Words from neighbour ones: Difference between revisions

From Rosetta Code
Content added Content deleted
(Added Wren)
m (corrected some misspellings, changed wording to ignore (small) words instead of directing that they be deleted from the dictionary, added related tasks..)
Line 3: Line 3:
;Task:
;Task:
Use the dictionary   [https://web.archive.org/web/20180611003215/http://www.puzzlers.org/pub/wordlists/unixdict.txt unixdict.txt]
Use the dictionary   [https://web.archive.org/web/20180611003215/http://www.puzzlers.org/pub/wordlists/unixdict.txt unixdict.txt]

<br> Delete from directory words which lenghts are smaller then 9
Ignore any word in the dictionary whose length is less than 9.
<br>Let's take the words from next characters:

<br>1 <= n < (dictionary lenght) - 9

<br>char1 = 1st character of nth word.
Let's take the words from next characters:
<br>char2 = 2st character of (n+1)th word.
<br>char3 = 3st character of (n+2)th word.
<br>1 <= n < (dictionary length) - 9.
<br>char1 = 1<sup>st</sup> character of n<sup>th</sup> word.
<br>char2 = 2(sup>nd</sup> character of (n+1)<sup>th</sup> word.
<br>char3 = 3<sup>rd</sup> character of (n+2)<sup>th</sup> word.
<br>...
<br>...
<br>char9 = 9st character of (n+8)th word.
<br>char9 = 9<sup>th</sup> character of (n+8)<sup>th</sup> word.

<br>''newword'' = char1+char2+char3+...+char9

<br>If ''newword'' in dictionary then show on this page.
Concatenate (append) the nine characters by:
<br> lenght of ''newword'' = 9
''newword'' = char1 + char2 + char3 + ... + char9
<br>If &nbsp; ''newword'' &nbsp; is in the dictionary, then show on this page.

Length of &nbsp;''newword'' = 9


{{Template:Strings}}
<br><br>


=={{header|C}}==
=={{header|C}}==

Revision as of 20:41, 6 February 2021

Words from neighbour ones 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

Ignore any word in the dictionary whose length is less than 9.


Let's take the words from next characters:
1 <= n < (dictionary length) - 9.
char1 = 1st character of nth word.
char2 = 2(sup>nd character of (n+1)th word.
char3 = 3rd character of (n+2)th word.
...
char9 = 9th character of (n+8)th word.


Concatenate (append) the nine characters by:

      newword = char1 + char2 + char3 + ... + char9 


If   newword   is in the dictionary, then show on this page.

Length of  newword = 9


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



C

<lang c>#include <stdio.h>

  1. include <stdlib.h>
  2. include <string.h>
  1. define MAX_WORD_SIZE 80
  2. define MIN_LENGTH 9
  3. define WORD_SIZE (MIN_LENGTH + 1)

void fatal(const char* message) {

   fprintf(stderr, "%s\n", message);
   exit(1);

}

void* xmalloc(size_t n) {

   void* ptr = malloc(n);
   if (ptr == NULL)
       fatal("Out of memory");
   return ptr;

}

void* xrealloc(void* p, size_t n) {

   void* ptr = realloc(p, n);
   if (ptr == NULL)
       fatal("Out of memory");
   return ptr;

}

int word_compare(const void* p1, const void* p2) {

   return memcmp(p1, p2, WORD_SIZE);

}

int main(int argc, char** argv) {

   const char* filename = argc < 2 ? "unixdict.txt" : argv[1];
   FILE* in = fopen(filename, "r");
   if (!in) {
       perror(filename);
       return EXIT_FAILURE;
   }
   char line[MAX_WORD_SIZE];
   size_t size = 0, capacity = 1024;
   char* words = xmalloc(WORD_SIZE * capacity);
   while (fgets(line, sizeof(line), in)) {
       size_t len = strlen(line) - 1; // last character is newline
       if (len < MIN_LENGTH)
           continue;
       line[len] = '\0';
       if (size == capacity) {
           capacity *= 2;
           words = xrealloc(words, WORD_SIZE * capacity);
       }
       memcpy(&words[size * WORD_SIZE], line, WORD_SIZE);
       ++size;
   }
   fclose(in);
   qsort(words, size, WORD_SIZE, word_compare);
   int count = 0;
   char prev_word[WORD_SIZE] = { 0 };
   for (size_t i = 0; i + MIN_LENGTH <= size; ++i) {
       char word[WORD_SIZE] = { 0 };
       for (size_t j = 0; j < MIN_LENGTH; ++j)
           word[j] = words[(i + j) * WORD_SIZE + j];
       if (word_compare(word, prev_word) == 0)
           continue;
       if (bsearch(word, words, size, WORD_SIZE, word_compare))
           printf("%2d. %s\n", ++count, word);
       memcpy(prev_word, word, WORD_SIZE);
   }
   free(words);
   return EXIT_SUCCESS;

}</lang>

Output:
 1. applicate
 2. architect
 3. astronomy
 4. christine
 5. christoph
 6. committee
 7. composite
 8. constrict
 9. construct
10. different
11. extensive
12. greenwood
13. implement
14. improvise
15. intercept
16. interpret
17. interrupt
18. philosoph
19. prescript
20. receptive
21. telephone
22. transcend
23. transport
24. transpose

