Shell Programming and Scripting

I need help in awk please help immediatly.

This below function is taking lot of time
Please help me to fine tune it so that it runs faster.
The file count is around 3million records

# Process Body
processbody() {

#set -x

while read line
do
ENTITY_TYPE=`print "$line" | cut -d'|' -f2 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`

if [ ${ENTITY_TYPE} == "O" ]
then
ENTITY_TYPE="B"
else
ENTITY_TYPE="P"
fi
CUSTOMER_ID=`print "$line" | cut -d'|' -f1 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`

#Branch and Account Numbers should be left blank

BRANCH_NUMBER=
ACCOUNT_NUMBER=
ACCOUNT_DATE_OPEN=`print "$line" | cut -d'|' -f3 |sed 's/[^0-9]//g' | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}' | cut -c1-8`
CORPORATE_NAME=`print "$line" | cut -d'|' -f4 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
LAST_NAME=`print "$line" | cut -d'|' -f5 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
FIRST_NAME=`print "$line" | cut -d'|' -f6 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
MIDDLE_NAME=`print "$line" | cut -d'|' -f7 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
NAME_SUFFIX=`print "$line" | cut -d'|' -f8 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`

# Extracting person gender information
PERSON_GENDER=`print "$line" | cut -d'|' -f9 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
# If gender is anything other than M or F,replace it with blank
if [[ ${PERSON_GENDER} != "M" && ${PERSON_GENDER} != "F" ]]
then
PERSON_GENDER=
fi

BIRTH_DATE=`print $line | cut -d'|' -f10 | sed 's/[^0-9]//g' | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}' | cut -c1-8`
#AGE should be left blank
AGE=



# Extracting citizenship code information
CITIZEN_COUNTRY_NAME=`print $line | cut -d'|' -f11 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`


if [[ ${CITIZEN_COUNTRY_NAME} == "US" || ${CITIZEN_COUNTRY_NAME} == "USA" || ${CITIZEN_COUNTRY_NAME} == "UNITED STATES" || ${CITIZEN_COUNTRY_NAME} == "UNITED STATES OF AMERICA" ]]
then
CITIZENSHIP_CODE="USA"
FED_ID=`print $line | cut -d'|' -f12 | sed -e 's/[^0-9]//g' | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
else
CITIZENSHIP_CODE=`print $line | cut -d'|' -f11 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}' | cut -c1-3`
FED_ID=
fi

if [[ ${ENTITY_TYPE} == "P" ]]
then
FED_ID_TYPE="S"
else
FED_ID_TYPE="T"
fi

#Extracting National ID information

ID_INFORMATION_1=`print $line | cut -d'|' -f13 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
ID_INFORMATION_2=`print $line | cut -d'|' -f14 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`


if [[ ! -z ${ID_INFORMATION_1} && ${ID_INFORMATION_1} != "" ]]
then
NATIONAL_ID=${ID_INFORMATION_1}

# Remove all non numeric characters in NATIONAL_ID field
NATIONAL_ID=`print ${NATIONAL_ID} | sed 's/[^0-9a-zA-Z]//g' | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
NATIONAL_ID_TYPE="DL"
elif [[ ! -z ${ID_INFORMATION_2} && ${ID_INFORMATION_2} != "" ]]
then
NATIONAL_ID=${ID_INFORMATION_2}


# Remove all non numeric characters in NATIONAL_ID field
NATIONAL_ID=`print ${NATIONAL_ID} | sed 's/[^0-9a-zA-Z]//g' | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
NATIONAL_ID_TYPE="PP"
else
NATIONAL_ID=
NATIONAL_ID_TYPE=
fi

#Extracting street address information

ADDRESS_1=`print $line | cut -d'|' -f15 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
ADDRESS_2=`print $line | cut -d'|' -f16 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
STREET_ADDRESS=${ADDRESS_1}${ADDRESS_2}
STREET_ADDRESS=`print ${STREET_ADDRESS} | cut -c1-60`

#Extracting city information

ADDRESS_3=`print $line | cut -d'|' -f17 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
CITY_NAME=${ADDRESS_3}

#Extracting country information

COUNTRY=`print $line | cut -d'|' -f20 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
ADDRESS_4=`print $line | cut -d'|' -f18 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`

