/open-dm-dq/standardizer/other/scripts/extractMasterClueEN.awk

BEGIN {

    OFS = "\t"

}



{

    id = extract(1, 4) + 0

    type = extract(61, 2)

    fullName = extract(5, 23)

    standardAbbreviation = extract(29, 13)

    shortAbbreviation = extract(43, 5)

    uspsAbbreviation = extract(49, 4)



    print id, \

          type, \

          fullName, \

          standardAbbreviation, \

          shortAbbreviation, \

          uspsAbbreviation

}



function extract(offset, len) {

    result = substr($0, offset, len)

    gsub(/^[	 ]*/, "", result)

    gsub(/[	 ]*$/, "", result)

    gsub(/\&/, "&", result)

    return result

}