Shell Programming and Scripting

# Col1  -  Col2 - Col3 - Col4
Patricia started Jun 22 05:22:58
Carolina started Jun 22 05:23:03
Carolina started Jun 22 05:23:37
Andrea   started Jun 22 05:25:52
Ana      started Jun 22 05:26:11
Andrea   started Jun 22 05:26:52

# Col1  -  Col2 - Col3 - Col4
Patricia started Jun 22 05:22:58
Carolina started Jun 22 05:23:03
Andrea   started Jun 22 05:25:52
Ana      started Jun 22 05:26:11

# Col1  -  Col2 - Col3 - Col4
Carolina started Jun 22 05:23:37
Andrea   started Jun 22 05:26:52

sort -k1,1 -k3M Dato01.txt | awk 'T[$1] {print > "Dato03.txt"} !T[$1]++ {print > "Dato02.txt"}'

infile=Dato01.txt
outfile=Dato02.txt

[[ ! -f $infile.bk ]] && cp $infile $infile.bk

ex $infile <<EDIT
$(awk '
  NR==1 {print ":" NR " w " outfile; next;}
  {if (a[$1]++) r[c++]=NR}
  END {
     for (i=0; i<c; i++) print ":" r[i] " w >> " outfile;
     for (i=c-1; i>=0; i--) print ":" r[i] " d";
     print ":wq!";
  }
' outfile=$outfile $infile)
EDIT

infile=Dato01.txt                                            # set input file name variable
outfile=Dato02.txt                                           # set second file (repeat lines) name variable

[[ ! -f $infile.bk ]] && cp $infile $infile.bk               # backup input file

ex $infile <<EDIT                                            # invoke inline editor (ex) for input file (ex script built by awk)
$(awk '                                                      # uset awk to build commands for ex
  NR==1 {print ":" NR " w " outfile; next;}                  # write first line to second file (done by ex)
  {if (a[$1]++) r[c++]=NR}                                   # build repeat lines array
  END {
     for (i=0; i<c; i++) print ":" r[i] " w >> " outfile;    # write repeat lines to second file (done by ex)
     for (i=c-1; i>=0; i--) print ":" r[i] " d";             # delete repeat lines from input file (done by ex)
     print ":wq!";                                           # write input file (done by ex)
  }
' outfile=$outfile $infile)                                  # end of awk
EDIT                                                         # end of ex script

#!/bin/ksh
# We can't use awk to overwrite the input file directly, so we create a
# temporary output file with the lines from the input file that are to be kept
# and a duplicate output file with the lines for names that appear two or more
# times in the input file.
#
# When awk compltes, if it was successful, we'll copy the temporary output file
# back to the input file.  Otherwise, the input file will not be changed.

InFile="Dato01.txt"		# Name the input file.
DupFile="Dato02.txt"		# Name the output file for duplicates.
TempFile="$InFile.$$"		# Name the temporary output file.

trap 'rm -f "$TempFile"' EXIT	# When the script completes, remove the temp file.

awk -v new="$TempFile" -v dup="$DupFile" '
NR == 1 {
	# Copy the header line from the input file to both output files.
	print > new
	print > dup
	next
}
{	if($1 in seen) {
		# We have seen this person before.  Copy this line to the
		# duplicates file.
		print > dup
	} else {
		# We have not seen this person before.  Copy this line to the
		# temporary file (which will replace the input file when we are
		# done).
		print > new

		# Note that we have seen this person.
		seen[$1]
	}
}' "$InFile" > "$TempFile" && cp "$TempFile" "$InFile"