X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiExternal.pm;h=accacf1a98d0ed15ed0ce079816380998a9912a6;hb=298751baed3ce7ae1549356152784b83220a31f0;hp=0378551a9d97cc3706df8f9f7dc3fb77e9053ab7;hpb=0d649fc15eab07976344a6ae32a946b2b1c32f4f;p=public-inbox.git diff --git a/lib/PublicInbox/LeiExternal.pm b/lib/PublicInbox/LeiExternal.pm index 0378551a..accacf1a 100644 --- a/lib/PublicInbox/LeiExternal.pm +++ b/lib/PublicInbox/LeiExternal.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2020 all contributors +# Copyright (C) 2020-2021 all contributors # License: AGPL-3.0+ # *-external commands of lei @@ -7,45 +7,187 @@ use strict; use v5.10.1; use parent qw(Exporter); our @EXPORT = qw(lei_ls_external lei_add_external lei_forget_external); +use PublicInbox::Config; -sub lei_ls_external { - my ($self, @argv) = @_; - my $stor = $self->_lei_store(0); +sub externals_each { + my ($self, $cb, @arg) = @_; my $cfg = $self->_lei_cfg(0); - my $out = $self->{1}; - my ($OFS, $ORS) = $self->{opt}->{z} ? ("\0", "\0\0") : (" ", "\n"); - my (%boost, @loc); + my %boost; for my $sec (grep(/\Aexternal\./, @{$cfg->{-section_order}})) { my $loc = substr($sec, length('external.')); $boost{$loc} = $cfg->{"$sec.boost"}; - push @loc, $loc; } - use sort 'stable'; + return \%boost if !wantarray && !$cb; + # highest boost first, but stable for alphabetic tie break - for (sort { $boost{$b} <=> $boost{$a} } sort keys %boost) { - # TODO: use miscidx and show docid so forget/set is easier - print $out $_, $OFS, 'boost=', $boost{$_}, $ORS; + use sort 'stable'; + my @order = sort { $boost{$b} <=> $boost{$a} } sort keys %boost; + return @order if !$cb; + for my $loc (@order) { + $cb->(@arg, $loc, $boost{$loc}); + } + @order; # scalar or array +} + +sub lei_ls_external { + my ($self, @argv) = @_; + my ($OFS, $ORS) = $self->{opt}->{z} ? ("\0", "\0\0") : (" ", "\n"); + externals_each($self, sub { + my ($loc, $boost_val) = @_; + $self->out($loc, $OFS, 'boost=', $boost_val, $ORS); + }); +} + +sub ext_canonicalize { + my ($location) = @_; + if ($location !~ m!\Ahttps?://!) { + PublicInbox::Config::rel2abs_collapsed($location); + } else { + require URI; + my $uri = URI->new($location)->canonical; + my $path = $uri->path . '/'; + $path =~ tr!/!/!s; # squeeze redundant '/' + $uri->path($path); + $uri->as_string; + } +} + +my %patmap = ('*' => '[^/]*?', '?' => '[^/]', '[' => '[', ']' => ']'); +sub glob2pat { + my ($glob) = @_; + $glob =~ s!(.)!$patmap{$1} || "\Q$1"!ge; + $glob; +} + +sub get_externals { + my ($self, $loc, $exclude) = @_; + return (ext_canonicalize($loc)) if -e $loc; + + my @m; + my @cur = externals_each($self); + my $do_glob = !$self->{opt}->{globoff}; # glob by default + if ($do_glob && ($loc =~ /[\*\?]/s || $loc =~ /\[.*\]/s)) { + my $re = glob2pat($loc); + @m = grep(m!$re!, @cur); + return @m if scalar(@m); + } elsif (index($loc, '/') < 0) { # exact basename match: + @m = grep(m!/\Q$loc\E/?\z!, @cur); + return @m if scalar(@m) == 1; + } elsif ($exclude) { # URL, maybe: + my $canon = ext_canonicalize($loc); + @m = grep(m!\A\Q$canon\E\z!, @cur); + return @m if scalar(@m) == 1; + } else { # URL: + return (ext_canonicalize($loc)); + } + if (scalar(@m) == 0) { + $self->fail("`$loc' is unknown"); + } else { + $self->fail("`$loc' is ambiguous:\n", map { "\t$_\n" } @m); } + (); } sub lei_add_external { - my ($self, $url_or_dir) = @_; + my ($self, $location) = @_; my $cfg = $self->_lei_cfg(1); - if ($url_or_dir !~ m!\Ahttps?://!) { - $url_or_dir = File::Spec->canonpath($url_or_dir); - } my $new_boost = $self->{opt}->{boost} // 0; - my $key = "external.$url_or_dir.boost"; + $location = ext_canonicalize($location); + if ($location !~ m!\Ahttps?://! && !-d $location) { + return $self->fail("$location not a directory"); + } + 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); - my $stor = $self->_lei_store(1); - # TODO: add to MiscIdx - $stor->done; + $self->_lei_store(1)->done; # just create the store } sub lei_forget_external { - # TODO + my ($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) = @_; + # 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; + if (@$argv) { + my @x = @$argv; + if ($cur eq ':' && @x) { + push @x, $cur; + $cur = ''; + } + while (@x > 2 && $x[0] !~ /\Ahttps?\z/ && $x[1] ne ':') { + shift @x; + } + if (@x >= 2) { # qw(https : hostname : 443) or qw(http :) + $re = join('', @x); + } else { # just filter out the flags and hope for the best + $re = join('', grep(!/^-/, @$argv)); + } + $re = quotemeta($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.')); + # 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}}); } 1;