Uses langcodes for lang names

.python-version

@@ -0,0 +1 @@
+3.12

bin/dict_summary.py

@@ -1,6 +1,7 @@
 import os
 import json
 import argparse
+import langcodes
 
 DOWNLOAD_TAG = "v4.0" # Set the GitHub tag version that asscociates with the release
 
@@ -119,8 +120,10 @@ def generate_summary(dict_dir):
             download_urls = get_downloadable_files(filebase, DOWNLOAD_TAG, dict_dir)
 
             # Get full language names in Vietnamese
-            source_full_name = language_names.get(metadata['Source'], f"Unknown ({metadata['Source']})")
-            target_full_name = language_names.get(metadata['Target'], f"Unknown ({metadata['Target']})")
+            source_full_name = langcodes.Language.get(metadata['Source']).display_name('vi')
+            # language_names.get(metadata['Source'], f"Unknown ({metadata['Source']})")
+            target_full_name = langcodes.Language.get(metadata['Target']).display_name('vi')
+            #language_names.get(metadata['Target'], f"Unknown ({metadata['Target']})")
 
             # Append the data to the list
             data.append({

bin/test.py

@@ -1,10 +1,8 @@
-from multiprocessing import Pool
-data = [
- {"name": "Delphi"}, {"name": "Orion"}, {"name": "Asher"}, {"name": "Baccus"}
-]
-def fun(object):
- print(object)
+import langcodes
 
-with Pool(4) as pool:
-    pool.map(fun,data)
-#Prints: """
+language_names = {
+    lang_code: langcodes.Language.get(lang_code).display_name('vi')
+    for lang_code in ['vi', 'en', 'fr', 'de', 'es', 'it', 'ja', 'ko', 'zh', 'ru']
+}
+
+print(language_names)

pyproject.toml

@@ -0,0 +1,16 @@
+[project]
+name = "tudien"
+version = "0.1.0"
+description = "Tudien project "
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+    "beautifulsoup4>=4.11.1",
+    "iso-language-codes>=1.1.0",
+    "langcodes>=3.5.0",
+    "lxml>=4.9.1",
+    "marisa-trie>=0.7.7",
+    "pinyin>=0.4.0",
+    "pyglossary>=4.6.1",
+    "ruff>=0.8.2",
+]