awk

print

#!/usr/bin/bash

awk '{ print }' "$@"

BEGIN

#!/usr/bin/bash

awk 'BEGIN { print "NAME\tRATE\tHOURS"; print "" }
    { print }' "$@"

END

#!/usr/bin/bash

awk ' { OFS="\t" }
BEGIN { print "NAME", "RATE", "HOURS"; print "" }
    { print $1, $2, $3}
    { rate = rate + $2 }
    { hours = hours + $3 }
END { print "AVERAGE", rate / NR, hours / NR }' "$@"

#!/usr/bin/bash

ExampleGroup 'basic awk oneliner'

  Example 'print emp.data'
    When call bin/eg1.sh bin/emp.data
    The output should eq 'Beth	4.00	0
Dan	3.75	0
Kathy	4.00	10
Mark	5.00	20
Mary	5.50	22
Susie	4.25	18'
  End

  Example 'print a header using BEGIN'
    When call bin/eg2.sh bin/emp.data
    The output should eq 'NAME	RATE	HOURS

Beth	4.00	0
Dan	3.75	0
Kathy	4.00	10
Mark	5.00	20
Mary	5.50	22
Susie	4.25	18'
  End

  Example 'print average rates and hours using END'
    When call bin/eg3.sh bin/emp.data
    The output should eq 'NAME RATE HOURS

Beth	4.00	0
Dan	3.75	0
Kathy	4.00	10
Mark	5.00	20
Mary	5.50	22
Susie	4.25	18
AVERAGE	4.41667	11.6667'
  End

End

Built-in variables

ARGC: number of command-line arguments
ARGV[n]: array of command-line arguments
FILENAME: name of current input file
FNR: input record number in current file
FS: input field separator (default blank)
NF: number of fields in current input record
NR: input record number since beginning
OFMT: output format for numbers (default "%.6g")
OFS: output field separator (default blank)
ORS: output record separator (default newline)
RLENGTH: length of string matched by regular expression in match
RS: input record separator (default newline)
RSTART: beginning position of string matched by match
SUBSEP: separator for array subscripts of form [i,j...] (default "\034")

Chapter 2 Awk book examples

countries.tsv

USSR	8649	275	Asia
Canada	3852	25	North America
China	3705	1032	Asia
USA	3615	237	North America
Brazil	3286	134	South America
India	1267	746	Asia
Mexico	762	78	North America
France	211	55	Europe
Japan	144	120	Asia
Germany	96	61	Europe
England	94	56	Europe

BEGIN and END example

#!/usr/bin/bash

awk 'BEGIN { FS = "\t"
             printf("%10s %6s %5s   %s\n\n", 
                   "COUNTRY", "AREA", "POP", "CONTINENT")
           }
    { printf("%10s %6d %5d   %s\n", $1, $2, $3, $4) 
      area = area + $2
      pop = pop + $3
    }
    END { printf("\n%10s %6d %5d\n", "TOTAL", area, pop) }' "$@"

#!/usr/bin/bash

ExampleGroup 'Chapter 2 Examples BEGIN and END'

  Example 'print countries with column headers and totals'
    When call bin/ch2_eg1.sh bin/countries.tsv
    The output should eq '   COUNTRY   AREA   POP   CONTINENT

      USSR   8649   275   Asia
    Canada   3852    25   North America
     China   3705  1032   Asia
       USA   3615   237   North America
    Brazil   3286   134   South America
     India   1267   746   Asia
    Mexico    762    78   North America
    France    211    55   Europe
     Japan    144   120   Asia
   Germany     96    61   Europe
   England     94    56   Europe

     TOTAL  25681  2819'
  End

End

String-matching Patterns

/regexpr/: Matches when the current input line contains a substring matched by regexpr. Shorthand for $0 ~ /regexpr/
expression ~ /regexpr/: Matches if the string value of expression contains a substring matched by regexpr.
expression !~ /regexpr/: Matches if the string value of expression does not contain a substring matched by regexpr.

#!/usr/bin/bash

ExampleGroup '/regexpr/'

  Example '$4 ~ /Asia/'
    When call awk '$4 ~ /Asia/' bin/countries.tsv
    The output should eq 'USSR	8649	275	Asia
China	3705	1032	Asia
India	1267	746	Asia
Japan	144	120	Asia'
  End

End

Range Patterns start, end

#!/usr/bin/bash

ExampleGroup 'Range Patterns'

  Example '/Canada/, /USA/'
    When call awk '/Canada/, /USA/' bin/countries.tsv
    The output should eq 'Canada	3852	25	North America
China	3705	1032	Asia
USA	3615	237	North America'
  End

End