diff options
Diffstat (limited to 'git-svn.perl')
| -rwxr-xr-x | git-svn.perl | 1869 |
1 files changed, 1633 insertions, 236 deletions
diff --git a/git-svn.perl b/git-svn.perl index d967594ee7..b67fef0bf6 100755 --- a/git-svn.perl +++ b/git-svn.perl @@ -1,11 +1,12 @@ #!/usr/bin/env perl # Copyright (C) 2006, Eric Wong <normalperson@yhbt.net> # License: GPL v2 or later +use 5.008; use warnings; use strict; use vars qw/ $AUTHOR $VERSION $sha1 $sha1_short $_revision $_repository - $_q $_authors %users/; + $_q $_authors $_authors_prog %users/; $AUTHOR = 'Eric Wong <normalperson@yhbt.net>'; $VERSION = '@@GIT_VERSION@@'; @@ -19,18 +20,31 @@ $ENV{GIT_DIR} ||= '.git'; $Git::SVN::default_repo_id = 'svn'; $Git::SVN::default_ref_id = $ENV{GIT_SVN_ID} || 'git-svn'; $Git::SVN::Ra::_log_window_size = 100; +$Git::SVN::_minimize_url = 'unset'; + +if (! exists $ENV{SVN_SSH} && exists $ENV{GIT_SSH}) { + $ENV{SVN_SSH} = $ENV{GIT_SSH}; +} + +if (exists $ENV{SVN_SSH} && $^O eq 'msys') { + $ENV{SVN_SSH} =~ s/\\/\\\\/g; + $ENV{SVN_SSH} =~ s/(.*)/"$1"/; +} $Git::SVN::Log::TZ = $ENV{TZ}; $ENV{TZ} = 'UTC'; $| = 1; # unbuffer STDOUT sub fatal (@) { print STDERR "@_\n"; exit 1 } -require SVN::Core; # use()-ing this causes segfaults for me... *shrug* -require SVN::Ra; -require SVN::Delta; -if ($SVN::Core::VERSION lt '1.1.0') { - fatal "Need SVN::Core 1.1.0 or better (got $SVN::Core::VERSION)"; +sub _req_svn { + require SVN::Core; # use()-ing this causes segfaults for me... *shrug* + require SVN::Ra; + require SVN::Delta; + if ($SVN::Core::VERSION lt '1.1.0') { + fatal "Need SVN::Core 1.1.0 or better (got $SVN::Core::VERSION)"; + } } +my $can_compress = eval { require Compress::Zlib; 1}; push @Git::SVN::Ra::ISA, 'SVN::Ra'; push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor'; push @SVN::Git::Fetcher::ISA, 'SVN::Delta::Editor'; @@ -39,21 +53,27 @@ use Digest::MD5; use IO::File qw//; use File::Basename qw/dirname basename/; use File::Path qw/mkpath/; +use File::Spec; +use File::Find; use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/; use IPC::Open3; use Git; +use Memoize; # core since 5.8.0, Jul 2002 BEGIN { # import functions from Git into our packages, en masse no strict 'refs'; foreach (qw/command command_oneline command_noisy command_output_pipe - command_input_pipe command_close_pipe/) { + command_input_pipe command_close_pipe + command_bidi_pipe command_close_bidi_pipe/) { for my $package ( qw(SVN::Git::Editor SVN::Git::Fetcher Git::SVN::Migration Git::SVN::Log Git::SVN), __PACKAGE__) { *{"${package}::$_"} = \&{"Git::$_"}; } } + Memoize::memoize 'Git::config'; + Memoize::memoize 'Git::config_bool'; } my ($SVN); @@ -61,26 +81,30 @@ my ($SVN); $sha1 = qr/[a-f\d]{40}/; $sha1_short = qr/[a-f\d]{4,40}/; my ($_stdin, $_help, $_edit, - $_message, $_file, + $_message, $_file, $_branch_dest, $_template, $_shared, - $_version, $_fetch_all, $_no_rebase, + $_version, $_fetch_all, $_no_rebase, $_fetch_parent, $_merge, $_strategy, $_dry_run, $_local, $_prefix, $_no_checkout, $_url, $_verbose, - $_git_format, $_commit_url, $_tag); + $_git_format, $_commit_url, $_tag, $_merge_info, $_interactive); $Git::SVN::_follow_parent = 1; +$SVN::Git::Fetcher::_placeholder_filename = ".gitignore"; +$_q ||= 0; my %remote_opts = ( 'username=s' => \$Git::SVN::Prompt::_username, 'config-dir=s' => \$Git::SVN::Ra::config_dir, 'no-auth-cache' => \$Git::SVN::Prompt::_no_auth_cache, - 'ignore-paths=s' => \$SVN::Git::Fetcher::_ignore_regex ); + 'ignore-paths=s' => \$SVN::Git::Fetcher::_ignore_regex, + 'ignore-refs=s' => \$Git::SVN::Ra::_ignore_refs_regex ); my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent, 'authors-file|A=s' => \$_authors, + 'authors-prog=s' => \$_authors_prog, 'repack:i' => \$Git::SVN::_repack, 'noMetadata' => \$Git::SVN::_no_metadata, 'useSvmProps' => \$Git::SVN::_use_svm_props, 'useSvnsyncProps' => \$Git::SVN::_use_svnsync_props, 'log-window-size=i' => \$Git::SVN::Ra::_log_window_size, 'no-checkout' => \$_no_checkout, - 'quiet|q' => \$_q, + 'quiet|q+' => \$_q, 'repack-flags|repack-args|repack-opts=s' => \$Git::SVN::_repack_flags, 'use-log-author' => \$Git::SVN::_use_log_author, @@ -88,17 +112,18 @@ my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent, 'localtime' => \$Git::SVN::_localtime, %remote_opts ); -my ($_trunk, $_tags, $_branches, $_stdlayout); +my ($_trunk, @_tags, @_branches, $_stdlayout); my %icv; my %init_opts = ( 'template=s' => \$_template, 'shared:s' => \$_shared, - 'trunk|T=s' => \$_trunk, 'tags|t=s' => \$_tags, - 'branches|b=s' => \$_branches, 'prefix=s' => \$_prefix, + 'trunk|T=s' => \$_trunk, 'tags|t=s@' => \@_tags, + 'branches|b=s@' => \@_branches, 'prefix=s' => \$_prefix, 'stdlayout|s' => \$_stdlayout, - 'minimize-url|m' => \$Git::SVN::_minimize_url, + 'minimize-url|m!' => \$Git::SVN::_minimize_url, 'no-metadata' => sub { $icv{noMetadata} = 1 }, 'use-svm-props' => sub { $icv{useSvmProps} = 1 }, 'use-svnsync-props' => sub { $icv{useSvnsyncProps} = 1 }, 'rewrite-root=s' => sub { $icv{rewriteRoot} = $_[1] }, + 'rewrite-uuid=s' => sub { $icv{rewriteUUID} = $_[1] }, %remote_opts ); my %cmt_opts = ( 'edit|e' => \$_edit, 'rmdir' => \$SVN::Git::Editor::_rmdir, @@ -111,9 +136,14 @@ my %cmd = ( fetch => [ \&cmd_fetch, "Download new revisions from SVN", { 'revision|r=s' => \$_revision, 'fetch-all|all' => \$_fetch_all, + 'parent|p' => \$_fetch_parent, %fc_opts } ], clone => [ \&cmd_clone, "Initialize and fetch revisions", { 'revision|r=s' => \$_revision, + 'preserve-empty-dirs' => + \$SVN::Git::Fetcher::_preserve_empty_dirs, + 'placeholder-filename=s' => + \$SVN::Git::Fetcher::_placeholder_filename, %fc_opts, %init_opts } ], init => [ \&cmd_init, "Initialize a repo for tracking" . " (requires URL argument)", @@ -132,23 +162,34 @@ my %cmd = ( 'commit-url=s' => \$_commit_url, 'revision|r=i' => \$_revision, 'no-rebase' => \$_no_rebase, + 'mergeinfo=s' => \$_merge_info, + 'interactive|i' => \$_interactive, %cmt_opts, %fc_opts } ], branch => [ \&cmd_branch, 'Create a branch in the SVN repository', { 'message|m=s' => \$_message, + 'destination|d=s' => \$_branch_dest, 'dry-run|n' => \$_dry_run, - 'tag|t' => \$_tag } ], + 'tag|t' => \$_tag, + 'username=s' => \$Git::SVN::Prompt::_username, + 'commit-url=s' => \$_commit_url } ], tag => [ sub { $_tag = 1; cmd_branch(@_) }, 'Create a tag in the SVN repository', { 'message|m=s' => \$_message, - 'dry-run|n' => \$_dry_run } ], + 'destination|d=s' => \$_branch_dest, + 'dry-run|n' => \$_dry_run, + 'username=s' => \$Git::SVN::Prompt::_username, + 'commit-url=s' => \$_commit_url } ], 'set-tree' => [ \&cmd_set_tree, "Set an SVN repository to a git tree-ish", - { 'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ], + { 'stdin' => \$_stdin, %cmt_opts, %fc_opts, } ], 'create-ignore' => [ \&cmd_create_ignore, 'Create a .gitignore per svn:ignore', { 'revision|r=i' => \$_revision } ], + 'mkdirs' => [ \&cmd_mkdirs , + "recreate empty directories after a checkout", + { 'revision|r=i' => \$_revision } ], 'propget' => [ \&cmd_propget, 'Print the value of a property on a file or directory', { 'revision|r=i' => \$_revision } ], @@ -206,14 +247,46 @@ my %cmd = ( 'blame' => [ \&Git::SVN::Log::cmd_blame, "Show what revision and author last modified each line of a file", { 'git-format' => \$_git_format } ], + 'reset' => [ \&cmd_reset, + "Undo fetches back to the specified SVN revision", + { 'revision|r=s' => \$_revision, + 'parent|p' => \$_fetch_parent } ], + 'gc' => [ \&cmd_gc, + "Compress unhandled.log files in .git/svn and remove " . + "index files in .git/svn", + {} ], ); +use Term::ReadLine; +package FakeTerm; +sub new { + my ($class, $reason) = @_; + return bless \$reason, shift; +} +sub readline { + my $self = shift; + die "Cannot use readline on FakeTerm: $$self"; +} +package main; + +my $term = eval { + $ENV{"GIT_SVN_NOTTY"} + ? new Term::ReadLine 'git-svn', \*STDIN, \*STDOUT + : new Term::ReadLine 'git-svn'; +}; +if ($@) { + $term = new FakeTerm "$@: going non-interactive"; +} + my $cmd; for (my $i = 0; $i < @ARGV; $i++) { if (defined $cmd{$ARGV[$i]}) { $cmd = $ARGV[$i]; splice @ARGV, $i, 1; last; + } elsif ($ARGV[$i] eq 'help') { + $cmd = $ARGV[$i+1]; + usage(0); } }; @@ -244,11 +317,11 @@ unless ($cmd && $cmd =~ /(?:clone|init|multi-init)$/) { my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd); -read_repo_config(\%opts); +read_git_config(\%opts); if ($cmd && ($cmd eq 'log' || $cmd eq 'blame')) { Getopt::Long::Configure('pass_through'); } -my $rv = GetOptions(%opts, 'help|H|h' => \$_help, 'version|V' => \$_version, +my $rv = GetOptions(%opts, 'h|H' => \$_help, 'version|V' => \$_version, 'minimize-connections' => \$Git::SVN::Migration::_minimize, 'id|i=s' => \$Git::SVN::default_ref_id, 'svn-remote|remote|R=s' => sub { @@ -260,6 +333,9 @@ usage(0) if $_help; version() if $_version; usage(1) unless defined $cmd; load_authors() if $_authors; +if (defined $_authors_prog) { + $_authors_prog = "'" . File::Spec->rel2abs($_authors_prog) . "'"; +} unless ($cmd =~ /^(?:clone|init|multi-init|commit-diff)$/) { Git::SVN::Migration::migration_check(); @@ -307,10 +383,41 @@ information. } sub version { + ::_req_svn(); print "git-svn version $VERSION (svn $SVN::Core::VERSION)\n"; exit 0; } +sub ask { + my ($prompt, %arg) = @_; + my $valid_re = $arg{valid_re}; + my $default = $arg{default}; + my $resp; + my $i = 0; + + if ( !( defined($term->IN) + && defined( fileno($term->IN) ) + && defined( $term->OUT ) + && defined( fileno($term->OUT) ) ) ){ + return defined($default) ? $default : undef; + } + + while ($i++ < 10) { + $resp = $term->readline($prompt); + if (!defined $resp) { # EOF + print "\n"; + return defined $default ? $default : undef; + } + if ($resp eq '' and defined $default) { + return $default; + } + if (!defined $valid_re or $resp =~ /$valid_re/) { + return $resp; + } + } + return undef; +} + sub do_git_init_db { unless (-d $ENV{GIT_DIR}) { my @init_db = ('init'); @@ -333,6 +440,18 @@ sub do_git_init_db { command_noisy('config', "$pfx.$i", $icv{$i}); $set = $i; } + my $ignore_paths_regex = \$SVN::Git::Fetcher::_ignore_regex; + command_noisy('config', "$pfx.ignore-paths", $$ignore_paths_regex) + if defined $$ignore_paths_regex; + my $ignore_refs_regex = \$Git::SVN::Ra::_ignore_refs_regex; + command_noisy('config', "$pfx.ignore-refs", $$ignore_refs_regex) + if defined $$ignore_refs_regex; + + if (defined $SVN::Git::Fetcher::_preserve_empty_dirs) { + my $fname = \$SVN::Git::Fetcher::_placeholder_filename; + command_noisy('config', "$pfx.preserve-empty-dirs", 'true'); + command_noisy('config', "$pfx.placeholder-filename", $$fname); + } } sub init_subdir { @@ -346,30 +465,38 @@ sub init_subdir { sub cmd_clone { my ($url, $path) = @_; if (!defined $path && - (defined $_trunk || defined $_branches || defined $_tags || + (defined $_trunk || @_branches || @_tags || defined $_stdlayout) && $url !