test (940B)
1 #!/bin/bash 2 # Check common misspellings 3 # input file format: 4 # word->word1, ... 5 # Source: http://en.wikipedia.org/wiki/Wikipedia:Lists_of_common_misspellings/For_machines 6 7 input=${INPUT:-List_of_common_misspellings.txt} 8 9 function check() { 10 cat $1 | awk 'BEGIN{maxord=0;FS="\t"}FILENAME=="-"{for (i=1; i<=NF; i++){a[NR,$(i)]=i};max=NR;next}{x1=a[NR-max,$2];x2=a[NR-max,$3];sug++;if($3)sug++;if (!x1&&!x2){mis2++;misrow=misrow"\n"$0};if(!x1||($3 && !x2))mis++;ord+=x1+x2;}END{ 11 print "Missed rows", misrow; 12 print "=======================================" 13 print maxord, "max. suggestion for a word"; 14 print max, "input rows"; 15 print mis2, "missing rows"; 16 print sug, "expected suggestions"; 17 print mis, "missing suggestions"; 18 print ord/(sug-mis), "average ranking"; 19 }' - $2 20 } 21 22 test -f $input.4 && check $input.4 $input.3 >result.aspell 23 check $input.5 $input.3 >result.hunspell 24 test -f result.aspell && tail -6 result.aspell 25 tail -6 result.hunspell