updates for version 1.0

code_snippets/Builtin_functions.sh

@@ -1,3 +1,5 @@
+## length
+
 awk 'BEGIN{print length("road"); print length(123456)}'
 
 printf 'fox\ntiger\n' | awk '{print length()}'
@@ -8,6 +10,10 @@ echo 'αλεπού' | awk '{print length()}'
 
 echo 'αλεπού' | awk -b '{print length()}'
 
+echo 'αλεπού' | LC_ALL=C awk '{print length()}'
+
+## Array sorting
+
 awk 'BEGIN{a["z"]=1; a["x"]=12; a["b"]=42; for(i in a) print i, a[i]}'
 
 awk 'BEGIN{PROCINFO["sorted_in"] = "@ind_str_asc";
@@ -16,6 +22,11 @@ awk 'BEGIN{PROCINFO["sorted_in"] = "@ind_str_asc";
 awk 'BEGIN{PROCINFO["sorted_in"] = "@val_num_asc";
      a["z"]=1; a["x"]=12; a["b"]=42; for(i in a) print i, a[i]}'
 
+awk 'BEGIN{PROCINFO["sorted_in"] = "@ind_str_asc"}
+     {a[$2]=$0} END{for(k in a) print a[k]}' table.txt
+
+## split
+
 printf '     one \t two\t\t\tthree  ' | awk '{split($0, a); print a[2]}'
 
 s='Joe,1996-10-25,64,78'
@@ -25,7 +36,7 @@ echo "$s" | awk -F, '{split($2, d, "-"); print $1 " was born in " d[1]}'
 s='air,water,12:42:3'
 
 echo "$s" | awk -F, '{n=split($NF, a, ":");
-                     for(i=1; i<=n; i++) print $1,$2,a[i]}'
+                     for(i=1; i<=n; i++) print $1, $2, a[i]}'
 
 s='Sample123string42with777numbers'
 
@@ -41,10 +52,14 @@ cat marks.txt
 awk 'BEGIN{OFS="\t"; split("DCBAS", g, //)}
      {$(NF+1) = NR==1 ? "Grade" : g[int($NF/10)-4]} 1' marks.txt
 
+## patsplit
+
 s='eagle,"fox,42",bee,frog'
 
 echo "$s" | awk '{patsplit($0, a, /"[^"]*"|[^,]*/); print a[2]}'
 
+## substr
+
 echo 'abcdefghij' | awk '{print substr($0, 1, 5)}'
 
 echo 'abcdefghij' | awk '{print substr($0, 4, 3)}'
@@ -57,6 +72,8 @@ echo 'abcdefghij' | awk -v FS= '{print $3}'
 
 echo 'abcdefghij' | awk -v FS= '{print $3, $5}'
 
+## match
+
 s='051 035 154 12 26 98234'
 
 echo "$s" | awk 'match($0, /[0-9]{4,}/){print substr($0, RSTART, RLENGTH)}'
@@ -72,6 +89,8 @@ s='42 foo-5, baz3; x-83, y-20: f12'
 echo "$s" | awk '{ while( match($0, /([0-9]+),/, m) ){print m[1];
                  $0=substr($0, RSTART+RLENGTH)} }'
 
+## index
+
 cat eqns.txt
 
 awk '/i*(t+9-g)/' eqns.txt
@@ -92,6 +111,8 @@ echo 'a\b\c\d' | awk -v s='a\\b' 'index($0, s)'
 
 echo 'a\b\c\d' | s='a\b' awk 'index($0, ENVIRON["s"])'
 
+## system
+
 awk 'BEGIN{system("echo Hello World")}'
 
 wc table.txt
@@ -102,20 +123,24 @@ awk 'BEGIN{system("seq 10 | paste -sd, > out.txt")}'
 
 cat out.txt
 
-cat f2.txt
+cat t2.txt
 
-echo 'f1,f2,f3' | awk -F, '{system("cat " $2 ".txt")}'
+echo 'f1,t2,f3' | awk -F, '{system("cat " $2 ".txt")}'
 
 ls xyz.txt
 
 echo $?
 