~ m#^[a-z\+]+://#) { $path = $url; } $path = basename($url) if !defined $path || !length $path; + my $authors_absolute = $_authors ? File::Spec->rel2abs($_authors) : ""; cmd_init($url, $path); + command_oneline('config', 'svn.authorsfile', $authors_absolute) + if $_authors; Git::SVN::fetch_all($Git::SVN::default_repo_id); } sub cmd_init { if (defined $_stdlayout) { $_trunk = 'trunk' if (!defined $_trunk); - $_tags = 'tags' if (!defined $_tags); - $_branches = 'branches' if (!defined $_branches); + @_tags = 'tags' if (! @_tags); + @_branches = 'branches' if (! @_branches); } - if (defined $_trunk || defined $_branches || defined $_tags) { + if (defined $_trunk || @_branches || @_tags) { return cmd_multi_init(@_); } my $url = shift or die "SVN repository location required ", "as a command-line argument\n"; + $url = canonicalize_url($url); init_subdir(@_); do_git_init_db(); + if ($Git::SVN::_minimize_url eq 'unset') { + $Git::SVN::_minimize_url = 0; + } + Git::SVN->init($url); } @@ -380,12 +507,22 @@ sub cmd_fetch { } my ($remote) = @_; if (@_ > 1) { - die "Usage: $0 fetch [--all] [svn-remote]\n"; + die "Usage: $0 fetch [--all] [--parent] [svn-remote]\n"; } - $remote ||= $Git::SVN::default_repo_id; - if ($_fetch_all) { + $Git::SVN::no_reuse_existing = undef; + if ($_fetch_parent) { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + unless ($gs) { + die "Unable to determine upstream SVN information from ", + "working tree history\n"; + } + # just fetch, don't checkout. + $_no_checkout = 'true'; + $_fetch_all ? $gs->fetch_all : $gs->fetch; + } elsif ($_fetch_all) { cmd_multi_fetch(); } else { + $remote ||= $Git::SVN::default_repo_id; Git::SVN::fetch_all($remote, Git::SVN::read_all_remotes()); } } @@ -426,14 +563,218 @@ sub cmd_set_tree { unlink $gs->{index}; } +sub split_merge_info_range { + my ($range) = @_; + if ($range =~ /(\d+)-(\d+)/) { + return (int($1), int($2)); + } else { + return (int($range), int($range)); + } +} + +sub combine_ranges { + my ($in) = @_; + + my @fnums = (); + my @arr = split(/,/, $in); + for my $element (@arr) { + my ($start, $end) = split_merge_info_range($element); + push @fnums, $start; + } + + my @sorted = @arr [ sort { + $fnums[$a] <=> $fnums[$b] + } 0..$#arr ]; + + my @return = (); + my $last = -1; + my $first = -1; + for my $element (@sorted) { + my ($start, $end) = split_merge_info_range($element); + + if ($last == -1) { + $first = $start; + $last = $end; + next; + } + if ($start <= $last+1) { + if ($end > $last) { + $last = $end; + } + next; + } + if ($first == $last) { + push @return, "$first"; + } else { + push @return, "$first-$last"; + } + $first = $start; + $last = $end; + } + + if ($first != -1) { + if ($first == $last) { + push @return, "$first"; + } else { + push @return, "$first-$last"; + } + } + + return join(',', @return); +} + +sub merge_revs_into_hash { + my ($hash, $minfo) = @_; + my @lines = split(' ', $minfo); + + for my $line (@lines) { + my ($branchpath, $revs) = split(/:/, $line); + + if (exists($hash->{$branchpath})) { + # Merge the two revision sets + my $combined = "$hash->{$branchpath},$revs"; + $hash->{$branchpath} = combine_ranges($combined); + } else { + # Just do range combining for consolidation + $hash->{$branchpath} = combine_ranges($revs); + } + } +} + +sub merge_merge_info { + my ($mergeinfo_one, $mergeinfo_two) = @_; + my %result_hash = (); + + merge_revs_into_hash(\%result_hash, $mergeinfo_one); + merge_revs_into_hash(\%result_hash, $mergeinfo_two); + + my $result = ''; + # Sort below is for consistency's sake + for my $branchname (sort keys(%result_hash)) { + my $revlist = $result_hash{$branchname}; + $result .= "$branchname:$revlist\n" + } + return $result; +} + +sub populate_merge_info { + my ($d, $gs, $uuid, $linear_refs, $rewritten_parent) = @_; + + my %parentshash; + read_commit_parents(\%parentshash, $d); + my @parents = @{$parentshash{$d}}; + if ($#parents > 0) { + # Merge commit + my $all_parents_ok = 1; + my $aggregate_mergeinfo = ''; + my $rooturl = $gs->repos_root; + + if (defined($rewritten_parent)) { + # Replace first parent with newly-rewritten version + shift @parents; + unshift @parents, $rewritten_parent; + } + + foreach my $parent (@parents) { + my ($branchurl, $svnrev, $paruuid) = + cmt_metadata($parent); + + unless (defined($svnrev)) { + # Should have been caught be preflight check + fatal "merge commit $d has ancestor $parent, but that change " + ."does not have git-svn metadata!"; + } + unless ($branchurl =~ /^$rooturl(.*)/) { + fatal "commit $parent git-svn metadata changed mid-run!"; + } + my $branchpath = $1; + + my $ra = Git::SVN::Ra->new($branchurl); + my (undef, undef, $props) = + $ra->get_dir(canonicalize_path("."), $svnrev); + my $par_mergeinfo = $props->{'svn:mergeinfo'}; + unless (defined $par_mergeinfo) { + $par_mergeinfo = ''; + } + # Merge previous mergeinfo values + $aggregate_mergeinfo = + merge_merge_info($aggregate_mergeinfo, + $par_mergeinfo, 0); + + next if $parent eq $parents[0]; # Skip first parent + # Add new changes being placed in tree by merge + my @cmd = (qw/rev-list --reverse/, + $parent, qw/--not/); + foreach my $par (@parents) { + unless ($par eq $parent) { + push @cmd, $par; + } + } + my @revsin = (); + my ($revlist, $ctx) = command_output_pipe(@cmd); + while (<$revlist>) { + my $irev = $_; + chomp $irev; + my (undef, $csvnrev, undef) = + cmt_metadata($irev); + unless (defined $csvnrev) { + # A child is missing SVN annotations... + # this might be OK, or might not be. + warn "W:child $irev is merged into revision " + ."$d but does not have git-svn metadata. " + ."This means git-svn cannot determine the " + ."svn revision numbers to place into the " + ."svn:mergeinfo property. You must ensure " + ."a branch is entirely committed to " + ."SVN before merging it in order for " + ."svn:mergeinfo population to function " + ."properly"; + } + push @revsin, $csvnrev; + } + command_close_pipe($revlist, $ctx); + + last unless $all_parents_ok; + + # We now have a list of all SVN revnos which are + # merged by this particular parent. Integrate them. + next if $#revsin == -1; + my $newmergeinfo = "$branchpath:" . join(',', @revsin); + $aggregate_mergeinfo = + merge_merge_info($aggregate_mergeinfo, + $newmergeinfo, 1); + } + if ($all_parents_ok and $aggregate_mergeinfo) { + return $aggregate_mergeinfo; + } + } + + return undef; +} + sub cmd_dcommit { my $head = shift; + command_noisy(qw/update-index --refresh/); git_cmd_try { command_oneline(qw/diff-index --quiet HEAD/) } 'Cannot dcommit with a dirty index. Commit your changes first, ' . "or stash them with `git stash'.\n"; $head ||= 'HEAD'; + + my $old_head; + if ($head ne 'HEAD') { + $old_head = eval { + command_oneline([qw/symbolic-ref -q HEAD/]) + }; + if ($old_head) { + $old_head =~ s{^refs/heads/}{}; + } else { + $old_head = eval { command_oneline(qw/rev-parse HEAD/) }; + } + command(['checkout', $head], STDERR => 0); + } + my @refs; - my ($url, $rev, $uuid, $gs) = working_head_info($head, \@refs); + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD', \@refs); unless ($gs) { die "Unable to determine upstream SVN information from ", "$head history.\nPerhaps the repository is empty."; @@ -445,7 +786,7 @@ sub cmd_dcommit { $url = eval { command_oneline('config', '--get', "svn-remote.$gs->{repo_id}.commiturl") }; if (!$url) { - $url = $gs->full_url + $url = $gs->full_pushurl } } @@ -460,8 +801,88 @@ sub cmd_dcommit { "If these changes depend on each other, re-running ", "without --no-rebase may be required." } + + if (defined $_interactive){ + my $ask_default = "y"; + foreach my $d (@$linear_refs){ + my ($fh, $ctx) = command_output_pipe(qw(show --summary), "$d"); + while (<$fh>){ + print $_; + } + command_close_pipe($fh, $ctx); + $_ = ask("Commit this patch to SVN? ([y]es (default)|[n]o|[q]uit|[a]ll): ", + valid_re => qr/^(?:yes|y|no|n|quit|q|all|a)/i, + default => $ask_default); + die "Commit this patch reply required" unless defined $_; + if (/^[nq]/i) { + exit(0); + } elsif (/^a/i) { + last; + } + } + } + my $expect_url = $url; + + my $push_merge_info = eval { + command_oneline(qw/config --get svn.pushmergeinfo/) + }; + if (not defined($push_merge_info) + or $push_merge_info eq "false" + or $push_merge_info eq "no" + or $push_merge_info eq "never") { + $push_merge_info = 0; + } + + unless (defined($_merge_info) || ! $push_merge_info) { + # Preflight check of changes to ensure no issues with mergeinfo + # This includes check for uncommitted-to-SVN parents + # (other than the first parent, which we will handle), + # information from different SVN repos, and paths + # which are not underneath this repository root. + my $rooturl = $gs->repos_root; + foreach my $d (@$linear_refs) { + my %parentshash; + read_commit_parents(\%parentshash, $d); + my @realparents = @{$parentshash{$d}}; + if ($#realparents > 0) { + # Merge commit + shift @realparents; # Remove/ignore first parent + foreach my $parent (@realparents) { + my ($branchurl, $svnrev, $paruuid) = cmt_metadata($parent); + unless (defined $paruuid) { + # A parent is missing SVN annotations... + # abort the whole operation. + fatal "$parent is merged into revision $d, " + ."but does not have git-svn metadata. " + ."Either dcommit the branch or use a " + ."local cherry-pick, FF merge, or rebase " + ."instead of an explicit merge commit."; + } + + unless ($paruuid eq $uuid) { + # Parent has SVN metadata from different repository + fatal "merge parent $parent for change $d has " + ."git-svn uuid $paruuid, while current change " + ."has uuid $uuid!"; + } + + unless ($branchurl =~ /^$rooturl(.*)/) { + # This branch is very strange indeed. + fatal "merge parent $parent for $d is on branch " + ."$branchurl, which is not under the " + ."git-svn root $rooturl!"; + } + } + } + } + } + + my $rewritten_parent; Git::SVN::remove_username($expect_url); + if (defined($_merge_info)) { + $_merge_info =~ tr{ }{\n}; + } while (1) { my $d = shift @$linear_refs or last; unless (defined $last_rev) { @@ -475,6 +896,14 @@ sub cmd_dcommit { print "diff-tree $d~1 $d\n"; } else { my $cmt_rev; + + unless (defined($_merge_info) || ! $push_merge_info) { + $_merge_info = populate_merge_info($d, $gs, + $uuid, + $linear_refs, + $rewritten_parent); + } + my %ed_opts = ( r => $last_rev, log => get_commit_entry($d)->{log}, ra => Git::SVN::Ra->new($url), @@ -487,6 +916,7 @@ sub cmd_dcommit { print "Committed r$_[0]\n"; $cmt_rev = $_[0]; }, + mergeinfo => $_merge_info, svn_path => ''); if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) { print "No changes\n$d~1 == $d\n"; @@ -516,10 +946,13 @@ sub cmd_dcommit { @finish = qw/reset --mixed/; } command_noisy(@finish, $gs->refname); + + $rewritten_parent = command_oneline(qw/rev-parse HEAD/); + if (@diff) { @refs = (); my ($url_, $rev_, $uuid_, $gs_) = - working_head_info($head, \@refs); + working_head_info('HEAD', \@refs); my ($linear_refs_, $parents_) = linearize_history($gs_, \@refs); if (scalar(@$linear_refs) != @@ -537,8 +970,15 @@ sub cmd_dcommit { "\nBefore dcommitting"; } if ($url_ ne $expect_url) { - fatal "URL mismatch after rebase: ", - "$url_ != $expect_url"; + if ($url_ eq $gs->metadata_url) { + print + "Accepting rewritten URL:", + " $url_\n"; + } else { + fatal + "URL mismatch after rebase:", + " $url_ != $expect_url"; + } } if ($uuid_ ne $uuid) { fatal "uuid mismatch after rebase: ", @@ -557,6 +997,22 @@ sub cmd_dcommit { } } } + + if ($old_head) { + my $new_head = command_oneline(qw/rev-parse HEAD/); + my $new_is_symbolic = eval { + command_oneline(qw/symbolic-ref -q HEAD/); + }; + if ($new_is_symbolic) { + print "dcommitted the branch ", $head, "\n"; + } else { + print "dcommitted on a detached HEAD because you gave ", + "a revision argument.