Find words which contains more than 3 e vowels: Difference between revisions

From Rosetta Code
Content added Content deleted
(Ada version)
(Added Arturo implementation)
Line 199: Line 199:
16: tennessee (4)
16: tennessee (4)
</pre>
</pre>

=={{header|Arturo}}==

<lang rebol>words: read.lines relative "unixdict.txt"
otherVowels: ["a" "i" "o" "u"]
containsMoreThan3Es?: function [w][
if 4 > size match w "e" -> return false

loop otherVowels 'v [
if contains? w v -> return false
]
return true
]

loop words 'word [
if containsMoreThan3Es? word ->
print word
]</lang>

{{out}}

<pre>belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee</pre>


=={{header|AWK}}==
=={{header|AWK}}==

Revision as of 12:16, 1 June 2021

Find words which contains more than 3 e vowels is a draft programming task. It is not yet considered ready to be promoted as a complete task, for reasons that should be found in its talk page.
Task

Use the dictionary   unixdict.txt

Find words which contains more than three   e   vowels   and   contains only   e   vowels.

Show the output here on this page.


Other tasks related to string operations:
Metrics
Counting
Remove/replace
Anagrams/Derangements/shuffling
Find/Search/Determine
Formatting
Song lyrics/poems/Mad Libs/phrases
Tokenize
Sequences



8080 Assembly

<lang 8080asm>puts: equ 9 ; CP/M syscall to print a string fopen: equ 15 ; Open file fread: equ 20 ; Read block FCB1: equ 5Ch ; File given on command line dma: equ 80h org 100h lxi d,FCB1 ; Try to open file mvi c,fopen call 5 inr a ; A=FF = error jz err lxi h,word ; Word buffer block: push h lxi d,FCB1 ; Read 128-byte block mvi c,fread call 5 pop h ; Restore word buffer pointer lxi d,dma ; Start of block dcr a ; If A=1, we're done rz inr a ; Otherwise, if A<>0, error jnz err char: ldax d ; Get character from block mov m,a ; Copy into word buffer inx h cpi 10 ; End of line? cz line ; Then test this line inr e ; Next character in block jnz char ; If rollover, read next block jmp block line: mvi m,'$' ; CP/M string terminator lxi h,word ; Start at beginning mvi c,0 ; 'E' counter letter: mov a,m ; Get letter from word inx h cpi '$' ; End of string? jz done cpi 'a' ; A / I / O / U = not valid jz no cpi 'i' jz no cpi 'o' jz no cpi 'u' jz no cpi 'e' ; E? jnz letter ; If not, try next letter inr c ; If so, count the E jmp letter done: mvi a,3 ; More than 3 Es? cmp c jnc no ; If not, then don't print push d ; Keep buffer pointer lxi d,word ; Print word mvi c,puts call 5 pop d ; Restore buffer pointer no: lxi h,word ; Start reading at begin of word buffer ret err: lxi d,emsg ; Print error mvi c,puts jmp 5 emsg: db 'Error$' word: equ $</lang>

Output:
A>ewords unixdict.txt
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

Ada

<lang Ada>with Ada.Text_Io; with Ada.Strings.Maps; with Ada.Strings.Fixed;

procedure Find_Three_E is 

  use Ada.Text_Io;
  use Ada.Strings;
  use type Ada.Strings.Maps.Character_Set;

