feat(database): started new database generation script

camarm-dev · Jul 5, 2024 · 9200f23 · 9200f23
1 parent 87d515c
commit 9200f23
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 13 deletions.
diff --git a/scripts/add_word.py b/scripts/add_word.py
@@ -4,6 +4,7 @@
 import sqlite3
 import sys
 
+from scripts.utils.dictionary_database import RemedeDatabase
 from scripts.utils.sanitize import sanitize_word
 
 
@@ -70,19 +71,13 @@ def getTimeDetails(time_object):
             document = get_word_document(word, phoneme)
             print("Fait.")
 
-            print("- Ajout du document aux bases JSON")
-            add_to_json(word, document)
+            print("- Insertion du document Remède...")
+            database.insert(word, phoneme)
             print("Fait.")
 
-            print("- Ajout du document à la base Sqlite")
-            insert_document(document, word)
-            print("Fait.")
-
-            print("- Mise à jour de l'index...")
-            cursor.execute("INSERT INTO wordlist VALUES (?,?)", (word, sanitize_word(word)))
-            print("Fait.")
-
-
+        print("- Sauvegarde de la base de données...")
+        database.save()
+        print("Fait.")
         print("- Génération des ressources...")
         runpy.run_module('pre_generate_ressources', run_name='__main__')
         print("Fait.")

diff --git a/scripts/generate.py b/scripts/generate.py
@@ -9,7 +9,7 @@
 from scripts.utils.dataset import get_words, get_word2ipa, get_custom_words
 from scripts.utils.dictionary_database import RemedeDatabase
 from scripts.utils.sanitize import sanitize_word
-from scripts.utils.scrap import get_conjugaisons, get_synonyms, get_antonyms, count_syllables
+from scripts.utils.scrap import get_conjugaisons, get_synonyms, get_antonyms, count_syllables, get_word_stats
 
 modes_conjugation_subjects = {
     "Participe_Présent": "(en)",
@@ -94,7 +94,8 @@ def remedize(word_list: list):
         if not document:
             errored += 1
         # TODO nature
-        database.insert(word, sanitize_word(word), ipa, "", count_syllables(ipa), )
+        elidable, feminine, syllables = get_word_stats(word, ipa)
+        database.insert(word, sanitize_word(word), ipa, "", syllables, elidable, feminine, document)
         print(f"\033[A\033[KMot n°{word_list.index(word) + 1}/{total}: \"{word}\"{' ' * (22 - len(word))} | {errored} erreurs")
 
 

diff --git a/scripts/utils/scrap.py b/scripts/utils/scrap.py
@@ -24,6 +24,7 @@ def get_word_stats(word: str, phoneme: str):
     :param phoneme: phoneme of word
     :return: Elidable, Feminine, Syllable count
     """
+    # TODO find with drime database
     return False, phoneme[-1] == 'e', count_syllables(word.lower())