json.py — langchain Source File

Source Code

"""Utilities for JSON."""

from __future__ import annotations

import json
import re
from typing import TYPE_CHECKING, Any

from langchain_core.exceptions import OutputParserException

if TYPE_CHECKING:
    from collections.abc import Callable


def _replace_new_line(match: re.Match[str]) -> str:
    """Replace newline characters in a regex match with escaped sequences.

    Args:
        match: Regex match object containing the string to process.

    Returns:
        String with newlines, carriage returns, tabs, and quotes properly escaped.
    """
    value = match.group(2)
    value = re.sub(r"\n", r"\\n", value)
    value = re.sub(r"\r", r"\\r", value)
    value = re.sub(r"\t", r"\\t", value)
    value = re.sub(r'(?<!\\)"', r"\"", value)

    return match.group(1) + value + match.group(3)


def _custom_parser(multiline_string: str | bytes | bytearray) -> str:
    r"""Custom parser for multiline strings.

    The LLM response for `action_input` may be a multiline string containing unescaped
    newlines, tabs or quotes. This function replaces those characters with their escaped
    counterparts. (newlines in JSON must be double-escaped: `\\n`).

    Returns:
        The modified string with escaped newlines, tabs and quotes.
    """
    if isinstance(multiline_string, (bytes, bytearray)):
        multiline_string = multiline_string.decode()

    return re.sub(
        r'("action_input"\:\s*")(.*?)(")',
        _replace_new_line,
        multiline_string,
        flags=re.DOTALL,
    )


# Adapted from https://github.com/KillianLucas/open-interpreter/blob/5b6080fae1f8c68938a1e4fa8667e3744084ee21/interpreter/utils/parse_partial_json.py
# MIT License


def parse_partial_json(s: str, *, strict: bool = False) -> Any:
    """Parse a JSON string that may be missing closing braces.

// ... (169 more lines)