#!/usr/bin/perl -w
-# $Id: t-prot,v 1.243 2005/05/27 10:00:35 jochen Exp $
+# $Id: t-prot,v 1.264 2009/12/19 22:18:47 jochen Exp $
require 5.006;
use strict;
use Fcntl qw(O_EXCL O_WRONLY O_CREAT);
use Getopt::Mixed qw(nextOption);
-use constant VER => '2.0';
+use constant VER => '2.8';
use constant REV => '';
-use constant REL => q$Revision: 1.243 $=~m/(\d+(?:\.\d+)+)/;
+use constant REL => q$Revision: 1.264 $=~m/(\d+(?:\.\d+)+)/;
# MTA expecting mail on STDIN
# (you might have to adjust this if using a different MTA)
use constant SENDMAIL => '/usr/sbin/sendmail -oi';
use vars qw(
$ad $ads $bigqn $bigqx $boun $check $check_ratio $cr $diff $elli
$footers $ftr_ad $ftr_ml $hdrs $indent $kamm $kdiff $kminl $kmaxl
- $lax $lsig $maxsig $mda $ml $ms $ms_smart $msg_quote $msg_ratio
- $mua $nohdr $ofile $pgpshort $pgpmove $pgpmovevrf $sig $sigint
- $sign $spass $spass_prefix $sysl $trad $trsp
+ $lax $lsig $maxsig $maxlines $mda $ml $gw $ms $ms_smart $msg_quote
+ $msg_ratio $mua $nohdr $ofile $pgpshort $pgpmove $pgpmovevrf $sig
+ $sigint $sign $spass $spass_prefix $sysl $trad $trsp
$gpg_WARNING $gpg_Warning $gpg_Cantcheck $gpg_aka $gpg_bad
$gpg_expired $gpg_good $gpg_bug
# command line can change them or they are used in rexexp's):
$0 =~ s!^.*/!!;
$maxsig = 4; # max. valid signature length
+$maxlines = undef; # no limit of message lines
$indent = '>'; # Indent string, regexp to identify a quoted line
$kminl = 65; # see decomb() for details
$kmaxl = 80;
# help(): print help text and exit with appropriate exit code
sub help {
print "Usage: $0 [options]
- -a remove ad footers; requires -A
-A=DIRECTORY ad footer directory, treat ad footers as signature
+ -a remove ad footers; requires -A
--bigq[=n[,x]] remove all but x lines of quotes with more than n
lines; default is n=30 and x=10
--body input has no headers; does not work with --pgp-short;
-e force ellipsis for excessive punctuation
--ftr-ad enable aggressive ad footer matching; requires -A
--ftr-ml enable aggressive mailing list footer matching; req. -L
+ --groupwise delete Novell Groupwise style TOFU
-h, --help show this short help and exit
-i=INFILE file to be read; '-' for STDIN (default)
-k try to fix \"Kammquotes\"
--kminl=n min. line length for wrapped line; requires -k
--kmaxl=n max. line length for wrapped line; requires -k
--kdiff=n max. length difference between wrapped lines; req. -k
- -L=DIRECTORY mailling list footer directory, treat mailing list
+ -L=DIRECTORY mailing list footer directory, treat mailing list
footers as signature
-l delete mailing list footer; requires -L
--lax-security use unsafe writing method; USE ON YOUR OWN RISK!
--locale=LOCALE internationalization; currently only used with -Mmutt
-M, --mua=MUA turn on special treatment for some mail user agents
-m delete MS style TOFU; careful: might be too agressive
+ --max-lines=x maximum number of message lines
--ms-smart try to be smart with MS style TOFU; req. -Mmutt and -m
-o=OUTFILE file to be written to; '-' for STDOUT (default), 'NONE'
for no output at all
}
if ($F && scalar(@$L)) {
- if (!opendir(DIR, $F)) { print STDERR "Could not open $F: $!\n"; exit(EX_IOERR); }
+ if (!opendir(DIR, $F))
+ { print STDERR "Could not open $F: $!\n"; exit(EX_IOERR); }
my @feet = grep { /^[^.]/ && -f "$F/$_" } readdir DIR;
closedir DIR;
foreach my $f (@feet) {
- if (!open(IN, "$F/$f")) { print STDERR "Could not open $F/$f: $!\n"; exit(EX_IOERR); }
+ if (!open(IN, "$F/$f"))
+ { print STDERR "Could not open $F/$f: $!\n"; exit(EX_IOERR); }
