I'm working on modernizing Rosetta Code's infrastructure. Starting with communications. Please accept this time-limited open invite to RC's Slack.. --Michael Mol (talk) 20:59, 30 May 2020 (UTC)

Words from neighbour ones

From Rosetta Code
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 = 2nd 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



11l[edit]

Translation of: Python
V wordList = File(‘unixdict.txt’).read().split("\n")
 
V filteredWords = wordList.filter(chosenWord -> chosenWord.len >= 9)
 
L(word) filteredWords[0 .< (len)-9]
   V position = filteredWords.index(word)
   V newWord = (0..8).map(i -> :filteredWords[@position + i][i]).join(‘’)
   I newWord C filteredWords
      print(newWord)
Output:
applicate
architect
astronomy
christine
christoph
committee
committee
committee
committee
committee
composite
constrict
constrict
construct
different
extensive
greenwood
implement
improvise
intercept
interpret
interrupt
interrupt
philosoph
prescript
receptive
telephone
transcend
transcend
transport
transpose

AppleScript[edit]

Core language[edit]

on task()
    -- Since the task specifically involves unixdict.txt, this code's written in
    -- the knowlege that the words are on individual lines and in dictionary order.
    set dictPath to (path to desktop as text) & "unixdict.txt"
    script o
        property wordList : paragraphs of (read file dictPath as «class utf8»)
        property matches : {}
    end script
    -- Zap words with fewer than 9 characters and work with what's left.
    repeat with i from 1 to (count o's wordList)
        if ((count item i of o's wordList) < 9) then set item i of o's wordList to missing value
    end repeat
    set o's wordList to o's wordList's every text
    set wordListCount to (count o's wordList)
    set previousNewWord to missing value
    repeat with i from 1 to (wordListCount - 8)
        set newWord to character 1 of item i of o's wordList
        set j to (i - 1)
        repeat with k from 2 to 9
            set newWord to newWord & character k of item (j + k) of o's wordList
        end repeat
        -- Since wordList's known to be in dictionary order, a lot of time can be saved
        -- by only checking the necessary few words ahead for a match instead of
        -- using AppleScript's 'is in' or 'contains' commands, which check the entire list.
        if (newWord is not previousNewWord) then
            repeat with j from i to wordListCount
                set thisWord to item j of o's wordList
                if (newWord comes after thisWord) then
                else
                    if (newWord is thisWord) then set end of o's matches to newWord
                    exit repeat
                end if
            end repeat
            set previousNewWord to newWord
        end if
    end repeat
 
    return o's matches
end task
 
task()
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"}

AppleScriptObjC[edit]

Same output as above. 

use AppleScript version "2.4" -- OS X 10.10 (Yosemite) or later
use framework "Foundation"
use scripting additions
 
on task()
    set |⌘| to current application
    set dictPath to (POSIX path of (path to desktop)) & "unixdict.txt"
    set dictText to |⌘|'s class "NSString"'s stringWithContentsOfFile:(dictPath) ¬
        usedEncoding:(missing value) |error|:(missing value)
    set newlineSet to |⌘|'s class "NSCharacterSet"'s newlineCharacterSet()
    set wordArray to dictText's componentsSeparatedByCharactersInSet:(newlineSet)
    -- Lose words with fewer than 9 characters.
    set filter to |⌘|'s class "NSPredicate"'s predicateWithFormat:("self MATCHES '.{9,}+'")
    set relevantWords to wordArray's filteredArrayUsingPredicate:(filter)
 
    -- Creating the new words is most easily and efficiently done with core AppleScript.
    script o
        property wordList : relevantWords as list
        property newWords : {}
    end script
    repeat with i from 1 to ((count o's wordList) - 8)
        set newWord to character 1 of item i of o's wordList
        set j to (i - 1)
        repeat with k from 2 to 9
            set newWord to newWord & character k of item (j + k) of o's wordList
        end repeat
        set end of o's newWords to newWord
    end repeat
 
    -- But Foundation sets are good for filtering the results.
    set matches to |⌘|'s class "NSMutableOrderedSet"'s orderedSetWithArray:(o's newWords)
    tell matches to intersectSet:(|⌘|'s class "NSSet"'s setWithArray:(relevantWords))
 
    return (matches's array()) as list
end task
 
task()

AutoHotkey[edit]

