You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spamassassin.apache.org by do...@apache.org on 2006/12/17 04:17:08 UTC
svn commit: r487934 - in /spamassassin/trunk/lib/Mail/SpamAssassin:
Message/Node.pm PerMsgStatus.pm Plugin/SPF.pm
Author: dos
Date: Sat Dec 16 19:17:07 2006
New Revision: 487934
URL: http://svn.apache.org/viewvc?view=rev&rev=487934
Log:
bug 5239: move hackish M::SA::M:Node crap to M::SA::PMS where it should be
Modified:
spamassassin/trunk/lib/Mail/SpamAssassin/Message/Node.pm
spamassassin/trunk/lib/Mail/SpamAssassin/PerMsgStatus.pm
spamassassin/trunk/lib/Mail/SpamAssassin/Plugin/SPF.pm
Modified: spamassassin/trunk/lib/Mail/SpamAssassin/Message/Node.pm
URL: http://svn.apache.org/viewvc/spamassassin/trunk/lib/Mail/SpamAssassin/Message/Node.pm?view=diff&rev=487934&r1=487933&r2=487934
==============================================================================
--- spamassassin/trunk/lib/Mail/SpamAssassin/Message/Node.pm (original)
+++ spamassassin/trunk/lib/Mail/SpamAssassin/Message/Node.pm Sat Dec 16 19:17:07 2006
@@ -652,14 +652,6 @@
return the raw headers, and the second parameter (optional) is whether
or not to include the mbox separator.
-The third and fourth parameters (optional) define the first and last
-values, respectively, of an index range of Received headers. Both of
-the Received headers specified by the indexes and the headers found
-between these Received headers will be returned, in order. Use undef
-as the first index value to start at the first header (possibly before
-the first Received header). Use undef as the last index value to end
-at the last header (probably after the last received header).
-
If get_all_header() is called in an array context, an array will be
returned with each header entry in a different element. In a scalar
context, the headers are returned in a single scalar.
@@ -668,30 +660,17 @@
# build it and it will not bomb
sub get_all_headers {
- my ($self, $raw, $include_mbox, $start_rcvd_index, $end_rcvd_index) = @_;
+ my ($self, $raw, $include_mbox) = @_;
$raw ||= 0;
$include_mbox ||= 0;
- $start_rcvd_index = -1 unless defined $start_rcvd_index;
my @lines = ();
# precalculate destination positions based on order of appearance
my $i = 0;
- my $lines_skipped = 0;
- my $cur_rcvd_index = -1;
my %locations;
-
for my $k (@{$self->{header_order}}) {
- last if (defined $end_rcvd_index && $end_rcvd_index <= $cur_rcvd_index);
- my $name = lc($k);
- $cur_rcvd_index++ if ($name eq 'received');
- if ($cur_rcvd_index < $start_rcvd_index) {
- push(@{$locations{$name}}, -1); # indicate we skipped the header
- $lines_skipped++;
- $i++;
- next;
- }
- push(@{$locations{$name}}, $i++);
+ push(@{$locations{lc($k)}}, $i++);
}
# process headers in order of first appearance
@@ -702,10 +681,8 @@
{
# get all same-name headers and poke into correct position
my $positions = $locations{$name};
- INSTANCE: for my $contents ($self->get_header($name, $raw)) {
+ for my $contents ($self->get_header($name, $raw)) {
my $position = shift @{$positions};
- last INSTANCE unless defined $position;
- next if $position == -1; # any headers we skipped above
$size += length($name) + length($contents) + 2;
if ($size > MAX_HEADER_LENGTH) {
$self->{'truncated_header'} = 1;
@@ -714,9 +691,6 @@
$lines[$position] = $self->{header_order}->[$position] . ": $contents";
}
}
-
- # remove these, they'll be undefined if we skipped over them
- splice @lines, 0, $lines_skipped if $lines_skipped;
# skip undefined lines if we truncated
@lines = grep { defined $_ } @lines if $self->{'truncated_header'};
Modified: spamassassin/trunk/lib/Mail/SpamAssassin/PerMsgStatus.pm
URL: http://svn.apache.org/viewvc/spamassassin/trunk/lib/Mail/SpamAssassin/PerMsgStatus.pm?view=diff&rev=487934&r1=487933&r2=487934
==============================================================================
--- spamassassin/trunk/lib/Mail/SpamAssassin/PerMsgStatus.pm (original)
+++ spamassassin/trunk/lib/Mail/SpamAssassin/PerMsgStatus.pm Sat Dec 16 19:17:07 2006
@@ -1476,33 +1476,28 @@
}
# ALL-TRUSTED: entire trusted raw headers
elsif ($request eq 'ALL-TRUSTED') {
- # if we didn't find any trusted relays, none of the headers are trusted
- return if $self->{last_trusted_relay_index} == -1;
- $result = $self->{msg}->get_all_headers(1, 0, undef,
- $self->{last_trusted_relay_index}+1);
+ # '+1' since we added the received header even though it's not considered
+ # trusted, so we know that those headers can be trusted too
+ return $self->get_all_hdrs_in_rcvd_index_range(
+ undef, $self->{last_trusted_relay_index}+1);
}
# ALL-INTERNAL: entire internal raw headers
- elsif ($request eq 'ALL-INTERNAL') {
- # if we didn't find any internal relays, none of the headers are internal
- return if $self->{last_internal_relay_index} == -1;
- $result = $self->{msg}->get_all_headers(1, 0, undef,
- $self->{last_internal_relay_index}+1);
+ elsif ($request eq 'ALL-INTERNAL') {
