X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiExternal.pm;h=30bb1a4579c74d8245d1eec7b66b9687bd526e71;hb=23af251dd607c4e75ab1e68063f2c885c48cc035;hp=b402eed4524cab6123191638581283ed01f6326c;hpb=16e016a3dddce6e65c7b69e4f4fd4b7e65b9ccc7;p=public-inbox.git diff --git a/lib/PublicInbox/LeiExternal.pm b/lib/PublicInbox/LeiExternal.pm index b402eed4..30bb1a45 100644 --- a/lib/PublicInbox/LeiExternal.pm +++ b/lib/PublicInbox/LeiExternal.pm @@ -9,7 +9,7 @@ use PublicInbox::Config; sub externals_each { my ($self, $cb, @arg) = @_; - my $cfg = $self->_lei_cfg(0); + my $cfg = $self->_lei_cfg; my %boost; for my $sec (grep(/\Aexternal\./, @{$cfg->{-section_order}})) { my $loc = substr($sec, length('external.')); @@ -31,7 +31,7 @@ sub externals_each { } sub ext_canonicalize { - my ($location) = @_; + my $location = $_[-1]; # $_[0] may be $lei if ($location !~ m!\Ahttps?://!) { PublicInbox::Config::rel2abs_collapsed($location); } else { @@ -44,29 +44,38 @@ sub ext_canonicalize { } } +# TODO: we will probably extract glob2re into a separate module for +# PublicInbox::Filter::Base and maybe other places my %re_map = ( '*' => '[^/]*?', '?' => '[^/]', '[' => '[', ']' => ']', ',' => ',' ); sub glob2re { - my ($re) = @_; + my $re = $_[-1]; # $_[0] may be $lei my $p = ''; my $in_bracket = 0; my $qm = 0; + my $schema_host_port = ''; + + # don't glob URL-looking things that look like IPv6 + if ($re =~ s!\A([a-z0-9\+]+://\[[a-f0-9\:]+\](?::[0-9]+)?/)!!i) { + $schema_host_port = quotemeta $1; # "http://[::1]:1234" + } my $changes = ($re =~ s!(.)! $re_map{$p eq '\\' ? '' : do { if ($1 eq '[') { ++$in_bracket } elsif ($1 eq ']') { --$in_bracket } + elsif ($1 eq ',') { ++$qm } # no change $p = $1; }} // do { $p = $1; ($p eq '-' && $in_bracket) ? $p : (++$qm, "\Q$p") }!sge); # bashism (also supported by curl): {a,b,c} => (a|b|c) - $re =~ s/([^\\]*)\\\{([^,]*?,[^\\]*?)\\\}/ - (my $in_braces = $2) =~ tr!,!|!; - $1."($in_braces)"; - /sge; - ($changes - $qm) ? $re : undef; + $changes += ($re =~ s/([^\\]*)\\\{([^,]*,[^\\]*)\\\}/ + (my $in_braces = $2) =~ tr!,!|!; + $1."($in_braces)"; + /sge); + ($changes - $qm) ? $schema_host_port.$re : undef; } # get canonicalized externals list matching $loc @@ -92,129 +101,38 @@ sub get_externals { return (ext_canonicalize($loc)); } if (scalar(@m) == 0) { - $self->fail("`$loc' is unknown"); + die "`$loc' is unknown\n"; } else { - $self->fail("`$loc' is ambiguous:\n", map { "\t$_\n" } @m); + die("`$loc' is ambiguous:\n", map { "\t$_\n" } @m, "\n"); } - (); } -sub lei_ls_external { - my ($self, $filter) = @_; - my $opt = $self->{opt}; - my $do_glob = !$opt->{globoff}; # glob by default - my ($OFS, $ORS) = $opt->{z} ? ("\0", "\0\0") : (" ", "\n"); - $filter //= '*'; - my $re = $do_glob ? glob2re($filter) : undef; - $re //= index($filter, '/') < 0 ? - qr!/\Q$filter\E/?\z! : # exact basename match - qr/\Q$filter\E/; # grep -F semantics - my @ext = externals_each($self, my $boost = {}); - @ext = $opt->{'invert-match'} ? grep(!/$re/, @ext) - : grep(/$re/, @ext); - if ($opt->{'local'} && !$opt->{remote}) { - @ext = grep(!m!\A[a-z\+]+://!, @ext); - } elsif ($opt->{remote} && !$opt->{'local'}) { - @ext = grep(m!\A[a-z\+]+://!, @ext); - } - for my $loc (@ext) { - $self->out($loc, $OFS, 'boost=', $boost->{$loc}, $ORS); +sub canonicalize_excludes { + my ($lei, $excludes) = @_; + my %x; + for my $loc (@$excludes) { + my @l = get_externals($lei, $loc, 1); + $x{$_} = 1 for @l; } + \%x; } -sub add_external_finish { - my ($self, $location) = @_; - my $cfg = $self->_lei_cfg(1); - my $new_boost = $self->{opt}->{boost} // 0; - my $key = "external.