Shell Programming and Scripting

File1


leave	kbl;tbc<A,B;alt<-23
leave	kbl;tbc<B,C,D
collect	kbl;tbc<A,B,C;alt<-34
collect	kbl;tbc<D,B,C,A
leave	lbl;tbc<A;J
leave	lbl;tbc<B;C
leave	kbl;tbc<A;B
leave	tbc<B;C;D

File2

leave	kbl;tbc<A,B;alt<-23
leave	kbl;tbc<B,C,D
collect	kbl;tbc<A;alt<-34
collect	kbl;tbc<C,A
collect	kbl;tbc<B,A
leave	lbl;tbc<A;J
leave	lbl;tbc<B;C
leave	kbl;tbc<A;B
leave	tbc<B;C;D

Output

File1	A	B	C	D
File2	A	B	C

awk ' 
if ($1=='collect')  
gsub(/*tbc*</,//);
gsub(/*;*/,"");
print FILENAME $2'

awk ' 
  $1=="collect" {  
     sub(/.*tbc\</,"");
     sub(/;.*/,"");
     print FILENAME, $0
  }
'  file

awk -F";" '/collect/ {sub(/tbc</,"");print $2}' File1 | paste -sd , - | awk -F, '{for(i=1;i<=NF;i++) print $i}' |sort -u | tr "\n" "\t"

$ awk ' 
  $1=="collect" {  
     sub(/.*tbc\</,"");
     sub(/;.*/,"");
     print FILENAME, $0
  } ' file1 file2
file1 A,B,C
file1 D,B,C,A
file2 A
file2 C,A
file2 B,A

awk -F '.*tbc<|,' '{sub(/;.*/,x, $NF); for (i=2; i<NF; i++) print FILENAME, $i }' file1 file2 | sort -u

file1 A
file1 B
file1 C
file1 D
file2 A
file2 B
file2 C

awk '{ x[$1]=x[$1] "," $2 } 
END { 
   for (k in x) print k,x[k];
}'

fil1.txt.txt A
fil1.txt.txt B
fil1.txt.txt C
fil1.txt.txt D
fil3.txt.txt A
fil3.txt.txt B
fil3.txt.txt C
fil3.txt.txt D

$ cat fil1.txt.txt
leave   kbl;tbc<A,B;alt<-23
leave   kbl;tbc<B,C,D
collect kbl;tbc<A,B,C;alt<-34
collect kbl;tbc<D,B,C,A
leave   lbl;tbc<A;J
leave   lbl;tbc<B;C
leave   kbl;tbc<A;B
leave   tbc<B;C;D


$ cat fil2.txt.txt
leave   kbl;tbc<A,B;alt<-23
leave   kbl;tbc<B,C,D
collect kbl;tbc<A;alt<-34
collect kbl;tbc<C,A
collect kbl;tbc<B,A
leave   lbl;tbc<A;J
leave   lbl;tbc<B;C
leave   kbl;tbc<A;B
leave   tbc<B;C;D



$ cat fil3.txt.txt
leave   kbl;tbc<A,B;alt<-23
leave   kbl;tbc<B,C,D
collect kbl;tbc<A,D;alt<-34
collect kbl;tbc<C,A
collect kbl;tbc<B,A
leave   lbl;tbc<A;J
leave   lbl;tbc<B;C
leave   kbl;tbc<A;B
leave   tbc<B;C;D

$ awk -F '.*tbc<|,' '{sub(/;.*/,x, $NF); for (i=2; i<NF; i++) print FILENAME, $i }' fil1.txt.txt fil2.txt.txt | sort -u
fil1.txt.txt A
fil1.txt.txt B
fil1.txt.txt C
fil1.txt.txt D
fil2.txt.txt A
fil2.txt.txt B
fil2.txt.txt C

awk -F '.*tbc<|,' '{sub(/;.*/,x, $NF); for (i=2; i<NF; i++) print FILENAME, $i }' fil1.txt.txt fil3.txt.txt | sort -u
fil1.txt.txt A
fil1.txt.txt B
fil1.txt.txt C
fil1.txt.txt D
fil3.txt.txt A
fil3.txt.txt B
fil3.txt.txt C

$ awk -F '.*tbc<|,' '{sub(/;.*/,x, $NF); for (i=2; i<NF; i++) print FILENAME, $i }' fil1.txt.txt fil2.txt.txt | sort -u