diff options
Diffstat (limited to 'git-svn.perl')
-rwxr-xr-x | git-svn.perl | 4745 |
1 files changed, 1519 insertions, 3226 deletions
diff --git a/git-svn.perl b/git-svn.perl index 326e89fe03..fa5f253065 100755 --- a/git-svn.perl +++ b/git-svn.perl @@ -1,104 +1,178 @@ -#!/usr/bin/env perl +#!/usr/bin/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 - $_q $_authors %users/; + $sha1 $sha1_short $_revision $_repository + $_q $_authors $_authors_prog %users/; $AUTHOR = 'Eric Wong <normalperson@yhbt.net>'; $VERSION = '@@GIT_VERSION@@'; -my $git_dir_user_set = 1 if defined $ENV{GIT_DIR}; -$ENV{GIT_DIR} ||= '.git'; -$Git::SVN::default_repo_id = 'svn'; -$Git::SVN::default_ref_id = $ENV{GIT_SVN_ID} || 'git-svn'; +use Carp qw/croak/; +use File::Basename qw/dirname basename/; +use File::Path qw/mkpath/; +use File::Spec; +use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/; +use Memoize; + +use Git::SVN; +use Git::SVN::Editor; +use Git::SVN::Fetcher; +use Git::SVN::Ra; +use Git::SVN::Prompt; +use Git::SVN::Log; +use Git::SVN::Migration; + +use Git::SVN::Utils qw( + fatal + can_compress + canonicalize_path + canonicalize_url + join_paths + add_path_to_url + join_paths +); + +use Git qw( + git_cmd_try + command + command_oneline + command_noisy + command_output_pipe + command_close_pipe + command_bidi_pipe + command_close_bidi_pipe +); + +BEGIN { + Memoize::memoize 'Git::config'; + Memoize::memoize 'Git::config_bool'; +} + + +# From which subdir have we been invoked? +my $cmd_dir_prefix = eval { + command_oneline([qw/rev-parse --show-prefix/], STDERR => 0) +} || ''; + $Git::SVN::Ra::_log_window_size = 100; +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'; $| = 1; # unbuffer STDOUT -sub fatal (@) { print STDERR @_; exit 1 } -require SVN::Core; # use()-ing this causes segfaults for me... *shrug* -require SVN::Ra; -require SVN::Delta; -if ($SVN::Core::VERSION lt '1.1.0') { - fatal "Need SVN::Core 1.1.0 or better (got $SVN::Core::VERSION)\n"; -} -push @Git::SVN::Ra::ISA, 'SVN::Ra'; -push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor'; -push @SVN::Git::Fetcher::ISA, 'SVN::Delta::Editor'; -use Carp qw/croak/; -use IO::File qw//; -use File::Basename qw/dirname basename/; -use File::Path qw/mkpath/; -use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/; -use IPC::Open3; -use Git; +# All SVN commands do it. Otherwise we may die on SIGPIPE when the remote +# repository decides to close the connection which we expect to be kept alive. +$SIG{PIPE} = 'IGNORE'; -BEGIN { - my $s; - foreach (qw/command command_oneline command_noisy command_output_pipe - command_input_pipe command_close_pipe/) { - $s .= "*SVN::Git::Editor::$_ = *SVN::Git::Fetcher::$_ = ". - "*Git::SVN::Migration::$_ = ". - "*Git::SVN::Log::$_ = *Git::SVN::$_ = *$_ = *Git::$_; "; +# Given a dot separated version number, "subtract" it from +# the SVN::Core::VERSION; non-negaitive return means the SVN::Core +# is at least at the version the caller asked for. +sub compare_svn_version { + my (@ours) = split(/\./, $SVN::Core::VERSION); + my (@theirs) = split(/\./, $_[0]); + my ($i, $diff); + + for ($i = 0; $i < @ours && $i < @theirs; $i++) { + $diff = $ours[$i] - $theirs[$i]; + return $diff if ($diff); } - eval $s; + return 1 if ($i < @ours); + return -1 if ($i < @theirs); + return 0; } -my ($SVN); +sub _req_svn { + require SVN::Core; # use()-ing this causes segfaults for me... *shrug* + require SVN::Ra; + require SVN::Delta; + if (::compare_svn_version('1.1.0') < 0) { + fatal "Need SVN::Core 1.1.0 or better (got $SVN::Core::VERSION)"; + } +} $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, - $_merge, $_strategy, $_dry_run, - $_prefix, $_no_checkout, $_verbose); -$Git::SVN::_follow_parent = 1; + $_version, $_fetch_all, $_no_rebase, $_fetch_parent, + $_before, $_after, + $_merge, $_strategy, $_preserve_merges, $_dry_run, $_parents, $_local, + $_prefix, $_no_checkout, $_url, $_verbose, + $_commit_url, $_tag, $_merge_info, $_interactive, $_set_svn_props); + +# This is a refactoring artifact so Git::SVN can get at this git-svn switch. +sub opt_prefix { return $_prefix || '' } + +$Git::SVN::Fetcher::_placeholder_filename = ".gitignore"; +$_q ||= 0; my %remote_opts = ( 'username=s' => \$Git::SVN::Prompt::_username, 'config-dir=s' => \$Git::SVN::Ra::config_dir, - 'no-auth-cache' => \$Git::SVN::Prompt::_no_auth_cache ); + 'no-auth-cache' => \$Git::SVN::Prompt::_no_auth_cache, + 'ignore-paths=s' => \$Git::SVN::Fetcher::_ignore_regex, + 'include-paths=s' => \$Git::SVN::Fetcher::_include_regex, + 'ignore-refs=s' => \$Git::SVN::Ra::_ignore_refs_regex ); my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent, 'authors-file|A=s' => \$_authors, + 'authors-prog=s' => \$_authors_prog, 'repack:i' => \$Git::SVN::_repack, 'noMetadata' => \$Git::SVN::_no_metadata, 'useSvmProps' => \$Git::SVN::_use_svm_props, 'useSvnsyncProps' => \$Git::SVN::_use_svnsync_props, 'log-window-size=i' => \$Git::SVN::Ra::_log_window_size, 'no-checkout' => \$_no_checkout, - 'quiet|q' => \$_q, + 'quiet|q+' => \$_q, 'repack-flags|repack-args|repack-opts=s' => \$Git::SVN::_repack_flags, + 'use-log-author' => \$Git::SVN::_use_log_author, + 'add-author-from' => \$Git::SVN::_add_author_from, + 'localtime' => \$Git::SVN::_localtime, %remote_opts ); -my ($_trunk, $_tags, $_branches); +my ($_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, '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, - 'find-copies-harder' => \$SVN::Git::Editor::_find_copies_harder, - 'l=i' => \$SVN::Git::Editor::_rename_limit, - 'copy-similarity|C=i'=> \$SVN::Git::Editor::_cp_similarity + 'rmdir' => \$Git::SVN::Editor::_rmdir, + 'find-copies-harder' => \$Git::SVN::Editor::_find_copies_harder, + 'l=i' => \$Git::SVN::Editor::_rename_limit, + 'copy-similarity|C=i'=> \$Git::SVN::Editor::_cp_similarity ); 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' => + \$Git::SVN::Fetcher::_preserve_empty_dirs, + 'placeholder-filename=s' => + \$Git::SVN::Fetcher::_placeholder_filename, %fc_opts, %init_opts } ], init => [ \&cmd_init, "Initialize a repo for tracking" . " (requires URL argument)", @@ -114,12 +188,55 @@ my %cmd = ( 'verbose|v' => \$_verbose, 'dry-run|n' => \$_dry_run, 'fetch-all|all' => \$_fetch_all, + 'commit-url=s' => \$_commit_url, + 'set-svn-props=s' => \$_set_svn_props, + '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, + 'parents' => \$_parents, + '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, + 'destination|d=s' => \$_branch_dest, + 'dry-run|n' => \$_dry_run, + 'parents' => \$_parents, + '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 } ], + 'propset' => [ \&cmd_propset, + 'Set the value of a property on a file or directory - will be set on commit', + {} ], + 'proplist' => [ \&cmd_proplist, + 'List all properties of a file or directory', + { 'revision|r=i' => \$_revision } ], 'show-ignore' => [ \&cmd_show_ignore, "Show svn:ignore listings", - { 'revision|r=i' => \$_revision } ], + { 'revision|r=i' => \$_revision + } ], + 'show-externals' => [ \&cmd_show_externals, "Show svn:externals listings", + { 'revision|r=i' => \$_revision + } ], 'multi-fetch' => [ \&cmd_multi_fetch, "Deprecated alias for $0 fetch --all", { 'revision|r=s' => \$_revision, %fc_opts } ], @@ -139,13 +256,20 @@ my %cmd = ( 'non-recursive' => \$Git::SVN::Log::non_recursive, 'authors-file|A=s' => \$_authors, 'color' => \$Git::SVN::Log::color, - 'pager=s' => \$Git::SVN::Log::pager, + 'pager=s' => \$Git::SVN::Log::pager } ], + 'find-rev' => [ \&cmd_find_rev, + "Translate between SVN revision numbers and tree-ish", + { 'B|before' => \$_before, + 'A|after' => \$_after } ], 'rebase' => [ \&cmd_rebase, "Fetch and rebase your working directory", { 'merge|m|M' => \$_merge, 'verbose|v' => \$_verbose, 'strategy|s=s' => \$_strategy, + 'local|l' => \$_local, 'fetch-all|all' => \$_fetch_all, + 'dry-run|n' => \$_dry_run, + 'preserve-merges|p' => \$_preserve_merges, %fc_opts } ], 'commit-diff' => [ \&cmd_commit_diff, 'Commit a diff between two trees', @@ -153,54 +277,105 @@ my %cmd = ( 'file|F=s' => \$_file, 'revision|r=s' => \$_revision, %cmt_opts } ], + 'info' => [ \&cmd_info, + "Show info about the latest SVN revision + on the current branch", + { 'url' => \$_url, } ], + 'blame' => [ \&Git::SVN::Log::cmd_blame, + "Show what revision and author last modified each line of a file", + { 'git-format' => \$Git::SVN::Log::_git_format } ], + 'reset' => [ \&cmd_reset, + "Undo fetches back to the specified SVN revision", + { 'revision|r=s' => \$_revision, + 'parent|p' => \$_fetch_parent } ], + 'gc' => [ \&cmd_gc, + "Compress unhandled.log files in .git/svn and remove " . + "index files in .git/svn", + {} ], ); +package FakeTerm; +sub new { + my ($class, $reason) = @_; + return bless \$reason, shift; +} +sub readline { + my $self = shift; + die "Cannot use readline on FakeTerm: $$self"; +} +package main; + +my $term; +sub term_init { + $term = eval { + require Term::ReadLine; + $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); } }; +# make sure we're always running at the top-level working directory +if ($cmd && $cmd =~ /(?:clone|init|multi-init)$/) { + $ENV{GIT_DIR} ||= ".git"; + # catch the submodule case + if (-f $ENV{GIT_DIR}) { + open(my $fh, '<', $ENV{GIT_DIR}) or + die "failed to open $ENV{GIT_DIR}: $!\n"; + $ENV{GIT_DIR} = $1 if <$fh> =~ /^gitdir: (.+)$/; + } +} else { + my ($git_dir, $cdup); + git_cmd_try { + $git_dir = command_oneline([qw/rev-parse --git-dir/]); + } "Unable to find .git directory\n"; + git_cmd_try { + $cdup = command_oneline(qw/rev-parse --show-cdup/); + chomp $cdup if ($cdup); + $cdup = "." unless ($cdup && length $cdup); + } "Already at toplevel, but $git_dir not found\n"; + $ENV{GIT_DIR} = $git_dir; + chdir $cdup or die "Unable to chdir up to '$cdup'\n"; + $_repository = Git->repository(Repository => $ENV{GIT_DIR}); +} + my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd); -read_repo_config(\%opts); -my $rv = GetOptions(%opts, 'help|H|h' => \$_help, 'version|V' => \$_version, +read_git_config(\%opts); +if ($cmd && ($cmd eq 'log' || $cmd eq 'blame')) { + Getopt::Long::Configure('pass_through'); +} +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 { $Git::SVN::no_reuse_existing = 1; $Git::SVN::default_repo_id = $_[1] }); -exit 1 if (!$rv && $cmd ne 'log'); +exit 1 if (!$rv && $cmd && $cmd ne 'log'); usage(0) if $_help; version() if $_version; usage(1) unless defined $cmd; load_authors() if $_authors; - -# make sure we're always running -unless ($cmd =~ /(?:clone|init|multi-init)$/) { - unless (-d $ENV{GIT_DIR}) { - if ($git_dir_user_set) { - die "GIT_DIR=$ENV{GIT_DIR} explicitly set, ", - "but it is not a directory\n"; - } - my $git_dir = delete $ENV{GIT_DIR}; - chomp(my $cdup = command_oneline(qw/rev-parse --show-cdup/)); - unless (length $cdup) { - die "Already at toplevel, but $git_dir ", - "not found '$cdup'\n"; - } - chdir $cdup or die "Unable to chdir up to '$cdup'\n"; - unless (-d $git_dir) { - die "$git_dir still not found after going to ", - "'$cdup'\n"; - } - $ENV{GIT_DIR} = $git_dir; - } +if (defined $_authors_prog) { + $_authors_prog = "'" . File::Spec->rel2abs($_authors_prog) . "'"; } + unless ($cmd =~ /^(?:clone|init|multi-init|commit-diff)$/) { Git::SVN::Migration::migration_check(); } @@ -208,9 +383,9 @@ Git::SVN::init_vars(); eval { Git::SVN::verify_remotes_sanity(); $cmd{$cmd}->[0]->(@ARGV); + post_fetch_checkout(); }; fatal $@ if $@; -post_fetch_checkout(); exit 0; ####################### primary functions ###################### @@ -219,7 +394,7 @@ sub usage { my $fd = $exit ? \*STDERR : \*STDOUT; print $fd <<""; git-svn - bidirectional operations between a single Subversion tree and git -Usage: $0 <command> [options] [arguments]\n +usage: git svn <command> [options] [arguments]\n print $fd "Available commands:\n" unless $cmd; @@ -227,7 +402,9 @@ Usage: $0 <command> [options] [arguments]\n next if $cmd && $cmd ne $_; next if /^multi-/; # don't show deprecated commands print $fd ' ',pack('A17',$_),$cmd{$_}->[1],"\n"; - foreach (keys %{$cmd{$_}->[2]}) { + foreach (sort keys %{$cmd{$_}->[2]}) { + # mixed-case options are for .git/config only + next if /[A-Z]/ && /^[a-z]+$/i; # prints out arguments as they should be passed: my $x = s#[:=]s$## ? '<arg>' : s#[:=]i$## ? '<num>' : ''; print $fd ' ' x 21, join(', ', map { length $_ > 1 ? @@ -245,10 +422,42 @@ 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; + term_init() unless $term; + + 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'); @@ -261,6 +470,7 @@ sub do_git_init_db { } } command_noisy(@init_db); + $_repository = Git->repository(Repository => ".git"); } my $set; my $pfx = "svn-remote.$Git::SVN::default_repo_id"; @@ -270,6 +480,21 @@ sub do_git_init_db { command_noisy('config', "$pfx.$i", $icv{$i}); $set = $i; } + my $ignore_paths_regex = \$Git::SVN::Fetcher::_ignore_regex; + command_noisy('config', "$pfx.ignore-paths", $$ignore_paths_regex) + if defined $$ignore_paths_regex; + my $include_paths_regex = \$Git::SVN::Fetcher::_include_regex; + command_noisy('config', "$pfx.include-paths", $$include_paths_regex) + if defined $$include_paths_regex; + my $ignore_refs_regex = \$Git::SVN::Ra::_ignore_refs_regex; + command_noisy('config', "$pfx.ignore-refs", $$ignore_refs_regex) + if defined $$ignore_refs_regex; + + if (defined $Git::SVN::Fetcher::_preserve_empty_dirs) { + my $fname = \$Git::SVN::Fetcher::_placeholder_filename; + command_noisy('config', "$pfx.preserve-empty-dirs", 'true'); + command_noisy('config', "$pfx.placeholder-filename", $$fname); + } } sub init_subdir { @@ -277,29 +502,44 @@ sub init_subdir { mkpath([$repo_path]) unless -d $repo_path; chdir $repo_path or die "Couldn't chdir to $repo_path: $!\n"; $ENV{GIT_DIR} = '.git'; + $_repository = Git->repository(Repository => $ENV{GIT_DIR}); } sub cmd_clone { my ($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 $_trunk || defined $_branches || defined $_tags) { + if (defined $_stdlayout) { + $_trunk = 'trunk' if (!defined $_trunk); + @_tags = 'tags' if (! @_tags); + @_branches = 'branches' if (! @_branches); + } + 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); } @@ -310,12 +550,22 @@ sub cmd_fetch { } my ($remote) = @_; if (@_ > 1) { - die "Usage: $0 fetch [--all] [svn-remote]\n"; - } - $remote ||= $Git::SVN::default_repo_id; - if ($_fetch_all) { + die "usage: $0 fetch [--all] [--parent] [svn-remote]\n"; + } + $Git::SVN::no_reuse_existing = undef; + if ($_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()); } } @@ -339,7 +589,7 @@ sub cmd_set_tree { } elsif (scalar @tmp > 1) { push @revs, reverse(command('rev-list',@tmp)); } else { - fatal "Failed to rev-parse $c\n"; + fatal "Failed to rev-parse $c"; } } my $gs = Git::SVN->new; @@ -349,120 +599,861 @@ sub cmd_set_tree { fatal "There are new revisions that were fetched ", "and need to be merged (or acknowledged) ", "before committing.