engine.py 文件源码

def get_plaintext_document_body(fpath, keep_layout=False):
    """Given a file-path to a full-text, return a list of unicode strings
       whereby each string is a line of the fulltext.
       In the case of a plain-text document, this simply means reading the
       contents in from the file. In the case of a PDF however,
       this means converting the document to plaintext.
       It raises UnknownDocumentTypeError if the document is not a PDF or
       plain text.
       @param fpath: (string) - the path to the fulltext file
       @return: (list) of strings - each string being a line in the document.
    """
    textbody = []
    mime_type = magic.from_file(fpath, mime=True)

    if mime_type == "text/plain":
        with open(fpath, "r") as f:
            textbody = [line.decode("utf-8") for line in f.readlines()]

    elif mime_type == "application/pdf":
        textbody = convert_PDF_to_plaintext(fpath, keep_layout)

    else:
        raise UnknownDocumentTypeError(mime_type)

    return textbody