no longer needful as a script to clean the data

hosts.awk

BEGIN		{
			fam = 0
			parasite_genus = 0
			host_genus = 0
			parasite_species = 0
			print "Host_fam\tHost_genus\tHost_sp\tParasite_genus\tParasite_sp\tk_i\tLocation\tParasite_fam"
			}
/^[A-Z]/		{fam = $1}
/^\t[A-Z]/		{
			host_genus = $1
			if ($2 ~ /\(.*\)/) 
				host_species = $3
			else
				host_species = $2
			match($0, /.*(\(.*\))$/, loc)
			}
/^\t\t[A-Z]/	{
			# the parasite family in in brackets; may or may not be at end of line
			match($0, /.*(\(.*\)).?/, parasite_fam)
			# A full parasite genus name is written in sentence case
			if ($1 ~ /[A-Z][a-z]/) parasite_genus = $1
			# koenobiont or idiobiont or question mark
			match($0, /([ki\?]+?$)/, ki)
			match($0, /.*([0-9]).*/, parasite_num)
			parasite_sp_name = $2 parasite_num[1]
			printf "%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n", fam, host_genus, host_species, parasite_genus, parasite_sp_name, ki[1], loc[1], parasite_fam[1]
			}

parasite.awk

BEGIN		{
			fam = 0
			parasite_genus = 0
			host_genus = 0
			parasite_species = 0
			print "Host_fam\tHost_genus\tHost_sp\tParasite_genus\tParasite_sp\tk_i\tLocation"
			}
/^[A-Z]/		{fam = $1}
/^\(?.*\t[A-Z]/{
			parasite_genus = $2
			if ($3 ~ /\(.*\)/) 
				parasite_species = $4
			else
				parasite_species = $3
			match($0, /.*(\(.*\))$/, loc)
			}
/^\t\t[A-Z]/	{
			if ($1 ~ /[A-Z][a-z]/) host_genus = $1
			printf "%s\t%s\t%s\t%s\t%s\t%s\t%s\n", fam, parasite_genus, parasite_species, host_genus, $2, $NF, loc[1]
			}