X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMsgIter.pm;h=c503eb98b8c502e3ecda265007772fada888424f;hb=af0b0fb7a454470a32c452119d0392e0dedb3fe1;hp=f238954bcdd5b7a04c8f631c8308d067f3146945;hpb=195c40c82e77c73e171f75529b80c7561565d512;p=public-inbox.git

diff --git a/lib/PublicInbox/MsgIter.pm b/lib/PublicInbox/MsgIter.pm
index f238954b..c503eb98 100644
--- a/lib/PublicInbox/MsgIter.pm
+++ b/lib/PublicInbox/MsgIter.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # read-only utilities for Email::MIME
@@ -7,12 +7,12 @@ use strict;
 use warnings;
 use base qw(Exporter);
 our @EXPORT = qw(msg_iter msg_part_text);
-use PublicInbox::MIME;
 
+# This becomes PublicInbox::MIME->each_part:
 # Like Email::MIME::walk_parts, but this is:
 # * non-recursive
 # * passes depth and indices to the iterator callback
-sub msg_iter ($$;$$) {
+sub em_each_part ($$;$$) {
 	my ($mime, $cb, $cb_arg, $do_undef) = @_;
 	my @parts = $mime->subparts;
 	if (@parts) {
@@ -20,19 +20,32 @@ sub msg_iter ($$;$$) {
 		my $i = 0;
 		@parts = map { [ $_, 1, ++$i ] } @parts;
 		while (my $p = shift @parts) {
-			my ($part, $depth, @idx) = @$p;
+			my ($part, $depth, $idx) = @$p;
 			my @sub = $part->subparts;
 			if (@sub) {
 				$depth++;
 				$i = 0;
-				@sub = map { [ $_, $depth, @idx, ++$i ] } @sub;
+				@sub = map {
+					[ $_, $depth, "$idx.".(++$i) ]
+				} @sub;
 				@parts = (@sub, @parts);
 			} else {
 				$cb->($p, $cb_arg);
 			}
 		}
 	} else {
-		$cb->([$mime, 0, 0], $cb_arg);
+		$cb->([$mime, 0, 1], $cb_arg);
+	}
+}
+
+# Use this when we may accept Email::MIME from user scripts
+# (not just PublicInbox::MIME)
+sub msg_iter ($$;$$) { # $_[0] = PublicInbox::MIME/Email::MIME-like obj
+	my (undef, $cb, $cb_arg, $once) = @_;
+	if (my $ep = $_[0]->can('each_part')) { # PublicInbox::{MIME,*}
+		$ep->($_[0], $cb, $cb_arg, $once);
+	} else { # for compatibility with existing Email::MIME users:
+		em_each_part($_[0], $cb, $cb_arg, $once);
 	}
 }
 
@@ -51,8 +64,12 @@ sub msg_part_text ($$) {
 	# times when it should not have been:
 	#   <87llgalspt.fsf@free.fr>
 	#   <200308111450.h7BEoOu20077@mail.osdl.org>
+	# But also do not try this with ->{is_submsg} (message/rfc822),
+	# since a broken multipart/mixed inside a message/rfc822 part
+	# has not been seen in the wild, yet...
 	if ($err && ($ct =~ m!\btext/\b!i ||
-			$ct =~ m!\bmultipart/mixed\b!i)) {
+			(!$part->{is_submsg} &&
+				$ct =~ m!\bmultipart/mixed\b!i) ) ) {
 		my $cte = $part->header_raw('Content-Transfer-Encoding');
 		if (defined($cte) && $cte =~ /\b7bit\b/i) {
 			$s = $part->body;
@@ -71,4 +88,14 @@ sub msg_part_text ($$) {
 	($s, $err);
 }
 
+# returns an array of quoted or unquoted sections
+sub split_quotes {
+	# Quiet "Complex regular subexpression recursion limit" warning
+	# in case an inconsiderate sender quotes 32K of text at once.
+	# The warning from Perl is harmless for us since our callers can
+	# tolerate less-than-ideal matches which work within Perl limits.
+	no warnings 'regexp';
+	split(/((?:^>[^\n]*\n)+)/sm, shift);
+}
+
 1;