* [PATCH v2] add filter for RubyLang lists
2017-06-21 23:33 5% [REJECT] add filter for RubyLang lists Eric Wong
2017-06-22 0:31 7% ` Eric Wong
@ 2017-06-22 7:11 5% ` Eric Wong
1 sibling, 0 replies; 3+ results
From: Eric Wong @ 2017-06-22 7:11 UTC (permalink / raw)
To: meta
Unfortunately, it appears we have to reject this and instead add
support filtering at View time(*), due to DKIM signatures in
messages from ruby-lang.org.
(*) which may not be worth it
---
MANIFEST | 1 +
lib/PublicInbox/AltId.pm | 4 +--
lib/PublicInbox/Filter/RubyLang.pm | 63 ++++++++++++++++++++++++++++++++++++++
lib/PublicInbox/WatchMaildir.pm | 2 +-
4 files changed, 67 insertions(+), 3 deletions(-)
create mode 100644 lib/PublicInbox/Filter/RubyLang.pm
diff --git a/MANIFEST b/MANIFEST
index d0b7f2b..c7c4a92 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -51,6 +51,7 @@ lib/PublicInbox/ExtMsg.pm
lib/PublicInbox/Feed.pm
lib/PublicInbox/Filter/Base.pm
lib/PublicInbox/Filter/Mirror.pm
+lib/PublicInbox/Filter/RubyLang.pm
lib/PublicInbox/Filter/SubjectTag.pm
lib/PublicInbox/Filter/Vger.pm
lib/PublicInbox/GetlineBody.pm
diff --git a/lib/PublicInbox/AltId.pm b/lib/PublicInbox/AltId.pm
index 6fdc3a2..73fecd5 100644
--- a/lib/PublicInbox/AltId.pm
+++ b/lib/PublicInbox/AltId.pm
@@ -9,7 +9,7 @@ use URI::Escape qw(uri_unescape);
# spec: TYPE:PREFIX:param1=value1¶m2=value2&...
# Example: serial:gmane:file=/path/to/altmsgmap.sqlite3
sub new {
- my ($class, $inbox, $spec) = @_;
+ my ($class, $inbox, $spec, $writable) = @_;
my ($type, $prefix, $query) = split(/:/, $spec, 3);
$type eq 'serial' or die "non-serial not supported, yet\n";
@@ -25,7 +25,7 @@ sub new {
$f = "$inbox->{mainrepo}/public-inbox/$f";
}
bless {
- mm_alt => PublicInbox::Msgmap->new_file($f),
+ mm_alt => PublicInbox::Msgmap->new_file($f, $writable),
xprefix => 'X'.uc($prefix),
}, $class;
}
diff --git a/lib/PublicInbox/Filter/RubyLang.pm b/lib/PublicInbox/Filter/RubyLang.pm
new file mode 100644
index 0000000..ec4bc32
--- /dev/null
+++ b/lib/PublicInbox/Filter/RubyLang.pm
@@ -0,0 +1,63 @@
+# Copyright (C) 2017 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+
+# Filter for lists.ruby-lang.org trailers
+package PublicInbox::Filter::RubyLang;
+use base qw(PublicInbox::Filter::Base);
+use strict;
+use warnings;
+
+my $l1 = qr/Unsubscribe:\s
+ <mailto:ruby-\w+-request\@ruby-lang\.org\?subject=unsubscribe>/x;
+my $l2 = qr{<http://lists\.ruby-lang\.org/cgi-bin/mailman/options/ruby-\w+>};
+
+sub new {
+ my ($class, %opts) = @_;
+ my $altid = delete $opts{-altid};
+ my $self = $class->SUPER::new(%opts);
+ # altid = serial:ruby-core:file=msgmap.sqlite3
+ if ($altid) {
+ require PublicInbox::MID; # mid_clean
+ my $ibx = $self->{-inbox};
+ require PublicInbox::AltId;
+ $self->{-altid} = PublicInbox::AltId->new($ibx, $altid, 1);
+ }
+ $self;
+}
+
+sub scrub {
+ my ($self, $mime) = @_;
+ # no msg_iter here, that is only for read-only access
+ $mime->walk_parts(sub {
+ my ($part) = $_[0];
+ my $ct = $part->content_type;
+ if (!$ct || $ct =~ m{\btext/plain\b}i) {
+ my $s = eval { $part->body_str };
