croak "$info->{'Last Changed Rev'} != $committed\n" } my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~ /(\d{4})\-(\d\d)\-(\d\d)\s @@ -728,16 +740,16 @@ sub svn_commit_tree { or croak "Failed to parse date: $date\n"; $log_msg{date} = "$tz $Y-$m-$d $H:$M:$S"; $log_msg{author} = $info->{'Last Changed Author'}; - $log_msg{revision} = $rev_committed; + $log_msg{revision} = $committed; $log_msg{msg} .= "\n"; my $parent = file_to_s("$REV_DIR/$svn_rev"); git_commit(\%log_msg, $parent, $commit); - return $rev_committed; + return $committed; } # resync immediately push @svn_up, "-r$svn_rev"; sys(@svn_up); - return fetch("$rev_committed=$commit")->{revision}; + return fetch("$committed=$commit")->{revision}; } # read the entire log into a temporary file (which is removed ASAP) From b63af9b340dd831840c70103c9f609940a910031 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Sat, 3 Jun 2006 02:56:33 -0700 Subject: [PATCH 05/25] git-svn: don't allow commit if svn tree is not current If new revisions are fetched, that implies we haven't merged, acked, or nacked them yet, and attempting to write the tree we're committing means we'd silently clobber the newly fetched changes. Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 8bc3d69fdb..72129de6a3 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -309,9 +309,16 @@ sub commit { } chomp @revs; - fetch(); - chdir $SVN_WC or croak $!; + chdir $SVN_WC or croak "Unable to chdir $SVN_WC: $!\n"; my $info = svn_info('.'); + my $fetched = fetch(); + if ($info->{Revision} != $fetched->{revision}) { + print STDERR "There are new revisions that were fetched ", + "and need to be merged (or acknowledged) ", + "before committing.\n"; + exit 1; + } + $info = svn_info('.'); read_uuid($info); my $svn_current_rev = $info->{'Last Changed Rev'}; foreach my $c (@revs) { From 162f41292167a800432fc6bbacfcd9f93a90b0c8 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Sun, 14 May 2006 20:00:00 -0700 Subject: [PATCH 06/25] git-svn: support -C passing to git-diff-tree The repo-config key is 'svn.copysimilarity' Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 72129de6a3..089d597d25 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -33,7 +33,8 @@ my $sha1 = qr/[a-f\d]{40}/; my $sha1_short = qr/[a-f\d]{4,40}/; my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, - $_find_copies_harder, $_l, $_version, $_upgrade, $_authors); + $_find_copies_harder, $_l, $_cp_similarity, + $_version, $_upgrade, $_authors); my (@_branch_from, %tree_map, %users); my ($_svn_co_url_revs, $_svn_pg_peg_revs); @@ -55,6 +56,7 @@ 'rmdir' => \$_rmdir, 'find-copies-harder' => \$_find_copies_harder, 'l=i' => \$_l, + 'copy-similarity|C=i'=> \$_cp_similarity, %fc_opts, } ], 'show-ignore' => [ \&show_ignore, "Show svn:ignore listings", { } ], @@ -580,7 +582,12 @@ sub svn_checkout_tree { my $pid = open my $diff_fh, '-|'; defined $pid or croak $!; if ($pid == 0) { - my @diff_tree = qw(git-diff-tree -z -r -C); + my @diff_tree = qw(git-diff-tree -z -r); + if ($_cp_similarity) { + push @diff_tree, "-C$_cp_similarity"; + } else { + push @diff_tree, '-C'; + } push @diff_tree, '--find-copies-harder' if $_find_copies_harder; push @diff_tree, "-l$_l" if defined $_l; exec(@diff_tree, $from, $treeish) or croak $!; From bf78b1d89b29f8524ccfbd7042fa277277e316ff Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Fri, 28 Apr 2006 03:42:38 -0700 Subject: [PATCH 07/25] git-svn: --branch-all-refs / -B support This should make life easier for all those who type: `git-rev-parse --symbolic --all | xargs -n1 echo -b` every time they run git-svn fetch. Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 089d597d25..c91160d37f 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -34,12 +34,13 @@ my $sha1_short = qr/[a-f\d]{4,40}/; my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, $_find_copies_harder, $_l, $_cp_similarity, - $_version, $_upgrade, $_authors); + $_version, $_upgrade, $_authors, $_branch_all_refs); my (@_branch_from, %tree_map, %users); my ($_svn_co_url_revs, $_svn_pg_peg_revs); my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext, 'branch|b=s' => \@_branch_from, + 'branch-all-refs|B' => \$_branch_all_refs, 'authors-file|A=s' => \$_authors ); # yes, 'native' sets "\n". Patches to fix this for non-*nix systems welcome: @@ -108,6 +109,7 @@ version() if $_version; usage(1) unless defined $cmd; load_authors() if $_authors; +load_all_refs() if $_branch_all_refs; svn_compat_check(); $cmd{$cmd}->[0]->(@ARGV); exit 0; @@ -1238,6 +1240,17 @@ sub map_tree_joins { } } +sub load_all_refs { + if (@_branch_from) { + print STDERR '--branch|-b parameters are ignored when ', + "--branch-all-refs|-B is passed\n"; + } + + # don't worry about rev-list on non-commit objects/tags, + # it shouldn't blow up if a ref is a blob or tree... + chomp(@_branch_from = `git-rev-parse --symbolic --all`); +} + # ' = real-name ' mapping based on git-svnimport: sub load_authors { open my $authors, '<', $_authors or die "Can't open $_authors $!\n"; From 098749d9bee6694abc8a0991996ff94b607abc7f Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Fri, 28 Apr 2006 03:51:16 -0700 Subject: [PATCH 08/25] git-svn: optimize --branch and --branch-all-ref By breaking the pipe read once we've seen a commit twice. This should make -B/--branch-all-ref faster and usable on a frequent basis. We use topological order now for calling git-rev-list, and any commit we've seen before should imply that all parents have been seen (at least I hope that's the case for --topo-order). Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index c91160d37f..d4b9323694 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -1220,23 +1220,30 @@ sub check_upgrade_needed { # fills %tree_map with a reverse mapping of trees to commits. Useful # for finding parents to commit on. sub map_tree_joins { + my %seen; foreach my $br (@_branch_from) { my $pid = open my $pipe, '-|'; defined $pid or croak $!; if ($pid == 0) { - exec(qw(git-rev-list --pretty=raw), $br) or croak $?; + exec(qw(git-rev-list --topo-order --pretty=raw), $br) + or croak $?; } while (<$pipe>) { if (/^commit ($sha1)$/o) { my $commit = $1; + + # if we've seen a commit, + # we've seen its parents + last if $seen{$commit}; my ($tree) = (<$pipe> =~ /^tree ($sha1)$/o); unless (defined $tree) { die "Failed to parse commit $commit\n"; } push @{$tree_map{$tree}}, $commit; + $seen{$commit} = 1; } } - close $pipe or croak $?; + close $pipe; # we could be breaking the pipe early } } From 6dfbe5163e26e3e1126c9b08c3cb38195e92a82c Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Wed, 3 May 2006 22:54:00 -0700 Subject: [PATCH 09/25] git-svn: support manually placed initial trees from fetch Sometimes I don't feel like downloading an entire tree again when I actually decide a branch is worth tracking, so some users can get around it more easily with this. Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index d4b9323694..54f3d6312e 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -262,7 +262,14 @@ sub fetch { } else { chdir $SVN_WC or croak $!; read_uuid(); - $last_commit = file_to_s("$REV_DIR/$base->{revision}"); + eval { $last_commit = file_to_s("$REV_DIR/$base->{revision}") }; + # looks like a user manually cp'd and svn switch'ed + unless ($last_commit) { + sys(qw/svn revert -R ./); + assert_svn_wc_clean($base->{revision}); + $last_commit = git_commit($base, @parents); + assert_tree($last_commit); + } } my @svn_up = qw(svn up); push @svn_up, '--ignore-externals' unless $_no_ignore_ext; From 883d0a78d2a28add079f809ffb8dd077f4a766d8 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Wed, 24 May 2006 01:22:07 -0700 Subject: [PATCH 10/25] git-svn: Move all git-svn-related paths into $GIT_DIR/svn Since GIT_SVN_ID usage is probably going to become more widespread , we won't run the chance of somebody having a GIT_SVN_ID name that conflicts with one of the default directories that already exist in $GIT_DIR (branches/tags). Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 99 +++++++++++++++++++++++++++----- contrib/git-svn/t/lib-git-svn.sh | 2 +- 2 files changed, 85 insertions(+), 16 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 54f3d6312e..2dce4e7b83 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -6,7 +6,7 @@ use vars qw/ $AUTHOR $VERSION $SVN_URL $SVN_INFO $SVN_WC $SVN_UUID $GIT_SVN_INDEX $GIT_SVN - $GIT_DIR $REV_DIR/; + $GIT_DIR $REV_DIR $GIT_SVN_DIR/; $AUTHOR = 'Eric Wong '; $VERSION = '1.1.0-pre'; @@ -37,6 +37,7 @@ $_version, $_upgrade, $_authors, $_branch_all_refs); my (@_branch_from, %tree_map, %users); my ($_svn_co_url_revs, $_svn_pg_peg_revs); +my @repo_path_split_cache; my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext, 'branch|b=s' => \@_branch_from, @@ -100,10 +101,11 @@ 'id|i=s' => \$GIT_SVN) or exit 1; $GIT_SVN ||= $ENV{GIT_SVN_ID} || 'git-svn'; -$GIT_SVN_INDEX = "$GIT_DIR/$GIT_SVN/index"; +$GIT_SVN_DIR = "$GIT_DIR/svn/$GIT_SVN"; +$GIT_SVN_INDEX = "$GIT_SVN_DIR/index"; $SVN_URL = undef; -$REV_DIR = "$GIT_DIR/$GIT_SVN/revs"; -$SVN_WC = "$GIT_DIR/$GIT_SVN/tree"; +$REV_DIR = "$GIT_SVN_DIR/revs"; +$SVN_WC = "$GIT_SVN_DIR/tree"; usage(0) if $_help; version() if $_version; @@ -111,6 +113,7 @@ load_authors() if $_authors; load_all_refs() if $_branch_all_refs; svn_compat_check(); +migration_check() unless $cmd eq 'init'; $cmd{$cmd}->[0]->(@ARGV); exit 0; @@ -200,7 +203,7 @@ sub rebuild { $latest = $rev; } assert_revision_eq_or_unknown($rev, $c); - sys('git-update-ref',"$GIT_SVN/revs/$rev",$c); + sys('git-update-ref',"svn/$GIT_SVN/revs/$rev",$c); $newest_rev = $rev if ($rev > $newest_rev); } close $rev_list or croak $?; @@ -241,7 +244,7 @@ sub init { sub fetch { my (@parents) = @_; check_upgrade_needed(); - $SVN_URL ||= file_to_s("$GIT_DIR/$GIT_SVN/info/url"); + $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); my @log_args = -d $SVN_WC ? ($SVN_WC) : ($SVN_URL); unless ($_revision) { $_revision = -d $SVN_WC ? 'BASE:HEAD' : '0:HEAD'; @@ -350,7 +353,7 @@ sub show_ignore { chomp(my @excludes = (<$fh>)); close $fh or croak $!; - $SVN_URL ||= file_to_s("$GIT_DIR/$GIT_SVN/info/url"); + $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); chdir $SVN_WC or croak $!; my %ign; File::Find::find({wanted=>sub{if(lstat $_ && -d _ && -d "$_/.svn"){ @@ -374,7 +377,44 @@ sub read_uuid { my $info = shift || svn_info('.'); $SVN_UUID = $info->{'Repository UUID'} or croak "Repository UUID unreadable\n"; - s_to_file($SVN_UUID,"$GIT_DIR/$GIT_SVN/info/uuid"); + s_to_file($SVN_UUID,"$GIT_SVN_DIR/info/uuid"); +} + +sub quiet_run { + my $pid = fork; + defined $pid or croak $!; + if (!$pid) { + open my $null, '>', '/dev/null' or croak $!; + open STDERR, '>&', $null or croak $!; + open STDOUT, '>&', $null or croak $!; + exec @_ or croak $!; + } + waitpid $pid, 0; + return $?; +} + +sub repo_path_split { + my $full_url = shift; + $full_url =~ s#/+$##; + + foreach (@repo_path_split_cache) { + if ($full_url =~ s#$_##) { + my $u = $1; + $full_url =~ s#^/+##; + return ($u, $full_url); + } + } + + my ($url, $path) = ($full_url =~ m!^([a-z\+]+://[^/]*)(.*)$!i); + $path =~ s#^/+##; + my @paths = split(m#/+#, $path); + + while (quiet_run(qw/svn ls --non-interactive/, $url)) { + my $n = shift @paths || last; + $url .= "/$n"; + } + push @repo_path_split_cache, qr/^(\Q$url\E)/; + return ($url, $path); } sub setup_git_svn { @@ -382,14 +422,17 @@ sub setup_git_svn { unless (-d $GIT_DIR) { croak "GIT_DIR=$GIT_DIR does not exist!\n"; } - mkpath(["$GIT_DIR/$GIT_SVN"]); - mkpath(["$GIT_DIR/$GIT_SVN/info"]); + mkpath([$GIT_SVN_DIR]); + mkpath(["$GIT_SVN_DIR/info"]); mkpath([$REV_DIR]); - s_to_file($SVN_URL,"$GIT_DIR/$GIT_SVN/info/url"); + s_to_file($SVN_URL,"$GIT_SVN_DIR/info/url"); - open my $fd, '>>', "$GIT_DIR/$GIT_SVN/info/exclude" or croak $!; + open my $fd, '>>', "$GIT_SVN_DIR/info/exclude" or croak $!; print $fd '.svn',"\n"; close $fd or croak $!; + my ($url, $path) = repo_path_split($SVN_URL); + s_to_file($url, "$GIT_SVN_DIR/info/repo_url"); + s_to_file($path, "$GIT_SVN_DIR/info/repo_path"); } sub assert_svn_wc_clean { @@ -688,7 +731,7 @@ sub handle_rmdir { sub svn_commit_tree { my ($svn_rev, $commit) = @_; - my $commit_msg = "$GIT_DIR/$GIT_SVN/.svn-commit.tmp.$$"; + my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$"; my %log_msg = ( msg => '' ); open my $msg, '>', $commit_msg or croak $!; @@ -965,7 +1008,7 @@ sub index_changes { 'remove', $no_text_base); do_update_index([qw/git-ls-files -z --others/, - "--exclude-from=$GIT_DIR/$GIT_SVN/info/exclude"], + "--exclude-from=$GIT_SVN_DIR/info/exclude"], 'add', $no_text_base); } @@ -1097,7 +1140,7 @@ sub git_commit { push @update_ref, $primary_parent unless $?; } sys(@update_ref); - sys('git-update-ref',"$GIT_SVN/revs/$log_msg->{revision}",$commit); + sys('git-update-ref',"svn/$GIT_SVN/revs/$log_msg->{revision}",$commit); print "r$log_msg->{revision} = $commit\n"; return $commit; } @@ -1283,6 +1326,32 @@ sub svn_propget_base { return safe_qx(qw/svn propget/, $p, $f); } +sub migration_check { + return if (-d "$GIT_DIR/svn" || !-d $GIT_DIR); + print "Upgrading repository...\n"; + unless (-d "$GIT_DIR/svn") { + mkdir "$GIT_DIR/svn" or croak $!; + } + print "Data from a previous version of git-svn exists, but\n\t", + "$GIT_SVN_DIR\n\t(required for this version ", + "($VERSION) of git-svn) does not.\n"; + + foreach my $x (`git-rev-parse --symbolic --all`) { + next unless $x =~ s#^refs/remotes/##; + chomp $x; + next unless -f "$GIT_DIR/$x/info/url"; + my $u = eval { file_to_s("$GIT_DIR/$x/info/url") }; + next unless $u; + my $dn = dirname("$GIT_DIR/svn/$x"); + mkpath([$dn]) unless -d $dn; + rename "$GIT_DIR/$x", "$GIT_DIR/svn/$x" or croak "$!: $x"; + my ($url, $path) = repo_path_split($u); + s_to_file($url, "$GIT_DIR/svn/$x/info/repo_url"); + s_to_file($path, "$GIT_DIR/svn/$x/info/repo_path"); + } + print "Done upgrading.\n"; +} + __END__ Data structures: diff --git a/contrib/git-svn/t/lib-git-svn.sh b/contrib/git-svn/t/lib-git-svn.sh index a98e9d164d..58408a6c07 100644 --- a/contrib/git-svn/t/lib-git-svn.sh +++ b/contrib/git-svn/t/lib-git-svn.sh @@ -10,7 +10,7 @@ fi . ./test-lib.sh GIT_DIR=$PWD/.git -GIT_SVN_DIR=$GIT_DIR/git-svn +GIT_SVN_DIR=$GIT_DIR/svn/git-svn SVN_TREE=$GIT_SVN_DIR/tree svnadmin >/dev/null 2>&1 From b8c92caddac61e556254bf93c3a4bd744de94320 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Wed, 24 May 2006 01:40:37 -0700 Subject: [PATCH 11/25] git-svn: minor cleanups, extra error-checking While we're at it, read_repo_config has been added and expanded to handle case where command-line arguments are optional to Getopt::Long Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 82 ++++++++++++++++++++---------------- 1 file changed, 46 insertions(+), 36 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 2dce4e7b83..a24306072e 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -77,39 +77,15 @@ my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd); -# convert GetOpt::Long specs for use by git-repo-config -foreach my $o (keys %opts) { - my $v = $opts{$o}; - my ($key) = ($o =~ /^([a-z\-]+)/); - $key =~ s/-//g; - my $arg = 'git-repo-config'; - $arg .= ' --int' if ($o =~ /=i$/); - $arg .= ' --bool' if ($o !~ /=[sfi]$/); - if (ref $v eq 'ARRAY') { - chomp(my @tmp = `$arg --get-all svn.$key`); - @$v = @tmp if @tmp; - } else { - chomp(my $tmp = `$arg --get svn.$key`); - if ($tmp && !($arg =~ / --bool / && $tmp eq 'false')) { - $$v = $tmp; - } - } -} - +read_repo_config(\%opts); GetOptions(%opts, 'help|H|h' => \$_help, 'version|V' => \$_version, 'id|i=s' => \$GIT_SVN) or exit 1; -$GIT_SVN ||= $ENV{GIT_SVN_ID} || 'git-svn'; -$GIT_SVN_DIR = "$GIT_DIR/svn/$GIT_SVN"; -$GIT_SVN_INDEX = "$GIT_SVN_DIR/index"; -$SVN_URL = undef; -$REV_DIR = "$GIT_SVN_DIR/revs"; -$SVN_WC = "$GIT_SVN_DIR/tree"; - usage(0) if $_help; version() if $_version; usage(1) unless defined $cmd; +init_vars(); load_authors() if $_authors; load_all_refs() if $_branch_all_refs; svn_compat_check(); @@ -132,7 +108,7 @@ sub usage { print $fd ' ',pack('A13',$_),$cmd{$_}->[1],"\n"; foreach (keys %{$cmd{$_}->[2]}) { # prints out arguments as they should be passed: - my $x = s#=s$## ? '' : s#=i$## ? '' : ''; + my $x = s#[:=]s$## ? '' : s#[:=]i$## ? '' : ''; print $fd ' ' x 17, join(', ', map { length $_ > 1 ? "--$_" : "-$_" } split /\|/,$_)," $x\n"; @@ -220,9 +196,10 @@ sub rebuild { sys(@svn_up,"-r$newest_rev"); $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX; index_changes(); - exec('git-write-tree'); + exec('git-write-tree') or croak $!; } waitpid $pid, 0; + croak $? if $?; if ($_upgrade) { print STDERR <<""; @@ -295,6 +272,7 @@ sub fetch { unless (-e "$GIT_DIR/refs/heads/master") { sys(qw(git-update-ref refs/heads/master),$last_commit); } + close $svn_log->{fh}; return $last; } @@ -830,7 +808,7 @@ sub svn_log_raw { exec (qw(svn log), @log_args) or croak $! } waitpid $pid, 0; - croak if $?; + croak $? if $?; seek $log_fh, 0, 0 or croak $!; return { state => 'sep', fh => $log_fh }; } @@ -1090,7 +1068,7 @@ sub git_commit { $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX; index_changes(); chomp(my $tree = `git-write-tree`); - croak if $?; + croak $? if $?; if (exists $tree_map{$tree}) { my %seen_parent = map { $_ => 1 } @exec_parents; foreach (@{$tree_map{$tree}}) { @@ -1118,7 +1096,7 @@ sub git_commit { exec @exec or croak $!; } waitpid($pid,0); - croak if $?; + croak $? if $?; $out_fh->flush == 0 or croak $!; seek $out_fh, 0, 0 or croak $!; @@ -1134,7 +1112,7 @@ sub git_commit { close STDERR; close STDOUT; exec 'git-rev-parse','--verify', - "refs/remotes/$GIT_SVN^0"; + "refs/remotes/$GIT_SVN^0" or croak $!; } waitpid $pid, 0; push @update_ref, $primary_parent unless $?; @@ -1190,7 +1168,7 @@ sub blob_to_file { if ($pid == 0) { open STDOUT, '>&', $blob_fh or croak $!; - exec('git-cat-file','blob',$blob); + exec('git-cat-file','blob',$blob) or croak $!; } waitpid $pid, 0; croak $? if $?; @@ -1202,7 +1180,7 @@ sub safe_qx { my $pid = open my $child, '-|'; defined $pid or croak $!; if ($pid == 0) { - exec(@_) or croak $?; + exec(@_) or croak $!; } my @ret = (<$child>); close $child or croak $?; @@ -1252,7 +1230,7 @@ sub check_upgrade_needed { defined $pid or croak $!; if ($pid == 0) { close STDERR; - exec('git-rev-parse',"$GIT_SVN-HEAD") or croak $?; + exec('git-rev-parse',"$GIT_SVN-HEAD") or croak $!; } my @ret = (<$child>); close $child or croak $?; @@ -1276,7 +1254,7 @@ sub map_tree_joins { defined $pid or croak $!; if ($pid == 0) { exec(qw(git-rev-list --topo-order --pretty=raw), $br) - or croak $?; + or croak $!; } while (<$pipe>) { if (/^commit ($sha1)$/o) { @@ -1352,6 +1330,38 @@ sub migration_check { print "Done upgrading.