def create_videomd_metadata(filename,
filerel=None,
workspace=None,
streams=None):
"""Creates and returns list of videoMD XML sections.
:filename: Video file path
:filerel: Video file path relative to base path
:workspace: Workspace path
:streams: Metadata dict of streams. Will be created if None.
:returns: List of VideoMD XML sections.
"""
if streams is None:
(streams, _) = scrape_file(filepath=filename,
filerel=filerel,
workspace=workspace,
skip_well_check=True)
fix_missing_metadata(streams, filename, ALLOW_UNAV, ALLOW_ZERO)
videomd_dict = {}
for index, stream_md in six.iteritems(streams):
if stream_md['stream_type'] != 'video':
continue
file_data_elem = _get_file_data(stream_md)
videomd_elem = videomd.create_videomd(file_data=file_data_elem)
videomd_dict[six.text_type(index)] = videomd_elem
if not videomd_dict:
print('The file has no video streams. No VideoMD metadata created.')
return None
return videomd_dict
def create_mix_metadata(filename, filerel=None, workspace=None):
"""Create MIX metadata XML element for an image file.
:image: image file
:returns: MIX XML element
"""
streams = scrape_file(filename, filerel=filerel, workspace=workspace)
stream_md = streams[0]
check_missing_metadata(stream_md, filename)
if stream_md['stream_type'] != 'image':
print("This is not an image file. No MIX metadata created.")
return None
if len(streams) > 1:
raise MixGenerationError(
'File containing multiple images not supported. File: ', filename)
mix_compression = nisomix.compression(
compression_scheme=stream_md["compression"])
if 'byte_order' not in stream_md:
if stream_md['mimetype'] == 'image/tiff':
raise MixGenerationError(
'Byte order missing from TIFF image file ', filename)
byte_order = None
else:
byte_order = stream_md["byte_order"]
basic_do_info = nisomix.digital_object_information(
byte_order=byte_order, child_elements=[mix_compression])
photom_interpret = nisomix.photometric_interpretation(
color_space=stream_md["colorspace"])
img_characteristics = nisomix.image_characteristics(
width=stream_md["width"],
height=stream_md["height"],
child_elements=[photom_interpret])
img_info = nisomix.image_information(child_elements=[img_characteristics])
bit_depth = nisomix.bits_per_sample(sample_values=stream_md["bps_value"],
sample_unit=stream_md["bps_unit"])
color_encoding = nisomix.color_encoding(
samples_pixel=stream_md["samples_per_pixel"],
child_elements=[bit_depth])
img_assessment = nisomix.image_assessment_metadata(
child_elements=[color_encoding])
mix_root = nisomix.mix(
child_elements=[basic_do_info, img_info, img_assessment])
if mix_root is None:
raise MixGenerationError('Image info could not be constructed.')
return mix_root
def add_premis_md(
self, filepath, attributes, filerel=None, properties=None):
"""
Create metadata for PREMIS metadata. This method:
- Scrapes a file
- Creates PREMIS metadata with amd references for a file
- Creates PREMIS metadata with amd references for streams in a file
- Returns stream dict from scraper
:filepath: Full path to file (including base_path)
:attributes: The following keys
skip_wellformed_check: True skips well-formedness checking
charset: Character encoding of a file,
file_format: File format and version (tuple) of a file,
format_registry: Format registry name and value (tuple),
identifier: File identifier type and value (tuple),
checksum: Checksum algorithm and value (tuple),
date_created: Creation date of a file
:filerel: Relative path from base_path to file
:returns: Stream dict and info dict from file-scraper as a tuple
"""
if not attributes["file_format"]:
mimetype = None
version = None
else:
mimetype = attributes["file_format"][0]
version = attributes["file_format"][1]
(streams, info) = scrape_file(
filepath=filepath,
skip_well_check=attributes["skip_wellformed_check"],
mimetype=mimetype,
version=version,
charset=attributes["charset"],
skip_json=True
)
# Add new properties of a file for other script files, e.g. structMap
if properties:
streams[0]['properties'] = properties
premis_elem = create_premis_object(filepath, streams, **attributes)
self.add_md(premis_elem, filerel, given_metadata_dict=streams)
premis_list = create_streams(streams, premis_elem)
if premis_list is not None:
for index, premis_stream in six.iteritems(premis_list):
self.add_md(
premis_stream, filerel, index, given_metadata_dict=streams)
return (streams, info)
def create_videomd_metadata(filename, filerel=None, workspace=None):
"""Creates and returns list of videoMD XML sections.
:filename: Audio file path
:returns: List of VideoMD XML sections.
"""
streams = scrape_file(filename, filerel=filerel, workspace=workspace)
fix_missing_metadata(streams, filename, ALLOW_UNAV, ALLOW_ZERO)
videomd_dict = {}
for index, stream_md in six.iteritems(streams):
if stream_md['stream_type'] != 'video':
continue
file_data_elem = _get_file_data(stream_md)
videomd_elem = videomd.create_videomd(file_data=file_data_elem)
videomd_dict[six.text_type(index)] = videomd_elem
if not videomd_dict:
raise ValueError('Video stream info could not be constructed.')
return videomd_dict
def create_audiomd_metadata(filename,
filerel=None,
workspace=None,
streams=None):
"""Creates and returns list of audioMD XML sections.
:filename: Audio file path
:filrel: Audio file path relative to base path
:workspace: Workspace path
:streams: Metadata dict of streams. Will be created if None.
:returns: Dict of AudioMD XML sections.
"""
if streams is None:
(streams, _) = scrape_file(filepath=filename,
filerel=filerel,
workspace=workspace,
skip_well_check=True)
fix_missing_metadata(streams, filename, ALLOW_UNAV, ALLOW_ZERO)
audiomd_dict = {}
for index, stream_md in six.iteritems(streams):
if stream_md['stream_type'] != 'audio':
continue
stream_md = _fix_data_rate(stream_md)
file_data_elem = _get_file_data(stream_md)
audio_info_elem = _get_audio_info(stream_md)
audiomd_elem = audiomd.create_audiomd(file_data=file_data_elem,
audio_info=audio_info_elem)
audiomd_dict[six.text_type(index)] = audiomd_elem
if not audiomd_dict:
print('The file has no audio streams. No AudioMD metadata created.')
return None
return audiomd_dict