+ if (defined $s && $s =~ s/\n?$l1\n$l2\n\z//os) {
+ $part->body_str_set($s);
+ }
+ }
+ });
+ my $altid = $self->{-altid};
+ if ($altid) {
+ my $hdr = $mime->header_obj;
+ my $mid = $hdr->header_raw('Message-ID');
+ unless (defined $mid) {
+ return $self->REJECT('Message-Id missing');
+ }
+ my $n = $hdr->header_raw('X-Mail-Count');
+ if (!defined($n) || $n !~ /\A\s*\d+\s*\z/) {
+ return $self->REJECT('X-Mail-Count not numeric');
+ }
+ $mid = PublicInbox::MID::mid_clean($mid);
+ $altid->{mm_alt}->mid_set($n, $mid);
+ }
+ $self->ACCEPT($mime);
+}
+
+sub delivery {
+ my ($self, $mime) = @_;
+ $self->scrub($mime);
+}
+
+1;
diff --git a/lib/PublicInbox/WatchMaildir.pm b/lib/PublicInbox/WatchMaildir.pm
index c436742..8588f16 100644
--- a/lib/PublicInbox/WatchMaildir.pm
+++ b/lib/PublicInbox/WatchMaildir.pm
@@ -242,7 +242,7 @@ sub _scrubber_for {
my ($inbox) = @_;
my $f = $inbox->{filter};
if ($f && $f =~ /::/) {
- my @args;
+ my @args = (-inbox => $inbox);
# basic line splitting, only
# Perhaps we can have proper quote splitting one day...
($f, @args) = split(/\s+/, $f) if $f =~ /\s+/;
--
EW
^ permalink raw reply related [relevance 5%]
* Re: [REJECT] add filter for RubyLang lists
2017-06-21 23:33 5% [REJECT] add filter for RubyLang lists Eric Wong
@ 2017-06-22 0:31 7% ` Eric Wong
2017-06-22 7:11 5% ` [PATCH v2] " Eric Wong
1 sibling, 0 replies; 3+ results
From: Eric Wong @ 2017-06-22 0:31 UTC (permalink / raw)
To: meta
Eric Wong <e@80x24.org> wrote:
> Unfortunately, it appears we have to reject this and instead add
> support filtering at View time(*), due to DKIM signatures in
> messages from ruby-lang.org.
Nevermind, I'll apply this patch. DKIM signatures are only
added by Redmine, and invalid by the time it hits ruby-core.
^ permalink raw reply [relevance 7%]
* [REJECT] add filter for RubyLang lists
@ 2017-06-21 23:33 5% Eric Wong
2017-06-22 0:31 7% ` Eric Wong
2017-06-22 7:11 5% ` [PATCH v2] " Eric Wong
0 siblings, 2 replies; 3+ results
From: Eric Wong @ 2017-06-21 23:33 UTC (permalink / raw)
To: meta
Unfortunately, it appears we have to reject this and instead add
support filtering at View time(*), due to DKIM signatures in
messages from ruby-lang.org.
(*) which may not be worth it
---
MANIFEST | 1 +
lib/PublicInbox/AltId.pm | 4 +--
lib/PublicInbox/Filter/RubyLang.pm | 59 ++++++++++++++++++++++++++++++++++++++
lib/PublicInbox/WatchMaildir.pm | 2 +-
4 files changed, 63 insertions(+), 3 deletions(-)
create mode 100644 lib/PublicInbox/Filter/RubyLang.pm
diff --git a/MANIFEST b/MANIFEST
index d0b7f2b..c7c4a92 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -51,6 +51,7 @@ lib/PublicInbox/ExtMsg.pm
lib/PublicInbox/Feed.pm
lib/PublicInbox/Filter/Base.pm
lib/PublicInbox/Filter/Mirror.pm
+lib/PublicInbox/Filter/RubyLang.pm
lib/PublicInbox/Filter/SubjectTag.pm
lib/PublicInbox/Filter/Vger.pm
lib/PublicInbox/GetlineBody.pm
diff --git a/lib/PublicInbox/AltId.pm b/lib/PublicInbox/AltId.pm
index 6fdc3a2..73fecd5 100644
--- a/lib/PublicInbox/AltId.pm
+++ b/lib/PublicInbox/AltId.pm
@@ -9,7 +9,7 @@ use URI::Escape qw(uri_unescape);
