From: Junio C Hamano Date: Sat, 17 Jun 2006 05:33:28 +0000 (-0700) Subject: Merge git://git.bogomips.org/git-svn X-Git-Url: https://git.octo.it/?a=commitdiff_plain;h=5b139a66fcac6ebe6a1ca483ced8cc70f65d3a78;hp=b642d9ef643371990c0a921836f2a074d48ce1b3;p=git.git Merge git://git.bogomips.org/git-svn * git://git.bogomips.org/git-svn: (25 commits) git-svn: rebuild convenience and bugfixes git-svn: svn (command-line) 1.0.x compatibility git-svn: tests no longer fail if LC_ALL is not a UTF-8 locale git-svn: bugfix and optimize the 'log' command git-svn: Eliminate temp file usage in libsvn_get_file() git-svn: fix several small bugs, enable branch optimization git-svn: avoid creating some small files git-svn: make the $GIT_DIR/svn/*/revs directory obsolete git-svn: add support for Perl SVN::* libraries git-svn: add 'log' command, a facsimile of basic `svn log' git-svn: add UTF-8 message test git-svn: add some functionality to better support branches in svn git-svn: add --shared and --template= options to pass to init-db git-svn: add --repack and --repack-flags= options git-svn: minor cleanups, extra error-checking git-svn: Move all git-svn-related paths into $GIT_DIR/svn git-svn: support manually placed initial trees from fetch git-svn: optimize --branch and --branch-all-ref git-svn: --branch-all-refs / -B support git-svn: support -C passing to git-diff-tree ... --- diff --git a/contrib/git-svn/Makefile b/contrib/git-svn/Makefile index 48f60b3a..6aedb10f 100644 --- a/contrib/git-svn/Makefile +++ b/contrib/git-svn/Makefile @@ -29,8 +29,17 @@ 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) + +# 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 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 \ + 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 aac87797..da0ff9ad 100755 --- a/contrib/git-svn/git-svn.perl +++ b/contrib/git-svn/git-svn.perl @@ -6,14 +6,16 @@ use strict; use vars qw/ $AUTHOR $VERSION $SVN_URL $SVN_INFO $SVN_WC $SVN_UUID $GIT_SVN_INDEX $GIT_SVN - $GIT_DIR $REV_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'); $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'; $ENV{LC_ALL} = 'C'; @@ -26,19 +28,41 @@ use Carp qw/croak/; use IO::File qw//; use File::Basename qw/dirname basename/; use File::Path qw/mkpath/; -use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/; +use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/; use File::Spec qw//; use POSIX qw/strftime/; +use IPC::Open3; +use Memoize; +memoize('revisions_eq'); + +my ($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, - $_find_copies_harder, $_l, $_version, $_upgrade, $_authors); -my (@_branch_from, %tree_map, %users); -my $_svn_co_url_revs; + $_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, + $_version, $_upgrade, $_authors, $_branch_all_refs, @_opt_m); +my (@_branch_from, %tree_map, %users, %rusers, %equiv); +my ($_svn_co_url_revs, $_svn_pg_peg_revs); +my @repo_path_split_cache; my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext, 'branch|b=s' => \@_branch_from, - 'authors-file|A=s' => \$_authors ); + 'branch-all-refs|B' => \$_branch_all_refs, + 'authors-file|A=s' => \$_authors, + 'repack:i' => \$_repack, + 'repack-flags|repack-args|repack-opts=s' => \$_repack_flags); + +my ($_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" ); @@ -47,20 +71,45 @@ my %cmd = ( 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)", + \%init_opts ], commit => [ \&commit, "Commit git revisions to SVN", { 'stdin|' => \$_stdin, 'edit|e' => \$_edit, '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", { } ], + '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, + 'copy-remote|remote=s' => \$_cp_remote, '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 ], + '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; for (my $i = 0; $i < @ARGV; $i++) { if (defined $cmd{$ARGV[$i]}) { @@ -72,40 +121,21 @@ for (my $i = 0; $i < @ARGV; $i++) { my %opts = %{$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; - } - } -} - -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_INDEX = "$GIT_DIR/$GIT_SVN/index"; -$SVN_URL = undef; -$REV_DIR = "$GIT_DIR/$GIT_SVN/revs"; -$SVN_WC = "$GIT_DIR/$GIT_SVN/tree"; +read_repo_config(\%opts); +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; version() if $_version; usage(1) unless defined $cmd; +init_vars(); load_authors() if $_authors; +load_all_refs() if $_branch_all_refs; svn_compat_check(); +migration_check() unless $cmd =~ /^(?:init|rebuild|multi-init)$/; $cmd{$cmd}->[0]->(@ARGV); exit 0; @@ -124,7 +154,7 @@ Usage: $0 [options] [arguments]\n 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"; @@ -145,6 +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) { @@ -165,18 +198,10 @@ 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 @@ -184,7 +209,6 @@ 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"; @@ -194,11 +218,13 @@ sub rebuild { setup_git_svn(); $latest = $rev; } - assert_revision_eq_or_unknown($rev, $c); - sys('git-update-ref',"$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 $?; + + goto out if $_use_lib; if (!chdir $SVN_WC) { svn_cmd_checkout($SVN_URL, $latest, $SVN_WC); chdir $SVN_WC or croak $!; @@ -212,10 +238,11 @@ 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 $?; +out: if ($_upgrade) { print STDERR <<""; Keeping deprecated refs/head/$GIT_SVN-HEAD for now. Please remove it @@ -227,16 +254,29 @@ when you have upgraded your tools and habits to use refs/remotes/$GIT_SVN 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) { - 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(); } 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 $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'; @@ -247,7 +287,11 @@ sub fetch { 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 $!; @@ -257,13 +301,18 @@ sub fetch { } else { chdir $SVN_WC or croak $!; read_uuid(); - $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; 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"; @@ -277,12 +326,89 @@ 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; + + # 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); + } + }); + 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(); @@ -307,36 +433,127 @@ sub commit { } } chomp @revs; + $_use_lib ? commit_lib(@revs) : commit_cmd(@revs); + print "Done committing ",scalar @revs," revisions to SVN\n"; +} - fetch(); - chdir $SVN_WC or croak $!; +sub commit_cmd { + my (@revs) = @_; + + 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'}; + 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); } - 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(); + 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 $mods = libsvn_checkout_tree($cmt_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(); +} - $SVN_URL ||= file_to_s("$GIT_DIR/$GIT_SVN/info/url"); +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"){ s#^\./##; - @{$ign{$_}} = safe_qx(qw(svn propget svn:ignore),$_); + @{$ign{$_}} = svn_propget_base('svn:ignore', $_); }}, no_chdir=>1},'.'); print "\n# /\n"; @@ -348,14 +565,495 @@ 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); + 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,$p); + } + } + unless ($_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, $gr_file); + unlink "$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, $_tags, '--tags/-t', 'tags/'); +} + +sub multi_fetch { + # try to do trunk first, since branches/tags + # may be descended from it. + if (-e "$GIT_DIR/svn/trunk/info/url") { + fetch_child_id('trunk', @_); + } + 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) { + 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 && cmt_showable($c) && $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}}, $_; + } elsif (/^ (git-svn-id:.+)$/) { + (undef, $c->{r}, undef) = extract_metadata($1); + } elsif (s/^ //) { + push @{$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 || $_oneline; +} + ########################### utility functions ######################### +sub cmt_showable { + my ($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"; + 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, $p, @args) = @_; + my @dir; + foreach (sort <$p/*>) { + if (-r "$_/info/url") { + $pfx .= '/' if $pfx && $pfx !~ m!/$!; + my $id = $pfx . basename $_; + next if $id eq 'trunk'; + fetch_child_id($id, @args); + } 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 = $_use_lib ? libsvn_ls_fullurl($var) + : safe_qx(qw/svn ls --non-interactive/, $var)); + my $old = $GIT_SVN; + defined(my $pid = fork) or croak $!; + if (!