Date: Wed, 22 Jun 94 03:16:43 GMT
From: dolan AT fnoc DOT navy DOT mil (Kent Dolan)
To: djgpp AT sun DOT soe DOT clarkson DOT edu
Subject: email header filter for overwhelmed mail echo byte junkies

For those who insist on keeping every valuable word of the djgpp email
echo, the appended nawk script sucked about half the volume out of a
megabyte of it without losing anything worth having.  Not recommended
for Mime mail that is really mixed mode, but fine for chat email.

Usage:

     nawk -f name_you_give_script bulky_email_archive > less_bulky_version

Before pitching the old version and replacing it with the new version, do a

     mail -f less_bulky_version

to make sure you haven't broken something your mailer needs to find the
boundaries between the files.

This script occassionally throws away useful bits of email, but not often
enough to be worth making robust.

The robust version would have another mode wrapped around the current
FollowOn mode, that finds a line starting with "From ", processes the
header as shown until a blank line is encountered, and then prints
everything until the next line starting with "From ".  This is left as
an exercise for the reader.  The value of this version is all the
various kinds of trash in a header that this script knows about, culled
from about 4 megs of saved email.


Xanthian.
--
Kent, the man from xanth.
Kent Paul Dolan.
<dolan AT fnoc DOT navy DOT mil>
<xanthian AT well DOT sf DOT ca DOT us>

---------------------------8<----cut here---->8-----------------------------
BEGIN {
  FollowOn = "F"
}

FollowOn == "T" {
  if ((NF == 0) || (index($0,$1) == 1)) { FollowOn = "F" } else { next }
}

$1 == "Received:" {
  FollowOn = "T"
  next
}

$1 == "Original-Received:" {
  FollowOn = "T"
  next
}

$1 == "X-Disclaimer:" {
  FollowOn = "T"
  next
}

$1 == "References:" {
  FollowOn = "T"
  next
}

$1 == "Content-transfer-encoding:" { next }

$1 == "Followup-To:" { next }

$1 == "Forwarded-By:" { next }

$1 == "Message-ID:" { next }

$1 == "Message-id:" { next }

$1 == "Originally-From:" { next }

$1 == "Originally-Message-Id:" { next }

$1 == "Resent-By:" { next }

$1 == "Resent-Date:" { next }

$1 == "Resent-From:" { next }

$1 == "Resent-Message-Id:" { next }

$1 == "Resent-To:" { next }

$1 == "Resent-message-id:" { next }

$1 == "Resent-to:" { next }

$1 == "Return-path:" { next }

$1 == "X-:" { next }

$1 == "X-Antipastobozoticataclysm:" { next }

$1 == "X-Cc:" { next }

$1 == "X-Envelope-From:" { next }

$1 == "X-Envelope-to:" { next }

$1 == "X-Followup-To:" { next }

$1 == "X-Mailed-To:" { next }

$1 == "X-News:" { next }

$1 == "X-Nsa-Fodder:" { next }

$1 == "X-Origin:" { next }

$1 == "X-Pcmail-Return-Receipt-Requested:" { next }

$1 == "X-Phone:" { next }

$1 == "X-Phones:" { next }

$1 == "X-Punted-By:" { next }

$1 == "X-Software:" { next }

$1 == "X-VMS-Cc:" { next }

$1 == "X-VMS-To:" { next }

$1 == "X-Vms-Mail-To:" { next }

$1 == "X-Vmsmail-To:" { next }

$1 == "XDate:" { next }

$1 == "XFrom:" { next }

$1 == "XIllegal-Object:" { next }

$1 == "XMessage-Id:" { next }

$1 == "XReceived:" { next }

$1 == "XStatus:" { next }

$1 == "XSubject:" { next }

$1 == "XTo:" { next }

$1 == "Message-Id:" { next }

$1 == "Lines:" { next }

$1 == "Path:" { next }

$1 == "Return-Path:" { next }

$1 == "X-Envelope-To:" { next }

$1 == "X-Vms-To:" { next }

$1 == "X-Mts:" { next }

$1 == "Mailer:" { next }

$1 == "Posted-Date:" { next }

$1 == "In-Reply-To:" { next }

$1 == "Mime-Version:" { next }

$1 == "Content-Type:" { next }

$1 == "Content-Transfer-Encoding:" { next }

$1 == "Content-Length:" { next }

$1 == "X-Mailer:" { next }

$1 == "X-Sender:" { next }

$1 == "Encoding:" { next }

$1 == "Pp-Warning:" { next }

$1 == "Reply-To:" { next }

$1 == "Sender:" { next }

$1 == "Xref:" { next }

$1 == "X-BBS-Msg-Type:" { next }

$1 == "X-Date:" { next }

$1 == "X-From:" { next }

$1 == "X-Md4-Signature:" { next }

$1 == "X-NEWS:" { next }

$1 == "X-Newsgroups:" { next }

$1 == "X-Newsreader:" { next }

$1 == "X-Organization:" { next }

$1 == "X-Posted-From:" { next }

$1 == "X-Posted-Through:" { next }

$1 == "X-Posting-Agent-by:" { next }

$1 == "X-Posting-Agent:" { next }

$1 == "X-Posting-Software:" { next }

$1 == "X-To:" { next }

$1 == "X-Unparsable-Date:" { next }

$1 == "X-UserAgent:" { next }

$1 == "X-XXDate:" { next }

$1 == "Cc:" { next }

$1 == "Nntp-Posting-Host:" { next }

$1 == "NNTP-Posting-Host:" { next }

$1 == "In-reply-to:" { next }

$1 == "Originator:" { next }

$1 == "Distribution:" { next }

$1 == "Apparently-To:" { next }

$1 == "Content-Identifier:" { next }

$1 == "Errors-To:" { next }

$1 == "Priority:" { next }

$1 == "Received-Date:" { next }

$1 == "Return-Receipt-To:" { next }

$1 == "S-Mail:" { next }

$1 == "X-Authentic-Sender:" { next }

$1 == "X-Char-Esc:" { next }

$1 == "X-Charset:" { next }

$1 == "X-Face:" { next }

$1 == "X-Hpvue$Revision:" { next }

$1 == "X-Pmrqc:" { next }

$1 == "X-Popmail-Charset:" { next }

$1 == "X-Sun-Charset:" { next }

$1 == "X-Vms-Cc:" { next }

$1 == "X-Vue-Mime-Level:" { next }

$1 == "X400-Content-Type:" { next }

$1 == "X400-Mts-Identifier:" { next }

$1 == "X400-Originator:" { next }

$1 == "X400-Received:" { next }

$1 == "X400-Recipients:" { next }

{ print }