FileRead, wList, % A_Desktop "\unixdict.txt"
for word in neighbour(wList)
    result .= word (Mod(A_Index, 6) ? "`t" : "`n")
MsgBox, 262144, , % result
return
 
neighbour(wList){
    words := [], wordExist := [], oRes := []
    for i, w in StrSplit(wList, "`n", "`r")
    {
        if (StrLen(w) < 9)
            continue
        words.Push(w)
        wordExist[w] := true
    }
    loop % words.Count()-9
    {
        n := A_Index
        newword := ""
        loop 9
            newword .= SubStr(words[n+A_Index-1], A_Index, 1)
        if wordExist[newword]
            oRes[newword] := true
    }
    return oRes
}
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

AWK[edit]

 
# syntax: GAWK -f WORDS_FROM_NEIGHBOUR_ONES.AWK unixdict.txt
{   if (length($0) < 9) { next }
    arr1[++n] = $0
    arr2[$0] = ""
}
END {
    for (i=1; i<=n; i++) {
      word = substr(arr1[i],1,1)
      for (j=2; j<=9; j++) {
        if (!((i+j) in arr1)) { continue }
        word = word substr(arr1[i+j],j,1)
      }
      if (word in arr2) {
        printf("%s\n",word)
        delete arr2[word] # eliminate duplicates
      }
    }
    exit(0)
}
 
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

C[edit]

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
 
#define MAX_WORD_SIZE 80
#define MIN_LENGTH 9
#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;
}
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++[edit]

#include <algorithm>
#include <cstdlib>
#include <fstream>
#include <iomanip>
#include <iostream>
#include <string>
#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;
}
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

Delphi[edit]

Library: System.SysUtils
Library: System.Classes
Translation of: Java
 
program Words_from_neighbour_ones;
 
{$APPTYPE CONSOLE}
 
uses
  System.SysUtils,
  System.Classes;
 
function GetWords(minLength: Integer = 1): TStringList;
var
  i: Integer;
begin
  Result := TStringList.create;
  Result.LoadFromFile('Unixdict.txt');
  with Result do
    for i := Count - 1 downto 0 do
      if Strings[i].Length < minLength then
        Delete(i);
  Result.Sort;
end;
 
var
  Words: TStringList;
 
const
  minLength = 9;
 
begin
  Words := GetWords(minLength);
  var previousWord := '';
  var count := 0;
  var n := Words.Count;
 
  for var i := 0 to n - minLength do
  begin
 
    var W := '';
    for var j := 0 to minLength - 1 do
      W := W + Words[i + j][j + 1];
    if W.Equals(previousWord) then
      Continue;
    if Words.IndexOf(W) >= 0 then
    begin
      inc(count);
      writeln(count: 2, '. ', W);
    end;
    previousWord := W;
  end;
 
  Words.Free;
  readln;
end.
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

F#[edit]

 
// Words from neighbour ones. Nigel Galloway: February 11th., 2021.
let g=[|use n=System.IO.File.OpenText("unixdict.txt") in while not n.EndOfStream do yield n.ReadLine()|]|>Array.filter(fun n->n.Length>8)
g|>Array.windowed 9|>Array.map(fun n->n|>Array.mapi(fun n g->g.[n])|>System.String)|>Array.filter(fun n-> Array.contains n g)|>Array.distinct|>Array.iter(printfn "%s")
 
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

Factor[edit]

{ "abc" "def" "ghi" } 2 clump produces { { "abc" "def" } { "def" "ghi" } }. <clumps> is the same idea except it doesn't actually store all that redundant information in memory; it's a generator that generates clumps on demand. Notice that clumps are matrices, so we can take their diagonal with main-diagonal.

Works with: Factor version 0.99 2020-08-14
USING: formatting grouping hash-sets io.encodings.ascii io.files
kernel literals math math.matrices sequences sequences.extras
sets strings ;
 
<< CONSTANT: words $[ "unixdict.txt" ascii file-lines ] >>
 
CONSTANT: wordset $[ words >hash-set ]
 
words                                       ! place word list on data stack
[ length 9 < ] reject                       ! remove small words from list
9 <clumps>                                  ! create virtual sequence of every 9 adjacent words (overlapping)
[ main-diagonal >string ]                   ! map clump to its diagonal
[ wordset in? ] map-filter                  ! filter diagonals that are words
members                                     ! remove duplicates
[ 1 + swap "%2d. %s\n" printf ] each-index  ! print words formatted nicely
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


FreeBASIC[edit]

Translation of: Ring
 
Open "unixdict.txt" For Input As #1
Dim As String cStr, wordList()
Dim As Integer n, p = 0, posic = 0
Do While Not Eof(1)
    Line Input #1, cStr
    p += 1
    If Len(cStr) > 8 Then
        posic += 1
        Redim Preserve wordList(posic)
        wordList(posic) = cStr
    End If
Loop
Close #1
 
Print p; " palabras en el archivo de diccionario: unixdict.txt"
Print Ubound(wordList); " palabras utilizables en el archivo del diccionario."
 