  Filename   : constant String  := "unixdict.txt";
  Y_Is_Vowel : constant Boolean := False;
  Set_E      : constant Maps.Character_Set := Maps.To_Set ("eE");
  Set_Y      : constant Maps.Character_Set := Maps.To_Set ("yY");
  Set_Others : constant Maps.Character_Set :=
    Maps.To_Set ("aiouAIOU") or (if Y_Is_Vowel then Set_Y else Maps.Null_Set);
  File       : File_Type;

begin 

  Open (File, In_File, Filename);
  while not End_Of_File (File) loop
     declare
        Word         : constant String  := Get_Line (File);
        Count_E      : constant Natural := Fixed.Count (Word, Set_E);
        Count_Others : constant Natural := Fixed.Count (Word, Set_Others);
     begin
        if Count_E > 3 and Count_Others = 0 then
           Put_Line (Word);
        end if;
     end;
  end loop;
  Close (File);

end Find_Three_E;</lang>

ALGOL 68

Interesting to note the word with the most es is "dereference" - a term first used (I believe) in Algol 68... <lang algol68># find words that contain more than 3 es and no other vowels #

  1. read the list of words and look for suitable words #

IF FILE input file; 

   STRING file name = "unixdict.txt";
   open( input file, file name, stand in channel ) /= 0

THEN 

   # failed to open the file #
   print( ( "Unable to open """ + file name + """", newline ) )

ELSE 

   # file opened OK #
   BOOL at eof := FALSE;
   # set the EOF handler for the file #
   on logical file end( input file, ( REF FILE f )BOOL:
                                    BEGIN
                                        # note that we reached EOF on the #
                                        # latest read #
                                        at eof := TRUE;
                                        # return TRUE so processing can continue #
                                        TRUE
                                    END
                      );
   INT eeee words := 0;
   WHILE STRING word;
         get( input file, ( word, newline ) );
         NOT at eof
   DO
       INT e count := 0, other vowel count := 0;
       FOR w pos FROM LWB word TO UPB word DO
           CHAR c = word[ w pos ];
           IF   c = "e"
           THEN e count +:= 1
           ELIF c = "a"
             OR c = "i"
             OR c = "o"
             OR c = "u"
           THEN other vowel count +:= 1
           FI
       OD;
       IF e count > 3 AND other vowel count = 0 THEN
          eeee words +:= 1;
          print( ( whole( eeee words, -5 ), ": ", word, "   (", whole( e count, 0 ), ")", newline ) )
       FI
   OD;
   close( input file )

FI</lang>

Output:
    1: belvedere   (4)
    2: dereference   (5)
    3: elsewhere   (4)
    4: erlenmeyer   (4)
    5: evergreen   (4)
    6: everywhere   (4)
    7: exegete   (4)
    8: freewheel   (4)
    9: nevertheless   (4)
   10: persevere   (4)
   11: preference   (4)
   12: referee   (4)
   13: seventeen   (4)
   14: seventeenth   (4)
   15: telemeter   (4)
   16: tennessee   (4)

Arturo

<lang rebol>words: read.lines relative "unixdict.txt" otherVowels: ["a" "i" "o" "u"] containsMoreThan3Es?: function [w][ 

   if 4 > size match w "e" -> return false

   loop otherVowels 'v [
       if contains? w v -> return false
   ]
   return true

]

loop words 'word [ 

   if containsMoreThan3Es? word ->
       print word

]</lang>

Output:
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

AWK

<lang AWK>/e.*e.*e.*e/ && !/a|i|o|u/ {print}</lang>

Output:
$ awk -f ewords.awk unixdict.txt
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

C

<lang c>#include <stdio.h>

  1. define SIZE 256

int check(char *word) { 

   int e = 0, ok = 1;
   for(; *word && ok; word++) {
       switch(*word) {
           case 'a':
           case 'i':
           case 'o':
           case 'u': ok = 0; break;
           case 'e': e++;
       }
   }
   
   return ok && e > 3;

}

int main() { 

   FILE *f;
   char line[SIZE];
   
   if (!(f = fopen("unixdict.txt", "r"))) {
       fprintf(stderr, "Cannot open unixdict.txt\n");
       return 1;
   }
   
   while (!feof(f)) {
       fgets(line, SIZE, f);
       if (check(line)) printf("%s", line);
   }
   
   fclose(f);
   return 0;

