library(tm)
library(ggplot2)

#tm is the text mining package of R
#ggplot is for visualization
#there are 2 sets of files for each type of mail and one will be used for training while other will be for testing

spam.path<-"data/spam/"
spam2.path<-"data/spam_2/"
easyham.path<-"data/easy_ham/"
easyham2.path<-"data/easy_ham_2/"
hardham.path<-"data/hard_ham/"
hardham2.path<-"data/hard_ham_2"

get.msg<-function(path){
  print(path)
  connection<-file(path,open="rt", encoding="Latin1")

  text<-readLines(connection)
  #the message begins after a full line break

  t<-which(text=="")[1]+1
  print(length(text))
  print(t)
  msg<-text[seq(t, length(text),1)]


  close(connection)
  return (paste(msg, collapse="n"))

}


# create a vector of emails
#use apply function

spam.docs<-dir(spam.path)
#this returns a list of file names in the directory
spam.docs<-spam.docs[c(1:length(spam.docs)-1)]
#spam.docs<-spam.docs[which(spam.docs!="")]
#cmds file is a UNIX file which we dont need
#spam.docs<-spam.docs[!startsWith(spam.docs, "cmds")]

all.spam<-sapply(spam.docs, function(p) get.msg(paste(spam.path,p, sep="")))

#use the command below for inspection
head(all.spam)

wReturn-Path: ler@lerami.lerctr.org
Delivery-Date: Sat Sep  7 06:14:26 2002
Received: via dmail-2002(12) for +lists/freebsd/ports; Sat, 7 Sep 2002 06:14:26 -0500 (CDT)
Return-Path: <owner-freebsd-ports@FreeBSD.ORG>
Received: from mx2.freebsd.org (mx2.FreeBSD.org [216.136.204.119])
    by lerami.lerctr.org (8.12.2/8.12.2/20020902/$Revision: 1.30 $) with ESMTP id g87BEIX2008158
    for <ler@lerctr.org>; Sat, 7 Sep 2002 06:14:19 -0500 (CDT)
Received: from hub.freebsd.org (hub.FreeBSD.org [216.136.204.18])
    by mx2.freebsd.org (Postfix) with ESMTP
    id D6B0B5548A; Sat,  7 Sep 2002 04:14:14 -0700 (PDT)
    (envelope-from owner-freebsd-ports@FreeBSD.ORG)
Received: by hub.freebsd.org (Postfix, from userid 538)
    id 448B137B401; Sat,  7 Sep 2002 04:14:14 -0700 (PDT)
Received: from localhost (localhost [127.0.0.1])
    by hub.freebsd.org (Postfix) with SMTP
    id 33D712E8016; Sat,  7 Sep 2002 04:14:14 -0700 (PDT)
Received: by hub.freebsd.org (bulk_mailer v1.12); Sat, 7 Sep 2002 04:14:14 -0700
Delivered-To: freebsd-ports@freebsd.org
Received: from mx1.FreeBSD.org (mx1.FreeBSD.org [216.136.204.125])
    by hub.freebsd.org (Postfix) with ESMTP id 31C6137B400
    for <ports@freebsd.org>; Sat,  7 Sep 2002 04:14:13 -0700 (PDT)
Received: from mgate.netpath.ne.jp (lilac.netpath.ne.jp [210.253.168.208])
    by mx1.FreeBSD.org (Postfix) with SMTP id 4816543E65
    for <ports@freebsd.org>; Sat,  7 Sep 2002 04:14:12 -0700 (PDT)
    (envelope-from joko@rs.128.ne.jp)
Received: (qmail 46020 invoked from network); 7 Sep 2002 09:24:03 -0000
Received: from p6044-ipad22marunouchi.tokyo.ocn.ne.jp (HELO D) (61.214.35.44)
  by lilac.netpath.ne.jp with SMTP; 7 Sep 2002 09:24:03 -0000
From: =?iso-2022-jp?B?am9rb0Bycy4xMjgubmUuanA=?=@FreeBSD.ORG
To: =?iso-2022-jp?B?MTIx?=@FreeBSD.ORG
Reply-To: joko@rs.128.ne.jp
Date: Sat, 07 Sep 2002 18:24:06 +0900
Subject: =?iso-2022-jp?B?GyRCJDckOCRfJEgkYiRiJE4lMyVpJVwlbCE8JTclZyVzGyhK?=
Content-Type: text/plain
Content-Transfer-Encoding: 7bit
MIME-Version: 1.0
Message-Id: <20020907111412.4816543E65@mx1.FreeBSD.org>
Sender: owner-freebsd-ports@FreeBSD.ORG
List-ID: <freebsd-ports.FreeBSD.ORG>
List-Archive: <http://docs.freebsd.org/mail/> (Web Archive)
List-Help: <mailto:majordomo@FreeBSD.ORG?subject=help> (List Instructions)
List-Subscribe: <mailto:majordomo@FreeBSD.ORG?subject=subscribe%20freebsd-ports>
List-Unsubscribe: <mailto:majordomo@FreeBSD.ORG?subject=unsubscribe%20freebsd-ports>
X-Loop: FreeBSD.org
Precedence: bulk
X-Virus-Scanned: by amavisd-milter (http://amavis.org/)
Status: RO
X-Status:
X-Keywords:
X-UID: 8

ààªÍ¶¯ÄÔǤªäêé->line 52
µ¶ÝÆààÌR{[V
[^rfIicucjêå
¢ÂÜÅcÆÅ«é©í©èܹñ
²¶Í¨ßÉI
http://www.transrave.com/PC/rori
ìiá
­`à@¼Ã®cn9@­Ì¹
ÈÇÈÇ132ìiBD]­I
(^-^)/~Fg[
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-ports" in the body of the message

msg<-text[seq(t, length(text),1)]