\nlast rev: $r_last\n", - " current: $gs->{last_rev}\n"; + " current: $gs->{last_rev}"; } $gs->set_tree($_) foreach @revs; print "Done committing ",scalar @revs," revisions to SVN\n"; + 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, $ignore_branch) = @_; + my %result_hash = (); + + merge_revs_into_hash(\%result_hash, $mergeinfo_one); + merge_revs_into_hash(\%result_hash, $mergeinfo_two); + + delete $result_hash{$ignore_branch} if $ignore_branch; + + 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 = $gs->repos_root; + my ($target_branch) = $gs->full_pushurl =~ /^\Q$rooturl\E(.*)/; + + 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 =~ /^\Q$rooturl\E(.*)/) { + 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, + $target_branch); + + 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, + $target_branch); + } + if ($all_parents_ok and $aggregate_mergeinfo) { + return $aggregate_mergeinfo; + } + } + + return undef; +} + +sub dcommit_rebase { + my ($is_last, $current, $fetched_ref, $svn_error) = @_; + my @diff; + + if ($svn_error) { + print STDERR "\nERROR from SVN:\n", + $svn_error->expanded_message, "\n"; + } + unless ($_no_rebase) { + # we always want to rebase against the current HEAD, + # not any head that was passed to us + @diff = command('diff-tree', $current, + $fetched_ref, '--'); + my @finish; + if (@diff) { + @finish = rebase_cmd(); + print STDERR "W: $current and ", $fetched_ref, + " differ, using @finish:\n", + join("\n", @diff), "\n"; + } elsif ($is_last) { + print "No changes between ", $current, " and ", + $fetched_ref, + "\nResetting to the latest ", + $fetched_ref, "\n"; + @finish = qw/reset --mixed/; + } + command_noisy(@finish, $fetched_ref) if @finish; + } + if ($svn_error) { + die "ERROR: Not all changes have been committed into SVN" + .($_no_rebase ? ".\n" : ", however the committed\n" + ."ones (if any) seem to be successfully integrated " + ."into the working tree.\n") + ."Please see the above messages for details.\n"; + } + return @diff; } 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, $uuid) = working_head_info($head, \@refs); - my $c = $refs[-1]; - unless (defined $url && defined $rev && defined $uuid) { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD', \@refs); + unless ($gs) { die "Unable to determine upstream SVN information from ", - "$head history\n"; - } - my $gs = Git::SVN->find_by_url($url); - my $last_rev; - foreach my $d (@refs) { - if (!verify_ref("$d~1")) { - fatal "Commit $d\n", - "has no parent commit, and therefore ", - "nothing to diff against.\n", - "You should be working from a repository ", - "originally created by git-svn\n"; + "$head history.\nPerhaps the repository is empty."; + } + + if (defined $_commit_url) { + $url = $_commit_url; + } else { + $url = eval { command_oneline('config', '--get', + "svn-remote.$gs->{repo_id}.commiturl") }; + if (!$url) { + $url = $gs->full_pushurl + } + } + + my $last_rev = $_revision if defined $_revision; + if ($url) { + print "Committing to $url ...\n"; + } + my ($linear_refs, $parents) = linearize_history($gs, \@refs); + if ($_no_rebase && scalar(@$linear_refs) > 1) { + warn "Attempting to commit more than one change while ", + "--no-rebase is enabled.\n", + "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 =~ /^\Q$rooturl\E(.*)/) { + # 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; + my $current_head = command_oneline(qw/rev-parse HEAD/); + Git::SVN::remove_username($expect_url); + if (defined($_merge_info)) { + $_merge_info =~ tr{ }{\n}; + } + while (1) { + my $d = shift @$linear_refs or last; unless (defined $last_rev) { (undef, $last_rev, undef) = cmt_metadata("$d~1"); unless (defined $last_rev) { fatal "Unable to extract revision information ", - "from commit $d~1\n"; + "from commit $d~1"; } } if ($_dry_run) { 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), + config => SVN::Core::config_get_config( + $Git::SVN::Ra::config_dir + ), tree_a => "$d~1", tree_b => $d, editor_cb => sub { print "Committed r$_[0]\n"; - $last_rev = $_[0]; }, + $cmt_rev = $_[0]; + }, + mergeinfo => $_merge_info, svn_path => ''); - if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) { + + my $err_handler = $SVN::Error::handler; + $SVN::Error::handler = sub { + my $err = shift; + dcommit_rebase(1, $current_head, $gs->refname, + $err); + }; + + if (!Git::SVN::Editor->new(\%ed_opts)->apply_diff) { print "No changes\n$d~1 == $d\n"; + } elsif ($parents->{$d} && @{$parents->{$d}}) { + $gs->{inject_parents_dcommit}->{$cmt_rev} = + $parents->{$d}; + } + $_fetch_all ? $gs->fetch_all : $gs->fetch; + $SVN::Error::handler = $err_handler; + $last_rev = $cmt_rev; + next if $_no_rebase; + + my @diff = dcommit_rebase(@$linear_refs == 0, $d, + $gs->refname, undef); + + $rewritten_parent = command_oneline(qw/rev-parse/, + $gs->refname); + + if (@diff) { + $current_head = command_oneline(qw/rev-parse + HEAD/); + @refs = (); + my ($url_, $rev_, $uuid_, $gs_) = + working_head_info('HEAD', \@refs); + my ($linear_refs_, $parents_) = + linearize_history($gs_, \@refs); + if (scalar(@$linear_refs) != + scalar(@$linear_refs_)) { + fatal "# of revisions changed ", + "\nbefore:\n", + join("\n", @$linear_refs), + "\n\nafter:\n", + join("\n", @$linear_refs_), "\n", + 'If you are attempting to commit ', + "merges, try running:\n\t", + 'git rebase --interactive', + '--preserve-merges ', + $gs->refname, + "\nBefore dcommitting"; + } + if ($url_ ne $expect_url) { + if ($url_ eq $gs->metadata_url) { + print + "Accepting rewritten URL:", + " $url_\n"; + } else { + fatal + "URL mismatch after rebase:", + " $url_ != $expect_url"; + } + } + if ($uuid_ ne $uuid) { + fatal "uuid mismatch after rebase: ", + "$uuid_ != $uuid"; + } + # remap parents + my (%p, @l, $i); + for ($i = 0; $i < scalar @$linear_refs; $i++) { + my $new = $linear_refs_->[$i] or next; + $p{$new} = + $parents->{$linear_refs->[$i]}; + push @l, $new; + } + $parents = \%p; + $linear_refs = \@l; + undef $last_rev; } } } - return if $_dry_run; - unless ($gs) { - warn "Could not determine fetch information for $url\n", - "Will not attempt to fetch and rebase commits.\n", - "This probably means you have useSvmProps and should\n", - "now resync your SVN::Mirror repository.\n"; - return; + + if ($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 $gs->{index}; +} + +sub cmd_branch { + my ($branch_name, $head) = @_; + + unless (defined $branch_name && length $branch_name) { + die(($_tag ? "tag" : "branch") . " name required\n"); + } + $head ||= '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 $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}) { + my $re = Git::SVN::Editor::glob2pat($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"; + } + } } - $_fetch_all ? $gs->fetch_all : $gs->fetch; - # we always want to rebase against the current HEAD, not any - # head that was passed to us - my @diff = command('diff-tree', 'HEAD', $gs->refname, '--'); - my @finish; - if (@diff) { - @finish = rebase_cmd(); - print STDERR "W: HEAD and ", $gs->refname, " differ, ", - "using @finish:\n", "@diff"; + my ($lft, $rgt) = @{ $glob->{path} }{qw/left right/}; + my $url; + if (defined $_commit_url) { + $url = $_commit_url; } else { - print "No changes between current HEAD and ", - $gs->refname, "\nResetting to the latest ", - $gs->refname, "\n"; - @finish = qw/reset --mixed/; + $url = eval { command_oneline('config', '--get', + "svn-remote.$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(); + require SVN::Client; + + my $ctx = SVN::Client->new( + config => SVN::Core::config_get_config( + $Git::SVN::Ra::config_dir + ), + log_msg => sub { + ${ $_[0] } = defined $_message + ? $_message + : 'Create ' . ($_tag ? 'tag ' : 'branch ' ) + . $branch_name; + }, + ); + + eval { + $ctx->ls($dst, 'HEAD', 0); + } and die "branch ${branch_name} already exists\n"; + + if ($_parents) { + mk_parent_dirs($ctx, $dst); } - command_noisy(@finish, $gs->refname); + + print "Copying ${src} at r${rev} to ${dst}...\n"; + $ctx->copy($src, $rev, $dst) + unless $_dry_run; + + $gs->fetch_all; +} + +sub mk_parent_dirs { + my ($ctx, $parent) = @_; + $parent =~ s{/[^/]*$}{}; + + if (!eval{$ctx->ls($parent, 'HEAD', 0)}) { + mk_parent_dirs($ctx, $parent); + print "Creating parent folder ${parent} ...\n"; + $ctx->mkdir($parent) unless $_dry_run; + } +} + +sub cmd_find_rev { + my $revision_or_hash = shift or die "SVN or git revision required ", + "as a command-line argument\n"; + my $result; + if ($revision_or_hash =~ /^r\d+$/) { + my $head = shift; + $head ||= 'HEAD'; + my @refs; + my (undef, undef, $uuid, $gs) = working_head_info($head, \@refs); + unless ($gs) { + die "Unable to determine upstream SVN information from ", + "$head history\n"; + } + my $desired_revision = substr($revision_or_hash, 1); + if ($_before) { + $result = $gs->find_rev_before($desired_revision, 1); + } elsif ($_after) { + $result = $gs->find_rev_after($desired_revision, 1); + } else { + $result = $gs->rev_map_get($desired_revision, $uuid); + } + } else { + my (undef, $rev, undef) = cmt_metadata($revision_or_hash); + $result = $rev; + } + print "$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 = (working_head_info('HEAD'))[0]; - if (!defined $url) { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + unless ($gs) { die "Unable to determine upstream SVN information from ", "working tree history\n"; } - - my $gs = Git::SVN->find_by_url($url); + if ($_dry_run) { + print "Remote Branch: " . $gs->refname . "\n"; + print "SVN URL: " . $url . "\n"; + return; + } if (command(qw/diff-index HEAD --/)) { - print STDERR "Cannot rebase with uncommited changes:\n"; + print STDERR "Cannot rebase with uncommitted changes:\n"; command_noisy('status'); exit 1; } - $_fetch_all ? $gs->fetch_all : $gs->fetch; + unless ($_local) { + # rebase will checkout for us, so no need to do it explicitly + $_no_checkout = 'true'; + $_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 { - my $url = (::working_head_info('HEAD'))[0]; - my $gs = Git::SVN->find_by_url($url) || Git::SVN->new; + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + $gs ||= Git::SVN->new; + my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum); + $gs->prop_walk($gs->path, $r, sub { + my ($gs, $path, $props) = @_; + 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 "$s\n"; + }); +} + +sub cmd_show_externals { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + $gs ||= Git::SVN->new; + my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum); + $gs->prop_walk($gs->path, $r, sub { + my ($gs, $path, $props) = @_; + print STDOUT "\n# $path\n"; + my $s = $props->{'svn:externals'} or return; + $s =~ s/[\r\n]+/\n/g; + chomp $s; + $s =~ s#^#$path#gm; + print STDOUT "$s\n"; + }); +} + +sub cmd_create_ignore { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + $gs ||= Git::SVN->new; + my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum); + $gs->prop_walk($gs->path, $r, sub { + my ($gs, $path, $props) = @_; + # $path is of the form /path/to/dir/ + $path = '.' . $path; + # SVN can have attributes on empty directories, + # which git won't track + mkpath([$path]) unless -d $path; + my $ignore = $path . '.gitignore'; + my $s = $props->{'svn:ignore'} or return; + 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. + $s =~ s#^#/#gm; + print GITIGNORE "$s\n"; + close(GITIGNORE) + or fatal("Failed to close `$ignore': $!"); + command_noisy('add', '-f', $ignore); + }); +} + +sub cmd_mkdirs { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + $gs ||= Git::SVN->new; + $gs->mkemptydirs($_revision); +} + +# get_svnprops(PATH) +# ------------------ +# Helper for cmd_propget and cmd_proplist below. +sub get_svnprops { + my $path = shift; + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + $gs ||= Git::SVN->new; + + # prefix THE PATH by the sub-directory from which the user + # invoked us. + $path = $cmd_dir_prefix . $path; + fatal("No such file or directory: $path") unless -e $path; + my $is_dir = -d $path ? 1 : 0; + $path = join_paths($gs->path, $path); + + # canonicalize the path (otherwise libsvn will abort or fail to + # find the file) + $path = canonicalize_path($path); + my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum); - $gs->traverse_ignore(\*STDOUT, $gs->{path}, $r); + my $props; + if ($is_dir) { + (undef, undef, $props) = $gs->ra->get_dir($path, $r); + } + else { + (undef, $props) = $gs->ra->get_file($path, $r, undef); + } + return $props; +} + +# cmd_propget (PROP, PATH) +# ------------------------ +# Print the SVN property PROP for PATH. +sub cmd_propget { + my ($prop, $path) = @_; + $path = '.' if not defined $path; + usage(1) if not defined $prop; + my $props = get_svnprops($path); + if (not defined $props->{$prop}) { + fatal("`$path' does not have a `$prop' SVN property."); + } + print $props->{$prop} . "\n"; +} + +# cmd_propset (PROPNAME, PROPVAL, PATH) +# ------------------------ +# Adjust the SVN property PROPNAME to PROPVAL for PATH. +sub cmd_propset { + my ($propname, $propval, $path) = @_; + $path = '.' if not defined $path; + $path = $cmd_dir_prefix . $path; + usage(1) if not defined $propname; + usage(1) if not defined $propval; + my $file = basename($path); + my $dn = dirname($path); + my $cur_props = Git::SVN::Editor::check_attr( "svn-properties", $path ); + my @new_props; + if (!$cur_props || $cur_props eq "unset" || $cur_props eq "" || $cur_props eq "set") { + push @new_props, "$propname=$propval"; + } else { + # TODO: handle combining properties better + my @props = split(/;/, $cur_props); + my $replaced_prop; + foreach my $prop (@props) { + # Parse 'name=value' syntax and set the property. + if ($prop =~ /([^=]+)=(.*)/) { + my ($n,$v) = ($1,$2); + if ($n eq $propname) { + $v = $propval; + $replaced_prop = 1; + } + push @new_props, "$n=$v"; + } + } + if (!$replaced_prop) { + push @new_props, "$propname=$propval"; + } + } + my $attrfile = "$dn/.gitattributes"; + open my $attrfh, '>>', $attrfile or die "Can't open $attrfile: $!\n"; + # TODO: don't simply append here if $file already has svn-properties + my $new_props = join(';', @new_props); + print $attrfh "$file svn-properties=$new_props\n" or + die "write to $attrfile: $!\n"; + close $attrfh or die "close $attrfile: $!\n"; +} + +# cmd_proplist (PATH) +# ------------------- +# Print the list of SVN properties for PATH. +sub cmd_proplist { + my $path = shift; + $path = '.' if not defined $path; + my $props = get_svnprops($path); + print "Properties on '$path':\n"; + foreach (sort keys %{$props}) { + print " $_\n"; + } } sub cmd_multi_init { my $url = shift; - unless (defined $_trunk || defined $_branches || defined $_tags) { + unless (defined $_trunk || @_branches || @_tags) { usage(1); } - $_prefix = '' unless defined $_prefix; + + $_prefix = 'origin/' 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) { @@ -472,13 +1463,18 @@ 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}) { @@ -490,18 +1486,18 @@ sub cmd_multi_fetch { # this command is special because it requires no metadata sub cmd_commit_diff { my ($ta, $tb, $url) = @_; - my $usage = "Usage: $0 commit-diff -r<revision> ". - "<tree-ish> <tree-ish> [<URL>]\n"; + my $usage = "usage: $0 commit-diff -r<revision> ". + "<tree-ish> <tree-ish> [<URL>]"; fatal($usage) if (!defined $ta || !defined $tb); - my $svn_path; + my $svn_path = ''; if (!defined $url) { my $gs = eval { Git::SVN->new }; if (!