}</lang>

Output:
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

C++

<lang cpp>#include <iostream>

  1. include <fstream>

bool test(const std::string &line) { 

   unsigned int e = 0;
   for (char c : line) {
       switch(std::tolower(c)) {
           case 'a': return false;
           case 'i': return false;
           case 'o': return false;
           case 'u': return false;
           case 'e': ++e;
       }
   }
   return e > 3;

}

int main() { 

   std::ifstream dict{"unixdict.txt"};
   
   if (! dict.is_open()) {
       std::cerr << "Cannot open unixdict.txt\n";
       return 3;
   }
   
   for (std::string line; std::getline(dict, line);) {
       if (test(line)) std::cout << line << std::endl;
   }
   
   return 0;

}</lang>

Output:
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

Cowgol

<lang cowgol>include "cowgol.coh"; include "file.coh";

interface LineCb(line: [uint8]); sub ForEachLine(file: [FCB], cb: LineCb) is 

   var buf: uint8[256];
   var ptr := &buf[0];
   
   var length := FCBExt(file);
   while length != 0 loop
       var ch := FCBGetChar(file);
       [ptr] := ch;
       ptr := @next ptr;
       if ch == '\n' then
           [ptr] := 0;
           ptr := &buf[0];
           cb(&buf[0]);
       end if;
       length := length - 1;
   end loop;

end sub;

sub CheckWord implements LineCb is 

   var ch := line; 
   var e: uint8 := 0;
   loop
       case [ch] is
           when 0: break;
           when 'a': return;
           when 'i': return;
           when 'o': return;
           when 'u': return;
           when 'e': e := e + 1;
       end case;
       ch := @next ch;
   end loop;
   
   if e > 3 then
       print(line);
   end if;

end sub;

var file: FCB; if FCBOpenIn(&file, "unixdict.txt") != 0 then 

   print("Cannot open unixdict.txt\n");
   ExitWithError();

end if;

ForEachLine(&file, CheckWord);</lang>

Output:
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

F#

<lang fsharp> // Words contains more than 3 e vowels. Nigel Galloway: February 11th., 2021. let fN g=let n=Map.ofSeq (Seq.countBy id g) in let fN g=not(n.ContainsKey g) in fN 'a' && fN 'i' && fN 'o' && fN 'u' && not(fN 'e') && n.['e']>3 seq{use n=System.IO.File.OpenText("unixdict.txt") in while not n.EndOfStream do yield n.ReadLine()}|>Seq.filter fN|>Seq.iter(printfn "%s") </lang>

Output:
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

Factor

<lang factor>USING: formatting io io.encodings.ascii io.files kernel math sequences ;

"unixdict.txt" ascii file-lines [ [ "aiou" member? ] any? ] reject [ [ CHAR: e = ] count 3 > ] filter [ 1 + "%2d: " printf print ] each-index</lang>

Output:
 1: belvedere
 2: dereference
 3: elsewhere
 4: erlenmeyer
 5: evergreen
 6: everywhere
 7: exegete
 8: freewheel
 9: nevertheless
10: persevere
11: preference
12: referee
13: seventeen
14: seventeenth
15: telemeter
16: tennessee

Forth

Works with: Gforth

<lang forth>: e3 ( addr u -- ? ) 

 0 { ecount }
 0 do
   dup c@ case
     'a' of false endof
     'e' of ecount 1+ to ecount true endof
     'i' of false endof
     'o' of false endof
     'u' of false endof
     true swap
   endcase
   invert if unloop drop false exit then
   1+
 loop
 drop
 ecount 3 > ;

256 constant max-line

main
 0 0 { count fd-in }
 s" unixdict.txt" r/o open-file throw to fd-in
 begin
   here max-line fd-in read-line throw
 while
   here swap 2dup e3 if
     count 1+ to count
     count 2 .r ." . " type cr
   else
     2drop
   then
 repeat
 drop
 fd-in close-file throw ;

main bye</lang>

Output:
 1. belvedere
 2. dereference
 3. elsewhere
 4. erlenmeyer
 5. evergreen
 6. everywhere
 7. exegete
 8. freewheel
 9. nevertheless
10. persevere
11. preference
12. referee
13. seventeen
14. seventeenth
15. telemeter
16. tennessee

