예제 #1
0
def copyfile_brainvision(vhdr_src, vhdr_dest, anonymize=None, verbose=False):
    """Copy a BrainVision file triplet to a new location and repair links.

    The BrainVision file format consists of three files: .vhdr, .eeg, and .vmrk
    The .eeg and .vmrk files associated with the .vhdr file will be given names
    as in `vhdr_dest` with adjusted extensions. Internal file pointers will be
    fixed.

    Parameters
    ----------
    vhdr_src : str
        The src path of the .vhdr file to be copied.
    vhdr_dest : str
        The destination path of the .vhdr file.
    anonymize : dict | None
        If None (default), no anonymization is performed.
        If dict, data will be anonymized depending on the keys provided with
        the dict: `daysback` is a required key, `keep_his` is an optional key.

        `daysback` : int
            Number of days by which to move back the recording date in time.
            In studies with multiple subjects the relative recording date
            differences between subjects can be kept by using the same number
            of `daysback` for all subject anonymizations. `daysback` should be
            great enough to shift the date prior to 1925 to conform with BIDS
            anonymization rules.

        `keep_his` : bool
            By default (False), all subject information next to the recording
            date will be overwritten as well. If True, keep subject information
            apart from the recording date.

    verbose : bool
        Determine whether results should be logged. Defaults to False.

    See Also
    --------
    mne.io.anonymize_info

    """
    # Get extenstion of the brainvision file
    fname_src, ext_src = _parse_ext(vhdr_src)
    fname_dest, ext_dest = _parse_ext(vhdr_dest)
    if ext_src != ext_dest:
        raise ValueError(f'Need to move data with same extension'
                         f' but got "{ext_src}", "{ext_dest}"')

    eeg_file_path, vmrk_file_path = _get_brainvision_paths(vhdr_src)

    # extract encoding from brainvision header file, or default to utf-8
    enc = _get_brainvision_encoding(vhdr_src, verbose)

    # Copy data .eeg ... no links to repair
    sh.copyfile(eeg_file_path, fname_dest + '.eeg')

    # Write new header and marker files, fixing the file pointer links
    # For that, we need to replace an old "basename" with a new one
    # assuming that all .eeg, .vhdr, .vmrk share one basename
    __, basename_src = op.split(fname_src)
    assert basename_src + '.eeg' == op.split(eeg_file_path)[-1]
    assert basename_src + '.vmrk' == op.split(vmrk_file_path)[-1]
    __, basename_dest = op.split(fname_dest)
    search_lines = ['DataFile=' + basename_src + '.eeg',
                    'MarkerFile=' + basename_src + '.vmrk']

    with open(vhdr_src, 'r', encoding=enc) as fin:
        with open(vhdr_dest, 'w', encoding=enc) as fout:
            for line in fin.readlines():
                if line.strip() in search_lines:
                    line = line.replace(basename_src, basename_dest)
                fout.write(line)

    with open(vmrk_file_path, 'r', encoding=enc) as fin:
        with open(fname_dest + '.vmrk', 'w', encoding=enc) as fout:
            for line in fin.readlines():
                if line.strip() in search_lines:
                    line = line.replace(basename_src, basename_dest)
                fout.write(line)

    if anonymize is not None:
        raw = read_raw_brainvision(vhdr_src, preload=False, verbose=0)
        daysback, keep_his = _check_anonymize(anonymize, raw, '.vhdr')
        raw.info = anonymize_info(raw.info, daysback=daysback,
                                  keep_his=keep_his)
        _anonymize_brainvision(fname_dest + '.vhdr',
                               date=raw.info['meas_date'])

    if verbose:
        for ext in ['.eeg', '.vhdr', '.vmrk']:
            _, fname = os.path.split(fname_dest + ext)
            dirname = op.dirname(op.realpath(vhdr_dest))
            print(f'Created "{fname}" in "{dirname}".')
        if anonymize:
            print('Anonymized all dates in VHDR and VMRK.')
예제 #2
0
def copyfile_edf(src, dest, anonymize=None):
    """Copy an EDF, EDF+, or BDF file to a new location, optionally anonymize.

