def __init__(self, path, extensions_to_ignore=None):
"""Open the Darwin Core Archive."""
if extensions_to_ignore is None:
extensions_to_ignore = []
#: The path to the Darwin Core Archive file, as passed to the constructor.
self.archive_path = path
if os.path.isdir(self.archive_path
): # Archive is a (directly readable) directory
self._workin_directory_path = self.archive_path
self._directory_to_clean = None
else: # Archive is zipped/tgzipped, we have to extract it first.
self._directory_to_clean, self._workin_directory_path = self._extract(
)
#: An :class:`descriptors.ArchiveDescriptor` instance giving access to the archive
#: descriptor/metafile (``meta.xml``)
try:
self.descriptor = ArchiveDescriptor(
self.open_included_file(METAFILE_NAME).read(),
files_to_ignore=extensions_to_ignore)
except IOError as exc:
if exc.errno == ENOENT:
self.descriptor = None
#: A :class:`xml.etree.ElementTree.Element` instance containing the (scientific) metadata
#: of the archive, or None if the Archive contains no metadata.
self.metadata = self._parse_metadata_file()
#: If the archive contains source metadata (typically, GBIF downloads) this dict will
#: be something like:
#: {'dataset1_UUID': <dataset1 EML (xml.etree.ElementTree.Element instance)>,
#: 'dataset2_UUID': <dataset2 EML (xml.etree.ElementTree.Element instance)>, ...}
#: see :doc:`gbif_results` for more details.
self.source_metadata = self._load_source_metadata()
if self.descriptor:
# We have an Archive descriptor that we can use to access data files.
self._corefile = CSVDataFile(self._workin_directory_path,
self.descriptor.core)
self._extensionfiles = [
CSVDataFile(work_directory=self._workin_directory_path,
file_descriptor=d)
for d in self.descriptor.extensions
]
else: # Archive without descriptor, we'll have to find and inspect the data file
try:
datafile_name = self._is_valid_simple_archive()
descriptor = DataFileDescriptor.make_from_file(
os.path.join(self._workin_directory_path, datafile_name))
self._corefile = CSVDataFile(
work_directory=self._workin_directory_path,
file_descriptor=descriptor)
self._extensionfiles = []
except InvalidSimpleArchive:
msg = "No metafile was found, but archive includes multiple files/directories."
raise InvalidSimpleArchive(msg)
def _is_valid_simple_archive(self) -> str:
# If the working dir appear to contains a valid simple darwin core archive
# (one single data file + possibly some metadata), returns the name of the data file.
#
# Otherwise, throws an InvalidSimpleArchive exception.
_, _, files = next(os.walk(self._working_directory_path))
if len(files) == 1:
return files[0] # A single file, so that's the one
elif len(files) == 2:
# Two files found: if one of them is EML.xml, the other is considered as the data file
if self.default_metadata_filename in files:
return [f for f in files if f != self.default_metadata_filename][0]
raise InvalidSimpleArchive()
def _is_valid_simple_archive(self):
# If the working dir appear to contains a valid simple darwin core archive
# (one single data file + possibly some metadata), returns the name of the data file.
#
# Otherwise, throws an InvalidSimpleArchive exception.
_, _, files = next(os.walk(self._workin_directory_path))
if len(files) == 1: # We found a single file
return files[0]
elif len(files) == 2:
# Two files found: if one of them is EML.xml, the other is considered as the data file
if DEFAULT_METADATA_FILENAME in files:
return [
f for f in files if f is not DEFAULT_METADATA_FILENAME
][0]
raise InvalidSimpleArchive()
def __init__(self, path, extensions_to_ignore=None):
# type: (str, List[str]) -> None
"""Open the Darwin Core Archive."""
if extensions_to_ignore is None:
extensions_to_ignore = []
#: The path to the Darwin Core Archive file, as passed to the constructor.
self.archive_path = path # type: str
if os.path.isdir(self.archive_path
): # Archive is a (directly readable) directory
self._working_directory_path = self.archive_path
self._directory_to_clean = None # type: Optional[str]
else: # Archive is zipped/tgzipped, we have to extract it first.
self._directory_to_clean, self._working_directory_path = self._extract(
)
#: An :class:`descriptors.ArchiveDescriptor` instance giving access to the archive
#: descriptor/metafile (``meta.xml``)
self.descriptor = None # type: Optional[ArchiveDescriptor]
try:
self.descriptor = ArchiveDescriptor(
self.open_included_file(self.default_metafile_name).read(),
files_to_ignore=extensions_to_ignore)
except IOError as exc:
if exc.errno == ENOENT:
pass
#: A :class:`xml.etree.ElementTree.Element` instance containing the (scientific) metadata
#: of the archive, or `None` if the archive has no metadata.
self.metadata = self._parse_metadata_file() # type: Optional[Element]
#: If the archive contains source-level metadata (typically, GBIF downloads), this is a dict such as::
#:
#: {'dataset1_UUID': <dataset1 EML> (xml.etree.ElementTree.Element object),
#: 'dataset2_UUID': <dataset2 EML> (xml.etree.ElementTree.Element object), ...}
#:
#: See :doc:`gbif_results` for more details.
self.source_metadata = self._get_source_metadata(
) # type: Dict[str, Element]
if self.descriptor: # We have an Archive descriptor that we can use to access data files.
#: An instance of :class:`dwca.files.CSVDataFile` for the core data file.
self.core_file = CSVDataFile(
self._working_directory_path,
self.descriptor.core) # type: CSVDataFile
#: A list of :class:`dwca.files.CSVDataFile`, one entry for each extension data file , sorted by order of
#: appearance in the Metafile (or an empty list if the archive doesn't use extensions).
self.extension_files = [
CSVDataFile(work_directory=self._working_directory_path,
file_descriptor=d)
for d in self.descriptor.extensions
] # type: List[CSVDataFile]
else: # Archive without descriptor, we'll have to find and inspect the data file
try:
datafile_name = self._is_valid_simple_archive()
descriptor = DataFileDescriptor.make_from_file(
os.path.join(self._working_directory_path, datafile_name))
self.core_file = CSVDataFile(
work_directory=self._working_directory_path,
file_descriptor=descriptor)
self.extension_files = []
except InvalidSimpleArchive:
msg = "No Metafile was found, but the archive contains multiple files/directories."
raise InvalidSimpleArchive(msg)