{"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":"a1024c35-8b5d-55bf-b275-34457a699e88","task_key":"default--v0~2e1~2e0~5fhf--a1024c35-8b5d-55bf-b275-34457a699e88","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf a1024c35-8b5d-55bf-b275-34457a699e88","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import re\\nimport os\\nfrom pathlib import Path\\nimport glob\\ndef task_func(directory_path: str, regex_pattern: str = r'\\\\\\\\(.+?\\\\\\\\)|\\\\\\\\w') -> dict:\\n\",\"complete_prompt\":\"import re\\nimport os\\nfrom pathlib import Path\\nimport glob\\n\\n\\ndef task_func(directory_path: str, regex_pattern: str = r'\\\\\\\\(.+?\\\\\\\\)|\\\\\\\\w') -> dict:\\n    \\\"\\\"\\\"\\n    Extracts matches from all text files in a specified directory based on a regular expression pattern. \\n    It captures whatever is between parentheses as a single match, and any character outside the parentheses \\n    as individual matches in the string.\\n\\n    Parameters:\\n    - directory_path (str): The path to the directory containing the text files.\\n    - regex_pattern (str): The regular expression pattern to use for matching. Defaults to REGEX_PATTERN.\\n\\n    Returns:\\n    - dict: A dictionary where keys are file names (without path) and values are lists of matches extracted from the files.\\n\\n    Requirements:\\n    - Utilizes libraries: re, os, pathlib.Path, and glob.glob\\n\\n    Example:\\n    >>> matches = task_func('/path/to/directory') # Test with fictional directory path\\n    >>> print(matches)\\n    {}\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Extracts matches from all text files in a specified directory based on a regular expression pattern. It captures whatever is between parentheses as a single match, and any character outside the parentheses as individual matches in the string.\\nThe function should output with:\\n    dict: A dictionary where keys are file names (without path) and values are lists of matches extracted from the files.\\nYou should write self-contained code starting with:\\n```\\nimport re\\nimport os\\nfrom pathlib import Path\\nimport glob\\ndef task_func(directory_path: str, regex_pattern: str = r'\\\\\\\\(.+?\\\\\\\\)|\\\\\\\\w') -> dict:\\n```\",\"libs\":\"['glob', 'pathlib', '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":[]}