UNIX for Beginners Questions & Answers

wc -l *|sort

15263 Image.txt
16401 reference.txt
40459 richtexteditor.txt

15263 1401 Image.txt
16401 15999 reference.txt
40459 35670 richtexteditor.txt

#!/bin/ksh

wc -l * | sed '$d' | sort | while read lines file junk
do
   echo $lines $(sort < $file | uniq -u |wc -l) $file
done

awk '{u[$0]; l++} ENDFILE {print length(u), l, FILENAME; delete u; l=0}' * | sort -k1,1n

gawk '{l[$0]++} ENDFILE {for (i in l) {if (l[i]==1) u++;t+=l[i]} print t, u, FILENAME; delete l; u=t=0}' *

1
2
3
3
4
1

1
2
3
3
4
1
5

#!/bin/bash
tmpf="/tmp/$$.result"

trap 'rm -f "$tmpf"' EXIT

awk '
function dump() {
	print linecount, distinct, lastfile
	linecount = distinct = 0
	split("", lines)
}

FILENAME != lastfile {
	if(lastfile)
		dump()
	lastfile = FILENAME
}

{	linecount++
	if(lines[$0]++ == 0)
		distinct++
}

END {	dump()
}' * > "$tmpf"

echo 'Sorted by increaasing number of lines in files:'
sort -n "$tmpf"

echo 'Sorted by increaasing number of distinct lines in files:'
sort -k2,2n "$tmpf"

awk '
FNR==1 {
  filenr++
  Name[filenr]=FILENAME
}

!Seen[filenr,$0]++ {
  Uniq[filenr]++
} 

{
  Total[filenr]++
} 

END {
  for(i in Name)
    print Total[i], Uniq[i], Name[i]
}
' file* | sort -nk1,1 -nk2,2 -k3,3

for f in *; do printf "%s/%s lines are unique in file %s\n" $(sort "$f" | uniq -u | wc -l) $(wc -l < "$f") "$f"; done

for f in *; do printf "%s/%s unique lines in file %s\n" $(sort  -u "$f" | wc -l) $(wc -l < "$f") "$f"; done