\n"; } +sub init_vars { + $GIT_SVN ||= $ENV{GIT_SVN_ID} || 'git-svn'; + $GIT_SVN_DIR = "$GIT_DIR/svn/$GIT_SVN"; + $GIT_SVN_INDEX = "$GIT_SVN_DIR/index"; + $SVN_URL = undef; + $REV_DIR = "$GIT_SVN_DIR/revs"; + $SVN_WC = "$GIT_SVN_DIR/tree"; +} + +# convert GetOpt::Long specs for use by git-repo-config +sub read_repo_config { + return unless -d $GIT_DIR; + my $opts = shift; + foreach my $o (keys %$opts) { + my $v = $opts->{$o}; + my ($key) = ($o =~ /^([a-z\-]+)/); + $key =~ s/-//g; + my $arg = 'git-repo-config'; + $arg .= ' --int' if ($o =~ /[:=]i$/); + $arg .= ' --bool' if ($o !~ /[:=][sfi]$/); + if (ref $v eq 'ARRAY') { + chomp(my @tmp = `$arg --get-all svn.$key`); + @$v = @tmp if @tmp; + } else { + chomp(my $tmp = `$arg --get svn.$key`); + if ($tmp && !($arg =~ / --bool / && $tmp eq 'false')) { + $$v = $tmp; + } + } + } +} + __END__ Data structures: From dc5869c00d9aafbddcc11b93b5a0a7fcdeb755ea Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Wed, 24 May 2006 02:07:32 -0700 Subject: [PATCH 12/25] git-svn: add --repack and --repack-flags= options This should help keep disk usage sane for large imports. --repack takes an optional argument for the interval, it defaults to 1000 if no argument is specified. Arguments to --repack-flags are passed directly to git-repack. No arguments are passed by default. Idea stolen from git-cvsimport :) Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index a24306072e..a04cf1d354 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -34,6 +34,7 @@ my $sha1_short = qr/[a-f\d]{4,40}/; my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, $_find_copies_harder, $_l, $_cp_similarity, + $_repack, $_repack_nr, $_repack_flags, $_version, $_upgrade, $_authors, $_branch_all_refs); my (@_branch_from, %tree_map, %users); my ($_svn_co_url_revs, $_svn_pg_peg_revs); @@ -42,7 +43,9 @@ my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext, 'branch|b=s' => \@_branch_from, 'branch-all-refs|B' => \$_branch_all_refs, - 'authors-file|A=s' => \$_authors ); + 'authors-file|A=s' => \$_authors, + 'repack:i' => \$_repack, + 'repack-flags|repack-args|repack-opts=s' => \$_repack_flags); # yes, 'native' sets "\n". Patches to fix this for non-*nix systems welcome: my %EOL = ( CR => "\015", LF => "\012", CRLF => "\015\012", native => "\012" ); @@ -82,6 +85,7 @@ 'version|V' => \$_version, 'id|i=s' => \$GIT_SVN) or exit 1; +set_default_vals(); usage(0) if $_help; version() if $_version; usage(1) unless defined $cmd; @@ -1120,6 +1124,10 @@ sub git_commit { sys(@update_ref); sys('git-update-ref',"svn/$GIT_SVN/revs/$log_msg->{revision}",$commit); print "r$log_msg->{revision} = $commit\n"; + if ($_repack && (--$_repack_nr == 0)) { + $_repack_nr = $_repack; + sys("git repack $_repack_flags"); + } return $commit; } @@ -1362,6 +1370,14 @@ sub read_repo_config { } } +sub set_default_vals { + if (defined $_repack) { + $_repack = 1000 if ($_repack <= 0); + $_repack_nr = $_repack; + $_repack_flags ||= ''; + } +} + __END__ Data structures: From f8ab6b732f0a2cead5089aea2ce0c3c3aa97cafe Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Wed, 31 May 2006 15:49:56 -0700 Subject: [PATCH 13/25] git-svn: add --shared and --template= options to pass to init-db Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index a04cf1d354..d8f103ed9a 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -35,6 +35,7 @@ my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, $_find_copies_harder, $_l, $_cp_similarity, $_repack, $_repack_nr, $_repack_flags, + $_template, $_shared, $_version, $_upgrade, $_authors, $_branch_all_refs); my (@_branch_from, %tree_map, %users); my ($_svn_co_url_revs, $_svn_pg_peg_revs); @@ -54,7 +55,9 @@ fetch => [ \&fetch, "Download new revisions from SVN", { 'revision|r=s' => \$_revision, %fc_opts } ], init => [ \&init, "Initialize a repo for tracking" . - " (requires URL argument)", { } ], + " (requires URL argument)", + { 'template=s' => \$_template, + 'shared' => \$_shared } ], commit => [ \&commit, "Commit git revisions to SVN", { 'stdin|' => \$_stdin, 'edit|e' => \$_edit, @@ -217,7 +220,10 @@ sub init { $SVN_URL = shift or die "SVN repository location required " . "as a command-line argument\n"; unless (-d $GIT_DIR) { - sys('git-init-db'); + my @init_db = ('git-init-db'); + push @init_db, "--template=$_template" if defined $_template; + push @init_db, "--shared" if defined $_shared; + sys(@init_db); } setup_git_svn(); } From 9d55b41aadd65b1ebfbbe1336db00168c2dd01c5 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Mon, 12 Jun 2006 15:53:13 -0700 Subject: [PATCH 14/25] git-svn: add some functionality to better support branches in svn New commands: graft-branches - The most interesting command of the bunch. It detects branches in SVN via various techniques (currently regexes and file copies). It can be later extended to handle svk and other properties people may use to track merges in svk. Basically, merge tracking is not standardized at all in the SVN world, and git grafts are perfect for dealing with this situation. Existing branch support (via tree matches) is only handled at fetch time. The following tow were originally implemented as shell scripts several months ago, but I just decided to streamline things a bit and added them to the main script. multi-init - supports git-svnimport-like command-line syntax for importing repositories that are layed out as recommended by the SVN folks. This is a bit more tolerant than the git-svnimport command-line syntax and doesn't require the user to figure out where the repository URL ends and where the repository path begins. multi-fetch - runs fetch on all known SVN branches we're tracking. This will NOT discover new branches (unlike git-svnimport), so multi-init will need to be re-run (it's idempotent). Consider these three to be auxilliary commands (like show-ignore, and rebuild) so their behavior won't receive as much testing or scrutiny as the core commands (fetch and commit). Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 429 ++++++++++++++++++++++++++++++++++- 1 file changed, 424 insertions(+), 5 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index d8f103ed9a..d5c7e47967 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -35,8 +35,8 @@ my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, $_find_copies_harder, $_l, $_cp_similarity, $_repack, $_repack_nr, $_repack_flags, - $_template, $_shared, - $_version, $_upgrade, $_authors, $_branch_all_refs); + $_template, $_shared, $_no_default_regex, $_no_graft_copy, + $_version, $_upgrade, $_authors, $_branch_all_refs, @_opt_m); my (@_branch_from, %tree_map, %users); my ($_svn_co_url_revs, $_svn_pg_peg_revs); my @repo_path_split_cache; @@ -48,6 +48,12 @@ 'repack:i' => \$_repack, 'repack-flags|repack-args|repack-opts=s' => \$_repack_flags); +my ($_trunk, $_tags, $_branches); +my %multi_opts = ( 'trunk|T=s' => \$_trunk, + 'tags|t=s' => \$_tags, + 'branches|b=s' => \$_branches ); +my %init_opts = ( 'template=s' => \$_template, 'shared' => \$_shared ); + # yes, 'native' sets "\n". Patches to fix this for non-*nix systems welcome: my %EOL = ( CR => "\015", LF => "\012", CRLF => "\015\012", native => "\012" ); @@ -56,8 +62,7 @@ { 'revision|r=s' => \$_revision, %fc_opts } ], init => [ \&init, "Initialize a repo for tracking" . " (requires URL argument)", - { 'template=s' => \$_template, - 'shared' => \$_shared } ], + \%init_opts ], commit => [ \&commit, "Commit git revisions to SVN", { 'stdin|' => \$_stdin, 'edit|e' => \$_edit, @@ -71,7 +76,19 @@ rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)", { 'no-ignore-externals' => \$_no_ignore_ext, 'upgrade' => \$_upgrade } ], + 'graft-branches' => [ \&graft_branches, + 'Detect merges/branches from already imported history', + { 'merge-rx|m' => \@_opt_m, + 'no-default-regex' => \$_no_default_regex, + 'no-graft-copy' => \$_no_graft_copy } ], + 'multi-init' => [ \&multi_init, + 'Initialize multiple trees (like git-svnimport)', + { %multi_opts, %fc_opts } ], + 'multi-fetch' => [ \&multi_fetch, + 'Fetch multiple trees (like git-svnimport)', + \%fc_opts ], ); + my $cmd; for (my $i = 0; $i < @ARGV; $i++) { if (defined $cmd{$ARGV[$i]}) { @@ -96,7 +113,7 @@ load_authors() if $_authors; load_all_refs() if $_branch_all_refs; svn_compat_check(); -migration_check() unless $cmd eq 'init'; +migration_check() unless $cmd =~ /^(?:init|multi-init)$/; $cmd{$cmd}->[0]->(@ARGV); exit 0; @@ -219,6 +236,7 @@ sub rebuild { sub init { $SVN_URL = shift or die "SVN repository location required " . "as a command-line argument\n"; + $SVN_URL =~ s!/+$!!; # strip trailing slash unless (-d $GIT_DIR) { my @init_db = ('git-init-db'); push @init_db, "--template=$_template" if defined $_template; @@ -358,8 +376,283 @@ sub show_ignore { } } +sub graft_branches { + my $gr_file = "$GIT_DIR/info/grafts"; + my ($grafts, $comments) = read_grafts($gr_file); + my $gr_sha1; + + if (%$grafts) { + # temporarily disable our grafts file to make this idempotent + chomp($gr_sha1 = safe_qx(qw/git-hash-object -w/,$gr_file)); + rename $gr_file, "$gr_file~$gr_sha1" or croak $!; + } + + my $l_map = read_url_paths(); + my @re = map { qr/$_/is } @_opt_m if @_opt_m; + unless ($_no_default_regex) { + push @re, ( qr/\b(?:merge|merging|merged)\s+(\S.+)/is, + qr/\b(?:from|of)\s+(\S.+)/is ); + } + foreach my $u (keys %$l_map) { + if (@re) { + foreach my $p (keys %{$l_map->{$u}}) { + graft_merge_msg($grafts,$l_map,$u,$p); + } + } + graft_file_copy($grafts,$l_map,$u) unless $_no_graft_copy; + } + + write_grafts($grafts, $comments, $gr_file); + unlink "$gr_file~$gr_sha1" if $gr_sha1; +} + +sub multi_init { + my $url = shift; + $_trunk ||= 'trunk'; + $_trunk =~ s#/+$##; + $url =~ s#/+$## if $url; + if ($_trunk !~ m#^[a-z\+]+://#) { + $_trunk = '/' . $_trunk if ($_trunk !~ m#^/#); + unless ($url) { + print STDERR "E: '$_trunk' is not a complete URL ", + "and a separate URL is not specified\n"; + exit 1; + } + $_trunk = $url . $_trunk; + } + if ($GIT_SVN eq 'git-svn') { + print "GIT_SVN_ID set to 'trunk' for $_trunk\n"; + $GIT_SVN = $ENV{GIT_SVN_ID} = 'trunk'; + } + init_vars(); + init($_trunk); + complete_url_ls_init($url, $_branches, '--branches/-b', ''); + complete_url_ls_init($url, $_tags, '--tags/-t', 'tags/'); +} + +sub multi_fetch { + # try to do trunk first, since branches/tags + # may be descended from it. + if (-d "$GIT_DIR/svn/trunk") { + print "Fetching trunk\n"; + defined(my $pid = fork) or croak $!; + if (!$pid) { + $GIT_SVN = $ENV{GIT_SVN_ID} = 'trunk'; + init_vars(); + fetch(@_); + exit 0; + } + waitpid $pid, 0; + croak $? if $?; + } + rec_fetch('', "$GIT_DIR/svn", @_); +} + ########################### utility functions ######################### +sub rec_fetch { + my ($pfx, $p, @args) = @_; + my @dir; + foreach (sort <$p/*>) { + if (-r "$_/info/url") { + $pfx .= '/' if $pfx && $pfx !~ m!/$!; + my $id = $pfx . basename $_; + next if $id eq 'trunk'; + print "Fetching $id\n"; + defined(my $pid = fork) or croak $!; + if (!$pid) { + $GIT_SVN = $ENV{GIT_SVN_ID} = $id; + init_vars(); + fetch(@args); + exit 0; + } + waitpid $pid, 0; + croak $? if $?; + } elsif (-d $_) { + push @dir, $_; + } + } + foreach (@dir) { + my $x = $_; + $x =~ s!^\Q$GIT_DIR\E/svn/!!; + rec_fetch($x, $_); + } +} + +sub complete_url_ls_init { + my ($url, $var, $switch, $pfx) = @_; + unless ($var) { + print STDERR "W: $switch not specified\n"; + return; + } + $var =~ s#/+$##; + if ($var !~ m#^[a-z\+]+://#) { + $var = '/' . $var if ($var !~ m#^/#); + unless ($url) { + print STDERR "E: '$var' is not a complete URL ", + "and a separate URL is not specified\n"; + exit 1; + } + $var = $url . $var; + } + chomp(my @ls = safe_qx(qw/svn ls --non-interactive/, $var)); + my $old = $GIT_SVN; + defined(my $pid = fork) or croak $!; + if (!$pid) { + foreach my $u (map { "$var/$_" } (grep m!/$!, @ls)) { + $u =~ s#/+$##; + if ($u !~ m!\Q$var\E/(.+)$!) { + print STDERR "W: Unrecognized URL: $u\n"; + die "This should never happen\n"; + } + my $id = $pfx.$1; + print "init $u => $id\n"; + $GIT_SVN = $ENV{GIT_SVN_ID} = $id; + init_vars(); + init($u); + } + exit 0; + } + waitpid $pid, 0; + croak $? if $?; +} + +sub common_prefix { + my $paths = shift; + my %common; + foreach (@$paths) { + my @tmp = split m#/#, $_; + my $p = ''; + while (my $x = shift @tmp) { + $p .= "/$x"; + $common{$p} ||= 0; + $common{$p}++; + } + } + foreach (sort {length $b <=> length $a} keys %common) { + if ($common{$_} == @$paths) { + return $_; + } + } + return ''; +} + +# this isn't funky-filename safe, but good enough for now... +sub graft_file_copy { + my ($grafts, $l_map, $u) = @_; + my $paths = $l_map->{$u}; + my $pfx = common_prefix([keys %$paths]); + + my $pid = open my $fh, '-|'; + defined $pid or croak $!; + unless ($pid) { + exec(qw/svn log -v/, $u.$pfx) or croak $!; + } + my ($r, $mp) = (undef, undef); + while (<$fh>) { + chomp; + if (/^\-{72}$/) { + $mp = $r = undef; + } elsif (/^r(\d+) \| /) { + $r = $1 unless defined $r; + } elsif (/^Changed paths:/) { + $mp = 1; + } elsif ($mp && m#^ [AR] /(\S.*?) \(from /(\S+?):(\d+)\)$#) { + my $dbg = "r$r | $_"; + my ($p1, $p0, $r0) = ($1, $2, $3); + my $c; + foreach my $x (keys %$paths) { + next unless ($p1 =~ /^\Q$x\E/); + my $i = $paths->{$x}; + my $f = "$GIT_DIR/svn/$i/revs/$r"; + unless (-r $f) { + print STDERR "r$r of $i not imported,", + " $dbg\n"; + next; + } + $c = file_to_s($f); + } + next unless $c; + foreach my $x (keys %$paths) { + next unless ($p0 =~ /^\Q$x\E/); + my $i = $paths->{$x}; + my $f = "$GIT_DIR/svn/$i/revs/$r0"; + while ($r0 && !-r $f) { + # could be an older revision, too... + $r0--; + $f = "$GIT_DIR/svn/$i/revs/$r0"; + } + unless (-r $f) { + print STDERR "r$r0 of $i not imported,", + " $dbg\n"; + next; + } + my $r1 = file_to_s($f); + $grafts->{$c}->{$r1} = 1; + } + } + } +} + +sub process_merge_msg_matches { + my ($grafts, $l_map, $u, $p, $c, @matches) = @_; + my (@strong, @weak); + foreach (@matches) { + # merging with ourselves is not interesting + next if $_ eq $p; + if ($l_map->{$u}->{$_}) { + push @strong, $_; + } else { + push @weak, $_; + } + } + foreach my $w (@weak) { + last if @strong; + # no exact match, use branch name as regexp. + my $re = qr/\Q$w\E/i; + foreach (keys %{$l_map->{$u}}) { + if (/$re/) { + push @strong, $_; + last; + } + } + last if @strong; + $w = basename($w); + $re = qr/\Q$w\E/i; + foreach (keys %{$l_map->{$u}}) { + if (/$re/) { + push @strong, $_; + last; + } + } + } + my ($rev) = ($c->{m} =~ /^git-svn-id:\s(?:\S+?)\@(\d+) + \s(?:[a-f\d\-]+)$/xsm); + unless (defined $rev) { + ($rev) = ($c->{m} =~/^git-svn-id:\s(\d+) + \@(?:[a-f\d\-]+)/xsm); + return unless defined $rev; + } + foreach my $m (@strong) { + my ($r0, $s0) = find_rev_before($rev, $m); + $grafts->{$c->{c}}->{$s0} = 1 if defined $s0; + } +} + +sub graft_merge_msg { + my ($grafts, $l_map, $u, $p, @re) = @_; + + my $x = $l_map->{$u}->{$p}; + my $rl = rev_list_raw($x); + while (my $c = next_rev_list_entry($rl)) { + foreach my $re (@re) { + my (@br) = ($c->{m} =~ /$re/g); + next unless @br; + process_merge_msg_matches($grafts,$l_map,$u,$p,$c,@br); + } + } +} + sub read_uuid { return if $SVN_UUID; my $info = shift || svn_info('.'); @@ -402,6 +695,7 @@ sub repo_path_split { $url .= "/$n"; } push @repo_path_split_cache, qr/^(\Q$url\E)/; + $path = join('/',@paths); return ($url, $path); } @@ -806,6 +1100,38 @@ sub svn_commit_tree { return fetch("$committed=$commit")->{revision}; } +sub rev_list_raw { + my (@args) = @_; + my $pid = open my $fh, '-|'; + defined $pid or croak $!; + if (!$pid) { + exec(qw/git-rev-list --pretty=raw/, @args) or croak $!; + } + return { fh => $fh, t => { } }; +} + +sub next_rev_list_entry { + my $rl = shift; + my $fh = $rl->{fh}; + my $x = $rl->{t}; + while (<$fh>) { + if (/^commit ($sha1)$/o) { + if ($x->{c}) { + $rl->{t} = { c => $1 }; + return $x; + } else { + $x->{c} = $1; + } + } elsif (/^parent ($sha1)$/o) { + $x->{p}->{$1} = 1; + } elsif (s/^ //) { + $x->{m} ||= ''; + $x->{m} .