    .. warning:: EDF/EDF+/BDF files contain two fields for recording dates:
                 A generic "startdate" field that supports only 2-digit years,
                 and a "Startdate" field as part of the "local recording
                 identification", which supports 4-digit years.
                 If you want to anonymize your file, MNE-BIDS will set the
                 "startdate" field to 85 (i.e., 1985), the earliest possible
                 date for that field. However, the "Startdate" field in the
                 file's "local recording identification" and the date in the
                 session's corresponding ``scans.tsv`` will be set correctly
                 according to the argument provided to the ``anonymize``
                 parameter. Note that it is possible that not all EDF/EDF+/BDF
                 reading software parses the accurate recording date, and
                 that for some reading software, the wrong year (1985) may
                 be parsed.

    Parameters
    ----------
    src : str | pathlib.Path
        The source path of the .edf or .bdf file to be copied.
    dest : str | pathlib.Path
        The destination path of the .edf or .bdf file.
    anonymize : dict | None
        If None (default), no anonymization is performed.
        If dict, data will be anonymized depending on the keys provided with
        the dict: `daysback` is a required key, `keep_his` is an optional key.

        `daysback` : int
            Number of days by which to move back the recording date in time.
            In studies with multiple subjects the relative recording date
            differences between subjects can be kept by using the same number
            of `daysback` for all subject anonymizations. `daysback` should be
            great enough to shift the date prior to 1925 to conform with BIDS
            anonymization rules. Due to limitations of the EDF/BDF format, the
            year of the anonymized date will always be set to 1985 in the
            'startdate' field of the file. The correctly-shifted year will be
            written to the 'local recording identification' region of the
            file header, which may not be parsed by all EDF/EDF+/BDF reader
            softwares.

        `keep_his` : bool
            By default (False), all subject information next to the recording
            date will be overwritten as well. If True, keep subject information
            apart from the recording date. Participant names and birthdates
            will always be anonymized if present, regardless of this setting.

    See Also
    --------
    mne.io.anonymize_info
    copyfile_brainvision
    copyfile_bti
    copyfile_ctf
    copyfile_eeglab
    copyfile_kit

    """
    # Ensure source & destination extensions are the same
    fname_src, ext_src = _parse_ext(src)
    fname_dest, ext_dest = _parse_ext(dest)
    if ext_src != ext_dest:
        raise ValueError(f'Need to move data with same extension, '
                         f' but got "{ext_src}" and "{ext_dest}"')

    # Copy data prior to any anonymization
    sh.copyfile(src, dest)

    # Anonymize EDF/BDF data, if requested
    if anonymize is not None:
        if ext_src == '.bdf':
            raw = read_raw_bdf(dest, preload=False, verbose=0)
        elif ext_src == '.edf':
            raw = read_raw_edf(dest, preload=False, verbose=0)
        else:
            raise ValueError('Unsupported file type ({0})'.format(ext_src))

        # Get subject info, recording info, and recording date
        with open(dest, 'rb') as f:
            f.seek(8)  # id_info field starts 8 bytes in
            id_info = f.read(80).decode('ascii').rstrip()
            rec_info = f.read(80).decode('ascii').rstrip()

        # Parse metadata from file
        if len(id_info) == 0 or len(id_info.split(' ')) != 4:
            id_info = "X X X X"
        if len(rec_info) == 0 or len(rec_info.split(' ')) != 5:
            rec_info = "Startdate X X X X"
        pid, sex, birthdate, name = id_info.split(' ')
        start_date, admin_code, tech, equip = rec_info.split(' ')[1:5]

        # Try to anonymize the recording date
        daysback, keep_his = _check_anonymize(anonymize, raw, '.edf')
        anonymize_info(raw.info, daysback=daysback, keep_his=keep_his)
        start_date = '01-JAN-1985'
        meas_date = '01.01.85'

        # Anonymize ID info and write to file
        if keep_his:
            # Always remove participant birthdate and name to be safe
            id_info = [pid, sex, "X", "X"]
            rec_info = ["Startdate", start_date, admin_code, tech, equip]
        else:
            id_info = ["0", "X", "X", "X"]
            rec_info = ["Startdate", start_date, "X",
                        "mne-bids_anonymize", "X"]
        with open(dest, 'r+b') as f:
            f.seek(8)  # id_info field starts 8 bytes in
            f.write(bytes(" ".join(id_info).ljust(80), 'ascii'))
            f.write(bytes(" ".join(rec_info).ljust(80), 'ascii'))
            f.write(bytes(meas_date, 'ascii'))