Use Wiktionary WikiWoordenboek list as source

src/alfagok/static/game.css

@@ -56,6 +56,7 @@ button {
 
 ul {
     list-style-type: none;
+    padding-left: 0;
 }
 
 .error {

src/alfagok/static/game.js

@@ -48,7 +48,6 @@ document.addEventListener('alpine:init', () => {
                 return;
             }
 
-            this.nrGuesses++;
             if (this.startTime === null) {
                 console.log('Setting startTime to now');
                 this.startTime = new Date();
@@ -70,6 +69,7 @@ document.addEventListener('alpine:init', () => {
                 }
                 return;
             }
+            this.nrGuesses++;
             if (result.hint && result.hint === 'after') {
                 this.guessesBefore.push(this.guessValue);
                 this.guessesBefore.sort();

src/alfagok/templates/index.html

@@ -12,7 +12,7 @@
 
         <div id="container" x-data="">
 
-            <a href="/" x-cloak class="title">alfagok</a> <span class="puzzleno">puzzel #<span x-text="$store.alfagok.gameID"></span> • <span id="nextgame"></span></span>
+            <a href="/" x-cloak class="title">alfagok</a> <span class="puzzleno">puzzel #<span x-text="$store.alfagok.gameID"></span> • <span id="nextgame"></span> • <span x-text="$store.alfagok.nrGuesses"></span> gokken</span>
 
             <div x-cloak class="instructions" x-show="$store.alfagok.guessesBefore.length === 0 && $store.alfagok.guessesAfter.length === 0">
                 <p>Raad het woord van de dag. Elke gok geeft een hint over waar het woord zich in het alfabet bevindt.</p>

wordlist/create_list.py

@@ -5,41 +5,88 @@ MAX_LENGTH = 10
 
 NUMBER_DAYS = 5 * 365
 
-with open('basiswoorden-gekeurd.txt', 'r', encoding='utf-8') as wordfile:
+# Set to True if you want to use the big but difficult OpenTaal list
-    all_words = wordfile.readlines()
+USE_OPENTAAL = False
-    print(f'original list contains {len(all_words)} words')
 
-    dictionary_list = []
+with open('wikiwoordenboek_basiswoorden.lst', 'r', encoding='utf-8') as wordfile:
-    result_list = []
+    wikiwoorden_words = wordfile.readlines()
-    for word in all_words:
+    print(f'wikiwoorden basic list contains {len(wikiwoorden_words)} words')
+
+with open('basiswoorden-gekeurd.txt', 'r', encoding='utf-8') as wordfile:
+    basis_words = wordfile.readlines()
+    print(f'opentaal basic list contains {len(basis_words)} words')
+
+with open('flexies-ongekeurd.txt', 'r', encoding='utf-8') as wordfile:
+    # Vervoegingen and such, see https://nl.wikipedia.org/wiki/Flexie_(taalkunde)
+    flexies_words = wordfile.readlines()
+    print(f'flexies list contains {len(flexies_words)} words')
+
+with open('/usr/share/dict/american-english', 'r', encoding='utf-8') as wordfile:
+    # English words we want to filter from the list; don't really care if there's accidental overlap with Dutch words
+    english_words = wordfile.readlines()
+    print(f'english list contains {len(english_words)} words')
+
+print()
+print('merging and filtering...')
+print()
+
+all_words_count = 0
+dictionary_list = []
+result_list = []
+for word in wikiwoorden_words + basis_words + flexies_words:
+    all_words_count += 1
     word = word.strip()
     if word.isalpha() and word.lower() == word:
         # Word is valid for our dictionary
         dictionary_list.append(f'{word}\n')
+
+# Deduplicate dictionary
+dictionary_list = sorted(list(set(dictionary_list)), key=str.casefold)
+
+if USE_OPENTAAL:
+    # Use basis_words if you want to use the big but difficult OpenTaal list
+    source_words = basis_words
+else:
+    source_words = wikiwoorden_words
+
+for word in source_words:
+    word = word.strip()
     if word.isalpha() and word.lower() == word and len(word) >= MIN_LENGTH and len(word) <= MAX_LENGTH:
         # Word is 'fit' for our game
         result_list.append(f'{word}\n')
 
-    # print(result_list)
+if USE_OPENTAAL:
-    print(f'words filtered: {len(result_list)} with length >= {MIN_LENGTH} and <= {MAX_LENGTH}')
+    nl_set = set(result_list)
-    print(f'words in dictionary: {len(dictionary_list)}')
+    en_set = set(english_words)
 
-    with open('filtered.txt', 'w', encoding='utf-8') as f:
+    # Only keep the words that are not found in the English set
-        f.writelines(result_list)
+    filtered_set = nl_set.difference(en_set)
+    filtered_list = sorted(list(filtered_set), key=str.casefold)
+else:
+    filtered_list = sorted(list(wikiwoorden_words), key=str.casefold)
 
-    with open('dictionary.txt', 'w', encoding='utf-8') as f:
+print(f'words total: {all_words_count}')
+print(f'words in dictionary: {len(dictionary_list)}')
+print(f'words initially filtered: {len(result_list)} with length >= {MIN_LENGTH} and <= {MAX_LENGTH}')
+if USE_OPENTAAL:
+    print(f'words after filtering english: {len(filtered_list)}')
+
+with open('filtered.txt', 'w', encoding='utf-8') as f:
+    f.writelines(filtered_list)
+
+with open('dictionary.txt', 'w', encoding='utf-8') as f:
     f.writelines(dictionary_list)
 
-    selection_list = []
+selection_list = []
 
-    # Randomly select words for each day
+# Randomly select words for each day
-    while len(selection_list) < NUMBER_DAYS:
+while len(selection_list) < NUMBER_DAYS:
     # Use index - 1 because lists start at index 0
-        word_index = random.randrange(0, len(result_list) - 1)
+    word_index = random.randrange(0, len(filtered_list) - 1)
-        selection_list.append(result_list[word_index])
+    selection_list.append(filtered_list[word_index])
 
-    # Save the result
+# Save the result
-    with open('word_of_the_day.txt', 'w', encoding='utf-8') as f:
+with open('word_of_the_day.txt', 'w', encoding='utf-8') as f:
     f.writelines(selection_list)
 
-    print(f'done writing {len(selection_list)} random words, enjoy!')
+print(f'done writing {len(selection_list)} random words, enjoy!')