Go

<lang go>package main

import ( 

   "bytes"
   "fmt"
   "io/ioutil"
   "log"
   "strings"
   "unicode/utf8"

)

func main() { 

   wordList := "unixdict.txt"
   b, err := ioutil.ReadFile(wordList)
   if err != nil {
       log.Fatal("Error reading file")
   }
   bwords := bytes.Fields(b)
   var words []string

outer: 

   for _, bword := range bwords {
       s := string(bword)
       if utf8.RuneCountInString(s) >= 4 {
           for _, c := range s {
               if strings.ContainsRune("aiou", c) {
                   continue outer
               }
           }
           words = append(words, s)
       }
   }
   wcount := 0
   for _, word := range words {
       ecount := 0
       for _, c := range word {
           if c == 'e' {
               ecount++
           }
       }
       if ecount > 3 {
           wcount++
           fmt.Printf("%2d: %s\n", wcount, word)
       }
   }

}</lang>

Output:
 1: belvedere
 2: dereference
 3: elsewhere
 4: erlenmeyer
 5: evergreen
 6: everywhere
 7: exegete
 8: freewheel
 9: nevertheless
10: persevere
11: preference
12: referee
13: seventeen
14: seventeenth
15: telemeter
16: tennessee

Haskell

<lang haskell>import System.IO

main = withFile "unixdict.txt" ReadMode $ \h -> do 

   words <- fmap lines $ hGetContents h
   putStrLn $ unlines $ filter valid words

valid w = not (any (`elem` "aiou") w) && length (filter (=='e') w) > 3</lang>

Output:
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

Julia

See Alternade_words#Julia for the foreachword function. <lang julia>ecount(word) = count(x -> x == 'e', word) vowelcount(word) = count(x -> x in ['a', 'e', 'i', 'o', 'u'], word) onlyevowelsmorethan3(word, _) = begin n, m = vowelcount(word), ecount(word); n == m && m > 3 ? word : "" end

foreachword("unixdict.txt", onlyevowelsmorethan3, colwidth=15, numcols=8)

</lang>

Output:
belvedere      dereference    elsewhere      erlenmeyer     evergreen      everywhere     exegete        freewheel      
nevertheless   persevere      preference     referee        seventeen      seventeenth    telemeter      tennessee

Pascal

Works with: Turbo Pascal

<lang pascal>program EWords; var 

  FileVar: Text;
  Line: string[255];
  I: Integer;
  E: Integer;
  OK: Boolean;

begin 

  Assign(FileVar, 'unixdict.txt');
  Reset(FileVar);

  while not Eof(FileVar) do
  begin
     ReadLn(FileVar, Line);
     E := 0;
     OK := True;
     for I := 1 to Length(Line) do
     begin
        OK := OK and (Pos(Line[I], 'aiou') = 0);
        if Line[I] = 'e' then E := E + 1
     end;
     if OK and (E > 3) then
     begin
        Write(Line);
        WriteLn;
     end
  end

end.</lang>

Output:
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

Perl

<lang perl>#!/usr/bin/perl

use strict; # https://rosettacode.org/wiki/Find_words_which_contains_more_than_3_e_vowels use warnings;

@ARGV = 'unixdict.txt'; tr/e// > 3 and tr/aiou// == 0 and print while <>;</lang>

Output:

belvedere dereference elsewhere erlenmeyer evergreen everywhere exegete freewheel nevertheless persevere preference referee seventeen seventeenth telemeter tennessee