 awk 'BEGIN{s=system("ls xyz.txt"); print "Exit status: " s}'
 
-awk 'BEGIN{sum = 3.1428 + 10; print sum}'
+## printf and sprintf
+
+awk 'BEGIN{print OFMT}'
 
 awk 'BEGIN{sum = 3.1428 + 100; print sum}'
 
+awk 'BEGIN{OFMT="%.5f"; sum = 3.1428 + 100; print sum}'
+
 awk 'BEGIN{sum = 3.1428 + 10; printf "%f\n", sum}'
 
 awk 'BEGIN{sum = 3.1428 + 10; printf "%.3f\n", sum}'
@@ -154,6 +179,8 @@ awk 'BEGIN{printf "n%%d gives the remainder\n"}'
 
 awk 'BEGIN{pi = 3.14159; s = sprintf("%010.3f", pi); print s}'
 
+## Redirecting print output
+
 seq 6 | awk 'NR%2{print > "odd.txt"; next} {print > "even.txt"}'
 
 cat odd.txt

code_snippets/Control_Structures.sh

@@ -1,3 +1,5 @@
+## if-else
+
 awk '/^b/{print; if($NF>0) print "------"}' table.txt
 
 awk '/^b/{print; if($NF>0) print "------"; else print "======"}' table.txt
@@ -6,6 +8,8 @@ seq 6 | awk '{ORS = NR%3 ? "-" : RS} 1'
 
 awk '/^b/{print; print($NF>0 ? "------" : "======")}' table.txt
 
+## loops
+
 awk 'BEGIN{for(i=2; i<7; i+=2) print i}'
 
 awk -v OFS=, '{for(i=1; i<=NF; i++) if($i ~ /^[bm]/) $i="["$i"]"} 1' table.txt
@@ -20,17 +24,23 @@ awk 'BEGIN{i=6; while(i>0){print i; i-=2}}'
 
 echo 'titillate' | awk '{while(gsub(/til/, "")) print}'
 
+echo 'titillate' | awk '{do{print} while(gsub(/til/, ""))}'
+
+## next
+
 awk '/\<par/{print "%% " $0; next} {print /s/ ? "X" : "Y"}' word_anchors.txt
 
+## exit
+
 seq 3542 4623452 | awk 'NR==2452{print; exit}'
 
 echo $?
 
-awk '/^br/{print "Invalid input"; exit 1}' table.txt 
+awk '/^br/{print "Invalid input"; exit 1}' table.txt
 
 echo $?
 
-awk 'FNR==2{print; exit}' table.txt greeting.txt 
+awk 'FNR==2{print; exit}' table.txt greeting.txt
 
 awk 'BEGIN{print "hi"; exit; print "hello"}
      /^b/;

code_snippets/Dealing_with_duplicates.sh

@@ -1,15 +1,21 @@
+## Whole line duplicates
+
 cat purchases.txt
 
 awk '{print +a[$0] "\t" $0; a[$0]++}' purchases.txt
 
 awk '!a[$0]++' purchases.txt
 
+## Column wise duplicates
+
 cat duplicates.txt
 
 awk -F, '!seen[$NF]++' duplicates.txt
 
 awk -F, '!seen[$1,$3]++' duplicates.txt
 
+## Duplicate count
+
 awk -F, '++seen[$2]==2' duplicates.txt
 
 awk -F, '++seen[$NF]==3' duplicates.txt

code_snippets/Field_separators.sh

@@ -1,3 +1,5 @@
+## Default field separation
+
 cat table.txt
 
 awk '$1 ~ /^b/{print $4}' table.txt
@@ -18,7 +20,7 @@ echo '   a   b   c   ' | awk '{print $NF "."}'
 
 printf '     one \t two\t\t\tthree  ' | awk '{print NF}'
 
-printf '     one \t two\t\t\tthree  ' | awk '{print $2}'
+printf '     one \t two\t\t\tthree  ' | awk '{print $2 "."}'
 
 awk 'BEGIN{printf "%.16f\n", 2.999999999999999}'
 