my @l = <IN>;
close IN;
for (my $z=0; $z<=$#l; $z++) { chomp($l[$z]); }
if (defined $V) {
- WIPE: for (my $z=scalar(@$L)-scalar(@l); $z>=0; $z--)
- {
+ WIPE: for (my $z=scalar(@$L)-scalar(@l); $z>=0; $z--) {
if (scalar(@l)+$z<=scalar(@$L)) {
my $y = 0;
for(my $x=1; $x<=scalar(@l); $x++) {
- if (index($$L[scalar(@$L)-$x-$z], $l[scalar(@l)-$x])!=0) {
+ if (index($$L[scalar(@$L)-$x-$z],
+ $l[scalar(@l)-$x])!=0) {
$y = 1;
}
}
(index($$L[$x+1], $indent)!=0) &&
($$L[$x+1] !~ /^$/) &&
($$L[$x+1] !~ /^[\s^]/) &&
- ($$L[$x] !~ /-$/) &&
+ ($$L[$x] !~ /-$/) &&
($$L[$x+1] !~ /^\Q[...]\E\s*$/) &&
($mua ne 'mutt' || $$L[$x+1] !~ /^(?:\e[^\a]+\a)?\[-- /) &&
(length($$L[$x])+index($$L[$x+1], ' ')>$max ||
- (index($$L[$x+1], ' ')<0 && length($$L[$x])+length($$L[$x+1])>$max)) &&
+ (index($$L[$x+1], ' ')<0 &&
+ length($$L[$x])+length($$L[$x+1])>$max)) &&
(length($$L[$x])+length($$L[$x+1])<$kmaxl) &&
(length($$L[$x])+length($$L[$x+1])>$kminl) &&
(length($$L[$x])-length($$L[$x+1])>$kdiff) &&
if (index($$H[$m], 'From:')==0) {
$from = $$H[$m];
$m++;
- while (exists($$H[$m]) && $$H[$m] =~ /^\s/) { $from .= $$H[$m]; $m++; }
+ while (exists($$H[$m]) && $$H[$m] =~ /^\s/)
+ { $from .= $$H[$m]; $m++; }
last;
}
}
my (@ads, @hdr, @bo1, @bo2, @ftr, @sig, @vrb, @att) =
((), (), (), (), (), (), (), (), ());
- # First, remove and store lines we might need later...
+ # First, check msg length and stop processing if msg is too long:
+ if ((defined $maxlines) && (@$lines > $maxlines)) {
+ return;
+ }
+
+ # Remove and store lines we might need later...
# Remove headers:
if (!$nohdr) {
for ($x=0; $x<$#$lines; $x++) { if (@$lines[$x] =~ /^$/) { last; }; }
/^(?:\e[^\a]+\a)?\Q$mutt_attachment\E\d+/o &&
$att[$x+1] =~ m!^
(?:\e[^\a]+\a)?
- (?:\Q$mutt_contenttype\E) message/rfc822
+ (?:\Q$mutt_contenttype\E) (?:message/rfc822|multipart/alternative)
!ox)
{
$x += 2;
# Remove signature:
if (scalar(@$lines)) {
my $sn = 0;
+ my $chk_empty = 1;
+ my $empty = 0;
+
for ($x = $#$lines; $x>=0; $x--) {
- if ((!$vrb[$x]) && $$lines[$x] =~ /^-- $/) {
- if ($diff) {
- for (my $i=1; $x+$i+1<scalar(@$lines); $i++) {
- if ($$lines[$x+$i] =~ /^-{3}\s+\S/ &&
- $$lines[$x+$i+1] =~ /^\+{3}\s+\S/)
- {
- $sig = 0;
- unshift(@sig, @$lines[$x..$#$lines]);
- splice(@$lines, $x);
- last;
+ if (!$vrb[$x]) {
+ if ($$lines[$x] =~ /^-- $/) {
+ if ($diff) {
+ for (my $i=1; $x+$i+1<scalar(@$lines); $i++) {
+ if ($$lines[$x+$i] =~ /^-{3}\s+\S/ &&
+ $$lines[$x+$i+1] =~ /^\+{3}\s+\S/)
+ {
+ $sig = 0;
+ unshift(@sig, @$lines[$x..$#$lines]);
+ splice(@$lines, $x);
+ last;
+ }
+ }
+ if (scalar(@sig)) {
+ if (defined($sign) && ++$sn==$sign) { last; } else { next; }
}
}
- if (scalar(@sig)) {
- if (defined($sign) && ++$sn==$sign) { last; } else { next; }
- }
- }
- if ($sig || ($lsig && ($#$lines-$x>$lsig))) {
- if ($lsig && !$sig) {
- unshift(@sig, "[---=| Overlong signature removed by $0: " .
- (scalar(@$lines)-$x) . " lines snipped |=---]\n");
+ if ($sig || ($lsig && ($#$lines-$x-$empty>$lsig))) {
+ if ($lsig && !$sig) {
+ unshift(@sig, "[---=| Overlong signature removed by $0: " .
+ (scalar(@$lines)-$x) . " lines snipped |=---]\n");
+ }
+ splice(@$lines, $x);
}
- splice(@$lines, $x);
- }
- else {
- unshift(@sig, @$lines[$x..$#$lines]);
- splice(@$lines, $x);
+ else {
+ unshift(@sig, @$lines[$x..$#$lines]);
+ splice(@$lines, $x);
+ }
+ if (defined($sign) && ++$sn==$sign) { last; } else { next; }
}
- if (defined($sign) && ++$sn==$sign) { last; } else { next; }
+ # any trailing newlines?