C++

<lang cpp>#include <algorithm>

  1. include <cstdlib>
  2. include <fstream>
  3. include <iomanip>
  4. include <iostream>
  5. include <string>
  6. include <vector>

int main(int argc, char** argv) {

   const int min_length = 9;
   const char* filename(argc < 2 ? "unixdict.txt" : argv[1]);
   std::ifstream in(filename);
   if (!in) {
       std::cerr << "Cannot open file '" << filename << "'.\n";
       return EXIT_FAILURE;
   }
   std::string line;
   std::vector<std::string> words;
   while (getline(in, line)) {
       if (line.size() >= min_length)
           words.push_back(line);
   }
   std::sort(words.begin(), words.end());
   std::string previous_word;
   int count = 0;
   for (size_t i = 0, n = words.size(); i + min_length <= n; ++i) {
       std::string word;
       word.reserve(min_length);
       for (size_t j = 0; j < min_length; ++j)
           word += words[i + j][j];
       if (previous_word == word)
           continue;
       auto w = std::lower_bound(words.begin(), words.end(), word);
       if (w != words.end() && *w == word)
           std::cout << std::setw(2) << ++count << ". " << word << '\n';
       previous_word = word;
   }
   return EXIT_SUCCESS;

}</lang>

Output:
 1. applicate
 2. architect
 3. astronomy
 4. christine
 5. christoph
 6. committee
 7. composite
 8. constrict
 9. construct
10. different
11. extensive
12. greenwood
13. implement
14. improvise
15. intercept
16. interpret
17. interrupt
18. philosoph
19. prescript
20. receptive
21. telephone
22. transcend
23. transport
24. transpose

Phix

Oh gosh, this is all rather new and exciting.... <lang Phix>function over9(string word) return length(word)>=9 end function sequence dictionary = filter(split_any(get_text("demo/unixdict.txt")," \r\n"),over9) function slicen(integer n) return vslice(dictionary,n)[n..-10+n] end function sequence neighwords = unique(filter(columnize(apply(tagset(9),slicen)),"in",dictionary)) printf(1,"%d words: %s\n",{length(neighwords),join(shorten(neighwords,"",3))})</lang>

Output:
24 words: applicate architect astronomy ... transcend transport transpose

Raku

<lang perl6>my @words_ge_9 = 'unixdict.txt'.IO.lines.grep( *.chars >= 9 ); my %words_eq_9 = @words_ge_9 .grep( *.chars == 9 ).Set;

my @new_words = gather for @words_ge_9.rotor( 9 => -8 ) -> @nine_words {

   my $new_word = [~] map { @nine_words[$_].substr($_, 1) }, ^9;
   take $new_word if %words_eq_9{$new_word};

}

.say for unique @new_words;</lang>

Output:
applicate
architect
astronomy
christine
christoph
committee
composite
constrict
construct
different
extensive
greenwood
implement
improvise
intercept
interpret
interrupt
philosoph
prescript
receptive
telephone
transcend
transport
transpose

Ring

<lang ring> cStr = read("unixdict.txt") wordList = str2list(cStr) nextwords = [] num = 0

see "working..." + nl

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

   if len(wordList[n]) < 9
      del(wordList,n)
   ok

next

see "New words are:" + nl

for n = 1 to len(wordList)-9

   c1 = substr(wordList[n],1,1)
   c2 = substr(wordList[n+1],2,1)
   c3 = substr(wordList[n+2],3,1)
   c4 = substr(wordList[n+3],4,1)
   c5 = substr(wordList[n+4],5,1)
   c6 = substr(wordList[n+5],6,1)
   c7 = substr(wordList[n+6],7,1)
   c8 = substr(wordList[n+7],8,1)
   c9 = substr(wordList[n+8],9,1)
   str = c1 + c2 + c3 + c4 + c5 + c6 + c7 + c8 + c9 
   ind = find(wordList,str)
   if ind > 0
      add(nextwords,wordList[ind])
   ok

next

nextwords = sort(nextwords) for n = len(nextwords) to 2 step -1

   if nextwords[n] = nextwords[n-1]
      del(nextwords,n)
   ok

next

for n = 1 to len(nextwords)

   see "" + n + ". " + nextwords[n] + nl

next

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

working...
New words are:
1. applicate
2. architect
3. astronomy
4. christine
5. christoph
6. committee
7. composite
8. constrict
9. construct
10. different
11. extensive
12. greenwood
13. implement
14. improvise
15. intercept
16. interpret
17. interrupt
18. philosoph
19. prescript
20. receptive
21. telephone
22. transcend
23. transport
24. transpose
done...

Wren

Library: Wren-sort
Library: Wren-fmt

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

var wordList = "unixdict.txt" // local copy var words = File.read(wordList).trimEnd().split("\n").where { |w| w.count >= 9 }.toList var count = 0 var alreadyFound = [] for (i in 0...words.count - 9) {

   var word = ""
   for (j in i...i+9) word = word + words[j][j-i]
   if (Find.all(words, word)[0] && !Find.all(alreadyFound, word)[0]) {
       count = count + 1
       Fmt.print("$2d: $s", count, word)
       alreadyFound.add(word)
   }

}</lang>

Output:
 1: applicate
 2: architect
 3: astronomy
 4: christine
 5: christoph
 6: committee
 7: composite
 8: constrict
 9: construct
10: different
11: extensive
12: greenwood
13: implement
14: improvise
15: intercept
16: interpret
17: interrupt
18: philosoph
19: prescript
20: receptive
21: telephone
22: transcend
23: transport
24: transpose