diff options
Diffstat (limited to 'perl')
-rw-r--r-- | perl/Git.pm | 315 | ||||
-rw-r--r-- | perl/Git/I18N.pm | 2 | ||||
-rw-r--r-- | perl/Git/SVN.pm | 192 | ||||
-rw-r--r-- | perl/Git/SVN/Editor.pm | 60 | ||||
-rw-r--r-- | perl/Git/SVN/Fetcher.pm | 35 | ||||
-rw-r--r-- | perl/Git/SVN/Log.pm | 3 | ||||
-rw-r--r-- | perl/Git/SVN/Migration.pm | 2 | ||||
-rw-r--r-- | perl/Git/SVN/Prompt.pm | 2 | ||||
-rw-r--r-- | perl/Git/SVN/Ra.pm | 122 | ||||
-rw-r--r-- | perl/Git/SVN/Utils.pm | 2 | ||||
-rw-r--r-- | perl/private-Error.pm | 6 |
11 files changed, 588 insertions, 153 deletions
diff --git a/perl/Git.pm b/perl/Git.pm index 57a17160f9..19ef081103 100644 --- a/perl/Git.pm +++ b/perl/Git.pm @@ -60,7 +60,8 @@ require Exporter; version exec_path html_path hash_object git_cmd_try remote_refs prompt get_tz_offset - temp_acquire temp_release temp_reset temp_path); + credential credential_read credential_write + temp_acquire temp_is_locked temp_release temp_reset temp_path); =head1 DESCRIPTION @@ -269,13 +270,13 @@ sub command { if (not defined wantarray) { # Nothing to pepper the possible exception with. - _cmd_close($fh, $ctx); + _cmd_close($ctx, $fh); } elsif (not wantarray) { local $/; my $text = <$fh>; try { - _cmd_close($fh, $ctx); + _cmd_close($ctx, $fh); } catch Git::Error::Command with { # Pepper with the output: my $E = shift; @@ -288,7 +289,7 @@ sub command { my @lines = <$fh>; defined and chomp for @lines; try { - _cmd_close($fh, $ctx); + _cmd_close($ctx, $fh); } catch Git::Error::Command with { my $E = shift; $E->{'-outputref'} = \@lines; @@ -315,7 +316,7 @@ sub command_oneline { my $line = <$fh>; defined $line and chomp $line; try { - _cmd_close($fh, $ctx); + _cmd_close($ctx, $fh); } catch Git::Error::Command with { # Pepper with the output: my $E = shift; @@ -383,7 +384,7 @@ have more complicated structure. sub command_close_pipe { my ($self, $fh, $ctx) = _maybe_self(@_); $ctx ||= '<unknown>'; - _cmd_close($fh, $ctx); + _cmd_close($ctx, $fh); } =item command_bidi_pipe ( COMMAND [, ARGUMENTS... ] ) @@ -420,7 +421,7 @@ and it is the fourth value returned by C<command_bidi_pipe()>. The call idiom is: my ($pid, $in, $out, $ctx) = $r->command_bidi_pipe('cat-file --batch-check'); - print "000000000\n" $out; + print $out "000000000\n"; while (<$in>) { ... } $r->command_close_bidi_pipe($pid, $in, $out, $ctx); @@ -428,23 +429,26 @@ Note that you should not rely on whatever actually is in C<CTX>; currently it is simply the command name but in future the context might have more complicated structure. +C<PIPE_IN> and C<PIPE_OUT> may be C<undef> if they have been closed prior to +calling this function. This may be useful in a query-response type of +commands where caller first writes a query and later reads response, eg: + + my ($pid, $in, $out, $ctx) = $r->command_bidi_pipe('cat-file --batch-check'); + print $out "000000000\n"; + close $out; + while (<$in>) { ... } + $r->command_close_bidi_pipe($pid, $in, undef, $ctx); + +This idiom may prevent potential dead locks caused by data sent to the output +pipe not being flushed and thus not reaching the executed command. + =cut sub command_close_bidi_pipe { local $?; - my ($pid, $in, $out, $ctx) = @_; - foreach my $fh ($in, $out) { - unless (close $fh) { - if ($!) { - carp "error closing pipe: $!"; - } elsif ($? >> 8) { - throw Git::Error::Command($ctx, $? >>8); - } - } - } - + my ($self, $pid, $in, $out, $ctx) = _maybe_self(@_); + _cmd_close($ctx, (grep { defined } ($in, $out))); waitpid $pid, 0; - if ($? >> 8) { throw Git::Error::Command($ctx, $? >>8); } @@ -691,7 +695,7 @@ Retrieve the integer configuration C<VARIABLE>. The return value is simple decimal number. An optional value suffix of 'k', 'm', or 'g' in the config file will cause the value to be multiplied by 1024, 1048576 (1024^2), or 1073741824 (1024^3) prior to output. -It would return C<undef> if configuration variable is not defined, +It would return C<undef> if configuration variable is not defined. =cut @@ -700,7 +704,7 @@ sub config_int { } # Common subroutine to implement bulk of what the config* family of methods -# do. This curently wraps command('config') so it is not so fast. +# do. This currently wraps command('config') so it is not so fast. sub _config_common { my ($opts) = shift @_; my ($self, $var) = _maybe_self(@_); @@ -860,6 +864,73 @@ sub ident_person { return "$ident[0] <$ident[1]>"; } +=item parse_mailboxes + +Return an array of mailboxes extracted from a string. + +=cut + +sub parse_mailboxes { + my $re_comment = qr/\((?:[^)]*)\)/; + my $re_quote = qr/"(?:[^\"\\]|\\.)*"/; + my $re_word = qr/(?:[^]["\s()<>:;@\\,.]|\\.)+/; + + # divide the string in tokens of the above form + my $re_token = qr/(?:$re_quote|$re_word|$re_comment|\S)/; + my @tokens = map { $_ =~ /\s*($re_token)\s*/g } @_; + + # add a delimiter to simplify treatment for the last mailbox + push @tokens, ","; + + my (@addr_list, @phrase, @address, @comment, @buffer) = (); + foreach my $token (@tokens) { + if ($token =~ /^[,;]$/) { + # if buffer still contains undeterminated strings + # append it at the end of @address or @phrase + if (@address) { + push @address, @buffer; + } else { + push @phrase, @buffer; + } + + my $str_phrase = join ' ', @phrase; + my $str_address = join '', @address; + my $str_comment = join ' ', @comment; + + # quote are necessary if phrase contains + # special characters + if ($str_phrase =~ /[][()<>:;@\\,.