\n", + "The rewritten commit is: ", $new_head, "\n"; + } + command(['checkout', $old_head], STDERR => 0); + } + unlink $gs->{index}; } @@ -568,12 +1024,68 @@ sub cmd_branch { } $head ||= 'HEAD'; - my ($src, $rev, undef, $gs) = working_head_info($head); + my (undef, $rev, undef, $gs) = working_head_info($head); + my $src = $gs->full_pushurl; my $remote = Git::SVN::read_all_remotes()->{$gs->{repo_id}}; - my $glob = $remote->{ $_tag ? 'tags' : 'branches' }; + my $allglobs = $remote->{ $_tag ? 'tags' : 'branches' }; + my $glob; + if ($#{$allglobs} == 0) { + $glob = $allglobs->[0]; + } else { + unless(defined $_branch_dest) { + die "Multiple ", + $_tag ? "tag" : "branch", + " paths defined for Subversion repository.\n", + "You must specify where you want to create the ", + $_tag ? "tag" : "branch", + " with the --destination argument.\n"; + } + foreach my $g (@{$allglobs}) { + # SVN::Git::Editor could probably be moved to Git.pm.. + my $re = SVN::Git::Editor::glob2pat($g->{path}->{left}); + if ($_branch_dest =~ /$re/) { + $glob = $g; + last; + } + } + unless (defined $glob) { + my $dest_re = qr/\b\Q$_branch_dest\E\b/; + foreach my $g (@{$allglobs}) { + $g->{path}->{left} =~ /$dest_re/ or next; + if (defined $glob) { + die "Ambiguous destination: ", + $_branch_dest, "\nmatches both '", + $glob->{path}->{left}, "' and '", + $g->{path}->{left}, "'\n"; + } + $glob = $g; + } + unless (defined $glob) { + die "Unknown ", + $_tag ? "tag" : "branch", + " destination $_branch_dest\n"; + } + } + } my ($lft, $rgt) = @{ $glob->{path} }{qw/left right/}; - my $dst = join '/', $remote->{url}, $lft, $branch_name, ($rgt || ()); + my $url; + if (defined $_commit_url) { + $url = $_commit_url; + } else { + $url = eval { command_oneline('config', '--get', + "svn-remote.$gs->{repo_id}.commiturl") }; + if (!$url) { + $url = $remote->{pushurl} || $remote->{url}; + } + } + my $dst = join '/', $url, $lft, $branch_name, ($rgt || ()); + + if ($dst =~ /^https:/ && $src =~ /^http:/) { + $src=~s/^http:/https:/; + } + + ::_req_svn(); my $ctx = SVN::Client->new( auth => Git::SVN::Ra::_auth_providers(), @@ -618,6 +1130,15 @@ sub cmd_find_rev { print "$result\n" if $result; } +sub auto_create_empty_directories { + my ($gs) = @_; + my $var = eval { command_oneline('config', '--get', '--bool', + "svn-remote.$gs->{repo_id}.automkdirs") }; + # By default, create empty directories by consulting the unhandled log, + # but allow setting it to 'false' to skip it. + return !($var && $var eq 'false'); +} + sub cmd_rebase { command_noisy(qw/update-index --refresh/); my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); @@ -641,6 +1162,9 @@ sub cmd_rebase { $_fetch_all ? $gs->fetch_all : $gs->fetch; } command_noisy(rebase_cmd(), $gs->refname); + if (auto_create_empty_directories($gs)) { + $gs->mkemptydirs; + } } sub cmd_show_ignore { @@ -652,6 +1176,7 @@ sub cmd_show_ignore { print STDOUT "\n# $path\n"; my $s = $props->{'svn:ignore'} or return; $s =~ s/[\r\n]+/\n/g; + $s =~ s/^\n+//; chomp $s; $s =~ s#^#$path#gm; print STDOUT "$s\n"; @@ -689,6 +1214,7 @@ sub cmd_create_ignore { open(GITIGNORE, '>', $ignore) or fatal("Failed to open `$ignore' for writing: $!"); $s =~ s/[\r\n]+/\n/g; + $s =~ s/^\n+//; chomp $s; # Prefix all patterns so that the ignore doesn't apply # to sub-directories. @@ -700,6 +1226,12 @@ sub cmd_create_ignore { }); } +sub cmd_mkdirs { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + $gs ||= Git::SVN->new; + $gs->mkemptydirs($_revision); +} + sub canonicalize_path { my ($path) = @_; my $dot_slash_added = 0; @@ -719,6 +1251,12 @@ sub canonicalize_path { return $path; } +sub canonicalize_url { + my ($url) = @_; + $url =~ s#^([^:]+://[^/]*/)(.*)$#$1 . canonicalize_path($2)#e; + return $url; +} + # get_svnprops(PATH) # ------------------ # Helper for cmd_propget and cmd_proplist below. @@ -778,22 +1316,19 @@ sub cmd_proplist { sub cmd_multi_init { my $url = shift; - unless (defined $_trunk || defined $_branches || defined $_tags) { + unless (defined $_trunk || @_branches || @_tags) { usage(1); } - # there are currently some bugs that prevent multi-init/multi-fetch - # setups from working well without this. - $Git::SVN::_minimize_url = 1; - $_prefix = '' unless defined $_prefix; if (defined $url) { - $url =~ s#/+$##; + $url = canonicalize_url($url); init_subdir(@_); } do_git_init_db(); if (defined $_trunk) { - my $trunk_ref = $_prefix . 'trunk'; + $_trunk =~ s#^/+##; + my $trunk_ref = 'refs/remotes/' . $_prefix . 'trunk'; # try both old-style and new-style lookups: my $gs_trunk = eval { Git::SVN->new($trunk_ref) }; unless ($gs_trunk) { @@ -803,13 +1338,18 @@ sub cmd_multi_init { undef, $trunk_ref); } } - return unless defined $_branches || defined $_tags; + return unless @_branches || @_tags; my $ra = $url ? Git::SVN::Ra->new($url) : undef; - complete_url_ls_init($ra, $_branches, '--branches/-b', $_prefix); - complete_url_ls_init($ra, $_tags, '--tags/-t', $_prefix . 'tags/'); + foreach my $path (@_branches) { + complete_url_ls_init($ra, $path, '--branches/-b', $_prefix); + } + foreach my $path (@_tags) { + complete_url_ls_init($ra, $path, '--tags/-t', $_prefix.'tags/'); + } } sub cmd_multi_fetch { + $Git::SVN::no_reuse_existing = undef; my $remotes = Git::SVN::read_all_remotes(); foreach my $repo_id (sort keys %$remotes) { if ($remotes->{$repo_id}->{url}) { @@ -927,6 +1467,7 @@ sub cmd_info { if ($@) { $result .= "Repository Root: (offline)\n"; } + ::_req_svn(); $result .= "Repository UUID: $uuid\n" unless $diff_status eq "A" && ($SVN::Core::VERSION le '1.5.4' || $file_type ne "dir"); $result .= "Revision: " . ($diff_status eq "A" ? 0 : $rev) . "\n"; @@ -999,6 +1540,29 @@ sub cmd_info { print $result, "\n"; } +sub cmd_reset { + my $target = shift || $_revision or die "SVN revision required\n"; + $target = $1 if $target =~ /^r(\d+)$/; + $target =~ /^\d+$/ or die "Numeric SVN revision expected\n"; + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + unless ($gs) { + die "Unable to determine upstream SVN information from ". + "history\n"; + } + my ($r, $c) = $gs->find_rev_before($target, not $_fetch_parent); + die "Cannot find SVN revision $target\n" unless defined($c); + $gs->rev_map_set($r, $c, 'reset', $uuid); + print "r$r = $c ($gs->{ref_id})\n"; +} + +sub cmd_gc { + if (!$can_compress) { + warn "Compress::Zlib could not be found; unhandled.log " . + "files will not be compressed.\n"; + } + find({ wanted => \&gc_directory, no_chdir => 1}, "$ENV{GIT_DIR}/svn"); +} + ########################### utility functions ######################### sub rebase_cmd { @@ -1014,6 +1578,17 @@ sub post_fetch_checkout { my $gs = $Git::SVN::_head or return; return if verify_ref('refs/heads/master^0'); + # look for "trunk" ref if it exists + my $remote = Git::SVN::read_all_remotes()->{$gs->{repo_id}}; + my $fetch = $remote->{fetch}; + if ($fetch) { + foreach my $p (keys %$fetch) { + basename($fetch->{$p}) eq 'trunk' or next; + $gs = Git::SVN->new($fetch->{$p}, $gs->{repo_id}, $p); + last; + } + } + my $valid_head = verify_ref('HEAD^0'); command_noisy(qw(update-ref refs/heads/master), $gs->refname); return if ($valid_head || !verify_ref('HEAD^0')); @@ -1027,6 +1602,9 @@ sub post_fetch_checkout { command_noisy(qw/read-tree -m -u -v HEAD HEAD/); print STDERR "Checked out HEAD:\n ", $gs->full_url, " r", $gs->last_rev, "\n"; + if (auto_create_empty_directories($gs)) { + $gs->mkemptydirs($gs->last_rev); + } } sub complete_svn_url { @@ -1068,7 +1646,8 @@ sub complete_url_ls_init { "wanted to set to: $gs->{url}\n"; } command_oneline('config', $k, $gs->{url}) unless $orig_url; - my $remote_path = "$ra->{svn_path}/$repo_path"; + my $remote_path = "$gs->{path}/$repo_path"; + $remote_path =~ s{%([0-9A-F]{2})}{chr hex($1)}ieg; $remote_path =~ s#/+#/#g; $remote_path =~ s#^/##g; $remote_path .= "/*" if $remote_path !~ /\*/; @@ -1077,6 +1656,7 @@ sub complete_url_ls_init { die "--prefix='$pfx' must have a trailing slash '/'\n"; } command_noisy('config', + '--add', "svn-remote.$gs->{repo_id}.$n", "$remote_path:refs/remotes/$pfx*" . ('/*' x (($remote_path =~ tr/*/*/) - 1)) ); @@ -1150,22 +1730,32 @@ sub get_commit_entry { close $log_fh or croak $!; if ($_edit || ($type eq 'tree')) { - my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi'; - # TODO: strip out spaces, comments, like git-commit.sh - system($editor, $commit_editmsg); + chomp(my $editor = command_oneline(qw(var GIT_EDITOR))); + system('sh', '-c', $editor.' "$@"', $editor, $commit_editmsg); } rename $commit_editmsg, $commit_msg or croak $!; { + require Encode; # SVN requires messages to be UTF-8 when entering the repo local $/; open $log_fh, '<', $commit_msg or croak $!; binmode $log_fh; chomp($log_entry{log} = <$log_fh>); - if (my $enc = Git::config('i18n.commitencoding')) { - require Encode; - Encode::from_to($log_entry{log}, $enc, 'UTF-8'); + my $enc = Git::config('i18n.commitencoding') || 'UTF-8'; + my $msg = $log_entry{log}; + + eval { $msg = Encode::decode($enc, $msg, 1) }; + if ($@) { + die "Could not decode as $enc:\n", $msg, + "\nPerhaps you need to set i18n.commitencoding\n"; } + + eval { $msg = Encode::encode('UTF-8', $msg, 1) }; + die "Could not encode as UTF-8:\n$msg\n" if $@; + + $log_entry{log} = $msg; + close $log_fh or croak $!; } unlink $commit_msg; @@ -1208,8 +1798,7 @@ sub load_authors { } # convert GetOpt::Long specs for use by git-config -sub read_repo_config { - return unless -d $ENV{GIT_DIR}; +sub read_git_config { my $opts = shift; my @config_only; foreach my $o (keys %$opts) { @@ -1239,11 +1828,11 @@ sub read_repo_config { sub extract_metadata { my $id = shift or return (undef, undef, undef); my ($url, $rev, $uuid) = ($id =~ /^\s*git-svn-id:\s+(.*)\@(\d+) - \s([a-f\d\-]+)$/x); + \s([a-f\d\-]+)$/ix); if (!defined $rev || !$uuid || !