Merge

Merge is a set of standalone functions for merging strings, spaCy Docs, and files.

lexos.cutter.merge.merge(segments, sep=None)

Merge a list of segments into a single string.

Parameters:

Name	Type	Description	Default
segments	_type_	The list of segments to merge.	required
sep	str	The separator to use when merging strings. Defaults to None.	None

Source code in lexos\cutter\merge.py

def merge(segments: Union[List[str], List[spacy.tokens.doc.Doc]], sep=None):
    """Merge a list of segments into a single string.

    Args:
        segments (_type_): The list of segments to merge.
        sep (str, optional): The separator to use when merging strings. Defaults to None.
    """
    if all(isinstance(segment, str) for segment in segments):
        if sep is None:
            sep = ""
        return sep.join(segments)
    elif all(isinstance(segment, spacy.tokens.doc.Doc) for segment in segments):
        return Doc.from_docs(segments)
    else:
        raise LexosException(
            "All segments must be either strings or spacy.tokens.doc.Doc."
        )

lexos.cutter.merge.merge_files(segment_files, output_file='merged_files.txt', binary=False)

Merge two files into a single string.

Parameters:

Name	Type	Description	Default
segment_files	List[str]	List of files to be merged.	required
output_file	str	The name of the output file.	'merged_files.txt'
binary	bool	Whether to read and write files as binary. Defaults to False.	False

Source code in lexos\cutter\merge.py

def merge_files(
    segment_files: List[str],
    output_file: str = "merged_files.txt",
    binary: bool = False,
) -> None:
    """Merge two files into a single string.

    Args:
        segment_files (List[str]): List of files to be merged.
        output_file (str, optional): The name of the output file.
        binary (bool, optional): Whether to read and write files as binary. Defaults to False.
    """
    if binary:
        read_mode = "rb"
        write_mode = "wb"
    else:
        read_mode = "r"
        write_mode = "w"
    with open("merged_file.txt", write_mode) as out_file:
        for file in segment_files:
            try:
                with open(output_file, read_mode) as f:
                    shutil.copyfileobj(file, out_file, 1024 * 1024 * 10)
            except Exception as e:
                raise LexosException(f"Error merging files: {e}.")