$pid) { + 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 $_; + } + } + return ''; +} + +# this isn't funky-filename safe, but good enough for now... +sub graft_file_copy_cmd { + my ($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) { + 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>) { + chomp; + if (/^\-{72}$/) { + $mp = $r = undef; + } elsif (/^r(\d+) \| /) { + $r = $1 unless defined $r; + } elsif (/^Changed paths:/) { + $mp = 1; + } elsif ($mp && m#^ [AR] /(\S.*?) \(from /(\S+?):(\d+)\)$#) { + my ($p1, $p0, $r0) = ($1, $2, $3); + my $c = find_graft_path_commit($paths, $p1, $r); + next unless $c; + find_graft_path_parents($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); + 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, $max, 0, 1, 1, + sub { + libsvn_graft_file_copies($grafts, $tree_paths, + $path, @_); + }, $pool); + $pool->clear; + last if ($max >= $head); + $min = $max + 1; + $max += $inc; + $max = $head if ($max > $head); + } + $SVN::Error::handler = $eh; +} + +sub process_merge_msg_matches { + my ($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('.'); - $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,"$GIT_DIR/$GIT_SVN/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#/+#, $path); + + if ($_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)/; + $path = join('/',@paths); + return ($url, $path); } sub setup_git_svn { @@ -363,17 +1061,16 @@ 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([$REV_DIR]); - s_to_file($SVN_URL,"$GIT_DIR/$GIT_SVN/info/url"); + mkpath([$GIT_SVN_DIR]); + mkpath(["$GIT_SVN_DIR/info"]); + open my $fh, '>>',$REVDB or croak $!; + close $fh; + s_to_file($SVN_URL,"$GIT_SVN_DIR/info/url"); - open my $fd, '>>', "$GIT_DIR/$GIT_SVN/info/exclude" or croak $!; - print $fd '.svn',"\n"; - close $fd or croak $!; } 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 $lcr = svn_info('.')->{'Last Changed Rev'}; @@ -396,7 +1093,7 @@ sub assert_svn_wc_clean { } } -sub assert_tree { +sub get_tree_from_treeish { my ($treeish) = @_; croak "Not a sha1: $treeish\n" unless $treeish =~ /^$sha1$/o; chomp(my $type = `git-cat-file -t $treeish`); @@ -413,20 +1110,22 @@ sub assert_tree { } else { die "$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"; } @@ -470,7 +1169,7 @@ sub parse_diff_tree { croak "Error parsing $_\n"; } } - close $diff_fh or croak $!; + close $diff_fh or croak $?; return \@mods; } @@ -564,24 +1263,31 @@ sub precommit_check { } } -sub svn_checkout_tree { - my ($svn_rev, $treeish) = @_; - my $from = file_to_s("$REV_DIR/$svn_rev"); + +sub get_diff { + my ($from, $treeish) = @_; assert_tree($from); print "diff-tree $from $treeish\n"; 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 $!; } - 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 ($from, $treeish) = @_; + my $mods = get_diff($from->{commit}, $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 ); @@ -604,12 +1310,12 @@ 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"; @@ -624,6 +1330,23 @@ sub svn_checkout_tree { return $mods; } +sub libsvn_checkout_tree { + my ($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) { + my $f = $m->{chg}; + if (defined $o{$f}) { + $ed->$f($m); + } else { + croak "Invalid change type: $f\n"; + } + } + $ed->rmdirs if $_rmdir; + return $mods; +} + # svn ls doesn't work with respect to the current working tree, but what's # in the repository. There's not even an option for it... *sigh* # (added files don't show up and removed files remain in the ls listing) @@ -662,12 +1385,12 @@ sub handle_rmdir { } } -sub svn_commit_tree { - my ($svn_rev, $commit) = @_; - my $commit_msg = "$GIT_DIR/$GIT_SVN/.svn-commit.tmp.$$"; +sub get_commit_message { + my ($commit, $commit_msg) = (@_); my %log_msg = ( msg => '' ); open my $msg, '>', $commit_msg or croak $!; + print "commit: $commit\n"; chomp(my $type = `git-cat-file -t $commit`); if ($type eq 'commit') { my $pid = open my $msg_fh, '-|'; @@ -687,7 +1410,7 @@ sub svn_commit_tree { print $msg $_ or croak $!; } } - close $msg_fh or croak $!; + close $msg_fh or croak $?; } close $msg or croak $!; @@ -701,43 +1424,93 @@ sub svn_commit_tree { { local $/; chomp($log_msg{msg} = <$msg>); } close $msg or croak $!; - my ($oneline) = ($log_msg{msg} =~ /([^\n\r]+)/); + return \%log_msg; +} + +sub svn_commit_tree { + my ($last, $commit) = @_; + my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$"; + my $log_msg = get_commit_message($commit, $commit_msg); + my ($oneline) = ($log_msg->{msg} =~ /([^\n\r]+)/); 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 ($_optimize_commits && ($committed == ($last->{revision} + 1))) { + push @svn_up, "-r$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 (\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} = $rev_committed; - $log_msg{msg} .