$url) { # some of the original repositories I made had # identifiers like this: - ($rev, $uuid) = ($id =~/^\s*git-svn-id:\s(\d+)\@([a-f\d\-]+)/); + ($rev, $uuid) = ($id =~/^\s*git-svn-id:\s(\d+)\@([a-f\d\-]+)/i); } return ($url, $rev, $uuid); } @@ -1253,9 +1842,44 @@ sub cmt_metadata { command(qw/cat-file commit/, shift)))[-1]); } +sub cmt_sha2rev_batch { + my %s2r; + my ($pid, $in, $out, $ctx) = command_bidi_pipe(qw/cat-file --batch/); + my $list = shift; + + foreach my $sha (@{$list}) { + my $first = 1; + my $size = 0; + print $out $sha, "\n"; + + while (my $line = <$in>) { + if ($first && $line =~ /^[[:xdigit:]]{40}\smissing$/) { + last; + } elsif ($first && + $line =~ /^[[:xdigit:]]{40}\scommit\s(\d+)$/) { + $first = 0; + $size = $1; + next; + } elsif ($line =~ /^(git-svn-id: )/) { + my (undef, $rev, undef) = + extract_metadata($line); + $s2r{$sha} = $rev; + } + + $size -= length($line); + last if ($size == 0); + } + } + + command_close_bidi_pipe($pid, $in, $out, $ctx); + + return \%s2r; +} + sub working_head_info { my ($head, $refs) = @_; - my @args = ('log', '--no-color', '--first-parent', '--pretty=medium'); + my @args = qw/log --no-color --no-decorate --first-parent + --pretty=medium/; my ($fh, $ctx) = command_output_pipe(@args, $head); my $hash; my %max; @@ -1373,6 +1997,25 @@ sub md5sum { return $md5->hexdigest(); } +sub gc_directory { + if ($can_compress && -f $_ && basename($_) eq "unhandled.log") { + my $out_filename = $_ . ".gz"; + open my $in_fh, "<", $_ or die "Unable to open $_: $!\n"; + binmode $in_fh; + my $gz = Compress::Zlib::gzopen($out_filename, "ab") or + die "Unable to open $out_filename: $!\n"; + + my $res; + while ($res = sysread($in_fh, my $str, 1024)) { + $gz->gzwrite($str) or + die "Unable to write: ".$gz->gzerror()."!\n"; + } + unlink $_ or die "unlink $File::Find::name: $!\n"; + } elsif (-f $_ && basename($_) eq "index") { + unlink $_ or die "unlink $_: $!\n"; + } +} + package Git::SVN; use strict; use warnings; @@ -1386,6 +2029,8 @@ use Carp qw/croak/; use File::Path qw/mkpath/; use File::Copy qw/copy/; use IPC::Open3; +use Memoize; # core since 5.8.0, Jul 2002 +use Memoize::Storable; my ($_gc_nr, $_gc_period); @@ -1436,23 +2081,23 @@ sub resolve_local_globs { return unless defined $glob_spec; my $ref = $glob_spec->{ref}; my $path = $glob_spec->{path}; - foreach (command(qw#for-each-ref --format=%(refname) refs/remotes#)) { - next unless m#^refs/remotes/$ref->{regex}$#; + foreach (command(qw#for-each-ref --format=%(refname) refs/#)) { + next unless m#^$ref->{regex}$#; my $p = $1; my $pathname = desanitize_refname($path->full_path($p)); my $refname = desanitize_refname($ref->full_path($p)); if (my $existing = $fetch->{$pathname}) { if ($existing ne $refname) { die "Refspec conflict:\n", - "existing: refs/remotes/$existing\n", - " globbed: refs/remotes/$refname\n"; + "existing: $existing\n", + " globbed: $refname\n"; } - my $u = (::cmt_metadata("refs/remotes/$refname"))[0]; + my $u = (::cmt_metadata("$refname"))[0]; $u =~ s!^\Q$url\E(/|$)!! or die - "refs/remotes/$refname: '$url' not found in '$u'\n"; + "$refname: '$url' not found in '$u'\n"; if ($pathname ne $u) { warn "W: Refspec glob conflict ", - "(ref: refs/remotes/$refname):\n", + "(ref: $refname):\n", "expected path: $pathname\n", " real path: $u\n", "Continuing ahead with $u\n"; @@ -1493,12 +2138,18 @@ sub fetch_all { my $ra = Git::SVN::Ra->new($url); my $uuid = $ra->get_uuid; my $head = $ra->get_latest_revnum; + + # ignore errors, $head revision may not even exist anymore + eval { $ra->get_log("", $head, 0, 1, 0, 1, sub { $head = $_[1] }) }; + warn "W: $@\n" if $@; + my $base = defined $fetch ? $head : 0; # read the max revs for wildcard expansion (branches/*, tags/*) foreach my $t (qw/branches tags/) { defined $remote->{$t} or next; - push @globs, $remote->{$t}; + push @globs, @{$remote->{$t}}; + my $max_rev = eval { tmp_config(qw/--int --get/, "svn-remote.$repo_id.${t}-maxRev") }; if (defined $max_rev && ($max_rev < $base)) { @@ -1528,32 +2179,41 @@ sub read_all_remotes { my $use_svm_props = eval { command_oneline(qw/config --bool svn.useSvmProps/) }; $use_svm_props = $use_svm_props eq 'true' if $use_svm_props; + my $svn_refspec = qr{\s*(.*?)\s*:\s*(.+?)\s*}; foreach (grep { s/^svn-remote\.// } command(qw/config -l/)) { - if (m!^(.+)\.fetch=\s*(.*)\s*:\s*(.+)\s*$!) { - my ($remote, $local_ref, $_remote_ref) = ($1, $2, $3); - die("svn-remote.$remote: remote ref '$_remote_ref' " - . "must start with 'refs/remotes/'\n") - unless $_remote_ref =~ m{^refs/remotes/(.+)}; - my $remote_ref = $1; - $local_ref =~ s{^/}{}; + if (m!^(.+)\.fetch=$svn_refspec$!) { + my ($remote, $local_ref, $remote_ref) = ($1, $2, $3); + die("svn-remote.$remote: remote ref '$remote_ref' " + . "must start with 'refs/'\n") + unless $remote_ref =~ m{^refs/}; + $local_ref = uri_decode($local_ref); $r->{$remote}->{fetch}->{$local_ref} = $remote_ref; $r->{$remote}->{svm} = {} if $use_svm_props; } elsif (m!^(.+)\.usesvmprops=\s*(.*)\s*$!) { $r->{$1}->{svm} = {}; } elsif (m!^(.+)\.url=\s*(.*)\s*$!) { $r->{$1}->{url} = $2; - } elsif (m!^(.+)\.(branches|tags)= - (.*):refs/remotes/(.+)\s*$/!x) { - my ($p, $g) = ($3, $4); - my $rs = $r->{$1}->{$2} = { - t => $2, - remote => $1, - path => Git::SVN::GlobSpec->new($p), - ref => Git::SVN::GlobSpec->new($g) }; + } elsif (m!^(.+)\.pushurl=\s*(.*)\s*$!) { + $r->{$1}->{pushurl} = $2; + } elsif (m!^(.+)\.ignore-refs=\s*(.*)\s*$!) { + $r->{$1}->{ignore_refs_regex} = $2; + } elsif (m!^(.+)\.(branches|tags)=$svn_refspec$!) { + my ($remote, $t, $local_ref, $remote_ref) = + ($1, $2, $3, $4); + die("svn-remote.$remote: remote ref '$remote_ref' ($t) " + . "must start with 'refs/'\n") + unless $remote_ref =~ m{^refs/}; + $local_ref = uri_decode($local_ref); + my $rs = { + t => $t, + remote => $remote, + path => Git::SVN::GlobSpec->new($local_ref, 1), + ref => Git::SVN::GlobSpec->new($remote_ref, 0) }; if (length($rs->{ref}->{right}) != 0) { die "The '*' glob character must be the last ", - "character of '$g'\n"; + "character of '$remote_ref'\n"; } + push @{ $r->{$remote}->{$t} }, $rs; } } @@ -1573,6 +2233,16 @@ sub read_all_remotes { } } keys %$r; + foreach my $remote (keys %$r) { + foreach ( grep { defined $_ } + map { $r->{$remote}->{$_} } qw(branches tags) ) { + foreach my $rs ( @$_ ) { + $rs->{ignore_refs_regex} = + $r->{$remote}->{ignore_refs_regex}; + } + } + } + $r; } @@ -1661,14 +2331,15 @@ sub init_remote_config { } } my ($xrepo_id, $xpath) = find_ref($self->refname); - if (defined $xpath) { + if (!$no_write && defined $xpath) { die "svn-remote.$xrepo_id.fetch already set to track ", - "$xpath:refs/remotes/", $self->refname, "\n"; + "$xpath:", $self->refname, "\n"; } unless ($no_write) { command_noisy('config', "svn-remote.$self->{repo_id}.url", $url); $self->{path} =~ s{^/}{}; + $self->{path} =~ s{%([0-9A-F]{2})}{chr hex($1)}ieg; command_noisy('config', '--add', "svn-remote.$self->{repo_id}.fetch", "$self->{path}:".$self->refname); @@ -1693,9 +2364,10 @@ sub find_by_url { # repos_root and, path are optional next if defined $repos_root && $repos_root ne $u; my $fetch = $remotes->{$repo_id}->{fetch} || {}; - foreach (qw/branches tags/) { - resolve_local_globs($u, $fetch, - $remotes->{$repo_id}->{$_}); + foreach my $t (qw/branches tags/) { + foreach my $globspec (@{$remotes->{$repo_id}->{$t}}) { + resolve_local_globs($u, $fetch, $globspec); + } } my $p = $path; my $rwr = rewrite_root({repo_id => $repo_id}); @@ -1737,7 +2409,7 @@ sub find_ref { my ($ref_id) = @_; foreach (command(qw/config -l/)) { next unless m!^svn-remote\.(.+)\.fetch= - \s*(.*)\s*:\s*refs/remotes/(.+)\s*$!x; + \s*(.*?)\s*:\s*(.+?)\s*$!x; my ($repo_id, $path, $ref) = ($1, $2, $3); if ($ref eq $ref_id) { $path = '' if ($path =~ m#^\./?#); @@ -1754,27 +2426,32 @@ sub new { if (!defined $repo_id) { die "Could not find a \"svn-remote.*.fetch\" key ", "in the repository configuration matching: ", - "refs/remotes/$ref_id\n"; + "$ref_id\n"; } } my $self = _new($class, $repo_id, $ref_id, $path); if (!defined $self->{path} || !length $self->{path}) { my $fetch = command_oneline('config', '--get', "svn-remote.$repo_id.fetch", - ":refs/remotes/$ref_id\$") or + ":$ref_id\$") or die "Failed to read \"svn-remote.$repo_id.fetch\" ", - "\":refs/remotes/$ref_id\$\" in config\n"; + "\":$ref_id\$\" in config\n"; ($self->{path}, undef) = split(/\s*:\s*/, $fetch); } + $self->{path} =~ s{/+}{/}g; + $self->{path} =~ s{\A/}{}; + $self->{path} =~ s{/\z}{}; $self->{url} = command_oneline('config', '--get', "svn-remote.$repo_id.url") or die "Failed to read \"svn-remote.$repo_id.url\" in config\n"; + $self->{pushurl} = eval { command_oneline('config', '--get', + "svn-remote.$repo_id.pushurl") }; $self->rebuild; $self; } sub refname { - my ($refname) = "refs/remotes/$_[0]->{ref_id}" ; + my ($refname) = $_[0]->{ref_id} ; # It cannot end with a slash /, we'll throw up on this because # SVN can't have directories with a slash in their name, either: @@ -1799,6 +2476,14 @@ sub refname { # .. becomes %2E%2E $refname =~ s{\.\.}{%2E%2E}g; + # trailing dots and .lock are not allowed + # .$ becomes %2E and .lock becomes %2Elock + $refname =~ s{\.(?=$|lock$)}{%2E}; + + # the sequence @{ is used to access the reflog + # @{ becomes %40{ + $refname =~ s{\@\{}{%40\{}g; + return $refname; } @@ -1853,7 +2538,7 @@ sub _set_svm_vars { chomp($src, $uuid); - $uuid =~ m{^[0-9a-f\-]{30,}$} + $uuid =~ m{^[0-9a-f\-]{30,}$}i or die "doesn't look right - svm:uuid is '$uuid'\n"; # the '!' is used to mark the repos_root!/relative/path @@ -1928,6 +2613,10 @@ sub svnsync { die "Can't have both 'useSvnsyncProps' and 'rewriteRoot' ", "options set!\n"; } + if ($self->rewrite_uuid) { + die "Can't have both 'useSvnsyncProps' and 'rewriteUUID' ", + "options set!\n"; + } my $svnsync; # see if we have it in our config, first: @@ -1939,7 +2628,7 @@ sub svnsync { die "doesn't look right - svn:sync-from-url is '$url'\n"; my $uuid = tmp_config('--get', "$section.svnsync-uuid"); - ($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}) or + ($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}i) or die "doesn't look right - svn:sync-from-uuid is '$uuid'\n"; $svnsync = { url => $url, uuid => $uuid } @@ -1957,7 +2646,7 @@ sub svnsync { die "doesn't look right - svn:sync-from-url is '$url'\n"; my $uuid = $rp->{'svn:sync-from-uuid'} or die $err . "uuid\n"; - ($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}) or + ($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}i) or die "doesn't look right - svn:sync-from-uuid is '$uuid'\n"; my $section = "svn-remote.$self->{repo_id}"; @@ -1973,7 +2662,7 @@ sub ra_uuid { unless ($self->{ra_uuid}) { my $key = "svn-remote.$self->{repo_id}.uuid"; my $uuid = eval { tmp_config('--get', $key) }; - if (!$@ && $uuid && $uuid =~ /^([a-f\d\-]{30,})$/) { + if (!$@ && $uuid && $uuid =~ /^([a-f\d\-]{30,})$/i) { $self->{ra_uuid} = $uuid; } else { die "ra_uuid called without URL\n" unless $self->{url}; @@ -2016,16 +2705,6 @@ sub ra { $ra; } -sub rel_path { - my ($self) = @_; - my $repos_root = $self->ra->{repos_root}; - return $self->{path} if ($self->{url} eq $repos_root); - my $url = $self->{url} . - (length $self->{path} ? "/$self->{path}" : $self->{path}); - $url =~ s!^\Q$repos_root\E(?:/+|$)!!g; - $url; -} - # prop_walk(PATH, REV, SUB) # ------------------------- # Recursively traverse PATH at revision REV and invoke SUB for each @@ -2201,12 +2880,6 @@ sub get_commit_parents { next if $seen{$p}; $seen{$p} = 1; push @ret, $p; - # MAXPARENT is defined to 16 in commit-tree.c: - last if @ret >= 16; - } - if (@tmp) { - die "r$log_entry->{revision}: No room for parents:\n\t", - join("\n\t", @tmp), "\n"; } @ret; } @@ -2225,6 +2898,20 @@ sub rewrite_root { $self->{-rewrite_root} = $rwr; } +sub rewrite_uuid { + my ($self) = @_; + return $self->{-rewrite_uuid} if exists $self->{-rewrite_uuid}; + my $k = "svn-remote.