Update output_parser.py

output_parser.py

@@ -1,6 +1,40 @@
 import re
 from collections import defaultdict
 
+def parse_analysis_output(text):
+    speakers_data = {}
+    current_speaker = None
+    explanation = ""
+    for line in text.split('\n'):
+        line = line.strip()
+        if line.startswith("-----------------------"):
+            if current_speaker and explanation:
+                speakers_data[current_speaker]["explanation"] = explanation.strip()
+            explanation = ""
+            current_speaker = None
+            continue
+        if line.startswith("Speaker"):
+            current_speaker = line.strip()
+            speakers_data[current_speaker] = {}
+        elif ':' in line and current_speaker:
+            key, value = line.split(':', 1)
+            key = key.strip()
+            value = value.strip()
+            if key.lower() == "explanation":
+                explanation += value + " "
+            else:
+                try:
+                    speakers_data[current_speaker][key] = float(value)
+                except ValueError:
+                    speakers_data[current_speaker][key] = value
+        elif line and current_speaker and not line.startswith("Explanation"):
+            explanation += line + " "
+    
+    if current_speaker and explanation:
+        speakers_data[current_speaker]["explanation"] = explanation.strip()
+
+    return speakers_data
+
 def parse_srt_output(srt_content):
     speakers = defaultdict(lambda: {"utterances": [], "total_duration": 0})
     current_speaker = None
@@ -25,17 +59,6 @@ def parse_srt_output(srt_content):
                 speakers[current_speaker]["utterances"].append(current_utterance.copy())
             current_utterance = {"start": "", "end": "", "text": ""}
 
-    # Print the parsed output for debugging
-    print("Parsed SRT Output:")
-    for speaker, data in speakers.items():
-        print(f"{speaker}:")
-        print(f"  Total duration: {data['total_duration']}")
-        print(f"  Utterances:")
-        for utterance in data['utterances'][:3]:  # Print first 3 utterances for brevity
-            print(f"    {utterance['start']} - {utterance['end']}: {utterance['text']}")
-        print(f"  Total utterances: {len(data['utterances'])}")
-        print()
-
     return speakers
 
 def get_speaker_data_for_charts(parsed_output):
@@ -46,9 +69,4 @@ def get_speaker_data_for_charts(parsed_output):
             "utterance_count": len(data["utterances"]),
             "average_utterance_length": sum(len(u["text"].split()) for u in data["utterances"]) / len(data["utterances"]) if data["utterances"] else 0
         }
-    
-    # Print the data for charts
-    print("Data for Charts:")
-    print(speaker_data)
-    
     return speaker_data