Phix

function note(string word) return find_any("aiou",word)=0 and length(find_all('e',word))>3 end function
sequence notes = filter(get_text("demo/unixdict.txt",GT_LF_STRIPPED),note)
printf(1,"%d words: %s\n",{length(notes),join(shorten(notes,"",3))})
Output:
16 words: belvedere dereference elsewhere ... seventeenth telemeter tennessee

Python

<lang python>with open('unixdict.txt', 'rt') as f: 

   for line in f.readlines():
       if not any(c in 'aiou' for c in line) and sum(c=='e' for c in line)>3:
           print(line.strip())</lang>
Output:
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

Raku

Hardly even worth saving as a script file; an easily entered one-liner. <lang perl6>.say for "unixdict.txt".IO.lines.grep: { !/<[aiou]>/ and /e.*e.*e.*e/ };</lang>

Output:
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

In an attempt to be a little less useless, here's an alternate script that allows you to specify a vowel, the minimum count to search for, and the file to search. Counts base vowels case, and combining accent insensitive; works with any text file, not just word lists. Defaults to finding words with at least 4 'e's in unixdict.txt. Default output is same as above.

<lang perl6>unit sub MAIN ($vowel = 'e', $min = 4, $file = 'unixdict.txt'); .say for squish sort 

 ( $file.IO.slurp.words.grep: { ((my $b = .lc.samemark(' ').comb.Bag){$vowel} >= $min) && $b<a e i o u>.sum == $b{$vowel} } )\
 ».subst(/<[":;,.?!_\[\]]>/, , :g);</lang>

How about: find words with at least 4 'a's in the Les Misérables file used for the Word frequency task?

Command line > raku monovowel a 4 lemiz.txt

Output:
Caracalla
Caracara
Salamanca
Vâsaphantâ

REXX

This REXX version doesn't care what order the words in the dictionary are in,   nor does it care what
case  (lower/upper/mixed)  the words are in,   the search for the words and vowels is   caseless.

It also allows the vowel to be specified,   and also the minimum number of the specific vowels to be specified on the command line (CL) as well as the dictionary file identifier. <lang rexx>/*REXX pgm finds words (within an identified dict.) which contain more than three "e"s.*/ parse arg char many iFID . /*obtain optional arguments from the CL*/ if char== | char=="," then char= 'e' /*Not specified? Then use the default.*/ if many== | many=="," then many= 4 /* " " " " " " */ if iFID== | iFID=="," then iFID='unixdict.txt' /* " " " " " " */ chrU= char; upper chrU /*obtain an uppercase version of char.*/ 

          do #=1  while lines(iFID)\==0         /*read each word in the file  (word=X).*/
          x= strip( linein( iFID) )             /*pick off a word from the input line. */
          @.#= x                                /*save:  the original case of the word.*/
          end   /*#*/
  1. = # - 1 /*adjust word count because of DO loop.*/

say copies('─', 30) # "words in the dictionary file: " iFID finds= 0 /*count of the "eeee" words found. */ vowels= 'aeiou' /*obtain the list of all the vowels. */ upper vowels /*uppercase all the other vowels. */ vowels= space( translate(vowels, , chrU), 0) /*elide the one vowel we're looking for*/ 

                                                /*process all the words that were found*/
    do j=1  for #;    $= @.j;         upper $   /*obtain word from dict.; uppercase it.*/
    if verify(vowels, $, 'M')>0  then iterate   /*Does it contain other vowels? Skip it*/
    if countstr(chrU, $) < many  then iterate   /*  "   " have enough of  'e's?   "   "*/
    finds= finds + 1                            /*bump count of only "e" vowels found. */
    say right( left(@.j, 30),  40)              /*indent original word for readability.*/
    end        /*j*/
                                                /*stick a fork in it,  we're all done. */

say copies('─', 30) finds " words found having " many ' ' copies(char, many) " letters."</lang>

output   when using the default inputs:
────────────────────────────── 25104 words in the dictionary file:  unixdict.txt
          belvedere
          dereference
          elsewhere
          erlenmeyer
          evergreen
          everywhere
          exegete
          freewheel
          nevertheless
          persevere
          preference
          referee
          seventeen
          seventeenth
          telemeter
          tennessee
────────────────────────────── 16  words found having  4   eeee  letters.