Dim As String char(1 To 9), palabra
Dim As String nextwords(Ubound(wordList))
 
Print !"\ntrabajando...\n"
Print !"Las nuevas palabras son:\n"
 
posic = 0
For n = 1 To Ubound(wordList)-8
    palabra = ""
    For p = 1 To 9
        char(p) = Mid(wordList(n+p-1),p,1)
        palabra += char(p)
    Next p
 
    For p = 1 To Ubound(wordList)
        If wordList(p) = palabra Then
            posic += 1
            nextwords(posic) = palabra
        End If
    Next p
Next n
 
posic = 0
For n = 2 To Ubound(nextwords)
    If nextwords(n) <> nextwords(n-1) Then
        posic += 1
        Print ""; posic; ". "; nextwords(n-1)
    End If
Next n
 
Print !"\nterminado..."
Sleep
 
Output:
 25104 palabras en el archivo de diccionario: unixdict.txt
 7250 palabras utilizables en el archivo del diccionario.

trabajando...

Las nuevas palabras son:

 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

terminado...


Go[edit]

package main
 
import (
    "bytes"
    "fmt"
    "io/ioutil"
    "log"
    "sort"
    "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
    for _, bword := range bwords {
        s := string(bword)
        if utf8.RuneCountInString(s) >= 9 {
            words = append(words, s)
        }
    }
    count := 0
    var alreadyFound []string
    le := len(words)
    var sb strings.Builder
    for i := 0; i < le-9; i++ {
        sb.Reset()
        for j := i; j < i+9; j++ {
            sb.WriteByte(words[j][j-i])
        }
        word := sb.String()
        ix := sort.SearchStrings(words, word)
        if ix < le && word == words[ix] {
            ix2 := sort.SearchStrings(alreadyFound, word)
            if ix2 == len(alreadyFound) {
                count++
                fmt.Printf("%2d: %s\n", count, word)
                alreadyFound = append(alreadyFound, word)
            }
        }
    }
}
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

Java[edit]

import java.io.*;
import java.util.*;
 
public class NeighbourWords {
    public static void main(String[] args) {
        try {
            int minLength = 9;
            List<String> words = new ArrayList<>();
            try (BufferedReader reader = new BufferedReader(new FileReader("unixdict.txt"))) {
                String line;
                while ((line = reader.readLine()) != null) {
                    if (line.length() >= minLength)
                        words.add(line);
                }
            }
            Collections.sort(words);
            String previousWord = null;
            int count = 0;
            for (int i = 0, n = words.size(); i + minLength <= n; ++i) {
                StringBuilder sb = new StringBuilder(minLength);
                for (int j = 0; j < minLength; ++j)
                    sb.append(words.get(i + j).charAt(j));
                String word = sb.toString();
                if (word.equals(previousWord))
                    continue;
                if (Collections.binarySearch(words, word) >= 0)
                    System.out.printf("%2d. %s\n", ++count, word);
                previousWord = word;
            }
        } catch (Exception e)  {
            e.printStackTrace();
        }
    }
}
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

JavaScript[edit]

 
document.write(`
  <p>Choose dictionary: <input id="dict" type="file"></p>
  <p>Word length: <input id="wlen" type="number" value="9"</p>
  <div id="out"></div>
`);
 
function go(dict) {
  let wordLen = parseInt(document.getElementById('wlen').value),
      result = [];
  dict = dict.replace(/\n|\r/g, '_');
  dict = dict.replace(/__/g, ' ').split(' ');
  dict = dict.filter(e => e.length >= wordLen);
  for (let i = 0; i < dict.length - wordLen; i++) {
    let word = dict[i][0];
    for (let j = 1; j < wordLen; j++) {
      word += dict[i+j][j];
    }
    if (dict.includes(word) && !result.includes(word)) result.push(word);
  }
  document.getElementById('out').innerText = result.join(', ');
}
 
document.getElementById('dict').onchange = function() {
  let f = document.getElementById('dict').files[0],
      fr = new FileReader();
  fr.onload = function() { go(fr.result) }
  fr.readAsText(f);
}
 