+ # '+1' for the same reason as in ALL-TRUSTED above
+ return $self->get_all_hdrs_in_rcvd_index_range(
+ undef, $self->{last_internal_relay_index}+1);
}
# ALL-UNTRUSTED: entire untrusted raw headers
elsif ($request eq 'ALL-UNTRUSTED') {
- # if we didn't find any trusted relays get all the headers, otherwise get
- # all the headers after the last trusted relay
- my $start_index = ($self->{last_trusted_relay_index} == -1 ? undef :
- $self->{last_trusted_relay_index} + 1);
- $result = $self->{msg}->get_all_headers(1, 0, $start_index);
+ # '+1' for the same reason as in ALL-TRUSTED above
+ return $self->get_all_hdrs_in_rcvd_index_range(
+ $self->{last_trusted_relay_index}+1, undef);
}
# ALL-EXTERNAL: entire external raw headers
elsif ($request eq 'ALL-EXTERNAL') {
- # if we didn't find any internal relays get all the headers, otherwise get
- # all the headers after the last internal relay
- my $start_index = ($self->{last_internal_relay_index} == -1 ? undef :
- $self->{last_internal_relay_index} + 1);
- $result = $self->{msg}->get_all_headers(1, 0, $start_index);
+ # '+1' for the same reason as in ALL-TRUSTED above
+ return $self->get_all_hdrs_in_rcvd_index_range(
+ $self->{last_internal_relay_index}+1, undef);
}
# EnvelopeFrom: the SMTP MAIL FROM: address
elsif ($request eq 'EnvelopeFrom') {
@@ -2305,6 +2300,50 @@
$envf =~ s/^<*//gs; # remove <
$envf =~ s/>*\s*$//gs; # remove >, whitespace, newlines
return $envf;
+}
+
+###########################################################################
+
+# helper for get(ALL-*). get() caches its results, so don't call this
+# directly unless you need a range of headers not covered by the ALL-*
+# psuedo-headers!
+
+# Get all the headers found between an index range of received headers, the
+# index doesn't care if we could parse the received headers or not.
+# Use undef for the $start_rcvd or $end_rcvd numbers to start/end with the
+# first/last header in the message, otherwise indicate the index number you
+# want to start/end at. Set $include_start_rcvd or $include_end_rcvd to 0 to
+# indicate you don't want to include the received header found at the start or
+# end indexes... basically toggles between [s,e], [s,e), (s,e], (s,e).
+sub get_all_hdrs_in_rcvd_index_range {
+ my ($self, $start_rcvd, $end_rcvd, $include_start_rcvd, $include_end_rcvd) = @_;
+
+ # prevent bad input causing us to return the first header found
+ return if (defined $end_rcvd && $end_rcvd < 0);
+
+ $include_start_rcvd = 1 unless defined $include_start_rcvd;
+ $include_end_rcvd = 1 unless defined $include_end_rcvd;
+
+ my $cur_rcvd_index = -1; # none found yet
+ my $result = '';
+ foreach my $hdr (split("\n", $self->get('ALL'))) {
+ if ($hdr =~ /^received: /i) {
+ $cur_rcvd_index++;
+ next if (defined $start_rcvd && !$include_start_rcvd &&
+ $start_rcvd == $cur_rcvd_index);
+ last if (defined $end_rcvd && !$include_end_rcvd &&
+ $end_rcvd == $cur_rcvd_index);
+ }
+ if ((!defined $start_rcvd || $start_rcvd <= $cur_rcvd_index) &&
+ (!defined $end_rcvd || $cur_rcvd_index < $end_rcvd)) {
+ $result .= $hdr."\n";
+ }
+ elsif (defined $end_rcvd && $cur_rcvd_index == $end_rcvd) {
+ $result .= $hdr."\n";
+ last;
+ }
+ }
+ return ($result eq '' ? undef : $result);
}
###########################################################################
Modified: spamassassin/trunk/lib/Mail/SpamAssassin/Plugin/SPF.pm
URL: http://svn.apache.org/viewvc/spamassassin/trunk/lib/Mail/SpamAssassin/Plugin/SPF.pm?view=diff&rev=487934&r1=487933&r2=487934
==============================================================================
--- spamassassin/trunk/lib/Mail/SpamAssassin/Plugin/SPF.pm (original)
+++ spamassassin/trunk/lib/Mail/SpamAssassin/Plugin/SPF.pm Sat Dec 16 19:17:07 2006
@@ -303,18 +303,15 @@
} else {
$scanner->{checked_for_received_spf_header} = 1;
dbg("spf: checking to see if the message has a Received-SPF header that we can use");
- # if we didn't find any internal relays, none of the headers are internal
- my @internal_hdrs;
- unless ($scanner->{last_internal_relay_index} == -1) { # -1 means there are none
- @internal_hdrs = $scanner->{msg}->get_all_headers(1, 0, undef,
- $scanner->{last_internal_relay_index}+1);
- unless ($scanner->{conf}->{use_newest_received_spf_header}) {
- @internal_hdrs = reverse(@internal_hdrs);
- } else {
- dbg("spf: starting with the newest Received-SPF headers first");
- }
+
+ my @internal_hdrs = split("\n", $scanner->get('ALL-INTERNAL'));
+ unless ($scanner->{conf}->{use_newest_received_spf_header}) {
+ # look for the LAST (earliest in time) header, it'll be the most accurate
+ @internal_hdrs = reverse(@internal_hdrs);
+ } else {
+ dbg("spf: starting with the newest Received-SPF headers first");
}
- # look for the LAST (earliest in time) header, it'll be the most accurate
+
foreach my $hdr (@internal_hdrs) {
if ($hdr =~ /^received-spf: /i) {
dbg("spf: found a Received-SPF header added by an internal host: $hdr");