show score composition

app.py

@@ -44,11 +44,23 @@ def process_ocr_qa(text, lang_choice):
             if 'language' in result:
                 output_lines.append(f"🌍 Language: {result['language']}")
             
-            # Quality score
-            if 'score' in result:
-                score = result['score']
+            # Quality score (with ratio)
+            score = result.get("score")
+            diagnostics = result.get("diagnostics", {})
+            known_tokens = diagnostics.get("known_tokens", [])
+            unknown_tokens = diagnostics.get("unknown_tokens", [])
+            
+            if score is not None:
+                k = len(known_tokens)
+                u = len(unknown_tokens)
+                total = k + u
+                ratio = f"{k}/{total}" if total > 0 else "0/0"
+            
                 score_emoji = "🟢" if score >= 0.8 else "🟡" if score >= 0.5 else "🔴"
-                output_lines.append(f"{score_emoji} Quality Score: {score}")
+                output_lines.append(
+                    f"{score_emoji} Quality Score: {score:.3f}  ({ratio})"
+                )
+
             
             # Diagnostics section
             if 'diagnostics' in result and result['diagnostics']:
@@ -61,12 +73,12 @@ def process_ocr_qa(text, lang_choice):
                 # Known tokens
                 if 'known_tokens' in diagnostics and diagnostics['known_tokens']:
                     known_tokens = diagnostics['known_tokens']
-                    output_lines.append(f"✅ Known unique tokens ({len(known_tokens)}):\n {' '.join(known_tokens)}")
+                    output_lines.append(f"✅ Known unique tokens ({k}):\n{' '.join(known_tokens)}")
                 
                 # Unknown tokens (potential OCR errors)
                 if 'unknown_tokens' in diagnostics and diagnostics['unknown_tokens']:
                     unknown_tokens = diagnostics['unknown_tokens']
-                    output_lines.append(f"❌ Unrecognized unique tokens ({len(unknown_tokens)}):\n {' '.join(unknown_tokens)}")
+                    output_lines.append(f"❌ Unrecognized unique tokens (u}):\n{' '.join(unknown_tokens)}")
                 elif 'unknown_tokens' in diagnostics:
                     output_lines.append("✨ All tokens were known – no OCR errors detected.")