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

jq[edit]

For speed, this solution constructs a JSON object as a dictionary ($hash):
 
# input: the dictionary
# $n: starting point (starting at 0)
def form_word($n):
   . as $dict
   | reduce range(0;9) as $i (""; . + $dict[$n+$i][$i: $i+1] );
 
[inputs | select(length >= 9)]
| . as $dict
| (reduce.[] as $x ({}; .[$x]=true)) as $hash
| range(0; length-9) as $i | form_word($i) | select($hash[.])
Output:
["applicate","architect","astronomy","christine","christoph","committee","committee","committee","committee","committee","composite","constrict","constrict","construct","different","extensive","greenwood","implement","improvise","intercept","interpret","interrupt","interrupt","philosoph","prescript","receptive","telephone","transcend","transcend","transport","transpose"]

Removing duplicates efficiently[edit]

Using `def form_word`, we have only to modify the last line above: 

[inputs | select(length >= 9)]
| . as $dict
| (reduce.[] as $x ({}; .[$x]=true)) as $hash
| reduce range(0; length-9) as $i ({$hash};
       ($dict | form_word($i)) as $w
       | if .hash[$w] then .hash[$w] = null | .words += [$w] else . end)
| .words

Julia[edit]

function wordsfromneighbourones(wordfile::String, len = 9, colwidth = 11, numcols = 8)
    println("Word source: $wordfile\n")
    words = filter(w -> length(w) >= len, split(read(wordfile, String), r"\s+"))
    dict, shown, found = Dict(w => 1 for w in words), 0, String[]
    for position in eachindex(@view words[1:end-len+1])
        new_word = prod([words[i + position - 1][i] for i in 1:len])
        if haskey(dict, new_word) && !(new_word in found)
            push!(found, new_word)
            print(rpad(new_word, colwidth), (shown += 1) % numcols == 0 ? "\n" : "")
        end
    end
end
 
wordsfromneighbourones("unixdict.txt")
 
Output:
Word source: unixdict.txt

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

Ksh[edit]

 
#!/bin/ksh
 
# Words from neighbour ones
 
#	# Variables:
#
dict='/home/ostrande/prj/roscode/unixdict.txt'
integer MIN_WORD_LEN=9 TRUE=1 FALSE=0
 
typeset -a word newword
integer i j=0
 
#	# Functions:
#
#	# Function _buildword(arr) - build MIN_WORD_LEN word from arr eles
#
function _buildword {
	typeset _arr ; nameref _arr="$1"
	typeset _indx ; integer _indx=$2
	typeset _i _str ; integer _i
 
	for ((_i=0; _i<MIN_WORD_LEN; _i++)); do
		_str+=${_arr[$((_indx+_i))]:${_i}:1}
	done
	echo "${_str}"
}
 
#	# Function _isword(word, wordlist) - return 1 if word in wordlist
#
function _isword {
	typeset _word ; _word="$1"
	typeset _wordlist ; nameref _wordlist="$2"
 
	[[ ${_word} == @(${_wordlist}) ]] && return $TRUE
	return $FALSE
}
 
 ######
# main #
 ######
 
while read; do
	(( ${#REPLY} >= MIN_WORD_LEN )) && word+=( $REPLY )
done < ${dict}
oldIFS="$IFS" ; IFS='|' ; words=${word[*]} ; IFS="${oldIFS}"
 
for ((i=0; i<${#word[*]}; i++)); do
	candidate=$(_buildword word ${i})
	_isword "${candidate}" words 
	if (( $? )); then
		if [[ ${candidate} != @(${uniq%\|*}) ]]; then
			print $((++j)) ${candidate}
			uniq+="${candidate}|"
		fi
	fi
done
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

Lua[edit]

wordlist, wordhash = {}, {}
for word in io.open("unixdict.txt", "r"):lines() do
  if #word >= 9 then
    wordlist[#wordlist+1] = word
    wordhash[word] = #wordlist
  end
end
for n = 1, #wordlist-8 do
  local word = ""
  for i = 0, 8 do
    word = word .. wordlist[n+i]:sub(i+1,i+1)
  end
  if wordhash[word] then
    -- task appears to say "for every n, do all of the following"
    -- but doesn't appear to say "..unless a duplicate"
    -- so, intentionally verbose/redundant:
    print(word)
  end
end
Output:
applicate
architect
astronomy
christine
christoph
committee
committee
committee
committee
committee
composite
constrict
constrict
construct
different
extensive
greenwood
implement
improvise
intercept
interpret
interrupt
interrupt
philosoph
prescript
receptive
telephone
transcend
transcend
transport
transpose