$gs) { fatal("Needed URL or usable git-svn --id in ", "the command-line\n", $usage); } - $url = $gs->{url}; - $svn_path = $gs->{path}; + $url = $gs->url; + $svn_path = $gs->path; } unless (defined $_revision) { fatal("-r|--revision is a required argument\n", $usage); @@ -509,7 +1505,7 @@ sub cmd_commit_diff { if (defined $_message && defined $_file) { fatal("Both --message/-m and --file/-F specified ", "for the commit message.\n", - "I have no idea what you mean\n"); + "I have no idea what you mean"); } if (defined $_file) { $_message = file_to_s($_file); @@ -517,7 +1513,6 @@ sub cmd_commit_diff { $_message ||= get_commit_entry($tb)->{log}; } my $ra ||= Git::SVN::Ra->new($url); - $svn_path ||= $ra->{svn_path}; my $r = $_revision; if ($r eq 'HEAD') { $r = $ra->get_latest_revnum; @@ -531,11 +1526,179 @@ sub cmd_commit_diff { tree_b => $tb, editor_cb => sub { print "Committed r$_[0]\n" }, svn_path => $svn_path ); - if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) { + if (!Git::SVN::Editor->new(\%ed_opts)->apply_diff) { print "No changes\n$ta == $tb\n"; } } +sub cmd_info { + my $path_arg = defined($_[0]) ? $_[0] : '.'; + my $path = $path_arg; + if (File::Spec->file_name_is_absolute($path)) { + $path = canonicalize_path($path); + + my $toplevel = eval { + my @cmd = qw/rev-parse --show-toplevel/; + command_oneline(\@cmd, STDERR => 0); + }; + + # remove $toplevel from the absolute path: + my ($vol, $dirs, $file) = File::Spec->splitpath($path); + my (undef, $tdirs, $tfile) = File::Spec->splitpath($toplevel); + my @dirs = File::Spec->splitdir($dirs); + my @tdirs = File::Spec->splitdir($tdirs); + pop @dirs if $dirs[-1] eq ''; + pop @tdirs if $tdirs[-1] eq ''; + push @dirs, $file; + push @tdirs, $tfile; + while (@tdirs && @dirs && $tdirs[0] eq $dirs[0]) { + shift @dirs; + shift @tdirs; + } + $dirs = File::Spec->catdir(@dirs); + $path = File::Spec->catpath($vol, $dirs); + + $path = canonicalize_path($path); + } else { + $path = canonicalize_path($cmd_dir_prefix . $path); + } + if (exists $_[1]) { + die "Too many arguments specified\n"; + } + + my ($file_type, $diff_status) = find_file_type_and_diff_status($path); + + if (!$file_type && !$diff_status) { + print STDERR "svn: '$path' is not under version control\n"; + exit 1; + } + + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + unless ($gs) { + die "Unable to determine upstream SVN information from ", + "working tree history\n"; + } + + # canonicalize_path() will return "" to make libsvn 1.5.x happy, + $path = "." if $path eq ""; + + my $full_url = canonicalize_url( add_path_to_url( $url, $path ) ); + + if ($_url) { + print "$full_url\n"; + return; + } + + my $result = "Path: $path_arg\n"; + $result .= "Name: " . basename($path) . "\n" if $file_type ne "dir"; + $result .= "URL: $full_url\n"; + + eval { + my $repos_root = $gs->repos_root; + Git::SVN::remove_username($repos_root); + $result .= "Repository Root: " . canonicalize_url($repos_root) . "\n"; + }; + if ($@) { + $result .= "Repository Root: (offline)\n"; + } + ::_req_svn(); + $result .= "Repository UUID: $uuid\n" unless $diff_status eq "A" && + (::compare_svn_version('1.5.4') <= 0 || $file_type ne "dir"); + $result .= "Revision: " . ($diff_status eq "A" ? 0 : $rev) . "\n"; + + $result .= "Node Kind: " . + ($file_type eq "dir" ? "directory" : "file") . "\n"; + + my $schedule = $diff_status eq "A" + ? "add" + : ($diff_status eq "D" ? "delete" : "normal"); + $result .= "Schedule: $schedule\n"; + + if ($diff_status eq "A") { + print $result, "\n"; + return; + } + + my ($lc_author, $lc_rev, $lc_date_utc); + my @args = Git::SVN::Log::git_svn_log_cmd($rev, $rev, "--", $path); + my $log = command_output_pipe(@args); + my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/; + while (<$log>) { + if (/^${esc_color}author (.+) <[^>]+> (\d+) ([\-\+]?\d+)$/o) { + $lc_author = $1; + $lc_date_utc = Git::SVN::Log::parse_git_date($2, $3); + } elsif (/^${esc_color} (git-svn-id:.+)$/o) { + (undef, $lc_rev, undef) = ::extract_metadata($1); + } + } + close $log; + + Git::SVN::Log::set_local_timezone(); + + $result .= "Last Changed Author: $lc_author\n"; + $result .= "Last Changed Rev: $lc_rev\n"; + $result .= "Last Changed Date: " . + Git::SVN::Log::format_svn_date($lc_date_utc) . "\n"; + + if ($file_type ne "dir") { + my $text_last_updated_date = + ($diff_status eq "D" ? $lc_date_utc : (stat $path)[9]); + $result .= + "Text Last Updated: " . + Git::SVN::Log::format_svn_date($text_last_updated_date) . + "\n"; + my $checksum; + if ($diff_status eq "D") { + my ($fh, $ctx) = + command_output_pipe(qw(cat-file blob), "HEAD:$path"); + if ($file_type eq "link") { + my $file_name = <$fh>; + $checksum = md5sum("link $file_name"); + } else { + $checksum = md5sum($fh); + } + command_close_pipe($fh, $ctx); + } elsif ($file_type eq "link") { + my $file_name = + command(qw(cat-file blob), "HEAD:$path"); + $checksum = + md5sum("link " . $file_name); + } else { + open FILE, "<", $path or die $!; + $checksum = md5sum(\*FILE); + close FILE or die $!; + } + $result .= "Checksum: " . $checksum . "\n"; + } + + 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 { + require File::Find; + if (!can_compress()) { + warn "Compress::Zlib could not be found; unhandled.log " . + "files will not be compressed.\n"; + } + File::Find::find({ wanted => \&gc_directory, no_chdir => 1}, + "$ENV{GIT_DIR}/svn"); +} + ########################### utility functions ######################### sub rebase_cmd { @@ -543,37 +1706,52 @@ sub rebase_cmd { push @cmd, '-v' if $_verbose; push @cmd, qw/--merge/ if $_merge; push @cmd, "--strategy=$_strategy" if $_strategy; + push @cmd, "--preserve-merges" if $_preserve_merges; @cmd; } sub post_fetch_checkout { return if $_no_checkout; + return if verify_ref('HEAD^0'); my $gs = $Git::SVN::_head or return; - return if verify_ref('refs/heads/master^0'); - 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')); + # 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; + } + } + + command_noisy(qw(update-ref HEAD), $gs->refname); + return unless verify_ref('HEAD^0'); return if $ENV{GIT_DIR} !~ m#^(?:.*/)?\.git$#; my $index = $ENV{GIT_INDEX_FILE} || "$ENV{GIT_DIR}/index"; return if -f $index; - chomp(my $bare = `git config --bool --get core.bare`); - return if $bare eq 'true'; + return if command_oneline(qw/rev-parse --is-inside-work-tree/) eq 'false'; return if command_oneline(qw/rev-parse --is-inside-git-dir/) eq 'true'; 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 { my ($url, $path) = @_; - $path =~ s#/+$##; + $path = canonicalize_path($path); + + # If the path is not a URL... if ($path !~ m#^[a-z\+]+://#) { if (!defined $url || $url !~ m#^[a-z\+]+://#) { fatal("E: '$path' is not a complete URL ", - "and a separate URL is not specified\n"); + "and a separate URL is not specified"); } return ($url, $path); } @@ -586,7 +1764,7 @@ sub complete_url_ls_init { print STDERR "W: $switch not specified\n"; return; } - $repo_path =~ s#/+$##; + $repo_path = canonicalize_path($repo_path); if ($repo_path =~ m#^[a-z\+]+://#) { $ra = Git::SVN::Ra->new($repo_path); $repo_path = ''; @@ -594,27 +1772,32 @@ sub complete_url_ls_init { $repo_path =~ s#^/+##; unless ($ra) { fatal("E: '$repo_path' is not a complete URL ", - "and a separate URL is not specified\n"); + "and a separate URL is not specified"); } } - my $url = $ra->{url}; + my $url = $ra->url; my $gs = Git::SVN->init($url, undef, undef, undef, 1); my $k = "svn-remote.$gs->{repo_id}.url"; my $orig_url = eval { command_oneline(qw/config --get/, $k) }; - if ($orig_url && ($orig_url ne $gs->{url})) { + if ($orig_url && ($orig_url ne $gs->url)) { die "$k already set: $orig_url\n", - "wanted to set to: $gs->{url}\n"; + "wanted to set to: $gs->url\n"; } - command_oneline('config', $k, $gs->{url}) unless $orig_url; - my $remote_path = "$ra->{svn_path}/$repo_path/*"; - $remote_path =~ s#/+#/#g; + command_oneline('config', $k, $gs->url) unless $orig_url; + + my $remote_path = join_paths( $gs->path, $repo_path ); + $remote_path =~ s{%([0-9A-F]{2})}{chr hex($1)}ieg; $remote_path =~ s#^/##g; + $remote_path .= "/*" if $remote_path !~ /\*/; my ($n) = ($switch =~ /^--(\w+)/); if (length $pfx && $pfx !~ m#/$#) { die "--prefix='$pfx' must have a trailing slash '/'\n"; } - command_noisy('config', "svn-remote.$gs->{repo_id}.$n", - "$remote_path:refs/remotes/$pfx*"); + command_noisy('config', + '--add', + "svn-remote.$gs->{repo_id}.$n", + "$remote_path:refs/remotes/$pfx*" . + ('/*' x (($remote_path =~ tr/*/*/) - 1)) ); } sub verify_ref { @@ -656,30 +1839,63 @@ sub get_commit_entry { my ($msg_fh, $ctx) = command_output_pipe('cat-file', $type, $treeish); my $in_msg = 0; + my $author; + my $saw_from = 0; + my $msgbuf = ""; while (<$msg_fh>) { if (!$in_msg) { - $in_msg = 1 if (/^\s*$/); + $in_msg = 1 if (/^$/); + $author = $1 if (/^author (.*>)/); } elsif (/^git-svn-id: /) { # skip this for now, we regenerate the # correct one on re-fetch anyways # TODO: set *:merge properties or like... } else { - print $log_fh $_ or croak $!; + if (/^From:/ || /^Signed-off-by:/) { + $saw_from = 1; + } + $msgbuf .= $_; } } + $msgbuf =~ s/\s+$//s; + if ($Git::SVN::_add_author_from && defined($author) + && !$saw_from) { + $msgbuf .= "\n\nFrom: $author"; + } + print $log_fh $msgbuf or croak $!; command_close_pipe($msg_fh, $ctx); } 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 $!; - open $log_fh, '<', $commit_msg or croak $!; - { local $/; chomp($log_entry{log} = <$log_fh>); } - close $log_fh 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>); + + 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; \%log_entry; } @@ -708,7 +1924,7 @@ sub load_authors { my $log = $cmd eq 'log'; while (<$authors>) { chomp; - next unless /^(\S+?|\(no author\))\s*=\s*(.+?)\s*<(.+)>\s*$/; + next unless /^(.+?|\(no author\))\s*=\s*(.+?)\s*<(.*)>\s*$/; my ($user, $name, $email) = ($1, $2, $3); if ($log) { $Git::SVN::Log::rusers{"$name <$email>"} = $user; @@ -720,8 +1936,7 @@ 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) { @@ -732,7 +1947,7 @@ sub read_repo_config { my $v = $opts->{$o}; my ($key) = ($o =~ /^([a-zA-Z\-]+)/); $key =~ s/-//g; - my $arg = 'git-config'; + my $arg = 'git config'; $arg .= ' --int' if ($o =~ /[:=]i$/); $arg .= ' --bool' if ($o !~ /[:=][sfi]$/); if (ref $v eq 'ARRAY') { @@ -750,12 +1965,12 @@ sub read_repo_config { sub extract_metadata { my $id = shift or return (undef, undef, undef); - my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+) - \s([a-f\d\-]+)$/x); + my ($url, $rev, $uuid) = ($id =~ /^\s*git-svn-id:\s+(.*)\@(\d+) + \s([a-f\d\-]+)$/ix); if (!defined $rev || !$uuid || !$url) { # some of the original repositories I made had # identifiers like this: - ($rev, $uuid) = ($id =~/^git-svn-id:\s(\d+)\@([a-f\d\-]+)/); + ($rev, $uuid) = ($id =~/^\s*git-svn-id:\s(\d+)\@([a-f\d\-]+)/i); } return ($url, $rev, $uuid); } @@ -765,3101 +1980,179 @@ sub cmt_metadata { command(qw/cat-file commit/, shift)))[-1]); } -sub working_head_info { - my ($head, $refs) = @_; - my ($url, $rev, $uuid); - my ($fh, $ctx) = command_output_pipe('rev-list', $head); - while (<$fh>) { - chomp; - ($url, $rev, $uuid) = cmt_metadata($_); - last if (defined $url && defined $rev && defined $uuid); - unshift @$refs, $_ if $refs; - } - close $fh; # break the pipe - ($url, $rev, $uuid); -} +sub cmt_sha2rev_batch { + my %s2r; + my ($pid, $in, $out, $ctx) = command_bidi_pipe(qw/cat-file --batch/); + my $list = shift; -package Git::SVN; -use strict; -use warnings; -use vars qw/$default_repo_id $default_ref_id $_no_metadata $_follow_parent - $_repack $_repack_flags $_use_svm_props $_head - $_use_svnsync_props $no_reuse_existing/; -use Carp qw/croak/; -use File::Path qw/mkpath/; -use File::Copy qw/copy/; -use IPC::Open3; + foreach my $sha (@{$list}) { + my $first = 1; + my $size = 0; + print $out $sha, "\n"; -my $_repack_nr; -# properties that we do not log: -my %SKIP_PROP; -BEGIN { - %SKIP_PROP = map { $_ => 1 } qw/svn:wc:ra_dav:version-url - svn:special svn:executable - svn:entry:committed-rev - svn:entry:last-author - svn:entry:uuid - svn:entry:committed-date/; - - # 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 - my $e; - foreach (qw/follow_parent no_metadata use_svm_props - use_svnsync_props/) { - my $key = $_; - $key =~ tr/_//d; - $e .= "sub $_ { - my (\$self) = \@_; - return \$self->{-$_} if exists \$self->{-$_}; - my \$k = \"svn-remote.\$self->{repo_id}\.$key\"; - eval { command_oneline(qw/config --get/, \$k) }; - if (\$@) { - \$self->{-$_} = \$Git::SVN::_$_; - } else { - my \$v = command_oneline(qw/config --bool/,\$k); - \$self->{-$_} = \$v eq 'false' ? 0 : 1; - } - return \$self->{-$_} }\n"; - } - $e .= "1;\n"; - eval $e or die $@; -} - -my %LOCKFILES; -END { unlink keys %LOCKFILES if %LOCKFILES } - -sub resolve_local_globs { - my ($url, $fetch, $glob_spec) = @_; - 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}$#; - my $p = $1; - my $pathname = $path->full_path($p); - my $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"; - } - my $u = (::cmt_metadata("refs/remotes/$refname"))[0]; - $u =~ s!^\Q$url\E(/|$)!! or die - "refs/remotes/$refname: '$url' not found in '$u'\n"; - if ($pathname ne $u) { - warn "W: Refspec glob conflict ", - "(ref: refs/remotes/$refname):\n", - "expected path: $pathname\n", - " real path: $u\n", - "Continuing ahead with $u\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; } - } else { - $fetch->{$pathname} = $refname; - } - } -} - -sub parse_revision_argument { - my ($base, $head) = @_; - if (!defined $::_revision || $::_revision eq 'BASE:HEAD') { - return ($base, $head); - } - return ($1, $2) if ($::_revision =~ /^(\d+):(\d+)$/); - return ($::_revision, $::_revision) if ($::_revision =~ /^\d+$/); - return ($head, $head) if ($::_revision eq 'HEAD'); - return ($base, $1) if ($::_revision =~ /^BASE:(\d+)$/); - return ($1, $head) if ($::_revision =~ /^(\d+):HEAD$/); - die "revision argument: $::_revision not understood by git-svn\n"; -} - -sub fetch_all { - my ($repo_id, $remotes) = @_; - if (ref $repo_id) { - my $gs = $repo_id; - $repo_id = undef; - $repo_id = $gs->{repo_id}; - } - $remotes ||= read_all_remotes(); - my $remote = $remotes->{$repo_id} or - die "[svn-remote \"$repo_id\"] unknown\n"; - my $fetch = $remote->{fetch}; - my $url = $remote->{url} or die "svn-remote.$repo_id.url not defined\n"; - my (@gs, @globs); - my $ra = Git::SVN::Ra->new($url); - my $uuid = $ra->get_uuid; - my $head = $ra->get_latest_revnum; - 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}; - my $max_rev = eval { tmp_config(qw/--int --get/, - "svn-remote.$repo_id.