= "\n"; - my $parent = file_to_s("$REV_DIR/$svn_rev"); - git_commit(\%log_msg, $parent, $commit); - return $rev_committed; + $log_msg->{date} = "$tz $Y-$m-$d $H:$M:$S"; + $log_msg->{author} = $info->{'Last Changed Author'}; + $log_msg->{revision} = $committed; + $log_msg->{msg} .= "\n"; + $log_msg->{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$last->{revision}"; sys(@svn_up); - return fetch("$rev_committed=$commit")->{revision}; + return fetch("$committed=$commit"); +} + +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) @@ -752,7 +1525,7 @@ 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 => $log_fh }; } @@ -851,7 +1624,7 @@ sub svn_info { push @{$ret->{-order}}, $1; } } - close $info_fh or croak $!; + close $info_fh or croak $?; return $ret; } @@ -859,26 +1632,39 @@ sub sys { system(@_) == 0 or croak $? } sub eol_cp { my ($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 $!; binmode $wfd or croak $!; + eol_cp_fd($rfd, $wfd, $es); + close $rfd or croak $!; + close $wfd or croak $!; +} - my $eol = $EOL{$es} or undef; - if ($eol) { - print "$eol: $from => $to\n"; - } +sub eol_cp_fd { + my ($rfd, $wfd, $es) = @_; + my $eol = defined $es ? $EOL{$es} : undef; 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 { @@ -897,7 +1683,7 @@ 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', @@ -914,16 +1700,23 @@ sub do_update_index { } print $ui $x,"\0"; } - close $ui or croak $!; + close $ui or croak $?; } sub index_changes { - my $no_text_base = shift; + 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', $no_text_base); do_update_index([qw/git-ls-files -z --others/, - "--exclude-from=$GIT_DIR/$GIT_SVN/info/exclude"], + "--exclude-from=$GIT_SVN_DIR/info/exclude"], 'add', $no_text_base); } @@ -947,10 +1740,9 @@ 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 = $c already exists! Why are we refetching it?"; } } @@ -966,103 +1758,92 @@ sub trees_eq { return 1; } -sub assert_revision_eq_or_unknown { - my ($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}); - 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 $tree = $log_msg->{tree}; + if (!defined $tree) { + my $index = set_index($GIT_SVN_INDEX); + index_changes(); + chomp($tree = `git-write-tree`); + croak $? if $?; + restore_index($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; + } - my $pid = fork; - defined $pid or croak $!; + defined(my $pid = open my $out_fh, '-|') or croak $!; if ($pid == 0) { - $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX; - index_changes(); - chomp(my $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; - } - } 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: $commit\n"; } my @update_ref = ('git-update-ref',"refs/remotes/$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"; - } - waitpid $pid, 0; + quiet_run(qw/git-rev-parse --verify/,"refs/remotes/$GIT_SVN^0"); push @update_ref, $primary_parent unless $?; } sys(@update_ref); - sys('git-update-ref',"$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"; + check_repack(); return $commit; } +sub check_repack { + if ($_repack && (--$_repack_nr == 0)) { + $_repack_nr = $_repack; + sys("git repack $_repack_flags"); + } +} + sub set_commit_env { my ($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} = $name; @@ -1105,7 +1886,7 @@ sub blob_to_file { if ($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 $?; @@ -1117,7 +1898,7 @@ 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 $?; @@ -1135,6 +1916,9 @@ 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)))) { @@ -1159,12 +1943,17 @@ 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; + } my $old = eval { my $pid = open my $child, '-|'; 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 $?; @@ -1182,26 +1971,44 @@ 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 } } +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"; @@ -1214,6 +2021,994 @@ 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; + 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 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"; + -d $GIT_SVN_DIR or mkpath([$GIT_SVN_DIR]); + 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") { + 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"; + } + migrate_revdb() if (-d $GIT_SVN_DIR && !