Source code for langchain.output_parsers.regex

from __future__ import annotations

import re
from typing import Dict, List, Optional

from langchain_core.output_parsers import BaseOutputParser


class RegexParser(BaseOutputParser):
    """使用正则表达式解析LLM调用的输出。"""

    @classmethod
    def is_lc_serializable(cls) -> bool:
        return True

    regex: str
    """用于解析输出的正则表达式。"""
    output_keys: List[str]
    """用于输出的键。"""
    default_output_key: Optional[str] = None
    """用于输出的默认键。"""

    @property
    def _type(self) -> str:
        """返回类型键。"""
        return "regex_parser"

    def parse(self, text: str) -> Dict[str, str]:
        """解析LLM调用的输出。"""
        match = re.search(self.regex, text)
        if match:
            return {key: match.group(i + 1) for i, key in enumerate(self.output_keys)}
        else:
            if self.default_output_key is None:
                raise ValueError(f"Could not parse output: {text}")
            else:
                return {
                    key: text if key == self.default_output_key else ""
                    for key in self.output_keys
                }