${t}-maxRev") }; - if (defined $max_rev && ($max_rev < $base)) { - $base = $max_rev; - } elsif (!defined $max_rev) { - $base = 0; - } - } - - if ($fetch) { - foreach my $p (sort keys %$fetch) { - my $gs = Git::SVN->new($fetch->{$p}, $repo_id, $p); - my $lr = $gs->rev_db_max; - if (defined $lr) { - $base = $lr if ($lr < $base); - } - push @gs, $gs; - } - } - - ($base, $head) = parse_revision_argument($base, $head); - $ra->gs_fetch_loop_common($base, $head, \@gs, \@globs); -} - -sub read_all_remotes { - my $r = {}; - foreach (grep { s/^svn-remote\.// } command(qw/config -l/)) { - if (m!^(.+)\.fetch=\s*(.*)\s*:\s*refs/remotes/(.+)\s*$!) { - $r->{$1}->{fetch}->{$2} = $3; - } elsif (m!^(.+)\.url=\s*(.*)\s*$!) { - $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($g) }; - if (length($rs->{ref}->{right}) != 0) { - die "The '*' glob character must be the last ", - "character of '$g'\n"; - } - } - } - $r; -} - -sub init_vars { - if (defined $_repack) { - $_repack = 1000 if ($_repack <= 0); - $_repack_nr = $_repack; - $_repack_flags ||= '-d'; - } -} - -sub verify_remotes_sanity { - return unless -d $ENV{GIT_DIR}; - my %seen; - foreach (command(qw/config -l/)) { - if (m!^svn-remote\.(?:.+)\.fetch=.*:refs/remotes/(\S+)\s*$!) { - if ($seen{$1}) { - die "Remote ref refs/remote/$1 is tracked by", - "\n \"$_\"\nand\n \"$seen{$1}\"\n", - "Please resolve this ambiguity in ", - "your git configuration file before ", - "continuing\n"; - } - $seen{$1} = $_; - } - } -} - -# we allow more chars than remotes2config.sh... -sub sanitize_remote_name { - my ($name) = @_; - $name =~ tr{A-Za-z0-9:,/+-}{.}c; - $name; -} - -sub find_existing_remote { - my ($url, $remotes) = @_; - return undef if $no_reuse_existing; - my $existing; - foreach my $repo_id (keys %$remotes) { - my $u = $remotes->{$repo_id}->{url} or next; - next if $u ne $url; - $existing = $repo_id; - last; - } - $existing; -} - -sub init_remote_config { - my ($self, $url, $no_write) = @_; - $url =~ s!/+$!!; # strip trailing slash - my $r = read_all_remotes(); - my $existing = find_existing_remote($url, $r); - if ($existing) { - unless ($no_write) { - print STDERR "Using existing ", - "[svn-remote \"$existing\"]\n"; - } - $self->{repo_id} = $existing; - } else { - my $min_url = Git::SVN::Ra->new($url)->minimize_url; - $existing = find_existing_remote($min_url, $r); - if ($existing) { - unless ($no_write) { - print STDERR "Using existing ", - "[svn-remote \"$existing\"]\n"; - } - $self->{repo_id} = $existing; - } - if ($min_url ne $url) { - unless ($no_write) { - print STDERR "Using higher level of URL: ", - "$url => $min_url\n"; - } - my $old_path = $self->{path}; - $self->{path} = $url; - $self->{path} =~ s!^\Q$min_url\E(/|$)!!; - if (length $old_path) { - $self->{path} .= "/$old_path"; - } - $url = $min_url; - } - } - my $orig_url; - if (!$existing) { - # verify that we aren't overwriting anything: - $orig_url = eval { - command_oneline('config', '--get', - "svn-remote.$self->{repo_id}.url") - }; - if ($orig_url && ($orig_url ne $url)) { - die "svn-remote.$self->{repo_id}.url already set: ", - "$orig_url\nwanted to set to: $url\n"; - } - } - my ($xrepo_id, $xpath) = find_ref($self->refname); - if (defined $xpath) { - die "svn-remote.$xrepo_id.fetch already set to track ", - "$xpath:refs/remotes/", $self->refname, "\n"; - } - unless ($no_write) { - command_noisy('config', - "svn-remote.$self->{repo_id}.url", $url); - command_noisy('config', '--add', - "svn-remote.$self->{repo_id}.fetch", - "$self->{path}:".$self->refname); - } - $self->{url} = $url; -} - -sub find_by_url { # repos_root and, path are optional - my ($class, $full_url, $repos_root, $path) = @_; - return undef unless defined $full_url; - my $remotes = read_all_remotes(); - if (defined $full_url && defined $repos_root && !defined $path) { - $path = $full_url; - $path =~ s#^\Q$repos_root\E(?:/|$)##; - } - foreach my $repo_id (keys %$remotes) { - my $u = $remotes->{$repo_id}->{url} or next; - 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}->{$_}); - } - my $p = $path; - unless (defined $p) { - $p = $full_url; - $p =~ s#^\Q$u\E(?:/|$)## or next; - } - foreach my $f (keys %$fetch) { - next if $f ne $p; - return Git::SVN->new($fetch->{$f}, $repo_id, $f); - } - } - undef; -} - -sub init { - my ($class, $url, $path, $repo_id, $ref_id, $no_write) = @_; - my $self = _new($class, $repo_id, $ref_id, $path); - if (defined $url) { - $self->init_remote_config($url, $no_write); - } - $self; -} - -sub find_ref { - my ($ref_id) = @_; - foreach (command(qw/config -l/)) { - next unless m!^svn-remote\.(.+)\.fetch= - \s*(.*)\s*:\s*refs/remotes/(.+)\s*$!x; - my ($repo_id, $path, $ref) = ($1, $2, $3); - if ($ref eq $ref_id) { - $path = '' if ($path =~ m#^\./?#); - return ($repo_id, $path); - } - } - (undef, undef, undef); -} - -sub new { - my ($class, $ref_id, $repo_id, $path) = @_; - if (defined $ref_id && !defined $repo_id && !defined $path) { - ($repo_id, $path) = find_ref($ref_id); - if (!defined $repo_id) { - die "Could not find a \"svn-remote.*.fetch\" key ", - "in the repository configuration matching: ", - "refs/remotes/$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/$ref_id\$") or - die "Failed to read \"svn-remote.$repo_id.fetch\" ", - "\":refs/remotes/$ref_id\$\" in config\n"; - ($self->{path}, undef) = split(/\s*:\s*/, $fetch); - } - $self->{url} = command_oneline('config', '--get', - "svn-remote.$repo_id.url") or - die "Failed to read \"svn-remote.$repo_id.url\" in config\n"; - $self->rebuild; - $self; -} - -sub refname { "refs/remotes/$_[0]->{ref_id}" } - -sub svm_uuid { - my ($self) = @_; - return $self->{svm}->{uuid} if $self->svm; - $self->ra; - unless ($self->{svm}) { - die "SVM UUID not cached, and reading remotely failed\n"; - } - $self->{svm}->{uuid}; -} - -sub svm { - my ($self) = @_; - return $self->{svm} if $self->{svm}; - my $svm; - # see if we have it in our config, first: - eval { - my $section = "svn-remote.$self->{repo_id}"; - $svm = { - source => tmp_config('--get', "$section.svm-source"), - uuid => tmp_config('--get', "$section.svm-uuid"), - replace => tmp_config('--get', "$section.svm-replace"), - } - }; - if ($svm && $svm->{source} && $svm->{uuid} && $svm->{replace}) { - $self->{svm} = $svm; - } - $self->{svm}; -} - -sub _set_svm_vars { - my ($self, $ra) = @_; - return $ra if $self->svm; - - my @err = ( "useSvmProps set, but failed to read SVM properties\n", - "(svm:source, svm:uuid) ", - "from the following URLs:\n" ); - sub read_svm_props { - my ($self, $ra, $path, $r) = @_; - my $props = ($ra->get_dir($path, $r))[2]; - my $src = $props->{'svm:source'}; - my $uuid = $props->{'svm:uuid'}; - return undef if (!$src || !$uuid); - - chomp($src, $uuid); - - $uuid =~ m{^[0-9a-f\-]{30,}$} - or die "doesn't look right - svm:uuid is '$uuid'\n"; - - # the '!' is used to mark the repos_root!/relative/path - $src =~ s{/?!/?}{/}; - $src =~ s{/+$}{}; # no trailing slashes please - # username is of no interest - $src =~ s{(^[a-z\+]*://)[^/@]*@}{$1}; - - my $replace = $ra->{url}; - $replace .= "/$path" if length $path; - - my $section = "svn-remote.$self->{repo_id}"; - tmp_config("$section.svm-source", $src); - tmp_config("$section.svm-replace", $replace); - tmp_config("$section.svm-uuid", $uuid); - $self->{svm} = { - source => $src, - uuid => $uuid, - replace => $replace - }; - } - - my $r = $ra->get_latest_revnum; - my $path = $self->{path}; - my %tried; - while (length $path) { - unless ($tried{"$self->{url}/$path"}) { - return $ra if $self->read_svm_props($ra, $path, $r); - $tried{"$self->{url}/$path"} = 1; - } - $path =~ s#/?[^/]+$##; - } - die "Path: '$path' should be ''\n" if $path ne ''; - return $ra if $self->read_svm_props($ra, $path, $r); - $tried{"$self->{url}/$path"} = 1; - - if ($ra->{repos_root} eq $self->{url}) { - die @err, (map { " $_\n" } keys %tried), "\n"; - } - - # nope, make sure we're connected to the repository root: - my $ok; - my @tried_b; - $path = $ra->{svn_path}; - $ra = Git::SVN::Ra->new($ra->{repos_root}); - while (length $path) { - unless ($tried{"$ra->{url}/$path"}) { - $ok = $self->read_svm_props($ra, $path, $r); - last if $ok; - $tried{"$ra->{url}/$path"} = 1; - } - $path =~ s#/?[^/]+$##; - } - die "Path: '$path' should be ''\n" if $path ne ''; - $ok ||= $self->read_svm_props($ra, $path, $r); - $tried{"$ra->{url}/$path"} = 1; - if (!$ok) { - die @err, (map { " $_\n" } keys %tried), "\n"; - } - Git::SVN::Ra->new($self->{url}); -} - -sub svnsync { - my ($self) = @_; - return $self->{svnsync} if $self->{svnsync}; - - if ($self->no_metadata) { - die "Can't have both 'noMetadata' and ", - "'useSvnsyncProps' options set!\n"; - } - if ($self->rewrite_root) { - die "Can't have both 'useSvnsyncProps' and 'rewriteRoot' ", - "options set!\n"; - } - - my $svnsync; - # see if we have it in our config, first: - eval { - my $section = "svn-remote.$self->{repo_id}"; - $svnsync = { - url => tmp_config('--get', "$section.svnsync-url"), - uuid => tmp_config('--get', "$section.svnsync-uuid"), - } - }; - if ($svnsync && $svnsync->{url} && $svnsync->{uuid}) { - return $self->{svnsync} = $svnsync; - } - - my $err = "useSvnsyncProps set, but failed to read " . - "svnsync property: svn:sync-from-"; - my $rp = $self->ra->rev_proplist(0); - - my $url = $rp->{'svn:sync-from-url'} or die $err . "url\n"; - $url =~ m{^[a-z\+]+://} or - die "doesn't look right - svn:sync-from-url is '$url'\n"; - - my $uuid = $rp->{'svn:sync-from-uuid'} or die $err . "uuid\n"; - $uuid =~ m{^[0-9a-f\-]{30,}$} or - die "doesn't look right - svn:sync-from-uuid is '$uuid'\n"; - - my $section = "svn-remote.$self->{repo_id}"; - tmp_config('--add', "$section.svnsync-uuid", $uuid); - tmp_config('--add', "$section.svnsync-url", $url); - return $self->{svnsync} = { url => $url, uuid => $uuid }; -} -# this allows us to memoize our SVN::Ra UUID locally and avoid a -# remote lookup (useful for 'git svn log'). -sub ra_uuid { - my ($self) = @_; - unless ($self->{ra_uuid}) { - my $key = "svn-remote.$self->{repo_id}.uuid"; - my $uuid = eval { tmp_config('--get', $key) }; - if (!$@ && $uuid && $uuid =~ /^([a-f\d\-]{30,})$/) { - $self->{ra_uuid} = $uuid; - } else { - die "ra_uuid called without URL\n" unless $self->{url}; - $self->{ra_uuid} = $self->ra->get_uuid; - tmp_config('--add', $key, $self->{ra_uuid}); + $size -= length($line); + last if ($size == 0); } } - $self->{ra_uuid}; -} -sub ra { - my ($self) = shift; - my $ra = Git::SVN::Ra->new($self->{url}); - if ($self->use_svm_props && !$self->{svm}) { - if ($self->no_metadata) { - die "Can't have both 'noMetadata' and ", - "'useSvmProps' options set!\n"; - } elsif ($self->use_svnsync_props) { - die "Can't have both 'useSvnsyncProps' and ", - "'useSvmProps' options set!\n"; - } - $ra = $self->_set_svm_vars($ra); - $self->{-want_revprops} = 1; - } - $ra; -} - -sub rel_path { - my ($self) = @_; - my $repos_root = $self->ra->{repos_root}; - return $self->{path} if ($self->{url} eq $repos_root); - die "BUG: rel_path failed! repos_root: $repos_root, Ra URL: ", - $self->ra->{url}, " path: $self->{path}, URL: $self->{url}\n"; -} + command_close_bidi_pipe($pid, $in, $out, $ctx); -sub traverse_ignore { - my ($self, $fh, $path, $r) = @_; - $path =~ s#^/+##g; - my $ra = $self->ra; - my ($dirent, undef, $props) = $ra->get_dir($path, $r); - my $p = $path; - $p =~ s#^\Q$self->{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; - $self->traverse_ignore($fh, "$path/$_", $r); - } + return \%s2r; } -sub last_rev { ($_[0]->last_rev_commit)[0] } -sub last_commit { ($_[0]->last_rev_commit)[1] } - -# returns the newest SVN revision number and newest commit SHA1 -sub last_rev_commit { - my ($self) = @_; - if (defined $self->{last_rev} && defined $self->{last_commit}) { - return ($self->{last_rev}, $self->{last_commit}); - } - my $c = ::verify_ref($self->refname.'^0'); - if ($c && !$self->use_svm_props && !$self->no_metadata) { - my $rev = (::cmt_metadata($c))[1]; - if (defined $rev) { - ($self->{last_rev}, $self->{last_commit}) = ($rev, $c); - return ($rev, $c); - } - } - my $db_path = $self->db_path; - unless (-e $db_path) { - ($self->{last_rev}, $self->{last_commit}) = (undef, undef); - return (undef, undef); - } - my $offset = -41; # from tail - my $rl; - open my $fh, '<', $db_path or croak "$db_path not readable: $!\n"; - sysseek($fh, $offset, 2); # don't care for errors - sysread($fh, $rl, 41) == 41 or return (undef, undef); - chomp $rl; - while (('0' x40) eq $rl && sysseek($fh, 0, 1) != 0) { - $offset -= 41; - sysseek($fh, $offset, 2); # don't care for errors - sysread($fh, $rl, 41) == 41 or return (undef, undef); - chomp $rl; - } - if ($c && $c ne $rl) { - die "$db_path and ", $self->refname, - " inconsistent!:\n$c != $rl\n"; - } - my $rev = sysseek($fh, 0, 1) or croak $!; - $rev = ($rev - 41) / 41; - close $fh or croak $!; - ($self->{last_rev}, $self->{last_commit}) = ($rev, $c); - return ($rev, $c); -} - -sub get_fetch_range { - my ($self, $min, $max) = @_; - $max ||= $self->ra->get_latest_revnum; - $min ||= $self->rev_db_max; - (++$min, $max); -} - -sub tmp_config { - my (@args) = @_; - my $old_def_config = "$ENV{GIT_DIR}/svn/config"; - my $config = "$ENV{GIT_DIR}/svn/.metadata"; - if (-e $old_def_config && ! -e $config) { - rename $old_def_config, $config or - die "Failed rename $old_def_config => $config: $!\n"; - } - my $old_config = $ENV{GIT_CONFIG}; - $ENV{GIT_CONFIG} = $config; - $@ = undef; - my @ret = eval { - unless (-f $config) { - mkfile($config); - open my $fh, '>', $config or - die "Can't open $config: $!\n"; - print $fh "; This file is used internally by ", - "git-svn\n" or die - "Couldn't write to $config: $!\n"; - print $fh "; You should not have to edit it\n" or - die "Couldn't write to $config: $!\n"; - close $fh or die "Couldn't close $config: $!\n"; - } - command('config', @args); - }; - my $err = $@; - if (defined $old_config) { - $ENV{GIT_CONFIG} = $old_config; - } else { - delete $ENV{GIT_CONFIG}; - } - die $err if $err; - wantarray ? @ret : $ret[0]; -} - -sub tmp_index_do { - my ($self, $sub) = @_; - my $old_index = $ENV{GIT_INDEX_FILE}; - $ENV{GIT_INDEX_FILE} = $self->{index}; - $@ = undef; - my @ret = eval { - my ($dir, $base) = ($self->{index} =~ m#^(.*?)/?([^/]+)$#); - mkpath([$dir]) unless -d $dir; - &$sub; - }; - my $err = $@; - if (defined $old_index) { - $ENV{GIT_INDEX_FILE} = $old_index; - } else { - delete $ENV{GIT_INDEX_FILE}; - } - die $err if $err; - wantarray ? @ret : $ret[0]; -} - -sub assert_index_clean { - my ($self, $treeish) = @_; - - $self->tmp_index_do(sub { - command_noisy('read-tree', $treeish) unless -e $self->{index}; - my $x = command_oneline('write-tree'); - my ($y) = (command(qw/cat-file commit/, $treeish) =~ - /^tree ($::sha1)/mo); - return if $y eq $x; - - warn "Index mismatch: $y != $x\nrereading $treeish\n"; - unlink $self->{index} or die "unlink $self->{index}: $!\n"; - command_noisy('read-tree', $treeish); - $x = command_oneline('write-tree'); - if ($y ne $x) { - ::fatal "trees ($treeish) $y != $x\n", - "Something is seriously wrong...\n"; - } - }); -} - -sub get_commit_parents { - my ($self, $log_entry) = @_; - my (%seen, @ret, @tmp); - # legacy support for 'set-tree'; this is only used by set_tree_cb: - if (my $ip = $self->{inject_parents}) { - if (my $commit = delete $ip->{$log_entry->{revision}}) { - push @tmp, $commit; - } - } - if (my $cur = ::verify_ref($self->refname.'