UNIX for Advanced & Expert Users

Aaaa|sdfhxfgh|sdgjhxfgjh|sdgjsdg|sgdjsg|
Aaaa|sdfhxfgh|sdgjhxfgjh|sdgjsdg|sgdjsg|
Aaaa|sdfhxfgh|sdgjhxfgjh|sdgjsdg|sgdjsg|

#------------------------------------------
#  Reading through the file and checking for the column length
#----------------------------------------------------
                logNote "Reading through the temp file and and checking for the column length"
 
                while read col_nm col_order_num col_len
                do
                                typeset -i col_len
                                typeset -i col_len_good
 
                                col_len_good=`expr $col_len + 1`
 
                                logNote "col_nm : $col_nm"
                                logNote "col_order_num : $col_order_num"
                                logNote "col_len : $col_len"
                                logNote "col_len_good : $col_len_good"
 
                                awk 'BEGIN{col_ord='$col_order_num';col_l='$col_len'}{FS="|"}{if (length($col_ord) > col_l) print $0;}'  $Src_File >> $Src_File.bad
 
                                awk 'BEGIN{col_ord='$col_order_num';col_l='$col_len_good'}{FS="|"}{if (length($col_ord) < col_l) print $0;}'  $Src_File > $Src_File.temp
 
                                rm -f $Src_File
                                mv $Src_File.temp $Src_File
 
                done <$RPT_FILE
==============================================================

sed '
  /^[A-Z][a-z]\{3\}|[a-z]\{8\}|[a-z]\{10\}|[a-z]\{7\}|[a-z]\{6\}|$/{
    w good_recs
    d
    }
 ' in_file >bad_recs

awk '
  NR==FNR{                                 # When the first file is being read (only then are FNR and NR equal)
    W[$2]=$3                               # create an (associative) array element for the column widths with the second
                                           # field as the index using the Field separator (see below)
    next                                   # Proceed to the next record
  }
  {
    for(i in W)                            # for every line in the second file, for every column in array W
      if(length($i)>W[i]){                 # if the length of the corresponding field is more than the max column width then
        print > "file.bad"                 # print that record of the second file to "file.bad"
        next                               # Proceed to the next record
      }
  }
  1                                        # If there are no fields with more characters than the max column width then print the record..
' FS='[^0-9]*' colwidthfile FS=\| file     # Set FS to any sequence of non-digits for the first file. Set it to "|" for the second file.