X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMbox.pm;h=67b671f5f4a8f31aa3bfca611ae78cc5001c10cf;hb=dbb6c7b51862d0ea7438f5fb393d115ea46f1fab;hp=11b23022ff5ed8270af2f5f70ad0bbf3524c08af;hpb=6f4fcc32237e46fb219df9ad4e92aeb3a170d03f;p=public-inbox.git

diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 11b23022..67b671f5 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -1,8 +1,12 @@
-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2019 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
-# Streaming interface for formatting messages as an mboxrd.
-# Used by the web interface
+# Streaming (via getline) interface for formatting messages as an mboxrd.
+# Used by the PSGI web interface.
+#
+# public-inbox-httpd favors "getline" response bodies to take a
+# "pull"-based approach to feeding slow clients (as opposed to a
+# more common "push" model)
 package PublicInbox::Mbox;
 use strict;
 use warnings;
@@ -12,8 +16,8 @@ use Email::Simple;
 use Email::MIME::Encode;
 
 sub subject_fn ($) {
-	my ($simple) = @_;
-	my $fn = $simple->header('Subject');
+	my ($hdr) = @_;
+	my $fn = $hdr->header('Subject');
 	return 'no-subject' unless defined($fn);
 
 	# no need for full Email::MIME, here
@@ -32,43 +36,47 @@ sub mb_stream {
 }
 
 # called by PSGI server as body response
+# this gets called twice for every message, once to return the header,
+# once to retrieve the body
 sub getline {
 	my ($more) = @_; # self
-	my ($ctx, $id, $prev, $next, $cur) = @$more;
-	if ($cur) { # first
-		pop @$more;
-		return msg_str($ctx, $cur);
+	my ($ctx, $id, $prev, $next, $mref, $hdr) = @$more;
+	if ($hdr) { # first message hits this, only
+		pop @$more; # $hdr
+		return msg_hdr($ctx, $hdr);
 	}
-	$cur = $next or return;
+	if ($mref) { # all messages hit this
+		pop @$more; # $mref
+		return msg_body($$mref);
+	}
+	my $cur = $next or return;
 	my $ibx = $ctx->{-inbox};
-	$next = $ibx->search->next_by_mid($ctx->{mid}, \$id, \$prev);
-	@$more = ($ctx, $id, $prev, $next); # $next may be undef, here
-	my $mref = $ibx->msg_by_smsg($cur) or return;
-	msg_str($ctx, Email::Simple->new($mref));
+	$next = $ibx->over->next_by_mid($ctx->{mid}, \$id, \$prev);
+	$mref = $ibx->msg_by_smsg($cur) or return;
+	$hdr = Email::Simple->new($mref)->header_obj;
+	@$more = ($ctx, $id, $prev, $next, $mref); # $next may be undef, here
+	msg_hdr($ctx, $hdr); # all but first message hits this
 }
 
 sub close {} # noop
 
+# /$INBOX/$MESSAGE_ID/raw
 sub emit_raw {
 	my ($ctx) = @_;
 	my $mid = $ctx->{mid};
 	my $ibx = $ctx->{-inbox};
-	my $first;
-	my $more;
-	if (my $srch = $ibx->search) {
-		my ($id, $prev);
-		my $smsg = $srch->next_by_mid($mid, \$id, \$prev) or return;
-		my $mref = $ibx->msg_by_smsg($smsg) or return;
-		$first = Email::Simple->new($mref);
-		my $next = $srch->next_by_mid($mid, \$id, \$prev);
-		# $more is for ->getline
-		$more = [ $ctx, $id, $prev, $next, $first ] if $next;
+	$ctx->{base_url} = $ibx->base_url($ctx->{env});
+	my ($mref, $more, $id, $prev, $next);
+	if (my $over = $ibx->over) {
+		my $smsg = $over->next_by_mid($mid, \$id, \$prev) or return;
+		$mref = $ibx->msg_by_smsg($smsg) or return;
+		$next = $over->next_by_mid($mid, \$id, \$prev);
 	} else {
-		my $mref = $ibx->msg_by_mid($mid) or return;
-		$first = Email::Simple->new($mref);
+		$mref = $ibx->msg_by_mid($mid) or return;
 	}
-	return unless defined $first;
-	my $fn = subject_fn($first);
+	my $hdr = Email::Simple->new($mref)->header_obj;
+	$more = [ $ctx, $id, $prev, $next, $mref, $hdr ]; # for ->getline
+	my $fn = subject_fn($hdr);
 	my @hdr = ('Content-Type');
 	if ($ibx->{obfuscate}) {
 		# obfuscation is stupid, but maybe scrapers are, too...
@@ -79,12 +87,11 @@ sub emit_raw {
 		$fn .= '.txt';
 	}
 	push @hdr, 'Content-Disposition', "inline; filename=$fn";
-	[ 200, \@hdr, $more ? mb_stream($more) : [ msg_str($ctx, $first) ] ];
+	[ 200, \@hdr, mb_stream($more) ];
 }
 
-sub msg_str {
-	my ($ctx, $simple, $mid) = @_; # Email::Simple object
-	my $header_obj = $simple->header_obj;
+sub msg_hdr ($$;$) {
+	my ($ctx, $header_obj, $mid) = @_;
 
