Update output_parser.py

output_parser.py

@@ -1,8 +1,7 @@
 from langchain.output_parsers import StructuredOutputParser, ResponseSchema
 from langchain.prompts import PromptTemplate
-from pydantic import BaseModel, Field
-from typing import List, Dict
-import re
+from pydantic import BaseModel
+from typing import Dict
 
 class AttachmentStyle(BaseModel):
     speaker: str
@@ -101,50 +100,3 @@ def parse_analysis_output(output: str, analysis_type: str) -> Dict[str, BaseMode
         return {parsed['speaker']: PersonalityDisorder(**parsed)}
     else:
         raise ValueError(f"Unknown analysis type: {analysis_type}")
-
-def parse_srt_output(srt_content: str) -> Dict[str, Dict[str, float]]:
-    speakers = {}
-    current_speaker = None
-    utterance_count = 0
-    total_words = 0
-
-    for line in srt_content.split('\n'):
-        if line.startswith("Speaker"):
-            current_speaker = line.strip()
-            if current_speaker not in speakers:
-                speakers[current_speaker] = {"total_duration": 0, "utterance_count": 0, "total_words": 0}
-        elif line.startswith(" time:"):
-            time_match = re.search(r'\((.+?) --> (.+?)\)', line)
-            if time_match and current_speaker:
-                start_time = time_to_seconds(time_match.group(1))
-                end_time = time_to_seconds(time_match.group(2))
-                duration = end_time - start_time
-                speakers[current_speaker]["total_duration"] += duration
-                speakers[current_speaker]["utterance_count"] += 1
-        elif line.startswith(" text:"):
-            text = line.replace(" text:", "").strip()
-            words = len(text.split())
-            speakers[current_speaker]["total_words"] += words
-
-    for speaker in speakers:
-        speakers[speaker]["average_utterance_length"] = (
-            speakers[speaker]["total_words"] / speakers[speaker]["utterance_count"]
-            if speakers[speaker]["utterance_count"] > 0
-            else 0
-        )
-
-    return speakers
-
-def time_to_seconds(time_str: str) -> float:
-    h, m, s = time_str.split(':')
-    return int(h) * 3600 + int(m) * 60 + float(s)
-
-def get_speaker_data_for_charts(parsed_output: Dict[str, Dict[str, float]]) -> Dict[str, Dict[str, float]]:
-    return {
-        speaker: {
-            "total_duration": data["total_duration"] / 60,  # Convert to minutes
-            "utterance_count": data["utterance_count"],
-            "average_utterance_length": data["average_utterance_length"]
-        }
-        for speaker, data in parsed_output.items()
-    }