\000-\037\177]/) { + $str_phrase =~ s/(^|[^\\])"/$1/g; + $str_phrase = qq["$str_phrase"]; + } + + # add "<>" around the address if necessary + if ($str_address ne "" && $str_phrase ne "") { + $str_address = qq[<$str_address>]; + } + + my $str_mailbox = "$str_phrase $str_address $str_comment"; + $str_mailbox =~ s/^\s*|\s*$//g; + push @addr_list, $str_mailbox if ($str_mailbox); + + @phrase = @address = @comment = @buffer = (); + } elsif ($token =~ /^\(/) { + push @comment, $token; + } elsif ($token eq "<") { + push @phrase, (splice @address), (splice @buffer); + } elsif ($token eq ">") { + push @address, (splice @buffer); + } elsif ($token eq "@") { + push @address, (splice @buffer), "@"; + } elsif ($token eq ".") { + push @address, (splice @buffer), "."; + } else { + push @buffer, $token; + } + } + + return @addr_list; +} =item hash_object ( TYPE, FILENAME ) @@ -1020,13 +1091,163 @@ sub _close_cat_blob { } +=item credential_read( FILEHANDLE ) + +Reads credential key-value pairs from C<FILEHANDLE>. Reading stops at EOF or +when an empty line is encountered. Each line must be of the form C<key=value> +with a non-empty key. Function returns hash with all read values. Any white +space (other than new-line character) is preserved. + +=cut + +sub credential_read { + my ($self, $reader) = _maybe_self(@_); + my %credential; + while (<$reader>) { + chomp; + if ($_ eq '') { + last; + } elsif (!/^([^=]+)=(.*)$/) { + throw Error::Simple("unable to parse git credential data:\n$_"); + } + $credential{$1} = $2; + } + return %credential; +} + +=item credential_write( FILEHANDLE, CREDENTIAL_HASHREF ) + +Writes credential key-value pairs from hash referenced by +C<CREDENTIAL_HASHREF> to C<FILEHANDLE>. Keys and values cannot contain +new-lines or NUL bytes characters, and key cannot contain equal signs nor be +empty (if they do Error::Simple is thrown). Any white space is preserved. If +value for a key is C<undef>, it will be skipped. + +If C<'url'> key exists it will be written first. (All the other key-value +pairs are written in sorted order but you should not depend on that). Once +all lines are written, an empty line is printed. + +=cut + +sub credential_write { + my ($self, $writer, $credential) = _maybe_self(@_); + my ($key, $value); + + # Check if $credential is valid prior to writing anything + while (($key, $value) = each %$credential) { + if (!defined $key || !length $key) { + throw Error::Simple("credential key empty or undefined"); + } elsif ($key =~ /[=\n\0]/) { + throw Error::Simple("credential key contains invalid characters: $key"); + } elsif (defined $value && $value =~ /[\n\0]/) { + throw Error::Simple("credential value for key=$key contains invalid characters: $value"); + } + } + + for $key (sort { + # url overwrites other fields, so it must come first + return -1 if $a eq 'url'; + return 1 if $b eq 'url'; + return $a cmp $b; + } keys %$credential) { + if (defined $credential->{$key}) { + print $writer $key, '=', $credential->{$key}, "\n"; + } + } + print $writer "\n"; +} + +sub _credential_run { + my ($self, $credential, $op) = _maybe_self(@_); + my ($pid, $reader, $writer, $ctx) = command_bidi_pipe('credential', $op); + + credential_write $writer, $credential; + close $writer; + + if ($op eq "fill") { + %$credential = credential_read $reader; + } + if (<$reader>) { + throw Error::Simple("unexpected output from git credential $op response:\n$_\n"); + } + + command_close_bidi_pipe($pid, $reader, undef, $ctx); +} + +=item credential( CREDENTIAL_HASHREF [, OPERATION ] ) + +=item credential( CREDENTIAL_HASHREF, CODE ) + +Executes C<git credential> for a given set of credentials and specified +operation. In both forms C<CREDENTIAL_HASHREF> needs to be a reference to +a hash which stores credentials. Under certain conditions the hash can +change. + +In the first form, C<OPERATION> can be C<'fill'>, C<'approve'> or C<'reject'>, +and function will execute corresponding C<git credential> sub-command. If +it's omitted C<'fill'> is assumed. In case of C<'fill'> the values stored in +C<CREDENTIAL_HASHREF> will be changed to the ones returned by the C<git +credential fill> command. The usual usage would look something like: + + my %cred = ( + 'protocol' => 'https', + 'host' => 'example.com', + 'username' => 'bob' + ); + Git::credential \%cred; + if (try_to_authenticate($cred{'username'}, $cred{'password'})) { + Git::credential \%cred, 'approve'; + ... do more stuff ... + } else { + Git::credential \%cred, 'reject'; + } + +In the second form, C<CODE> needs to be a reference to a subroutine. The +function will execute C<git credential fill> to fill the provided credential +hash, then call C<CODE> with C<CREDENTIAL_HASHREF> as the sole argument. If +C<CODE>'s return value is defined, the function will execute C<git credential +approve> (if return value yields true) or C<git credential reject> (if return +value is false). If the return value is undef, nothing at all is executed; +this is useful, for example, if the credential could neither be verified nor +rejected due to an unrelated network error. The return value is the same as +what C<CODE> returns. With this form, the usage might look as follows: + + if (Git::credential { + 'protocol' => 'https', + 'host' => 'example.com', + 'username' => 'bob' + }, sub { + my $cred = shift; + return !!try_to_authenticate($cred->{'username'}, + $cred->{'password'}); + }) { + ... do more stuff ... + } + +=cut + +sub credential { + my ($self, $credential, $op_or_code) = (_maybe_self(@_), 'fill'); + + if ('CODE' eq ref $op_or_code) { + _credential_run $credential, 'fill'; + my $ret = $op_or_code->($credential); + if (defined $ret) { + _credential_run $credential, $ret ? 