= $_; + } + } + return ($x != $rl->{t}) ? $x : undef; +} + # read the entire log into a temporary file (which is removed ASAP) # and store the file handle + parser state sub svn_log_raw { @@ -1318,6 +1644,16 @@ sub svn_propget_base { return safe_qx(qw/svn propget/, $p, $f); } +sub git_svn_each { + my $sub = shift; + foreach (`git-rev-parse --symbolic --all`) { + next unless s#^refs/remotes/##; + chomp $_; + next unless -f "$GIT_DIR/svn/$_/info/url"; + &$sub($_); + } +} + sub migration_check { return if (-d "$GIT_DIR/svn" || !-d $GIT_DIR); print "Upgrading repository...\n"; @@ -1344,6 +1680,16 @@ sub migration_check { print "Done upgrading.\n"; } +sub find_rev_before { + my ($r, $git_svn_id) = @_; + my @revs = map { basename $_ } <$GIT_DIR/svn/$git_svn_id/revs/*>; + foreach my $r0 (sort { $b <=> $a } @revs) { + next if $r0 >= $r; + return ($r0, file_to_s("$GIT_DIR/svn/$git_svn_id/revs/$r0")); + } + return (undef, undef); +} + sub init_vars { $GIT_SVN ||= $ENV{GIT_SVN_ID} || 'git-svn'; $GIT_SVN_DIR = "$GIT_DIR/svn/$GIT_SVN"; @@ -1384,6 +1730,79 @@ sub set_default_vals { } } +sub read_grafts { + my $gr_file = shift; + my ($grafts, $comments) = ({}, {}); + if (open my $fh, '<', $gr_file) { + my @tmp; + while (<$fh>) { + if (/^($sha1)\s+/) { + my $c = $1; + if (@tmp) { + @{$comments->{$c}} = @tmp; + @tmp = (); + } + foreach my $p (split /\s+/, $_) { + $grafts->{$c}->{$p} = 1; + } + } else { + push @tmp, $_; + } + } + close $fh or croak $!; + @{$comments->{'END'}} = @tmp if @tmp; + } + return ($grafts, $comments); +} + +sub write_grafts { + my ($grafts, $comments, $gr_file) = @_; + + open my $fh, '>', $gr_file or croak $!; + foreach my $c (sort keys %$grafts) { + if ($comments->{$c}) { + print $fh $_ foreach @{$comments->{$c}}; + } + my $p = $grafts->{$c}; + delete $p->{$c}; # commits are not self-reproducing... + my $pid = open my $ch, '-|'; + defined $pid or croak $!; + if (!$pid) { + exec(qw/git-cat-file commit/, $c) or croak $!; + } + while (<$ch>) { + if (/^parent ([a-f\d]{40})/) { + $p->{$1} = 1; + } else { + last unless /^\S/i; + } + } + close $ch; # breaking the pipe + print $fh $c, ' ', join(' ', sort keys %$p),"\n"; + } + if ($comments->{'END'}) { + print $fh $_ foreach @{$comments->{'END'}}; + } + close $fh or croak $!; +} + +sub read_url_paths { + my $l_map = {}; + git_svn_each(sub { my $x = shift; + my $u = file_to_s("$GIT_DIR/svn/$x/info/repo_url"); + my $p = file_to_s("$GIT_DIR/svn/$x/info/repo_path"); + # we hate trailing slashes + if ($u =~ s#(?:^\/+|\/+$)##g) { + s_to_file($u,"$GIT_DIR/svn/$x/info/repo_url"); + } + if ($p =~ s#(?:^\/+|\/+$)##g) { + s_to_file($p,"$GIT_DIR/svn/$x/info/repo_path"); + } + $l_map->{$u}->{$p} = $x; + }); + return $l_map; +} + __END__ Data structures: From 7a97de4e19757b5576f32ce67d90cb792dbb893b Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Mon, 12 Jun 2006 05:57:02 -0700 Subject: [PATCH 15/25] git-svn: add UTF-8 message test Signed-off-by: Eric Wong --- contrib/git-svn/t/t0000-contrib-git-svn.sh | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/contrib/git-svn/t/t0000-contrib-git-svn.sh b/contrib/git-svn/t/t0000-contrib-git-svn.sh index a07fbad68b..0c6ff2066b 100644 --- a/contrib/git-svn/t/t0000-contrib-git-svn.sh +++ b/contrib/git-svn/t/t0000-contrib-git-svn.sh @@ -4,6 +4,7 @@ # test_description='git-svn tests' +GIT_SVN_LC_ALL=$LC_ALL . ./lib-git-svn.sh mkdir import @@ -163,6 +164,18 @@ test_expect_success "$name" \ diff -u help $SVN_TREE/exec-2.sh" +if test -n "$GIT_SVN_LC_ALL" && echo $GIT_SVN_LC_ALL | grep -q '\.UTF-8$' +then + name="commit with UTF-8 message: locale: $GIT_SVN_LC_ALL" + echo '# hello' >> exec-2.sh + git update-index exec-2.sh + git commit -m 'éï∏' + export LC_ALL="$GIT_SVN_LC_ALL" + test_expect_success "$name" "git-svn commit HEAD" + unset LC_ALL +else + echo "UTF-8 locale not set, test skipped ($GIT_SVN_LC_ALL)" +fi name='test fetch functionality (svn => git) with alternate GIT_SVN_ID' GIT_SVN_ID=alt From 79bb8d88fc61b03a80fe99915f15a25172286c1f Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Thu, 1 Jun 2006 02:35:44 -0700 Subject: [PATCH 16/25] git-svn: add 'log' command, a facsimile of basic `svn log' This quick feature should make it easy to look up svn log messages when svn users refer to -r/--revision numbers. The following features from `svn log' are supported: --revision=[:] - is supported, non-numeric args are not: HEAD, NEXT, BASE, PREV, etc ... -v/--verbose - just maps to --raw (in git log), so it's completely incompatible with the --verbose output in svn log --limit= - is NOT the same as --max-count, doesn't count merged/excluded commits --incremental - supported (trivial :P) New features: --show-commit - shows the git commit sha1, as well --oneline - our version of --pretty=oneline Any other arguments are passed directly to `git log' Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 260 ++++++++++++++++++++++++++++++++--- 1 file changed, 243 insertions(+), 17 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index d5c7e47967..03416aeec1 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -15,6 +15,7 @@ $ENV{GIT_DIR} = $GIT_DIR; my $LC_ALL = $ENV{LC_ALL}; +my $TZ = $ENV{TZ}; # make sure the svn binary gives consistent output between locales and TZs: $ENV{TZ} = 'UTC'; $ENV{LC_ALL} = 'C'; @@ -27,7 +28,7 @@ use IO::File qw//; use File::Basename qw/dirname basename/; use File::Path qw/mkpath/; -use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/; +use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/; use File::Spec qw//; use POSIX qw/strftime/; my $sha1 = qr/[a-f\d]{40}/; @@ -36,8 +37,9 @@ $_find_copies_harder, $_l, $_cp_similarity, $_repack, $_repack_nr, $_repack_flags, $_template, $_shared, $_no_default_regex, $_no_graft_copy, + $_limit, $_verbose, $_incremental, $_oneline, $_l_fmt, $_show_commit, $_version, $_upgrade, $_authors, $_branch_all_refs, @_opt_m); -my (@_branch_from, %tree_map, %users); +my (@_branch_from, %tree_map, %users, %rusers); my ($_svn_co_url_revs, $_svn_pg_peg_revs); my @repo_path_split_cache; @@ -87,6 +89,15 @@ 'multi-fetch' => [ \&multi_fetch, 'Fetch multiple trees (like git-svnimport)', \%fc_opts ], + 'log' => [ \&show_log, 'Show commit logs', + { 'limit=i' => \$_limit, + 'revision|r=s' => \$_revision, + 'verbose|v' => \$_verbose, + 'incremental' => \$_incremental, + 'oneline' => \$_oneline, + 'show-commit' => \$_show_commit, + 'authors-file|A=s' => \$_authors, + } ], ); my $cmd; @@ -101,9 +112,10 @@ my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd); read_repo_config(\%opts); -GetOptions(%opts, 'help|H|h' => \$_help, - 'version|V' => \$_version, - 'id|i=s' => \$GIT_SVN) or exit 1; +my $rv = GetOptions(%opts, 'help|H|h' => \$_help, + 'version|V' => \$_version, + 'id|i=s' => \$GIT_SVN); +exit 1 if (!$rv && $cmd ne 'log'); set_default_vals(); usage(0) if $_help; @@ -173,18 +185,10 @@ sub rebuild { croak "Non-SHA1: $c\n" unless $c =~ /^$sha1$/o; my @commit = grep(/^git-svn-id: /,`git-cat-file commit $c`); next if (!@commit); # skip merges - my $id = $commit[$#commit]; - my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+) - \s([a-f\d\-]+)$/x); - if (!$rev || !$uuid || !$url) { - # some of the original repositories I made had - # indentifiers like this: - ($rev, $uuid) = ($id =~/^git-svn-id:\s(\d+) - \@([a-f\d\-]+)/x); - if (!$rev || !$uuid) { - croak "Unable to extract revision or UUID from ", - "$c, $id\n"; - } + my ($url, $rev, $uuid) = extract_metadata($commit[$#commit]); + if (!$rev || !$uuid) { + croak "Unable to extract revision or UUID from ", + "$c, $commit[$#commit]\n"; } # if we merged or otherwise started elsewhere, this is @@ -448,6 +452,81 @@ sub multi_fetch { rec_fetch('', "$GIT_DIR/svn", @_); } +sub show_log { + my (@args) = @_; + my ($r_min, $r_max); + my $r_last = -1; # prevent dupes + rload_authors() if $_authors; + if (defined $TZ) { + $ENV{TZ} = $TZ; + } else { + delete $ENV{TZ}; + } + if (defined $_revision) { + if ($_revision =~ /^(\d+):(\d+)$/) { + ($r_min, $r_max) = ($1, $2); + } elsif ($_revision =~ /^\d+$/) { + $r_min = $r_max = $_revision; + } else { + print STDERR "-r$_revision is not supported, use ", + "standard \'git log\' arguments instead\n"; + exit 1; + } + } + + my $pid = open(my $log,'-|'); + defined $pid or croak $!; + if (!$pid) { + my @rl = (qw/git-log --abbrev-commit --pretty=raw + --default/, "remotes/$GIT_SVN"); + push @rl, '--raw' if $_verbose; + exec(@rl, @args) or croak $!; + } + setup_pager(); + my (@k, $c, $d); + while (<$log>) { + if (/^commit ($sha1_short)/o) { + my $cmt = $1; + if ($c && defined $c->{r} && $c->{r} != $r_last) { + $r_last = $c->{r}; + process_commit($c, $r_min, $r_max, \@k) or + goto out; + } + $d = undef; + $c = { c => $cmt }; + } elsif (/^author (.+) (\d+) ([\-\+]?\d+)$/) { + get_author_info($c, $1, $2, $3); + } elsif (/^(?:tree|parent|committer) /) { + # ignore + } elsif (/^:\d{6} \d{6} $sha1_short/o) { + push @{$c->{raw}}, $_; + } elsif (/^diff /) { + $d = 1; + push @{$c->{diff}}, $_; + } elsif ($d) { + push @{$c->{diff}}, $_; + } elsif (/^ (git-svn-id:.+)$/) { + my ($url, $rev, $uuid) = extract_metadata($1); + $c->{r} = $rev; + } elsif (s/^ //) { + push @{$c->{l}}, $_; + } + } + if ($c && defined $c->{r} && $c->{r} != $r_last) { + $r_last = $c->{r}; + process_commit($c, $r_min, $r_max, \@k); + } + if (@k) { + my $swap = $r_max; + $r_max = $r_min; + $r_min = $swap; + process_commit($_, $r_min, $r_max) foreach reverse @k; + } +out: + close $log; + print '-' x72,"\n" unless $_incremental || $_oneline; +} + ########################### utility functions ######################### sub rec_fetch { @@ -1638,6 +1717,17 @@ sub load_authors { close $authors or croak $!; } +sub rload_authors { + open my $authors, '<', $_authors or die "Can't open $_authors $!\n"; + while (<$authors>) { + chomp; + next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/; + my ($user, $name, $email) = ($1, $2, $3); + $rusers{"$name <$email>"} = $user; + } + close $authors or croak $!; +} + sub svn_propget_base { my ($p, $f) = @_; $f .= '@BASE' if $_svn_pg_peg_revs; @@ -1803,6 +1893,142 @@ sub read_url_paths { return $l_map; } +sub extract_metadata { + my $id = shift; + my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+) + \s([a-f\d\-]+)$/x); + if (!$rev || !$uuid || !$url) { + # some of the original repositories I made had + # indentifiers like this: + ($rev, $uuid) = ($id =~/^git-svn-id:\s(\d+)\@([a-f\d\-]+)/); + } + return ($url, $rev, $uuid); +} + +sub tz_to_s_offset { + my ($tz) = @_; + $tz =~ s/(\d\d)$//; + return ($1 * 60) + ($tz * 3600); +} + +sub setup_pager { # translated to Perl from pager.c + return unless (-t *STDOUT); + my $pager = $ENV{PAGER}; + if (!defined $pager) { + $pager = 'less'; + } elsif (length $pager == 0 || $pager eq 'cat') { + return; + } + pipe my $rfd, my $wfd or return; + defined(my $pid = fork) or croak $!; + if (!$pid) { + open STDOUT, '>&', $wfd or croak $!; + return; + } + open STDIN, '<&', $rfd or croak $!; + $ENV{LESS} ||= '-S'; + exec $pager or croak "Can't run pager: $!\n";; +} + +sub get_author_info { + my ($dest, $author, $t, $tz) = @_; + $author =~ s/(?:^\s*|\s*$)//g; + my $_a; + if ($_authors) { + $_a = $rusers{$author} || undef; + } + if (!$_a) { + ($_a) = ($author =~ /<([^>]+)\@[^>]+>$/); + } + $dest->{t} = $t; + $dest->{tz} = $tz; + $dest->{a} = $_a; + # Date::Parse isn't in the standard Perl distro :( + if ($tz =~ s/^\+//) { + $t += tz_to_s_offset($tz); + } elsif ($tz =~ s/^\-//) { + $t -= tz_to_s_offset($tz); + } + $dest->{t_utc} = $t; +} + +sub process_commit { + my ($c, $r_min, $r_max, $defer) = @_; + if (defined $r_min && defined $r_max) { + if ($r_min == $c->{r} && $r_min == $r_max) { + show_commit($c); + return 0; + } + return 1 if $r_min == $r_max; + if ($r_min < $r_max) { + # we need to reverse the print order + return 0 if (defined $_limit && --$_limit < 0); + push @$defer, $c; + return 1; + } + if ($r_min != $r_max) { + return 1 if ($r_min < $c->{r}); + return 1 if ($r_max > $c->{r}); + } + } + return 0 if (defined $_limit && --$_limit < 0); + show_commit($c); + return 1; +} + +sub show_commit { + my $c = shift; + if ($_oneline) { + my $x = "\n"; + if (my $l = $c->{l}) { + while ($l->[0] =~ /^\s*$/) { shift @$l } + $x = $l->[0]; + } + $_l_fmt ||= 'A' . length($c->{r}); + print 'r',pack($_l_fmt, $c->{r}),' | '; + print "$c->{c} | " if $_show_commit; + print $x; + } else { + show_commit_normal($c); + } +} + +sub show_commit_normal { + my ($c) = @_; + print '-' x72, "\nr$c->{r} | "; + print "$c->{c} | " if $_show_commit; + print "$c->{a} | ", strftime("%Y-%m-%d %H:%M:%S %z (%a, %d %b %Y)", + localtime($c->{t_utc})), ' | '; + my $nr_line = 0; + + if (my $l = $c->{l}) { + while ($l->[$#$l] eq "\n" && $l->[($#$l - 1)] eq "\n") { + pop @$l; + } + $nr_line = scalar @$l; + if (!$nr_line) { + print "1 line\n\n\n"; + } else { + if ($nr_line == 1) { + $nr_line = '1 line'; + } else { + $nr_line .= ' lines'; + } + print $nr_line, "\n\n"; + print $_ foreach @$l; + } + } else { + print "1 line\n\n"; + + } + foreach my $x (qw/raw diff/) { + if ($c->{$x}) { + print "\n"; + print $_ foreach @{$c->{$x}} + } + } +} + __END__ Data structures: From a5e0cedc0a4d0018f3e7e4ba8ca54c91742dd859 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Mon, 12 Jun 2006 15:23:48 -0700 Subject: [PATCH 17/25] git-svn: add support for Perl SVN::* libraries This means we no longer have to deal with having bloated SVN working copies around and we get a nice performance increase as well because we don't have to exec the SVN binary and start a new server connection each time. Of course we have to manually manage memory with SVN::Pool whenever we can, and hack around cases where SVN just eats memory despite pools (I blame Perl, too). I would like to keep memory usage as stable as possible during long fetch/commit processes since I still use computers with only 256-512M RAM. commit should always be faster with the SVN library code. The SVN::Delta interface is leaky (or I'm not using it with pools correctly), so I'm forking on every commit, but that doesn't seem to hurt performance too much (at least on normal Unix/Linux systems where fork() is pretty cheap). fetch should be faster in most common cases, but probably not all. fetches will be faster where client/server delta generation is the bottleneck and not bandwidth. Of course, full-files are generated server-side via deltas, too. Full files are always transferred when they're updated, just like git-svnimport and unlike command-line svn. I'm also hacking around memory leaks (see comments) here by using some more forks. I've tested fetch with http://, https://, file://, and svn:// repositories, so we should be reasonably covered in terms of error handling for fetching. Of course, we'll keep plain command-line svn compatibility as a fallback for people running SVN 1.1 (I'm looking into library support for 1.1.x SVN, too). If you want to force command-line SVN usage, set GIT_SVN_NO_LIB=1 in your environment. We also require two simultaneous connections (just like git-svnimport), but this shouldn't be a problem for most servers. Less important commands: show-ignore is slower because it requires repository access, but -r/--revision can be specified. graft-branches may use more memory, but it's a short-term process and is funky-filename-safe. Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 1068 ++++++++++++++++++-- contrib/git-svn/t/lib-git-svn.sh | 2 +- contrib/git-svn/t/t0000-contrib-git-svn.sh | 15 +- 3 files changed, 974 insertions(+), 111 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 03416aeec1..9618c8bab5 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -31,6 +31,10 @@ use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/; use File::Spec qw//; use POSIX qw/strftime/; + +my ($SVN_PATH, $SVN, $SVN_LOG, $_use_lib); +$_use_lib = 1 unless $ENV{GIT_SVN_NO_LIB}; +libsvn_load(); my $sha1 = qr/[a-f\d]{40}/; my $sha1_short = qr/[a-f\d]{4,40}/; my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, @@ -74,7 +78,8 @@ 'copy-similarity|C=i'=> \$_cp_similarity, %fc_opts, } ], - 'show-ignore' => [ \&show_ignore, "Show svn:ignore listings", { } ], + 'show-ignore' => [ \&show_ignore, "Show svn:ignore listings", + { 'revision|r=i' => \$_revision } ], rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)", { 'no-ignore-externals' => \$_no_ignore_ext, 'upgrade' => \$_upgrade } ], @@ -211,6 +216,8 @@ sub rebuild { $newest_rev = $rev if ($rev > $newest_rev); } close $rev_list or croak $?; + + goto out if $_use_lib; if (!chdir $SVN_WC) { svn_cmd_checkout($SVN_URL, $latest, $SVN_WC); chdir $SVN_WC or croak $!; @@ -228,7 +235,7 @@ sub rebuild { } waitpid $pid, 0; croak $? if $?; - +out: if ($_upgrade) { print STDERR <<""; Keeping deprecated refs/head/$GIT_SVN-HEAD for now. Please remove it @@ -251,9 +258,18 @@ sub init { } sub fetch { - my (@parents) = @_; check_upgrade_needed(); $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); + my $ret = $_use_lib ? fetch_lib(@_) : fetch_cmd(@_); + if ($ret->{commit} && quiet_run(qw(git-rev-parse --verify + refs/heads/master^0))) { + sys(qw(git-update-ref refs/heads/master),$ret->{commit}); + } + return $ret; +} + +sub fetch_cmd { + my (@parents) = @_; my @log_args = -d $SVN_WC ? ($SVN_WC) : ($SVN_URL); unless ($_revision) { $_revision = -d $SVN_WC ? 