AWK Oneliners

Taken from http://web.archive.org/web/20060212103434/http://ullas.modblog.com/?gourl=http://www.softpanorama.org/Tools/awk.shtml

# Print the length of the longest input line:
awk '{ if (length($0) > max) max = length($0) } END { print max }' data

# Print every line that is longer than 80 characters:
awk 'length($0) > 80' data

# Print the length of the longest line in data:
expand data | awk '{ if (x < length()) x = length() }
END { print "maximum line length is " x }'

# Print seven random numbers from 0 to 100, inclusive:
awk 'BEGIN { for (i = 1; i <= 7; i++) print int(101 * rand()) }

# Print the total number of bytes used by files:
ls -l files | awk '{ x += $5 }
END { print "total bytes: " x }'

# Print the even-numbered lines in the data file:
awk 'NR % 2 == 0' data

# Print first two fields in opposite order:
awk '{ print $2, $1 }' file

# Print lines longer than 72 characters:
awk 'length > 72' file

# Print length of string in 2nd column
awk '{print length($2)}' file

# Add up first column, print sum and average:
{ s += $1 }
END { print "sum is", s, " average is", s/NR }
# Print fields in reverse order:
awk '{ for (i = NF; i > 0; --i) print $i }' file

# Print the last line
awk '{line = $0} END {print line}' file

# Print the total number of lines that contain the word Pat
awk '/Pat/ {nlines = nlines + 1}
END {print nlines}' file

# Print all lines between start/stop pairs:
awk '/start/, /stop/' file

# Print all lines whose first field is different from previous one:
awk '$1 != prev { print; prev = $1 }' file

# Print column 3 if column 1 > column 2:
awk '$1 > $2 {print $3}' file

# Print line if column 3 > column 2:
awk '$3 > $2' file

# Count number of lines where col 3 > col 1
awk '$3 > $1 {print i + "1"; i++}' file

# Print sequence number and then column 1 of file:
awk '{print NR, $1}' file

# Print every line after erasing the 2nd field
awk '{$2 = ""; print}' file

# Print hi 28 times
yes | head -28 | awk '{ print "hi" }'

# Print hi.0010 to hi.0099 (NOTE IRAF USERS!)
yes | head -90 | awk '{printf("hi00%2.0 f \n", NR+9)}'

# Find maximum and minimum values present in column 1
NR == 1 {m=$1 ; p=$1}
$1 >= m {m = $1}
$1 <= p {p = $1}
END { print "Max = " m, " Min = " p }

# Example of using substrings
# substr($2,9,7) picks out characters 9 thru 15 of column 2
{print "imarith", substr($2,1,7) " - " $3, "out."substr($2,5, 3)}
{print "imarith", substr($2,9,7) " - " $3, "out."substr($2,13 ,3)}
{print "imarith", substr($2,17,7) " - " $3, "out."substr($2,21 ,3)}
{print "imarith", substr($2,25,7) " - " $3, "out."substr($2,29 ,3)}

# Single space to Double space
awk '{print ; print ""}' infile > outfile

To find out the number of files of each type in your current directory

find ${*-.} -type f | xargs file | awk -F, '{print $1}' | awk '{$1=NULL;print $0}' | sort | uniq -c | sort -nr

One liner to find biggest file or directory.

du -sk ./* | sort -n | awk 'BEGIN{ pref[1]="K"; pref[2]="M"; pref[3]="G";} { total = total + $1; x = $1; y = 1; while( x > 1024 ) { x = (x + 1023)/1024; y++; } printf("%g%s\t%s\n",int(x*10)/10,pref[y],$2); } END { y = 1; while( total > 1024 ) { total = (total + 1023)/1024; y++; } printf("Total: %g%s\n",int(total*10)/10,pref[y]); }'

Awk script to create Insert statements

#!/usr/bin/awk -f
BEGIN {
# change the record separator from newline to nothing
#RS=""
# change the field separator from whitespace to newline
#FS="n"

}
{
# print the second and third line of the file
if ($1=="") $1 = "NULL";
if ($2=="") $2 = "NULL";
if ($3=="") $3 = "NULL";
if ($4=="") $4 = "NULL";
print "insert into mytable (someno,sequance,1_id1,2_id2,3_id3)values(501," NR "," $2 "," $3 "," $4")
;"


}
END {

}