^0')) { - push @tmp, $cur; - } - push @tmp, $_ foreach (@{$log_entry->{parents}}, @tmp); - while (my $p = shift @tmp) { - 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; -} - -sub rewrite_root { - my ($self) = @_; - return $self->{-rewrite_root} if exists $self->{-rewrite_root}; - my $k = "svn-remote.$self->{repo_id}.rewriteRoot"; - my $rwr = eval { command_oneline(qw/config --get/, $k) }; - if ($rwr) { - $rwr =~ s#/+$##; - if ($rwr !~ m#^[a-z\+]+://#) { - die "$rwr is not a valid URL (key: $k)\n"; - } - } - $self->{-rewrite_root} = $rwr; -} - -sub metadata_url { - my ($self) = @_; - ($self->rewrite_root || $self->{url}) . - (length $self->{path} ? '/' . $self->{path} : ''); -} - -sub full_url { - my ($self) = @_; - $self->{url} . (length $self->{path} ? '/' . $self->{path} : ''); -} - -sub do_git_commit { - my ($self, $log_entry) = @_; - my $lr = $self->last_rev; - if (defined $lr && $lr >= $log_entry->{revision}) { - die "Last fetched revision of ", $self->refname, - " was r$lr, but we are about to fetch: ", - "r$log_entry->{revision}!\n"; - } - if (my $c = $self->rev_db_get($log_entry->{revision})) { - croak "$log_entry->{revision} = $c already exists! ", - "Why are we refetching it?\n"; - } - $ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $log_entry->{name}; - $ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} = - $log_entry->{email}; - $ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_entry->{date}; - - my $tree = $log_entry->{tree}; - if (!defined $tree) { - $tree = $self->tmp_index_do(sub { - command_oneline('write-tree') }); - } - die "Tree is not a valid sha1: $tree\n" if $tree !~ /^$::sha1$/o; - - my @exec = ('git-commit-tree', $tree); - foreach ($self->get_commit_parents($log_entry)) { - push @exec, '-p', $_; - } - defined(my $pid = open3(my $msg_fh, my $out_fh, '>&STDERR', @exec)) - or croak $!; - print $msg_fh $log_entry->{log} or croak $!; - unless ($self->no_metadata) { - print $msg_fh "\ngit-svn-id: $log_entry->{metadata}\n" - or croak $!; - } - $msg_fh->flush == 0 or croak $!; - close $msg_fh or croak $!; - chomp(my $commit = do { local $/; <$out_fh> }); - close $out_fh or croak $!; - waitpid $pid, 0; - croak $? if $?; - if ($commit !~ /^$::sha1$/o) { - die "Failed to commit, invalid sha1: $commit\n"; - } - - $self->rev_db_set($log_entry->{revision}, $commit, 1); - - $self->{last_rev} = $log_entry->{revision}; - $self->{last_commit} = $commit; - print "r$log_entry->{revision}"; - if (defined $log_entry->{svm_revision}) { - print " (\@$log_entry->{svm_revision})"; - $self->rev_db_set($log_entry->{svm_revision}, $commit, - 0, $self->svm_uuid); - } - print " = $commit ($self->{ref_id})\n"; - if (defined $_repack && (--$_repack_nr == 0)) { - $_repack_nr = $_repack; - # repack doesn't use any arguments with spaces in them, does it? - print "Running git repack $_repack_flags ...\n"; - command_noisy('repack', split(/\s+/, $_repack_flags)); - print "Done repacking\n"; - } - return $commit; -} - -sub match_paths { - my ($self, $paths, $r) = @_; - return 1 if $self->{path} eq ''; - if (my $path = $paths->{"/$self->{path}"}) { - return ($path->{action} eq 'D') ? 0 : 1; - } - $self->{path_regex} ||= qr/^\/\Q$self->{path}\E\//; - if (grep /$self->{path_regex}/, keys %$paths) { - return 1; - } - my $c = ''; - foreach (split m#/#, $self->{path}) { - $c .= "/$_"; - next unless ($paths->{$c} && - ($paths->{$c}->{action} =~ /^[AR]$/)); - if ($self->ra->check_path($self->{path}, $r) == - $SVN::Node::dir) { - return 1; - } - } - return 0; -} - -sub find_parent_branch { - my ($self, $paths, $rev) = @_; - return undef unless $self->follow_parent; - 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]) }); - $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 @a_path_components; - my $i; - while (@b_path_components) { - $i = $paths->{'/'.join('/', @b_path_components)}; - last if $i && defined $i->{copyfrom_path}; - unshift(@a_path_components, pop(@b_path_components)); - } - return undef unless defined $i && defined $i->{copyfrom_path}; - my $branch_from = $i->{copyfrom_path}; - if (@a_path_components) { - print STDERR "branch_from: $branch_from => "; - $branch_from .= '/'.join('/', @a_path_components); - print STDERR $branch_from, "\n"; - } - my $r = $i->{copyfrom_rev}; - my $repos_root = $self->ra->{repos_root}; - my $url = $self->ra->{url}; - my $new_url = $repos_root . $branch_from; - print STDERR "Found possible branch point: ", - "$new_url => ", $self->full_url, ", $r\n"; - $branch_from =~ s#^/##; - my $gs = Git::SVN->find_by_url($new_url, $repos_root, $branch_from); - unless ($gs) { - my $ref_id = $self->{ref_id}; - $ref_id =~ s/\@\d+$//; - $ref_id .= "\@$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"; - $gs = Git::SVN->init($new_url, '', $ref_id, $ref_id, 1); - } - my ($r0, $parent) = $gs->find_rev_before($r, 1); - if (!defined $r0 || !defined $parent) { - $gs->fetch(0, $r); - ($r0, $parent) = $gs->last_rev_commit; - } - if (defined $r0 && defined $parent) { - print STDERR "Found branch parent: ($self->{ref_id}) $parent\n"; - my $ed; - if ($self->ra->can_do_switch) { - $self->assert_index_clean($parent); - print STDERR "Following parent with do_switch\n"; - # 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 - $self->{last_commit} = $parent; - $ed = SVN::Git::Fetcher->new($self); - $gs->ra->gs_do_switch($r0, $rev, $gs, - $self->full_url, $ed) - or die "SVN connection failed somewhere...\n"; - } else { - print STDERR "Following parent with do_update\n"; - $ed = SVN::Git::Fetcher->new($self); - $self->ra->gs_do_update($rev, $rev, $self, $ed) - or die "SVN connection failed somewhere...\n"; - } - print STDERR "Successfully followed parent\n"; - return $self->make_log_entry($rev, [$parent], $ed); - } - return undef; -} - -sub do_fetch { - my ($self, $paths, $rev) = @_; - my $ed; - my ($last_rev, @parents); - if (my $lc = $self->last_commit) { - # we can have a branch that was deleted, then re-added - # under the same name but copied from another path, in - # which case we'll have multiple parents (we don't - # want to break the original ref, nor lose copypath info): - if (my $log_entry = $self->find_parent_branch($paths, $rev)) { - push @{$log_entry->{parents}}, $lc; - return $log_entry; - } - $ed = SVN::Git::Fetcher->new($self); - $last_rev = $self->{last_rev}; - $ed->{c} = $lc; - @parents = ($lc); - } else { - $last_rev = $rev; - if (my $log_entry = $self->find_parent_branch($paths, $rev)) { - return $log_entry; +sub working_head_info { + my ($head, $refs) = @_; + my @args = qw/rev-list --first-parent --pretty=medium/; + my ($fh, $ctx) = command_output_pipe(@args, $head, "--"); + my $hash; + my %max; + while (<$fh>) { + if ( m{^commit ($::sha1)$} ) { + unshift @$refs, $hash if $hash and $refs; + $hash = $1; + next; } - $ed = SVN::Git::Fetcher->new($self); - } - unless ($self->ra->gs_do_update($last_rev, $rev, $self, $ed)) { - die "SVN connection failed somewhere...\n"; - } - $self->make_log_entry($rev, \@parents, $ed); -} - -sub get_untracked { - my ($self, $ed) = @_; - my @out; - my $h = $ed->{empty}; - foreach (sort keys %$h) { - my $act = $h->{$_} ? '+empty_dir' : '-empty_dir'; - push @out, " $act: " . uri_encode($_); - warn "W: $act: $_\n"; - } - foreach my $t (qw/dir_prop file_prop/) { - $h = $ed->{$t} or next; - foreach my $path (sort keys %$h) { - my $ppath = $path eq '' ? '.' : $path; - foreach my $prop (sort keys %{$h->{$path}}) { - next if $SKIP_PROP{$prop}; - my $v = $h->{$path}->{$prop}; - my $t_ppath_prop = "$t: " . - uri_encode($ppath) . ' ' . - uri_encode($prop); - if (defined $v) { - push @out, " +$t_ppath_prop " . - uri_encode($v); + next unless s{^\s*(git-svn-id:)}{$1}; + my ($url, $rev, $uuid) = extract_metadata($_); + if (defined $url && defined $rev) { + next if $max{$url} and $max{$url} < $rev; + if (my $gs = Git::SVN->find_by_url($url)) { + my $c = $gs->rev_map_get($rev, $uuid); + if ($c && $c eq $hash) { + close $fh; # break the pipe + return ($url, $rev, $uuid, $gs); } else { - push @out, " -$t_ppath_prop"; + $max{$url} ||= $gs->rev_map_max; } } } } - foreach my $t (qw/absent_file absent_directory/) { - $h = $ed->{$t} or next; - foreach my $parent (sort keys %$h) { - foreach my $path (sort @{$h->{$parent}}) { - push @out, " $t: " . - uri_encode("$parent/$path"); - warn "W: $t: $parent/$path ", - "Insufficient permissions?\n"; - } - } - } - \@out; -} - -sub parse_svn_date { - my $date = shift || return '+0000 1970-01-01 00:00:00'; - my ($Y,$m,$d,$H,$M,$S) = ($date =~ /^(\d{4})\-(\d\d)\-(\d\d)T - (\d\d)\:(\d\d)\:(\d\d).\d+Z$/x) or - croak "Unable to parse date: $date\n"; - "+0000 $Y-$m-$d $H:$M:$S"; -} - -sub check_author { - my ($author) = @_; - if (!defined $author || length $author == 0) { - $author = '(no author)'; - } - if (defined $::_authors && ! defined $::users{$author}) { - die "Author: $author not defined in $::_authors file\n"; - } - $author; -} - -sub make_log_entry { - my ($self, $rev, $parents, $ed) = @_; - my $untracked = $self->get_untracked($ed); - - 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, - log => ''); - - my $headrev; - my $logged = delete $self->{logged_rev_props}; - if (!$logged || $self->{-want_revprops}) { - my $rp = $self->ra->rev_proplist($rev); - foreach (sort keys %$rp) { - my $v = $rp->{$_}; - if (/^svn:(author|date|log)$/) { - $log_entry{$1} = $v; - } elsif ($_ eq 'svm:headrev') { - $headrev = $v; - } else { - print $un " rev_prop: ", uri_encode($_), ' ', - uri_encode($v), "\n"; - } - } - } else { - map { $log_entry{$_} = $logged->{$_} } keys %$logged; - } - close $un or croak $!; - - $log_entry{date} = parse_svn_date($log_entry{date}); - $log_entry{log} .= "\n"; - my $author = $log_entry{author} = check_author($log_entry{author}); - my ($name, $email) = defined $::users{$author} ? @{$::users{$author}} - : ($author, undef); - if (defined $headrev && $self->use_svm_props) { - if ($self->rewrite_root) { - die "Can't have both 'useSvmProps' and 'rewriteRoot' ", - "options set!\n"; - } - my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$}; - # we don't want "SVM: initializing mirror for junk" ... - return undef if $r == 0; - my $svm = $self->svm; - if ($uuid ne $svm->{uuid}) { - die "UUID mismatch on SVM path:\n", - "expected: $svm->{uuid}\n", - " got: $uuid\n"; - } - my $full_url = $self->full_url; - $full_url =~ s#^\Q$svm->{replace}\E(/|$)#$svm->{source}$1# or - die "Failed to replace '$svm->{replace}' with ", - "'$svm->{source}' in $full_url\n"; - # throw away username for storing in records - remove_username($full_url); - $log_entry{metadata} = "$full_url\@$r $uuid"; - $log_entry{svm_revision} = $r; - $email ||= "$author\@$uuid" - } elsif ($self->use_svnsync_props) { - my $full_url = $self->svnsync->{url}; - $full_url .= "/$self->{path}" if length $self->{path}; - my $uuid = $self->svnsync->{uuid}; - $log_entry{metadata} = "$full_url\@$rev $uuid"; - $email ||= "$author\@$uuid" - } else { - $log_entry{metadata} = $self->metadata_url. "\@$rev " . - $self->ra->get_uuid; - $email ||= "$author\@" . $self->ra->get_uuid; - } - $log_entry{name} = $name; - $log_entry{email} = $email; - \%log_entry; -} - -sub fetch { - my ($self, $min_rev, $max_rev, @parents) = @_; - my ($last_rev, $last_commit) = $self->last_rev_commit; - my ($base, $head) = $self->get_fetch_range($min_rev, $max_rev); - $self->ra->gs_fetch_loop_common($base, $head, [$self]); -} - -sub set_tree_cb { - my ($self, $log_entry, $tree, $rev, $date, $author) = @_; - $self->{inject_parents} = { $rev => $tree }; - $self->fetch(undef, undef); -} - -sub set_tree { - my ($self, $tree) = (shift, shift); - my $log_entry = ::get_commit_entry($tree); - unless ($self->{last_rev}) { - fatal("Must have an existing revision to commit\n"); - } - my %ed_opts = ( r => $self->{last_rev}, - log => $log_entry->{log}, - ra => $self->ra, - tree_a => $self->{last_commit}, - tree_b => $tree, - editor_cb => sub { - $self->set_tree_cb($log_entry, $tree, @_) }, - svn_path => $self->{path} ); - if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) { - print "No changes\nr$self->{last_rev} = $tree\n"; - } -} - -sub rebuild { - my ($self) = @_; - my $db_path = $self->db_path; - return if (-e $db_path && ! -z $db_path); - return unless ::verify_ref($self->refname.'^0'); - if (-f $self->{db_root}) { - rename $self->{db_root}, $db_path or die - "rename $self->{db_root} => $db_path failed: $!\n"; - my ($dir, $base) = ($db_path =~ m#^(.*?)/?([^/]+)$#); - symlink $base, $self->{db_root} or die - "symlink $base => $self->{db_root} failed: $!\n"; - return; - } - print "Rebuilding $db_path ...\n"; - my ($rev_list, $ctx) = command_output_pipe("rev-list", $self->refname); - my $latest; - my $full_url = $self->full_url; - remove_username($full_url); - my $svn_uuid; - while (<$rev_list>) { - chomp; - my $c = $_; - die "Non-SHA1: $c\n" unless $c =~ /^$::sha1$/o; - my ($url, $rev, $uuid) = ::cmt_metadata($c); - remove_username($url); - - # ignore merges (from set-tree) - next if (!defined $rev || !$uuid); - - # if we merged or otherwise started elsewhere, this is - # how we break out of it - if ((defined $svn_uuid && ($uuid ne $svn_uuid)) || - ($full_url && $url && ($url ne $full_url))) { - next; - } - $latest ||= $rev; - $svn_uuid ||= $uuid; - - $self->rev_db_set($rev, $c); - print "r$rev = $c\n"; - } - command_close_pipe($rev_list, $ctx); - print "Done rebuilding $db_path\n"; -} - -# rev_db: -# Tie::File seems to be prone to offset errors if revisions get sparse, -# it's not that fast, either. Tie::File is also not in Perl 5.6. So -# one of my favorite modules is out :< Next up would be one of the DBM -# modules, but I'm not sure which is most portable... So I'll just -# go with something that's plain-text, but still capable of -# being randomly accessed. So here's my ultra-simple fixed-width -# database. All records are 40 characters + "\n", so it's easy to seek -# to a revision: (41 * rev) is the byte offset. -# A record of 40 0s denotes an empty revision. -# And yes, it's still pretty fast (faster than Tie::File). -# These files are disposable unless noMetadata or useSvmProps is set - -sub _rev_db_set { - my ($fh, $rev, $commit) = @_; - my $offset = $rev * 41; - # assume that append is the common case: - seek $fh, 0, 2 or croak $!; - my $pos = tell $fh; - if ($pos < $offset) { - for (1 .. (($offset - $pos) / 41)) { - print $fh (('0' x 40),"\n") or croak $!; - } - } - seek $fh, $offset, 0 or croak $!; - print $fh $commit,"\n" or croak $!; -} - -sub mkfile { - my ($path) = @_; - unless (-e $path) { - my ($dir, $base) = ($path =~ m#^(.*?)/?([^/]+)$#); - mkpath([$dir]) unless -d $dir; - open my $fh, '>>', $path or die "Couldn't create $path: $!\n"; - close $fh or die "Couldn't close (create) $path: $!