Paul Bailey
77437348ed
- Created RoleDetector class with colon and bracket pattern extraction - Implemented role deduplication logic - Added fallback to default 'Narrator' role when no patterns found - Created /api/tts/roles endpoint using RoleDetector - Added comprehensive test suite for role detection - All tests passing (7/7) Requirements: 2.1, 2.2, 2.3, 2.4, 2.5, 2.6
94 lines
2.7 KiB
Python
94 lines
2.7 KiB
Python
"""
|
|
Role detection service for identifying distinct speakers in text.
|
|
"""
|
|
import re
|
|
from typing import List, Set, Dict
|
|
|
|
|
|
class RoleDetector:
|
|
"""
|
|
Service for detecting distinct speaker roles in text.
|
|
|
|
Supports two pattern types:
|
|
1. Colon pattern: "RoleName:" at the start of a line
|
|
2. Bracket pattern: "[RoleName]" preceding dialogue
|
|
"""
|
|
|
|
# Regex patterns for role detection
|
|
COLON_PATTERN = r'^([A-Z][a-zA-Z\s]+?):\s'
|
|
BRACKET_PATTERN = r'\[([A-Z][a-zA-Z\s]+?)\]'
|
|
DEFAULT_ROLE = "Narrator"
|
|
|
|
def detect_roles(self, text: str) -> List[Dict[str, str]]:
|
|
"""
|
|
Analyzes text to identify distinct speaker roles.
|
|
|
|
Args:
|
|
text: Input text to analyze
|
|
|
|
Returns:
|
|
List of role dictionaries with 'id' and 'label' fields.
|
|
Returns default "Narrator" role if no patterns found.
|
|
"""
|
|
if not text or not text.strip():
|
|
return [{"id": self.DEFAULT_ROLE, "label": self.DEFAULT_ROLE}]
|
|
|
|
# Extract roles from both patterns
|
|
colon_roles = self._extract_colon_pattern(text)
|
|
bracket_roles = self._extract_bracket_pattern(text)
|
|
|
|
# Combine and deduplicate
|
|
all_roles = colon_roles.union(bracket_roles)
|
|
|
|
# If no roles found, return default
|
|
if not all_roles:
|
|
return [{"id": self.DEFAULT_ROLE, "label": self.DEFAULT_ROLE}]
|
|
|
|
# Convert to role dictionaries and sort for consistent ordering
|
|
role_list = [
|
|
{"id": role.strip(), "label": role.strip()}
|
|
for role in sorted(all_roles)
|
|
]
|
|
|
|
return role_list
|
|
|
|
def _extract_colon_pattern(self, text: str) -> Set[str]:
|
|
"""
|
|
Extracts roles from "RoleName:" pattern at line starts.
|
|
|
|
Args:
|
|
text: Input text to analyze
|
|
|
|
Returns:
|
|
Set of role names found
|
|
"""
|
|
roles = set()
|
|
pattern = re.compile(self.COLON_PATTERN, re.MULTILINE)
|
|
|
|
for match in pattern.finditer(text):
|
|
role_name = match.group(1).strip()
|
|
if role_name:
|
|
roles.add(role_name)
|
|
|
|
return roles
|
|
|
|
def _extract_bracket_pattern(self, text: str) -> Set[str]:
|
|
"""
|
|
Extracts roles from "[RoleName]" pattern.
|
|
|
|
Args:
|
|
text: Input text to analyze
|
|
|
|
Returns:
|
|
Set of role names found
|
|
"""
|
|
roles = set()
|
|
pattern = re.compile(self.BRACKET_PATTERN)
|
|
|
|
for match in pattern.finditer(text):
|
|
role_name = match.group(1).strip()
|
|
if role_name:
|
|
roles.add(role_name)
|
|
|
|
return roles
|