import re
from typing import Union

from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.exceptions import OutputParserException

from langchain.agents.agent import AgentOutputParser
from langchain.agents.mrkl.prompt import FORMAT_INSTRUCTIONS

FINAL_ANSWER_ACTIONS = ["Final Answer:**", "Final Answer:", "Final Answer**:", "Final Answer"]
MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE = "Invalid Format: Missing 'Action:' after 'Thought:"
MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE = "Invalid Format: Missing 'Action Input:' after 'Action:'"
FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE = "Parsing LLM output produced both a final answer and a parse-able action:"


class ReActSingleInputOutputParser(AgentOutputParser):
    """Parses ReAct-style LLM calls that have a single tool input.

    Expects output to be in one of two formats.

    If the output signals that an action should be taken,
    should be in the below format. This will result in an AgentAction
    being returned.

    ```
    Thought: agent thought here
    Action: search
    Action Input: what is the temperature in SF?
    ```

    If the output signals that a final answer should be given,
    should be in the below format. This will result in an AgentFinish
    being returned.

    ```
    Thought: agent thought here
    Final Answer: The temperature is 100 degrees
    ```

    """

    def get_format_instructions(self) -> str:
        return FORMAT_INSTRUCTIONS

    def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
        for final_answer_action in FINAL_ANSWER_ACTIONS:
            includes_answer = final_answer_action in text
            if includes_answer:
                return AgentFinish({"output": text.split(final_answer_action)[-1].strip()}, text)

        regex = r"Action\s*\d*\s*:[\s]*(.*?)[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)"
        action_match = re.search(regex, text, re.DOTALL)
        if action_match:
            action = action_match.group(1).strip()
            action_input = action_match.group(2)
            tool_input = action_input.strip(" ")
            tool_input = tool_input.strip('"')

            return AgentAction(action, tool_input, text)

        if not re.search(r"Action\s*\d*\s*:[\s]*(.*?)", text, re.DOTALL):
            raise OutputParserException(
                f"Could not parse LLM output: `{text}`",
                observation=MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE,
                llm_output=text,
                send_to_llm=True,
            )
        elif not re.search(r"[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)", text, re.DOTALL):
            raise OutputParserException(
                f"Could not parse LLM output: `{text}`",
                observation=MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE,
                llm_output=text,
                send_to_llm=True,
            )
        else:
            raise OutputParserException(f"Could not parse LLM output: `{text}`")

    @property
    def _type(self) -> str:
        return "react-single-input"