$self->{repo_id}.rewriteUUID"; + my $rwid = eval { command_oneline(qw/config --get/, $k) }; + if ($rwid) { + $rwid =~ s#/+$##; + if ($rwid !~ m#^[a-f0-9]{8}-(?:[a-f0-9]{4}-){3}[a-f0-9]{12}$#) { + die "$rwid is not a valid UUID (key: $k)\n"; + } + } + $self->{-rewrite_uuid} = $rwid; +} + sub metadata_url { my ($self) = @_; ($self->rewrite_root || $self->{url}) . @@ -2236,6 +2923,15 @@ sub full_url { $self->{url} . (length $self->{path} ? '/' . $self->{path} : ''); } +sub full_pushurl { + my ($self) = @_; + if ($self->{pushurl}) { + return $self->{pushurl} . (length $self->{path} ? '/' . + $self->{path} : ''); + } else { + return $self->full_url; + } +} sub set_commit_header_env { my ($log_entry) = @_; @@ -2331,13 +3027,13 @@ sub do_git_commit { $self->{last_rev} = $log_entry->{revision}; $self->{last_commit} = $commit; - print "r$log_entry->{revision}"; + print "r$log_entry->{revision}" unless $::_q > 1; if (defined $log_entry->{svm_revision}) { - print " (\@$log_entry->{svm_revision})"; + print " (\@$log_entry->{svm_revision})" unless $::_q > 1; $self->rev_map_set($log_entry->{svm_revision}, $commit, 0, $self->svm_uuid); } - print " = $commit ($self->{ref_id})\n"; + print " = $commit ($self->{ref_id})\n" unless $::_q > 1; if (--$_gc_nr == 0) { $_gc_nr = $_gc_period; gc(); @@ -2374,15 +3070,14 @@ sub find_parent_branch { unless (defined $paths) { my $err_handler = $SVN::Error::handler; $SVN::Error::handler = \&Git::SVN::Ra::skip_unknown_revs; - $self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1, sub { - $paths = - Git::SVN::Ra::dup_changed_paths($_[0]) }); + $self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1, + sub { $paths = $_[0] }); $SVN::Error::handler = $err_handler; } return undef unless defined $paths; # look for a parent from another branch: - my @b_path_components = split m#/#, $self->rel_path; + my @b_path_components = split m#/#, $self->{path}; my @a_path_components; my $i; while (@b_path_components) { @@ -2400,11 +3095,12 @@ sub find_parent_branch { my $r = $i->{copyfrom_rev}; my $repos_root = $self->ra->{repos_root}; my $url = $self->ra->{url}; - my $new_url = $repos_root . $branch_from; + my $new_url = $url . $branch_from; print STDERR "Found possible branch point: ", - "$new_url => ", $self->full_url, ", $r\n"; + "$new_url => ", $self->full_url, ", $r\n" + unless $::_q > 1; $branch_from =~ s#^/##; - my $gs = $self->other_gs($new_url, $url, $repos_root, + my $gs = $self->other_gs($new_url, $url, $branch_from, $r, $self->{ref_id}); my ($r0, $parent) = $gs->find_rev_before($r, 1); { @@ -2423,11 +3119,13 @@ sub find_parent_branch { ($r0, $parent) = $gs->find_rev_before($r, 1); } if (defined $r0 && defined $parent) { - print STDERR "Found branch parent: ($self->{ref_id}) $parent\n"; + print STDERR "Found branch parent: ($self->{ref_id}) $parent\n" + unless $::_q > 1; my $ed; if ($self->ra->can_do_switch) { $self->assert_index_clean($parent); - print STDERR "Following parent with do_switch\n"; + print STDERR "Following parent with do_switch\n" + unless $::_q > 1; # do_switch works with svn/trunk >= r22312, but that # is not included with SVN 1.4.3 (the latest version # at the moment), so we can't rely on it @@ -2442,18 +3140,20 @@ sub find_parent_branch { print STDERR "Trees match:\n", " $new_url\@$r0\n", " ${\$self->full_url}\@$rev\n", - "Following parent with no changes\n"; + "Following parent with no changes\n" + unless $::_q > 1; $self->tmp_index_do(sub { command_noisy('read-tree', $parent); }); $self->{last_commit} = $parent; } else { - print STDERR "Following parent with do_update\n"; + print STDERR "Following parent with do_update\n" + unless $::_q > 1; $ed = SVN::Git::Fetcher->new($self); $self->ra->gs_do_update($rev, $rev, $self, $ed) or die "SVN connection failed somewhere...\n"; } - print STDERR "Successfully followed parent\n"; + print STDERR "Successfully followed parent\n" unless $::_q > 1; return $self->make_log_entry($rev, [$parent], $ed); } return undef; @@ -2489,6 +3189,62 @@ sub do_fetch { $self->make_log_entry($rev, \@parents, $ed); } +sub mkemptydirs { + my ($self, $r) = @_; + + sub scan { + my ($r, $empty_dirs, $line) = @_; + if (defined $r && $line =~ /^r(\d+)$/) { + return 0 if $1 > $r; + } elsif ($line =~ /^ \+empty_dir: (.+)$/) { + $empty_dirs->{$1} = 1; + } elsif ($line =~ /^ \-empty_dir: (.+)$/) { + my @d = grep {m[^\Q$1\E(/|$)]} (keys %$empty_dirs); + delete @$empty_dirs{@d}; + } + 1; # continue + }; + + my %empty_dirs = (); + my $gz_file = "$self->{dir}/unhandled.log.gz"; + if (-f $gz_file) { + if (!$can_compress) { + warn "Compress::Zlib could not be found; ", + "empty directories in $gz_file will not be read\n"; + } else { + my $gz = Compress::Zlib::gzopen($gz_file, "rb") or + die "Unable to open $gz_file: $!\n"; + my $line; + while ($gz->gzreadline($line) > 0) { + scan($r, \%empty_dirs, $line) or last; + } + $gz->gzclose; + } + } + + if (open my $fh, '<', "$self->{dir}/unhandled.log") { + binmode $fh or croak "binmode: $!"; + while (<$fh>) { + scan($r, \%empty_dirs, $_) or last; + } + close $fh; + } + + my $strip = qr/\A\Q$self->{path}\E(?:\/|$)/; + foreach my $d (sort keys %empty_dirs) { + $d = uri_decode($d); + $d =~ s/$strip//; + next unless length($d); + next if -d $d; + if (-e $d) { + warn "$d exists but is not a directory\n"; + } else { + print "creating empty directory: $d\n"; + mkpath([$d]); + } + } +} + sub get_untracked { my ($self, $ed) = @_; my @out; @@ -2589,45 +3345,414 @@ sub parse_svn_date { } sub other_gs { - my ($self, $new_url, $url, $repos_root, + my ($self, $new_url, $url, $branch_from, $r, $old_ref_id) = @_; - my $gs = Git::SVN->find_by_url($new_url, $repos_root, $branch_from); + my $gs = Git::SVN->find_by_url($new_url, $url, $branch_from); unless ($gs) { my $ref_id = $old_ref_id; - $ref_id =~ s/\@\d+$//; + $ref_id =~ s/\@\d+-*$//; $ref_id .= "\@$r"; # just grow a tail if we're not unique enough :x $ref_id .= '-' while find_ref($ref_id); - print STDERR "Initializing parent: $ref_id\n"; my ($u, $p, $repo_id) = ($new_url, '', $ref_id); if ($u =~ s#^\Q$url\E(/|$)##) { $p = $u; $u = $url; $repo_id = $self->{repo_id}; } - $gs = Git::SVN->init($u, $p, $repo_id, $ref_id, 1); + while (1) { + # It is possible to tag two different subdirectories at + # the same revision. If the url for an existing ref + # does not match, we must either find a ref with a + # matching url or create a new ref by growing a tail. + $gs = Git::SVN->init($u, $p, $repo_id, $ref_id, 1); + my (undef, $max_commit) = $gs->rev_map_max(1); + last if (!$max_commit); + my ($url) = ::cmt_metadata($max_commit); + last if ($url eq $gs->metadata_url); + $ref_id .= '-'; + } + print STDERR "Initializing parent: $ref_id\n" unless $::_q > 1; } $gs } +sub call_authors_prog { + my ($orig_author) = @_; + $orig_author = command_oneline('rev-parse', '--sq-quote', $orig_author); + my $author = `$::_authors_prog $orig_author`; + if ($? != 0) { + die "$::_authors_prog failed with exit code $?\n" + } + if ($author =~ /^\s*(.+?)\s*<(.*)>\s*$/) { + my ($name, $email) = ($1, $2); + $email = undef if length $2 == 0; + return [$name, $email]; + } else { + die "Author: $orig_author: $::_authors_prog returned " + . "invalid author format: $author\n"; + } +} + sub check_author { my ($author) = @_; if (!defined $author || length $author == 0) { $author = '(no author)'; - } elsif (defined $::_authors && ! defined $::users{$author}) { - die "Author: $author not defined in $::_authors file\n"; + } + if (!defined $::users{$author}) { + if (defined $::_authors_prog) { + $::users{$author} = call_authors_prog($author); + } elsif (defined $::_authors) { + die "Author: $author not defined in $::_authors file\n"; + } } $author; } +sub find_extra_svk_parents { + my ($self, $ed, $tickets, $parents) = @_; + # aha! svk:merge property changed... + my @tickets = split "\n", $tickets; + my @known_parents; + for my $ticket ( @tickets ) { + my ($uuid, $path, $rev) = split /:/, $ticket; + if ( $uuid eq $self->ra_uuid ) { + my $url = $self->{url}; + my $repos_root = $url; + my $branch_from = $path; + $branch_from =~ s{^/}{}; + my $gs = $self->other_gs($repos_root."/".$branch_from, + $url, + $branch_from, + $rev, + $self->{ref_id}); + if ( my $commit = $gs->rev_map_get($rev, $uuid) ) { + # wahey! we found it, but it might be + # an old one (!) + push @known_parents, [ $rev, $commit ]; + } + } + } + # Ordering matters; highest-numbered commit merge tickets + # first, as they may account for later merge ticket additions + # or changes. + @known_parents = map {$_->[1]} sort {$b->[0] <=> $a->[0]} @known_parents; + for my $parent ( @known_parents ) { + my @cmd = ('rev-list', $parent, map { "^$_" } @$parents ); + my ($msg_fh, $ctx) = command_output_pipe(@cmd); + my $new; + while ( <$msg_fh> ) { + $new=1;last; + } + command_close_pipe($msg_fh, $ctx); + if ( $new ) { + print STDERR + "Found merge parent (svk:merge ticket): $parent\n"; + push @$parents, $parent; + } + } +} + +sub lookup_svn_merge { + my $uuid = shift; + my $url = shift; + my $merge = shift; + + my ($source, $revs) = split ":", $merge; + my $path = $source; + $path =~ s{^/}{}; + my $gs = Git::SVN->find_by_url($url.$source, $url, $path); + if ( !$gs ) { + warn "Couldn't find revmap for $url$source\n"; + return; + } + my @ranges = split ",", $revs; + my ($tip, $tip_commit); + my @merged_commit_ranges; + # find the tip + for my $range ( @ranges ) { + my ($bottom, $top) = split "-", $range; + $top ||= $bottom; + my $bottom_commit = $gs->find_rev_after( $bottom, 1, $top ); + my $top_commit = $gs->find_rev_before( $top, 1, $bottom ); + + unless ($top_commit and $bottom_commit) { + warn "W:unknown path/rev in svn:mergeinfo " + ."dirprop: $source:$range\n"; + next; + } + + if (scalar(command('rev-parse', "$bottom_commit^@"))) { + push @merged_commit_ranges, + "$bottom_commit^..