Word frequency: Difference between revisions

<lang zkl>fname,count := vm.arglist; // grab cammand line args

File(fname).pump(Void, // read the file line by line and hash words

"toLower",findAll,Void.Xplode,Dictionary().incV)

.toList().copy().sort(fcn(a,b){ b[1]<a[1] })[0,count.toInt()]

.apply("concat",",").concat("\n").println();

fcn findAll(text){

// \w is [a-zA-Z0-9_] many words (jn Les Misérables)

// have leading or trailing "_", ie "the" and "_the"

var re=RegExp("[a-zA-Z]+"), r=List(); // static variables, not re-entrant

n,sz := 0,0; r.clear();

while(re.search(text,True,n)){ // moving search starting at n

n,sz=re.matched[0];

r.append(text[n,sz]);

n+=sz;

}

r

}</lang>

$ zkl bbb ~/Documents/Les\ Miserables.txt 10

the,41038

of,19908

and,14925

a,14602

to,13946

in,11196

he,9646

was,8613

that,7922

it,6657