\n"; - } -} - -sub rev_db_set { - my ($self, $rev, $commit, $update_ref, $uuid) = @_; - length $commit == 40 or die "arg3 must be a full SHA1 hexsum\n"; - my $db = $self->db_path($uuid); - my $db_lock = "$db.lock"; - my $sig; - if ($update_ref) { - $SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} = - $SIG{USR1} = $SIG{USR2} = sub { $sig = $_[0] }; - } - mkfile($db); - - $LOCKFILES{$db_lock} = 1; - my $sync; - # both of these options make our .rev_db file very, very important - # and we can't afford to lose it because rebuild() won't work - if ($self->use_svm_props || $self->no_metadata) { - $sync = 1; - copy($db, $db_lock) or die "rev_db_set(@_): ", - "Failed to copy: ", - "$db => $db_lock ($!)\n"; - } else { - rename $db, $db_lock or die "rev_db_set(@_): ", - "Failed to rename: ", - "$db => $db_lock ($!)\n"; - } - open my $fh, '+<', $db_lock or die "Couldn't open $db_lock: $!\n"; - _rev_db_set($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"; - } - close $fh or croak $!; - if ($update_ref) { - $_head = $self; - command_noisy('update-ref', '-m', "r$rev", - $self->refname, $commit); - } - rename $db_lock, $db or die "rev_db_set(@_): ", "Failed to rename: ", - "$db_lock => $db ($!)\n"; - delete $LOCKFILES{$db_lock}; - if ($update_ref) { - $SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} = - $SIG{USR1} = $SIG{USR2} = 'DEFAULT'; - kill $sig, $$ if defined $sig; - } -} - -sub rev_db_max { - my ($self) = @_; - $self->rebuild; - my $db_path = $self->db_path; - my @stat = stat $db_path or return 0; - ($stat[7] % 41) == 0 or die "$db_path inconsistent size: $stat[7]\n"; - my $max = $stat[7] / 41; - (($max > 0) ? $max - 1 : 0); -} - -sub rev_db_get { - my ($self, $rev, $uuid) = @_; - my $ret; - my $offset = $rev * 41; - my $db_path = $self->db_path($uuid); - return undef unless -e $db_path; - open my $fh, '<', $db_path or croak $!; - if (sysseek($fh, $offset, 0) == $offset) { - my $read = sysread($fh, $ret, 40); - $ret = undef if ($read != 40 || $ret eq ('0'x40)); - } - close $fh or croak $!; - $ret; -} - -sub find_rev_before { - my ($self, $rev, $eq_ok) = @_; - --$rev unless $eq_ok; - while ($rev > 0) { - if (my $c = $self->rev_db_get($rev)) { - return ($rev, $c); - } - --$rev; - } - return (undef, undef); -} - -sub _new { - my ($class, $repo_id, $ref_id, $path) = @_; - unless (defined $repo_id && length $repo_id) { - $repo_id = $Git::SVN::default_repo_id; - } - unless (defined $ref_id && length $ref_id) { - $_[2] = $ref_id = $Git::SVN::default_ref_id; - } - $_[1] = $repo_id = sanitize_remote_name($repo_id); - my $dir = "$ENV{GIT_DIR}/svn/$ref_id"; - $_[3] = $path = '' unless (defined $path); - mkpath(["$ENV{GIT_DIR}/svn"]); - bless { - ref_id => $ref_id, dir => $dir, index => "$dir/index", - path => $path, config => "$ENV{GIT_DIR}/svn/config", - db_root => "$dir/.rev_db", repo_id => $repo_id }, $class; -} - -sub db_path { - my ($self, $uuid) = @_; - $uuid ||= $self->ra_uuid; - "$self->{db_root}.$uuid"; -} - -sub uri_encode { - my ($f) = @_; - $f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg; - $f -} - -sub remove_username { - $_[0] =~ s{^([^:]*://)[^@]+@}{$1}; -} - -package Git::SVN::Prompt; -use strict; -use warnings; -require SVN::Core; -use vars qw/$_no_auth_cache $_username/; - -sub simple { - my ($cred, $realm, $default_username, $may_save, $pool) = @_; - $may_save = undef if $_no_auth_cache; - $default_username = $_username if defined $_username; - if (defined $default_username && length $default_username) { - if (defined $realm && length $realm) { - print STDERR "Authentication realm: $realm\n"; - STDERR->flush; - } - $cred->username($default_username); - } else { - username($cred, $realm, $may_save, $pool); - } - $cred->password(_read_password("Password for '" . - $cred->username . "': ", $realm)); - $cred->may_save($may_save); - $SVN::_Core::SVN_NO_ERROR; -} - -sub ssl_server_trust { - my ($cred, $realm, $failures, $cert_info, $may_save, $pool) = @_; - $may_save = undef if $_no_auth_cache; - print STDERR "Error validating server certificate for '$realm':\n"; - if ($failures & $SVN::Auth::SSL::UNKNOWNCA) { - print STDERR " - The certificate is not issued by a trusted ", - "authority. Use the\n", - " fingerprint to validate the certificate manually!\n"; - } - if ($failures & $SVN::Auth::SSL::CNMISMATCH) { - print STDERR " - The certificate hostname does not match.\n"; - } - if ($failures & $SVN::Auth::SSL::NOTYETVALID) { - print STDERR " - The certificate is not yet valid.\n"; - } - if ($failures & $SVN::Auth::SSL::EXPIRED) { - print STDERR " - The certificate has expired.\n"; - } - if ($failures & $SVN::Auth::SSL::OTHER) { - print STDERR " - The certificate has an unknown error.\n"; - } - printf STDERR - "Certificate information:\n". - " - Hostname: %s\n". - " - Valid: from %s until %s\n". - " - Issuer: %s\n". - " - Fingerprint: %s\n", - map $cert_info->$_, qw(hostname valid_from valid_until - issuer_dname fingerprint); - my $choice; -prompt: - print STDERR $may_save ? - "(R)eject, accept (t)emporarily or accept (p)ermanently? " : - "(R)eject or accept (t)emporarily? "; - STDERR->flush; - $choice = lc(substr(<STDIN> || 'R', 0, 1)); - if ($choice =~ /^t$/i) { - $cred->may_save(undef); - } elsif ($choice =~ /^r$/i) { - return -1; - } elsif ($may_save && $choice =~ /^p$/i) { - $cred->may_save($may_save); - } else { - goto prompt; - } - $cred->accepted_failures($failures); - $SVN::_Core::SVN_NO_ERROR; -} - -sub ssl_client_cert { - my ($cred, $realm, $may_save, $pool) = @_; - $may_save = undef if $_no_auth_cache; - print STDERR "Client certificate filename: "; - STDERR->flush; - chomp(my $filename = <STDIN>); - $cred->cert_file($filename); - $cred->may_save($may_save); - $SVN::_Core::SVN_NO_ERROR; -} - -sub ssl_client_cert_pw { - my ($cred, $realm, $may_save, $pool) = @_; - $may_save = undef if $_no_auth_cache; - $cred->password(_read_password("Password: ", $realm)); - $cred->may_save($may_save); - $SVN::_Core::SVN_NO_ERROR; -} - -sub username { - my ($cred, $realm, $may_save, $pool) = @_; - $may_save = undef if $_no_auth_cache; - if (defined $realm && length $realm) { - print STDERR "Authentication realm: $realm\n"; - } - my $username; - if (defined $_username) { - $username = $_username; - } else { - print STDERR "Username: "; - STDERR->flush; - chomp($username = <STDIN>); - } - $cred->username($username); - $cred->may_save($may_save); - $SVN::_Core::SVN_NO_ERROR; -} - -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; - } - Term::ReadKey::ReadMode('restore'); - print STDERR "\n"; - STDERR->flush; - $password; -} - -package main; - -{ - 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. - $SVN::Auth::SSL::CNMISMATCH. - $SVN::Auth::SSL::NOTYETVALID. - $SVN::Auth::SSL::EXPIRED. - $SVN::Auth::SSL::UNKNOWNCA. - $SVN::Auth::SSL::OTHER; -} - -package SVN::Git::Fetcher; -use vars qw/@ISA/; -use strict; -use warnings; -use Carp qw/croak/; -use IO::File qw//; -use Digest::MD5; - -# file baton members: path, mode_a, mode_b, pool, fh, blob, base -sub new { - my ($class, $git_svn) = @_; - my $self = SVN::Delta::Editor->new; - bless $self, $class; - $self->{c} = $git_svn->{last_commit} if exists $git_svn->{last_commit}; - $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; -} - -sub set_path_strip { - my ($self, $path) = @_; - $self->{path_strip} = qr/^\Q$path\E(\/|$)/ if length $path; -} - -sub open_root { - { path => '' }; -} - -sub open_directory { - my ($self, $path, $pb, $rev) = @_; - { path => $path }; -} - -sub git_path { - my ($self, $path) = @_; - if ($self->{path_strip}) { - $path =~ s!$self->{path_strip}!! or - die "Failed to strip path '$path' ($self->{path_strip})\n"; - } - $path; -} - -sub delete_entry { - my ($self, $path, $rev, $pb) = @_; - - my $gpath = $self->git_path($path); - return undef if ($gpath eq ''); - - # remove entire directories. - if (command('ls-tree', $self->{c}, '--', $gpath) =~ /^040000 tree/) { - my ($ls, $ctx) = command_output_pipe(qw/ls-tree - -r --name-only -z/, - $self->{c}, '--', $gpath); - local $/ = "\0"; - while (<$ls>) { - chomp; - $self->{gii}->remove($_); - print "\tD\t$_\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; - } - undef; -} - -sub open_file { - my ($self, $path, $pb, $rev) = @_; - my $gpath = $self->git_path($path); - my ($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath) - =~ /^(\d{6}) blob ([a-f\d]{40})\t/); - unless (defined $mode && defined $blob) { - die "$path was not found in commit $self->{c} (r$rev)\n"; - } - { path => $path, mode_a => $mode, mode_b => $mode, blob => $blob, - pool => SVN::Pool->new, action => 'M' }; -} - -sub add_file { - my ($self, $path, $pb, $cp_path, $cp_rev) = @_; - my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#); - delete $self->{empty}->{$dir}; - { path => $path, mode_a => 100644, mode_b => 100644, - pool => SVN::Pool->new, action => 'A' }; -} - -sub add_directory { - my ($self, $path, $cp_path, $cp_rev) = @_; - my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#); - delete $self->{empty}->{$dir}; - $self->{empty}->{$path} = 1; - { path => $path }; -} - -sub change_dir_prop { - my ($self, $db, $prop, $value) = @_; - $self->{dir_prop}->{$db->{path}} ||= {}; - $self->{dir_prop}->{$db->{path}}->{$prop} = $value; - undef; -} - -sub absent_directory { - my ($self, $path, $pb) = @_; - $self->{absent_dir}->{$pb->{path}} ||= []; - push @{$self->{absent_dir}->{$pb->{path}}}, $path; - undef; -} - -sub absent_file { - my ($self, $path, $pb) = @_; - $self->{absent_file}->{$pb->{path}} ||= []; - push @{$self->{absent_file}->{$pb->{path}}}, $path; - undef; -} - -sub change_file_prop { - my ($self, $fb, $prop, $value) = @_; - if ($prop eq 'svn:executable') { - if ($fb->{mode_b} != 120000) { - $fb->{mode_b} = defined $value ? 100755 : 100644; - } - } elsif ($prop eq 'svn:special') { - $fb->{mode_b} = defined $value ? 120000 : 100644; - } else { - $self->{file_prop}->{$fb->{path}} ||= {}; - $self->{file_prop}->{$fb->{path}}->{$prop} = $value; - } - undef; -} - -sub apply_textdelta { - my ($self, $fb, $exp) = @_; - my $fh = IO::File->new_tmpfile; - $fh->autoflush(1); - # $fh gets auto-closed() by SVN::TxDelta::apply(), - # (but $base does not,) so dup() it for reading in close_file - open my $dup, '<&', $fh or croak $!; - my $base = IO::File->new_tmpfile; - $base->autoflush(1); - if ($fb->{blob}) { - defined (my $pid = fork) or croak $!; - if (!$pid) { - open STDOUT, '>&', $base or croak $!; - print STDOUT 'link ' if ($fb->{mode_a} == 120000); - exec qw/git-cat-file blob/, $fb->{blob} or croak $!; - } - waitpid $pid, 0; - croak $? if $?; - - if (defined $exp) { - seek $base, 0, 0 or croak $!; - my $md5 = Digest::MD5->new; - $md5->addfile($base); - my $got = $md5->hexdigest; - die "Checksum mismatch: $fb->{path} $fb->{blob}\n", - "expected: $exp\n", - " got: $got\n" if ($got ne $exp); - } - } - seek $base, 0, 0 or croak $!; - $fb->{fh} = $dup; - $fb->{base} = $base; - [ SVN::TxDelta::apply($base, $fh, undef, $fb->{path}, $fb->{pool}) ]; -} - -sub close_file { - my ($self, $fb, $exp) = @_; - my $hash; - my $path = $self->git_path($fb->{path}); - if (my $fh = $fb->{fh}) { - seek($fh, 0, 0) or croak $!; - my $md5 = Digest::MD5->new; - $md5->addfile($fh); - my $got = $md5->hexdigest; - die "Checksum mismatch: $path\n", - "expected: $exp\n got: $got\n" if ($got ne $exp); - seek($fh, 0, 0) or croak $!; - if ($fb->{mode_b} == 120000) { - read($fh, my $buf, 5) == 5 or croak $!; - $buf eq 'link ' or die "$path has mode 120000", - "but is not a link\n"; - } - defined(my $pid = open my $out,'-|') or die "Can't fork: $!\n"; - if (!$pid) { - open STDIN, '<&', $fh or croak $!; - exec qw/git-hash-object -w --stdin/ or croak $!; - } - chomp($hash = do { local $/; <$out> }); - close $out or croak $!; - close $fh or croak $!; - $hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n"; - close $fb->{base} or croak $!; - } else { - $hash = $fb->{blob} or die "no blob information\n"; - } - $fb->{pool}->clear; - $self->{gii}->update($fb->{mode_b}, $hash, $path) or croak $!; - print "\t$fb->{action}\t$path\n" if $fb->{action} && ! $::_q; - undef; -} - -sub abort_edit { - my $self = shift; - $self->{nr} = $self->{gii}->{nr}; - delete $self->{gii}; - $self->SUPER::abort_edit(@_); -} - -sub close_edit { - my $self = shift; - $self->{git_commit_ok} = 1; - $self->{nr} = $self->{gii}->{nr}; - delete $self->{gii}; - $self->SUPER::close_edit(@_); -} - -package SVN::Git::Editor; -use vars qw/@ISA $_rmdir $_cp_similarity $_find_copies_harder $_rename_limit/; -use strict; -use warnings; -use Carp qw/croak/; -use IO::File; -use Digest::MD5; - -sub new { - my ($class, $opts) = @_; - foreach (qw/svn_path r ra tree_a tree_b log editor_cb/) { - die "$_ required!\n" unless (defined $opts->{$_}); - } - - my $pool = SVN::Pool->new; - my $mods = generate_diff($opts->{tree_a}, $opts->{tree_b}); - my $types = check_diff_paths($opts->{ra}, $opts->{svn_path}, - $opts->{r}, $mods); - - # $opts->{ra} functions should not be used after this: - my @ce = $opts->{ra}->get_commit_editor($opts->{log}, - $opts->{editor_cb}, $pool); - my $self = SVN::Delta::Editor->new(@ce, $pool); - bless $self, $class; - foreach (qw/svn_path r tree_a tree_b/) { - $self->{$_} = $opts->{$_}; - } - $self->{url} = $opts->{ra}->{url}; - $self->{mods} = $mods; - $self->{types} = $types; - $self->{pool} = $pool; - $self->{bat} = { '' => $self->open_root($self->{r}, $self->{pool}) }; - $self->{rm} = { }; - $self->{path_prefix} = length $self->{svn_path} ? - "$self->{svn_path}/" : ''; - return $self; -} - -sub generate_diff { - my ($tree_a, $tree_b) = @_; - my @diff_tree = qw(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$_rename_limit" if defined $_rename_limit; - push @diff_tree, $tree_a, $tree_b; - my ($diff_fh, $ctx) = command_output_pipe(@diff_tree); - local $/ = "\0"; - my $state = 'meta'; - my @mods; - while (<$diff_fh>) { - chomp $_; # this gets rid of the trailing "\0" - if ($state eq 'meta' && /^:(\d{6})\s(\d{6})\s - $::sha1\s($::sha1)\s - ([MTCRAD])\d*$/xo) { - push @mods, { mode_a => $1, mode_b => $2, - sha1_b => $3, chg => $4 }; - if ($4 =~ /^(?:C|R)$/) { - $state = 'file_a'; - } else { - $state = 'file_b'; - } - } elsif ($state eq 'file_a') { - my $x = $mods[$#mods] or croak "Empty array\n"; - if ($x->{chg} !~ /^(?:C|R)$/) { - croak "Error parsing $_, $x->{chg}\n"; - } - $x->{file_a} = $_; - $state = 'file_b'; - } elsif ($state eq 'file_b') { - my $x = $mods[$#mods] or croak "Empty array\n"; - if (exists $x->{file_a} && $x->{chg} !~ /^(?:C|R)$/) { - croak "Error parsing $_, $x->{chg}\n"; - } - if (!exists $x->{file_a} && $x->{chg} =~ /^(?:C|R)$/) { - croak "Error parsing $_, $x->{chg}\n"; - } - $x->{file_b} = $_; - $state = 'meta'; - } else { - croak "Error parsing $_\n"; - } - } - command_close_pipe($diff_fh, $ctx); - \@mods; -} - -sub check_diff_paths { - my ($ra, $pfx, $rev, $mods) = @_; - my %types; - $pfx .= '/' if length $pfx; - - sub type_diff_paths { - my ($ra, $types, $path, $rev) = @_; - my @p = split m#/+#, $path; - my $c = shift @p; - unless (defined $types->{$c}) { - $types->{$c} = $ra->check_path($c, $rev); - } - while (@p) { - $c .