'BASE:HEAD' : '0:HEAD'; @@ -301,13 +317,91 @@ sub fetch { $last_commit = git_commit($log_msg, $last_commit, @parents); $last = $log_msg; } - unless (-e "$GIT_DIR/refs/heads/master") { - sys(qw(git-update-ref refs/heads/master),$last_commit); - } close $svn_log->{fh}; + $last->{commit} = $last_commit; return $last; } +sub fetch_lib { + my (@parents) = @_; + $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); + my $repo; + ($repo, $SVN_PATH) = repo_path_split($SVN_URL); + $SVN_LOG ||= libsvn_connect($repo); + $SVN ||= libsvn_connect($repo); + my ($last_rev, $last_commit) = svn_grab_base_rev(); + my ($base, $head) = libsvn_parse_revision($last_rev); + if ($base > $head) { + return { revision => $last_rev, commit => $last_commit } + } + my $index = set_index($GIT_SVN_INDEX); + + # limit ourselves and also fork() since get_log won't release memory + # after processing a revision and SVN stuff seems to leak + my $inc = 1000; + my ($min, $max) = ($base, $head < $base+$inc ? $head : $base+$inc); + read_uuid(); + if (defined $last_commit) { + unless (-e $GIT_SVN_INDEX) { + sys(qw/git-read-tree/, $last_commit); + } + chomp (my $x = `git-write-tree`); + my ($y) = (`git-cat-file commit $last_commit` + =~ /^tree ($sha1)/m); + if ($y ne $x) { + unlink $GIT_SVN_INDEX or croak $!; + sys(qw/git-read-tree/, $last_commit); + } + chomp ($x = `git-write-tree`); + if ($y ne $x) { + print STDERR "trees ($last_commit) $y != $x\n", + "Something is seriously wrong...\n"; + } + } + while (1) { + # fork, because using SVN::Pool with get_log() still doesn't + # seem to help enough to keep memory usage down. + defined(my $pid = fork) or croak $!; + if (!$pid) { + $SVN::Error::handler = \&libsvn_skip_unknown_revs; + print "Fetching revisions $min .. $max\n"; + + # Yes I'm perfectly aware that the fourth argument + # below is the limit revisions number. Unfortunately + # performance sucks with it enabled, so it's much + # faster to fetch revision ranges instead of relying + # on the limiter. + $SVN_LOG->get_log( '/'.$SVN_PATH, $min, $max, 0, 1, 1, + sub { + my $log_msg; + if ($last_commit) { + $log_msg = libsvn_fetch( + $last_commit, @_); + $last_commit = git_commit( + $log_msg, + $last_commit, + @parents); + } else { + $log_msg = libsvn_new_tree(@_); + $last_commit = git_commit( + $log_msg, @parents); + } + }); + $SVN::Error::handler = sub { 'quiet warnings' }; + exit 0; + } + waitpid $pid, 0; + croak $? if $?; + ($last_rev, $last_commit) = svn_grab_base_rev(); + last if ($max >= $head); + $min = $max + 1; + $max += $inc; + $max = $head if ($max > $head); + } + restore_index($index); + return { revision => $last_rev, commit => $last_commit }; +} + sub commit { my (@commits) = @_; check_upgrade_needed(); @@ -332,6 +426,12 @@ sub commit { } } chomp @revs; + $_use_lib ? commit_lib(@revs) : commit_cmd(@revs); + print "Done committing ",scalar @revs," revisions to SVN\n"; +} + +sub commit_cmd { + my (@revs) = @_; chdir $SVN_WC or croak "Unable to chdir $SVN_WC: $!\n"; my $info = svn_info('.'); @@ -353,17 +453,95 @@ sub commit { } $svn_current_rev = svn_commit_tree($svn_current_rev, $c); } - print "Done committing ",scalar @revs," revisions to SVN\n"; +} + +sub commit_lib { + my (@revs) = @_; + my ($r_last, $cmt_last) = svn_grab_base_rev(); + defined $r_last or die "Must have an existing revision to commit\n"; + my $fetched = fetch_lib(); + if ($r_last != $fetched->{revision}) { + print STDERR "There are new revisions that were fetched ", + "and need to be merged (or acknowledged) ", + "before committing.\n", + "last rev: $r_last\n", + " current: $fetched->{revision}\n"; + exit 1; + } + read_uuid(); + my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : (); + my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$"; + + foreach my $c (@revs) { + # fork for each commit because there's a memory leak I + # can't track down... (it's probably in the SVN code) + defined(my $pid = open my $fh, '-|') or croak $!; + if (!$pid) { + if (defined $LC_ALL) { + $ENV{LC_ALL} = $LC_ALL; + } else { + delete $ENV{LC_ALL}; + } + my $log_msg = get_commit_message($c, $commit_msg); + my $ed = SVN::Git::Editor->new( + { r => $r_last, + ra => $SVN, + c => $c, + svn_path => $SVN_PATH + }, + $SVN->get_commit_editor( + $log_msg->{msg}, + sub { + libsvn_commit_cb( + @_, $c, + $log_msg->{msg}, + $r_last, + $cmt_last) + }, + @lock) + ); + my $mods = libsvn_checkout_tree($r_last, $c, $ed); + if (@$mods == 0) { + print "No changes\nr$r_last = $cmt_last\n"; + $ed->abort_edit; + } else { + $ed->close_edit; + } + exit 0; + } + my ($r_new, $cmt_new, $no); + while (<$fh>) { + print $_; + chomp; + if (/^r(\d+) = ($sha1)$/o) { + ($r_new, $cmt_new) = ($1, $2); + } elsif ($_ eq 'No changes') { + $no = 1; + } + } + close $fh or croak $!; + if (! defined $r_new && ! defined $cmt_new) { + unless ($no) { + die "Failed to parse revision information\n"; + } + } else { + ($r_last, $cmt_last) = ($r_new, $cmt_new); + } + } + unlink $commit_msg; } sub show_ignore { - require File::Find or die $!; - my $exclude_file = "$GIT_DIR/info/exclude"; - open my $fh, '<', $exclude_file or croak $!; - chomp(my @excludes = (<$fh>)); - close $fh or croak $!; - $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); + $_use_lib ? show_ignore_lib() : show_ignore_cmd(); +} + +sub show_ignore_cmd { + require File::Find or die $!; + if (defined $_revision) { + die "-r/--revision option doesn't work unless the Perl SVN ", + "libraries are used\n"; + } chdir $SVN_WC or croak $!; my %ign; File::Find::find({wanted=>sub{if(lstat $_ && -d _ && -d "$_/.svn"){ @@ -380,6 +558,14 @@ sub show_ignore { } } +sub show_ignore_lib { + my $repo; + ($repo, $SVN_PATH) = repo_path_split($SVN_URL); + $SVN ||= libsvn_connect($repo); + my $r = defined $_revision ? $_revision : $SVN->get_latest_revnum; + libsvn_traverse_ignore(\*STDOUT, $SVN_PATH, $r); +} + sub graft_branches { my $gr_file = "$GIT_DIR/info/grafts"; my ($grafts, $comments) = read_grafts($gr_file); @@ -403,7 +589,13 @@ sub graft_branches { graft_merge_msg($grafts,$l_map,$u,$p); } } - graft_file_copy($grafts,$l_map,$u) unless $_no_graft_copy; + unless ($_no_graft_copy) { + if ($_use_lib) { + graft_file_copy_lib($grafts,$l_map,$u); + } else { + graft_file_copy_cmd($grafts,$l_map,$u); + } + } } write_grafts($grafts, $comments, $gr_file); @@ -574,7 +766,8 @@ sub complete_url_ls_init { } $var = $url . $var; } - chomp(my @ls = safe_qx(qw/svn ls --non-interactive/, $var)); + chomp(my @ls = $_use_lib ? libsvn_ls_fullurl($var) + : safe_qx(qw/svn ls --non-interactive/, $var)); my $old = $GIT_SVN; defined(my $pid = fork) or croak $!; if (!$pid) { @@ -617,7 +810,7 @@ sub common_prefix { } # this isn't funky-filename safe, but good enough for now... -sub graft_file_copy { +sub graft_file_copy_cmd { my ($grafts, $l_map, $u) = @_; my $paths = $l_map->{$u}; my $pfx = common_prefix([keys %$paths]); @@ -625,7 +818,9 @@ sub graft_file_copy { my $pid = open my $fh, '-|'; defined $pid or croak $!; unless ($pid) { - exec(qw/svn log -v/, $u.$pfx) or croak $!; + my @exec = qw/svn log -v/; + push @exec, "-r$_revision" if defined $_revision; + exec @exec, $u.$pfx or croak $!; } my ($r, $mp) = (undef, undef); while (<$fh>) { @@ -637,42 +832,40 @@ sub graft_file_copy { } elsif (/^Changed paths:/) { $mp = 1; } elsif ($mp && m#^ [AR] /(\S.*?) \(from /(\S+?):(\d+)\)$#) { - my $dbg = "r$r | $_"; my ($p1, $p0, $r0) = ($1, $2, $3); - my $c; - foreach my $x (keys %$paths) { - next unless ($p1 =~ /^\Q$x\E/); - my $i = $paths->{$x}; - my $f = "$GIT_DIR/svn/$i/revs/$r"; - unless (-r $f) { - print STDERR "r$r of $i not imported,", - " $dbg\n"; - next; - } - $c = file_to_s($f); - } + my $c = find_graft_path_commit($paths, $p1, $r); next unless $c; - foreach my $x (keys %$paths) { - next unless ($p0 =~ /^\Q$x\E/); - my $i = $paths->{$x}; - my $f = "$GIT_DIR/svn/$i/revs/$r0"; - while ($r0 && !-r $f) { - # could be an older revision, too... - $r0--; - $f = "$GIT_DIR/svn/$i/revs/$r0"; - } - unless (-r $f) { - print STDERR "r$r0 of $i not imported,", - " $dbg\n"; - next; - } - my $r1 = file_to_s($f); - $grafts->{$c}->{$r1} = 1; - } + find_graft_path_parents($grafts, $paths, $c, $p0, $r0); } } } +sub graft_file_copy_lib { + my ($grafts, $l_map, $u) = @_; + my $tree_paths = $l_map->{$u}; + my $pfx = common_prefix([keys %$tree_paths]); + my ($repo, $path) = repo_path_split($u.$pfx); + $SVN_LOG ||= libsvn_connect($repo); + $SVN ||= libsvn_connect($repo); + + my ($base, $head) = libsvn_parse_revision(); + my $inc = 1000; + my ($min, $max) = ($base, $head < $base+$inc ? $head : $base+$inc); + while (1) { + my $pool = SVN::Pool->new; + $SVN_LOG->get_log( "/$path", $min, $max, 0, 1, 1, + sub { + libsvn_graft_file_copies($grafts, $tree_paths, + $path, @_); + }, $pool); + $pool->clear; + last if ($max >= $head); + $min = $max + 1; + $max += $inc; + $max = $head if ($max > $head); + } +} + sub process_merge_msg_matches { my ($grafts, $l_map, $u, $p, $c, @matches) = @_; my (@strong, @weak); @@ -734,9 +927,15 @@ sub graft_merge_msg { sub read_uuid { return if $SVN_UUID; - my $info = shift || svn_info('.'); - $SVN_UUID = $info->{'Repository UUID'} or + if ($_use_lib) { + my $pool = SVN::Pool->new; + $SVN_UUID = $SVN->get_uuid($pool); + $pool->clear; + } else { + my $info = shift || svn_info('.'); + $SVN_UUID = $info->{'Repository UUID'} or croak "Repository UUID unreadable\n"; + } s_to_file($SVN_UUID,"$GIT_SVN_DIR/info/uuid"); } @@ -769,9 +968,19 @@ sub repo_path_split { $path =~ s#^/+##; my @paths = split(m#/+#, $path); - while (quiet_run(qw/svn ls --non-interactive/, $url)) { - my $n = shift @paths || last; - $url .= "/$n"; + if ($_use_lib) { + while (1) { + $SVN = libsvn_connect($url); + last if (defined $SVN && + defined eval { $SVN->get_latest_revnum }); + my $n = shift @paths || last; + $url .= "/$n"; + } + } else { + while (quiet_run(qw/svn ls --non-interactive/, $url)) { + my $n = shift @paths || last; + $url .= "/$n"; + } } push @repo_path_split_cache, qr/^(\Q$url\E)/; $path = join('/',@paths); @@ -797,6 +1006,7 @@ sub setup_git_svn { } sub assert_svn_wc_clean { + return if $_use_lib; my ($svn_rev) = @_; croak "$svn_rev is not an integer!\n" unless ($svn_rev =~ /^\d+$/); my $lcr = svn_info('.')->{'Last Changed Rev'}; @@ -819,7 +1029,7 @@ sub assert_svn_wc_clean { } } -sub assert_tree { +sub get_tree_from_treeish { my ($treeish) = @_; croak "Not a sha1: $treeish\n" unless $treeish =~ /^$sha1$/o; chomp(my $type = `git-cat-file -t $treeish`); @@ -836,20 +1046,22 @@ sub assert_tree { } else { die "$treeish is a $type, expected tree, tag or commit\n"; } + return $expected; +} + +sub assert_tree { + return if $_use_lib; + my ($treeish) = @_; + my $expected = get_tree_from_treeish($treeish); - my $old_index = $ENV{GIT_INDEX_FILE}; my $tmpindex = $GIT_SVN_INDEX.'.assert-tmp'; if (-e $tmpindex) { unlink $tmpindex or croak $!; } - $ENV{GIT_INDEX_FILE} = $tmpindex; + my $old_index = set_index($tmpindex); index_changes(1); chomp(my $tree = `git-write-tree`); - if ($old_index) { - $ENV{GIT_INDEX_FILE} = $old_index; - } else { - delete $ENV{GIT_INDEX_FILE}; - } + restore_index($old_index); if ($tree ne $expected) { croak "Tree mismatch, Got: $tree, Expected: $expected\n"; } @@ -987,7 +1199,8 @@ sub precommit_check { } } -sub svn_checkout_tree { + +sub get_diff { my ($svn_rev, $treeish) = @_; my $from = file_to_s("$REV_DIR/$svn_rev"); assert_tree($from); @@ -1005,11 +1218,13 @@ sub svn_checkout_tree { push @diff_tree, "-l$_l" if defined $_l; exec(@diff_tree, $from, $treeish) or croak $!; } - my $mods = parse_diff_tree($diff_fh); - unless (@$mods) { - # git can do empty commits, but SVN doesn't allow it... - return $mods; - } + return parse_diff_tree($diff_fh); +} + +sub svn_checkout_tree { + my ($svn_rev, $treeish) = @_; + my $mods = get_diff($svn_rev, $treeish); + return $mods unless (scalar @$mods); my ($rm, $add) = precommit_check($mods); my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 ); @@ -1052,6 +1267,23 @@ sub svn_checkout_tree { return $mods; } +sub libsvn_checkout_tree { + my ($svn_rev, $treeish, $ed) = @_; + my $mods = get_diff($svn_rev, $treeish); + return $mods unless (scalar @$mods); + my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 ); + foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) { + my $f = $m->{chg}; + if (defined $o{$f}) { + $ed->$f($m); + } else { + croak "Invalid change type: $f\n"; + } + } + $ed->rmdirs if $_rmdir; + return $mods; +} + # svn ls doesn't work with respect to the current working tree, but what's # in the repository. There's not even an option for it... *sigh* # (added files don't show up and removed files remain in the ls listing) @@ -1090,12 +1322,12 @@ sub handle_rmdir { } } -sub svn_commit_tree { - my ($svn_rev, $commit) = @_; - my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$"; +sub get_commit_message { + my ($commit, $commit_msg) = (@_); my %log_msg = ( msg => '' ); open my $msg, '>', $commit_msg or croak $!; + print "commit: $commit\n"; chomp(my $type = `git-cat-file -t $commit`); if ($type eq 'commit') { my $pid = open my $msg_fh, '-|'; @@ -1129,7 +1361,14 @@ sub svn_commit_tree { { local $/; chomp($log_msg{msg} = <$msg>); } close $msg or croak $!; - my ($oneline) = ($log_msg{msg} =~ /([^\n\r]+)/); + return \%log_msg; +} + +sub svn_commit_tree { + my ($svn_rev, $commit) = @_; + my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$"; + my $log_msg = get_commit_message($commit, $commit_msg); + my ($oneline) = ($log_msg->{msg} =~ /([^\n\r]+)/); print "Committing $commit: $oneline\n"; if (defined $LC_ALL) { @@ -1165,12 +1404,12 @@ sub svn_commit_tree { /(\d{4})\-(\d\d)\-(\d\d)\s (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x) or croak "Failed to parse date: $date\n"; - $log_msg{date} = "$tz $Y-$m-$d $H:$M:$S"; - $log_msg{author} = $info->{'Last Changed Author'}; - $log_msg{revision} = $committed; - $log_msg{msg} .= "\n"; + $log_msg->{date} = "$tz $Y-$m-$d $H:$M:$S"; + $log_msg->{author} = $info->{'Last Changed Author'}; + $log_msg->{revision} = $committed; + $log_msg->{msg} .= "\n"; my $parent = file_to_s("$REV_DIR/$svn_rev"); - git_commit(\%log_msg, $parent, $commit); + git_commit($log_msg, $parent, $commit); return $committed; } # resync immediately @@ -1335,8 +1574,14 @@ sub eol_cp { binmode $rfd or croak $!; open my $wfd, '>', $to or croak $!; binmode $wfd or croak $!; + eol_cp_fd($rfd, $wfd, $es); + close $rfd or croak $!; + close $wfd or croak $!; +} - my $eol = $EOL{$es} or undef; +sub eol_cp_fd { + my ($rfd, $wfd, $es) = @_; + my $eol = defined $es ? $EOL{$es} : undef; my $buf; use bytes; while (1) { @@ -1396,6 +1641,7 @@ sub do_update_index { } sub index_changes { + return if $_use_lib; my $no_text_base = shift; do_update_index([qw/git-diff-files --name-only -z/], 'remove', @@ -1459,63 +1705,59 @@ sub assert_revision_eq_or_unknown { sub git_commit { my ($log_msg, @parents) = @_; assert_revision_unknown($log_msg->{revision}); - my $out_fh = IO::File->new_tmpfile or croak $!; - map_tree_joins() if (@_branch_from && !%tree_map); + my (@tmp_parents, @exec_parents, %seen_parent); + if (my $lparents = $log_msg->{parents}) { + @tmp_parents = @$lparents + } # commit parents can be conditionally bound to a particular # svn revision via: "svn_revno=commit_sha1", filter them out here: - my @exec_parents; foreach my $p (@parents) { next unless defined $p; if ($p =~ /^(\d+)=($sha1_short)$/o) { if ($1 == $log_msg->{revision}) { - push @exec_parents, $2; + push @tmp_parents, $2; } } else { - push @exec_parents, $p if $p =~ /$sha1_short/o; + push @tmp_parents, $p if $p =~ /$sha1_short/o; } } - - my $pid = fork; - defined $pid or croak $!; - if ($pid == 0) { - $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX; + my $tree = $log_msg->{tree}; + if (!defined $tree) { + my $index = set_index($GIT_SVN_INDEX); index_changes(); - chomp(my $tree = `git-write-tree`); + chomp($tree = `git-write-tree`); croak $? if $?; - if (exists $tree_map{$tree}) { - my %seen_parent = map { $_ => 1 } @exec_parents; - foreach (@{$tree_map{$tree}}) { - # MAXPARENT is defined to 16 in commit-tree.c: - if ($seen_parent{$_} || @exec_parents > 16) { - next; - } - push @exec_parents, $_; - $seen_parent{$_} = 1; - } - } + restore_index($index); + } + if (exists $tree_map{$tree}) { + push @tmp_parents, @{$tree_map{$tree}}; + } + foreach (@tmp_parents) { + next if $seen_parent{$_}; + $seen_parent{$_} = 1; + push @exec_parents, $_; + # MAXPARENT is defined to 16 in commit-tree.c: + last if @exec_parents > 16; + } + + defined(my $pid = open my $out_fh, '-|') or croak $!; + if ($pid == 0) { my $msg_fh = IO::File->new_tmpfile or croak $!; print $msg_fh $log_msg->{msg}, "\ngit-svn-id: ", "$SVN_URL\@$log_msg->{revision}", " $SVN_UUID\n" or croak $!; $msg_fh->flush == 0 or croak $!; seek $msg_fh, 0, 0 or croak $!; - set_commit_env($log_msg); - my @exec = ('git-commit-tree',$tree); push @exec, '-p', $_ foreach @exec_parents; open STDIN, '<&', $msg_fh or croak $!; - open STDOUT, '>&', $out_fh or croak $!; exec @exec or croak $!; } - waitpid($pid,0); - croak $? if $?; - - $out_fh->flush == 0 or croak $!; - seek $out_fh, 0, 0 or croak $!; chomp(my $commit = do { local $/; <$out_fh> }); + close $out_fh or croak $?; if ($commit !