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 test_lines_to_ignore_attribute(self):
""".lines_to_ignore works as documented"""
metaxml_section = r"""
<core encoding="utf-8" fieldsTerminatedBy="\t" linesTerminatedBy="\n" fieldsEnclosedBy="" ignoreHeaderLines="1" rowType="http://rs.tdwg.org/dwc/terms/Occurrence">
<files>
<location>occurrence.txt</location>
</files>
<id index="0" />
<field index="1" term="http://rs.tdwg.org/dwc/terms/basisOfRecord"/>
<field index="2" term="http://rs.tdwg.org/dwc/terms/locality"/>
<field index="3" term="http://rs.tdwg.org/dwc/terms/family"/>
<field index="4" term="http://rs.tdwg.org/dwc/terms/scientificName"/>
</core>
"""
descriptor = DataFileDescriptor.make_from_metafile_section(
ET.fromstring(metaxml_section))
data_file = CSVDataFile(sample_data_path('dwca-simple-dir'),
descriptor)
self.assertEqual(data_file.lines_to_ignore, 1)
metaxml_section = r"""
<core encoding="utf-8" fieldsTerminatedBy="\t" linesTerminatedBy="\n" fieldsEnclosedBy="" ignoreHeaderLines="3" rowType="http://rs.tdwg.org/dwc/terms/Occurrence">
<files>
<location>occurrence.txt</location>
</files>
<id index="0" />
<field index="1" term="http://rs.tdwg.org/dwc/terms/basisOfRecord"/>
<field index="2" term="http://rs.tdwg.org/dwc/terms/locality"/>
<field index="3" term="http://rs.tdwg.org/dwc/terms/family"/>
<field index="4" term="http://rs.tdwg.org/dwc/terms/scientificName"/>
</core>
"""
descriptor = DataFileDescriptor.make_from_metafile_section(
ET.fromstring(metaxml_section))
data_file = CSVDataFile(sample_data_path('dwca-simple-dir'),
descriptor)
self.assertEqual(data_file.lines_to_ignore, 3)
def test_iterate(self):
metaxml_section = r"""
<core encoding="utf-8" fieldsTerminatedBy="\t" linesTerminatedBy="\n" fieldsEnclosedBy="" ignoreHeaderLines="1" rowType="http://rs.tdwg.org/dwc/terms/Occurrence">
<files><location>occurrence.txt</location></files>
<id index="0" />
<field index="1" term="http://rs.tdwg.org/dwc/terms/basisOfRecord"/>
<field index="2" term="http://rs.tdwg.org/dwc/terms/locality"/>
<field index="3" term="http://rs.tdwg.org/dwc/terms/family"/>
<field index="4" term="http://rs.tdwg.org/dwc/terms/scientificName"/>
</core>
"""
descriptor = DataFileDescriptor.make_from_metafile_section(
ET.fromstring(metaxml_section))
data_file = CSVDataFile(sample_data_path("dwca-simple-dir"),
descriptor)
for row in data_file:
self.assertIsInstance(row, str)
def test_close(self):
metaxml_section = r"""
<core encoding="utf-8" fieldsTerminatedBy="\t" linesTerminatedBy="\n" fieldsEnclosedBy="" ignoreHeaderLines="1" rowType="http://rs.tdwg.org/dwc/terms/Occurrence">
<files><location>occurrence.txt</location></files>
<id index="0" />
<field index="1" term="http://rs.tdwg.org/dwc/terms/basisOfRecord"/>
<field index="2" term="http://rs.tdwg.org/dwc/terms/locality"/>
<field index="3" term="http://rs.tdwg.org/dwc/terms/family"/>
<field index="4" term="http://rs.tdwg.org/dwc/terms/scientificName"/>
</core>
"""
descriptor = DataFileDescriptor.make_from_metafile_section(
ET.fromstring(metaxml_section))
data_file = CSVDataFile(DIRECTORY_ARCHIVE_PATH, descriptor)
data_file.close()
with self.assertRaises(ValueError):
# It's not possible anymore to access the data because file has been closed.
data_file.get_row_by_position(1)
def test_file_descriptor_attribute(self):
"""The instance of DataFileDescriptor which is passed to the constructor is available in .file_descriptor"""
metaxml_section = r"""
<core encoding="utf-8" fieldsTerminatedBy="\t" linesTerminatedBy="\n" fieldsEnclosedBy="" ignoreHeaderLines="1" rowType="http://rs.tdwg.org/dwc/terms/Occurrence">
<files>
<location>occurrence.txt</location>
</files>
<id index="0" />
<field index="1" term="http://rs.tdwg.org/dwc/terms/basisOfRecord"/>
<field index="2" term="http://rs.tdwg.org/dwc/terms/locality"/>
<field index="3" term="http://rs.tdwg.org/dwc/terms/family"/>
<field index="4" term="http://rs.tdwg.org/dwc/terms/scientificName"/>
</core>
"""
descriptor = DataFileDescriptor.make_from_metafile_section(
ET.fromstring(metaxml_section))
data_file = CSVDataFile(DIRECTORY_ARCHIVE_PATH, descriptor)
self.assertEqual(data_file.file_descriptor, descriptor)
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)
