X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLEI.pm;h=0bd52a469925041995bb3d09d2e2e3d42815cf94;hb=a00fdf39b4ec4ed045f28c29c79c8dcb9abac836;hp=8825fa4379d87006880a715b64abe9621060cca1;hpb=232f8e376fe2856c8d34092e33a2c0750734c285;p=public-inbox.git diff --git a/lib/PublicInbox/LEI.pm b/lib/PublicInbox/LEI.pm index 8825fa43..0bd52a46 100644 --- a/lib/PublicInbox/LEI.pm +++ b/lib/PublicInbox/LEI.pm @@ -27,7 +27,7 @@ use Time::HiRes qw(stat); # ctime comparisons for config cache use File::Path qw(mkpath); use File::Spec; our $quit = \&CORE::exit; -our ($current_lei, $errors_log, $listener); +our ($current_lei, $errors_log, $listener, $oldset); my ($recv_cmd, $send_cmd); my $GLP = Getopt::Long::Parser->new; $GLP->configure(qw(gnu_getopt no_ignore_case auto_abbrev)); @@ -83,7 +83,7 @@ sub rel2abs ($$) { File::Spec->rel2abs($p, $pwd); } -sub _store_path ($) { +sub store_path ($) { my ($self) = @_; rel2abs($self, ($self->{env}->{XDG_DATA_HOME} // ($self->{env}->{HOME} // '/nonexistent').'/.local/share') @@ -97,6 +97,21 @@ sub _config_path ($) { .'/lei/config'); } +sub cache_dir ($) { + my ($self) = @_; + rel2abs($self, ($self->{env}->{XDG_CACHE_HOME} // + ($self->{env}->{HOME} // '/nonexistent').'/.cache') + .'/lei'); +} + +sub ale { + my ($self) = @_; + $self->{ale} //= do { + require PublicInbox::LeiALE; + $self->_lei_cfg(1)->{ale} //= PublicInbox::LeiALE->new($self); + }; +} + sub index_opt { # TODO: drop underscore variants everywhere, they're undocumented qw(fsync|sync! jobs|j=i indexlevel|L=s compact @@ -104,88 +119,92 @@ sub index_opt { batch_size|batch-size=s skip-docdata) } +my @c_opt = qw(c=s@ C=s@ quiet|q); + # we generate shell completion + help using %CMD and %OPTDESC, # see lei__complete() and PublicInbox::LeiHelp # command => [ positional_args, 1-line description, Getopt::Long option spec ] our %CMD = ( # sorted in order of importance/use: -'q' => [ '--stdin|SEARCH_TERMS...', 'search for messages matching terms', qw( - save-as=s output|mfolder|o=s format|f=s dedupe|d=s threads|t+ augment|a +'q' => [ '--stdin|SEARCH_TERMS...', 'search for messages matching terms', + 'stdin|', # /|\z/ must be first for lone dash + qw(save-as=s output|mfolder|o=s format|f=s dedupe|d=s threads|t+ sort|s=s reverse|r offset=i remote! local! external! pretty - include|I=s@ exclude=s@ only=s@ jobs|j=s globoff|g stdin| - import-remote! - alert=s@ mua=s no-torsocks torsocks=s verbose|v+ quiet|q C=s@), + include|I=s@ exclude=s@ only=s@ jobs|j=s globoff|g augment|a + import-remote! import-before! lock=s@ rsyncable + alert=s@ mua=s no-torsocks torsocks=s verbose|v+), @c_opt, PublicInbox::LeiQuery::curl_opt(), opt_dash('limit|n=i', '[0-9]+') ], 'show' => [ 'MID|OID', 'show a given object (Message-ID or object ID)', - qw(type=s solve! format|f=s dedupe|d=s threads|t remote local! C=s@), - pass_through('git show') ], + qw(type=s solve! format|f=s dedupe|d=s threads|t remote local! + verbose|v+), @c_opt, pass_through('git show') ], 'add-external' => [ 'LOCATION', 'add/set priority of a publicinbox|extindex for extra matches', - qw(boost=i c=s@ mirror=s no-torsocks torsocks=s inbox-version=i), - qw(quiet|q verbose|v+ C=s@), - index_opt(), PublicInbox::LeiQuery::curl_opt() ], + qw(boost=i mirror=s no-torsocks torsocks=s inbox-version=i + verbose|v+), @c_opt, index_opt(), + PublicInbox::LeiQuery::curl_opt() ], 'ls-external' => [ '[FILTER]', 'list publicinbox|extindex locations', - qw(format|f=s z|0 globoff|g invert-match|v local remote C=s@) ], + qw(format|f=s z|0 globoff|g invert-match|v local remote), @c_opt ], 'forget-external' => [ 'LOCATION...