COUNTRY_NAME=${COUNTRY}

if [[ ${COUNTRY_NAME} == "US" || ${COUNTRY_NAME} == "USA" || ${COUNTRY_NAME} == "UNITED STATES" || ${COUNTRY_NAME} == "UNITED STATES OF AMERICA" ]]
then
COUNTRY_CODE="USA"
else
COUNTRY_CODE=`print ${COUNTRY} | sed 's/ //g' | cut -c1-3`
fi

#POSTCODE=`print $line | cut -d'|' -f19 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}' |cut -c1-5`
if [[ ${COUNTRY_CODE} == "USA" ]]
then
STATE_CODE=${ADDRESS_4}
POSTCODE=`print $line | cut -d'|' -f19 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}' |cut -c1-5`

FOREIGN_PROVINCE=
FOREIGN_POSTAL_CODE=
else
STATE_CODE=
POSTCODE=
FOREIGN_PROVINCE=${ADDRESS_4}
FOREIGN_POSTAL_CODE=`print $line | cut -d'|' -f19 | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}'`
fi

PROCESSBODY="CDCI|"
PROCESSBODY="${PROCESSBODY}${ENTITY_TYPE}|"
PROCESSBODY="${PROCESSBODY}${CUSTOMER_ID}|"
PROCESSBODY="${PROCESSBODY}${BRANCH_NUMBER}|"
PROCESSBODY="${PROCESSBODY}${ACCOUNT_NUMBER}|"
PROCESSBODY="${PROCESSBODY}${ACCOUNT_DATE_OPEN}|"
PROCESSBODY="${PROCESSBODY}${CORPORATE_NAME}|"
PROCESSBODY="${PROCESSBODY}${LAST_NAME}|"
PROCESSBODY="${PROCESSBODY}${FIRST_NAME}|"
PROCESSBODY="${PROCESSBODY}${MIDDLE_NAME}|"
PROCESSBODY="${PROCESSBODY}${NAME_SUFFIX}|"
PROCESSBODY="${PROCESSBODY}${PERSON_GENDER}|"
PROCESSBODY="${PROCESSBODY}${BIRTH_DATE}|"
PROCESSBODY="${PROCESSBODY}${AGE}|"
PROCESSBODY="${PROCESSBODY}${CITIZENSHIP_CODE}|"
PROCESSBODY="${PROCESSBODY}${FED_ID}|"
PROCESSBODY="${PROCESSBODY}${FED_ID_TYPE}|"
PROCESSBODY="${PROCESSBODY}${NATIONAL_ID}|"
PROCESSBODY="${PROCESSBODY}${NATIONAL_ID_TYPE}|"
PROCESSBODY="${PROCESSBODY}${STREET_ADDRESS}|"
PROCESSBODY="${PROCESSBODY}${CITY_NAME}|"
PROCESSBODY="${PROCESSBODY}${STATE_CODE}|"
PROCESSBODY="${PROCESSBODY}${POSTCODE}|"
PROCESSBODY="${PROCESSBODY}${FOREIGN_PROVINCE}|"
PROCESSBODY="${PROCESSBODY}${FOREIGN_POSTAL_CODE}|"
PROCESSBODY="${PROCESSBODY}${COUNTRY_NAME}|"
PROCESSBODY="${PROCESSBODY}${COUNTRY_CODE}"

print "${PROCESSBODY}" >> ${INQ_TEMP_FILE}
done < ${EDD_HOME}/tmp/inquiry.txt

}

looks like you could have done all of this in ONE awk program withOUT constant chopping of lines with print|sed|cut|awk.

vgersh99,
can you please let me know how to use
cut and sed inside awk program?

Thanks & Regards

example
how to write below line inside awk
ACCOUNT_DATE_OPEN=`print "$line" | cut -d'|' -f3 |sed 's/[^0-9]//g' | awk '{gsub(/^[ \t]+|[ \t]+$/,"");print}' | cut -c1-8`

you don't need to use cut/sed - awk provides most of the cut/sed functions natively.

what does the 'line' look like AND what part of it you want?
A sample pls!

example of line
COL001 | P | 2007-02-01-00.00.00.000000 | | sam | babu | | | M | 1949-01-04-00.00.00.000000 | INDIA | | C60 | | 110 S | | ENNIS | IN | 46563 | INDIA |