@@ -28,6 +30,8 @@ awk '{print $2.999999999999999}' table.txt
 
 awk '{print $2.9999999999999999}' table.txt
 
+## Input field separator
+
 echo 'goal:amazing:whistle:kwality' | awk -F: '{print $1}'
 
 echo 'goal:amazing:whistle:kwality' | awk -F: '{print $NF}'
@@ -60,6 +64,14 @@ echo '   a   b   c   ' | awk -F' ' '{print NF}'
 
 echo '   a   b   c   ' | awk -F'[ ]' '{print NF}'
 
+echo 'RECONSTRUCTED' | awk -F'[aeiou]+' -v IGNORECASE=1 '{print $1}'
+
+echo 'RECONSTRUCTED' | awk -F'e' -v IGNORECASE=1 '{print $1}'
+
+echo 'RECONSTRUCTED' | awk -F'[e]' -v IGNORECASE=1 '{print $1}'
+
+## Output field separator
+
 awk '{print $1, $3}' table.txt
 
 echo 'goal:amazing:whistle:kwality' | awk -F: -v OFS=: '{print $2, $NF}'
@@ -78,6 +90,8 @@ echo 'Sample123string42with777numbers' | awk -F'[0-9]+' -v OFS=, '1'
 
 echo 'Sample123string42with777numbers' | awk -F'[0-9]+' -v OFS=, '{$1=$1} 1'
 
+## Manipulating NF
+
 echo 'goal:amazing:whistle:kwality' | awk -F: -v OFS=, '{NF=2} 1'
 
 echo 'goal:amazing:whistle:kwality' | awk -F: -v OFS=: '{$(NF+1)="sea"} 1'
@@ -86,6 +100,8 @@ echo 'goal:amazing:whistle:kwality' | awk -F: -v OFS=: '{$8="go"} 1'
 
 echo 'goal:amazing:whistle:kwality' | awk -F: -v OFS=: '{NF=-1} 1'
 
+## FPAT
+
 s='Sample123string42with777numbers'
 
 echo "$s" | awk -v FPAT='[0-9]+' '{print $2}'
@@ -98,6 +114,14 @@ echo "$s" | awk -F, '{print $2}'
 
 echo "$s" | awk -v FPAT='"[^"]*"|[^,]*' '{print $2}'
 
+echo 'Read Eat Sleep' | awk -v FPAT='e' '{print NF}'
+
+echo 'Read Eat Sleep' | awk -v IGNORECASE=1 -v FPAT='e' '{print NF}'
+
+echo 'Read Eat Sleep' | awk -v IGNORECASE=1 -v FPAT='[e]' '{print NF}'
+
+## FIELDWIDTHS
+
 cat items.txt
 
 awk -v FIELDWIDTHS='8 4 6' '{print $2}' items.txt

code_snippets/Gotchas_and_Tips.sh

@@ -1,9 +1,13 @@
+## Prefixing $ for variables
+
 awk -v word="cake" '$2==$word' table.txt
 
 awk -v word="cake" '$2==word' table.txt
 
 awk -v field=2 '{print $field}' table.txt
 
+## Dos style line endings
+
 printf 'mat dog\n123 789\n' | awk '{print $2, $1}'
 
 printf 'mat dog\r\n123 789\r\n' | awk '{print $2, $1}'
@@ -14,6 +18,8 @@ printf 'mat dog\r\n123 789\r\n' | awk -v RS='\r\n' '{print $2, $1}'
 
 printf 'mat dog\r\n123 789\r\n' | awk -v RS='\r\n' '{sub(/$/, ".")} 1'
 
+## Word boundary differences
+
 echo 'I have 12, he has 2!' | awk '{gsub(/\y..\y/, "[&]")} 1'
 
 echo 'I have 12, he has 2!' | awk '{gsub(/\<..\>/, "[&]")} 1'
@@ -24,6 +30,8 @@ echo 'hi log_42 12b' | awk '{gsub(/\</, ":")} 1'
 
 echo 'hi log_42 12b' | awk '{gsub(/\>/, ":")} 1'
 