= '/' . shift @p; - next if defined $types->{$c}; - $types->{$c} = $ra->check_path($c, $rev); - } - } - - foreach my $m (@$mods) { - foreach my $f (qw/file_a file_b/) { - next unless defined $m->{$f}; - my ($dir) = ($m->{$f} =~ m#^(.*?)/?(?:[^/]+)$#); - if (length $pfx.$dir && ! defined $types{$dir}) { - type_diff_paths($ra, \%types, $pfx.$dir, $rev); - } - } - } - \%types; -} - -sub split_path { - return ($_[0] =~ m#^(.*?)/?([^/]+)$#); -} - -sub repo_path { - my ($self, $path) = @_; - $self->{path_prefix}.(defined $path ? $path : ''); -} - -sub url_path { - my ($self, $path) = @_; - $self->{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; - - my ($fh, $ctx) = command_output_pipe(qw/ls-tree --name-only -r -z/, - $self->{tree_b}); - local $/ = "\0"; - while (<$fh>) { - chomp; - my @dn = split m#/#, $_; - while (pop @dn) { - delete $rm->{join '/', @dn}; - } - unless (%$rm) { - close $fh; - return; - } - } command_close_pipe($fh, $ctx); - - 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#^(.*?)/?(?:[^/]+)$#); - print "\tD+\t$d/\n" unless $::_q; - $self->SUPER::delete_entry($d, $r, $bat->{$dn}, $p); - delete $bat->{$d}; - } -} - -sub open_or_add_dir { - my ($self, $full_path, $baton) = @_; - my $t = $self->{types}->{$full_path}; - if (!defined $t) { - die "$full_path not known in r$self->{r} or we have a bug!\n"; - } - 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}; - my $repo_path = $self->repo_path($path); - return $bat->{''} unless (length $repo_path); - my @p = split m#/+#, $repo_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); - print "\tA\t$m->{file_b}\n" unless $::_q; - $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}); - print "\tC\t$m->{file_a} => $m->{file_b}\n" unless $::_q; - $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}); - print "\tR\t$m->{file_a} => $m->{file_b}\n" unless $::_q; - $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}); - print "\t$m->{chg}\t$m->{file_b}\n" unless $::_q; - $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 $pool = SVN::Pool->new; - my $atd = $self->apply_textdelta($fbat, undef, $pool); - my $got = SVN::TxDelta::send_stream($fh, @$atd, $pool); - die "Checksum mismatch\nexpected: $exp\ngot: $got\n" if ($got ne $exp); - $pool->clear; - - close $fh or croak $!; -} - -sub D { - my ($self, $m) = @_; - my ($dir, $file) = split_path($m->{file_b}); - my $pbat = $self->ensure_path($dir); - print "\tD\t$m->{file_b}\n" unless $::_q; - $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}); -} - -sub DESTROY { - my $self = shift; - $self->SUPER::DESTROY(@_); - $self->{pool}->clear; -} - -# this drives the editor -sub apply_diff { - my ($self) = @_; - my $mods = $self->{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}) { - $self->$f($m); - } else { - fatal("Invalid change type: $f\n"); - } - } - $self->rmdirs if $_rmdir; - if (@$mods == 0) { - $self->abort_edit; - } else { - $self->close_edit; - } - return scalar @$mods; + (undef, undef, undef, undef); } -package Git::SVN::Ra; -use vars qw/@ISA $config_dir $_log_window_size/; -use strict; -use warnings; -my ($can_do_switch); -my $RA; - -BEGIN { - # enforce temporary pool usage for some simple functions - my $e; - foreach (qw/get_latest_revnum get_uuid get_repos_root/) { - $e .= "sub $_ { - my \$self = shift; - my \$pool = SVN::Pool->new; - my \@ret = \$self->SUPER::$_(\@_,\$pool); - \$pool->clear; - wantarray ? \@ret : \$ret[0]; }\n"; - } - - # get_dir needs $pool held in cache for dirents to work, - # check_path is cacheable and rev_proplist is close enough - # for our purposes. - foreach (qw/check_path get_dir rev_proplist/) { - $e .= "my \%${_}_cache; my \$${_}_rev = 0; sub $_ { - my \$self = shift; - my \$r = pop; - my \$k = join(\"\\0\", \@_); - if (my \$x = \$${_}_cache{\$r}->{\$k}) { - return wantarray ? \@\$x : \$x->[0]; - } - my \$pool = SVN::Pool->new; - my \@ret = \$self->SUPER::$_(\@_, \$r, \$pool); - if (\$r != \$${_}_rev) { - \%${_}_cache = ( pool => [] ); - \$${_}_rev = \$r; - } - \$${_}_cache{\$r}->{\$k} = \\\@ret; - push \@{\$${_}_cache{pool}}, \$pool; - wantarray ? \@ret : \$ret[0]; }\n"; - } - $e .= "\n1;"; - eval $e or die $@; +sub read_commit_parents { + my ($parents, $c) = @_; + chomp(my $p = command_oneline(qw/rev-list --parents -1/, $c)); + $p =~ s/^($c)\s*// or die "rev-list --parents -1 $c failed!\n"; + @{$parents->{$c}} = split(/ /, $p); } -sub new { - my ($class, $url) = @_; - $url =~ s!/+$!!; - return $RA if ($RA && $RA->{url} eq $url); - $RA->{pool}->clear if $RA; - - SVN::_Core::svn_config_ensure($config_dir, undef); - my ($baton, $callbacks) = SVN::Core::auth_open_helper([ - SVN::Client::get_simple_provider(), - SVN::Client::get_ssl_server_trust_file_provider(), - SVN::Client::get_simple_prompt_provider( - \&Git::SVN::Prompt::simple, 2), - SVN::Client::get_ssl_client_cert_prompt_provider( - \&Git::SVN::Prompt::ssl_client_cert, 2), - SVN::Client::get_ssl_client_cert_pw_prompt_provider( - \&Git::SVN::Prompt::ssl_client_cert_pw, 2), - SVN::Client::get_username_provider(), - SVN::Client::get_ssl_server_trust_prompt_provider( - \&Git::SVN::Prompt::ssl_server_trust), - SVN::Client::get_username_prompt_provider( - \&Git::SVN::Prompt::username, 2), - ]); - my $config = SVN::Core::config_get_config($config_dir); - my $self = SVN::Ra->new(url => $url, auth => $baton, - config => $config, - pool => SVN::Pool->new, - auth_provider_callbacks => $callbacks); - $self->{svn_path} = $url; - $self->{repos_root} = $self->get_repos_root; - $self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/|$)##; - $RA = bless $self, $class; -} - -sub DESTROY { - # do not call the real DESTROY since we store ourselves in $RA -} - -sub get_log { - my ($self, @args) = @_; - my $pool = SVN::Pool->new; - splice(@args, 3, 1) if ($SVN::Core::VERSION le '1.2.0'); - my $ret = $self->SUPER::get_log(@args, $pool); - $pool->clear; - $ret; -} - -sub get_commit_editor { - my ($self, $log, $cb, $pool) = @_; - my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : (); - $self->SUPER::get_commit_editor($log, $cb, @lock, $pool); -} - -sub gs_do_update { - my ($self, $rev_a, $rev_b, $gs, $editor) = @_; - my $new = ($rev_a == $rev_b); - my $path = $gs->{path}; - - if ($new && -e $gs->{index}) { - unlink $gs->{index} or die - "Couldn't unlink index: $gs->{index}: $!\n"; - } - my $pool = SVN::Pool->new; - $editor->set_path_strip($path); - my (@pc) = split m#/#, $path; - my $reporter = $self->do_update($rev_b, (@pc ? shift @pc : ''), - 1, $editor, $pool); - my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : (); - - # Since we can't rely on svn_ra_reparent being available, we'll - # just have to do some magic with set_path to make it so - # we only want a partial path. - my $sp = ''; - my $final = join('/', @pc); - while (@pc) { - $reporter->set_path($sp, $rev_b, 0, @lock, $pool); - $sp .= '/' if length $sp; - $sp .= shift @pc; - } - die "BUG: '$sp' != '$final'\n" if ($sp ne $final); - - $reporter->set_path($sp, $rev_a, $new, @lock, $pool); - - $reporter->finish_report($pool); - $pool->clear; - $editor->{git_commit_ok}; -} - -# this requires SVN 1.4.3 or later (do_switch didn't work before 1.4.3, and -# svn_ra_reparent didn't work before 1.4) -sub gs_do_switch { - my ($self, $rev_a, $rev_b, $gs, $url_b, $editor) = @_; - my $path = $gs->{path}; - my $pool = SVN::Pool->new; - - my $full_url = $self->{url}; - my $old_url = $full_url; - $full_url .= "/$path" if length $path; - my ($ra, $reparented); - if ($old_url ne $full_url) { - if ($old_url !~ m#^svn(\+ssh)?://#) { - SVN::_Ra::svn_ra_reparent($self->{session}, $full_url, - $pool); - $self->{url} = $full_url; - $reparented = 1; - } else { - $ra = Git::SVN::Ra->new($full_url); - } - } - $ra ||= $self; - my $reporter = $ra->do_switch($rev_b, '', 1, $url_b, $editor, $pool); - my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : (); - $reporter->set_path('', $rev_a, 0, @lock, $pool); - $reporter->finish_report($pool); - - if ($reparented) { - SVN::_Ra::svn_ra_reparent($self->{session}, $old_url, $pool); - $self->{url} = $old_url; - } - - $pool->clear; - $editor->{git_commit_ok}; -} - -sub gs_fetch_loop_common { - my ($self, $base, $head, $gsv, $globs) = @_; - return if ($base > $head); - my $inc = $_log_window_size; - my ($min, $max) = ($base, $head < $base + $inc ? $head : $base + $inc); - my %common; - my $common_max = scalar @$gsv; - - foreach my $gs (@$gsv) { - my @tmp = split m#/#, $gs->{path}; - my $p = ''; - foreach (@tmp) { - $p .= length($p) ? "/$_" : $_; - $common{$p} ||= 0; - $common{$p}++; - } - } - $globs ||= []; - $common_max += scalar @$globs; - foreach my $glob (@$globs) { - my @tmp = split m#/#, $glob->{path}->{left}; - my $p = ''; - foreach (@tmp) { - $p .= length($p) ? "/$_" : $_; - $common{$p} ||= 0; - $common{$p}++; - } - } - - my $longest_path = ''; - foreach (sort {length $b <=> length $a} keys %common) { - if ($common{$_} == $common_max) { - $longest_path = $_; - last; - } - } - while (1) { - my %revs; - my $err; - my $err_handler = $SVN::Error::handler; - $SVN::Error::handler = sub { - ($err) = @_; - skip_unknown_revs($err); - }; - sub _cb { - my ($paths, $r, $author, $date, $log) = @_; - [ dup_changed_paths($paths), - { author => $author, date => $date, log => $log } ]; - } - $self->get_log([$longest_path], $min, $max, 0, 1, 1, - sub { $revs{$_[1]} = _cb(@_) }); - if ($err && $max >= $head) { - print STDERR "Path '$longest_path' ", - "was probably deleted:\n", - $err->expanded_message, - "\nWill attempt to follow ", - "revisions r$min .. r$max ", - "committed before the deletion\n"; - my $hi = $max; - while (--$hi >= $min) { - my $ok; - $self->get_log([$longest_path], $min, $hi, - 0, 1, 1, sub { - $ok ||= $_[1]; - $revs{$_[1]} = _cb(@_) }); - if ($ok) { - print STDERR "r$min .. r$ok OK\n"; - last; - } - } - } - $SVN::Error::handler = $err_handler; - - my %exists = map { $_->{path} => $_ } @$gsv; - foreach my $r (sort {$a <=> $b} keys %revs) { - my ($paths, $logged) = @{$revs{$r}}; - - foreach my $gs ($self->match_globs(\%exists, $paths, - $globs, $r)) { - if ($gs->rev_db_max >= $r) { - next; - } - next unless $gs->match_paths($paths, $r); - $gs->{logged_rev_props} = $logged; - if (my $last_commit = $gs->last_commit) { - $gs->assert_index_clean($last_commit); - } - my $log_entry = $gs->do_fetch($paths, $r); - if ($log_entry) { - $gs->do_git_commit($log_entry); - } - } - foreach my $g (@$globs) { - my $k = "svn-remote.$g->{remote}." . - "$g->{t}-maxRev"; - Git::SVN::tmp_config($k, $r); - } - } - # pre-fill the .rev_db since it'll eventually get filled in - # with '0' x40 if something new gets committed - foreach my $gs (@$gsv) { - next if defined $gs->rev_db_get($max); - $gs->rev_db_set($max, 0 x40); - } - foreach my $g (@$globs) { - my $k = "svn-remote.$g->{remote}.$g->{t}-maxRev"; - Git::SVN::tmp_config($k, $max); - } - last if $max >= $head; - $min = $max + 1; - $max += $inc; - $max = $head if ($max > $head); - } -} - -sub match_globs { - my ($self, $exists, $paths, $globs, $r) = @_; - - sub get_dir_check { - my ($self, $exists, $g, $r) = @_; - my @x = eval { $self->get_dir($g->{path}->{left}, $r) }; - return unless scalar @x == 3; - my $dirents = $x[0]; - foreach my $de (keys %$dirents) { - next if $dirents->{$de}->kind != $SVN::Node::dir; - my $p = $g->{path}->full_path($de); - next if $exists->{$p}; - next if (length $g->{path}->{right} && - ($self->check_path($p, $r) != - $SVN::Node::dir)); - $exists->{$p} = Git::SVN->init($self->{url}, $p, undef, - $g->{ref}->full_path($de), 1); - } +sub linearize_history { + my ($gs, $refs) = @_; + my %parents; + foreach my $c (@$refs) { + read_commit_parents(\%parents, $c); } - foreach my $g (@$globs) { - if (my $path = $paths->{"/$g->{path}->{left}"}) { - if ($path->{action} =~ /^[AR]$/) { - get_dir_check($self, $exists, $g, $r); - } - } - foreach (keys %$paths) { - if (/$g->{path}->{left_regex}/ && - !/$g->{path}->{regex}/) { - next if $paths->{$_}->{action} !~ /^[AR]$/; - get_dir_check($self, $exists, $g, $r); - } - next unless /$g->{path}->{regex}/; - my $p = $1; - my $pathname = $g->{path}->full_path($p); - next if $exists->{$pathname}; - $exists->{$pathname} = Git::SVN->init( - $self->{url}, $pathname, undef, - $g->{ref}->full_path($p), 1); - } - my $c = ''; - foreach (split m#/#, $g->{path}->{left}) { - $c .= "/$_"; - next unless ($paths->{$c} && - ($paths->{$c}->{action} =~ /^[AR]$/)); - get_dir_check($self, $exists, $g, $r); - } - } - values %$exists; -} - -sub minimize_url { - my ($self) = @_; - return $self->{url} if ($self->{url} eq $self->{repos_root}); - my $url = $self->{repos_root}; - my @components = split(m!/!, $self->{svn_path}); - my $c = ''; - do { - $url .= "/$c" if length $c; - eval { (ref $self)->new($url)->get_latest_revnum }; - } while ($@ && ($c = shift @components)); - $url; -} -sub can_do_switch { - my $self = shift; - unless (defined $can_do_switch) { - my $pool = SVN::Pool->new; - my $rep = eval { - $self->do_switch(1, '', 0, $self->{url}, - SVN::Delta::Editor->new, $pool); - }; - if ($@) { - $can_do_switch = 0; - } else { - $rep->abort_report($pool); - $can_do_switch = 1; - } - $pool->clear; - } - $can_do_switch; -} - -sub skip_unknown_revs { - my ($err) = @_; - 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):// - # 175007 - http(s):// (this repo required authorization, too...) - # More codes may be discovered later... - if ($errno == 175007 || $errno == 175002 || $errno == 160013) { - warn "W: Ignoring error from SVN, path probably ", - "does not exist: ($errno): ", - $err->expanded_message,"\n"; - return; - } - die "Error from SVN, ($errno): ", $err->expanded_message,"\n"; -} + my @linear_refs; + my %skip = (); + my $last_svn_commit = $gs->last_commit; + foreach my $c (reverse @$refs) { + next if $c eq $last_svn_commit; + last if $skip{$c}; -# 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; -} + unshift @linear_refs, $c; + $skip{$c} = 1; -package Git::SVN::Log; -use strict; -use warnings; -use POSIX qw/strftime/; -use vars qw/$TZ $limit $color $pager $non_recursive $verbose $oneline - %rusers $show_commit $incremental/; -my $l_fmt; - -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 @log = command(qw/cat-file commit/, $c->{c}); - shift @log while ($log[0] ne "\n"); - shift @log; - @{$c->{l}} = grep !/^git-svn-id: /, @log; - - (undef, $c->{r}, undef) = ::extract_metadata( - (grep(/^git-svn-id: /, @log))[-1]); - } - return defined $c->{r}; -} - -sub log_use_color { - return 1 if $color; - my ($dc, $dcvar); - $dcvar = 'color.diff'; - $dc = `git-config --get $dcvar`; - if ($dc eq '') { - # nothing at all; fallback to "diff.color" - $dcvar = 'diff.color'; - $dc = `git-config --get $dcvar`; - } - chomp($dc); - if ($dc eq 'auto') { - my $pc; - $pc = `git-config --get color.pager`; - if ($pc eq '') { - # does not have it -- fallback to pager.color - $pc = `git-config --bool --get pager.color`; - } - else { - $pc = `git-config --bool --get color.pager`; - if ($?) { - $pc = 'false'; - } + # we only want the first parent to diff against for linear + # history, we save the rest to inject when we finalize the + # svn commit + my $fp_a = verify_ref("$c~1"); + my $fp_b = shift @{$parents{$c}} if $parents{$c}; + if (!