X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMsgIter.pm;h=7c28d019abc8c7e9fae81c9db2b0196c21e81310;hb=453dee4881a9c764b09d33f3a827879f2cd3669d;hp=6453d9f1043630d267d19c8c1445ef8a288f3abe;hpb=55b11c59936125aab26694e17631828c7ea9954e;p=public-inbox.git

diff --git a/lib/PublicInbox/MsgIter.pm b/lib/PublicInbox/MsgIter.pm
index 6453d9f1..7c28d019 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) 2016-2020 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
@@ -7,31 +7,45 @@ 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 ($$) {
-	my ($mime, $cb) = @_;
+sub em_each_part ($$;$$) {
+	my ($mime, $cb, $cb_arg, $do_undef) = @_;
 	my @parts = $mime->subparts;
 	if (@parts) {
+		$mime = $_[0] = undef if $do_undef; # saves some memory
 		my $i = 0;
 		@parts = map { [ $_, 1, ++$i ] } @parts;
 		while (my $p = shift @parts) {
-			my ($part, $depth, @idx) = @$p;
+			my ($part, $depth, $idx) = @$p;
 			my @sub = $part->subparts;
 			if (@sub) {
 				$depth++;
 				$i = 0;
-				@sub = map { [ $_, $depth, @idx, ++$i ] } @sub;
+				@sub = map {
+					[ $_, $depth, "$idx.".(++$i) ]
+				} @sub;
 				@parts = (@sub, @parts);
 			} else {
-				$cb->($p);
+				$cb->($p, $cb_arg);
 			}
 		}
 	} else {
-		$cb->([$mime, 0, 0]);
+		$cb->([$mime, 0, 0], $cb_arg);
+	}
+}
+
+# Use this when we may accept Email::MIME from user scripts
+# (not just PublicInbox::MIME)
+sub msg_iter ($$;$$) { # $_[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);
 	}
 }
 
@@ -70,4 +84,14 @@ 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;