Mathematica/Wolfram Language[edit]

dict = Once[Import["https://web.archive.org/web/20180611003215/http://www.puzzlers.org/pub/wordlists/unixdict.txt"]];
dict //= StringSplit[#,"\n"]&;
dict //= Select[StringLength/*GreaterEqualThan[9]];
firsts9 = Characters[dict][[All,;;9]];
words = StringJoin[Diagonal[firsts9,-#]]&/@Range[0,Length[firsts9]-9];
Intersection[words,dict]
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"}

Nim[edit]

import sets, strutils, sugar
 
# Build list and set of words with length >= 9.
let words = collect(newSeq):
              for word in "unixdict.txt".lines:
                if word.len >= 9: word
let wordSet = words.toHashSet
 
var lastWord = ""
var newWord = newString(9)
var count = 0
for i in 0..words.high-9:
  for j in 0..8: newWord[j] = words[i+j][j]
  if newWord in wordSet:
    if newWord != lastWord:
      inc count
      echo ($count).align(2), ' ', newWord
      lastWord = newWord
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

Perl[edit]

#!/usr/bin/perl
 
use strict; # https://rosettacode.org/wiki/Words_from_neighbour_ones
use warnings;
 
@ARGV = 'unixdict.txt';
my $skew = join '', map { s/^.{9}\K.+//r } my @words = grep length() > 9, <>;
my %dict = map { $_ => 1 } grep length == 10, @words;
my %seen;
my $nextch = '.{10}(\\w)' x 8;
while( $skew =~ /^(\w)(?=$nextch)/gms )
  {
  my $new = join '', @{^CAPTURE}, "\n";
  $dict{$new} and !$seen{$new}++ and print $new;
  }
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

Phix[edit]

with javascript_semantics
function over9(string word) return length(word)>=9 end function
sequence words = filter(unix_dict(),over9)
function slicen(integer n) return vslice(words,n)[n..-10+n] end function
sequence neighwords = unique(filter(columnize(apply(tagset(9),slicen)),"in",words))
printf(1,"%d words: %s\n",{length(neighwords),join(shorten(neighwords,"",3))})
Output:
24 words: applicate architect astronomy ... transcend transport transpose

Processing[edit]

StringList words = new StringList(), found = new StringList();
for (String str : loadStrings("unixdict.txt")) {
  if (str.length() >= 9) {
    words.append(str);
  }
}
for (int i = 0; i < words.size() - 9; i++) {
  String temp = "";
  for (int j = 0; j < 9; j++) {
    temp += words.get(i + j).charAt(j);
  }
  if (words.hasValue(temp) && !found.hasValue(temp)) {
    found.append(temp);
  }
}
for (String word : found) {
  println(word);
}
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


Python[edit]

Tested on Python 3+, the file download will work only if the link is still active. It is possible that you may be able to fetch the file in your browser but download via code may still fail. Check whether you are connected to a VPN, it works on open networks. 

 
#Aamrun, 5th November 2021
 
import urllib.request
from collections import Counter
 
urllib.request.urlretrieve("http://wiki.puzzlers.org/pub/wordlists/unixdict.txt", "unixdict.txt")
 
dictionary = open("unixdict.txt","r")
 
wordList = dictionary.read().split('\n')
 
dictionary.close()
 
filteredWords = [chosenWord for chosenWord in wordList if len(chosenWord)>=9]
 
for word in filteredWords[:-9]:
  position = filteredWords.index(word)
  newWord = "".join([filteredWords[position+i][i] for i in range(0,9)])
  if newWord in filteredWords:
   print(newWord)  
 
Output:

Yes, there are duplicates, the task doesn't say that only unique elements should be present, hence the complete raw list will appear as below : 

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

Raku[edit]

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;
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

REXX[edit]

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 is   caseless.

It also allows the minimum length to be specified on the command line (CL) as well as the dictionary file identifier. 