'approve' : 'reject'; + } + return $ret; + } else { + _credential_run $credential, $op_or_code; + } +} + { # %TEMP_* Lexical Context my (%TEMP_FILEMAP, %TEMP_FILES); =item temp_acquire ( NAME ) -Attempts to retreive the temporary file mapped to the string C<NAME>. If an +Attempts to retrieve the temporary file mapped to the string C<NAME>. If an associated temp file has not been created this session or was closed, it is created, cached, and set for autoflush and binmode. @@ -1052,6 +1273,35 @@ sub temp_acquire { $temp_fd; } +=item temp_is_locked ( NAME ) + +Returns true if the internal lock created by a previous C<temp_acquire()> +call with C<NAME> is still in effect. + +When temp_acquire is called on a C<NAME>, it internally locks the temporary +file mapped to C<NAME>. That lock will not be released until C<temp_release()> +is called with either the original C<NAME> or the L<File::Handle> that was +returned from the original call to temp_acquire. + +Subsequent attempts to call C<temp_acquire()> with the same C<NAME> will fail +unless there has been an intervening C<temp_release()> call for that C<NAME> +(or its corresponding L<File::Handle> that was returned by the original +C<temp_acquire()> call). + +If true is returned by C<temp_is_locked()> for a C<NAME>, an attempt to +C<temp_acquire()> the same C<NAME> will cause an error unless +C<temp_release> is first called on that C<NAME> (or its corresponding +L<File::Handle> that was returned by the original C<temp_acquire()> call). + +=cut + +sub temp_is_locked { + my ($self, $name) = _maybe_self(@_); + my $temp_fd = \$TEMP_FILEMAP{$name}; + + defined $$temp_fd && $$temp_fd->opened && $TEMP_FILES{$$temp_fd}{locked}; +} + =item temp_release ( NAME ) =item temp_release ( FILEHANDLE ) @@ -1111,8 +1361,11 @@ sub _temp_cache { $tmpdir = $self->repo_path(); } - ($$temp_fd, $fname) = File::Temp->tempfile( - 'Git_XXXXXX', UNLINK => 1, DIR => $tmpdir, + my $n = $name; + $n =~ s/\W/_/g; # no strange chars + + ($$temp_fd, $fname) = File::Temp::tempfile( + "Git_${n}_XXXXXX", UNLINK => 1, DIR => $tmpdir, ) or throw Error::Simple("couldn't open new temp file"); $$temp_fd->autoflush; @@ -1335,12 +1588,12 @@ sub _command_common_pipe { if (not defined $pid) { throw Error::Simple("open failed: $!"); } elsif ($pid == 0) { - if (defined $opts{STDERR}) { - close STDERR; - } if ($opts{STDERR}) { open (STDERR, '>&', $opts{STDERR}) or die "dup failed: $!"; + } elsif (defined $opts{STDERR}) { + open (STDERR, '>', '/dev/null') + or die "opening /dev/null failed: $!"; } _cmd_exec($self, $cmd, @args); } @@ -1375,9 +1628,11 @@ sub _execv_git_cmd { exec('git', @_); } # Close pipe to a subprocess. sub _cmd_close { - my ($fh, $ctx) = @_; - if (not close $fh) { - if ($!) { + my $ctx = shift @_; + foreach my $fh (@_) { + if (close $fh) { + # nop + } elsif ($!) { # It's just close, no point in fatalities carp "error closing pipe: $!"; } elsif ($? >> 8) { diff --git a/perl/Git/I18N.pm b/perl/Git/I18N.pm index 40dd897191..f889fd6da9 100644 --- a/perl/Git/I18N.pm +++ b/perl/Git/I18N.pm @@ -68,7 +68,7 @@ Git::I18N - Perl interface to Git's Gettext localizations print __("Welcome to Git!\n"); - printf __("The following error occured: %s\n"), $error; + printf __("The following error occurred: %s\n"), $error; =head1 DESCRIPTION diff --git a/perl/Git/SVN.pm b/perl/Git/SVN.pm index 8c84560a49..152fb7e927 100644 --- a/perl/Git/SVN.pm +++ b/perl/Git/SVN.pm @@ -9,11 +9,10 @@ use vars qw/$_no_metadata $_use_log_author $_add_author_from $_localtime/; use Carp qw/croak/; use File::Path qw/mkpath/; -use File::Copy qw/copy/; use IPC::Open3; use Memoize; # core since 5.8.0, Jul 2002 -use Memoize::Storable; use POSIX qw(:signal_h); +use Time::Local; use Git qw( command @@ -32,11 +31,7 @@ use Git::SVN::Utils qw( add_path_to_url ); -my $can_use_yaml; -BEGIN { - $can_use_yaml = eval { require Git::SVN::Memoize::YAML; 1}; -} - +my $memo_backend; our $_follow_parent = 1; our $_minimize_url = 'unset'; our $default_repo_id = 'svn'; @@ -480,8 +475,8 @@ sub refname { # It cannot end with a slash /, we'll throw up on this because # SVN can't have directories with a slash in their name, either: if ($refname =~ m{/$}) { - die "ref: '$refname' ends with a trailing slash, this is ", - "not permitted by git nor Subversion\n"; + die "ref: '$refname' ends with a trailing slash; this is ", + "not permitted by git or Subversion\n"; } # It cannot have ASCII control character space, tilde ~, caret ^, @@ -490,7 +485,7 @@ sub refname { # # Additionally, % must be escaped because it is used for escaping # and we want our escaped refname to be reversible - $refname =~ s{([ \%~\^:\?\*\[\t])}{uc sprintf('%%%02x',ord($1))}eg; + $refname =~ s{([ \%~\^:\?\*\[\t])}{sprintf('%%%02X',ord($1))}eg; # no slash-separated component can begin with a dot . # /.* becomes /%2E* @@ -1178,7 +1173,7 @@ sub find_parent_branch { or die "SVN connection failed somewhere...\n"; } print STDERR "Successfully followed parent\n" unless $::_q > 1; - return $self->make_log_entry($rev, [$parent], $ed); + return $self->make_log_entry($rev, [$parent], $ed, $r0, $branch_from); } return undef; } @@ -1191,7 +1186,7 @@ sub do_fetch { # 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): + # want to break the original ref or lose copypath info): if (my $log_entry = $self->find_parent_branch($paths, $rev)) { push @{$log_entry->{parents}}, $lc; return $log_entry; @@ -1210,7 +1205,7 @@ sub do_fetch { unless ($self->ra->gs_do_update($last_rev, $rev, $self, $ed)) { die "SVN connection failed somewhere...