Find words which contains more than 3 e vowels

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

• String length
• Empty string  (assignment)

Counting

• Word frequency
• Letter frequency
• Jewels and stones
• I before E except after C
• Bioinformatics/base count
• Count occurrences of a substring

Remove/replace

• XXXX redacted
• Remove vowels from a string
• Strip block comments
• Strip comments from a string
• Strip a set of characters from a string
• Strip whitespace from a string -- top and tail
• Strip control codes and extended characters from a string

Anagrams/Derangements/shuffling

• Word wheel
• ABC problem
• Anagrams
• Anagrams/Deranged anagrams
• Permutations/Derangements
• Superpermutation minimisation
• Sattolo cycle
• Knuth shuffle
• Ordered words
• Textonyms (using a phone text pad)

Find/Search/Determine

• ABC words
• Odd words
• Semordnilap
• String matching
• Alternade words
• Changeable words
• String comparison
• Extract file extension
• Levenshtein distance
• Palindrome detection
• Compare a list of strings
• Longest common prefix
• Longest common suffix
• Longest common substring
• Find common directory path
• Words from neighbour ones
• Change e letters to i in words
• Non-continuous subsequences
• Longest common subsequence
• Longest palindromic substrings
• Longest increasing subsequence
• Words containing "the" substring
• Determine if a string is numeric
• Determine if a string is collapsible
• Determine if a string is squeezable
• Determine if a string has all unique characters
• Determine if a string has all the same characters
• Find words which contains all the vowels
• Find words which contains most consonants
• Find words which contains more than 3 vowels
• Find words which first and last three letters are equals
• Find words which odd letters are consonants and even letters are vowels or vice_versa

Formatting

• String case
• Align columns
• Literals/String
• Repeat a string
• Brace expansion
• Brace expansion using ranges
• Reverse a string
• Phrase reversals
• Comma quibbling
• Special characters
• String concatenation
• Substring/Top and tail
• Commatizing numbers
• Reverse words in a string
• Suffixation of decimal numbers
• Long literals, with continuations
• Numerical and alphabetical suffixes
• Abbreviations, easy
• Abbreviations, simple
• Abbreviations, automatic

Song lyrics/poems/Mad Libs/phrases

• 99 Bottles of Beer
• The Twelve Days of Christmas
• The Old lady swallowed a fly
• The Name Game (a song)
• Magic 8-ball
• Mad Libs

Tokenize

• Word break problem
• Tokenize a string
• Tokenize a string with escaping
• Split a character string based on change of character

Sequences

• Show ASCII table
• De Bruijn sequences
• Self-referential sequences
• Generate lower case ASCII alphabet

8080 Assembly

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	$

Output:

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

ALGOL 68

Interesting to note the word with the most es is "dereference" - a term first used (I believe) in Algol 68...

# find words that contain more than 3 es and no other vowels         #
 
# 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

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)

AWK

/e.*e.*e.*e/ && !/a|i|o|u/ {print}

Output:

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

C

#include <stdio.h>
#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;
}

Output:

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

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);

Output:

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

F#

 
// 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")
 

Output:

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

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

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

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)
        }
    }
}

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

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

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.

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)
 

Output:

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

Pascal

Works with: Turbo 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.

Output:

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

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 <>;

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

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())

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.

.say for "unixdict.txt".IO.lines.grep: { !/<[aiou]>/ and /e.*e.*e.*e/ };

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.

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);

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.

/*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                                         /*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."

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

 
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
 

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

        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

Output:

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

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)
}

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

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)
    }
}

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