From: Eric Wong <e@80x24.org>
Date: Sat, 9 Apr 2016 01:27:37 +0000 (+0000)
Subject: public-inbox-learn: drop leading "From " line from mboxes
X-Git-Tag: v1.0.0~615
X-Git-Url: http://www.git.stargrave.org/?a=commitdiff_plain;h=dea396ae54867cc901d586c8af70d5f9fc14f1a8;p=public-inbox.git

public-inbox-learn: drop leading "From " line from mboxes

It can confuse Email::MIME if we have it.
---

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 0c7b4199..81675d02 100755
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -17,7 +17,12 @@ if ($train !~ /\A(?:ham|spam)\z/) {
 }
 
 my $pi_config = PublicInbox::Config->new;
-my $mime = Email::MIME->new(eval { local $/; <> });
+my $mime = Email::MIME->new(eval {
+	local $/;
+	my $data = scalar <STDIN>;
+	$data =~ s/\AFrom [^\r\n]*\r?\n//s;
+	$data
+});
 
 # get all recipients
 my %dests;