\n"; } - $self->make_log_entry($rev, \@parents, $ed); + $self->make_log_entry($rev, \@parents, $ed, $last_rev, $self->path); } sub mkemptydirs { @@ -1321,7 +1316,7 @@ sub get_untracked { 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$/x) or + (\d\d?)\:(\d\d)\:(\d\d)\.\d*Z$/x) or croak "Unable to parse date: $date\n"; my $parsed_date; # Set next. @@ -1332,7 +1327,7 @@ sub parse_svn_date { $ENV{TZ} = 'UTC'; my $epoch_in_UTC = - POSIX::strftime('%s', $S, $M, $H, $d, $m - 1, $Y - 1900); + Time::Local::timelocal($S, $M, $H, $d, $m - 1, $Y - 1900); # Determine our local timezone (including DST) at the # time of $epoch_in_UTC. $Git::SVN::Log::TZ stored the @@ -1433,7 +1428,7 @@ sub check_author { } sub find_extra_svk_parents { - my ($self, $ed, $tickets, $parents) = @_; + my ($self, $tickets, $parents) = @_; # aha! svk:merge property changed... my @tickets = split "\n", $tickets; my @known_parents; @@ -1478,9 +1473,9 @@ sub find_extra_svk_parents { sub lookup_svn_merge { my $uuid = shift; my $url = shift; - my $merge = shift; + my $source = shift; + my $revs = shift; - my ($source, $revs) = split ":", $merge; my $path = $source; $path =~ s{^/}{}; my $gs = Git::SVN->find_by_url($url.$source, $url, $path); @@ -1493,13 +1488,18 @@ sub lookup_svn_merge { my @merged_commit_ranges; # find the tip for my $range ( @ranges ) { + if ($range =~ /[*]$/) { + warn "W: Ignoring partial merge in svn:mergeinfo " + ."dirprop: $source:$range\n"; + next; + } my ($bottom, $top) = split "-", $range; $top ||= $bottom; my $bottom_commit = $gs->find_rev_after( $bottom, 1, $top ); my $top_commit = $gs->find_rev_before( $top, 1, $bottom ); unless ($top_commit and $bottom_commit) { - warn "W:unknown path/rev in svn:mergeinfo " + warn "W: unknown path/rev in svn:mergeinfo " ."dirprop: $source:$range\n"; next; } @@ -1532,7 +1532,7 @@ sub _rev_list { @rv; } -sub check_cherry_pick { +sub check_cherry_pick2 { my $base = shift; my $tip = shift; my $parents = shift; @@ -1547,7 +1547,8 @@ sub check_cherry_pick { delete $commits{$commit}; } } - return (keys %commits); + my @k = (keys %commits); + return (scalar @k, $k[0]); } sub has_no_changes { @@ -1572,7 +1573,16 @@ sub tie_for_persistent_memoization { my $hash = shift; my $path = shift; - if ($can_use_yaml) { + unless ($memo_backend) { + if (eval { require Git::SVN::Memoize::YAML; 1}) { + $memo_backend = 1; + } else { + require Memoize::Storable; + $memo_backend = -1; + } + } + + if ($memo_backend > 0) { tie %$hash => 'Git::SVN::Memoize::YAML', "$path.yaml"; } else { tie %$hash => 'Memoize::Storable', "$path.db", 'nstore'; @@ -1592,7 +1602,7 @@ sub tie_for_persistent_memoization { mkpath([$cache_path]) unless -d $cache_path; my %lookup_svn_merge_cache; - my %check_cherry_pick_cache; + my %check_cherry_pick2_cache; my %has_no_changes_cache; tie_for_persistent_memoization(\%lookup_svn_merge_cache, @@ -1602,11 +1612,11 @@ sub tie_for_persistent_memoization { LIST_CACHE => ['HASH' => \%lookup_svn_merge_cache], ; - tie_for_persistent_memoization(\%check_cherry_pick_cache, - "$cache_path/check_cherry_pick"); - memoize 'check_cherry_pick', + tie_for_persistent_memoization(\%check_cherry_pick2_cache, + "$cache_path/check_cherry_pick2"); + memoize 'check_cherry_pick2', SCALAR_CACHE => 'FAULT', - LIST_CACHE => ['HASH' => \%check_cherry_pick_cache], + LIST_CACHE => ['HASH' => \%check_cherry_pick2_cache], ; tie_for_persistent_memoization(\%has_no_changes_cache, @@ -1622,7 +1632,7 @@ sub tie_for_persistent_memoization { $memoized = 0; Memoize::unmemoize 'lookup_svn_merge'; - Memoize::unmemoize 'check_cherry_pick'; + Memoize::unmemoize 'check_cherry_pick2'; Memoize::unmemoize 'has_no_changes'; } @@ -1633,7 +1643,8 @@ sub tie_for_persistent_memoization { return unless -d $cache_path; for my $cache_file (("$cache_path/lookup_svn_merge", - "$cache_path/check_cherry_pick", + "$cache_path/check_cherry_pick", # old + "$cache_path/check_cherry_pick2", "$cache_path/has_no_changes")) { for my $suffix (qw(yaml db)) { my $file = "$cache_file.$suffix"; @@ -1687,11 +1698,49 @@ sub parents_exclude { return @excluded; } +# Compute what's new in svn:mergeinfo. +sub mergeinfo_changes { + my ($self, $old_path, $old_rev, $path, $rev, $mergeinfo_prop) = @_; + my %minfo = map {split ":", $_ } split "\n", $mergeinfo_prop; + my $old_minfo = {}; + + my $ra = $self->ra; + # Give up if $old_path isn't in the repo. + # This is probably a merge on a subtree. + if ($ra->check_path($old_path, $old_rev) != $SVN::Node::dir) { + warn "W: ignoring svn:mergeinfo on $old_path, ", + "directory didn't exist in r$old_rev\n"; + return {}; + } + my (undef, undef, $props) = $ra->get_dir($old_path, $old_rev); + if (defined $props->{"svn:mergeinfo"}) { + my %omi = map {split ":", $_ } split "\n", + $props->{"svn:mergeinfo"}; + $old_minfo = \%omi; + } + + my %changes = (); + foreach my $p (keys %minfo) { + my $a = $old_minfo->{$p} || ""; + my $b = $minfo{$p}; + # Omit merged branches whose ranges lists are unchanged. + next if $a eq $b; + # Remove any common range list prefix. + ($a ^ $b) =~ /^[\0]*/; + my $common_prefix = rindex $b, ",", $+[0] - 1; + $changes{$p} = substr $b, $common_prefix + 1; + } + print STDERR "Checking svn:mergeinfo changes since r$old_rev: ", + scalar(keys %minfo), " sources, ", + scalar(keys %changes), " changed\n"; + + return \%changes; +} # note: this function should only be called if the various dirprops # have actually changed sub find_extra_svn_parents { - my ($self, $ed, $mergeinfo, $parents) = @_; + my ($self, $mergeinfo, $parents) = @_; # aha! svk:merge property changed... memoize_svn_mergeinfo_functions(); @@ -1700,14 +1749,15 @@ sub find_extra_svn_parents { # history. Then, we figure out which git revisions are in # that tip, but not this revision. If all of those revisions # are now marked as merge, we can add the tip as a parent. - my @merges = split "\n", $mergeinfo; + my @merges = sort keys %$mergeinfo; my @merge_tips; my $url = $self->url; my $uuid = $self->ra_uuid; my @all_ranges; for my $merge ( @merges ) { my ($tip_commit, @ranges) = - lookup_svn_merge( $uuid, $url, $merge ); + lookup_svn_merge( $uuid, $url, + $merge, $mergeinfo->{$merge} ); unless (!