$top_commit"; + } else { + push @merged_commit_ranges, "$top_commit"; + } + + if ( !defined $tip or $top > $tip ) { + $tip = $top; + $tip_commit = $top_commit; + } + } + return ($tip_commit, @merged_commit_ranges); +} + +sub _rev_list { + my ($msg_fh, $ctx) = command_output_pipe( + "rev-list", @_, + ); + my @rv; + while ( <$msg_fh> ) { + chomp; + push @rv, $_; + } + command_close_pipe($msg_fh, $ctx); + @rv; +} + +sub check_cherry_pick { + my $base = shift; + my $tip = shift; + my $parents = shift; + my @ranges = @_; + my %commits = map { $_ => 1 } + _rev_list("--no-merges", $tip, "--not", $base, @$parents, "--"); + for my $range ( @ranges ) { + delete @commits{_rev_list($range, "--")}; + } + for my $commit (keys %commits) { + if (has_no_changes($commit)) { + delete $commits{$commit}; + } + } + return (keys %commits); +} + +sub has_no_changes { + my $commit = shift; + + my @revs = split / /, command_oneline( + qw(rev-list --parents -1 -m), $commit); + + # Commits with no parents, e.g. the start of a partial branch, + # have changes by definition. + return 1 if (@revs < 2); + + # Commits with multiple parents, e.g a merge, have no changes + # by definition. + return 0 if (@revs > 2); + + return (command_oneline("rev-parse", "$commit^{tree}") eq + command_oneline("rev-parse", "$commit~1^{tree}")); +} + +# The GIT_DIR environment variable is not always set until after the command +# line arguments are processed, so we can't memoize in a BEGIN block. +{ + my $memoized = 0; + + sub memoize_svn_mergeinfo_functions { + return if $memoized; + $memoized = 1; + + my $cache_path = "$ENV{GIT_DIR}/svn/.caches/"; + mkpath([$cache_path]) unless -d $cache_path; + + tie my %lookup_svn_merge_cache => 'Memoize::Storable', + "$cache_path/lookup_svn_merge.db", 'nstore'; + memoize 'lookup_svn_merge', + SCALAR_CACHE => 'FAULT', + LIST_CACHE => ['HASH' => \%lookup_svn_merge_cache], + ; + + tie my %check_cherry_pick_cache => 'Memoize::Storable', + "$cache_path/check_cherry_pick.db", 'nstore'; + memoize 'check_cherry_pick', + SCALAR_CACHE => 'FAULT', + LIST_CACHE => ['HASH' => \%check_cherry_pick_cache], + ; + + tie my %has_no_changes_cache => 'Memoize::Storable', + "$cache_path/has_no_changes.db", 'nstore'; + memoize 'has_no_changes', + SCALAR_CACHE => ['HASH' => \%has_no_changes_cache], + LIST_CACHE => 'FAULT', + ; + } + + sub unmemoize_svn_mergeinfo_functions { + return if not $memoized; + $memoized = 0; + + Memoize::unmemoize 'lookup_svn_merge'; + Memoize::unmemoize 'check_cherry_pick'; + Memoize::unmemoize 'has_no_changes'; + } + + Memoize::memoize 'Git::SVN::repos_root'; +} + +END { + # Force cache writeout explicitly instead of waiting for + # global destruction to avoid segfault in Storable: + # http://rt.cpan.org/Public/Bug/Display.html?id=36087 + unmemoize_svn_mergeinfo_functions(); +} + +sub parents_exclude { + my $parents = shift; + my @commits = @_; + return unless @commits; + + my @excluded; + my $excluded; + do { + my @cmd = ('rev-list', "-1", @commits, "--not", @$parents ); + $excluded = command_oneline(@cmd); + if ( $excluded ) { + my @new; + my $found; + for my $commit ( @commits ) { + if ( $commit eq $excluded ) { + push @excluded, $commit; + $found++; + last; + } + else { + push @new, $commit; + } + } + die "saw commit '$excluded' in rev-list output, " + ."but we didn't ask for that commit (wanted: @commits --not @$parents)" + unless $found; + @commits = @new; + } + } + while ($excluded and @commits); + + return @excluded; +} + + +# note: this function should only be called if the various dirprops +# have actually changed +sub find_extra_svn_parents { + my ($self, $ed, $mergeinfo, $parents) = @_; + # aha! svk:merge property changed... + + memoize_svn_mergeinfo_functions(); + + # We first search for merged tips which are not in our + # history. Then, we figure out which git revisions are in + # that tip, but not this revision. If all of those revisions + # are now marked as merge, we can add the tip as a parent. + my @merges = split "\n", $mergeinfo; + my @merge_tips; + my $url = $self->{url}; + my $uuid = $self->ra_uuid; + my %ranges; + for my $merge ( @merges ) { + my ($tip_commit, @ranges) = + lookup_svn_merge( $uuid, $url, $merge ); + unless (!$tip_commit or + grep { $_ eq $tip_commit } @$parents ) { + push @merge_tips, $tip_commit; + $ranges{$tip_commit} = \@ranges; + } else { + push @merge_tips, undef; + } + } + + my %excluded = map { $_ => 1 } + parents_exclude($parents, grep { defined } @merge_tips); + + # check merge tips for new parents + my @new_parents; + for my $merge_tip ( @merge_tips ) { + my $spec = shift @merges; + next unless $merge_tip and $excluded{$merge_tip}; + + my $ranges = $ranges{$merge_tip}; + + # check out 'new' tips + my $merge_base; + eval { + $merge_base = command_oneline( + "merge-base", + @$parents, $merge_tip, + ); + }; + if ($@) { + die "An error occurred during merge-base" + unless $@->isa("Git::Error::Command"); + + warn "W: Cannot find common ancestor between ". + "@$parents and $merge_tip. Ignoring merge info.\n"; + next; + } + + # double check that there are no missing non-merge commits + my (@incomplete) = check_cherry_pick( + $merge_base, $merge_tip, + $parents, + @$ranges, + ); + + if ( @incomplete ) { + warn "W:svn cherry-pick ignored ($spec) - missing " + .@incomplete." commit(s) (eg $incomplete[0])\n"; + } else { + warn + "Found merge parent (svn:mergeinfo prop): ", + $merge_tip, "\n"; + push @new_parents, $merge_tip; + } + } + + # cater for merges which merge commits from multiple branches + if ( @new_parents > 1 ) { + for ( my $i = 0; $i <= $#new_parents; $i++ ) { + for ( my $j = 0; $j <= $#new_parents; $j++ ) { + next if $i == $j; + next unless $new_parents[$i]; + next unless $new_parents[$j]; + my $revs = command_oneline( + "rev-list", "-1", + "$new_parents[$i]..$new_parents[$j]", + ); + if ( !$revs ) { + undef($new_parents[$j]); + } + } + } + } + push @$parents, grep { defined } @new_parents; +} + sub make_log_entry { my ($self, $rev, $parents, $ed) = @_; my $untracked = $self->get_untracked($ed); + my @parents = @$parents; + my $ps = $ed->{path_strip} || ""; + for my $path ( grep { m/$ps/ } %{$ed->{dir_prop}} ) { + my $props = $ed->{dir_prop}{$path}; + if ( $props->{"svk:merge"} ) { + $self->find_extra_svk_parents + ($ed, $props->{"svk:merge"}, \@parents); + } + if ( $props->{"svn:mergeinfo"} ) { + $self->find_extra_svn_parents + ($ed, + $props->{"svn:mergeinfo"}, + \@parents); + } + } + open my $un, '>>', "$self->{dir}/unhandled.log" or croak $!; print $un "r$rev\n" or croak $!; print $un $_, "\n" foreach @$untracked; - my %log_entry = ( parents => $parents || [], revision => $rev, + my %log_entry = ( parents => \@parents, revision => $rev, log => ''); my $headrev; @@ -2681,7 +3806,11 @@ sub make_log_entry { die "Can't have both 'useSvmProps' and 'rewriteRoot' ", "options set!\n"; } - my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$}; + if ($self->rewrite_uuid) { + die "Can't have both 'useSvmProps' and 'rewriteUUID' ", + "options set!\n"; + } + my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$}i; # we don't want "SVM: initializing mirror for junk" ... return undef if $r == 0; my $svm = $self->svm; @@ -2711,10 +3840,10 @@ sub make_log_entry { } else { my $url = $self->metadata_url; remove_username($url); - $log_entry{metadata} = "$url\@$rev " . - $self->ra->get_uuid; - $email ||= "$author\@" . $self->ra->get_uuid; - $commit_email ||= "$author\@" . $self->ra->get_uuid; + my $uuid = $self->rewrite_uuid || $self->ra->get_uuid; + $log_entry{metadata} = "$url\@$rev " . $uuid; + $email ||= "$author\@" . $uuid; + $commit_email ||= "$author\@" . $uuid; } $log_entry{name} = $name; $log_entry{email} = $email; @@ -2796,7 +3925,7 @@ sub rebuild { '--'); my $metadata_url = $self->metadata_url; remove_username($metadata_url); - my $svn_uuid = $self->ra_uuid; + my $svn_uuid = $self->rewrite_uuid || $self->ra_uuid; my $c; while (<$log>) { if ( m{^commit ($::sha1)$} ) { @@ -2899,6 +4028,14 @@ sub _rev_map_set { croak "write: $!"; } +sub _rev_map_reset { + my ($fh, $rev, $commit) = @_; + my $c = _rev_map_get($fh, $rev); + $c eq $commit or die "_rev_map_reset(@_) commit $c does not match!\n"; + my $offset = sysseek($fh, 0, SEEK_CUR) or croak "seek: $!"; + truncate $fh, $offset or croak "truncate: $!"; +} + sub mkfile { my ($path) = @_; unless (-e $path) { @@ -2911,10 +4048,12 @@ sub mkfile { sub rev_map_set { my ($self, $rev, $commit, $update_ref, $uuid) = @_; + defined $commit or die "missing arg3\n"; length $commit == 40 or die "arg3 must be a full SHA1 hexsum\n"; my $db = $self->map_path($uuid); my $db_lock = "$db.lock"; my $sig; + $update_ref ||= 0; if ($update_ref) { $SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} = $SIG{USR1} = $SIG{USR2} = sub { $sig = $_[0] }; @@ -2938,7 +4077,8 @@ sub rev_map_set { sysopen(my $fh, $db_lock, O_RDWR | O_CREAT) or croak "Couldn't open $db_lock: $!\n"; - _rev_map_set($fh, $rev, $commit); + $update_ref eq 'reset' ? _rev_map_reset($fh, $rev, $commit) : + _rev_map_set($fh, $rev, $commit); if ($sync) { $fh->flush or die "Couldn't flush $db_lock: $!\n"; $fh->sync or die "Couldn't sync $db_lock: $!\n"; @@ -2946,7 +4086,9 @@ sub rev_map_set { close $fh or croak $!; if ($update_ref) { $_head = $self; - command_noisy('update-ref', '-m', "r$rev", + my $note = ""; + $note = " ($update_ref)" if ($update_ref !~ /^\d*$/); + command_noisy('update-ref', '-m', "r$rev$note", $self->refname, $commit); } rename $db_lock, $db or die "rev_map_set(@_): ", "Failed to rename: ", @@ -3008,12 +4150,19 @@ sub rev_map_get { return undef unless -e $map_path; sysopen(my $fh, $map_path, O_RDONLY) or croak "open: $!"; + my $c = _rev_map_get($fh, $rev); + close($fh) or croak "close: $!"; + $c +} + +sub _rev_map_get { + my ($fh, $rev) = @_; + binmode $fh or croak "binmode: $!"; my $size = (stat($fh))[7]; ($size % 24) == 0 or croak "inconsistent size: $size"; if ($size == 0) { - close $fh or croak "close: $fh"; return undef; } @@ -3024,18 +4173,16 @@ sub rev_map_get { my $i = int(($l/24 + $u/24) / 2) * 24; sysseek($fh, $i, SEEK_SET) or croak "seek: $!"; sysread($fh, my $buf, 24) == 24 or croak "read: $!"; - my ($r, $c) = unpack('NH40', $buf); + my ($r, $c) = unpack(rev_map_fmt, $buf); if ($r < $rev) { $l = $i + 24; } elsif ($r > $rev) { $u = $i - 24; } else { # $r == $rev - close($fh) or croak "close: $!"; return $c eq ('0' x 40) ? undef : $c; } } - close($fh) or croak "close: $!"; undef; } @@ -3047,6 +4194,8 @@ sub find_rev_before { my ($self, $rev, $eq_ok, $min_rev) = @_; --$rev unless $eq_ok; $min_rev ||= 1; + my $max_rev = $self->rev_map_max; + $rev = $max_rev if ($rev > $max_rev); while ($rev >= $min_rev) { if (my $c = $self->rev_map_get($rev)) { return ($rev, $c); @@ -3079,12 +4228,24 @@ sub _new { $repo_id = $Git::SVN::default_repo_id; } unless (defined $ref_id && length $ref_id) { - $_[2] = $ref_id = $Git::SVN::default_ref_id; + $_prefix = '' unless defined($_prefix); + $_[2] = $ref_id = + "refs/remotes/$_prefix$Git::SVN::default_ref_id"; } $_[1] = $repo_id; my $dir = "$ENV{GIT_DIR}/svn/$ref_id"; + + # Older repos imported by us used $GIT_DIR/svn/foo instead of + # $GIT_DIR/svn/refs/remotes/foo when tracking refs/remotes/foo + if ($ref_id =~ m{^refs/remotes/(.*)}) { + my $old_dir = "$ENV{GIT_DIR}/svn/$1"; + if (-d $old_dir && ! -d $dir) { + $dir = $old_dir; + } + } + $_[3] = $path = '' unless (defined $path); - mkpath(["$ENV{GIT_DIR}/svn"]); + mkpath([$dir]); bless { ref_id => $ref_id, dir => $dir, index => "$dir/index", path => $path, config => "$ENV{GIT_DIR}/svn/config", @@ -3122,6 +4283,12 @@ sub uri_encode { $f } +sub uri_decode { + my ($f) = @_; + $f =~ s#%([0-9a-fA-F]{2})#chr(hex($1))#eg; + $f +} + sub remove_username { $_[0] =~ s{^([^:]*://)[^@]+@}{$1}; } @@ -3248,29 +4415,36 @@ sub username { sub _read_password { my ($prompt, $realm) = @_; - print STDERR $prompt; - STDERR->flush; - require Term::ReadKey; - Term::ReadKey::ReadMode('noecho'); my $password = ''; - while (defined(my $key = Term::ReadKey::ReadKey(0))) { - last if $key =~ /[\012\015]/; # \n\r - $password .