$fp_a || !$fp_b) { + die "Commit $c\n", + "has no parent commit, and therefore ", + "nothing to diff against.\n", + "You should be working from a repository ", + "originally created by git-svn\n"; } - chomp($pc); - if (-t *STDOUT || (defined $pager && $pc eq 'true')) { - return ($ENV{TERM} && $ENV{TERM} ne 'dumb'); + if ($fp_a ne $fp_b) { + die "$c~1 = $fp_a, however parsing commit $c ", + "revealed that:\n$c~1 = $fp_b\nBUG!\n"; } - return 0; - } - return 0 if $dc eq 'never'; - return 1 if $dc eq 'always'; - chomp($dc = `git-config --bool --get $dcvar`); - return ($dc eq 'true'); -} -sub git_svn_log_cmd { - my ($r_min, $r_max, @args) = @_; - my $head = 'HEAD'; - foreach my $x (@args) { - last if $x eq '--'; - next unless ::verify_ref("$x^0"); - $head = $x; - last; - } - - my $url = (::working_head_info($head))[0]; - my $gs = Git::SVN->find_by_url($url) || Git::SVN->_new; - my @cmd = (qw/log --abbrev-commit --pretty=raw --default/, - $gs->refname); - push @cmd, '-r' unless $non_recursive; - push @cmd, qw/--raw --name-status/ if $verbose; - push @cmd, '--color' if log_use_color(); - return @cmd unless defined $r_max; - if ($r_max == $r_min) { - push @cmd, '--max-count=1'; - if (my $c = $gs->rev_db_get($r_max)) { - push @cmd, $c; + foreach my $p (@{$parents{$c}}) { + $skip{$p} = 1; } - } else { - my ($c_min, $c_max); - $c_max = $gs->rev_db_get($r_max); - $c_min = $gs->rev_db_get($r_min); - if (defined $c_min && defined $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; -} - -# 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') { - $pager = undef; } + (\@linear_refs, \%parents); } -sub run_pager { - return unless -t *STDOUT; - pipe my $rfd, my $wfd or return; - defined(my $pid = fork) or ::fatal "Can't fork: $!\n"; - if (!$pid) { - open STDOUT, '>&', $wfd or - ::fatal "Can't redirect to stdout: $!\n"; - return; - } - open STDIN, '<&', $rfd or ::fatal "Can't redirect stdin: $!\n"; - $ENV{LESS} ||= 'FRSX'; - exec $pager or ::fatal "Can't run pager: $! ($pager)\n"; -} +sub find_file_type_and_diff_status { + my ($path) = @_; + return ('dir', '') if $path eq ''; -sub tz_to_s_offset { - my ($tz) = @_; - $tz =~ s/(\d\d)$//; - return ($1 * 60) + ($tz * 3600); -} + my $diff_output = + command_oneline(qw(diff --cached --name-status --), $path) || ""; + my $diff_status = (split(' ', $diff_output))[0] || ""; -sub get_author_info { - my ($dest, $author, $t, $tz) = @_; - $author =~ s/(?:^\s*|\s*$)//g; - $dest->{a_raw} = $author; - my $au; - if ($::_authors) { - $au = $rusers{$author} || undef; - } - if (!$au) { - ($au) = ($author =~ /<([^>]+)\@[^>]+>$/); - } - $dest->{t} = $t; - $dest->{tz} = $tz; - $dest->{a} = $au; - # 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; -} + my $ls_tree = command_oneline(qw(ls-tree HEAD), $path) || ""; -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; -} + return (undef, undef) if !$diff_status && !$ls_tree; -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); + if ($diff_status eq "A") { + return ("link", $diff_status) if -l $path; + return ("dir", $diff_status) if -d $path; + return ("file", $diff_status); } -} -sub show_commit_changed_paths { - my ($c) = @_; - return unless $c->{changed}; - print "Changed paths:\n", @{$c->{changed}}; -} - -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 > 0 - && $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"; - show_commit_changed_paths($c); - print "\n"; - print $_ foreach @$l; - } - } else { - print "1 line\n"; - show_commit_changed_paths($c); - print "\n"; + my $mode = (split(' ', $ls_tree))[0] || ""; - } - foreach my $x (qw/raw stat diff/) { - if ($c->{$x}) { - print "\n"; - print $_ foreach @{$c->{$x}} - } - } + return ("link", $diff_status) if $mode eq "120000"; + return ("dir", $diff_status) if $mode eq "040000"; + return ("file", $diff_status); } -sub cmd_show_log { - my (@args) = @_; - my ($r_min, $r_max); - my $r_last = -1; # prevent dupes - if (defined $TZ) { - $ENV{TZ} = $TZ; +sub md5sum { + my $arg = shift; + my $ref = ref $arg; + require Digest::MD5; + my $md5 = Digest::MD5->new(); + if ($ref eq 'GLOB' || $ref eq 'IO::File' || $ref eq 'File::Temp') { + $md5->addfile($arg) or croak $!; + } elsif ($ref eq 'SCALAR') { + $md5->add($$arg) or croak $!; + } elsif (!$ref) { + $md5->add($arg) or croak $!; } else { - delete $ENV{TZ}; - } - if (defined $::_revision) { - if ($::_revision =~ /^(\d+):(\d+)$/) { - ($r_min, $r_max) = ($1, $2); - } elsif ($::_revision =~ /^\d+$/) { - $r_min = $r_max = $::_revision; - } else { - ::fatal "-r$::_revision is not supported, use ", - "standard \'git log\' arguments instead\n"; - } - } - - config_pager(); - @args = (git_svn_log_cmd($r_min, $r_max, @args), @args); - my $log = command_output_pipe(@args); - run_pager(); - my (@k, $c, $d, $stat); - my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/; - while (<$log>) { - if (/^${esc_color}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 => $cmt }; - } elsif (/^${esc_color}author (.+) (\d+) ([\-\+]?\d+)$/o) { - get_author_info($c, $1, $2, $3); - } elsif (/^${esc_color}(?:tree|parent|committer) /o) { - # ignore - } elsif (/^${esc_color}:\d{6} \d{6} $::sha1_short/o) { - push @{$c->{raw}}, $_; - } elsif (/^${esc_color}[ACRMDT]\t/) { - # we could add $SVN->{svn_path} here, but that requires - # remote access at the moment (repo_path_split)... - s#^(${esc_color})([ACRMDT])\t#$1 $2 #o; - push @{$c->{changed}}, $_; - } elsif (/^${esc_color}diff /o) { - $d = 1; - push @{$c->{diff}}, $_; - } elsif ($d) { - push @{$c->{diff}}, $_; - } elsif (/^\ .+\ \|\s*\d+\ $esc_color[\+\-]* - $esc_color*[\+\-]*$esc_color$/x) { - $stat = 1; - push @{$c->{stat}}, $_; - } elsif ($stat && /^ \d+ files changed, \d+ insertions/) { - push @{$c->{stat}}, $_; - $stat = undef; - } elsif (/^${esc_color} (git-svn-id:.+)$/o) { - ($c->{url}, $c->{r}, undef) = ::extract_metadata($1); - } elsif (s/^${esc_color} //o) { - 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 || $oneline; -} - -package Git::SVN::Migration; -# these version numbers do NOT correspond to actual version numbers -# of git nor git-svn. They are just relative. -# -# v0 layout: .git/$id/info/url, refs/heads/$id-HEAD -# -# v1 layout: .git/$id/info/url, refs/remotes/$id -# -# v2 layout: .git/svn/$id/info/url, refs/remotes/$id -# -# v3 layout: .git/svn/$id, refs/remotes/$id -# - info/url may remain for backwards compatibility -# - this is what we migrate up to this layout automatically, -# - this will be used by git svn init on single branches -# v3.1 layout (auto migrated): -# - .rev_db => .rev_db.$UUID, .rev_db will remain as a symlink -# for backwards compatibility -# -# v4 layout: .git/svn/$repo_id/$id, refs/remotes/$repo_id/$id -# - this is only created for newly multi-init-ed -# repositories. Similar in spirit to the -# --use-separate-remotes option in git-clone (now default) -# - we do not automatically migrate to this (following -# the example set by core git) -use strict; -use warnings; -use Carp qw/croak/; -use File::Path qw/mkpath/; -use File::Basename qw/dirname basename/; -use vars qw/$_minimize/; - -sub migrate_from_v0 { - my $git_dir = $ENV{GIT_DIR}; - return undef unless -d $git_dir; - my ($fh, $ctx) = command_output_pipe(qw/rev-parse --symbolic --all/); - my $migrated = 0; - while (<$fh>) { - chomp; - my ($id, $orig_ref) = ($_, $_); - next unless $id =~ s#^refs/heads/(.+)-HEAD$#$1#; - next unless -f "$git_dir/$id/info/url"; - my $new_ref = "refs/remotes/$id"; - if (::verify_ref("$new_ref^0")) { - print STDERR "W: $orig_ref is probably an old ", - "branch used by an ancient version of ", - "git-svn.\n", - "However, $new_ref also exists.\n", - "We will not be able ", - "to use this branch until this ", - "ambiguity is resolved.\n"; - next; - } - print STDERR "Migrating from v0 layout...\n" if !$migrated; - print STDERR "Renaming ref: $orig_ref => $new_ref\n"; - command_noisy('update-ref', $new_ref, $orig_ref); - command_noisy('update-ref', '-d', $orig_ref, $orig_ref); - $migrated++; + fatal "Can't provide MD5 hash for unknown ref type: '", $ref, "'"; } - command_close_pipe($fh, $ctx); - print STDERR "Done migrating from v0 layout...\n" if $migrated; - $migrated; + return $md5->hexdigest(); } -sub migrate_from_v1 { - my $git_dir = $ENV{GIT_DIR}; - my $migrated = 0; - return $migrated unless -d $git_dir; - my $svn_dir = "$git_dir/svn"; - - # just in case somebody used 'svn' as their $id at some point... - return $migrated if -d $svn_dir && ! -f "$svn_dir/info/url"; - - print STDERR "Migrating from a git-svn v1 layout...\n"; - mkpath([$svn_dir]); - print STDERR "Data from a previous version of git-svn exists, but\n\t", - "$svn_dir\n\t(required for this version ", - "($::VERSION) of git-svn) does not. exist\n"; - my ($fh, $ctx) = command_output_pipe(qw/rev-parse --symbolic --all/); - while (<$fh>) { - my $x = $_; - 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 $dn; - if ($x eq 'svn') { # they used 'svn' as GIT_SVN_ID: - mkpath(["$git_dir/svn/svn"]); - print STDERR " - $git_dir/$x/info => ", - "$git_dir/svn/$x/info\n"; - rename "$git_dir/$x/info", "$git_dir/svn/$x/info" or - croak "$!: $x"; - # don't worry too much about these, they probably - # don't exist with repos this old (save for index, - # and we can easily regenerate that) - foreach my $f (qw/unhandled.log index .rev_db/) { - rename "$git_dir/$x/$f", "$git_dir/svn/$x/$f"; - } - } else { - print STDERR " - $git_dir/$x => $git_dir/svn/$x\n"; - rename "$git_dir/$x", "$git_dir/svn/$x" or - croak "$!: $x"; - } - $migrated++; - } - command_close_pipe($fh, $ctx); - print STDERR "Done migrating from a git-svn v1 layout\n"; - $migrated; -} - -sub read_old_urls { - my ($l_map, $pfx, $path) = @_; - my @dir; - foreach (<$path/*>) { - if (-r "$_/info/url") { - $pfx .= '/' if $pfx && $pfx !~ m!/$!; - my $ref_id = $pfx . basename $_; - my $url = ::file_to_s("$_/info/url"); - $l_map->{$ref_id} = $url; - } elsif (-d $_) { - push @dir, $_; - } - } - foreach (@dir) { - my $x = $_; - $x =~ s!^\Q$ENV{GIT_DIR}\E/svn/!!o; - read_old_urls($l_map, $x, $_); - } -} - -sub migrate_from_v2 { - my @cfg = command(qw/config -l/); - return if grep /^svn-remote\..+\.url=/, @cfg; - my %l_map; - read_old_urls(\%l_map, '', "$ENV{GIT_DIR}/svn"); - my $migrated = 0; - - foreach my $ref_id (sort keys %l_map) { - eval { Git::SVN->init($l_map{$ref_id}, '', undef, $ref_id) }; - if ($@) { - Git::SVN->init($l_map{$ref_id}, '', $ref_id, $ref_id); - } - $migrated++; - } - $migrated; -} - -sub minimize_connections { - my $r = Git::SVN::read_all_remotes(); - my $new_urls = {}; - my $root_repos = {}; - foreach my $repo_id (keys %$r) { - my $url = $r->{$repo_id}->{url} or next; - my $fetch = $r->{$repo_id}->{fetch} or next; - my $ra = Git::SVN::Ra->new($url); - - # skip existing cases where we already connect to the root - if (($ra->{url} eq $ra->{repos_root}) || - (Git::SVN::sanitize_remote_name($ra->{repos_root}) eq - $repo_id)) { - $root_repos->{$ra->{url}} = $repo_id; - next; - } - - my $root_ra = Git::SVN::Ra->new($ra->{repos_root}); - my $root_path = $ra->{url}; - $root_path =~ s#^\Q$ra->{repos_root}\E(/|$)##; - foreach my $path (keys %$fetch) { - my $ref_id = $fetch->{$path}; - my $gs = Git::SVN->new($ref_id, $repo_id, $path); - - # make sure we can read when connecting to - # a higher level of a repository - my ($last_rev, undef) = $gs->last_rev_commit; - if (!defined $last_rev) { - $last_rev = eval { - $root_ra->get_latest_revnum; - }; - next if $@; - } - my $new = $root_path; - $new .= length $path ? "/$path" : ''; - eval { - $root_ra->get_log([$new], $last_rev, $last_rev, - 0, 0, 1, sub { }); - }; - next if $@; - $new_urls->{$ra->{repos_root}}->{$new} = - { ref_id => $ref_id, - old_repo_id => $repo_id, - old_path => $path }; - } - } +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 @emptied; - foreach my $url (keys %$new_urls) { - # see if we can re-use an existing [svn-remote "repo_id"] - # instead of creating a(n ugly) new section: - my $repo_id = $root_repos->{$url} || - Git::SVN::sanitize_remote_name($url); - - my $fetch = $new_urls->{$url}; - foreach my $path (keys %$fetch) { - my $x = $fetch->{$path}; - Git::SVN->init($url, $path, $repo_id, $x->{ref_id}); - my $pfx = "svn-remote.$x->{old_repo_id}"; - - my $old_fetch = quotemeta("$x->{old_path}:". - "refs/remotes/$x->{ref_id}"); - command_noisy(qw/config --unset/, - "$pfx.fetch", '^'. $old_fetch . '$'); - delete $r->{$x->{old_repo_id}}-> - {fetch}->{$x->{old_path}}; - if (!keys %{$r->{$x->{old_repo_id}}->{fetch}}) { - command_noisy(qw/config --unset/, - "$pfx.url"); - push @emptied, $x->{old_repo_id} - } + my $res; + while ($res = sysread($in_fh, my $str, 1024)) { + $gz->gzwrite($str) or + die "Unable to write: ".$gz->gzerror()."!\n"; } + no warnings 'once'; # $File::Find::name would warn + unlink $_ or die "unlink $File::Find::name: $!\n"; + } elsif (-f $_ && basename($_) eq "index") { + unlink $_ or die "unlink $_: $!\n"; } - if (@emptied) { - my $file = $ENV{GIT_CONFIG} || $ENV{GIT_CONFIG_LOCAL} || - "$ENV{GIT_DIR}/config"; - print STDERR <<EOF; -The following [svn-remote] sections in your config file ($file) are empty -and can be safely removed: -EOF - print STDERR "[svn-remote \"$_\"]\n" foreach @emptied; - } -} - -sub migration_check { - migrate_from_v0(); - migrate_from_v1(); - migrate_from_v2(); - minimize_connections() if $_minimize; -} - -package Git::IndexInfo; -use strict; -use warnings; -use Git qw/command_input_pipe command_close_pipe/; - -sub new { - my ($class) = @_; - my ($gui, $ctx) = command_input_pipe(qw/update-index -z --index-info/); - bless { gui => $gui, ctx => $ctx, nr => 0}, $class; -} - -sub remove { - my ($self, $path) = @_; - if (print { $self->{gui} } '0 ', 0 x 40, "\t", $path, "\0") { - return ++$self->{nr}; - } - undef; -} - -sub update { - my ($self, $mode, $hash, $path) = @_; - if (print { $self->{gui} } $mode, ' ', $hash, "\t", $path, "\0") { - return ++$self->{nr}; - } - undef; -} - -sub DESTROY { - my ($self) = @_; - command_close_pipe($self->{gui}, $self->{ctx}); -} - -package Git::SVN::GlobSpec; -use strict; -use warnings; - -sub new { - my ($class, $glob) = @_; - my $re = $glob; - $re =~ s!/+$!!g; # no need for trailing slashes - my $nr = ($re =~ s!^(.*)\*(.*)$!\(\[^/\]+\)!g); - my ($left, $right) = ($1, $2); - if ($nr > 1) { - die "Only one '*' wildcard expansion ", - "is supported (got $nr): '$glob'\n"; - } elsif ($nr == 0) { - die "One '*' is needed for glob: '$glob'\n"; - } - $re = quotemeta($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"; - } - my $left_re = qr/^\/\Q$left\E(\/|$)/; - bless { left => $left, right => $right, left_regex => $left_re, - regex => qr/$re/, glob => $glob }, $class; -} - -sub full_path { - my ($self, $path) = @_; - return (length $self->{left} ? "$self->{left}/" : '') . - $path . (length $self->{right} ? "/$self->{right}" : ''); } __END__ |