X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FInbox.pm;h=0b118b28cea84418f18a73cd5f6a63cfbbe0dae9;hb=b6f480ed58abc5ae2a426ef4f792621b9d3cf283;hp=51ada0bc390458df9a992ff77ca934097293db60;hpb=f1a38b18d9a46531e18143a7cd4c7a66fc89adbc;p=public-inbox.git diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm index 51ada0bc..0b118b28 100644 --- a/lib/PublicInbox/Inbox.pm +++ b/lib/PublicInbox/Inbox.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2016 all contributors +# Copyright (C) 2016-2018 all contributors # License: AGPL-3.0+ # # Represents a public-inbox (which may have multiple mailing addresses) @@ -7,19 +7,66 @@ use strict; use warnings; use PublicInbox::Git; use PublicInbox::MID qw(mid2path); +use PublicInbox::MIME; +# Long-running "git-cat-file --batch" processes won't notice +# unlinked packs, so we need to restart those processes occasionally. +# Xapian and SQLite file handles are mostly stable, but sometimes an +# admin will attempt to replace them atomically after compact/vacuum +# and we need to be prepared for that. my $cleanup_timer; -eval { - $cleanup_timer = 'disabled'; - require PublicInbox::EvCleanup; - $cleanup_timer = undef; # OK if we get here -}; - +my $cleanup_avail = -1; # 0, or 1 +my $have_devel_peek; my $CLEANUP = {}; # string(inbox) -> inbox sub cleanup_task () { $cleanup_timer = undef; - delete $_->{git} for values %$CLEANUP; - $CLEANUP = {}; + my $next = {}; + for my $ibx (values %$CLEANUP) { + my $again; + if ($have_devel_peek) { + foreach my $f (qw(mm search)) { + # we bump refcnt by assigning tmp, here: + my $tmp = $ibx->{$f} or next; + next if Devel::Peek::SvREFCNT($tmp) > 2; + delete $ibx->{$f}; + # refcnt is zero when tmp is out-of-scope + } + } + my $expire = time - 60; + if (my $git = $ibx->{git}) { + $again = $git->cleanup($expire); + } + if (my $gits = $ibx->{-repo_objs}) { + foreach my $git (@$gits) { + $again = 1 if $git->cleanup($expire); + } + } + if ($have_devel_peek) { + $again ||= !!($ibx->{mm} || $ibx->{search}); + } + $next->{"$ibx"} = $ibx if $again; + } + $CLEANUP = $next; +} + +sub cleanup_possible () { + # no need to require EvCleanup, here, if it were enabled another + # module would've require'd it, already + eval { PublicInbox::EvCleanup::enabled() } or return 0; + + eval { + require Devel::Peek; # needs separate package in Fedora + $have_devel_peek = 1; + }; + 1; +} + +sub _cleanup_later ($) { + my ($self) = @_; + $cleanup_avail = cleanup_possible() if $cleanup_avail < 0; + return if $cleanup_avail != 1; + $cleanup_timer ||= PublicInbox::EvCleanup::later(*cleanup_task); + $CLEANUP->{"$self"} = $self; } sub _set_uint ($$$) { @@ -62,29 +109,88 @@ sub new { _set_limiter($opts, $pi_config, 'httpbackend'); _set_uint($opts, 'feedmax', 25); $opts->{nntpserver} ||= $pi_config->{'publicinbox.nntpserver'}; + my $dir = $opts->{mainrepo}; + if (defined $dir && -f "$dir/inbox.lock") { + $opts->{version} = 2; + } + + # allow any combination of multi-line or comma-delimited hide entries + my $hide = {}; + if (defined(my $h = $opts->{hide})) { + foreach my $v (@$h) { + $hide->{$_} = 1 foreach (split(/\s*,\s*/, $v)); + } + $opts->{-hide} = $hide; + } bless $opts, $class; } +sub git_part { + my ($self, $part) = @_; + ($self->{version} || 1) == 2 or return; + $self->{"$part.git"} ||= eval { + my $git_dir = "$self->{mainrepo}/git/$part.git"; + my $g = PublicInbox::Git->new($git_dir); + $g->{-httpbackend_limiter} = $self->{-httpbackend_limiter}; + # no cleanup needed, we never cat-file off this, only clone + $g; + }; +} + sub git { my ($self) = @_; $self->{git} ||= eval { - my $g = PublicInbox::Git->new($self->{mainrepo}); + my $git_dir = $self->{mainrepo}; + $git_dir .