 	# drop potentially confusing headers, ssoma already should've dropped
 	# Lines and Content-Length
@@ -92,7 +99,7 @@ sub msg_str {
 		$header_obj->header_set($d);
 	}
 	my $ibx = $ctx->{-inbox};
-	my $base = $ibx->base_url($ctx->{env});
+	my $base = $ctx->{base_url};
 	$mid = $ctx->{mid} unless defined $mid;
 	$mid = mid_escape($mid);
 	my @append = (
@@ -100,7 +107,7 @@ sub msg_str {
 		'List-Archive', "<$base>",
 		'List-Post', "<mailto:$ibx->{-primary_address}>",
 	);
-	my $crlf = $simple->crlf;
+	my $crlf = $header_obj->crlf;
 	my $buf = "From mboxrd\@z Thu Jan  1 00:00:00 1970\n" .
 			$header_obj->as_string;
 	for (my $i = 0; $i < @append; $i += 2) {
@@ -116,21 +123,23 @@ sub msg_str {
 		$buf .= "$k: $v$crlf" if defined $v;
 	}
 	$buf .= $crlf;
+}
 
+sub msg_body ($) {
 	# mboxrd quoting style
-	# ref: http://www.qmail.org/man/man5/mbox.html
-	my $body = $simple->body;
-	$body =~ s/^(>*From )/>$1/gm;
-	$buf .= $body;
-	$buf .= "\n";
+	# https://en.wikipedia.org/wiki/Mbox#Modified_mbox
+	# https://www.loc.gov/preservation/digital/formats/fdd/fdd000385.shtml
+	# https://web.archive.org/http://www.qmail.org/man/man5/mbox.html
+	$_[0] =~ s/^(>*From )/>$1/gm;
+	$_[0] .= "\n";
 }
 
 sub thread_mbox {
-	my ($ctx, $srch, $sfx) = @_;
+	my ($ctx, $over, $sfx) = @_;
 	eval { require IO::Compress::Gzip };
 	return sub { need_gzip(@_) } if $@;
 	my $mid = $ctx->{mid};
-	my $msgs = $srch->get_thread($mid, {});
+	my $msgs = $over->get_thread($mid, {});
 	return [404, [qw(Content-Type text/plain)], []] if !@$msgs;
 	my $prev = $msgs->[-1];
 	my $i = 0;
@@ -140,7 +149,7 @@ sub thread_mbox {
 				return $smsg;
 			}
 			# refill result set
-			$msgs = $srch->get_thread($mid, $prev);
+			$msgs = $over->get_thread($mid, $prev);
 			return unless @$msgs;
 			$prev = $msgs->[-1];
 			$i = 0;
@@ -164,17 +173,19 @@ sub emit_range {
 sub mbox_all_ids {
 	my ($ctx) = @_;
 	my $prev = 0;
-	my $ids = $ctx->{-inbox}->mm->ids_after(\$prev) or return
+	my $ibx = $ctx->{-inbox};
+	my $ids = $ibx->mm->ids_after(\$prev) or return
 		[404, [qw(Content-Type text/plain)], ["No results found\n"]];
 	my $i = 0;
-	my $over = $ctx->{srch}->{over_ro};
+	my $over = $ibx->over or
+		return PublicInbox::WWW::need($ctx, 'Overview');
 	my $cb = sub {
 		do {
 			while ((my $num = $ids->[$i++])) {
 				my $smsg = $over->get_art($num) or next;
 				return $smsg;
 			}
-			$ids = $ctx->{-inbox}->mm->ids_after(\$prev);
+			$ids = $ibx->mm->ids_after(\$prev);
 			$i = 0;
 		} while (@$ids);
 		undef;
@@ -189,7 +200,8 @@ sub mbox_all {
 	return sub { need_gzip(@_) } if $@;
 	return mbox_all_ids($ctx) if $query eq '';
 	my $opts = { mset => 2 };
-	my $srch = $ctx->{srch};
+	my $srch = $ctx->{-inbox}->search or
+		return PublicInbox::WWW::need($ctx, 'Search');;
 	my $mset = $srch->query($query, $opts);
 	$opts->{offset} = $mset->size or
 			return [404, [qw(Content-Type text/plain)],
@@ -236,6 +248,7 @@ use PublicInbox::Hval qw/to_filename/;
 sub new {
 	my ($class, $ctx, $cb) = @_;
 	my $buf = '';
+	$ctx->{base_url} = $ctx->{-inbox}->base_url($ctx->{env});
 	bless {
 		buf => \$buf,
 		gz => IO::Compress::Gzip->new(\$buf, Time => 0),
@@ -260,11 +273,13 @@ sub response {
 sub getline {
 	my ($self) = @_;
 	my $ctx = $self->{ctx} or return;
+	my $gz = $self->{gz};
 	while (my $smsg = $self->{cb}->()) {
-		my $msg = $ctx->{-inbox}->msg_by_smsg($smsg) or next;
-		$msg = Email::Simple->new($msg);
-		$self->{gz}->write(PublicInbox::Mbox::msg_str($ctx, $msg,
-				$smsg->{mid}));
+		my $mref = $ctx->{-inbox}->msg_by_smsg($smsg) or next;
+		my $h = Email::Simple->new($mref)->header_obj;
+		$gz->write(PublicInbox::Mbox::msg_hdr($ctx, $h, $smsg->{mid}));
+		$gz->write(PublicInbox::Mbox::msg_body($$mref));
+
 		my $bref = $self->{buf};
 		if (length($$bref) >= 8192) {
 			my $ret = $$bref; # copy :<