[PATCH] mda: drop leading "From " lines again

[PATCH] mda: drop leading "From " lines again

[Eric Wong]

Oops...

While we're at it, drop blank lines before the "From ", too,
since it could happen.
---
 script/public-inbox-learn | 2 +-
 script/public-inbox-mda   | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 7ef2a31..09fd7c8 100755
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -26,7 +26,7 @@ my $err;
 my $mime = Email::MIME->new(eval {
 	local $/;
 	my $data = scalar <STDIN>;
-	$data =~ s/\AFrom [^\r\n]*\r?\n//s;
+	$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
 	eval {
 		if ($train eq 'ham') {
 			$spamc->hamlearn(\$data);
diff --git a/script/public-inbox-mda b/script/public-inbox-mda
index f739ad0..d76f33a 100755
--- a/script/public-inbox-mda
+++ b/script/public-inbox-mda
@@ -32,6 +32,7 @@ use PublicInbox::Spamcheck::Spamc;
 my $emergency = $ENV{PI_EMERGENCY} || "$ENV{HOME}/.public-inbox/emergency/";
 $ems = PublicInbox::Emergency->new($emergency);
 my $str = eval { local $/; <STDIN> };
+$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
 $ems->prepare(\$str);
 my $simple = Email::Simple->new(\$str);
 my $config = PublicInbox::Config->new;

[PATCH 2/1] inbox: ensure we do not show leading "From " lines

[Eric Wong]

Some messages will be misimported due to an old bug,
clean them up and ensure we do not propagate the mistake.

Followup-to: a0c07cba0e5d ("mda: drop leading "From " lines again")
---
 lib/PublicInbox/Inbox.pm     | 4 +++-
 lib/PublicInbox/SearchIdx.pm | 2 ++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index 34191fc..87c2c9f 100644
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -99,7 +99,9 @@ sub nntp_usable {
 sub msg_by_path ($$;$) {
 	my ($self, $path, $ref) = @_;
 	# TODO: allow other refs:
-	git($self)->cat_file('HEAD:'.$path, $ref);
+	my $str = git($self)->cat_file('HEAD:'.$path, $ref);
+	$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+	$str;
 }
 
 sub msg_by_mid ($$;$) {
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 58eccc1..c2bf9a2 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -311,6 +311,8 @@ sub do_cat_mail {
 	my ($git, $blob, $sizeref) = @_;
 	my $mime = eval {
 		my $str = $git->cat_file($blob, $sizeref);
+		# fixup bugs from import:
+		$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
 		Email::MIME->new($str);
 	};
 	$@ ? undef : $mime;
-- 
EW

[PATCH 3/1] inbox: avoid trying s// on undef

[Eric Wong]

Oops, I guess I'm trigger-happy today.

Fixes: 31a6ff1221fe ("inbox: ensure we do not show leading "From " lines")
---
 lib/PublicInbox/Inbox.pm | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index 87c2c9f..ada713c 100644
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -100,7 +100,7 @@ sub msg_by_path ($$;$) {
 	my ($self, $path, $ref) = @_;
 	# TODO: allow other refs:
 	my $str = git($self)->cat_file('HEAD:'.$path, $ref);
-	$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+	$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s if $str;
 	$str;
 }