~ /^$sha1$/o) { croak "Failed to commit, invalid sha1: $commit\n"; } @@ -1534,6 +1776,7 @@ sub git_commit { } sys(@update_ref); sys('git-update-ref',"svn/$GIT_SVN/revs/$log_msg->{revision}",$commit); + # this output is read via pipe, do not change: print "r$log_msg->{revision} = $commit\n"; if ($_repack && (--$_repack_nr == 0)) { $_repack_nr = $_repack; @@ -1545,6 +1788,9 @@ sub git_commit { sub set_commit_env { my ($log_msg) = @_; my $author = $log_msg->{author}; + if (!defined $author || length $author == 0) { + $author = '(no author)'; + } my ($name,$email) = defined $users{$author} ? @{$users{$author}} : ($author,"$author\@$SVN_UUID"); $ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $name; @@ -2029,6 +2275,612 @@ sub show_commit_normal { } } +sub libsvn_load { + return unless $_use_lib; + $_use_lib = eval { + require SVN::Core; + if ($SVN::Core::VERSION lt '1.2.1') { + die "Need SVN::Core 1.2.1 or better ", + "(got $SVN::Core::VERSION) ", + "Falling back to command-line svn\n"; + } + require SVN::Ra; + require SVN::Delta; + push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor'; + my $kill_stupid_warnings = $SVN::Node::none.$SVN::Node::file. + $SVN::Node::dir.$SVN::Node::unknown. + $SVN::Node::none.$SVN::Node::file. + $SVN::Node::dir.$SVN::Node::unknown; + 1; + }; +} + +sub libsvn_connect { + my ($url) = @_; + my $auth = SVN::Core::auth_open([SVN::Client::get_simple_provider(), + SVN::Client::get_ssl_server_trust_file_provider(), + SVN::Client::get_username_provider()]); + my $s = eval { SVN::Ra->new(url => $url, auth => $auth) }; + return $s; +} + +sub libsvn_get_file { + my ($gui, $f, $rev) = @_; + my $p = $f; + return unless ($p =~ s#^\Q$SVN_PATH\E/?##); + + my $fd = IO::File->new_tmpfile or croak $!; + my $pool = SVN::Pool->new; + my ($r, $props) = $SVN->get_file($f, $rev, $fd, $pool); + $pool->clear; + $fd->flush == 0 or croak $!; + seek $fd, 0, 0 or croak $!; + if (my $es = $props->{'svn:eol-style'}) { + my $new_fd = IO::File->new_tmpfile or croak $!; + eol_cp_fd($fd, $new_fd, $es); + close $fd or croak $!; + $fd = $new_fd; + seek $fd, 0, 0 or croak $!; + $fd->flush == 0 or croak $!; + } + my $mode = '100644'; + if (exists $props->{'svn:executable'}) { + $mode = '100755'; + } + if (exists $props->{'svn:special'}) { + $mode = '120000'; + local $/; + my $link = <$fd>; + $link =~ s/^link // or die "svn:special file with contents: <", + $link, "> is not understood\n"; + seek $fd, 0, 0 or croak $!; + truncate $fd, 0 or croak $!; + print $fd $link or croak $!; + seek $fd, 0, 0 or croak $!; + $fd->flush == 0 or croak $!; + } + my $pid = open my $ho, '-|'; + defined $pid or croak $!; + if (!$pid) { + open STDIN, '<&', $fd or croak $!; + exec qw/git-hash-object -w --stdin/ or croak $!; + } + chomp(my $hash = do { local $/; <$ho> }); + close $ho or croak $?; + $hash =~ /^$sha1$/o or die "not a sha1: $hash\n"; + print $gui $mode,' ',$hash,"\t",$p,"\0" or croak $!; + close $fd or croak $!; +} + +sub libsvn_log_entry { + my ($rev, $author, $date, $msg, $parents) = @_; + my ($Y,$m,$d,$H,$M,$S) = ($date =~ /^(\d{4})\-(\d\d)\-(\d\d)T + (\d\d)\:(\d\d)\:(\d\d).\d+Z$/x) + or die "Unable to parse date: $date\n"; + if (defined $_authors && ! defined $users{$author}) { + die "Author: $author not defined in $_authors file\n"; + } + return { revision => $rev, date => "+0000 $Y-$m-$d $H:$M:$S", + author => $author, msg => $msg."\n", parents => $parents || [] } +} + +sub process_rm { + my ($gui, $last_commit, $f) = @_; + $f =~ s#^\Q$SVN_PATH\E/?## or return; + # remove entire directories. + if (safe_qx('git-ls-tree',$last_commit,'--',$f) =~ /^040000 tree/) { + defined(my $pid = open my $ls, '-|') or croak $!; + if (!$pid) { + exec(qw/git-ls-tree -r --name-only -z/, + $last_commit,'--',$f) or croak $!; + } + local $/ = "\0"; + while (<$ls>) { + print $gui '0 ',0 x 40,"\t",$_ or croak $!; + } + close $ls or croak $!; + } else { + print $gui '0 ',0 x 40,"\t",$f,"\0" or croak $!; + } +} + +sub libsvn_fetch { + my ($last_commit, $paths, $rev, $author, $date, $msg) = @_; + open my $gui, '| git-update-index -z --index-info' or croak $!; + my @amr; + foreach my $f (keys %$paths) { + my $m = $paths->{$f}->action(); + $f =~ s#^/+##; + if ($m =~ /^[DR]$/) { + process_rm($gui, $last_commit, $f); + next if $m eq 'D'; + # 'R' can be file replacements, too, right? + } + my $pool = SVN::Pool->new; + my $t = $SVN->check_path($f, $rev, $pool); + if ($t == $SVN::Node::file) { + if ($m =~ /^[AMR]$/) { + push @amr, $f; + } else { + die "Unrecognized action: $m, ($f r$rev)\n"; + } + } + $pool->clear; + } + libsvn_get_file($gui, $_, $rev) foreach (@amr); + close $gui or croak $!; + return libsvn_log_entry($rev, $author, $date, $msg, [$last_commit]); +} + +sub svn_grab_base_rev { + defined(my $pid = open my $fh, '-|') or croak $!; + if (!$pid) { + open my $null, '>', '/dev/null' or croak $!; + open STDERR, '>&', $null or croak $!; + exec qw/git-rev-parse --verify/,"refs/remotes/$GIT_SVN^0" + or croak $!; + } + chomp(my $c = do { local $/; <$fh> }); + close $fh; + if (defined $c && length $c) { + my ($url, $rev, $uuid) = extract_metadata((grep(/^git-svn-id: /, + safe_qx(qw/git-cat-file commit/, $c)))[0]); + return ($rev, $c); + } + return (undef, undef); +} + +sub libsvn_parse_revision { + my $base = shift; + my $head = $SVN->get_latest_revnum(); + if (!defined $_revision || $_revision eq 'BASE:HEAD') { + return ($base + 1, $head) if (defined $base); + return (0, $head); + } + return ($1, $2) if ($_revision =~ /^(\d+):(\d+)$/); + return ($_revision, $_revision) if ($_revision =~ /^\d+$/); + if ($_revision =~ /^BASE:(\d+)$/) { + return ($base + 1, $1) if (defined $base); + return (0, $head); + } + return ($1, $head) if ($_revision =~ /^(\d+):HEAD$/); + die "revision argument: $_revision not understood by git-svn\n", + "Try using the command-line svn client instead\n"; +} + +sub libsvn_traverse { + my ($gui, $pfx, $path, $rev) = @_; + my $cwd = "$pfx/$path"; + my $pool = SVN::Pool->new; + $cwd =~ s#^/+##g; + my ($dirent, $r, $props) = $SVN->get_dir($cwd, $rev, $pool); + foreach my $d (keys %$dirent) { + my $t = $dirent->{$d}->kind; + if ($t == $SVN::Node::dir) { + libsvn_traverse($gui, $cwd, $d, $rev); + } elsif ($t == $SVN::Node::file) { + libsvn_get_file($gui, "$cwd/$d", $rev); + } + } + $pool->clear; +} + +sub libsvn_traverse_ignore { + my ($fh, $path, $r) = @_; + $path =~ s#^/+##g; + my $pool = SVN::Pool->new; + my ($dirent, undef, $props) = $SVN->get_dir($path, $r, $pool); + my $p = $path; + $p =~ s#^\Q$SVN_PATH\E/?##; + print $fh length $p ? "\n# $p\n" : "\n# /\n"; + if (my $s = $props->{'svn:ignore'}) { + $s =~ s/[\r\n]+/\n/g; + chomp $s; + if (length $p == 0) { + $s =~ s#\n#\n/$p#g; + print $fh "/$s\n"; + } else { + $s =~ s#\n#\n/$p/#g; + print $fh "/$p/$s\n"; + } + } + foreach (sort keys %$dirent) { + next if $dirent->{$_}->kind != $SVN::Node::dir; + libsvn_traverse_ignore($fh, "$path/$_", $r); + } + $pool->clear; +} + +sub libsvn_new_tree { + my ($paths, $rev, $author, $date, $msg) = @_; + my $svn_path = '/'.$SVN_PATH; + + # look for a parent from another branch: + foreach (keys %$paths) { + next if ($_ ne $svn_path); + my $i = $paths->{$_}; + my $branch_from = $i->copyfrom_path or next; + my $r = $i->copyfrom_rev; + print STDERR "Found possible branch point: ", + "$branch_from => $svn_path, $r\n"; + $branch_from =~ s#^/##; + my $l_map = read_url_paths(); + my $url = $SVN->{url}; + defined $l_map->{$url} or next; + my $id = $l_map->{$url}->{$branch_from} or next; + my $f = "$GIT_DIR/svn/$id/revs/$r"; + while ($r && !-r $f) { + $r--; + $f = "$GIT_DIR/svn/$id/revs/$r"; + } + if (-r $f) { + my $parent = file_to_s($f); + unlink $GIT_SVN_INDEX; + print STDERR "Found branch parent: $parent\n"; + sys(qw/git-read-tree/, $parent); + return libsvn_fetch($parent, $paths, $rev, + $author, $date, $msg); + } + print STDERR "Nope, branch point not imported or unknown\n"; + } + open my $gui, '| git-update-index -z --index-info' or croak $!; + my $pool = SVN::Pool->new; + libsvn_traverse($gui, '', $SVN_PATH, $rev, $pool); + $pool->clear; + close $gui or croak $!; + return libsvn_log_entry($rev, $author, $date, $msg); +} + +sub find_graft_path_commit { + my ($tree_paths, $p1, $r1) = @_; + foreach my $x (keys %$tree_paths) { + next unless ($p1 =~ /^\Q$x\E/); + my $i = $tree_paths->{$x}; + my $f = "$GIT_DIR/svn/$i/revs/$r1"; + + return file_to_s($f) if (-r $f); + + print STDERR "r$r1 of $i not imported\n"; + next; + } + return undef; +} + +sub find_graft_path_parents { + my ($grafts, $tree_paths, $c, $p0, $r0) = @_; + foreach my $x (keys %$tree_paths) { + next unless ($p0 =~ /^\Q$x\E/); + my $i = $tree_paths->{$x}; + my $f = "$GIT_DIR/svn/$i/revs/$r0"; + while ($r0 && !-r $f) { + # could be an older revision, too... + $r0--; + $f = "$GIT_DIR/svn/$i/revs/$r0"; + } + unless (-r $f) { + print STDERR "r$r0 of $i not imported\n"; + next; + } + my $parent = file_to_s($f); + $grafts->{$c}->{$parent} = 1; + } +} + +sub libsvn_graft_file_copies { + my ($grafts, $tree_paths, $path, $paths, $rev) = @_; + foreach (keys %$paths) { + my $i = $paths->{$_}; + my ($m, $p0, $r0) = ($i->action, $i->copyfrom_path, + $i->copyfrom_rev); + next unless (defined $p0 && defined $r0); + + my $p1 = $_; + $p1 =~ s#^/##; + $p0 =~ s#^/##; + my $c = find_graft_path_commit($tree_paths, $p1, $rev); + next unless $c; + find_graft_path_parents($grafts, $tree_paths, $c, $p0, $r0); + } +} + +sub set_index { + my $old = $ENV{GIT_INDEX_FILE}; + $ENV{GIT_INDEX_FILE} = shift; + return $old; +} + +sub restore_index { + my ($old) = @_; + if (defined $old) { + $ENV{GIT_INDEX_FILE} = $old; + } else { + delete $ENV{GIT_INDEX_FILE}; + } +} + +sub libsvn_commit_cb { + my ($rev, $date, $committer, $c, $msg, $r_last, $cmt_last) = @_; + if ($rev == ($r_last + 1)) { + # optimized (avoid fetch) + my $log = libsvn_log_entry($rev,$committer,$date,$msg); + $log->{tree} = get_tree_from_treeish($c); + my $cmt = git_commit($log, $cmt_last, $c); + my @diff = safe_qx('git-diff-tree', $cmt, $c); + if (@diff) { + print STDERR "Trees differ: $cmt $c\n", + join('',@diff),"\n"; + exit 1; + } + } else { + fetch_lib("$rev=$c"); + } +} + +sub libsvn_ls_fullurl { + my $fullurl = shift; + my ($repo, $path) = repo_path_split($fullurl); + $SVN ||= libsvn_connect($repo); + my @ret; + my $pool = SVN::Pool->new; + my ($dirent, undef, undef) = $SVN->get_dir($path, + $SVN->get_latest_revnum, $pool); + foreach my $d (keys %$dirent) { + if ($dirent->{$d}->kind == $SVN::Node::dir) { + push @ret, "$d/"; # add '/' for compat with cli svn + } + } + $pool->clear; + return @ret; +} + + +sub libsvn_skip_unknown_revs { + my $err = shift; + my $errno = $err->apr_err(); + # Maybe the branch we're tracking didn't + # exist when the repo started, so it's + # not an error if it doesn't, just continue + # + # Wonderfully consistent library, eh? + # 160013 - svn:// and file:// + # 175002 - http(s):// + # More codes may be discovered later... + if ($errno == 175002 || $errno == 160013) { + print STDERR "directory non-existent\n"; + return; + } + croak "Error from SVN, ($errno): ", $err->expanded_message,"\n"; +}; + +package SVN::Git::Editor; +use vars qw/@ISA/; +use strict; +use warnings; +use Carp qw/croak/; +use IO::File; + +sub new { + my $class = shift; + my $git_svn = shift; + my $self = SVN::Delta::Editor->new(@_); + bless $self, $class; + foreach (qw/svn_path c r ra /) { + die "$_ required!\n" unless (defined $git_svn->{$_}); + $self->{$_} = $git_svn->{$_}; + } + $self->{pool} = SVN::Pool->new; + $self->{bat} = { '' => $self->open_root($self->{r}, $self->{pool}) }; + $self->{rm} = { }; + require Digest::MD5; + return $self; +} + +sub split_path { + return ($_[0] =~ m#^(.*?)/?([^/]+)$#); +} + +sub repo_path { + (defined $_[1] && length $_[1]) ? "$_[0]->{svn_path}/$_[1]" + : $_[0]->{svn_path} +} + +sub url_path { + my ($self, $path) = @_; + $self->{ra}->{url} . '/' . $self->repo_path($path); +} + +sub rmdirs { + my ($self) = @_; + my $rm = $self->{rm}; + delete $rm->{''}; # we never delete the url we're tracking + return unless %$rm; + + foreach (keys %$rm) { + my @d = split m#/#, $_; + my $c = shift @d; + $rm->{$c} = 1; + while (@d) { + $c .= '/' . shift @d; + $rm->{$c} = 1; + } + } + delete $rm->{$self->{svn_path}}; + delete $rm->{''}; # we never delete the url we're tracking + return unless %$rm; + + defined(my $pid = open my $fh,'-|') or croak $!; + if (!$pid) { + exec qw/git-ls-tree --name-only -r -z/, $self->{c} or croak $!; + } + local $/ = "\0"; + while (<$fh>) { + chomp; + $_ = $self->{svn_path} . '/' . $_; + my ($dn) = ($_ =~ m#^(.*?)/?(?:[^/]+)$#); + delete $rm->{$dn}; + last unless %$rm; + } + my ($r, $p, $bat) = ($self->{r}, $self->{pool}, $self->{bat}); + foreach my $d (sort { $b =~ tr#/#/# <=> $a =~ tr#/#/# } keys %$rm) { + $self->close_directory($bat->{$d}, $p); + my ($dn) = ($d =~ m#^(.*?)/?(?:[^/]+)$#); + $self->SUPER::delete_entry($d, $r, $bat->{$dn}, $p); + delete $bat->{$d}; + } +} + +sub open_or_add_dir { + my ($self, $full_path, $baton) = @_; + my $p = SVN::Pool->new; + my $t = $self->{ra}->check_path($full_path, $self->{r}, $p); + $p->clear; + if ($t == $SVN::Node::none) { + return $self->add_directory($full_path, $baton, + undef, -1, $self->{pool}); + } elsif ($t == $SVN::Node::dir) { + return $self->open_directory($full_path, $baton, + $self->{r}, $self->{pool}); + } + print STDERR "$full_path already exists in repository at ", + "r$self->{r} and it is not a directory (", + ($t == $SVN::Node::file ? 'file' : 'unknown'),"/$t)\n"; + exit 1; +} + +sub ensure_path { + my ($self, $path) = @_; + my $bat = $self->{bat}; + $path = $self->repo_path($path); + return $bat->{''} unless (length $path); + my @p = split m#/+#, $path; + my $c = shift @p; + $bat->{$c} ||= $self->open_or_add_dir($c, $bat->{''}); + while (@p) { + my $c0 = $c; + $c .= '/' . shift @p; + $bat->{$c} ||= $self->open_or_add_dir($c, $bat->{$c0}); + } + return $bat->{$c}; +} + +sub A { + my ($self, $m) = @_; + my ($dir, $file) = split_path($m->{file_b}); + my $pbat = $self->ensure_path($dir); + my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat, + undef, -1); + $self->chg_file($fbat, $m); + $self->close_file($fbat,undef,$self->{pool}); +} + +sub C { + my ($self, $m) = @_; + my ($dir, $file) = split_path($m->{file_b}); + my $pbat = $self->ensure_path($dir); + my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat, + $self->url_path($m->{file_a}), $self->{r}); + $self->chg_file($fbat, $m); + $self->close_file($fbat,undef,$self->{pool}); +} + +sub delete_entry { + my ($self, $path, $pbat) = @_; + my $rpath = $self->repo_path($path); + my ($dir, $file) = split_path($rpath); + $self->{rm}->{$dir} = 1; + $self->SUPER::delete_entry($rpath, $self->{r}, $pbat, $self->{pool}); +} + +sub R { + my ($self, $m) = @_; + my ($dir, $file) = split_path($m->{file_b}); + my $pbat = $self->ensure_path($dir); + my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat, + $self->url_path($m->{file_a}), $self->{r}); + $self->chg_file($fbat, $m); + $self->close_file($fbat,undef,$self->{pool}); + + ($dir, $file) = split_path($m->{file_a}); + $pbat = $self->ensure_path($dir); + $self->delete_entry($m->{file_a}, $pbat); +} + +sub M { + my ($self, $m) = @_; + my ($dir, $file) = split_path($m->{file_b}); + my $pbat = $self->ensure_path($dir); + my $fbat = $self->open_file($self->repo_path($m->{file_b}), + $pbat,$self->{r},$self->{pool}); + $self->chg_file($fbat, $m); + $self->close_file($fbat,undef,$self->{pool}); +} + +sub T { shift->M(@_) } + +sub change_file_prop { + my ($self, $fbat, $pname, $pval) = @_; + $self->SUPER::change_file_prop($fbat, $pname, $pval, $self->{pool}); +} + +sub chg_file { + my ($self, $fbat, $m) = @_; + if ($m->{mode_b} =~ /755$/ && $m->{mode_a} !~ /755$/) { + $self->change_file_prop($fbat,'svn:executable','*'); + } elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) { + $self->change_file_prop($fbat,'svn:executable',undef); + } + my $fh = IO::File->new_tmpfile or croak $!; + if ($m->{mode_b} =~ /^120/) { + print $fh 'link ' or croak $!; + $self->change_file_prop($fbat,'svn:special','*'); + } elsif ($m->{mode_a} =~ /^120/ && $m->{mode_b} !~ /^120/) { + $self->change_file_prop($fbat,'svn:special',undef); + } + defined(my $pid = fork) or croak $!; + if (!