$tip_commit or grep { $_ eq $tip_commit } @$parents ) { push @merge_tips, $tip_commit; @@ -1723,8 +1773,9 @@ sub find_extra_svn_parents { # check merge tips for new parents my @new_parents; for my $merge_tip ( @merge_tips ) { - my $spec = shift @merges; + my $merge = shift @merges; next unless $merge_tip and $excluded{$merge_tip}; + my $spec = "$merge:$mergeinfo->{$merge}"; # check out 'new' tips my $merge_base; @@ -1744,19 +1795,17 @@ sub find_extra_svn_parents { } # double check that there are no missing non-merge commits - my (@incomplete) = check_cherry_pick( + my ($ninc, $ifirst) = check_cherry_pick2( $merge_base, $merge_tip, $parents, @all_ranges, ); - if ( @incomplete ) { - warn "W:svn cherry-pick ignored ($spec) - missing " - .@incomplete." commit(s) (eg $incomplete[0])\n"; + if ($ninc) { + warn "W: svn cherry-pick ignored ($spec) - missing " . + "$ninc commit(s) (eg $ifirst)\n"; } else { - warn - "Found merge parent (svn:mergeinfo prop): ", - $merge_tip, "\n"; + warn "Found merge parent ($spec): ", $merge_tip, "\n"; push @new_parents, $merge_tip; } } @@ -1782,23 +1831,20 @@ sub find_extra_svn_parents { } sub make_log_entry { - my ($self, $rev, $parents, $ed) = @_; + my ($self, $rev, $parents, $ed, $parent_rev, $parent_path) = @_; my $untracked = $self->get_untracked($ed); my @parents = @$parents; - my $ps = $ed->{path_strip} || ""; - for my $path ( grep { m/$ps/ } %{$ed->{dir_prop}} ) { - my $props = $ed->{dir_prop}{$path}; - if ( $props->{"svk:merge"} ) { - $self->find_extra_svk_parents - ($ed, $props->{"svk:merge"}, \@parents); - } - if ( $props->{"svn:mergeinfo"} ) { - $self->find_extra_svn_parents - ($ed, - $props->{"svn:mergeinfo"}, - \@parents); - } + my $props = $ed->{dir_prop}{$self->path}; + if ( $props->{"svk:merge"} ) { + $self->find_extra_svk_parents($props->{"svk:merge"}, \@parents); + } + if ( $props->{"svn:mergeinfo"} ) { + my $mi_changes = $self->mergeinfo_changes + ($parent_path, $parent_rev, + $self->path, $rev, + $props->{"svn:mergeinfo"}); + $self->find_extra_svn_parents($mi_changes, \@parents); } open my $un, '>>', "$self->{dir}/unhandled.log" or croak $!; @@ -1954,11 +2000,25 @@ sub rebuild_from_rev_db { unlink $path or croak "unlink: $!"; } +#define a global associate map to record rebuild status +my %rebuild_status; +#define a global associate map to record rebuild verify status +my %rebuild_verify_status; + sub rebuild { my ($self) = @_; my $map_path = $self->map_path; my $partial = (-e $map_path && ! -z $map_path); - return unless ::verify_ref($self->refname.'^0'); + my $verify_key = $self->refname.'^0'; + if (!$rebuild_verify_status{$verify_key}) { + my $verify_result = ::verify_ref($verify_key); + if ($verify_result) { + $rebuild_verify_status{$verify_key} = 1; + } + } + if (!$rebuild_verify_status{$verify_key}) { + return; + } if (!$partial && ($self->use_svm_props || $self->no_metadata)) { my $rev_db = $self->rev_db_path; $self->rebuild_from_rev_db($rev_db); @@ -1972,10 +2032,21 @@ sub rebuild { print "Rebuilding $map_path ...\n" if (!$partial); my ($base_rev, $head) = ($partial ? $self->rev_map_max_norebuild(1) : (undef, undef)); + my $key_value = ($head ? "$head.." : "") . $self->refname; + if (exists $rebuild_status{$key_value}) { + print "Done rebuilding $map_path\n" if (!$partial || !$head); + my $rev_db_path = $self->rev_db_path; + if (-f $self->rev_db_path) { + unlink $self->rev_db_path or croak "unlink: $!"; + } + $self->unlink_rev_db_symlink; + return; + } my ($log, $ctx) = - command_output_pipe(qw/rev-list --pretty=raw --reverse/, - ($head ? "$head.." : "") . $self->refname, + command_output_pipe(qw/rev-list --pretty=raw --reverse/, + $key_value, '--'); + $rebuild_status{$key_value} = 1; my $metadata_url = $self->metadata_url; remove_username($metadata_url); my $svn_uuid = $self->rewrite_uuid || $self->ra_uuid; @@ -2121,8 +2192,9 @@ sub rev_map_set { # both of these options make our .rev_db file very, very important # and we can't afford to lose it because rebuild() won't work if ($self->use_svm_props || $self->no_metadata) { + require File::Copy; $sync = 1; - copy($db, $db_lock) or die "rev_map_set(@_): ", + File::Copy::copy($db, $db_lock) or die "rev_map_set(@_): ", "Failed to copy: ", "$db => $db_lock ($!)\n"; } else { @@ -2298,7 +2370,7 @@ sub _new { # Older repos imported by us used $GIT_DIR/svn/foo instead of # $GIT_DIR/svn/refs/remotes/foo when tracking refs/remotes/foo - if ($ref_id =~ m{^refs/remotes/(.*)}) { + if ($ref_id =~ m{^refs/remotes/(.+)}) { my $old_dir = "$ENV{GIT_DIR}/svn/$1"; if (-d $old_dir && ! -d $dir) { $dir = $old_dir; @@ -2369,7 +2441,7 @@ sub map_path { sub uri_encode { my ($f) = @_; - $f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg; + $f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#sprintf("%%%02X",ord($1))#eg; $f } diff --git a/perl/Git/SVN/Editor.pm b/perl/Git/SVN/Editor.pm index 3bbc20a054..c50176eec9 100644 --- a/perl/Git/SVN/Editor.pm +++ b/perl/Git/SVN/Editor.pm @@ -5,7 +5,6 @@ use warnings; use SVN::Core; use SVN::Delta; use Carp qw/croak/; -use IO::File; use Git qw/command command_oneline command_noisy command_output_pipe command_input_pipe command_close_pipe command_bidi_pipe command_close_bidi_pipe/; @@ -145,7 +144,8 @@ sub repo_path { sub url_path { my ($self, $path) = @_; if ($self->{url} =~ m#^https?://#) { - $path =~ s!