|--prune', 'exclude further results from a publicinbox|extindex', - qw(prune quiet|q C=s@) ], + qw(prune), @c_opt ], 'ls-query' => [ '[FILTER...]', 'list saved search queries', - qw(name-only format|f=s z C=s@) ], -'rm-query' => [ 'QUERY_NAME', 'remove a saved search', qw(C=s@) ], -'mv-query' => [ qw(OLD_NAME NEW_NAME), 'rename a saved search', qw(C=s@) ], + qw(name-only format|f=s), @c_opt ], +'rm-query' => [ 'QUERY_NAME', 'remove a saved search', @c_opt ], +'mv-query' => [ qw(OLD_NAME NEW_NAME), 'rename a saved search', @c_opt ], 'plonk' => [ '--threads|--from=IDENT', 'exclude mail matching From: or threads from non-Message-ID searches', - qw(stdin| threads|t from|f=s mid=s oid=s C=s@) ], + qw(stdin| threads|t from|f=s mid=s oid=s), @c_opt ], 'mark' => [ 'MESSAGE_FLAGS...', 'set/unset keywords on message(s) from stdin', - qw(stdin| oid=s exact by-mid|mid:s C=s@) ], + qw(stdin| oid=s exact by-mid|mid:s), @c_opt ], 'forget' => [ '[--stdin|--oid=OID|--by-mid=MID]', "exclude message(s) on stdin from `q' search results", - qw(stdin| oid=s exact by-mid|mid:s quiet|q C=s@) ], + qw(stdin| oid=s exact by-mid|mid:s), @c_opt ], 'purge-mailsource' => [ 'LOCATION|--all', 'remove imported messages from IMAP, Maildirs, and MH', - qw(exact! all jobs:i indexed C=s@) ], + qw(exact! all jobs:i indexed), @c_opt ], # code repos are used for `show' to solve blobs from patch mails 'add-coderepo' => [ 'DIRNAME', 'add or set priority of a git code repo', - qw(boost=i C=s@) ], + qw(boost=i), @c_opt ], 'ls-coderepo' => [ '[FILTER_TERMS...]', - 'list known code repos', qw(format|f=s z C=s@) ], + 'list known code repos', qw(format|f=s z), @c_opt ], 'forget-coderepo' => [ 'DIRNAME', 'stop using repo to solve blobs from patches', - qw(prune C=s@) ], + qw(prune), @c_opt ], 'add-watch' => [ 'LOCATION', 'watch for new messages and flag changes', qw(import! kw|keywords|flags! interval=s recursive|r - exclude=s include=s C=s@) ], + exclude=s include=s), @c_opt ], 'ls-watch' => [ '[FILTER...]', 'list active watches with numbers and status', - qw(format|f=s z C=s@) ], -'pause-watch' => [ '[WATCH_NUMBER_OR_FILTER]', qw(all local remote C=s@) ], -'resume-watch' => [ '[WATCH_NUMBER_OR_FILTER]', qw(all local remote C=s@) ], + qw(format|f=s z), @c_opt ], +'pause-watch' => [ '[WATCH_NUMBER_OR_FILTER]', qw(all local remote), @c_opt ], +'resume-watch' => [ '[WATCH_NUMBER_OR_FILTER]', qw(all local remote), @c_opt ], 'forget-watch' => [ '{WATCH_NUMBER|--prune}', 'stop and forget a watch', - qw(prune C=s@) ], + qw(prune), @c_opt ], 'import' => [ 'LOCATION...