插件启动接入

pilot/json_utils/json_fix_general.py

@@ -0,0 +1,121 @@
+"""This module contains functions to fix JSON strings using general programmatic approaches, suitable for addressing
+common JSON formatting issues."""
+from __future__ import annotations
+
+import contextlib
+import json
+import re
+from typing import Optional
+
+from pilot.configs.config import Config
+from pilot.logs import logger
+from pilot.json_utils.utilities import extract_char_position
+
+CFG = Config()
+
+
+def fix_invalid_escape(json_to_load: str, error_message: str) -> str:
+    """Fix invalid escape sequences in JSON strings.
+
+    Args:
+        json_to_load (str): The JSON string.
+        error_message (str): The error message from the JSONDecodeError
+          exception.
+
+    Returns:
+        str: The JSON string with invalid escape sequences fixed.
+    """
+    while error_message.startswith("Invalid \\escape"):
+        bad_escape_location = extract_char_position(error_message)
+        json_to_load = (
+            json_to_load[:bad_escape_location] + json_to_load[bad_escape_location + 1 :]
+        )
+        try:
+            json.loads(json_to_load)
+            return json_to_load
+        except json.JSONDecodeError as e:
+            logger.debug("json loads error - fix invalid escape", e)
+            error_message = str(e)
+    return json_to_load
+
+
+def balance_braces(json_string: str) -> Optional[str]:
+    """
+    Balance the braces in a JSON string.
+
+    Args:
+        json_string (str): The JSON string.
+
+    Returns:
+        str: The JSON string with braces balanced.
+    """
+
+    open_braces_count = json_string.count("{")
+    close_braces_count = json_string.count("}")
+
+    while open_braces_count > close_braces_count:
+        json_string += "}"
+        close_braces_count += 1
+
+    while close_braces_count > open_braces_count:
+        json_string = json_string.rstrip("}")
+        close_braces_count -= 1
+
+    with contextlib.suppress(json.JSONDecodeError):
+        json.loads(json_string)
+        return json_string
+
+
+def add_quotes_to_property_names(json_string: str) -> str:
+    """
+    Add quotes to property names in a JSON string.
+
+    Args:
+        json_string (str): The JSON string.
+
+    Returns:
+        str: The JSON string with quotes added to property names.
+    """
+
+    def replace_func(match: re.Match) -> str:
+        return f'"{match[1]}":'
+
+    property_name_pattern = re.compile(r"(\w+):")
+    corrected_json_string = property_name_pattern.sub(replace_func, json_string)
+
+    try:
+        json.loads(corrected_json_string)
+        return corrected_json_string
+    except json.JSONDecodeError as e:
+        raise e
+
+
+def correct_json(json_to_load: str) -> str:
+    """
+    Correct common JSON errors.
+    Args:
+        json_to_load (str): The JSON string.
+    """
+
+    try:
+        logger.debug("json", json_to_load)
+        json.loads(json_to_load)
+        return json_to_load
+    except json.JSONDecodeError as e:
+        logger.debug("json loads error", e)
+        error_message = str(e)
+        if error_message.startswith("Invalid \\escape"):
+            json_to_load = fix_invalid_escape(json_to_load, error_message)
+        if error_message.startswith(
+            "Expecting property name enclosed in double quotes"
+        ):
+            json_to_load = add_quotes_to_property_names(json_to_load)
+            try:
+                json.loads(json_to_load)
+                return json_to_load
+            except json.JSONDecodeError as e:
+                logger.debug("json loads error - add quotes", e)
+                error_message = str(e)
+        if balanced_str := balance_braces(json_to_load):
+            return balanced_str
+    return json_to_load

pilot/json_utils/utilities.py

@@ -0,0 +1,81 @@
+"""Utilities for the json_fixes package."""
+import json
+import os.path
+import re
+
+from jsonschema import Draft7Validator
+
+from pilot.configs.config import Config
+from pilot.logs import logger
+
+CFG = Config()
+LLM_DEFAULT_RESPONSE_FORMAT = "llm_response_format_1"
+
+
+def extract_char_position(error_message: str) -> int:
+    """Extract the character position from the JSONDecodeError message.
+
+    Args:
+        error_message (str): The error message from the JSONDecodeError
+          exception.
+
+    Returns:
+        int: The character position.
+    """
+
+    char_pattern = re.compile(r"\(char (\d+)\)")
+    if match := char_pattern.search(error_message):
+        return int(match[1])
+    else:
+        raise ValueError("Character position not found in the error message.")
+
+
+def validate_json(json_object: object, schema_name: str) -> dict | None:
+    """
+    :type schema_name: object
+    :param schema_name: str
+    :type json_object: object
+    """
+    scheme_file = os.path.join(os.path.dirname(__file__), f"{schema_name}.json")
+    with open(scheme_file, "r") as f:
+        schema = json.load(f)
+    validator = Draft7Validator(schema)
+
+    if errors := sorted(validator.iter_errors(json_object), key=lambda e: e.path):
+        logger.error("The JSON object is invalid.")
+        if CFG.debug_mode:
+            logger.error(
+                json.dumps(json_object, indent=4)
+            )  # Replace 'json_object' with the variable containing the JSON data
+            logger.error("The following issues were found:")
+
+            for error in errors:
+                logger.error(f"Error: {error.message}")
+    else:
+        logger.debug("The JSON object is valid.")
+
+    return json_object
+
+
+def validate_json_string(json_string: str, schema_name: str) -> dict | None:
+    """
+    :type schema_name: object
+    :param schema_name: str
+    :type json_object: object
+    """
+
+    try:
+        json_loaded = json.loads(json_string)
+        return validate_json(json_loaded, schema_name)
+    except:
+        return None
+
+
+def is_string_valid_json(json_string: str, schema_name: str) -> bool:
+    """
+    :type schema_name: object
+    :param schema_name: str
+    :type json_object: object
+    """
+
+    return validate_json_string(json_string, schema_name) is not None