# spec: TYPE:PREFIX:param1=value1¶m2=value2&...
# Example: serial:gmane:file=/path/to/altmsgmap.sqlite3
sub new {
- my ($class, $inbox, $spec) = @_;
+ my ($class, $inbox, $spec, $writable) = @_;
my ($type, $prefix, $query) = split(/:/, $spec, 3);
$type eq 'serial' or die "non-serial not supported, yet\n";
@@ -25,7 +25,7 @@ sub new {
$f = "$inbox->{mainrepo}/public-inbox/$f";
}
bless {
- mm_alt => PublicInbox::Msgmap->new_file($f),
+ mm_alt => PublicInbox::Msgmap->new_file($f, $writable),
xprefix => 'X'.uc($prefix),
}, $class;
}
diff --git a/lib/PublicInbox/Filter/RubyLang.pm b/lib/PublicInbox/Filter/RubyLang.pm
new file mode 100644
index 0000000..a0e6d7b
--- /dev/null
+++ b/lib/PublicInbox/Filter/RubyLang.pm
@@ -0,0 +1,59 @@
+# Copyright (C) 2017 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+
+# Filter for lists.ruby-lang.org trailers
+package PublicInbox::Filter::RubyLang;
+use base qw(PublicInbox::Filter::Base);
+use strict;
+use warnings;
+
+my $l1 = qr/Unsubscribe:\s
+ <mailto:ruby-\w+-request\@ruby-lang\.org\?subject=unsubscribe>/x;
+my $l2 = qr{<http://lists\.ruby-lang\.org/cgi-bin/mailman/options/ruby-\w+>};
+
+sub new {
+ my ($class, %opts) = @_;
+ my $altid = delete $opts{-altid};
+ my $self = $class->SUPER::new(%opts);
+ # altid = serial:ruby-core:file=msgmap.sqlite3
+ if ($altid) {
+ require PublicInbox::MID; # mid_clean
+ my $ibx = $self->{-inbox};
+ require PublicInbox::AltId;
+ $self->{-altid} = PublicInbox::AltId->new($ibx, $altid, 1);
+ }
+ $self;
+}
+
+sub scrub {
+ my ($self, $mime) = @_;
+ # no msg_iter here, that is only for read-only access
+ $mime->walk_parts(sub {
+ my ($part) = $_[0];
+ my $ct = $part->content_type;
+ if (!$ct || $ct =~ m{\btext/plain\b}i) {
+ my $s = eval { $part->body_str };
+ if (defined $s && $s =~ s/\n?$l1\n$l2\n\z//os) {
+ $part->body_str_set($s);
+ }
+ }
+ });
+ my $altid = $self->{-altid};
+ if ($altid) {
+ my $hdr = $mime->header_obj;
+ my $n = $hdr->header_raw('X-Mail-Count');
+ my $mid = $hdr->header_raw('Message-ID');
+ if (defined $n && defined $mid && $n =~ /\A\s*\d+\s*\z/) {
+ $mid = PublicInbox::MID::mid_clean($mid);
+ $altid->{mm_alt}->mid_set($n, $mid);
+ }
+ }
+ $self->ACCEPT($mime);
+}
+
+sub delivery {
+ my ($self, $mime) = @_;
+ $self->scrub($mime);
+}
+
+1;
diff --git a/lib/PublicInbox/WatchMaildir.pm b/lib/PublicInbox/WatchMaildir.pm
index c436742..8588f16 100644
--- a/lib/PublicInbox/WatchMaildir.pm
+++ b/lib/PublicInbox/WatchMaildir.pm
@@ -242,7 +242,7 @@ sub _scrubber_for {
my ($inbox) = @_;
my $f = $inbox->{filter};
if ($f && $f =~ /::/) {
- my @args;
+ my @args = (-inbox => $inbox);
# basic line splitting, only
# Perhaps we can have proper quote splitting one day...
($f, @args) = split(/\s+/, $f) if $f =~ /\s+/;
--
EW
^ permalink raw reply related [relevance 5%]
Results 1-3 of 3 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2017-06-21 23:33 5% [REJECT] add filter for RubyLang lists Eric Wong
2017-06-22 0:31 7% ` Eric Wong
2017-06-22 7:11 5% ` [PATCH v2] " Eric Wong
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).