|--stdin', 'one-time import/update from URL or filesystem', qw(stdin| offset=i recursive|r exclude=s include|I=s - in-format|F=s kw|keywords|flags! C=s@), - ], + lock=s@ in-format|F=s kw|keywords|flags! verbose|v+), @c_opt ], 'convert' => [ 'LOCATION...|--stdin', 'one-time conversion from URL or filesystem to another format', - qw(stdin| in-format|F=s out-format|f=s output|mfolder|o=s quiet|q - kw|keywords|flags! C=s@), - ], + qw(stdin| in-format|F=s out-format|f=s output|mfolder|o=s + lock=s@ kw|keywords|flags!), @c_opt ], +'p2q' => [ 'FILE|COMMIT_OID|--stdin', + "use a patch to generate a query for `lei q --stdin'", + qw(stdin| want|w=s@ uri debug), @c_opt ], 'config' => [ '[...]', sub { 'git-config(1) wrapper for '._config_path($_[0]); }, qw(config-file|system|global|file|f=s), # for conflict detection - qw(C=s@), pass_through('git config') ], + qw(c=s@ C=s@), pass_through('git config') ], 'init' => [ '[DIRNAME]', sub { - "initialize storage, default: "._store_path($_[0]); - }, qw(quiet|q C=s@) ], + "initialize storage, default: ".store_path($_[0]); + }, @c_opt ], 'daemon-kill' => [ '[-SIGNAL]', 'signal the lei-daemon', # "-C DIR" conflicts with -CHLD, here, and chdir makes no sense, here opt_dash('signal|s=s', '[0-9]+|(?:[A-Z][A-Z0-9]+)') ], @@ -197,7 +216,7 @@ our %CMD = ( # sorted in order of importance/use: 'reorder-local-store-and-break-history' => [ '[REFNAME]', 'rewrite git history in an attempt to improve compression', - qw(gc! C=s@) ], + qw(gc!), @c_opt ], # internal commands are prefixed with '_' '_complete' => [ '[...]', 'internal shell completion helper', @@ -216,11 +235,16 @@ my $ls_format = [ 'OUT|plain|json|null', 'listing output format' ]; # we use \x{a0} (non-breaking SP) to avoid wrapping in PublicInbox::LeiHelp my %OPTDESC = ( 'help|h' => 'show this built-in help', +'c=s@' => [ 'NAME=VALUE', 'set config option' ], 'C=s@' => [ 'DIR', 'chdir to specify to directory' ], 'quiet|q' => 'be quiet', +'lock=s@' => [ 'METHOD|dotlock|fcntl|flock|none', + 'mbox(5) locking method(s) to use (default: fcntl,dotlock)' ], + 'globoff|g' => "do not match locations using '*?' wildcards ". "and\xa0'[]'\x{a0}ranges", 'verbose|v+' => 'be more verbose', +'external!' => 'do not use externals', 'solve!' => 'do not attempt to reconstruct blobs from emails', 'torsocks=s' => ['VAL|auto|no|yes', 'whether or not to wrap git and curl commands with torsocks'], @@ -232,9 +256,12 @@ my %OPTDESC = ( 'dedupe|d=s' => ['STRATEGY|content|oid|mid|none', 'deduplication strategy'], -'show threads|t' => 'display entire thread a message belongs to', -'q threads|t+' => +'threads|t+' => 'return all messages in the same threads as the actual match(es)', + +'want|w=s@' => [ 'PREFIX|dfpost|dfn', # common ones in help... + 'search prefixes to extract (default: dfpost7)' ], + 'alert=s@' => ['CMD,:WINCH,:bell,', 'run command(s) or perform ops when done writing to output ' . '(default: ":WINCH,:bell" with --mua and Maildir/IMAP output, ' . @@ -248,17 +275,11 @@ my %OPTDESC = ( 'mua=s' => [ 'CMD', "MUA to run on --output Maildir or mbox (e.g.