update languages

src/process_data.py

@@ -1,6 +1,7 @@
 import pandas as pd
 import json
 import os
+import pycountry
 
 from src.collect_data import fetch_version_metadata, fetch_registry_data
 from assets.text_content import LANG_MAPPING
@@ -25,18 +26,37 @@ def clean_price(price):
 def map_languages(languages):
     if isinstance(languages, float) and pd.isna(languages):
         return None
-    # If it's already a list
+        
+    def get_language_name(lang):
+        # Clean and standardize the language code
+        lang = str(lang).strip().lower()
+        
+        # Try to find the language
+        try:
+            # First try as language code (en, fr, etc.)
+            language = pycountry.languages.get(alpha_2=lang)
+            if not language:
+                # Try as language name (English, French, etc.)
+                language = pycountry.languages.get(name=lang.capitalize())
+            
+            return language.name if language else lang
+        except (AttributeError, LookupError):
+            return lang
+    
+    # Handle different input types
     if isinstance(languages, list):
-        return ', '.join([LANG_MAPPING.get(str(lang), str(lang)) for lang in languages])
-    # If it's a string
-    if isinstance(languages, str):
-        return ', '.join([LANG_MAPPING.get(lang.strip(), lang.strip()) for lang in languages.split(',')])
-    # If it's an array or any other type
-    try:
-        return ', '.join([str(lang) for lang in languages])
-    except:
-        return str(languages)
+        lang_list = languages
+    elif isinstance(languages, str):
+        lang_list = [l.strip() for l in languages.split(',')]
+    else:
+        try:
+            lang_list = list(languages)
+        except:
+            return str(languages)
     
+    # Map all languages and join them
+    return ', '.join(get_language_name(lang) for lang in lang_list)
+
 # Extract multimodality fields
 def get_multimodality_field(model_data, field):
     try:

tempapp.py

@@ -1,33 +0,0 @@
-import gradio as gr
-from date_rangeslider import RangeSlider
-from pathlib import Path
-
-text = "## The selected date range is: {min} to {max}"
-
-with gr.Blocks() as demo:
-    with gr.Tabs():
-        with gr.Tab("Demo"):
-            gr.Markdown("""## 🛝 Date RangeSlider
-
-            ## Drag either end and see the selected date range update in real-time.
-            """) 
-            range_slider = RangeSlider(
-                minimum="2023-01-01",
-                maximum="2024-12-31",
-                value=("2023-01-01", "2024-12-31")
-            )
-            range_ = gr.Markdown(value=text.format(min="2023-01-01", max="2024-12-31"))
-            range_slider.change(
-                lambda s: text.format(min=s[0], max=s[1]), 
-                range_slider, 
-                range_,
-                show_progress="hide", 
-                trigger_mode="always_last"
-            )
-            gr.Examples([
-                ("2023-03-01", "2023-06-30"), 
-                ("2023-07-01", "2023-12-31")
-            ], inputs=[range_slider])
-
-if __name__ == "__main__":
-    demo.launch()