= $key; + if (exists $ENV{GIT_ASKPASS}) { + open(PH, "-|", $ENV{GIT_ASKPASS}, $prompt); + $password = <PH>; + $password =~ s/[\012\015]//; # \n\r + close(PH); + } else { + print STDERR $prompt; + STDERR->flush; + require Term::ReadKey; + Term::ReadKey::ReadMode('noecho'); + while (defined(my $key = Term::ReadKey::ReadKey(0))) { + last if $key =~ /[\012\015]/; # \n\r + $password .= $key; + } + Term::ReadKey::ReadMode('restore'); + print STDERR "\n"; + STDERR->flush; } - Term::ReadKey::ReadMode('restore'); - print STDERR "\n"; - STDERR->flush; $password; } package SVN::Git::Fetcher; -use vars qw/@ISA/; +use vars qw/@ISA $_ignore_regex $_preserve_empty_dirs $_placeholder_filename + @deleted_gpath %added_placeholder $repo_id/; use strict; use warnings; use Carp qw/croak/; -use File::Temp qw/tempfile/; +use File::Basename qw/dirname/; use IO::File qw//; -use vars qw/$_ignore_regex/; # file baton members: path, mode_a, mode_b, pool, fh, blob, base sub new { @@ -3282,12 +4456,41 @@ sub new { $self->{empty_symlinks} = _mark_empty_symlinks($git_svn, $switch_path); } + + # some options are read globally, but can be overridden locally + # per [svn-remote "..."] section. Command-line options will *NOT* + # override options set in an [svn-remote "..."] section + $repo_id = $git_svn->{repo_id}; + my $k = "svn-remote.$repo_id.ignore-paths"; + my $v = eval { command_oneline('config', '--get', $k) }; + $self->{ignore_regex} = $v; + + $k = "svn-remote.$repo_id.preserve-empty-dirs"; + $v = eval { command_oneline('config', '--get', '--bool', $k) }; + if ($v && $v eq 'true') { + $_preserve_empty_dirs = 1; + $k = "svn-remote.$repo_id.placeholder-filename"; + $v = eval { command_oneline('config', '--get', $k) }; + $_placeholder_filename = $v; + } + + # Load the list of placeholder files added during previous invocations. + $k = "svn-remote.$repo_id.added-placeholder"; + $v = eval { command_oneline('config', '--get-all', $k) }; + if ($_preserve_empty_dirs && $v) { + # command() prints errors to stderr, so we only call it if + # command_oneline() succeeded. + my @v = command('config', '--get-all', $k); + $added_placeholder{ dirname($_) } = $_ foreach @v; + } + $self->{empty} = {}; $self->{dir_prop} = {}; $self->{file_prop} = {}; $self->{absent_dir} = {}; $self->{absent_file} = {}; $self->{gii} = $git_svn->tmp_index_do(sub { Git::IndexInfo->new }); + $self->{pathnameencoding} = Git::config('svn.pathnameencoding'); $self; } @@ -3297,7 +4500,7 @@ sub new { sub _mark_empty_symlinks { my ($git_svn, $switch_path) = @_; my $bool = Git::config_bool('svn.brokenSymlinkWorkaround'); - return {} if (defined($bool) && ! $bool); + return {} if (!defined($bool)) || (defined($bool) && ! $bool); my %ret; my ($rev, $cmt) = $git_svn->last_rev_commit; @@ -3346,8 +4549,10 @@ sub in_dot_git { # return value: 0 -- don't ignore, 1 -- ignore sub is_path_ignored { - my ($path) = @_; + my ($self, $path) = @_; return 1 if in_dot_git($path); + return 1 if defined($self->{ignore_regex}) && + $path =~ m!$self->{ignore_regex}!; return 0 unless defined($_ignore_regex); return 1 if $path =~ m!$_ignore_regex!o; return 0; @@ -3369,6 +4574,10 @@ sub open_directory { sub git_path { my ($self, $path) = @_; + if (my $enc = $self->{pathnameencoding}) { + require Encode; + Encode::from_to($path, 'UTF-8', $enc); + } if ($self->{path_strip}) { $path =~ s!$self->{path_strip}!! or die "Failed to strip path '$path' ($self->{path_strip})\n"; @@ -3378,29 +4587,34 @@ sub git_path { sub delete_entry { my ($self, $path, $rev, $pb) = @_; - return undef if is_path_ignored($path); + return undef if $self->is_path_ignored($path); my $gpath = $self->git_path($path); return undef if ($gpath eq ''); # remove entire directories. - if (command('ls-tree', $self->{c}, '--', $gpath) =~ /^040000 tree/) { + my ($tree) = (command('ls-tree', '-z', $self->{c}, "./$gpath") + =~ /\A040000 tree ([a-f\d]{40})\t\Q$gpath\E\0/); + if ($tree) { my ($ls, $ctx) = command_output_pipe(qw/ls-tree -r --name-only -z/, - $self->{c}, '--', $gpath); + $tree); local $/ = "\0"; while (<$ls>) { chomp; - $self->{gii}->remove($_); - print "\tD\t$_\n" unless $::_q; + my $rmpath = "$gpath/$_"; + $self->{gii}->remove($rmpath); + print "\tD\t$rmpath\n" unless $::_q; } print "\tD\t$gpath/\n" unless $::_q; command_close_pipe($ls, $ctx); - $self->{empty}->{$path} = 0 } else { $self->{gii}->remove($gpath); print "\tD\t$gpath\n" unless $::_q; } + # Don't add to @deleted_gpath if we're deleting a placeholder file. + push @deleted_gpath, $gpath unless $added_placeholder{dirname($path)}; + $self->{empty}->{$path} = 0; undef; } @@ -3408,11 +4622,11 @@ sub open_file { my ($self, $path, $pb, $rev) = @_; my ($mode, $blob); - goto out if is_path_ignored($path); + goto out if $self->is_path_ignored($path); my $gpath = $self->git_path($path); - ($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath) - =~ /^(\d{6}) blob ([a-f\d]{40})\t/); + ($mode, $blob) = (command('ls-tree', '-z', $self->{c}, "./$gpath") + =~ /\A(\d{6}) blob ([a-f\d]{40})\t\Q$gpath\E\0/); unless (defined $mode && defined $blob) { die "$path was not found in commit $self->{c} (r$rev)\n"; } @@ -3428,18 +4642,26 @@ sub add_file { my ($self, $path, $pb, $cp_path, $cp_rev) = @_; my $mode; - if (!is_path_ignored($path)) { + if (!$self->is_path_ignored($path)) { my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#); delete $self->{empty}->{$dir}; $mode = '100644'; + + if ($added_placeholder{$dir}) { + # Remove our placeholder file, if we created one. + delete_entry($self, $added_placeholder{$dir}) + unless $path eq $added_placeholder{$dir}; + delete $added_placeholder{$dir} + } } + { path => $path, mode_a => $mode, mode_b => $mode, pool => SVN::Pool->new, action => 'A' }; } sub add_directory { my ($self, $path, $cp_path, $cp_rev) = @_; - goto out if is_path_ignored($path); + goto out if $self->is_path_ignored($path); my $gpath = $self->git_path($path); if ($gpath eq '') { my ($ls, $ctx) = command_output_pipe(qw/ls-tree @@ -3450,6 +4672,7 @@ sub add_directory { chomp; $self->{gii}->remove($_); print "\tD\t$_\n" unless $::_q; + push @deleted_gpath, $gpath; } command_close_pipe($ls, $ctx); $self->{empty}->{$path} = 0; @@ -3457,13 +4680,20 @@ sub add_directory { my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#); delete $self->{empty}->{$dir}; $self->{empty}->{$path} = 1; + + if ($added_placeholder{$dir}) { + # Remove our placeholder file, if we created one. + delete_entry($self, $added_placeholder{$dir}); + delete $added_placeholder{$dir} + } + out: { path => $path }; } sub change_dir_prop { my ($self, $db, $prop, $value) = @_; - return undef if is_path_ignored($db->{path}); + return undef if $self->is_path_ignored($db->{path}); $self->{dir_prop}->{$db->{path}} ||= {}; $self->{dir_prop}->{$db->{path}}->{$prop} = $value; undef; @@ -3471,7 +4701,7 @@ sub change_dir_prop { sub absent_directory { my ($self, $path, $pb) = @_; - return undef if is_path_ignored($path); + return undef if $self->is_path_ignored($path); $self->{absent_dir}->{$pb->{path}} ||= []; push @{$self->{absent_dir}->{$pb->{path}}}, $path; undef; @@ -3479,7 +4709,7 @@ sub absent_directory { sub absent_file { my ($self, $path, $pb) = @_; - return undef if is_path_ignored($path); + return undef if $self->is_path_ignored($path); $self->{absent_file}->{$pb->{path}} ||= []; push @{$self->{absent_file}->{$pb->{path}}}, $path; undef; @@ -3487,7 +4717,7 @@ sub absent_file { sub change_file_prop { my ($self, $fb, $prop, $value) = @_; - return undef if is_path_ignored($fb->{path}); + return undef if $self->is_path_ignored($fb->{path}); if ($prop eq 'svn:executable') { if ($fb->{mode_b} != 120000) { $fb->{mode_b} = defined $value ? 100755 : 100644; @@ -3503,7 +4733,7 @@ sub change_file_prop { sub apply_textdelta { my ($self, $fb, $exp) = @_; - return undef if is_path_ignored($fb->{path}); + return undef if $self->is_path_ignored($fb->{path}); my $fh = $::_repository->temp_acquire('svn_delta'); # $fh gets auto-closed() by SVN::TxDelta::apply(), # (but $base does not,) so dup() it for reading in close_file @@ -3550,7 +4780,7 @@ sub apply_textdelta { sub close_file { my ($self, $fb, $exp) = @_; - return undef if is_path_ignored($fb->{path}); + return undef if $self->is_path_ignored($fb->{path}); my $hash; my $path = $self->git_path($fb->{path}); @@ -3620,12 +4850,96 @@ sub abort_edit { sub close_edit { my $self = shift; + + if ($_preserve_empty_dirs) { + my @empty_dirs; + + # Any entry flagged as empty that also has an associated + # dir_prop represents a newly created empty directory. + foreach my $i (keys %{$self->{empty}}) { + push @empty_dirs, $i if exists $self->{dir_prop}->{$i}; + } + + # Search for directories that have become empty due subsequent + # file deletes. + push @empty_dirs, $self->find_empty_directories(); + + # Finally, add a placeholder file to each empty directory. + $self->add_placeholder_file($_) foreach (@empty_dirs); + + $self->stash_placeholder_list(); + } + $self->{git_commit_ok} = 1; $self->{nr} = $self->{gii}->{nr}; delete $self->{gii}; $self->SUPER::close_edit(@_); } +sub find_empty_directories { + my ($self) = @_; + my @empty_dirs; + my %dirs = map { dirname($_) => 1 } @deleted_gpath; + + foreach my $dir (sort keys %dirs) { + next if $dir eq "."; + + # If there have been any additions to this directory, there is + # no reason to check if it is empty. + my $skip_added = 0; + foreach my $t (qw/dir_prop file_prop/) { + foreach my $path (keys %{ $self->{$t} }) { + if (exists $self->{$t}->{dirname($path)}) { + $skip_added = 1; + last; + } + } + last if $skip_added; + } + next if $skip_added; + + # Use `git ls-tree` to get the filenames of this directory + # that existed prior to this particular commit. + my $ls = command('ls-tree', '-z', '--name-only', + $self->{c}, "$dir/"); + my %files = map { $_ => 1 } split(/\0/, $ls); + + # Remove the filenames that were deleted during this commit. + delete $files{$_} foreach (@deleted_gpath); + + # Report the directory if there are no filenames left. + push @empty_dirs, $dir unless (scalar %files); + } + @empty_dirs; +} + +sub add_placeholder_file { + my ($self, $dir) = @_; + my $path = "$dir/$_placeholder_filename"; + my $gpath = $self->git_path($path); + + my $fh = $::_repository->temp_acquire($gpath); + my $hash = $::_repository->hash_and_insert_object(Git::temp_path($fh)); + Git::temp_release($fh, 1); + $self->{gii}->update('100644', $hash, $gpath) or croak $!; + + # The directory should no longer be considered empty. + delete $self->{empty}->{$dir} if exists $self->{empty}->{$dir}; + + # Keep track of any placeholder files we create. + $added_placeholder{$dir} = $path; +} + +sub stash_placeholder_list { + my ($self) = @_; + my $k = "svn-remote.