X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMsgIter.pm;h=7c28d019abc8c7e9fae81c9db2b0196c21e81310;hb=453dee4881a9c764b09d33f3a827879f2cd3669d;hp=d9df32abc37c7fc7da68c0e09ed2f942ddbb4827;hpb=e5cc97f6a2ff53f072a5d692e56d0918b33c5081;p=public-inbox.git
diff --git a/lib/PublicInbox/MsgIter.pm b/lib/PublicInbox/MsgIter.pm
index d9df32ab..7c28d019 100644
--- a/lib/PublicInbox/MsgIter.pm
+++ b/lib/PublicInbox/MsgIter.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2019 all contributors
+# Copyright (C) 2016-2020 all contributors
# License: AGPL-3.0+
# read-only utilities for Email::MIME
@@ -7,37 +7,56 @@ 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 ($$) {
- my ($mime, $cb) = @_;
+sub em_each_part ($$;$$) {
+ my ($mime, $cb, $cb_arg, $do_undef) = @_;
my @parts = $mime->subparts;
if (@parts) {
+ $mime = $_[0] = undef if $do_undef; # saves some memory
my $i = 0;
@parts = map { [ $_, 1, ++$i ] } @parts;
while (my $p = shift @parts) {
- my ($part, $depth, @idx) = @$p;
+ my ($part, $depth, $idx) = @$p;
my @sub = $part->subparts;
if (@sub) {
$depth++;
$i = 0;
- @sub = map { [ $_, $depth, @idx, ++$i ] } @sub;
+ @sub = map {
+ [ $_, $depth, "$idx.".(++$i) ]
+ } @sub;
@parts = (@sub, @parts);
} else {
- $cb->($p);
+ $cb->($p, $cb_arg);
}
}
} else {
- $cb->([$mime, 0, 0]);
+ $cb->([$mime, 0, 0], $cb_arg);
+ }
+}
+
+# Use this when we may accept Email::MIME from user scripts
+# (not just PublicInbox::MIME)
+sub msg_iter ($$;$$) { # $_[0] = PublicInbox::MIME/Email::MIME-like obj
+ my (undef, $cb, $cb_arg, $once) = @_;
+ if (my $ep = $_[0]->can('each_part')) { # PublicInbox::{MIME,*}
+ $ep->($_[0], $cb, $cb_arg, $once);
+ } else { # for compatibility with existing Email::MIME users:
+ em_each_part($_[0], $cb, $cb_arg, $once);
}
}
sub msg_part_text ($$) {
my ($part, $ct) = @_;
+ # TODO: we may offer a separate sub for people who need to index
+ # HTML-only mail, but the majority of HTML mail is multipart/alternative
+ # with a text part which we don't have to waste cycles decoding
+ return if $ct =~ m!\btext/x?html\b!;
+
my $s = eval { $part->body_str };
my $err = $@;
@@ -65,4 +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;