+ elsif ($chk_empty && $$lines[$x] =~ /^\s*$/) { $empty++; }
+ elsif ($chk_empty) { $chk_empty = 0; }
}
}
}
if ($kamm) { decomb($lines, \@vrb); }
# Now care about TOFU.
- # One common mispractice is M$ style TOFU:
- if ($ms) {
+ # One common mispractice is M$ and Groupwise style TOFU:
+ if ($ms||$gw) {
# bloat this array if you want more internationalization:
my @tofu = ('Original Message',
+ 'Original-Nachricht',
'Ursprüngliche Nachricht',
+ 'Ursprüngliche Nachricht',
'Ursprungliche Nachricht',
'Mensagem original',
'Ursprungligt meddelande',
DONE: for ($x=0; $x<scalar(@$lines); $x++) {
if (!$vrb[$x]) {
foreach my $tmp (@tofu) {
- if ($$lines[$x] =~ /^-+\s?$tmp\s?-+/) {
+ if (($ms && $$lines[$x] =~ /^\s?-+\s?$tmp\s?-+/) ||
+ ($gw &&
+ ($$lines[$x] =~ /^>>>[^\<]+<[^\>]+> \d\d?\/\d\d?\/\d\d? \d\d?:\d\d [AP]M >>>/ ||
+ $$lines[$x] =~ /^>>> On [A-Z][a-z][a-z]?, [A-Z][a-z][a-z]? \d\d?, \d\d\d\d at [ \d]\d:\d\d [AP]M, in message/))) {
$x++;
$trad = 0;
$bigqn = 0;
# environment
-my $locale = $ENV{'LC_ALL'}?$ENV{'LC_ALL'}:($ENV{'LC_MESSAGES'}?$ENV{'LC_MESSAGES'}:$ENV{'LANG'});
+my $locale = $ENV{'LC_ALL'}?$ENV{'LC_ALL'}:
+ ($ENV{'LC_MESSAGES'}?$ENV{'LC_MESSAGES'}:$ENV{'LANG'});
# command line switches
($ad, $ads, $bigqn, $bigqx, $check, $cr, $sysl, $diff, $elli, $footers, $lax,
- $ml, $ms, $ms_smart, $mda, $mua, $hdrs, $kamm, $lsig, $nohdr, $sig, $sigint,
- $spass, $trad, $trsp) =
+ $ml, $gw, $ms, $ms_smart, $mda, $mua, $hdrs, $kamm, $lsig, $nohdr, $sig,
+ $sigint, $spass, $trad, $trsp) =
(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
my $ifile = '-'; # use STDIN if nothing specified
# get command line params:
Getopt::Mixed::init('a A=s c d e h i=s k L=s l m M=s o=s P=s p:s r S:i'.
- ' s t v w bigq:s body check:s debug>d diff ftr-ad ftr-ml help>h'.
- ' kminl=i kmaxl=i kdiff=i lax-security locale=s ms-smart mua>M'.
- ' pgp-short pgp-move pgp-move-vrf sigsmax:i spass version>v');
+ ' s t v w bigq:s body check:s debug>d diff ftr-ad ftr-ml groupwise'.
+ ' help>h kminl=i kmaxl=i kdiff=i lax-security locale=s max-lines=i'.
+ ' ms-smart mua>M pgp-short pgp-move pgp-move-vrf sigsmax:i spass'.
+ ' version>v');
while (my ($opt, $val, $pretty) = nextOption()) {
if ($opt eq 'a') { $ad = 1; }
elsif ($opt eq 'A') { $ads = $val; }
elsif ($opt eq 'e') { $elli = 1; }
elsif ($opt eq 'ftr-ad') { $ftr_ad = 1; $ad = 1; }
elsif ($opt eq 'ftr-ml') { $ftr_ml = 1; $ml = 1; }
+ elsif ($opt eq 'groupwise') { $gw = 1; }
elsif ($opt eq 'i') { $ifile = $val; }
elsif ($opt eq 'k') { $kamm = 1; }
elsif ($opt eq 'kminl') { $kminl = $val; $kamm = 1; }
elsif ($opt eq 'lax-security') { $lax = 1; }
elsif ($opt eq 'locale') { $locale = $val; }
elsif ($opt eq 'm') { $ms = 1; }
+ elsif ($opt eq 'max-lines') { $maxlines = $val; }
elsif ($opt eq 'ms-smart') { $ms_smart = 1; $ms = 1; }
elsif ($opt eq 'M') {
$mua = lc($val);
# Read message:
-if (!open(IN, $ifile)) { print STDERR "Could not open $ifile: $!\n"; exit(EX_IOERR); }
+if (!open(IN, $ifile))
+ { print STDERR "Could not open $ifile: $!\n"; exit(EX_IOERR); }
my @message = <IN>;
close IN;