([^~a-zA-Z0-9_./-])!uc sprintf("%%%02x",ord($1))!eg; + # characters are taken from subversion/libsvn_subr/path.c + $path =~ s#([^~a-zA-Z0-9_./!$&'()*+,-])#sprintf("%%%02X",ord($1))#eg; } $self->{url} . '/' . $self->repo_path($path); } @@ -287,6 +287,40 @@ sub apply_autoprops { } } +sub check_attr { + my ($attr,$path) = @_; + my $val = command_oneline("check-attr", $attr, "--", $path); + if ($val) { $val =~ s/^[^:]*:\s*[^:]*:\s*(.*)\s*$/$1/; } + return $val; +} + +sub apply_manualprops { + my ($self, $file, $fbat) = @_; + my $pending_properties = check_attr( "svn-properties", $file ); + if ($pending_properties eq "") { return; } + # Parse the list of properties to set. + my @props = split(/;/, $pending_properties); + # TODO: get existing properties to compare to + # - this fails for add so currently not done + # my $existing_props = ::get_svnprops($file); + my $existing_props = {}; + # TODO: caching svn properties or storing them in .gitattributes + # would make that faster + foreach my $prop (@props) { + # Parse 'name=value' syntax and set the property. + if ($prop =~ /([^=]+)=(.*)/) { + my ($n,$v) = ($1,$2); + for ($n, $v) { + s/^\s+//; s/\s+$//; + } + my $existing = $existing_props->{$n}; + if (!defined($existing) || $existing ne $v) { + $self->change_file_prop($fbat, $n, $v); + } + } + } +} + sub A { my ($self, $m, $deletions) = @_; my ($dir, $file) = split_path($m->{file_b}); @@ -295,6 +329,7 @@ sub A { undef, -1); print "\tA\t$m->{file_b}\n" unless $::_q; $self->apply_autoprops($file, $fbat); + $self->apply_manualprops($m->{file_b}, $fbat); $self->chg_file($fbat, $m); $self->close_file($fbat,undef,$self->{pool}); } @@ -303,9 +338,14 @@ sub C { my ($self, $m, $deletions) = @_; my ($dir, $file) = split_path($m->{file_b}); my $pbat = $self->ensure_path($dir, $deletions); + # workaround for a bug in svn serf backend (v1.8.5 and below): + # store third argument to ->add_file() in a local variable, to make it + # have the same lifetime as $fbat + my $upa = $self->url_path($m->{file_a}); my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat, - $self->url_path($m->{file_a}), $self->{r}); + $upa, $self->{r}); print "\tC\t$m->{file_a} => $m->{file_b}\n" unless $::_q; + $self->apply_manualprops($m->{file_b}, $fbat); $self->chg_file($fbat, $m); $self->close_file($fbat,undef,$self->{pool}); } @@ -322,10 +362,13 @@ sub R { my ($self, $m, $deletions) = @_; my ($dir, $file) = split_path($m->{file_b}); my $pbat = $self->ensure_path($dir, $deletions); + # workaround for a bug in svn serf backend, see comment in C() above + my $upa = $self->url_path($m->{file_a}); my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat, - $self->url_path($m->{file_a}), $self->{r}); + $upa, $self->{r}); print "\tR\t$m->{file_a} => $m->{file_b}\n" unless $::_q; $self->apply_autoprops($file, $fbat); + $self->apply_manualprops($m->{file_b}, $fbat); $self->chg_file($fbat, $m); $self->close_file($fbat,undef,$self->{pool}); @@ -341,6 +384,7 @@ sub M { 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; + $self->apply_manualprops($m->{file_b}, $fbat); $self->chg_file($fbat, $m); $self->close_file($fbat,undef,$self->{pool}); } @@ -358,12 +402,12 @@ sub T { mode_a => $m->{mode_a}, mode_b => '000000', sha1_a => $m->{sha1_a}, sha1_b => '0' x 40, chg => 'D', file_b => $m->{file_b} - }); + }, $deletions); $self->A({ mode_a => '000000', mode_b => $m->{mode_b}, sha1_a => '0' x 40, sha1_b => $m->{sha1_b}, chg => 'A', file_b => $m->{file_b} - }); + }, $deletions); return; } @@ -498,6 +542,8 @@ sub apply_diff { 1; __END__ +=head1 NAME + Git::SVN::Editor - commit driver for "git svn set-tree" and dcommit =head1 SYNOPSIS @@ -539,7 +585,7 @@ The interface will change as git-svn evolves. =head1 DEPENDENCIES Subversion perl bindings, -the core L<Carp> and L<IO::File> modules, +the core L<Carp> module, and git's L<Git> helper module. C<Git::SVN::Editor> has not been tested using callers other than diff --git a/perl/Git/SVN/Fetcher.pm b/perl/Git/SVN/Fetcher.pm index 046a7a2f31..d8c21ad915 100644 --- a/perl/Git/SVN/Fetcher.pm +++ b/perl/Git/SVN/Fetcher.pm @@ -1,12 +1,12 @@ package Git::SVN::Fetcher; -use vars qw/@ISA $_ignore_regex $_preserve_empty_dirs $_placeholder_filename - @deleted_gpath %added_placeholder $repo_id/; +use vars qw/@ISA $_ignore_regex $_include_regex $_preserve_empty_dirs + $_placeholder_filename @deleted_gpath %added_placeholder + $repo_id/; use strict; use warnings; use SVN::Delta; use Carp qw/croak/; use File::Basename qw/dirname/; -use IO::File qw//; use Git qw/command command_oneline command_noisy command_output_pipe command_input_pipe command_close_pipe command_bidi_pipe command_close_bidi_pipe/; @@ -33,6 +33,10 @@ sub new { my $v = eval { command_oneline('config', '--get', $k) }; $self->{ignore_regex} = $v; + $k = "svn-remote.$repo_id.include-paths"; + $v = eval { command_oneline('config', '--get', $k) }; + $self->{include_regex} = $v; + $k = "svn-remote.$repo_id.preserve-empty-dirs"; $v = eval { command_oneline('config', '--get', '--bool', $k) }; if ($v && $v eq 'true') { @@ -117,11 +121,18 @@ sub in_dot_git { } # return value: 0 -- don't ignore, 1 -- ignore +# This will also check whether the path is explicitly included sub is_path_ignored { my ($self, $path) = @_; return 1 if in_dot_git($path); return 1 if defined($self->{ignore_regex}) && $path =~ m!