/*REXX pgm finds words that're composed from neighbor words (within an identified dict).*/
parse arg minL iFID .                            /*obtain optional arguments from the CL*/
if minL=='' | minL=="," then minL= 9             /*Not specified?  Then use the default.*/
if iFID=='' | iFID=="," then iFID='unixdict.txt' /* "      "         "   "   "     "    */
#= 0;          @.=;                     !.= 0    /*number of usable words in dictionary.*/
            do recs=0  while lines(iFID)\==0     /*read each word in the file  (word=X).*/
            x= strip( linein( iFID) )            /*pick off a word from the input line. */
            if length(x)<minL  then iterate      /*Is the word too short?  Then skip it.*/
            #= # + 1                             /*bump the count of usable words.      */
            @.#= x;       upper x;      !.x= 1   /*original case;  create findable word.*/
            end   /*recs*/                       /* [↑]   semaphore name is uppercased. */
say copies('─', 30)        recs               "words in the dictionary file: "        iFID
say copies('─', 30)  right(#, length(recs) )  "usable words in the dictionary file."
finds= 0                                         /*count of the  changable  words found.*/
say;                             $=
        do j=1  for #;           y= left(@.j, 1) /*initialize the new word to be built. */
             do k=2  to 9  until n>#;   n= j + k /*use next 8 usable words in dictionary*/
             y= y || substr(@.n, k, 1)           /*build a new word, 1 letter at a time.*/
             end   /*k*/
        uy=y;                    upper uy        /*obtain uppercase version of the word.*/
        if \!.uy  then iterate                   /*Does the new word exist?  No, skip it*/
        if wordpos(uy, $)>0  then iterate        /*Word is a dup?  Then skip duplicate. */
        finds= finds + 1                         /*bump count of found neighboring words*/
        $= $ uy                                  /*add a word to the list of words found*/
        say right( left(y, 30), 40)              /*indent original word for readability.*/
        end      /*j*/
                                                 /*stick a fork in it,  we're all done. */
say copies('─', 30)     finds     ' neighbor words found with a minimum length of '   minL
output   when using the default inputs:
────────────────────────────── 25104 words in the dictionary file:  unixdict.txt
──────────────────────────────  7250 usable words in the dictionary file.

          applicate
          architect
          astronomy
          christine
          christoph
          committee
          composite
          constrict
          construct
          different
          extensive
          greenwood
          implement
          improvise
          intercept
          interpret
          interrupt
          philosoph
          prescript
          receptive
          telephone
          transcend
          transport
          transpose
────────────────────────────── 24  neighbor words found with a minimum length of  9

Ring[edit]

 
cStr = read("unixdict.txt")
wordList = str2list(cStr)
char = list(9)
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)-8
    for m = 1 to 9
        char[m] = substr(wordList[n+m-1],m,1)
    next
    str = ""
    for p = 1 to 9
        str = str + char[p]
    next
    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
 

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[edit]

Library: Wren-sort
Library: Wren-fmt
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)
    }
}
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

Yabasic[edit]

Translation of: FreeBASIC
 
open "unixdict.txt" for reading as #1
p = 0
posic = 0
while not eof(1)
    line input #1 cStr$
    p = p + 1
    if len(cStr$) > 8 then
        posic = posic + 1
        redim wordList$(posic)
        wordList$(posic) = cStr$
    end if
wend
close #1
 
print p, " palabras en el archivo de diccionario: unixdict.txt"
print arraysize(wordList$(), 1), " palabras utilizables en el archivo del diccionario."
 
dim char$(9)
dim nextwords$(arraysize(wordList$(), 1))
 
print chr$(10), "trabajando...", chr$(10)
 
print "Las nuevas palabras son:", chr$(10)
 
posic = 0
for n = 1 to arraysize(wordList$(), 1) - 8
    palabra$ = ""
    for p = 1 to 9
        char$(p) = mid$(wordList$(n + p - 1), p, 1)
        palabra$ = palabra$ + char$(p)
    next p
 
    for p = 1 to arraysize(wordList$(), 1)
        if wordList$(p) = palabra$ then
            posic = posic + 1
            nextwords$(posic) = palabra$
        end if
    next p
next n
 
posic = 0
for n = 2 to arraysize(nextwords$(), 1)
    if nextwords$(n) <> nextwords$(n - 1) then
        posic = posic + 1
        print "", posic, ". ", nextwords$(n - 1)
    end if
next n
end
 
Output:
Igual que la entrada de FreeBASIC.
Retrieved from "http://rosettacode.org/mw/index.php?title=Words_from_neighbour_ones&oldid=351701"
  • GNU Free Documentation License 1.2
  • Powered by MediaWiki
  • Powered by Semantic MediaWiki