Ring

<lang ring> load "stdlib.ring"

cStr = read("unixdict.txt") wordList = str2list(cStr) char = list(9) nextwords = [] nr = 0 num = 0

see "working..." + nl

ln = len(wordList) for n = ln to 1 step -1 

   if len(wordList[n]) < 6
      del(wordList,n)
   ok

next

see "Words are:" + nl

for n = 1 to len(wordList) 

   num = 0
   flag = 1
   for m = 1 to len(wordList[n])
       if isvowel(wordList[n][m])
          if wordList[n][m] != "e"
             flag = 0
             exit
          else
             num = num + 1
          ok
       ok
   next
   if flag = 1 and num > 3
      nr = nr + 1
      see "" + nr + ". " + wordList[n] + nl
   ok

next

see "done..." + nl </lang> Output: 

working...
Words are:
1. belvedere
2. dereference
3. elsewhere
4. erlenmeyer
5. evergreen
6. everywhere
7. exegete
8. freewheel
9. nevertheless
10. persevere
11. preference
12. referee
13. seventeen
14. seventeenth
15. telemeter
16. tennessee
done...

Snobol

<lang snobol> input(.words, 1,, 'unixdict.txt') :s(line) 

       output = 'Error!'                   :(end)

line word = words :f(end) 

       word 'a' | 'i' | 'o' | 'u'          :s(line)
       word 'e' arb 'e' arb 'e' arb 'e'    :f(line)
       output = word                       :(line)

end</lang>

Output:
belvedere
dereference
elsewhere
erlenmeyer
evergreen
everywhere
exegete
freewheel
nevertheless
persevere
preference
referee
seventeen
seventeenth
telemeter
tennessee

Swift

<lang swift>import Foundation

func e3(_ word: String) -> Bool { 

   var ecount = 0
   for ch in word {
       switch (ch) {
       case "a", "A", "i", "I", "o", "O", "u", "U":
           return false
       case "e", "E":
           ecount += 1
       default:
           break
       }
   }
   return ecount > 3

}

do { 

   try String(contentsOfFile: "unixdict.txt", encoding: String.Encoding.ascii)
       .components(separatedBy: "\n")
       .filter{e3($0)}
       .enumerated()
       .forEach{print(String(format: "%2d. %@", $0.0 + 1, $0.1))}

} catch { 

   print(error.localizedDescription)

}</lang>

Output:
 1. belvedere
 2. dereference
 3. elsewhere
 4. erlenmeyer
 5. evergreen
 6. everywhere
 7. exegete
 8. freewheel
 9. nevertheless
10. persevere
11. preference
12. referee
13. seventeen
14. seventeenth
15. telemeter
16. tennessee

Wren

Library: Wren-fmt

<lang ecmascript>import "io" for File import "/fmt" for Fmt

var hasAIOU = Fn.new { |word| word.any { |c| "aiou".contains(c) } } var wordList = "unixdict.txt" // local copy var words = File.read(wordList).trimEnd().split("\n").where { |w| w.count >= 4 && !hasAIOU.call(w) }.toList var count = 0 for (word in words) { 

   if (word.count { |c| c == "e" } > 3) {
       count = count + 1
       Fmt.print("$2d: $s", count, word)
   }

}</lang>

Output:
 1: belvedere
 2: dereference
 3: elsewhere
 4: erlenmeyer
 5: evergreen
 6: everywhere
 7: exegete
 8: freewheel
 9: nevertheless
10: persevere
11: preference
12: referee
13: seventeen
14: seventeenth
15: telemeter
16: tennessee
Retrieved from "https://rosettacode.org/wiki/Find_words_which_contains_more_than_3_e_vowels?oldid=307757"