-w $REVDB); + print "Done upgrading.\n"; +} + +sub find_rev_before { + my ($r, $id, $eq_ok) = @_; + my $f = "$GIT_DIR/svn/$id/.rev_db"; + return (undef,undef) unless -r $f; + --$r unless $eq_ok; + while ($r > 0) { + if (my $c = revdb_get($f, $r)) { + return ($r, $c); + } + --$r; + } + return (undef, undef); +} + +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; + $SVN_WC = "$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; + } + } + } +} + +sub set_default_vals { + if (defined $_repack) { + $_repack = 1000 if ($_repack <= 0); + $_repack_nr = $_repack; + $_repack_flags ||= '-d'; + } +} + +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 $url = file_to_s("$GIT_DIR/svn/$x/info/url"); + my ($u, $p) = repo_path_split($url); + $l_map->{$u}->{$p} = $x; + }); + return $l_map; +} + +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; + $dest->{a_raw} = $author; + 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}} + } + } +} + +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$SVN_PATH\E/?##); + + my ($hash, $pid, $in, $out); + my $pool = SVN::Pool->new; + defined($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 $!; + $pool->clear; + chomp($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'; + my $link = `git-cat-file blob $hash`; + $link =~ s/^link // or die "svn:special file with contents: <", + $link, "> is not understood\n"; + defined($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"; + } + print $gui $mode,' ',$hash,"\t",$p,"\0" 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/, $c)))[-1]); + return ($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); + } + $pool->clear; +} + +sub revisions_eq { + my ($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 { + my ($paths, $rev, $author, $date, $msg) = @_; + my $svn_path = '/'.$SVN_PATH; + + # look for a parent from another branch: + 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; +} + +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); + $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 ($r0, $parent) = find_rev_before($r1,$i,1); + return $parent if (defined $r0 && $r0 == $r1); + print STDERR "r$r1 of $i not imported\n"; + next; + } + return undef; +} + +sub find_graft_path_parents { + my ($grafts, $tree_paths, $c, $p0, $r0) = @_; + foreach my $x (keys %$tree_paths) { + next unless ($p0 =~ /^\Q$x\E/); + my $i = $tree_paths->{$x}; + my ($r, $parent) = find_rev_before($r0, $i, 1); + if (defined $r && defined $parent && revisions_eq($x,$r,$r0)) { + $grafts->{$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, $cmt_last) = @_; + if ($_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); + my @diff = safe_qx('git-diff-tree', $cmt, $c); + if (@diff) { + print STDERR "Trees differ: $cmt $c\n", + join('',@diff),"\n"; + exit 1; + } + } else { + fetch("$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 || $errno == 160013) { + return; + } + croak "Error from SVN, ($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; +} + +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; +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}); + $self->{pool}->clear; +} + __END__ Data structures: @@ -1247,3 +3042,7 @@ diff-index line ($m hash) 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 a98e9d16..2843258f 100644 --- a/contrib/git-svn/t/lib-git-svn.sh +++ b/contrib/git-svn/t/lib-git-svn.sh @@ -10,8 +10,8 @@ fi . ./test-lib.sh GIT_DIR=$PWD/.git -GIT_SVN_DIR=$GIT_DIR/git-svn -SVN_TREE=$GIT_SVN_DIR/tree +GIT_SVN_DIR=$GIT_DIR/svn/git-svn +SVN_TREE=$GIT_SVN_DIR/svn-tree svnadmin >/dev/null 2>&1 if test $? != 1 diff --git a/contrib/git-svn/t/t0000-contrib-git-svn.sh b/contrib/git-svn/t/t0000-contrib-git-svn.sh index 8b3a0d90..443d5183 100644 --- a/contrib/git-svn/t/t0000-contrib-git-svn.sh +++ b/contrib/git-svn/t/t0000-contrib-git-svn.sh @@ -4,13 +4,17 @@ # test_description='git-svn tests' +GIT_SVN_LC_ALL=$LC_ALL . ./lib-git-svn.sh 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 @@ -30,9 +34,10 @@ test_expect_success \ 'import an SVN revision into git' \ 'git-svn fetch' +test_expect_success "checkout from svn" "svn co $svnrepo $SVN_TREE" name='try a deep --rmdir with a commit' -git checkout -b mybranch remotes/git-svn +git checkout -f -b mybranch remotes/git-svn mv dir/a/b/c/d/e/file dir/file cp dir/file file git update-index --add --remove dir/a/b/c/d/e/file dir/file file @@ -40,6 +45,7 @@ git commit -m "$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 $SVN_TREE/dir/a" @@ -51,14 +57,14 @@ git update-index --remove dir/file git update-index --add dir/file/file git commit -m "$name" -test_expect_code 1 "$name" \ +test_expect_failure "$name" \ 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch' \ || true name='detect node change from directory to file #1' rm -rf dir $GIT_DIR/index -git checkout -b mybranch2 remotes/git-svn +git checkout -f -b mybranch2 remotes/git-svn mv bar/zzz zzz rm -rf bar mv zzz bar @@ -66,14 +72,14 @@ git update-index --remove -- bar/zzz git update-index --add -- bar git commit -m "$name" -test_expect_code 1 "$name" \ +test_expect_failure "$name" \ 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch2' \ || true name='detect node change from file to directory #2' rm -f $GIT_DIR/index -git checkout -b mybranch3 remotes/git-svn +git checkout -f -b mybranch3 remotes/git-svn rm bar/zzz git-update-index --remove bar/zzz mkdir bar/zzz @@ -81,14 +87,14 @@ echo yyy > bar/zzz/yyy git-update-index --add bar/zzz/yyy git commit -m "$name" -test_expect_code 1 "$name" \ +test_expect_failure "$name" \ 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch3' \ || true name='detect node change from directory to file #2' rm -f $GIT_DIR/index -git checkout -b mybranch4 remotes/git-svn +git checkout -f -b mybranch4 remotes/git-svn rm -rf dir git update-index --remove -- dir/file touch dir @@ -96,20 +102,21 @@ echo asdf > dir git update-index --add -- dir git commit -m "$name" -test_expect_code 1 "$name" \ +test_expect_failure "$name" \ 'git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch4' \ || true 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" test_expect_success "$name" \ "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + svn up $SVN_TREE && test ! -x $SVN_TREE/exec.sh" @@ -120,49 +127,64 @@ git commit -m "$name" test_expect_success "$name" \ "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && + svn up $SVN_TREE && test -x $SVN_TREE/exec.sh" -name='executable file becomes a symlink to bar/zzz (file)' -rm exec.sh -ln -s bar/zzz exec.sh -git update-index exec.sh -git commit -m "$name" - -test_expect_success "$name" \ - "git-svn commit --find-copies-harder --rmdir remotes/git-svn..mybranch5 && - 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 && - 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 && - test -f $SVN_TREE/exec-2.sh && - test ! -L $SVN_TREE/exec-2.sh && - diff -u help $SVN_TREE/exec-2.sh" - - +if test -z "$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 $SVN_TREE/exec.sh" + + name='new symlink is added to a file that was also just made executable' + chmod +x bar/zzz + ln -s bar/zzz exec-2.sh + git update-index --add bar/zzz exec-2.sh + git commit -m "$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 $SVN_TREE/exec-2.sh" + + name='modify a symlink to become a file' + git help > help || true + rm exec-2.sh + cp help exec-2.sh + git update-index exec-2.sh + git commit -m "$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 $SVN_TREE/exec-2.sh" +fi + + +if test -n "$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 @@ -173,5 +195,28 @@ 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 $GIT_SVN_LC_ALL | grep -q '\.UTF-8$' +then + echo tree f735671b89a7eb30cab1d8597de35bd4271ab813 > expected +fi +cat >> expected <<\EOF +tree 4b9af72bb861eaed053854ec502cf7df72618f0f +tree 031b8d557afc6fea52894eaebb45bec52f1ba6d1 +tree 0b094cbff17168f24c302e297f55bfac65eb8bd3 +tree d667270a1f7b109f5eb3aaea21ede14b56bfdd6e +tree 56a30b966619b863674f5978696f4a3594f2fca9 +tree d667270a1f7b109f5eb3aaea21ede14b56bfdd6e +tree 8f51f74cf0163afc9ad68a4b1537288c4558b5a4 +EOF +test_expect_success "$name" "diff -u a expected" + test_done diff --git a/contrib/git-svn/t/t0001-contrib-git-svn-props.sh b/contrib/git-svn/t/t0001-contrib-git-svn-props.sh index 23a5a2a2..54e0ed73 100644 --- a/contrib/git-svn/t/t0001-contrib-git-svn-props.sh +++ b/contrib/git-svn/t/t0001-contrib-git-svn-props.sh @@ -52,49 +52,49 @@ EOF cd .. rm -rf import -svn co "$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 ..' + +test_expect_success 'initialize git-svn' "git-svn init $svnrepo" +test_expect_success 'fetch revisions from svn' 'git-svn fetch' -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 .. - -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`"