$pid) { + open STDOUT, '>&', $fh or croak $!; + exec qw/git-cat-file blob/, $m->{sha1_b} or croak $!; + } + waitpid $pid, 0; + croak $? if $?; + $fh->flush == 0 or croak $!; + seek $fh, 0, 0 or croak $!; + + my $md5 = Digest::MD5->new; + $md5->addfile($fh) or croak $!; + seek $fh, 0, 0 or croak $!; + + my $exp = $md5->hexdigest; + my $atd = $self->apply_textdelta($fbat, undef, $self->{pool}); + my $got = SVN::TxDelta::send_stream($fh, @$atd, $self->{pool}); + die "Checksum mismatch\nexpected: $exp\ngot: $got\n" if ($got ne $exp); + + close $fh or croak $!; +} + +sub D { + my ($self, $m) = @_; + my ($dir, $file) = split_path($m->{file_b}); + my $pbat = $self->ensure_path($dir); + $self->delete_entry($m->{file_b}, $pbat); +} + +sub close_edit { + my ($self) = @_; + my ($p,$bat) = ($self->{pool}, $self->{bat}); + foreach (sort { $b =~ tr#/#/# <=> $a =~ tr#/#/# } keys %$bat) { + $self->close_directory($bat->{$_}, $p); + } + $self->SUPER::close_edit($p); + $p->clear; +} + +sub abort_edit { + my ($self) = @_; + $self->SUPER::abort_edit($self->{pool}); + $self->{pool}->clear; +} + __END__ Data structures: @@ -2062,3 +2914,7 @@ sub show_commit_normal { file_b => new/current file name of a file (any chg) } ; + +Notes: + I don't trust the each() function on unless I created %hash myself + because the internal iterator may not have started at base. diff --git a/contrib/git-svn/t/lib-git-svn.sh b/contrib/git-svn/t/lib-git-svn.sh index 58408a6c07..2843258fc4 100644 --- a/contrib/git-svn/t/lib-git-svn.sh +++ b/contrib/git-svn/t/lib-git-svn.sh @@ -11,7 +11,7 @@ fi GIT_DIR=$PWD/.git GIT_SVN_DIR=$GIT_DIR/svn/git-svn -SVN_TREE=$GIT_SVN_DIR/tree +SVN_TREE=$GIT_SVN_DIR/svn-tree svnadmin >/dev/null 2>&1 if test $? != 1 diff --git a/contrib/git-svn/t/t0000-contrib-git-svn.sh b/contrib/git-svn/t/t0000-contrib-git-svn.sh index 0c6ff2066b..c33b522d08 100644 --- a/contrib/git-svn/t/t0000-contrib-git-svn.sh +++ b/contrib/git-svn/t/t0000-contrib-git-svn.sh @@ -31,6 +31,7 @@ test_expect_success \ 'import an SVN revision into git' \ 'git-svn fetch' +test_expect_success "checkout from svn" "svn co $svnrepo $SVN_TREE" name='try a deep --rmdir with a commit' git checkout -f -b mybranch remotes/git-svn @@ -41,6 +42,7 @@ git commit -m "$name" test_expect_success "$name" \ "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch && + svn up $SVN_TREE && test -d $SVN_TREE/dir && test ! -d $SVN_TREE/dir/a" @@ -52,7 +54,7 @@ git update-index --remove dir/file git update-index --add dir/file/file git commit -m "$name" -test_expect_code 1 "$name" \ +test_expect_failure "$name" \ 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch' \ || true @@ -67,7 +69,7 @@ git update-index --remove -- bar/zzz git update-index --add -- bar git commit -m "$name" -test_expect_code 1 "$name" \ +test_expect_failure "$name" \ 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch2' \ || true @@ -82,7 +84,7 @@ echo yyy > bar/zzz/yyy git-update-index --add bar/zzz/yyy git commit -m "$name" -test_expect_code 1 "$name" \ +test_expect_failure "$name" \ 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch3' \ || true @@ -97,7 +99,7 @@ echo asdf > dir git update-index --add -- dir git commit -m "$name" -test_expect_code 1 "$name" \ +test_expect_failure "$name" \ 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch4' \ || true @@ -111,6 +113,7 @@ git commit -m "$name" test_expect_success "$name" \ "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + svn up $SVN_TREE && test ! -x $SVN_TREE/exec.sh" @@ -121,6 +124,7 @@ git commit -m "$name" test_expect_success "$name" \ "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + svn up $SVN_TREE && test -x $SVN_TREE/exec.sh" @@ -133,6 +137,7 @@ git commit -m "$name" test_expect_success "$name" \ "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + svn up $SVN_TREE && test -L $SVN_TREE/exec.sh" @@ -145,6 +150,7 @@ git commit -m "$name" test_expect_success "$name" \ "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + svn up $SVN_TREE && test -x $SVN_TREE/bar/zzz && test -L $SVN_TREE/exec-2.sh" @@ -159,6 +165,7 @@ git commit -m "$name" test_expect_success "$name" \ "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + svn up $SVN_TREE && test -f $SVN_TREE/exec-2.sh && test ! -L $SVN_TREE/exec-2.sh && diff -u help $SVN_TREE/exec-2.sh" From 42d328701dbdbc02c3361673629a44df478e69d7 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Tue, 13 Jun 2006 04:02:23 -0700 Subject: [PATCH 18/25] git-svn: make the $GIT_DIR/svn/*/revs directory obsolete This is a very intrusive change, so I've beefed up the tests significantly. Added 'full-test' a target to the Makefile, to test different possible configurations. This is intended for maintainers only. Users should only be concerned with 'test' succeeding. We now have a very simple custom database format for handling mapping of svn revisions => git commits. Of course, we're not really using it yet, either. Also disabled automatic branch-finding on new trees for now. It's too easily broken. revisions_eq() function should be helpful for branch detection. Also removed an extra assertion in fetch_cmd() that wasn't correctly done. This bug was found by full-test. Signed-off-by: Eric Wong --- contrib/git-svn/Makefile | 12 +- contrib/git-svn/git-svn.perl | 245 +++++++++++------- contrib/git-svn/t/t0000-contrib-git-svn.sh | 13 + .../git-svn/t/t0001-contrib-git-svn-props.sh | 84 +++--- 4 files changed, 223 insertions(+), 131 deletions(-) diff --git a/contrib/git-svn/Makefile b/contrib/git-svn/Makefile index 48f60b3a0d..d73aa5641c 100644 --- a/contrib/git-svn/Makefile +++ b/contrib/git-svn/Makefile @@ -29,8 +29,16 @@ git-svn.html : git-svn.txt asciidoc -b xhtml11 -d manpage \ -f ../../Documentation/asciidoc.conf $< test: git-svn - cd t && $(SHELL) ./t0000-contrib-git-svn.sh - cd t && $(SHELL) ./t0001-contrib-git-svn-props.sh + cd t && $(SHELL) ./t0000-contrib-git-svn.sh $(TEST_FLAGS) + cd t && $(SHELL) ./t0001-contrib-git-svn-props.sh $(TEST_FLAGS) + +full-test: + $(MAKE) test GIT_SVN_NO_LIB=1 GIT_SVN_NO_OPTIMIZE_COMMITS=1 + $(MAKE) test GIT_SVN_NO_LIB=0 GIT_SVN_NO_OPTIMIZE_COMMITS=1 + $(MAKE) test GIT_SVN_NO_LIB=1 GIT_SVN_NO_OPTIMIZE_COMMITS=0 \ + LC_ALL=en_US.UTF-8 + $(MAKE) test GIT_SVN_NO_LIB=0 GIT_SVN_NO_OPTIMIZE_COMMITS=0 \ + LC_ALL=en_US.UTF-8 clean: rm -f git-svn *.xml *.html *.1 diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 9618c8bab5..884969ebdd 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -6,9 +6,9 @@ use vars qw/ $AUTHOR $VERSION $SVN_URL $SVN_INFO $SVN_WC $SVN_UUID $GIT_SVN_INDEX $GIT_SVN - $GIT_DIR $REV_DIR $GIT_SVN_DIR/; + $GIT_DIR $GIT_SVN_DIR $REVDB/; $AUTHOR = 'Eric Wong '; -$VERSION = '1.1.0-pre'; +$VERSION = '1.1.1-broken'; use Cwd qw/abs_path/; $GIT_DIR = abs_path($ENV{GIT_DIR} || '.git'); @@ -31,10 +31,13 @@ use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/; use File::Spec qw//; use POSIX qw/strftime/; +use Memoize; +memoize('revisions_eq'); my ($SVN_PATH, $SVN, $SVN_LOG, $_use_lib); $_use_lib = 1 unless $ENV{GIT_SVN_NO_LIB}; libsvn_load(); +my $_optimize_commits = 1 unless $ENV{GIT_SVN_NO_OPTIMIZE_COMMITS}; my $sha1 = qr/[a-f\d]{40}/; my $sha1_short = qr/[a-f\d]{4,40}/; my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, @@ -43,7 +46,7 @@ $_template, $_shared, $_no_default_regex, $_no_graft_copy, $_limit, $_verbose, $_incremental, $_oneline, $_l_fmt, $_show_commit, $_version, $_upgrade, $_authors, $_branch_all_refs, @_opt_m); -my (@_branch_from, %tree_map, %users, %rusers); +my (@_branch_from, %tree_map, %users, %rusers, %equiv); my ($_svn_co_url_revs, $_svn_pg_peg_revs); my @repo_path_split_cache; @@ -201,7 +204,6 @@ sub rebuild { next if (defined $SVN_UUID && ($uuid ne $SVN_UUID)); next if (defined $SVN_URL && defined $url && ($url ne $SVN_URL)); - print "r$rev = $c\n"; unless (defined $latest) { if (!$SVN_URL && !$url) { croak "SVN repository location required: $url\n"; @@ -211,8 +213,8 @@ sub rebuild { setup_git_svn(); $latest = $rev; } - assert_revision_eq_or_unknown($rev, $c); - sys('git-update-ref',"svn/$GIT_SVN/revs/$rev",$c); + revdb_set($REVDB, $rev, $c); + print "r$rev = $c\n"; $newest_rev = $rev if ($rev > $newest_rev); } close $rev_list or croak $?; @@ -280,7 +282,11 @@ sub fetch_cmd { my $svn_log = svn_log_raw(@log_args); my $base = next_log_entry($svn_log) or croak "No base revision!\n"; - my $last_commit = undef; + # don't need last_revision from grab_base_rev() because + # user could've specified a different revision to skip (they + # didn't want to import certain revisions into git for whatever + # reason, so trust $base->{revision} instead. + my (undef, $last_commit) = svn_grab_base_rev(); unless (-d $SVN_WC) { svn_cmd_checkout($SVN_URL,$base->{revision},$SVN_WC); chdir $SVN_WC or croak $!; @@ -290,7 +296,6 @@ sub fetch_cmd { } else { chdir $SVN_WC or croak $!; read_uuid(); - eval { $last_commit = file_to_s("$REV_DIR/$base->{revision}") }; # looks like a user manually cp'd and svn switch'ed unless ($last_commit) { sys(qw/svn revert -R ./); @@ -303,7 +308,6 @@ sub fetch_cmd { push @svn_up, '--ignore-externals' unless $_no_ignore_ext; my $last = $base; while (my $log_msg = next_log_entry($svn_log)) { - assert_tree($last_commit); if ($last->{revision} >= $log_msg->{revision}) { croak "Out of order: last >= current: ", "$last->{revision} >= $log_msg->{revision}\n"; @@ -444,14 +448,14 @@ sub commit_cmd { } $info = svn_info('.'); read_uuid($info); - my $svn_current_rev = $info->{'Last Changed Rev'}; + my $last = $fetched; foreach my $c (@revs) { - my $mods = svn_checkout_tree($svn_current_rev, $c); + my $mods = svn_checkout_tree($last, $c); if (scalar @$mods == 0) { print "Skipping, no changes detected\n"; next; } - $svn_current_rev = svn_commit_tree($svn_current_rev, $c); + $last = svn_commit_tree($last, $c); } } @@ -500,7 +504,7 @@ sub commit_lib { }, @lock) ); - my $mods = libsvn_checkout_tree($r_last, $c, $ed); + my $mods = libsvn_checkout_tree($cmt_last, $c, $ed); if (@$mods == 0) { print "No changes\nr$r_last = $cmt_last\n"; $ed->abort_edit; @@ -814,7 +818,7 @@ sub graft_file_copy_cmd { my ($grafts, $l_map, $u) = @_; my $paths = $l_map->{$u}; my $pfx = common_prefix([keys %$paths]); - + $SVN_URL ||= $u.$pfx; my $pid = open my $fh, '-|'; defined $pid or croak $!; unless ($pid) { @@ -851,6 +855,8 @@ sub graft_file_copy_lib { my ($base, $head) = libsvn_parse_revision(); my $inc = 1000; my ($min, $max) = ($base, $head < $base+$inc ? $head : $base+$inc); + my $eh = $SVN::Error::handler; + $SVN::Error::handler = \&libsvn_skip_unknown_revs; while (1) { my $pool = SVN::Pool->new; $SVN_LOG->get_log( "/$path", $min, $max, 0, 1, 1, @@ -864,6 +870,7 @@ sub graft_file_copy_lib { $max += $inc; $max = $head if ($max > $head); } + $SVN::Error::handler = $eh; } sub process_merge_msg_matches { @@ -994,7 +1001,8 @@ sub setup_git_svn { } mkpath([$GIT_SVN_DIR]); mkpath(["$GIT_SVN_DIR/info"]); - mkpath([$REV_DIR]); + open my $fh, '>>',$REVDB or croak $!; + close $fh; s_to_file($SVN_URL,"$GIT_SVN_DIR/info/url"); open my $fd, '>>', "$GIT_SVN_DIR/info/exclude" or croak $!; @@ -1201,8 +1209,7 @@ sub precommit_check { sub get_diff { - my ($svn_rev, $treeish) = @_; - my $from = file_to_s("$REV_DIR/$svn_rev"); + my ($from, $treeish) = @_; assert_tree($from); print "diff-tree $from $treeish\n"; my $pid = open my $diff_fh, '-|'; @@ -1222,8 +1229,8 @@ sub get_diff { } sub svn_checkout_tree { - my ($svn_rev, $treeish) = @_; - my $mods = get_diff($svn_rev, $treeish); + my ($from, $treeish) = @_; + my $mods = get_diff($from->{commit}, $treeish); return $mods unless (scalar @$mods); my ($rm, $add) = precommit_check($mods); @@ -1268,8 +1275,8 @@ sub svn_checkout_tree { } sub libsvn_checkout_tree { - my ($svn_rev, $treeish, $ed) = @_; - my $mods = get_diff($svn_rev, $treeish); + my ($from, $treeish, $ed) = @_; + my $mods = get_diff($from, $treeish); return $mods unless (scalar @$mods); my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 ); foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) { @@ -1365,7 +1372,7 @@ sub get_commit_message { } sub svn_commit_tree { - my ($svn_rev, $commit) = @_; + my ($last, $commit) = @_; my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$"; my $log_msg = get_commit_message($commit, $commit_msg); my ($oneline) = ($log_msg->{msg} =~ /([^\n\r]+)/); @@ -1392,7 +1399,7 @@ sub svn_commit_tree { my @svn_up = qw(svn up); push @svn_up, '--ignore-externals' unless $_no_ignore_ext; - if ($committed == ($svn_rev + 1)) { + if ($_optimize_commits && ($committed == ($last->{revision} + 1))) { push @svn_up, "-r$committed"; sys(@svn_up); my $info = svn_info('.'); @@ -1408,14 +1415,14 @@ sub svn_commit_tree { $log_msg->{author} = $info->{'Last Changed Author'}; $log_msg->{revision} = $committed; $log_msg->{msg} .= "\n"; - my $parent = file_to_s("$REV_DIR/$svn_rev"); - git_commit($log_msg, $parent, $commit); - return $committed; + $log_msg->{parents} = [ $last->{commit} ]; + $log_msg->{commit} = git_commit($log_msg, $commit); + return $log_msg; } # resync immediately - push @svn_up, "-r$svn_rev"; + push @svn_up, "-r$last->{revision}"; sys(@svn_up); - return fetch("$committed=$commit")->{revision}; + return fetch("$committed=$commit"); } sub rev_list_raw { @@ -1671,10 +1678,9 @@ sub file_to_s { } sub assert_revision_unknown { - my $revno = shift; - if (-f "$REV_DIR/$revno") { - croak "$REV_DIR/$revno already exists! ", - "Why are we refetching it?"; + my $r = shift; + if (my $c = revdb_get($REVDB, $r)) { + croak "$r = $c already exists! Why are we refetching it?"; } } @@ -1690,18 +1696,6 @@ sub trees_eq { return 1; } -sub assert_revision_eq_or_unknown { - my ($revno, $commit) = @_; - if (-f "$REV_DIR/$revno") { - my $current = file_to_s("$REV_DIR/$revno"); - if (($commit ne $current) && !trees_eq($commit, $current)) { - croak "$REV_DIR/$revno already exists!\n", - "current: $current\nexpected: $commit\n"; - } - return; - } -} - sub git_commit { my ($log_msg, @parents) = @_; assert_revision_unknown($log_msg->{revision}); @@ -1763,19 +1757,12 @@ sub git_commit { } my @update_ref = ('git-update-ref',"refs/remotes/$GIT_SVN",$commit); if (my $primary_parent = shift @exec_parents) { - $pid = fork; - defined $pid or croak $!; - if (!$pid) { - close STDERR; - close STDOUT; - exec 'git-rev-parse','--verify', - "refs/remotes/$GIT_SVN^0" or croak $!; - } - waitpid $pid, 0; + quiet_run(qw/git-rev-parse --verify/,"refs/remotes/$GIT_SVN^0"); push @update_ref, $primary_parent unless $?; } sys(@update_ref); - sys('git-update-ref',"svn/$GIT_SVN/revs/$log_msg->{revision}",$commit); + revdb_set($REVDB, $log_msg->{revision}, $commit); + # this output is read via pipe, do not change: print "r$log_msg->{revision} = $commit\n"; if ($_repack && (--$_repack_nr == 0)) { @@ -1990,7 +1977,29 @@ sub git_svn_each { } } +sub migrate_revdb { + git_svn_each(sub { + my $id = shift; + defined(my $pid = fork) or croak $!; + if (!$pid) { + $GIT_SVN = $ENV{GIT_SVN_ID} = $id; + init_vars(); + exit 0 if -r $REVDB; + print "Upgrading svn => git mapping...\n"; + open my $fh, '>>',$REVDB or croak $!; + close $fh; + rebuild(); + print "Done upgrading. You may now delete the ", + "deprecated $GIT_SVN_DIR/revs directory\n"; + exit 0; + } + waitpid $pid, 0; + croak $? if $?; + }); +} + sub migration_check { + migrate_revdb() unless (-e $REVDB); return if (-d "$GIT_DIR/svn" || !-d $GIT_DIR); print "Upgrading repository...\n"; unless (-d "$GIT_DIR/svn") { @@ -2013,15 +2022,19 @@ sub migration_check { s_to_file($url, "$GIT_DIR/svn/$x/info/repo_url"); s_to_file($path, "$GIT_DIR/svn/$x/info/repo_path"); } + migrate_revdb() if (-d $GIT_SVN_DIR && !-w $REVDB); print "Done upgrading.\n"; } sub find_rev_before { - my ($r, $git_svn_id) = @_; - my @revs = map { basename $_ } <$GIT_DIR/svn/$git_svn_id/revs/*>; - foreach my $r0 (sort { $b <=> $a } @revs) { - next if $r0 >= $r; - return ($r0, file_to_s("$GIT_DIR/svn/$git_svn_id/revs/$r0")); + my ($r, $id, $eq_ok) = @_; + my $f = "$GIT_DIR/svn/$id/.rev_db"; + # --$r unless $eq_ok; + while ($r > 0) { + if (my $c = revdb_get($f, $r)) { + return ($r, $c); + } + --$r; } return (undef, undef); } @@ -2029,9 +2042,9 @@ sub find_rev_before { sub init_vars { $GIT_SVN ||= $ENV{GIT_SVN_ID} || 'git-svn'; $GIT_SVN_DIR = "$GIT_DIR/svn/$GIT_SVN"; + $REVDB = "$GIT_SVN_DIR/.rev_db"; $GIT_SVN_INDEX = "$GIT_SVN_DIR/index"; $SVN_URL = undef; - $REV_DIR = "$GIT_SVN_DIR/revs"; $SVN_WC = "$GIT_SVN_DIR/tree"; } @@ -2491,7 +2504,27 @@ sub libsvn_traverse_ignore { $pool->clear; } -sub libsvn_new_tree { +sub revisions_eq { + my ($path, $r0, $r1) = @_; + return 1 if $r0 == $r1; + my $nr = 0; + if ($_use_lib) { + # should be OK to use Pool here (r1 - r0) should be small + my $pool = SVN::Pool->new; + $SVN->get_log("/$path", $r0, $r1, 0, 1, 1, sub {$nr++},$pool); + $pool->clear; + } else { + my ($url, undef) = repo_path_split($SVN_URL); + my $svn_log = svn_log_raw("$url/$path","-r$r0:$r1"); + while (next_log_entry($svn_log)) { $nr++ } + close $svn_log->{fh}; + } + return 0 if ($nr > 1); + return 1; +} + +sub libsvn_find_parent_branch { + return undef; # XXX this function is disabled atm (not tested enough) my ($paths, $rev, $author, $date, $msg) = @_; my $svn_path = '/'.$SVN_PATH; @@ -2502,27 +2535,33 @@ sub libsvn_new_tree { my $branch_from = $i->copyfrom_path or next; my $r = $i->copyfrom_rev; print STDERR "Found possible branch point: ", - "$branch_from => $svn_path, $r\n"; + "$branch_from => $svn_path, $r\n"; $branch_from =~ s#^/##; my $l_map = read_url_paths(); my $url = $SVN->{url}; defined $l_map->{$url} or next; my $id = $l_map->{$url}->{$branch_from} or next; - my $f = "$GIT_DIR/svn/$id/revs/$r"; - while ($r && !