\xa0`mutt\xa0-f\xa0%f')" ], -'show format|f=s' => [ 'OUT|plain|raw|html|mboxrd|mboxcl2|mboxcl', - 'message/object output format' ], -'mark format|f=s' => $stdin_formats, -'forget format|f=s' => $stdin_formats, - -'add-external inbox-version=i' => [ 'NUM|1|2', +'inbox-version=i' => [ 'NUM|1|2', 'force a public-inbox version with --mirror'], -'add-external mirror=s' => [ 'URL', 'mirror a public-inbox'], +'mirror=s' => [ 'URL', 'mirror a public-inbox'], # public-inbox-index options -'add-external jobs|j=i' => 'set parallelism when indexing after --mirror', 'fsync!' => 'speed up indexing after --mirror, risk index corruption', 'compact' => 'run compact index after mirroring', 'indexlevel|L=s' => [ 'LEVEL|full|medium|basic', @@ -272,23 +293,22 @@ my %OPTDESC = ( 'skip-docdata' => 'drop compatibility w/ public-inbox <1.6 to save ~1.5% space', -'q format|f=s' => [ +'format|f=s q' => [ 'OUT|maildir|mboxrd|mboxcl2|mboxcl|mboxo|html|json|jsonl|concatjson', 'specify output format, default depends on --output'], -'q exclude=s@' => [ 'LOCATION', +'exclude=s@ q' => [ 'LOCATION', 'exclude specified external(s) from search' ], -'q include|I=s@' => [ 'LOCATION', +'include|I=s@ q' => [ 'LOCATION', 'include specified external(s) in search' ], -'q only=s@' => [ 'LOCATION', +'only=s@ q' => [ 'LOCATION', 'only use specified external(s) for search' ], - -'q jobs=s' => [ '[SEARCH_JOBS][,WRITER_JOBS]', +'jobs=s q' => [ '[SEARCH_JOBS][,WRITER_JOBS]', 'control number of search and writer jobs' ], +'jobs|j=i add-external' => 'set parallelism when indexing after --mirror', -'import format|f=s' => $stdin_formats, - -'ls-query format|f=s' => $ls_format, -'ls-external format|f=s' => $ls_format, +'in-format|F=s' => $stdin_formats, +'format|f=s ls-query' => $ls_format, +'format|f=s ls-external' => $ls_format, 'limit|n=i@' => ['NUM', 'limit on number of matches (default: 10000)' ], 'offset=i' => ['OFF', 'search result offset (default: 0)'], @@ -328,7 +348,7 @@ my %CONFIG_KEYS = ( 'leistore.dir' => 'top-level storage location', ); -my @WQ_KEYS = qw(lxs l2m imp mrr cnv); # internal workers +my @WQ_KEYS = qw(lxs l2m imp mrr cnv p2q); # internal workers # pronounced "exit": x_it(1 << 8) => exit(1); x_it(13) => SIGPIPE sub x_it ($$) { @@ -399,26 +419,11 @@ sub fail ($$;$) { undef; } -sub check_input_format ($;$) { - my ($self, $files) = @_; - my $opt_key = 'in-format'; - my $fmt = $self->{opt}->{$opt_key}; - if (!$fmt) { - my $err = $files ? "regular file(s):\n@$files" : '--stdin'; - return fail($self, "--$opt_key unset for $err"); - } - return 1 if $fmt eq 'eml'; - # XXX: should this handle {gz,bz2,xz}? that's currently in LeiToMail - require PublicInbox::MboxReader; - PublicInbox::MboxReader->can($fmt) || - fail($self, "--$opt_key=$fmt unrecognized"); -} - sub out ($;@) { my $self = shift; return if print { $self->{1} // return } @_; # likely return note_sigpipe($self, 1) if $! == EPIPE; - my $err = "error writing to stdout: $!"; + my $err = "error writing to output: $!"; delete $self->{1}; fail($self, $err); } @@ -451,7 +456,8 @@ sub lei_atfork_child { unless ($self->{oneshot}) { close($_) for @io; } - } else { + } else { # worker, Net::NNTP (Net::Cmd) uses STDERR directly + open STDERR, '+>&='.fileno($self->{2}) or warn "open $!"; delete $self->{0}; } delete @$self{qw(cnv)}; @@ -565,20 +571,59 @@ sub optparse ($$$) { $err ? fail($self, "usage: lei $cmd $proto\nE: $err") : 1; } +sub _tmp_cfg { # for lei -c = ... + my ($self) = @_; + my $cfg = _lei_cfg($self, 1); + require File::Temp; + my $ft = File::Temp->new(TEMPLATE => 'lei_cfg-XXXX', TMPDIR => 1); + my $tmp = { '-f' => $ft->filename, -tmp => $ft }; + $ft->autoflush(1); + print $ft <{-f}: $!"); +[include] + path = $cfg->{-f} +EOM + $tmp = $self->{cfg} = bless { %$cfg, %$tmp }, ref($cfg); + for (@{$self->{opt}->{c}}) { + /\A([^=\.]+\.[^=]+)(?:=(.*))?\z/ or return fail($self, <=' +EOM + my $name = $1; + my $value = $2 // 1; + _config($self, '--add', $name, $value); + if (defined(my $v = $tmp->{$name})) { + if (ref($v) eq 'ARRAY') { + push @$v, $value; + } else { + $tmp->{$name} = [ $v, $value ]; + } + } else { + $tmp->{$name} = $value; + } + } +} + sub dispatch { my ($self, $cmd, @argv) = @_; local $current_lei = $self; # for __WARN__ dump_and_clear_log("from previous run\n"); return _help($self, 'no command given') unless defined($cmd); - while ($cmd eq '-C') { # do not support Getopt bundling for this - my $d = shift(@argv) // return fail($self, '-C DIRECTORY'); - push @{$self->{opt}->{C}}, $d; + # do not support Getopt bundling for this + while ($cmd eq '-C' || $cmd eq '-c') { + my $v = shift(@argv) // return fail($self, $cmd eq '-C' ? + '-C DIRECTORY' : '-c ='); + push @{$self->{opt}->{substr($cmd, 1, 1)}}, $v; $cmd = shift(@argv) // return _help($self, 'no command given'); } my $func = "lei_$cmd"; $func =~ tr/-/_/; - if (my $cb = __PACKAGE__->can($func)) { + my $cb = __PACKAGE__->can($func) // ($CMD{$cmd} ? do { + my $mod = "PublicInbox::Lei\u$cmd"; + ($INC{"PublicInbox/Lei\u$cmd.pm"} // + eval("require $mod")) ? $mod->can($func) : undef; + } : undef); + if ($cb) { optparse($self, $cmd, \@argv) or return; + $self->{opt}->{c} and (_tmp_cfg($self) // return); if (my $chdir = $self->{opt}->{C}) { for my $d (@$chdir) { next if $d eq ''; # same as git(1) @@ -597,11 +642,14 @@ sub dispatch { sub _lei_cfg ($;$) { my ($self, $creat) = @_; + return $self->{cfg} if $self->{cfg}; my $f = _config_path($self); my @st = stat($f); my $cur_st = @st ? pack('dd', $st[10], $st[7]) : ''; # 10:ctime, 7:size + my ($sto, $sto_dir); if (my $cfg = $PATH2CFG{$f}) { # reuse existing object in common case return ($self->{cfg} = $cfg) if $cur_st eq $cfg->{-st}; + ($sto, $sto_dir) = @$cfg{qw(-lei_store leistore.dir)}; } if (!@st) { unless ($creat) { @@ -619,6 +667,10 @@ sub _lei_cfg ($;$) { bless $cfg, 'PublicInbox::Config'; $cfg->{-st} = $cur_st; $cfg->{'-f'} = $f; + if ($sto && File::Spec->canonpath($sto_dir) eq + File::Spec->canonpath($cfg->{'leistore.dir'})) { + $cfg->{-lei_store} = $sto; + } $self->{cfg} = $PATH2CFG{$f} = $cfg; } @@ -628,7 +680,7 @@ sub _lei_store ($;$) { $cfg->{-lei_store} //= do { require PublicInbox::LeiStore; my $dir = $cfg->{'leistore.dir'}; - $dir //= $creat ? _store_path($self) : return; + $dir //= $creat ? store_path($self) : return; PublicInbox::LeiStore->new($dir, { creat => $creat }); }; } @@ -658,21 +710,11 @@ sub lei_config { x_it($self, $?) if $?; } -sub lei_import { - require PublicInbox::LeiImport; - PublicInbox::LeiImport->call(@_); -} - -sub lei_convert { - require PublicInbox::LeiConvert; - PublicInbox::LeiConvert->call(@_); -} - sub lei_init { my ($self, $dir) = @_; my $cfg = _lei_cfg($self, 1); my $cur = $cfg->{'leistore.dir'}; - $dir //= _store_path($self); + $dir //= store_path($self); $dir = rel2abs($self, $dir); my @cur = stat($cur) if defined($cur); $cur = File::Spec->canonpath($cur // $dir); @@ -725,7 +767,7 @@ sub lei__complete { my ($proto, undef, @spec) = @$info; my $cur = pop @argv; my $re = defined($cur) ? qr/\A\Q$cur\E/ : qr/./; - if (substr($cur // '-', 0, 1) eq '-') { # --switches + if (substr(my $_cur = $cur // '-', 0, 1) eq '-') { # --switches # gross special case since the only git-config options # Consider moving to a table if we need more special cases # we use Getopt::Long for are the ones we reject, so these @@ -749,9 +791,9 @@ sub lei__complete { } map { my $x = length > 1 ? "--$_" : "-$_"; - $x eq $cur ? () : $x; + $x eq $_cur ? () : $x; } grep(!/_/, split(/\|/, $_, -1)) # help|h - } grep { $OPTDESC{"$cmd\t$_"} || $OPTDESC{$_} } @spec); + } grep { $OPTDESC{"$_\t$cmd"} || $OPTDESC{$_} } @spec); } elsif ($cmd eq 'config' && !@argv && !$CONFIG_KEYS{$cur}) { puts $self, grep(/$re/, keys %CONFIG_KEYS); } @@ -764,13 +806,13 @@ sub lei__complete { my @v = ref($v) ? split(/\|/, $v->[0]) : (); # get rid of ALL CAPS placeholder (e.g "OUT") # (TODO: completion for external paths) - shift(@v) if uc($v[0]) eq $v[0]; + shift(@v) if scalar(@v) && uc($v[0]) eq $v[0]; @v; - } grep(/\A(?:$cmd\t|)(?:[\w-]+\|)*$opt\b/, keys %OPTDESC); + } grep(/\A(?:[\w-]+\|)*$opt\b.*?(?:\t$cmd)?\z/, keys %OPTDESC); } $cmd =~ tr/-/_/; if (my $sub = $self->can("_complete_$cmd")) { - puts $self, $sub->($self, @argv, $cur); + puts $self, $sub->($self, @argv, $cur ? ($cur) : ()); } # TODO: URLs, pathnames, OIDs, MIDs, etc... See optparse() for # proto parsing. @@ -849,6 +891,22 @@ sub poke_mua { # forces terminal MUAs to wake up and hopefully notice new mail } } +my %path_to_fd = ('/dev/stdin' => 0, '/dev/stdout' => 1, '/dev/stderr' => 2); +$path_to_fd{"/dev/fd/$_"} = $path_to_fd{"/proc/self/fd/$_"} for (0..2); +sub fopen { + my ($self, $mode, $path) = @_; + rel2abs($self, $path); + $path =~ tr!/!/!s; + if (defined(my $fd = $path_to_fd{$path})) { + return $self->{$fd}; + } + if ($path =~ m!\A/(?:dev|proc/self)/fd/[0-9]+\z!) { + return fail($self, "cannot open $path from daemon"); + } + open my $fh, $mode, $path or return; + $fh; +} + # caller needs to "-t $self->{1}" to check if tty sub start_pager { my ($self) = @_; @@ -936,7 +994,10 @@ sub dclose { } } close(delete $self->{1}) if $self->{1}; # may reap_compress - $self->close if $self->{sock}; # PublicInbox::DS::close + if (my $sto = delete $self->{sto}) { + $sto->ipc_do('done'); + } + $self->close if $self->{-event_init_done}; # PublicInbox::DS::close } # for long-running results @@ -976,7 +1037,7 @@ sub event_step_init { sub noop {} -our $oldset; sub oldset { $oldset } +sub oldset { $oldset } sub dump_and_clear_log { if (defined($errors_log) && -s STDIN && seek(STDIN, 0, SEEK_SET)) {