#!/bin/csh -f
#
# known word unknown word  ϴ program
#
#
# UNKNOWNFREQ   format µȴ
#
#      ( tag , freq(known-word,tag) , freq(unknown-word,tag) ) 
#
#
#
#
if ($#argv == 0) then       # if no argument
   echo "Unknown Word Freq Ѵ."
   echo "GetUnFreq ̹-±-۽ KTS--±-۽ UNKNOWNFREQ"
   echo "Usage : GetUnFreq UnknownTrainingCrps TaggedCrpsByKTS UNKNOWNFREQ"
   exit 1
endif

#
#
#
awk ' { print "o", $0 } ' $1 > $1.qwe
#
#

diff $1.qwe $2 | ediff >! $2.t1
../spltdif $2.t1 $2.k_f $2.u_f $2.e_f
../getdiff $2.u_f $2.t_d_f
#
echo "Getting Common Eojeols"
#
diff $2.t_d_f $1.qwe | ediff >! comm 
awk ' /^o/ { print $2 } ' comm >! comm.area
#
echo "Done...."
echo "Getting Unknown Eojeols"
awk ' { print $2 } ' $2.t_d_f >! unkn.area
echo "Done...."
#
#
#
#
echo 'Getting first word from common.area'
awk -F+ ' { print $1 } ' comm.area > comm.area.1
echo 'Done....'
#
#

#
#
echo 'Getting first word from unknown.area'
awk -F+ ' { print $1 } ' unkn.area > unkn.area.1
echo 'Done....'
#
#

#
#
echo 'Getting tag of word from common.area'
awk -F/ ' { print $2 } ' comm.area.1 > comm.area.2
echo 'Done....'
/bin/rm comm.area.1
#
#

#
#
echo 'Getting tag of word from unknown.area'
awk -F/ ' { print $2 } ' unkn.area.1 > unkn.area.2
echo 'Done....'
/bin/rm unkn.area.1
#
#

#
#
echo 'Sorting tag of word from common.area'
sort comm.area.2 > comm.area.3
echo 'Done....'
/bin/rm comm.area.2
#
#

#
#
echo 'Sorting tag of word from unknown.area'
sort unkn.area.2 > unkn.area.3
echo 'Done....'
/bin/rm unkn.area.2
#
#

#
#
echo 'Getting Frequencies from common.area'
freq < comm.area.3 > comm.area.4
echo 'Done....'
/bin/rm comm.area.3
#
#

#
#
echo 'Getting Frequencies from unknown.area'
freq < unkn.area.3 > unkn.area.4
echo 'Done....'
/bin/rm unkn.area.3
#
#

#
#
echo 'Merging Frequencies : format (tag,known,unknown)'
freqmrg comm.area.4 unkn.area.4 $3
echo 'Done....'
/bin/rm comm.area.4
/bin/rm unkn.area.4
/bin/rm $1.qwe
/bin/rm $2.t1
/bin/rm $2.u_f
/bin/rm $2.k_f
/bin/rm $2.t_d_f
/bin/rm $2.e_f
#
#