-r $f) { - $r--; - $f = "$GIT_DIR/svn/$id/revs/$r"; - } - if (-r $f) { - my $parent = file_to_s($f); + my ($r0, $parent) = find_rev_before($r,$id,1); + if (defined $r0 && defined $parent && + revisions_eq($branch_from, $r0, $r)) { unlink $GIT_SVN_INDEX; print STDERR "Found branch parent: $parent\n"; sys(qw/git-read-tree/, $parent); return libsvn_fetch($parent, $paths, $rev, $author, $date, $msg); + } else { + print STDERR + "Nope, branch point not imported or unknown\n"; } - print STDERR "Nope, branch point not imported or unknown\n"; } + return undef; +} + +sub libsvn_new_tree { + if (my $log_entry = libsvn_find_parent_branch(@_)) { + return $log_entry; + } + my ($paths, $rev, $author, $date, $msg) = @_; open my $gui, '| git-update-index -z --index-info' or croak $!; my $pool = SVN::Pool->new; libsvn_traverse($gui, '', $SVN_PATH, $rev, $pool); @@ -2536,10 +2575,8 @@ sub find_graft_path_commit { foreach my $x (keys %$tree_paths) { next unless ($p1 =~ /^\Q$x\E/); my $i = $tree_paths->{$x}; - my $f = "$GIT_DIR/svn/$i/revs/$r1"; - - return file_to_s($f) if (-r $f); - + my ($r0, $parent) = find_rev_before($r1,$i,1); + return $parent if (defined $r0 && $r0 == $r1); print STDERR "r$r1 of $i not imported\n"; next; } @@ -2551,18 +2588,10 @@ sub find_graft_path_parents { foreach my $x (keys %$tree_paths) { next unless ($p0 =~ /^\Q$x\E/); my $i = $tree_paths->{$x}; - my $f = "$GIT_DIR/svn/$i/revs/$r0"; - while ($r0 && !-r $f) { - # could be an older revision, too... - $r0--; - $f = "$GIT_DIR/svn/$i/revs/$r0"; + my ($r, $parent) = find_rev_before($r0, $i, 1); + if (defined $r && defined $parent && revisions_eq($x,$r,$r0)) { + $grafts->{$c}->{$parent} = 1; } - unless (-r $f) { - print STDERR "r$r0 of $i not imported\n"; - next; - } - my $parent = file_to_s($f); - $grafts->{$c}->{$parent} = 1; } } @@ -2600,8 +2629,7 @@ sub restore_index { sub libsvn_commit_cb { my ($rev, $date, $committer, $c, $msg, $r_last, $cmt_last) = @_; - if ($rev == ($r_last + 1)) { - # optimized (avoid fetch) + if ($_optimize_commits && $rev == ($r_last + 1)) { my $log = libsvn_log_entry($rev,$committer,$date,$msg); $log->{tree} = get_tree_from_treeish($c); my $cmt = git_commit($log, $cmt_last, $c); @@ -2652,6 +2680,49 @@ sub libsvn_skip_unknown_revs { croak "Error from SVN, ($errno): ", $err->expanded_message,"\n"; }; +# Tie::File seems to be prone to offset errors if revisions get sparse, +# it's not that fast, either. Tie::File is also not in Perl 5.6. So +# one of my favorite modules is out :< Next up would be one of the DBM +# modules, but I'm not sure which is most portable... So I'll just +# go with something that's plain-text, but still capable of +# being randomly accessed. So here's my ultra-simple fixed-width +# database. All records are 40 characters + "\n", so it's easy to seek +# to a revision: (41 * rev) is the byte offset. +# A record of 40 0s denotes an empty revision. +# And yes, it's still pretty fast (faster than Tie::File). +sub revdb_set { + my ($file, $rev, $commit) = @_; + length $commit == 40 or croak "arg3 must be a full SHA1 hexsum\n"; + open my $fh, '+<', $file or croak $!; + my $offset = $rev * 41; + # assume that append is the common case: + seek $fh, 0, 2 or croak $!; + my $pos = tell $fh; + if ($pos < $offset) { + print $fh (('0' x 40),"\n") x (($offset - $pos) / 41); + } + seek $fh, $offset, 0 or croak $!; + print $fh $commit,"\n"; + close $fh or croak $!; +} + +sub revdb_get { + my ($file, $rev) = @_; + my $ret; + my $offset = $rev * 41; + open my $fh, '<', $file or croak $!; + seek $fh, $offset, 0; + if (tell $fh == $offset) { + $ret = readline $fh; + if (defined $ret) { + chomp $ret; + $ret = undef if ($ret =~ /^0{40}$/); + } + } + close $fh or croak $!; + return $ret; +} + package SVN::Git::Editor; use vars qw/@ISA/; use strict; diff --git a/contrib/git-svn/t/t0000-contrib-git-svn.sh b/contrib/git-svn/t/t0000-contrib-git-svn.sh index c33b522d08..f896e2c2a8 100644 --- a/contrib/git-svn/t/t0000-contrib-git-svn.sh +++ b/contrib/git-svn/t/t0000-contrib-git-svn.sh @@ -193,5 +193,18 @@ test_expect_success "$name" \ git-rev-list --pretty=raw remotes/alt | grep ^tree | uniq > b && diff -u a b" +name='check imported tree checksums expected tree checksums' +cat > expected <<\EOF +tree f735671b89a7eb30cab1d8597de35bd4271ab813 +tree 4b9af72bb861eaed053854ec502cf7df72618f0f +tree 031b8d557afc6fea52894eaebb45bec52f1ba6d1 +tree 0b094cbff17168f24c302e297f55bfac65eb8bd3 +tree d667270a1f7b109f5eb3aaea21ede14b56bfdd6e +tree 56a30b966619b863674f5978696f4a3594f2fca9 +tree d667270a1f7b109f5eb3aaea21ede14b56bfdd6e +tree 8f51f74cf0163afc9ad68a4b1537288c4558b5a4 +EOF +test_expect_success "$name" "diff -u a expected" + test_done diff --git a/contrib/git-svn/t/t0001-contrib-git-svn-props.sh b/contrib/git-svn/t/t0001-contrib-git-svn-props.sh index 23a5a2a223..54e0ed7353 100644 --- a/contrib/git-svn/t/t0001-contrib-git-svn-props.sh +++ b/contrib/git-svn/t/t0001-contrib-git-svn-props.sh @@ -52,49 +52,49 @@ EOF cd .. rm -rf import -svn co "$svnrepo" test_wc +test_expect_success 'checkout working copy from svn' "svn co $svnrepo test_wc" +test_expect_success 'setup some commits to svn' \ + 'cd test_wc && + echo Greetings >> kw.c && + svn commit -m "Not yet an Id" && + svn up && + echo Hello world >> kw.c && + svn commit -m "Modified file, but still not yet an Id" && + svn up && + svn propset svn:keywords Id kw.c && + svn commit -m "Propset Id" && + svn up && + cd ..' -cd test_wc - echo 'Greetings' >> kw.c - svn commit -m 'Not yet an $Id$' - svn up +test_expect_success 'initialize git-svn' "git-svn init $svnrepo" +test_expect_success 'fetch revisions from svn' 'git-svn fetch' - echo 'Hello world' >> kw.c - svn commit -m 'Modified file, but still not yet an $Id$' - svn up - - svn propset svn:keywords Id kw.c - svn commit -m 'Propset $Id$' - svn up -cd .. - -git-svn init "$svnrepo" -git-svn fetch - -git checkout -b mybranch remotes/git-svn -echo 'Hi again' >> kw.c name='test svn:keywords ignoring' - -git commit -a -m "$name" -git-svn commit remotes/git-svn..mybranch -git pull . remotes/git-svn +test_expect_success "$name" \ + 'git checkout -b mybranch remotes/git-svn && + echo Hi again >> kw.c && + git commit -a -m "test keywoards ignoring" && + git-svn commit remotes/git-svn..mybranch && + git pull . remotes/git-svn' expect='/* $Id$ */' got="`sed -ne 2p kw.c`" test_expect_success 'raw $Id$ found in kw.c' "test '$expect' = '$got'" -cd test_wc - svn propset svn:eol-style CR empty - svn propset svn:eol-style CR crlf - svn propset svn:eol-style CR ne_crlf - svn commit -m 'propset CR on crlf files' - svn up -cd .. +test_expect_success "propset CR on crlf files" \ + 'cd test_wc && + svn propset svn:eol-style CR empty && + svn propset svn:eol-style CR crlf && + svn propset svn:eol-style CR ne_crlf && + svn commit -m "propset CR on crlf files" && + svn up && + cd ..' -git-svn fetch -git pull . remotes/git-svn +test_expect_success 'fetch and pull latest from svn and checkout a new wc' \ + "git-svn fetch && + git pull . remotes/git-svn && + svn co $svnrepo new_wc" -svn co "$svnrepo" new_wc for i in crlf ne_crlf lf ne_lf cr ne_cr empty_cr empty_lf empty empty_crlf do test_expect_success "Comparing $i" "cmp $i new_wc/$i" @@ -106,16 +106,16 @@ cd test_wc printf '$Id$\rHello\rWorld' > ne_cr a_cr=`printf '$Id$\r\nHello\r\nWorld\r\n' | git-hash-object --stdin` a_ne_cr=`printf '$Id$\r\nHello\r\nWorld' | git-hash-object --stdin` - svn propset svn:eol-style CRLF cr - svn propset svn:eol-style CRLF ne_cr - svn propset svn:keywords Id cr - svn propset svn:keywords Id ne_cr - svn commit -m 'propset CRLF on cr files' - svn up + test_expect_success 'Set CRLF on cr files' \ + 'svn propset svn:eol-style CRLF cr && + svn propset svn:eol-style CRLF ne_cr && + svn propset svn:keywords Id cr && + svn propset svn:keywords Id ne_cr && + svn commit -m "propset CRLF on cr files" && + svn up' cd .. - -git-svn fetch -git pull . remotes/git-svn +test_expect_success 'fetch and pull latest from svn' \ + 'git-svn fetch && git pull . remotes/git-svn' b_cr="`git-hash-object cr`" b_ne_cr="`git-hash-object ne_cr`" From 6c5cda89e93915ed2984ba560f3c3d048c7a5702 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Wed, 14 Jun 2006 21:24:03 -0700 Subject: [PATCH 19/25] git-svn: avoid creating some small files repo_path_split() is already pretty fast, and is already optimized via caching. We also don't need to create an exclude file if we're relying on the SVN libraries. Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 26 ++++++++------------------ 1 file changed, 8 insertions(+), 18 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 884969ebdd..88af9c5704 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -1005,12 +1005,6 @@ sub setup_git_svn { close $fh; s_to_file($SVN_URL,"$GIT_SVN_DIR/info/url"); - open my $fd, '>>', "$GIT_SVN_DIR/info/exclude" or croak $!; - print $fd '.svn',"\n"; - close $fd or croak $!; - my ($url, $path) = repo_path_split($SVN_URL); - s_to_file($url, "$GIT_SVN_DIR/info/repo_url"); - s_to_file($path, "$GIT_SVN_DIR/info/repo_path"); } sub assert_svn_wc_clean { @@ -1649,6 +1643,12 @@ sub do_update_index { sub index_changes { return if $_use_lib; + + if (!-f "$GIT_SVN_DIR/info/exclude") { + open my $fd, '>>', "$GIT_SVN_DIR/info/exclude" or croak $!; + print $fd '.svn',"\n"; + close $fd or croak $!; + } my $no_text_base = shift; do_update_index([qw/git-diff-files --name-only -z/], 'remove', @@ -2018,9 +2018,6 @@ sub migration_check { my $dn = dirname("$GIT_DIR/svn/$x"); mkpath([$dn]) unless -d $dn; rename "$GIT_DIR/$x", "$GIT_DIR/svn/$x" or croak "$!: $x"; - my ($url, $path) = repo_path_split($u); - s_to_file($url, "$GIT_DIR/svn/$x/info/repo_url"); - s_to_file($path, "$GIT_DIR/svn/$x/info/repo_path"); } migrate_revdb() if (-d $GIT_SVN_DIR && !-w $REVDB); print "Done upgrading.\n"; @@ -2138,15 +2135,8 @@ sub write_grafts { sub read_url_paths { my $l_map = {}; git_svn_each(sub { my $x = shift; - my $u = file_to_s("$GIT_DIR/svn/$x/info/repo_url"); - my $p = file_to_s("$GIT_DIR/svn/$x/info/repo_path"); - # we hate trailing slashes - if ($u =~ s#(?:^\/+|\/+$)##g) { - s_to_file($u,"$GIT_DIR/svn/$x/info/repo_url"); - } - if ($p =~ s#(?:^\/+|\/+$)##g) { - s_to_file($p,"$GIT_DIR/svn/$x/info/repo_path"); - } + my $url = file_to_s("$GIT_DIR/svn/$x/info/url"); + my ($u, $p) = repo_path_split($url); $l_map->{$u}->{$p} = $x; }); return $l_map; From cf7424b021f99fbc5dc1127725e57ca3d48e981c Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Thu, 15 Jun 2006 12:50:12 -0700 Subject: [PATCH 20/25] git-svn: fix several small bugs, enable branch optimization Share the repack counter between branches when doing multi-fetch. Pass the -d flag to git repack by default. That's the main reason we will want automatic pack generation, to save space and improve disk cache performance. I won't add -a by default since it can generate extremely large packs that make RAM-starved systems unhappy. We no longer generate the .git/svn/$GIT_SVN_ID/info/uuid file, either. It was never read in the first place. Check for and create .rev_db if we need to during fetch (in case somebody manually blew away their .rev_db and wanted to start over. Mainly makes debugging easier). Croak with $? instead of $! if there's an error closing pipes Quiet down some of the chatter, too. Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 144 +++++++++++++++++++---------------- 1 file changed, 80 insertions(+), 64 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 88af9c5704..27f1d682c8 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -368,7 +368,6 @@ sub fetch_lib { defined(my $pid = fork) or croak $!; if (!$pid) { $SVN::Error::handler = \&libsvn_skip_unknown_revs; - print "Fetching revisions $min .. $max\n"; # Yes I'm perfectly aware that the fourth argument # below is the limit revisions number. Unfortunately @@ -391,7 +390,6 @@ sub fetch_lib { $log_msg, @parents); } }); - $SVN::Error::handler = sub { 'quiet warnings' }; exit 0; } waitpid $pid, 0; @@ -463,7 +461,7 @@ sub commit_lib { my (@revs) = @_; my ($r_last, $cmt_last) = svn_grab_base_rev(); defined $r_last or die "Must have an existing revision to commit\n"; - my $fetched = fetch_lib(); + my $fetched = fetch(); if ($r_last != $fetched->{revision}) { print STDERR "There are new revisions that were fetched ", "and need to be merged (or acknowledged) ", @@ -523,7 +521,7 @@ sub commit_lib { $no = 1; } } - close $fh or croak $!; + close $fh or croak $?; if (! defined $r_new && ! defined $cmt_new) { unless ($no) { die "Failed to parse revision information\n"; @@ -633,17 +631,8 @@ sub multi_init { sub multi_fetch { # try to do trunk first, since branches/tags # may be descended from it. - if (-d "$GIT_DIR/svn/trunk") { - print "Fetching trunk\n"; - defined(my $pid = fork) or croak $!; - if (!$pid) { - $GIT_SVN = $ENV{GIT_SVN_ID} = 'trunk'; - init_vars(); - fetch(@_); - exit 0; - } - waitpid $pid, 0; - croak $? if $?; + if (-e "$GIT_DIR/svn/trunk/info/url") { + fetch_child_id('trunk', @_); } rec_fetch('', "$GIT_DIR/svn", @_); } @@ -725,6 +714,41 @@ sub show_log { ########################### utility functions ######################### +sub fetch_child_id { + my $id = shift; + print "Fetching $id\n"; + my $ref = "$GIT_DIR/refs/remotes/$id"; + my $ca = file_to_s($ref) if (-r $ref); + defined(my $pid = fork) or croak $!; + if (!$pid) { + $GIT_SVN = $ENV{GIT_SVN_ID} = $id; + init_vars(); + fetch(@_); + exit 0; + } + waitpid $pid, 0; + croak $? if $?; + return unless $_repack || -r $ref; + + my $cb = file_to_s($ref); + + defined($pid = open my $fh, '-|') or croak $!; + my $url = file_to_s("$GIT_DIR/svn/$id/info/url"); + $url = qr/\Q$url\E/; + if (!$pid) { + exec qw/git-rev-list --pretty=raw/, + $ca ? "$ca..$cb" : $cb or croak $!; + } + while (<$fh>) { + if (/^ git-svn-id: $url\@\d+ [a-f0-9\-]+$/) { + check_repack(); + } elsif (/^ git-svn-id: \S+\@\d+ [a-f0-9\-]+$/) { + last; + } + } + close $fh; +} + sub rec_fetch { my ($pfx, $p, @args) = @_; my @dir; @@ -733,16 +757,7 @@ sub rec_fetch { $pfx .= '/' if $pfx && $pfx !~ m!/$!; my $id = $pfx . basename $_; next if $id eq 'trunk'; - print "Fetching $id\n"; - defined(my $pid = fork) or croak $!; - if (!$pid) { - $GIT_SVN = $ENV{GIT_SVN_ID} = $id; - init_vars(); - fetch(@args); - exit 0; - } - waitpid $pid, 0; - croak $? if $?; + fetch_child_id($id, @args); } elsif (-d $_) { push @dir, $_; } @@ -943,7 +958,6 @@ sub read_uuid { $SVN_UUID = $info->{'Repository UUID'} or croak "Repository UUID unreadable\n"; } - s_to_file($SVN_UUID,"$GIT_SVN_DIR/info/uuid"); } sub quiet_run { @@ -1107,7 +1121,7 @@ sub parse_diff_tree { croak "Error parsing $_\n"; } } - close $diff_fh or croak $!; + close $diff_fh or croak $?; return \@mods; } @@ -1348,7 +1362,7 @@ sub get_commit_message { print $msg $_ or croak $!; } } - close $msg_fh or croak $!; + close $msg_fh or croak $?; } close $msg or croak $!; @@ -1562,7 +1576,7 @@ sub svn_info { push @{$ret->{-order}}, $1; } } - close $info_fh or croak $!; + close $info_fh or croak $?; return $ret; } @@ -1638,7 +1652,7 @@ sub do_update_index { } print $ui $x,"\0"; } - close $ui or croak $!; + close $ui or croak $?; } sub index_changes { @@ -1765,11 +1779,15 @@ sub git_commit { # this output is read via pipe, do not change: print "r$log_msg->{revision} = $commit\n"; + check_repack(); + return $commit; +} + +sub check_repack { if ($_repack && (--$_repack_nr == 0)) { $_repack_nr = $_repack; sys("git repack $_repack_flags"); } - return $commit; } sub set_commit_env { @@ -1877,6 +1895,10 @@ sub svn_cmd_checkout { } sub check_upgrade_needed { + if (!-r $REVDB) { + open my $fh, '>>',$REVDB or croak $!; + close $fh; + } my $old = eval { my $pid = open my $child, '-|'; defined $pid or croak $!; @@ -2026,7 +2048,8 @@ sub migration_check { sub find_rev_before { my ($r, $id, $eq_ok) = @_; my $f = "$GIT_DIR/svn/$id/.rev_db"; - # --$r unless $eq_ok; + return (undef,undef) unless -r $f; + --$r unless $eq_ok; while ($r > 0) { if (my $c = revdb_get($f, $r)) { return ($r, $c); @@ -2072,7 +2095,7 @@ sub set_default_vals { if (defined $_repack) { $_repack = 1000 if ($_repack <= 0); $_repack_nr = $_repack; - $_repack_flags ||= ''; + $_repack_flags ||= '-d'; } } @@ -2352,7 +2375,7 @@ sub libsvn_get_file { close $ho or croak $?; $hash =~ /^$sha1$/o or die "not a sha1: $hash\n"; print $gui $mode,' ',$hash,"\t",$p,"\0" or croak $!; - close $fd or croak $!; + close $fd or croak $?; } sub libsvn_log_entry { @@ -2381,7 +2404,7 @@ sub process_rm { while (<$ls>) { print $gui '0 ',0 x 40,"\t",$_ or croak $!; } - close $ls or croak $!; + close $ls or croak $?; } else { print $gui '0 ',0 x 40,"\t",$f,"\0" or croak $!; } @@ -2411,7 +2434,7 @@ sub libsvn_fetch { $pool->clear; } libsvn_get_file($gui, $_, $rev) foreach (@amr); - close $gui or croak $!; + close $gui or croak $?; return libsvn_log_entry($rev, $author, $date, $msg, [$last_commit]); } @@ -2514,36 +2537,30 @@ sub revisions_eq { } sub libsvn_find_parent_branch { - return undef; # XXX this function is disabled atm (not tested enough) my ($paths, $rev, $author, $date, $msg) = @_; my $svn_path = '/'.