UNIX for Advanced & Expert Users

#! /usr/bin/ksh

exec < file1.txt
integer saved limit
saved=0
limit=1000

#
#  read a line and break it into fields
while IFS="" read line ; do
        tmp=${line#?????????}
        field1=${line%$tmp}
        line="$tmp"
        tmp=${line#????}
        field2=${line%$tmp}
        line="$tmp"
        tmp=${line#??}
        field3=${line%$tmp}
        line="$tmp"
        tmp=${line#????}
        field4=${line%$tmp}
        field5="$tmp"

#
#  If field2 is numeric we will use it to search for a new field4

        if [[ $field2 == +([0-9]) ]] ; then

#
#  See if we previously saved the data for this field2

                eval data=\${XX${field2}:-NOT_THERE}
                if [[ $data != NOT_THERE ]] ; then
                        field4="$data"
                else

#
#  See if we can find field2 in the second file

                        if data=$(grep "^${field2}," file2.txt) ; then
                                data=${data##*,}
                                echo found data = $data
                                field4="$data"

#
#  Save the first $limit records we find in memory to avoid re-examining the file each time

                                if ((saved<limit)) ; then
                                        ((saved=saved+1))
                                        eval XX${field2}=\${data}
                                fi
                        fi
                fi
        fi
        echo "${field1}${field2}${field3}${field4}${field5}"
done
exit 0

#!/usr/bin/python
f2data = {} #store as look up table
for f2 in open("file2.txt"):
	fone,ftwo = f2.strip().split(",") # get 1235, 9998 etc
	f2data[fone] = ftwo
for f1 in open("file1.txt"):				
		if f1[9:13] in f2data:			
			print f1[0:14] + f2data.get(f1[9:13]) + f1[19:].strip()
		else:
			print f1.strip()

#/home/test> python test.py
abcd.....1234......XY
abcd.....1235.9998XX
abcd.................
abcd...231236..1111YX
abcd...241236..1112YY
abcd...241237.9999YY
abce.....1235.9998YY

awk 'BEGIN{
             FS = ","
             while (getline < "file2" > 0)
                     arr[$1] = $2
     }
     {
             key = substr($0, 10, 4)
             if (key in arr)
                     print substr($0, 1, 15) arr[key] substr($0, 20, 2)
             else
                     print $0
     }
     ' file1