How to use the refextract.references.engine.get_plaintext_document_body function in refextract

def test_get_plaintext_document_body(tmpdir):
    input = [u"Some text\n", u"on multiple lines\n"]
    f = tmpdir.join("plain.txt")
    f.write("".join(input))
    assert input == get_plaintext_document_body(str(f))

    with pytest.raises(UnknownDocumentTypeError) as excinfo:
        html = "Some page"
        f = tmpdir.join("page.html")
        f.write(html)
        get_plaintext_document_body(str(f))
    assert 'text/html' in excinfo.value.args

If you want to also link each reference to some other resource (like a record),
    you can provide a linker_callback function to be executed for every reference
    element found.

    To override KBs for journal names etc., use ``override_kbs_files``:

    >>> extract_references_from_file(path, override_kbs_files={'journals': 'my/path/to.kb'})

    """
    if not os.path.isfile(path):
        raise FullTextNotAvailableError(u"File not found: '{0}'".format(path))

    docbody = get_plaintext_document_body(path)
    reflines, dummy, dummy = extract_references_from_fulltext(docbody)
    if not reflines:
        docbody = get_plaintext_document_body(path, keep_layout=True)
        reflines, dummy, dummy = extract_references_from_fulltext(docbody)

    parsed_refs, stats = parse_references(
        reflines,
        recid=recid,
        reference_format=reference_format,
        linker_callback=linker_callback,
        override_kbs_files=override_kbs_files,
    )

    if magic.from_file(path, mime=True) == "application/pdf":
        texkeys = extract_texkeys_from_pdf(path)
        if len(texkeys) == len(parsed_refs):
            parsed_refs = [dict(ref, texkey=[key]) for ref, key in zip(parsed_refs, texkeys)]

    return parsed_refs

>>> extract_references_from_file(path, reference_format=u"{title},{volume},{page}")

    If you want to also link each reference to some other resource (like a record),
    you can provide a linker_callback function to be executed for every reference
    element found.

    To override KBs for journal names etc., use ``override_kbs_files``:

    >>> extract_references_from_file(path, override_kbs_files={'journals': 'my/path/to.kb'})

    """
    if not os.path.isfile(path):
        raise FullTextNotAvailableError(u"File not found: '{0}'".format(path))

    docbody = get_plaintext_document_body(path)
    reflines, dummy, dummy = extract_references_from_fulltext(docbody)
    if not reflines:
        docbody = get_plaintext_document_body(path, keep_layout=True)
        reflines, dummy, dummy = extract_references_from_fulltext(docbody)

    parsed_refs, stats = parse_references(
        reflines,
        recid=recid,
        reference_format=reference_format,
        linker_callback=linker_callback,
        override_kbs_files=override_kbs_files,
    )

    if magic.from_file(path, mime=True) == "application/pdf":
        texkeys = extract_texkeys_from_pdf(path)
        if len(texkeys) == len(parsed_refs):