Update app.py

app.py

@@ -755,6 +755,7 @@ def highlight_tokens_html(tokens, labels):
                 j += 1
             chunk = " ".join(tokens[i:j])
             chunk = re.sub(r"\s+([.,!?;:])", r"\1", chunk)
+            chunk = fix_apostrophe_spacing(chunk)
             esc = html.escape(chunk)
             title = html.escape(lab)
 
@@ -2296,35 +2297,74 @@ def clean_bpe_text(text):
 
 ###############################################################################
 
+###############################################################################
+def fix_apostrophe_spacing(s):
+    if not s:
+        return s
+    s = s.replace("’", "'")
+
+    # didn't / don't / isn't / can't ...
+    s = re.sub(r"\bn\s+'\s+t\b", "n't", s, flags=re.I)
+    s = re.sub(r"(\w)n\s+'\s+t\b", r"\1n't", s, flags=re.I)
+
+    # she's / it's / he's / I'm / you're / we'll / I've ...
+    s = re.sub(
+        r"(\w)\s+'\s+(s|re|ll|ve|d|m)\b",
+        r"\1'\2",
+        s,
+        flags=re.I,
+    )
+
+    # any leftover spaces touching an apostrophe
+    s = re.sub(r"\s+'\s+", "'", s)
+    s = re.sub(r"(\w)'\s+(\w)", r"\1'\2", s)
+    s = re.sub(r"(\w)\s+'(\w)", r"\1'\2", s)
+
+    return s
+###############################################################################
 
 ###############################################################################
 def clean_output(text):
     if not text:
         return ""
-    
+
     # brackets and WordPiece fragments
     text = re.sub(r'[\[\]]+', '', text)
     text = re.sub(r'\s*##\s*', '', text)
     text = re.sub(r'#', '', text)
-    
+
     text = re.sub(r'\s+', ' ', text).strip()
-    
+
     # normal spacing around punctuation
     text = re.sub(r'\s+([.,!?;:])', r'\1', text)
     text = re.sub(r'([.,!?;:])\s+', r'\1 ', text)
-    
+
     # --- fix the trailing ",." pattern ---
-    text = re.sub(r',+\s*\.', '.', text)   # ",." or ", ." → "."
-    text = re.sub(r',+\s*$', '', text)     # trailing commas at end of string
-    text = re.sub(r'\.+$', '.', text)      # collapse multiple periods
-    
+    text = re.sub(r',+\s*\.', '.', text)
+    text = re.sub(r',+\s*$', '', text)
+    text = re.sub(r'\.+$', '.', text)
+
+    # --- spaces around apostrophes (didn't / she's / it's) ---
+    text = text.replace("’", "'")
+    text = re.sub(r"\bn\s+'\s+t\b", "n't", text, flags=re.I)
+    text = re.sub(r"(\w)n\s+'\s+t\b", r"\1n't", text, flags=re.I)
+    text = re.sub(
+        r"(\w)\s+'\s+(s|re|ll|ve|d|m)\b",
+        r"\1'\2",
+        text,
+        flags=re.I,
+    )
+    text = re.sub(r"\s+'\s+", "'", text)
+    text = re.sub(r"(\w)'\s+(\w)", r"\1'\2", text)
+    text = re.sub(r"(\w)\s+'(\w)", r"\1'\2", text)
+
     text = text.strip()
-    
+
     if text:
         text = text[0].upper() + text[1:]
         if not text.endswith(('.', '!', '?')):
             text += '.'
-    
+
     return text.strip()
 
 ###############################################################################