$location.boost"; - my $cur_boost = $cfg->{$key}; - return if defined($cur_boost) && $cur_boost == $new_boost; # idempotent - $self->lei_config($key, $new_boost); -} - -sub lei_add_external { - my ($self, $location) = @_; - $self->_lei_store(1)->write_prepare($self); - my $opt = $self->{opt}; - my $mirror = $opt->{mirror} // do { - my @fail; - for my $sw ($self->index_opt, $self->curl_opt, - qw(c no-torsocks torsocks inbox-version)) { - my ($f) = (split(/|/, $sw, 2))[0]; - next unless defined $opt->{$f}; - $f = length($f) == 1 ? "-$f" : "--$f"; - push @fail, $f; - } - if (scalar(@fail) == 1) { - return $self->("@fail requires --mirror"); - } elsif (@fail) { - my $last = pop @fail; - my $fail = join(', ', @fail); - return $self->("@fail and $last require --mirror"); - } - undef; - }; - my $new_boost = $opt->{boost} // 0; - $location = ext_canonicalize($location); - if (defined($mirror) && -d $location) { - $self->fail(<<""); # TODO: did you mean "update-external?" ---mirror destination `$location' already exists - - } - if ($location !~ m!\Ahttps?://! && !-d $location) { - $mirror // return $self->fail("$location not a directory"); - $mirror = ext_canonicalize($mirror); - require PublicInbox::LeiMirror; - PublicInbox::LeiMirror->start($self, $mirror => $location); - } else { - add_external_finish($self, $location); - } -} - -sub lei_forget_external { - my ($self, @locations) = @_; - my $cfg = $self->_lei_cfg(1); - my $quiet = $self->{opt}->{quiet}; - my %seen; - for my $loc (@locations) { - my (@unset, @not_found); - for my $l ($loc, ext_canonicalize($loc)) { - next if $seen{$l}++; - my $key = "external.$l.boost"; - delete($cfg->{$key}); - $self->_config('--unset', $key); - if ($? == 0) { - push @unset, $l; - } elsif (($? >> 8) == 5) { - push @not_found, $l; - } else { - $self->err("# --unset $key error"); - return $self->x_it($?); - } - } - if (@unset) { - next if $quiet; - $self->err("# $_ gone") for @unset; - } elsif (@not_found) { - $self->err("# $_ not found") for @not_found; - } # else { already exited - } -} - -sub _complete_url_common ($) { - my ($argv) = @_; +# returns an anonymous sub which returns an array of potential results +sub complete_url_prepare { + my $argv = $_[-1]; # $_[0] may be $lei # Workaround bash word-splitting URLs to ['https', ':', '//' ...] # Maybe there's a better way to go about this in # contrib/completion/lei-completion.bash my $re = ''; - my $cur = pop @$argv; + my $cur = pop(@$argv) // ''; if (@$argv) { my @x = @$argv; if ($cur eq ':' && @x) { push @x, $cur; $cur = ''; } - while (@x > 2 && $x[0] !~ /\Ahttps?\z/ && $x[1] ne ':') { + while (@x > 2 && $x[0] !~ /\A(?:http|nntp|imap)s?\z/i && + $x[1] ne ':') { shift @x; } if (@x >= 2) { # qw(https : hostname : 443) or qw(http :) @@ -224,38 +142,17 @@ sub _complete_url_common ($) { } $re = quotemeta($re); } - ($cur, $re); -} - -# shell completion helper called by lei__complete -sub _complete_forget_external { - my ($self, @argv) = @_; - my $cfg = $self->_lei_cfg(0); - my ($cur, $re) = _complete_url_common(\@argv); - # FIXME: bash completion off "http:" or "https:" when the last - # character is a colon doesn't work properly even if we're - # returning "//$HTTP_HOST/$PATH_INFO/", not sure why, could - # be a bash issue. - map { - my $x = substr($_, length('external.')); + my $match_cb = sub { + # the "//;" here (for AUTH=ANONYMOUS) interacts badly with + # bash tab completion, strip it out for now since our commands + # work w/o it. Not sure if there's a better solution... + $_[0] =~ s!//;AUTH=ANONYMOUS\@!//!i; + $_[0] =~ s!;!\\;!g; # only return the part specified on the CLI # don't duplicate if already 100% completed - $x =~ /\A$re(\Q$cur\E.*)/ ? ($cur eq $1 ? () : $1) : (); - } grep(/\Aexternal\.$re\Q$cur/, @{$cfg->{-section_order}}); -} - -sub _complete_add_external { # for bash, this relies on "compopt -o nospace" - my ($self, @argv) = @_; - my $cfg = $self->_lei_cfg(0); - my ($cur, $re) = _complete_url_common(\@argv); - require URI; - map { - my $u = URI->new(substr($_, length('external.'))); - my ($base) = ($u->path =~ m!((?:/?.*)?/)[^/]+/?\z!); - $u->path($base); - $u = $u->as_string; - $u =~ /\A$re(\Q$cur\E.*)/ ? ($cur eq $1 ? () : $1) : (); - } grep(m!\Aexternal\.https?://!, @{$cfg->{-section_order}}); + $_[0] =~ /\A$re(\Q$cur\E.*)/ ? ($cur eq $1 ? () : $1) : () + }; + wantarray ? ($re, $cur, $match_cb) : $match_cb; } 1;