$repo_id.added-placeholder"; + my $v = eval { command_oneline('config', '--get-all', $k) }; + command_noisy('config', '--unset-all', $k) if $v; + foreach (values %added_placeholder) { + command_noisy('config', '--add', $k, $_); + } +} + package SVN::Git::Editor; use vars qw/@ISA $_rmdir $_cp_similarity $_find_copies_harder $_rename_limit/; use strict; @@ -3661,6 +4975,7 @@ sub new { $self->{path_prefix} = length $self->{svn_path} ? "$self->{svn_path}/" : ''; $self->{config} = $opts->{config}; + $self->{mergeinfo} = $opts->{mergeinfo}; return $self; } @@ -3754,13 +5069,17 @@ sub split_path { sub repo_path { my ($self, $path) = @_; + if (my $enc = $self->{pathnameencoding}) { + require Encode; + Encode::from_to($path, $enc, 'UTF-8'); + } $self->{path_prefix}.(defined $path ? $path : ''); } sub url_path { my ($self, $path) = @_; if ($self->{url} =~ m#^https?://#) { - $path =~ s/([^~a-zA-Z0-9_.-])/uc sprintf("%%%02x",ord($1))/eg; + $path =~ s!([^~a-zA-Z0-9_./-])!uc sprintf("%%%02x",ord($1))!eg; } $self->{url} . '/' . $self->repo_path($path); } @@ -3966,6 +5285,11 @@ sub change_file_prop { $self->SUPER::change_file_prop($fbat, $pname, $pval, $self->{pool}); } +sub change_dir_prop { + my ($self, $pbat, $pname, $pval) = @_; + $self->SUPER::change_dir_prop($pbat, $pname, $pval, $self->{pool}); +} + sub _chg_file_get_blob ($$$$) { my ($self, $fbat, $m, $which) = @_; my $fh = $::_repository->temp_acquire("git_blob_$which"); @@ -4059,6 +5383,11 @@ sub apply_diff { fatal("Invalid change type: $f"); } } + + if (defined($self->{mergeinfo})) { + $self->change_dir_prop($self->{bat}{''}, "svn:mergeinfo", + $self->{mergeinfo}); + } $self->rmdirs if $_rmdir; if (@$mods == 0) { $self->abort_edit; @@ -4069,7 +5398,7 @@ sub apply_diff { } package Git::SVN::Ra; -use vars qw/@ISA $config_dir $_log_window_size/; +use vars qw/@ISA $config_dir $_ignore_refs_regex $_log_window_size/; use strict; use warnings; my ($ra_invalid, $can_do_switch, %ignored_err, $RA); @@ -4134,6 +5463,8 @@ sub new { $url =~ s!/+$!!; return $RA if ($RA && $RA->{url} eq $url); + ::_req_svn(); + SVN::_Core::svn_config_ensure($config_dir, undef); my ($baton, $callbacks) = SVN::Core::auth_open_helper(_auth_providers); my $config = SVN::Core::config_get_config($config_dir); @@ -4220,6 +5551,34 @@ sub get_log { my ($self, @args) = @_; my $pool = SVN::Pool->new; + # svn_log_changed_path_t objects passed to get_log are likely to be + # overwritten even if only the refs are copied to an external variable, + # so we should dup the structures in their entirety. Using an + # externally passed pool (instead of our temporary and quickly cleared + # pool in Git::SVN::Ra) does not help matters at all... + my $receiver = pop @args; + my $prefix = "/".$self->{svn_path}; + $prefix =~ s#/+($)##; + my $prefix_regex = qr#^\Q$prefix\E#; + push(@args, sub { + my ($paths) = $_[0]; + return &$receiver(@_) unless $paths; + $_[0] = (); + foreach my $p (keys %$paths) { + my $i = $paths->{$p}; + # Make path relative to our url, not repos_root + $p =~ s/$prefix_regex//; + my %s = map { $_ => $i->$_; } + qw/copyfrom_path copyfrom_rev action/; + if ($s{'copyfrom_path'}) { + $s{'copyfrom_path'} =~ s/$prefix_regex//; + } + $_[0]{$p} = \%s; + } + &$receiver(@_); + }); + + # the limit parameter was not supported in SVN 1.1.x, so we # drop it. Therefore, the receiver callback passed to it # is made aware of this limitation by being wrapped if @@ -4304,10 +5663,12 @@ sub gs_do_switch { my $full_url = $self->{url}; my $old_url = $full_url; - $full_url .= '/' . escape_uri_only($path) if length $path; + $full_url .= '/' . $path if length $path; my ($ra, $reparented); - if ($old_url =~ m#^svn(\+ssh)?://#) { + if ($old_url =~ m#^svn(\+ssh)?://# || + ($full_url =~ m#^https?://# && + escape_url($full_url) ne $full_url)) { $_[0] = undef; $self = undef; $RA = undef; @@ -4378,6 +5739,7 @@ sub gs_fetch_loop_common { my ($min, $max) = ($base, $head < $base + $inc ? $head : $base + $inc); my $longest_path = longest_common_path($gsv, $globs); my $ra_url = $self->{url}; + my $find_trailing_edge; while (1) { my %revs; my $err; @@ -4388,15 +5750,17 @@ sub gs_fetch_loop_common { }; sub _cb { my ($paths, $r, $author, $date, $log) = @_; - [ dup_changed_paths($paths), + [ $paths, { author => $author, date => $date, log => $log } ]; } $self->get_log([$longest_path], $min, $max, 0, 1, 1, sub { $revs{$_[1]} = _cb(@_) }); if ($err) { print "Checked through r$max\r"; + } else { + $find_trailing_edge = 1; } - if ($err && $max >= $head) { + if ($err and $find_trailing_edge) { print STDERR "Path '$longest_path' ", "was probably deleted:\n", $err->expanded_message, @@ -4408,13 +5772,14 @@ sub gs_fetch_loop_common { my $ok; $self->get_log([$longest_path], $min, $hi, 0, 1, 1, sub { - $ok ||= $_[1]; + $ok = $_[1]; $revs{$_[1]} = _cb(@_) }); if ($ok) { print STDERR "r$min .. r$ok OK\n"; last; } } + $find_trailing_edge = 0; } $SVN::Error::handler = $err_handler; @@ -4491,6 +5856,17 @@ sub get_dir_globbed { @finalents; } +# return value: 0 -- don't ignore, 1 -- ignore +sub is_ref_ignored { + my ($g, $p) = @_; + my $refname = $g->{ref}->full_path($p); + return 1 if defined($g->{ignore_refs_regex}) && + $refname =~ m!$g->{ignore_refs_regex}!; + return 0 unless defined($_ignore_refs_regex); + return 1 if $refname =~ m!$_ignore_refs_regex!o; + return 0; +} + sub match_globs { my ($self, $exists, $paths, $globs, $r) = @_; @@ -4507,6 +5883,7 @@ sub match_globs { next if (length $g->{path}->{right} && ($self->check_path($p, $r) != $SVN::Node::dir)); + next unless $p =~ /$g->{path}->{regex}/; $exists->{$p} = Git::SVN->init($self->{url}, $p, undef, $g->{ref}->full_path($de), 1); } @@ -4526,6 +5903,7 @@ sub match_globs { next unless /$g->{path}->{regex}/; my $p = $1; my $pathname = $g->{path}->full_path($p); + next if is_ref_ignored($g, $p); next if $exists->{$pathname}; next if ($self->check_path($pathname, $r) != $SVN::Node::dir); @@ -4552,7 +5930,11 @@ sub minimize_url { my $c = ''; do { $url .= "/$c" if length $c; - eval { (ref $self)->new($url)->get_latest_revnum }; + eval { + my $ra = (ref $self)->new($url); + my $latest = $ra->get_latest_revnum; + $ra->get_log("", $latest, 0, 1, 0, 1, sub {}); + }; } while ($@ && ($c = shift @components)); $url; } @@ -4608,24 +5990,6 @@ sub skip_unknown_revs { die "Error from SVN, ($errno): ", $err->expanded_message,"\n"; } -# svn_log_changed_path_t objects passed to get_log are likely to be -# overwritten even if only the refs are copied to an external variable, -# so we should dup the structures in their entirety. Using an externally -# passed pool (instead of our temporary and quickly cleared pool in -# Git::SVN::Ra) does not help matters at all... -sub dup_changed_paths { - my ($paths) = @_; - return undef unless $paths; - my %ret; - foreach my $p (keys %$paths) { - my $i = $paths->{$p}; - my %s = map { $_ => $i->$_ } - qw/copyfrom_path copyfrom_rev action/; - $ret{$p} = \%s; - } - \%ret; -} - package Git::SVN::Log; use strict; use warnings; @@ -4713,17 +6077,20 @@ sub git_svn_log_cmd { # adapted from pager.c sub config_pager { - $pager ||= $ENV{GIT_PAGER} || $ENV{PAGER}; - if (!defined $pager) { - $pager = 'less'; - } elsif (length $pager == 0 || $pager eq 'cat') { + if (! -t *STDOUT) { + $ENV{GIT_PAGER_IN_USE} = 'false'; + $pager = undef; + return; + } + chomp($pager = command_oneline(qw(var GIT_PAGER))); + if ($pager eq 'cat') { $pager = undef; } $ENV{GIT_PAGER_IN_USE} = defined($pager); } sub run_pager { - return unless -t *STDOUT && defined $pager; + return unless defined $pager; pipe my ($rfd, $wfd) or return; defined(my $pid = fork) or ::fatal "Can't fork: $!"; if (!$pid) { @@ -4738,7 +6105,7 @@ sub run_pager { sub format_svn_date { # some systmes don't handle or mishandle %z, so be creative. - my $t = shift; + my $t = shift || time; my $gm = timelocal(gmtime($t)); my $sign = qw( + + - )[ $t <=> $gm ]; my $gmoff = sprintf("%s%02d%02d", $sign, (gmtime(abs($t - $gm)))[2,1]); @@ -4901,7 +6268,7 @@ sub cmd_show_log { my (@k, $c, $d, $stat); my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/; while (<$log>) { - if (/^${esc_color}commit -?($::sha1_short)/o) { + if (/^${esc_color}commit (?:- )?($::sha1_short)/o) { my $cmt = $1; if ($c && cmt_showable($c) && $c->{r} != $r_last) { $r_last = $c->{r}; @@ -4984,11 +6351,22 @@ sub cmd_blame { '--', $path); my ($sha1); my %authors; + my @buffer; + my %dsha; #distinct sha keys + while (my $line = <$fh>) { + push @buffer, $line; + if ($line =~ /^([[:xdigit:]]{40})\s\d+\s\d+/) { + $dsha{$1} = 1; + } + } + + my $s2r = ::cmt_sha2rev_batch([keys %dsha]); + + foreach my $line (@buffer) { if ($line =~ /^([[:xdigit:]]{40})\s\d+\s\d+/) { - $sha1 = $1; - (undef, $rev, undef) = ::cmt_metadata($1); - $rev = '0' if (!$rev); + $rev = $s2r->{$1}; + $rev = '0' if (!$rev) } elsif ($line =~ /^author (.*)/) { $authors{$rev} = $1; @@ -5219,7 +6597,7 @@ sub minimize_connections { my $pfx = "svn-remote.$x->{old_repo_id}"; my $old_fetch = quotemeta("$x->{old_path}:". - "refs/remotes/$x->{ref_id}"); + "$x->{ref_id}"); command_noisy(qw/config --unset/, "$pfx.fetch", '^'. $old_fetch . '$'); delete $r->{$x->{old_repo_id}}-> @@ -5285,29 +6663,48 @@ use strict; use warnings; sub new { - my ($class, $glob) = @_; + my ($class, $glob, $pattern_ok) = @_; my $re = $glob; $re =~ s!/+$!!g; # no need for trailing slashes - $re =~ m!^([^*]*)(\*(?:/\*)*)([^*]*)$!; - my $temp = $re; - my ($left, $right) = ($1, $3); - $re = $2; - my $depth = $re =~ tr/*/*/; - if ($depth != $temp =~ tr/*/*/) { - die "Only one set of wildcard directories " . - "(e.g. '*' or '*/*/*') is supported: '$glob'\n"; + my (@left, @right, @patterns); + my $state = "left"; + my $die_msg = "Only one set of wildcard directories " . + "(e.g. '*' or '*/*/*') is supported: '$glob'\n"; + for my $part (split(m|/|, $glob)) { + if ($part =~ /\*/ && $part ne "*") { + die "Invalid pattern in '$glob': $part\n"; + } elsif ($pattern_ok && $part =~ /[{}]/ && + $part !~ /^\{[^{}]+\}/) { + die "Invalid pattern in '$glob': $part\n"; + } + if ($part eq "*") { + die $die_msg if $state eq "right"; + $state = "pattern"; + push(@patterns, "[^/]*"); + } elsif ($pattern_ok && $part =~ /^\{(.*)\}$/) { + die $die_msg if $state eq "right"; + $state = "pattern"; + my $p = quotemeta($1); + $p =~ s/\\,/|/g; + push(@patterns, "(?:$p)"); + } else { + if ($state eq "left") { + push(@left, $part); + } else { + push(@right, $part); + $state = "right"; + } + } } + my $depth = @patterns; if ($depth == 0) { - die "One '*' is needed for glob: '$glob'\n"; - } - $re =~ s!\*!\[^/\]*!g; - $re = quotemeta($left) . "($re)" . quotemeta($right); - if (length $left && !($left =~ s!/+$!!g)) { - die "Missing trailing '/' on left side of: '$glob' ($left)\n"; - } - if (length $right && !($right =~ s!^/+!!g)) { - die "Missing leading '/' on right side of: '$glob' ($right)\n"; + die "One '*' is needed in glob: '$glob'\n"; } + my $left = join('/', @left); + my $right = join('/', @right); + $re = join('/', @patterns); + $re = join('\/', + grep(length, quotemeta($left), "($re)", quotemeta($right))); my $left_re = qr/^\/\Q$left\E(\/|$)/; bless { left => $left, right => $right, left_regex => $left_re, regex => qr/$re/, glob => $glob, depth => $depth }, $class; |