awk built-in functions

参考: http://www.gnu.org/software/gawk/

1. Numeric

int(x): return the nearest integer

rand(): return a random number

srand([x]): set the starting seed for random generator; if x is omitted, the current date and time are used for a seed.

$ awk 'BEGIN{print int(1.8), int(-1.8), int(010), int(0x0A), int(3a), int(b2)}'
1 -1 8 10 3 0

# rand()
function roll(n) { return 1 + int(rand() * n) }
{ printf("%d points", roll(6) + roll(6) + roll(6)); }

# fixed seed, unchanged random number
$ awk 'BEGIN{srand(1); print rand()}'
0.237788
$ awk 'BEGIN{srand(1); print rand()}'
0.237788

# the current date and time as a seed
$ awk 'BEGIN{srand(); print rand()}'
0.367979
$ awk 'BEGIN{srand(); print rand()}'
0.291809

2. String

2.1 sort

2.1.1 sorted by values.

len = asort(a): a is changed, the indices are replaced by sequential integers starting with one

len = asort(a, b): a isn’t changed. b is new array that comprises sequential integer indices and values of a.

2.1.1 sorted by indeces.

len = asorti(a): s is changed. the indices change into values, the sequential integers act as the indices

len = asorti(a, b): s isn’t changed. b is new array that comprises sequential integer indices and values came from the indices of a.

$ cat afile
last de
first sac
middle cul

$ awk '{a[$1]=$2} END{for(i in a) print i, a[i]}' afile
first sac
middle cul
last de

$ awk '{a[$1]=$2} END{len=asort(a); for(i=1;i<=len;i++) print i, a[i]}' afile
1 cul
2 de
3 sac

$ awk '{a[$1]=$2} END{len=asort(a,b); for(i=1;i<=len;i++) print i, b[i]}' afile
1 cul
2 de
3 sac

$ awk '{a[$1]=$2} END{len=asorti(a); for(i=1;i<=len;i++) print i, a[i]}' afile
1 first
2 last
3 middle

$ awk '{a[$1]=$2} END{len=asorti(a,b); for(i=1;i<=len;i++) print i, b[i], a[b[i]]}' afile
1 first sac
2 last de
3 middle cul

2.2 substitution

result = gensub(regexp, replacement, how, [target]): “how” is g/G/1-n

$ gawk 'BEGIN{a="abc def"; b=gensub(/(.+) (.+)/, "\\2 \\1", "g", a); print b}'
def abc

$ echo "a b c a b c" | gawk '{s=gensub(/a/, "AA", 2); print s}'
a b c AA b c

sub(regexp, replacement [, target])

gsub(regexp, replacement [, target]): global sub()

$ awk 'BEGIN{s="water, water, everywhere"; sub(/at/,"ith",s); print s}'
wither, water, everywhere

# the precise substring (&)
$ awk 'BEGIN{s="daabaaaa"; sub(/a+/, "C&C", s); print s}'
dCaaCbaaaa

$ cat bfile
American
Britain
China
Germany
France
$ awk '{gsub(/Britain/, "United Kingdom"); print}' bfile
American
United Kingdom
China
Germany
France

2.3 substring

substr(string, start [, length ])

split(string, array [, fieldsep [, seps ] ])

$ awk 'BEGIN{a="abcdefg";b=substr(a,1,2)"CDE"substr(a,6); print b}'
abCDEfg

$ awk 'BEGIN{split("cul-de-sac",a,"-",seps); for(i in a) print "a["i"]="a[i]; for(j in seps) print "seps["j"]="seps[j]}'
a[1]=cul
a[2]=de
a[3]=sac
seps[1]=-
seps[2]=-

2.4 others

pos = index(string, find)

len = length([string])

match(string, regexp [, array])

str = sprintf(format, expr-list)

num = strtonum(str)

tolower(str)

tolower(str)

$ awk 'BEGIN{print index("peanut", "an")}'
3

$ awk 'BEGIN{print length("peanut")}'
6

# the older versions of awk, the length() function could be called without any parentheses, but forget it.
$ awk 'BEGIN{len=length "peanut"; print len}'
0peanut

$ echo "foooobazbarrrrrr" | awk '{match($0, /(fo+).+(bar*)/, arr); print arr[1], arr[2]}'
foooo barrrrrr

$ awk 'BEGIN{pi=sprintf("%.2f (approx.)", 22/7); print pi}'
3.14 (approx.)

$ awk 'BEGIN{s="0x11"; printf("%d\n", strtonum(s))}'
17

$ awk 'BEGIN{print toupper("cest la vie")}'
CEST LA VIE
$ awk 'BEGIN{print tolower("Welcome You")}'
welcome you

3. IO

close(filename [, how]): “how” is “from” or “to”

fflush(filename)

system(command)

4. Time

mktime(“YYYY MM DD HH MM SS [DST]”)

strftime([format [, timestamp [, utc-flag] ] ])

systime(): the current time stamp since the system epoch

# default time format
$ awk 'BEGIN{print PROCINFO["strftime"]}'
%a %b %e %H:%M:%S %Z %Y

$ awk 'BEGIN{print strftime()}'
Mon Jul  6 09:29:13 EDT 2015

5. Bit-Manipulation

and(v1, v2 [, …])

or(v1, v2 [, …])

xor(v1, v2 [, …])

compl(val): the bitwise complement

lshift(val, count): shifted left by count bits

rshift(val, count): shifted right by count bits

$ cat bits2str.awk
function bits2str(bits, data, mask)
{
if (bits == 0)
return "0"

mask = 1;
for (; bits != 0; bits = rshift(bits, 1))
data = (and(bits, mask) ? "1" : "0") data

while ((length(data) % 8) != 0)
data = "0" data

return data
}

BEGIN {
printf "123 = %s\n", bits2str(123)
printf "0123 = %s\n", bits2str(0123)
printf "0x99 = %s\n", bits2str(0x99)
comp = compl(0x99)
printf "compl(0x99) = %#x = %s\n", comp, bits2str(comp)
shift = lshift(0x99, 2)
printf "lshift(0x99, 2) = %#x = %s\n", shift, bits2str(shift)
shift = rshift(0x99, 2)
printf "rshift(0x99, 2) = %#x = %s\n", shift, bits2str(shift)
}

$ awk -f bits2str.awk
123 = 01111011
0123 = 01010011
0x99 = 10011001
compl(0x99) = 0x1fffffffffff66 = 00011111111111111111111111111111111111111111111101100110
lshift(0x99, 2) = 0x264 = 0000001001100100
rshift(0x99, 2) = 0x26 = 00100110

6. Data Type(gawk 4.0+)

isarray(x): distinguish an array from a scalar variable

$ awk 'BEGIN{a[1]="one"; print isarray(a)}'
1

$ awk 'BEGIN{a="one"; print isarray(a)}'
0