AutoParser

AutoParser is the main entry point for parsing chemical files. It automatically selects the appropriate parser based on the file extension.

The Entrypoint of MolOP

参数：

名称	类型	描述	默认
file_path	str	use regax to match files.	必需
total_charge	int | None	forced charge of the molecule, if not given, will use the charge written in the file or 0.	None
total_multiplicity	int | None	forced multiplicity of the molecule, if not given, will use the charge written in the file or 1.	None
n_jobs	int	number of jobs to use, if -1, use cpu with default max number.	-1
only_extract_structure	bool	if True, only extract the structure, else extract the whole file.	False
only_last_frame	bool	if True, only extract the last frame, else extract all frames.	False
release_file_content	bool	if True, release the file content after parsing, else keep the file content in memory.	True
parser_detection	str	if “auto”, use the file extension to detect the parser, else use the given format id.	'auto'

返回：

类型	描述
FileBatchModelDisk[FileDiskObj]	FileBatchParserDisk

How to use

Python

from molop import AutoParser

parser = AutoParser("/path/to/file")  # return FileBatchParserDisk with singlefile_parser
parser = AutoParser("/path/to/files/*.log")  # return FileBatchParserDisk

源代码位于： src/molop/io/__init__.py

Python

def AutoParser(
    file_path: str,
    *,
    total_charge: int | None = None,
    total_multiplicity: int | None = None,
    n_jobs: int = -1,
    only_extract_structure=False,
    only_last_frame=False,
    release_file_content: bool = True,
    parser_detection: str = "auto",
) -> FileBatchModelDisk["FileDiskObj"]:
    """
    The Entrypoint of MolOP

    Parameters:
        file_path (str):
            use regax to match files.
        total_charge (int | None):
            forced charge of the molecule, if not given, will use the charge written in the file or 0.
        total_multiplicity (int | None):
            forced multiplicity of the molecule, if not given, will use the charge written in the file or 1.
        n_jobs (int):
            number of jobs to use, if -1, use cpu with default max number.
        only_extract_structure (bool):
            if True, only extract the structure, else extract the whole file.
        only_last_frame (bool):
            if True, only extract the last frame, else extract all frames.
        release_file_content (bool):
            if True, release the file content after parsing, else keep the file content in memory.
        parser_detection (str):
            if "auto", use the file extension to detect the parser, else use the given format id.

    Returns:
        FileBatchParserDisk

    How to use
    ----------
    ```python
    from molop import AutoParser

    parser = AutoParser("/path/to/file")  # return FileBatchParserDisk with singlefile_parser
    parser = AutoParser("/path/to/files/*.log")  # return FileBatchParserDisk
    ```
    """
    if os.path.isfile(file_path) and os.path.exists(file_path):
        files = [file_path]
    else:
        base_path, pattern = split_path_pattern(file_path)
        files = [str(p) for p in base_path.glob(pattern)]
    return FileBatchParserDisk(n_jobs=n_jobs).parse(
        files,
        total_charge=total_charge,
        total_multiplicity=total_multiplicity,
        only_extract_structure=only_extract_structure,
        only_last_frame=only_last_frame,
        release_file_content=release_file_content,
        parser_detection=parser_detection,
    )