redis-om-python/redis_om/model/token_escaper.py
2021-10-22 06:33:05 -07:00

26 lines
811 B
Python

import re
from typing import Optional, Pattern
class TokenEscaper:
"""
Escape punctuation within an input string.
"""
# Characters that RediSearch requires us to escape during queries.
# Source: https://oss.redis.com/redisearch/Escaping/#the_rules_of_text_field_tokenization
DEFAULT_ESCAPED_CHARS = r"[,.<>{}\[\]\\\"\':;!@#$%^&*()\-+=~\ ]"
def __init__(self, escape_chars_re: Optional[Pattern] = None):
if escape_chars_re:
self.escaped_chars_re = escape_chars_re
else:
self.escaped_chars_re = re.compile(self.DEFAULT_ESCAPED_CHARS)
def escape(self, value: str) -> str:
def escape_symbol(match):
value = match.group(0)
return f"\\{value}"
return self.escaped_chars_re.sub(escape_symbol, value)