Update app.py

app.py

@@ -3,7 +3,7 @@ import pandas as pd
 
 # Load and parse the CSV file from Hugging Face
 def load_data():
-    url = "https://huggingface.co/datasets/unijoh/RAVNlex/resolve/main/RAVNlex_small.csv"
+    url = "https://huggingface.co/datasets/unijoh/RAVNlex/blob/main/RAVNlex_small.csv"
     df = pd.read_csv(url, delimiter='\t', encoding='iso-8859-10', names=["#ORTO", "#PPOS", "#PHON1", "#PHON2", "#COMM"], dtype=str)
     lemmas = {}
     current_lemma = None
@@ -31,16 +31,16 @@ lemmas = load_data()
 
 def create_noun_table(lemma, forms):
     table_data = {
-        'Nsns': '', 'Nsnst': '', 'Nsas': '', 'Nsast': '',
-        'Nsds': '', 'Nsdst': '', 'Nsgs': '', 'Nsgst': '',
-        'Npns': '', 'Npnst': '', 'Npas': '', 'Npast': '',
-        'Npds': '', 'Npdt': '', 'Npgs': '', 'Npgst': ''
+        'ncmns': '', 'ncmsn==duu': '', 'ncmsa': '', 'ncmsa==duu': '',
+        'ncmsd': '', 'ncmsd==duu': '', 'ncmsg': '', 'ncmsg==dou': '',
+        'ncmpn': '', 'ncmpn==duu': '', 'ncmpa': '', 'ncmpa==duu': '',
+        'ncmpd': '', 'ncmpd==duu': '', 'ncmpg': '', 'ncmpg==dou': ''
     }
     
     for form in forms:
-        ppos = form['PPOS']
+        ppos = form['PPOS'].lower()  # Normalize to lowercase
         word = form['word']
-        key = ppos[1:5]  # Extracting relevant part of PPOS
+        key = ppos.split('=')[0]  # Extracting relevant part of PPOS
         print(f"Processing: word={word}, ppos={ppos}, key={key}")  # Debugging output
         if key in table_data:
             table_data[key] = word
@@ -63,28 +63,28 @@ def create_noun_table(lemma, forms):
         </thead>
         <tbody>
             <tr>
-                <td>{table_data['Nsns']}</td>
-                <td>{table_data['Nsnst']}</td>
-                <td>{table_data['Npns']}</td>
-                <td>{table_data['Npnst']}</td>
+                <td>{table_data['ncmns']}</td>
+                <td>{table_data['ncmsn==duu']}</td>
+                <td>{table_data['ncmpn']}</td>
+                <td>{table_data['ncmpn==duu']}</td>
             </tr>
             <tr>
-                <td>{table_data['Nsas']}</td>
-                <td>{table_data['Nsast']}</td>
-                <td>{table_data['Npas']}</td>
-                <td>{table_data['Npast']}</td>
+                <td>{table_data['ncmsa']}</td>
+                <td>{table_data['ncmsa==duu']}</td>
+                <td>{table_data['ncmpa']}</td>
+                <td>{table_data['ncmpa==duu']}</td>
             </tr>
             <tr>
-                <td>{table_data['Nsds']}</td>
-                <td>{table_data['Nsdst']}</td>
-                <td>{table_data['Npds']}</td>
-                <td>{table_data['Npdt']}</td>
+                <td>{table_data['ncmsd']}</td>
+                <td>{table_data['ncmsd==duu']}</td>
+                <td>{table_data['ncmpd']}</td>
+                <td>{table_data['ncmpd==duu']}</td>
             </tr>
             <tr>
-                <td>{table_data['Nsgs']}</td>
-                <td>{table_data['Nsgst']}</td>
-                <td>{table_data['Npgs']}</td>
-                <td>{table_data['Npgst']}</td>
+                <td>{table_data['ncmsg']}</td>
+                <td>{table_data['ncmsg==dou']}</td>
+                <td>{table_data['ncmpg']}</td>
+                <td>{table_data['ncmpg==dou']}</td>
             </tr>
         </tbody>
     </table>
@@ -98,7 +98,7 @@ def search_lemma(lemma):
         print(f"No results found for {lemma}")  # Debugging output
         return f"No results found for {lemma}"
     
-    if 'N' in results[0]['PPOS']:
+    if 'n' in results[0]['PPOS'].lower():
         table = create_noun_table(lemma, results)
     else:
         table = "Only noun tables are currently supported."