{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"bigcodebench","formal_name":"BigCodeBench","introduction":"BigCodeBench poses 1,140 function-level tasks drawn across 139 libraries. It tests whether a model can compose several real APIs correctly rather than write one self-contained function.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://bigcode-bench.github.io/","indexing_mode":"index","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[],"history":"","construction":"","limitations":"","saturation":"","scores":[]}},"task_id":"f08eb3b6-27cc-5eb4-b022-aa8a878eb7a3","task_key":"default--v0~2e1~2e0~5fhf--f08eb3b6-27cc-5eb4-b022-aa8a878eb7a3","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf f08eb3b6-27cc-5eb4-b022-aa8a878eb7a3","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import re\\nimport json\\nimport os\\ndef task_func(file_path: str, regex_pattern=r'\\\\(.+?\\\\)|\\\\w') -> dict:\\n\",\"complete_prompt\":\"import re\\nimport json\\nimport os\\n\\n\\ndef task_func(file_path: str, regex_pattern=r'\\\\(.+?\\\\)|\\\\w') -> dict:\\n    \\\"\\\"\\\"\\n    Extracts matches from a JSON file based on a predefined regular pattern.\\n    The default regular expression pattern is designed to extract any content between parentheses\\n    as a single match and any individual character outside the parentheses as a separate match.\\n    \\n    Parameters:\\n    - file_path (str): The path to the JSON file. The JSON file should contain key-value pairs\\n                       where the values are strings to be matched against the regex pattern.\\n                       \\n    Returns:\\n    - dict: A dictionary with the JSON file name as the key and a list of matches as values.\\n            The format is: {filename: [match1, match2, ...]}.\\n            \\n    Requirements:\\n    - The function makes use of the following libraries/modules: re, json, os.\\n    \\n    Example:\\n    >>> import tempfile\\n    >>> temp_dir = tempfile.mkdtemp()\\n    >>> file_path = os.path.join(temp_dir, 'sample_data.json')\\n    >>> with open(file_path, 'w') as file:\\n    ...     json.dump({'content': 'This is a (sample) text with some (matches) and characters.'}, file)\\n    >>> matches = task_func(file_path)\\n    >>> len(matches['sample_data.json'])\\n    34\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Extracts matches from a JSON file based on a predefined regular pattern. The default regular expression pattern is designed to extract any content between parentheses as a single match and any individual character outside the parentheses as a separate match.\\nThe function should output with:\\n    dict: A dictionary with the JSON file name as the key and a list of matches as values.\\n    The format is: {filename: [match1, match2, ...]}.\\nYou should write self-contained code starting with:\\n```\\nimport re\\nimport json\\nimport os\\ndef task_func(file_path: str, regex_pattern=r'\\\\(.+?\\\\)|\\\\w') -> dict:\\n```\",\"libs\":\"['json', 're', 'os']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}