$SVN_PATH; # look for a parent from another branch: - foreach (keys %$paths) { - next if ($_ ne $svn_path); - my $i = $paths->{$_}; - my $branch_from = $i->copyfrom_path or next; - my $r = $i->copyfrom_rev; - print STDERR "Found possible branch point: ", - "$branch_from => $svn_path, $r\n"; - $branch_from =~ s#^/##; - my $l_map = read_url_paths(); - my $url = $SVN->{url}; - defined $l_map->{$url} or next; - my $id = $l_map->{$url}->{$branch_from} or next; - my ($r0, $parent) = find_rev_before($r,$id,1); - if (defined $r0 && defined $parent && - revisions_eq($branch_from, $r0, $r)) { - unlink $GIT_SVN_INDEX; - print STDERR "Found branch parent: $parent\n"; - sys(qw/git-read-tree/, $parent); - return libsvn_fetch($parent, $paths, $rev, - $author, $date, $msg); - } else { - print STDERR - "Nope, branch point not imported or unknown\n"; - } + my $i = $paths->{$svn_path} or return; + my $branch_from = $i->copyfrom_path or return; + my $r = $i->copyfrom_rev; + print STDERR "Found possible branch point: ", + "$branch_from => $svn_path, $r\n"; + $branch_from =~ s#^/##; + my $l_map = read_url_paths(); + my $url = $SVN->{url}; + defined $l_map->{$url} or return; + my $id = $l_map->{$url}->{$branch_from} or return; + my ($r0, $parent) = find_rev_before($r,$id,1); + return unless (defined $r0 && defined $parent); + if (revisions_eq($branch_from, $r0, $r)) { + unlink $GIT_SVN_INDEX; + print STDERR "Found branch parent: $parent\n"; + sys(qw/git-read-tree/, $parent); + return libsvn_fetch($parent, $paths, $rev, + $author, $date, $msg); } + print STDERR "Nope, branch point not imported or unknown\n"; return undef; } @@ -2556,7 +2573,7 @@ sub libsvn_new_tree { my $pool = SVN::Pool->new; libsvn_traverse($gui, '', $SVN_PATH, $rev, $pool); $pool->clear; - close $gui or croak $!; + close $gui or croak $?; return libsvn_log_entry($rev, $author, $date, $msg); } @@ -2630,7 +2647,7 @@ sub libsvn_commit_cb { exit 1; } } else { - fetch_lib("$rev=$c"); + fetch("$rev=$c"); } } @@ -2664,7 +2681,6 @@ sub libsvn_skip_unknown_revs { # 175002 - http(s):// # More codes may be discovered later... if ($errno == 175002 || $errno == 160013) { - print STDERR "directory non-existent\n"; return; } croak "Error from SVN, ($errno): ", $err->expanded_message,"\n"; From 968bdf1f3da677255c8950bb5b5a9de7e1150279 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Thu, 15 Jun 2006 13:36:12 -0700 Subject: [PATCH 21/25] git-svn: Eliminate temp file usage in libsvn_get_file() This means we'll have a loose object when we encounter a symlink but that's not the common case. We also don't have to worry about svn:eol-style when using the SVN libraries, either. So remove the code to deal with that. Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 56 +++++++++++++++--------------------- 1 file changed, 23 insertions(+), 33 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 27f1d682c8..149149f0ef 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -31,6 +31,7 @@ use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/; use File::Spec qw//; use POSIX qw/strftime/; +use IPC::Open3; use Memoize; memoize('revisions_eq'); @@ -2335,47 +2336,36 @@ sub libsvn_get_file { my $p = $f; return unless ($p =~ s#^\Q$SVN_PATH\E/?##); - my $fd = IO::File->new_tmpfile or croak $!; + my ($hash, $pid, $in, $out); my $pool = SVN::Pool->new; - my ($r, $props) = $SVN->get_file($f, $rev, $fd, $pool); + defined($pid = open3($in, $out, '>&STDERR', + qw/git-hash-object -w --stdin/)) or croak $!; + my ($r, $props) = $SVN->get_file($f, $rev, $in, $pool); + $in->flush == 0 or croak $!; + close $in or croak $!; $pool->clear; - $fd->flush == 0 or croak $!; - seek $fd, 0, 0 or croak $!; - if (my $es = $props->{'svn:eol-style'}) { - my $new_fd = IO::File->new_tmpfile or croak $!; - eol_cp_fd($fd, $new_fd, $es); - close $fd or croak $!; - $fd = $new_fd; - seek $fd, 0, 0 or croak $!; - $fd->flush == 0 or croak $!; - } - my $mode = '100644'; - if (exists $props->{'svn:executable'}) { - $mode = '100755'; - } + chomp($hash = do { local $/; <$out> }); + close $out or croak $!; + waitpid $pid, 0; + $hash =~ /^$sha1$/o or die "not a sha1: $hash\n"; + + my $mode = exists $props->{'svn:executable'} ? '100755' : '100644'; if (exists $props->{'svn:special'}) { $mode = '120000'; - local $/; - my $link = <$fd>; + my $link = `git-cat-file blob $hash`; $link =~ s/^link // or die "svn:special file with contents: <", $link, "> is not understood\n"; - seek $fd, 0, 0 or croak $!; - truncate $fd, 0 or croak $!; - print $fd $link or croak $!; - seek $fd, 0, 0 or croak $!; - $fd->flush == 0 or croak $!; + defined($pid = open3($in, $out, '>&STDERR', + qw/git-hash-object -w --stdin/)) or croak $!; + print $in $link; + $in->flush == 0 or croak $!; + close $in or croak $!; + chomp($hash = do { local $/; <$out> }); + close $out or croak $!; + waitpid $pid, 0; + $hash =~ /^$sha1$/o or die "not a sha1: $hash\n"; } - my $pid = open my $ho, '-|'; - defined $pid or croak $!; - if (!$pid) { - open STDIN, '<&', $fd or croak $!; - exec qw/git-hash-object -w --stdin/ or croak $!; - } - chomp(my $hash = do { local $/; <$ho> }); - close $ho or croak $?; - $hash =~ /^$sha1$/o or die "not a sha1: $hash\n"; print $gui $mode,' ',$hash,"\t",$p,"\0" or croak $!; - close $fd or croak $?; } sub libsvn_log_entry { From c0d4822268d30b1668e94986a845b8bb5441e8b3 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Thu, 15 Jun 2006 18:48:22 -0700 Subject: [PATCH 22/25] git-svn: bugfix and optimize the 'log' command Revisions with long commit messages were being skipped, since the 'git-svn-id' metadata line was at the end and git-log uses a 32k buffer to print the commits. Also the last 'git-svn-id' metadata line in a commit is always the valid one, so make sure we use that, as well. Made the verbose flag work by passing the correct option switch ('--summary') to git-log. Finally, optimize -r/--revision argument handling by passing the appropriate limits to revision Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 60 +++++++++++++++++++++++++++++++----- 1 file changed, 52 insertions(+), 8 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 149149f0ef..417fcf1feb 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -663,17 +663,15 @@ sub show_log { my $pid = open(my $log,'-|'); defined $pid or croak $!; if (!$pid) { - my @rl = (qw/git-log --abbrev-commit --pretty=raw - --default/, "remotes/$GIT_SVN"); - push @rl, '--raw' if $_verbose; - exec(@rl, @args) or croak $!; + exec(git_svn_log_cmd($r_min,$r_max), @args) or croak $!; } setup_pager(); my (@k, $c, $d); + while (<$log>) { if (/^commit ($sha1_short)/o) { my $cmt = $1; - if ($c && defined $c->{r} && $c->{r} != $r_last) { + if ($c && cmt_showable($c) && $c->{r} != $r_last) { $r_last = $c->{r}; process_commit($c, $r_min, $r_max, \@k) or goto out; @@ -692,8 +690,7 @@ sub show_log { } elsif ($d) { push @{$c->{diff}}, $_; } elsif (/^ (git-svn-id:.+)$/) { - my ($url, $rev, $uuid) = extract_metadata($1); - $c->{r} = $rev; + (undef, $c->{r}, undef) = extract_metadata($1); } elsif (s/^ //) { push @{$c->{l}}, $_; } @@ -715,6 +712,52 @@ sub show_log { ########################### utility functions ######################### +sub cmt_showable { + my ($c) = @_; + return 1 if defined $c->{r}; + if ($c->{l} && $c->{l}->[-1] eq "...\n" && + $c->{a_raw} =~ /\@([a-f\d\-]+)>$/) { + my @msg = safe_qx(qw/git-cat-file commit/, $c->{c}); + shift @msg while ($msg[0] ne "\n"); + shift @msg; + @{$c->{l}} = grep !/^git-svn-id: /, @msg; + + (undef, $c->{r}, undef) = extract_metadata( + (grep(/^git-svn-id: /, @msg))[-1]); + } + return defined $c->{r}; +} + +sub git_svn_log_cmd { + my ($r_min, $r_max) = @_; + my @cmd = (qw/git-log --abbrev-commit --pretty=raw + --default/, "refs/remotes/$GIT_SVN"); + push @cmd, '--summary' if $_verbose; + return @cmd unless defined $r_max; + if ($r_max == $r_min) { + push @cmd, '--max-count=1'; + if (my $c = revdb_get($REVDB, $r_max)) { + push @cmd, $c; + } + } else { + my ($c_min, $c_max); + $c_max = revdb_get($REVDB, $r_max); + $c_min = revdb_get($REVDB, $r_min); + if ($c_min && $c_max) { + if ($r_max > $r_max) { + push @cmd, "$c_min..$c_max"; + } else { + push @cmd, "$c_max..$c_min"; + } + } elsif ($r_max > $r_min) { + push @cmd, $c_max; + } else { + push @cmd, $c_min; + } + } + return @cmd; +} + sub fetch_child_id { my $id = shift; print "Fetching $id\n"; @@ -2206,6 +2249,7 @@ sub setup_pager { # translated to Perl from pager.c sub get_author_info { my ($dest, $author, $t, $tz) = @_; $author =~ s/(?:^\s*|\s*$)//g; + $dest->{a_raw} = $author; my $_a; if ($_authors) { $_a = $rusers{$author} || undef; @@ -2440,7 +2484,7 @@ sub svn_grab_base_rev { close $fh; if (defined $c && length $c) { my ($url, $rev, $uuid) = extract_metadata((grep(/^git-svn-id: /, - safe_qx(qw/git-cat-file commit/, $c)))[0]); + safe_qx(qw/git-cat-file commit/, $c)))[-1]); return ($rev, $c); } return (undef, undef); From 86f363791b281fb916414a89282b2e67cdaa36c0 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Thu, 15 Jun 2006 19:13:56 -0700 Subject: [PATCH 23/25] git-svn: tests no longer fail if LC_ALL is not a UTF-8 locale Signed-off-by: Eric Wong --- contrib/git-svn/Makefile | 5 +++-- contrib/git-svn/t/t0000-contrib-git-svn.sh | 8 ++++++-- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/contrib/git-svn/Makefile b/contrib/git-svn/Makefile index d73aa5641c..6aedb10f12 100644 --- a/contrib/git-svn/Makefile +++ b/contrib/git-svn/Makefile @@ -32,9 +32,10 @@ test: git-svn cd t && $(SHELL) ./t0000-contrib-git-svn.sh $(TEST_FLAGS) cd t && $(SHELL) ./t0001-contrib-git-svn-props.sh $(TEST_FLAGS) +# we can test NO_OPTIMIZE_COMMITS independently of LC_ALL full-test: - $(MAKE) test GIT_SVN_NO_LIB=1 GIT_SVN_NO_OPTIMIZE_COMMITS=1 - $(MAKE) test GIT_SVN_NO_LIB=0 GIT_SVN_NO_OPTIMIZE_COMMITS=1 + $(MAKE) test GIT_SVN_NO_LIB=1 GIT_SVN_NO_OPTIMIZE_COMMITS=1 LC_ALL=C + $(MAKE) test GIT_SVN_NO_LIB=0 GIT_SVN_NO_OPTIMIZE_COMMITS=1 LC_ALL=C $(MAKE) test GIT_SVN_NO_LIB=1 GIT_SVN_NO_OPTIMIZE_COMMITS=0 \ LC_ALL=en_US.UTF-8 $(MAKE) test GIT_SVN_NO_LIB=0 GIT_SVN_NO_OPTIMIZE_COMMITS=0 \ diff --git a/contrib/git-svn/t/t0000-contrib-git-svn.sh b/contrib/git-svn/t/t0000-contrib-git-svn.sh index f896e2c2a8..0f52746647 100644 --- a/contrib/git-svn/t/t0000-contrib-git-svn.sh +++ b/contrib/git-svn/t/t0000-contrib-git-svn.sh @@ -194,8 +194,12 @@ test_expect_success "$name" \ diff -u a b" name='check imported tree checksums expected tree checksums' -cat > expected <<\EOF -tree f735671b89a7eb30cab1d8597de35bd4271ab813 +rm -f expected +if test -n "$GIT_SVN_LC_ALL" && echo $GIT_SVN_LC_ALL | grep -q '\.UTF-8$' +then + echo tree f735671b89a7eb30cab1d8597de35bd4271ab813 > expected +fi +cat >> expected <<\EOF tree 4b9af72bb861eaed053854ec502cf7df72618f0f tree 031b8d557afc6fea52894eaebb45bec52f1ba6d1 tree 0b094cbff17168f24c302e297f55bfac65eb8bd3 From 0e8a002c59cbaca692dac81320be44c965588291 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Thu, 15 Jun 2006 19:51:05 -0700 Subject: [PATCH 24/25] git-svn: svn (command-line) 1.0.x compatibility Tested on a plain Ubuntu Warty installation using subversion 1.0.6-1.2ubuntu3 svn add --force was never needed, as it only affected directories, which git (thankfully) doesn't track The 1.0.x also didn't support symlinks(!), so allow NO_SYMLINK to be defined for running tests Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 4 +- contrib/git-svn/t/t0000-contrib-git-svn.sh | 80 ++++++++++++---------- 2 files changed, 46 insertions(+), 38 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index 417fcf1feb..ab1d06500d 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -1306,12 +1306,12 @@ sub svn_checkout_tree { } elsif ($m->{chg} eq 'T') { sys(qw(svn rm --force),$m->{file_b}); apply_mod_line_blob($m); - sys(qw(svn add --force), $m->{file_b}); + sys(qw(svn add), $m->{file_b}); svn_check_prop_executable($m); } elsif ($m->{chg} eq 'A') { svn_ensure_parent_path( $m->{file_b} ); apply_mod_line_blob($m); - sys(qw(svn add --force), $m->{file_b}); + sys(qw(svn add), $m->{file_b}); svn_check_prop_executable($m); } else { croak "Invalid chg: $m->{chg}\n"; diff --git a/contrib/git-svn/t/t0000-contrib-git-svn.sh b/contrib/git-svn/t/t0000-contrib-git-svn.sh index 0f52746647..443d518367 100644 --- a/contrib/git-svn/t/t0000-contrib-git-svn.sh +++ b/contrib/git-svn/t/t0000-contrib-git-svn.sh @@ -11,7 +11,10 @@ mkdir import cd import echo foo > foo -ln -s foo foo.link +if test -z "$NO_SYMLINK" +then + ln -s foo foo.link +fi mkdir -p dir/a/b/c/d/e echo 'deep dir' > dir/a/b/c/d/e/file mkdir -p bar @@ -129,46 +132,45 @@ test_expect_success "$name" \ -name='executable file becomes a symlink to bar/zzz (file)' -rm exec.sh -ln -s bar/zzz exec.sh -git update-index exec.sh -git commit -m "$name" +if test -z "$NO_SYMLINK" +then + name='executable file becomes a symlink to bar/zzz (file)' + rm exec.sh + ln -s bar/zzz exec.sh + git update-index exec.sh + git commit -m "$name" -test_expect_success "$name" \ - "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && - svn up $SVN_TREE && - test -L $SVN_TREE/exec.sh" + test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + svn up $SVN_TREE && + test -L $SVN_TREE/exec.sh" + name='new symlink is added to a file that was also just made executable' + chmod +x bar/zzz + ln -s bar/zzz exec-2.sh + git update-index --add bar/zzz exec-2.sh + git commit -m "$name" + test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + svn up $SVN_TREE && + test -x $SVN_TREE/bar/zzz && + test -L $SVN_TREE/exec-2.sh" -name='new symlink is added to a file that was also just made executable' -chmod +x bar/zzz -ln -s bar/zzz exec-2.sh -git update-index --add bar/zzz exec-2.sh -git commit -m "$name" + name='modify a symlink to become a file' + git help > help || true + rm exec-2.sh + cp help exec-2.sh + git update-index exec-2.sh + git commit -m "$name" -test_expect_success "$name" \ - "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && - svn up $SVN_TREE && - test -x $SVN_TREE/bar/zzz && - test -L $SVN_TREE/exec-2.sh" - - - -name='modify a symlink to become a file' -git help > help || true -rm exec-2.sh -cp help exec-2.sh -git update-index exec-2.sh -git commit -m "$name" - -test_expect_success "$name" \ - "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && - svn up $SVN_TREE && - test -f $SVN_TREE/exec-2.sh && - test ! -L $SVN_TREE/exec-2.sh && - diff -u help $SVN_TREE/exec-2.sh" + test_expect_success "$name" \ + "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + svn up $SVN_TREE && + test -f $SVN_TREE/exec-2.sh && + test ! -L $SVN_TREE/exec-2.sh && + diff -u help $SVN_TREE/exec-2.sh" +fi if test -n "$GIT_SVN_LC_ALL" && echo $GIT_SVN_LC_ALL | grep -q '\.UTF-8$' @@ -193,6 +195,12 @@ test_expect_success "$name" \ git-rev-list --pretty=raw remotes/alt | grep ^tree | uniq > b && diff -u a b" +if test -n "$NO_SYMLINK" +then + test_done + exit 0 +fi + name='check imported tree checksums expected tree checksums' rm -f expected if test -n "$GIT_SVN_LC_ALL" && echo $GIT_SVN_LC_ALL | grep -q '\.UTF-8$' From 1a82e79315ed633f6b0b1fc4076054950c5380d3 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Fri, 16 Jun 2006 02:55:13 -0700 Subject: [PATCH 25/25] git-svn: rebuild convenience and bugfixes We will now automatically fetch the refs/remotes/git-svn ref from origin and store a Pull: line for it. --remote= may be passed if your remote is named something other than 'origin' Also, remember to make GIT_SVN_DIR whenever we need to create .rev_db Signed-off-by: Eric Wong --- contrib/git-svn/git-svn.perl | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/contrib/git-svn/git-svn.perl b/contrib/git-svn/git-svn.perl index ab1d06500d..da0ff9ad8a 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -42,7 +42,7 @@ my $sha1 = qr/[a-f\d]{40}/; my $sha1_short = qr/[a-f\d]{4,40}/; my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, - $_find_copies_harder, $_l, $_cp_similarity, + $_find_copies_harder, $_l, $_cp_similarity, $_cp_remote, $_repack, $_repack_nr, $_repack_flags, $_template, $_shared, $_no_default_regex, $_no_graft_copy, $_limit, $_verbose, $_incremental, $_oneline, $_l_fmt, $_show_commit, @@ -86,6 +86,7 @@ { 'revision|r=i' => \$_revision } ], rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)", { 'no-ignore-externals' => \$_no_ignore_ext, + 'copy-remote|remote=s' => \$_cp_remote, 'upgrade' => \$_upgrade } ], 'graft-branches' => [ \&graft_branches, 'Detect merges/branches from already imported history', @@ -134,7 +135,7 @@ load_authors() if $_authors; load_all_refs() if $_branch_all_refs; svn_compat_check(); -migration_check() unless $cmd =~ /^(?:init|multi-init)$/; +migration_check() unless $cmd =~ /^(?:init|rebuild|multi-init)$/; $cmd{$cmd}->[0]->(@ARGV); exit 0; @@ -174,6 +175,9 @@ sub version { } sub rebuild { + if (quiet_run(qw/git-rev-parse --verify/,"refs/remotes/$GIT_SVN^0")) { + copy_remote_ref(); + } $SVN_URL = shift or undef; my $newest_rev = 0; if ($_upgrade) { @@ -1940,6 +1944,7 @@ sub svn_cmd_checkout { sub check_upgrade_needed { if (!-r $REVDB) { + -d $GIT_SVN_DIR or mkpath([$GIT_SVN_DIR]); open my $fh, '>>',$REVDB or croak $!; close $fh; } @@ -2052,6 +2057,7 @@ sub migrate_revdb { init_vars(); exit 0 if -r $REVDB; print "Upgrading svn => git mapping...\n"; + -d $GIT_SVN_DIR or mkpath([$GIT_SVN_DIR]); open my $fh, '>>',$REVDB or croak $!; close $fh; rebuild(); @@ -2763,6 +2769,17 @@ sub revdb_get { return $ret; } +sub copy_remote_ref { + my $origin = $_cp_remote ? $_cp_remote : 'origin'; + my $ref = "refs/remotes/$GIT_SVN"; + if (safe_qx('git-ls-remote', $origin, $ref)) { + sys(qw/git fetch/, $origin, "$ref:$ref"); + } else { + die "Unable to find remote reference: ", + "refs/remotes/$GIT_SVN on $origin\n"; + } +} + package SVN::Git::Editor; use vars qw/@ISA/; use strict;