$self->{ignore_regex}!; + return 0 if defined($self->{include_regex}) && + $path =~ m!$self->{include_regex}!; + return 0 if defined($_include_regex) && + $path =~ m!$_include_regex!; + return 1 if defined($self->{include_regex}); + return 1 if defined($_include_regex); return 0 unless defined($_ignore_regex); return 1 if $path =~ m!$_ignore_regex!o; return 0; @@ -303,11 +314,21 @@ sub change_file_prop { sub apply_textdelta { my ($self, $fb, $exp) = @_; return undef if $self->is_path_ignored($fb->{path}); - my $fh = $::_repository->temp_acquire('svn_delta'); + my $suffix = 0; + ++$suffix while $::_repository->temp_is_locked("svn_delta_${$}_$suffix"); + my $fh = $::_repository->temp_acquire("svn_delta_${$}_$suffix"); # $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 = $::_repository->temp_acquire('git_blob'); + my $base = $::_repository->temp_acquire("git_blob_${$}_$suffix"); + # close_file may call temp_acquire on 'svn_hash', but because of the + # call chain, if the temp_acquire call from close_file ends up being the + # call that first creates the 'svn_hash' temp file, then the FileHandle + # that's created as a result will end up in an SVN::Pool that we clear + # in SVN::Ra::gs_fetch_loop_common. Avoid that by making sure the + # 'svn_hash' FileHandle is already created before close_file is called. + my $tmp_fh = $::_repository->temp_acquire('svn_hash'); + $::_repository->temp_release($tmp_fh, 1); if ($fb->{blob}) { my ($base_is_link, $size); @@ -512,6 +533,8 @@ sub stash_placeholder_list { 1; __END__ +=head1 NAME + Git::SVN::Fetcher - tree delta consumer for "git svn fetch" =head1 SYNOPSIS @@ -584,7 +607,7 @@ developing git-svn. =head1 DEPENDENCIES L<SVN::Delta> from the Subversion perl bindings, -the core L<Carp>, L<File::Basename>, and L<IO::File> modules, +the core L<Carp> and L<File::Basename> modules, and git's L<Git> helper module. C<Git::SVN::Fetcher> has not been tested using callers other than diff --git a/perl/Git/SVN/Log.pm b/perl/Git/SVN/Log.pm index 3f8350a57d..664105357c 100644 --- a/perl/Git/SVN/Log.pm +++ b/perl/Git/SVN/Log.pm @@ -116,7 +116,8 @@ sub run_pager { return; } open STDIN, '<&', $rfd or fatal "Can't redirect stdin: $!"; - $ENV{LESS} ||= 'FRSX'; + $ENV{LESS} ||= 'FRX'; + $ENV{LV} ||= '-c'; exec $pager or fatal "Can't run pager: $! ($pager)"; } diff --git a/perl/Git/SVN/Migration.pm b/perl/Git/SVN/Migration.pm index 30daf35465..cf6ffa7581 100644 --- a/perl/Git/SVN/Migration.pm +++ b/perl/Git/SVN/Migration.pm @@ -1,6 +1,6 @@ package Git::SVN::Migration; # these version numbers do NOT correspond to actual version numbers -# of git nor git-svn. They are just relative. +# of git or git-svn. They are just relative. # # v0 layout: .git/$id/info/url, refs/heads/$id-HEAD # diff --git a/perl/Git/SVN/Prompt.pm b/perl/Git/SVN/Prompt.pm index 74daa7a597..e940b08505 100644 --- a/perl/Git/SVN/Prompt.pm +++ b/perl/Git/SVN/Prompt.pm @@ -125,6 +125,8 @@ sub _read_password { 1; __END__ +=head1 NAME + Git::SVN::Prompt - authentication callbacks for git-svn =head1 SYNOPSIS diff --git a/perl/Git/SVN/Ra.pm b/perl/Git/SVN/Ra.pm index 049c97bfaf..4a499fcb38 100644 --- a/perl/Git/SVN/Ra.pm +++ b/perl/Git/SVN/Ra.pm @@ -2,7 +2,7 @@ package Git::SVN::Ra; use vars qw/@ISA $config_dir $_ignore_refs_regex $_log_window_size/; use strict; use warnings; -use SVN::Client; +use Memoize; use Git::SVN::Utils qw( canonicalize_url canonicalize_path @@ -32,7 +32,16 @@ BEGIN { } } +# serf has a bug that leads to a coredump upon termination if the +# remote access object is left around (not fixed yet in serf 1.3.1). +# Explicitly free it to work around the issue. +END { + $RA = undef; + $ra_invalid = 1; +} + sub _auth_providers () { + require SVN::Client; my @rv = ( SVN::Client::get_simple_provider(), SVN::Client::get_ssl_server_trust_file_provider(), @@ -68,6 +77,40 @@ sub _auth_providers () { \@rv; } +sub prepare_config_once { + SVN::_Core::svn_config_ensure($config_dir, undef); + my ($baton, $callbacks) = SVN::Core::auth_open_helper(_auth_providers); + my $config = SVN::Core::config_get_config($config_dir); + my $dont_store_passwords = 1; + my $conf_t = $config->{'config'}; + + no warnings 'once'; + # The usage of $SVN::_Core::SVN_CONFIG_* variables + # produces warnings that variables are used only once. + # I had not found the better way to shut them up, so + # the warnings of type 'once' are disabled in this block. + if (SVN::_Core::svn_config_get_bool($conf_t, + $SVN::_Core::SVN_CONFIG_SECTION_AUTH, + $SVN::_Core::SVN_CONFIG_OPTION_STORE_PASSWORDS, + 1) == 0) { + SVN::_Core::svn_auth_set_parameter($baton, + $SVN::_Core::SVN_AUTH_PARAM_DONT_STORE_PASSWORDS, + bless (\$dont_store_passwords, "_p_void")); + } + if (SVN::_Core::svn_config_get_bool($conf_t, + $SVN::_Core::SVN_CONFIG_SECTION_AUTH, + $SVN::_Core::SVN_CONFIG_OPTION_STORE_AUTH_CREDS, + 1) == 0) { + $Git::SVN::Prompt::_no_auth_cache = 1; + } + + return ($config, $baton, $callbacks); +} # no warnings 'once' + +INIT { + Memoize::memoize '_auth_providers'; + Memoize::memoize 'prepare_config_once'; +} sub new { my ($class, $url) = @_; @@ -76,34 +119,8 @@ sub new { ::_req_svn(); - SVN::_Core::svn_config_ensure($config_dir, undef); - my ($baton, $callbacks) = SVN::Core::auth_open_helper(_auth_providers); - my $config = SVN::Core::config_get_config($config_dir); $RA = undef; - my $dont_store_passwords = 1; - my $conf_t = ${$config}{'config'}; - { - no warnings 'once'; - # The usage of $SVN::_Core::SVN_CONFIG_* variables - # produces warnings that variables are used only once. - # I had not found the better way to shut them up, so - # the warnings of type 'once' are disabled