+## Relying on default initial value
+
 awk '{sum += $NF} END{print sum}' table.txt
 
 awk '{sum += $NF} ENDFILE{print FILENAME ":" sum}' table.txt
@@ -32,6 +40,16 @@ awk '{sum += $NF} ENDFILE{print FILENAME ":" sum}' table.txt marks.txt
 
 awk '{sum += $NF} ENDFILE{print FILENAME ":" sum; sum=0}' table.txt marks.txt
 
+## Code in replacement section
+
+awk '{sub(/^(br|ye)/, ++c ") &")} 1' table.txt
+
+awk '/^(br|ye)/{sub(/^/, ++c ") ")} 1' table.txt
+
+awk '{gsub(/\<b/, ++c ") &")} 1' table.txt
+
+## Forcing numeric context
+
 awk '{sum += $NF} END{print sum}' table.txt
 
 awk '{sum += $1} END{print sum}' table.txt
@@ -40,10 +58,14 @@ awk '{sum += $1} END{print sum}' /dev/null
 
 awk '{sum += $1} END{print +sum}' /dev/null
 
+## Forcing string context
+
 echo '5 5.0' | awk '{print ($1==$2 ? "same" : "different"), "number"}'
 
 echo '5 5.0' | awk '{print ($1""==$2 ? "same" : "different"), "string"}'
 
+## Negative NF
+
 cat varying.txt
 
 awk '{NF -= 2} 1' varying.txt
@@ -54,6 +76,8 @@ awk '{print $(NF-2)}' varying.txt
 
 awk 'NF>2{print $(NF-2)}' varying.txt
 
+## Faster execution
+
 time awk '/^([a-d][r-z]){3}$/' /usr/share/dict/words > f1
 
 time LC_ALL=C awk '/^([a-d][r-z]){3}$/' /usr/share/dict/words > f2

code_snippets/Inplace_file_editing.sh

@@ -1,8 +1,10 @@
-cat greeting.txt
+## Without backup
 
-awk -i inplace '{print NR ". " $0}' greeting.txt
+cat greet.txt
 
-cat greeting.txt
+awk -i inplace '{print NR ". " $0}' greet.txt
+
+cat greet.txt
 
 cat f1.txt
 
@@ -14,6 +16,8 @@ cat f1.txt
 
 cat f2.txt
 
+## With backup
+
 cat f3.txt
 
 awk -i inplace -v inplace::suffix='.bkp' -v OFS=, '{$1=$1} 1' f3.txt

code_snippets/Installation_and_Documentation.sh

@@ -1,8 +1,10 @@
-wget https://ftp.gnu.org/gnu/gawk/gawk-5.0.1.tar.xz
+## Installation
 
-tar -Jxf gawk-5.0.1.tar.xz
+wget https://ftp.gnu.org/gnu/gawk/gawk-5.1.0.tar.xz
 
-cd gawk-5.0.1/
+tar -Jxf gawk-5.1.0.tar.xz
+
+cd gawk-5.1.0/
 
 ./configure 
 
@@ -14,7 +16,11 @@ type -a awk
 
 awk --version | head -n1
 
+## Documentation
+
 man awk
 
+## Options overview
+
 awk --help
 

code_snippets/Multiple_file_input.sh

@@ -1,12 +1,18 @@
+## BEGINFILE, ENDFILE and FILENAME
+
 awk 'BEGINFILE{print "--- " FILENAME " ---"} 1' greeting.txt table.txt
 
 awk 'ENDFILE{print $0}' greeting.txt table.txt
 
-awk '/3/{print FILENAME; nextfile}' f[1-3].txt greeting.txt
+## nextfile
+
+awk '/I/{print FILENAME; nextfile}' f[1-3].txt greeting.txt
 
 awk 'BEGINFILE{m1=m2=0} /o/{m1=1} /at/{m2=1}
      m1 && m2{print FILENAME; nextfile}' f[1-3].txt greeting.txt
 
+## ARGC and ARGV
+
 awk 'BEGIN{for(i=0; i<ARGC; i++) print ARGV[i]}' f[1-3].txt greeting.txt
 
 awk 'BEGIN{for(i=0; i<ARGC; i++) print ARGV[i]}' table.txt n=5 greeting.txt