= '/all.git' if (($self->{version} || 1) == 2); + my $g = PublicInbox::Git->new($git_dir); $g->{-httpbackend_limiter} = $self->{-httpbackend_limiter}; - $cleanup_timer ||= PublicInbox::EvCleanup::later(*cleanup_task); - $CLEANUP->{"$self"} = $self; + _cleanup_later($self); $g; }; } +sub max_git_part { + my ($self) = @_; + my $v = $self->{version}; + return unless defined($v) && $v == 2; + my $part = $self->{-max_git_part}; + my $changed = git($self)->alternates_changed; + if (!defined($part) || $changed) { + $self->git->cleanup if $changed; + my $gits = "$self->{mainrepo}/git"; + if (opendir my $dh, $gits) { + my $max = -1; + while (defined(my $git_dir = readdir($dh))) { + $git_dir =~ m!\A(\d+)\.git\z! or next; + $max = $1 if $1 > $max; + } + $part = $self->{-max_git_part} = $max if $max >= 0; + } else { + warn "opendir $gits failed: $!\n"; + } + } + $part; +} + sub mm { my ($self) = @_; - $self->{mm} ||= eval { PublicInbox::Msgmap->new($self->{mainrepo}) }; + $self->{mm} ||= eval { + require PublicInbox::Msgmap; + _cleanup_later($self); + my $dir = $self->{mainrepo}; + if (($self->{version} || 1) >= 2) { + PublicInbox::Msgmap->new_file("$dir/msgmap.sqlite3"); + } else { + PublicInbox::Msgmap->new($dir); + } + }; } sub search { my ($self) = @_; $self->{search} ||= eval { - PublicInbox::Search->new($self->{mainrepo}, $self->{altid}); + _cleanup_later($self); + PublicInbox::Search->new($self, $self->{altid}); }; } @@ -106,7 +212,7 @@ sub description { local $/ = "\n"; chomp $desc; $desc =~ s/\s+/ /smg; - $desc = '($GIT_DIR/description missing)' if $desc eq ''; + $desc = '($REPO_DIR/description missing)' if $desc eq ''; $self->{description} = $desc; } @@ -123,8 +229,8 @@ sub cloneurl { sub base_url { my ($self, $env) = @_; - if ($env) { # PSGI env - my $scheme = $env->{'psgi.url_scheme'}; + my $scheme; + if ($env && ($scheme = $env->{'psgi.url_scheme'})) { # PSGI env my $host_port = $env->{HTTP_HOST} || "$env->{SERVER_NAME}:$env->{SERVER_PORT}"; my $url = "$scheme://$host_port". ($env->{SCRIPT_NAME} || '/'); @@ -208,26 +314,62 @@ sub msg_by_path ($$;$) { sub msg_by_smsg ($$;$) { my ($self, $smsg, $ref) = @_; - return unless defined $smsg; # ghost - - # backwards compat to fallback to msg_by_mid - # TODO: remove if we bump SCHEMA_VERSION in Search.pm: - defined(my $blob = $smsg->{blob}) or - return msg_by_mid($self, $smsg->mid); + # ghosts may have undef smsg (from SearchThread.node) or + # no {blob} field + return unless defined $smsg; + defined(my $blob = $smsg->{blob}) or return; my $str = git($self)->cat_file($blob, $ref); $$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s if $str; $str; } -sub path_check { - my ($self, $path) = @_; - git($self)->check('HEAD:'.$path); +sub smsg_mime { + my ($self, $smsg, $ref) = @_; + if (my $s = msg_by_smsg($self, $smsg, $ref)) { + $smsg->{mime} = PublicInbox::MIME->new($s); + return $smsg; + } +} + +sub mid2num($$) { + my ($self, $mid) = @_; + my $mm = mm($self) or return; + $mm->num_for($mid); +} + +sub smsg_by_mid ($$) { + my ($self, $mid) = @_; + my $srch = search($self) or return; + # favor the Message-ID we used for the NNTP article number: + defined(my $num = mid2num($self, $mid)) or return; + my $smsg = $srch->lookup_article($num) or return; + PublicInbox::SearchMsg::psgi_cull($smsg); } sub msg_by_mid ($$;$) { my ($self, $mid, $ref) = @_; - msg_by_path($self, mid2path($mid), $ref); + my $srch = search($self) or + return msg_by_path($self, mid2path($mid), $ref); + my $smsg = smsg_by_mid($self, $mid); + $smsg ? msg_by_smsg($self, $smsg, $ref) : undef; +} + +sub recent { + my ($self, $opts, $after, $before) = @_; + search($self)->{over_ro}->recent($opts, $after, $before); +} + +sub modified { + my ($self) = @_; + if (my $srch = search($self)) { + my $msgs = $srch->{over_ro}->recent({limit => 1}); + if (my $smsg = $msgs->[0]) { + return $smsg->{ts}; + } + return time; + } + git($self)->modified; # v1 } 1;