in this block. - if (SVN::_Core::svn_config_get_bool($conf_t, - $SVN::_Core::SVN_CONFIG_SECTION_AUTH, - $SVN::_Core::SVN_CONFIG_OPTION_STORE_PASSWORDS, - 1) == 0) { - SVN::_Core::svn_auth_set_parameter($baton, - $SVN::_Core::SVN_AUTH_PARAM_DONT_STORE_PASSWORDS, - bless (\$dont_store_passwords, "_p_void")); - } - if (SVN::_Core::svn_config_get_bool($conf_t, - $SVN::_Core::SVN_CONFIG_SECTION_AUTH, - $SVN::_Core::SVN_CONFIG_OPTION_STORE_AUTH_CREDS, - 1) == 0) { - $Git::SVN::Prompt::_no_auth_cache = 1; - } - } # no warnings 'once' - + my ($config, $baton, $callbacks) = prepare_config_once(); my $self = SVN::Ra->new(url => $url, auth => $baton, config => $config, pool => SVN::Pool->new, @@ -158,7 +175,17 @@ sub get_dir { } } my $pool = SVN::Pool->new; - my ($d, undef, $props) = $self->SUPER::get_dir($dir, $r, $pool); + my ($d, undef, $props); + + if (::compare_svn_version('1.4.0') >= 0) { + # n.b. in addition to being potentially more efficient, + # this works around what appears to be a bug in some + # SVN 1.8 versions + my $kind = 1; # SVN_DIRENT_KIND + ($d, undef, $props) = $self->get_dir2($dir, $r, $kind, $pool); + } else { + ($d, undef, $props) = $self->SUPER::get_dir($dir, $r, $pool); + } my %dirents = map { $_ => { kind => $d->{$_}->kind } } keys %$d; $pool->clear; if ($r != $cache->{r}) { @@ -169,10 +196,6 @@ sub get_dir { wantarray ? (\%dirents, $r, $props) : \%dirents; } -sub DESTROY { - # do not call the real DESTROY since we store ourselves in $RA -} - # get_log(paths, start, end, limit, # discover_changed_paths, strict_node_history, receiver) sub get_log { @@ -224,7 +247,10 @@ sub get_log { $ret; } +# uncommon, only for ancient SVN (<= 1.4.2) sub trees_match { + require IO::File; + require SVN::Client; my ($self, $url1, $rev1, $url2, $rev2) = @_; my $ctx = SVN::Client->new(auth => _auth_providers); my $out = IO::File->new_tmpfile; @@ -295,7 +321,7 @@ sub gs_do_switch { my $full_url = add_path_to_url( $self->url, $path ); my ($ra, $reparented); - if ($old_url =~ m#^svn(\+ssh)?://# || + if ($old_url =~ m#^svn(\+\w+)?://# || ($full_url =~ m#^https?://# && canonicalize_url($full_url) ne $full_url)) { $_[0] = undef; @@ -368,10 +394,22 @@ sub longest_common_path { sub gs_fetch_loop_common { my ($self, $base, $head, $gsv, $globs) = @_; return if ($base > $head); + # Make sure the cat_blob open2 FileHandle is created before calling + # SVN::Pool::new_default so that it does not incorrectly end up in the pool. + $::_repository->_open_cat_blob_if_needed; + my $gpool = SVN::Pool->new_default; + my $ra_url = $self->url; + my $reload_ra = sub { + $_[0] = undef; + $self = undef; + $RA = undef; + $gpool->clear; + $self = Git::SVN::Ra->new($ra_url); + $ra_invalid = undef; + }; my $inc = $_log_window_size; my ($min, $max) = ($base, $head < $base + $inc ? $head : $base + $inc); my $longest_path = longest_common_path($gsv, $globs); - my $ra_url = $self->url; my $find_trailing_edge; while (1) { my %revs; @@ -418,7 +456,7 @@ sub gs_fetch_loop_common { my %exists = map { $_->path => $_ } @$gsv; foreach my $r (sort {$a <=> $b} keys %revs) { - my ($paths, $logged) = @{$revs{$r}}; + my ($paths, $logged) = @{delete $revs{$r}}; foreach my $gs ($self->match_globs(\%exists, $paths, $globs, $r)) { @@ -441,13 +479,7 @@ sub gs_fetch_loop_common { "$g->{t}-maxRev"; Git::SVN::tmp_config($k, $r); } - if ($ra_invalid) { - $_[0] = undef; - $self = undef; - $RA = undef; - $self = Git::SVN::Ra->new($ra_url); - $ra_invalid = undef; - } + $reload_ra->() if $ra_invalid; } # pre-fill the .rev_db since it'll eventually get filled in # with '0' x40 if something new gets committed @@ -464,6 +496,8 @@ sub gs_fetch_loop_common { $min = $max + 1; $max += $inc; $max = $head if ($max > $head); + + $reload_ra->(); } Git::SVN::gc(); } @@ -627,6 +661,8 @@ sub skip_unknown_revs { 1; __END__ +=head1 NAME + Git::SVN::Ra - Subversion remote access functions for git-svn =head1 SYNOPSIS diff --git a/perl/Git/SVN/Utils.pm b/perl/Git/SVN/Utils.pm index 8b8cf3755c..3d1a0933a2 100644 --- a/perl/Git/SVN/Utils.pm +++ b/perl/Git/SVN/Utils.pm @@ -155,7 +155,7 @@ sub _canonicalize_url_path { my @parts; foreach my $part (split m{/+}, $uri_path) { - $part =~ s/([^~\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg; + $part =~ s/([^!\$%&'()*+,.\/\w:=\@_`~-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg; push @parts, $part; } diff --git a/perl/private-Error.pm b/perl/private-Error.pm index 11e9cd9a02..6098135ae2 100644 --- a/perl/private-Error.pm +++ b/perl/private-Error.pm @@ -630,7 +630,7 @@ Only one finally block may be specified per try block =head2 CONSTRUCTORS The C<Error> object is implemented as a HASH. This HASH is initialized -with the arguments that are passed to it's constructor. The elements +with the arguments that are passed to its constructor. The elements that are used by, or are retrievable by the C<Error> class are listed below, other classes may add to these. @@ -763,13 +763,13 @@ to the constructor. =item Error::Simple -This class can be used to hold simple error strings and values. It's +This class can be used to hold simple error strings and values. Its constructor takes two arguments. The first is a text value, the second is a numeric value. These values are what will be returned by the overload methods. If the text value ends with C<at file line 1> as $@ strings do, then -this infomation will be used to set the C<-file> and C<-line> arguments +this information will be used to set the C<-file> and C<-line> arguments of the error object. This class is used internally if an eval'd block die's with an error |