python-dwca-reader 0.16.2__tar.gz → 0.16.3__tar.gz

{python-dwca-reader-0.16.2 → python-dwca-reader-0.16.3}/CHANGES.txt

@@ -1,4 +1,10 @@
+v0.16.3 (2024-10-18)
+--------------------
+
+- Added a new `skip_metadata` parameter to the `DwCAReader` constructor. When set to `True`, the metadata file is not read. This can be useful for example if the metadata is corrupt (invalid XML) and you don't need it.
+
 v0.16.2 (2024-08-23)
+--------------------
 
 - Fix a packaging issue that prevented the release of v0.16.1 on PyPI.
 

{python-dwca-reader-0.16.2 → python-dwca-reader-0.16.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: python-dwca-reader
-Version: 0.16.2
+Version: 0.16.3
 Summary: A simple Python package to read Darwin Core Archive (DwC-A) files.
 Home-page: https://github.com/BelgianBiodiversityPlatform/python-dwca-reader
 Author: Nicolas Noé - Belgian Biodiversity Platform

{python-dwca-reader-0.16.2 → python-dwca-reader-0.16.3}/dwca/darwincore/build_dc_terms_list.py

@@ -11,12 +11,14 @@
 import argparse
 import xml.etree.ElementTree as ET
 
-parser = argparse.ArgumentParser(description="Generate a list of qualnames "
-                                             "of Darwin Core terms from XML "
-                                             "description files.")
+parser = argparse.ArgumentParser(
+    description="Generate a list of qualnames "
+    "of Darwin Core terms from XML "
+    "description files."
+)
 
 # Required positional argument: one or more XML files to be read
-parser.add_argument('source_xml', nargs='+', type=argparse.FileType('r'))
+parser.add_argument("source_xml", nargs="+", type=argparse.FileType("r"))
 parser.parse_args()
 args = parser.parse_args()
 
@@ -26,11 +28,11 @@ qualnames = set()
 for source_file in args.source_xml:
     root = ET.parse(source_file).getroot()
     # First, extract the RowType itself... (Occcurrence, Taxon, ...)
-    qualnames.add(root.get('rowType'))
+    qualnames.add(root.get("rowType"))
 
     # Store each qualname found in any tag to our set
     for ch in root.iter():
-        qn = ch.get('qualName')
+        qn = ch.get("qualName")
         if qn:
             qualnames.add(qn)
 

python-dwca-reader-0.16.3/dwca/darwincore/terms.py

@@ -0,0 +1,171 @@
+TERMS = [
+    "http://rs.tdwg.org/dwc/terms/occurrenceDetails",
+    "http://rs.tdwg.org/dwc/terms/highestBiostratigraphicZone",
+    "http://rs.tdwg.org/dwc/terms/associatedTaxa",
+    "http://rs.tdwg.org/dwc/terms/latestEpochOrHighestSeries",
+    "http://rs.tdwg.org/dwc/terms/informationWithheld",
+    "http://rs.tdwg.org/dwc/terms/minimumDistanceAboveSurfaceInMeters",
+    "http://rs.tdwg.org/dwc/terms/behavior",
+    "http://rs.tdwg.org/dwc/terms/verbatimLongitude",
+    "http://rs.tdwg.org/dwc/terms/countryCode",
+    "http://rs.tdwg.org/dwc/terms/associatedSequences",
+    "http://rs.tdwg.org/dwc/terms/habitat",
+    "http://rs.tdwg.org/dwc/terms/islandGroup",
+    "http://rs.tdwg.org/dwc/terms/nomenclaturalCode",
+    "http://purl.org/dc/terms/license",
+    "http://rs.tdwg.org/dwc/terms/earliestEonOrLowestEonothem",
+    "http://rs.tdwg.org/dwc/terms/year",
+    "http://rs.tdwg.org/dwc/terms/taxonID",
+    "http://rs.tdwg.org/dwc/terms/continent",
+    "http://rs.tdwg.org/dwc/terms/nameAccordingTo",
+    "http://rs.tdwg.org/dwc/terms/latestEraOrHighestErathem",
+    "http://rs.tdwg.org/dwc/terms/eventID",
+    "http://rs.tdwg.org/dwc/terms/nameAccordingToID",
+    "http://rs.tdwg.org/dwc/terms/decimalLongitude",
+    "http://rs.tdwg.org/dwc/terms/sampleSizeValue",
+    "http://rs.tdwg.org/dwc/terms/identifiedBy",
+    "http://rs.tdwg.org/dwc/terms/latestEonOrHighestEonothem",
+    "http://rs.tdwg.org/dwc/terms/catalogNumber",
+    "http://rs.tdwg.org/dwc/terms/eventRemarks",
+    "http://rs.tdwg.org/dwc/terms/taxonRank",
+    "http://rs.tdwg.org/dwc/terms/verbatimDepth",
+    "http://rs.tdwg.org/dwc/terms/originalNameUsageID",
+    "http://purl.org/dc/terms/rightsHolder",
+    "http://rs.tdwg.org/dwc/terms/lowestBiostratigraphicZone",
+    "http://purl.org/dc/terms/bibliographicCitation",
+    "http://rs.tdwg.org/dwc/terms/island",
+    "http://rs.tdwg.org/dwc/terms/associatedMedia",
+    "http://rs.tdwg.org/dwc/terms/group",
+    "http://rs.tdwg.org/dwc/terms/endDayOfYear",
+    "http://rs.tdwg.org/dwc/terms/individualCount",
+    "http://rs.tdwg.org/dwc/terms/occurrenceRemarks",
+    "http://rs.tdwg.org/dwc/terms/disposition",
+    "http://rs.tdwg.org/dwc/terms/collectionID",
+    "http://rs.tdwg.org/dwc/terms/sampleSizeUnit",
+    "http://rs.tdwg.org/dwc/terms/earliestPeriodOrLowestSystem",
+    "http://rs.tdwg.org/dwc/terms/county",
+    "http://rs.tdwg.org/dwc/terms/eventDate",
+    "http://rs.tdwg.org/dwc/terms/earliestEpochOrLowestSeries",
+    "http://rs.tdwg.org/dwc/terms/formation",
+    "http://rs.tdwg.org/dwc/terms/Taxon",
+    "http://purl.org/dc/terms/references",
+    "http://purl.org/dc/terms/language",
+    "http://rs.tdwg.org/dwc/terms/decimalLatitude",
+    "http://rs.tdwg.org/dwc/terms/startDayOfYear",
+    "http://rs.tdwg.org/dwc/terms/fieldNotes",
+    "http://rs.tdwg.org/dwc/terms/municipality",
+    "http://rs.tdwg.org/dwc/terms/namePublishedInYear",
+    "http://rs.tdwg.org/dwc/terms/associatedReferences",
+    "http://rs.tdwg.org/dwc/terms/georeferenceVerificationStatus",
+    "http://rs.tdwg.org/dwc/terms/datasetName",
+    "http://rs.tdwg.org/dwc/terms/locality",
+    "http://rs.tdwg.org/dwc/terms/identificationID",
+    "http://purl.org/dc/terms/type",
+    "http://rs.tdwg.org/dwc/terms/scientificNameID",
+    "http://rs.tdwg.org/dwc/terms/verbatimLatitude",
+    "http://rs.tdwg.org/dwc/terms/occurrenceID",
+    "http://rs.tdwg.org/dwc/terms/verbatimTaxonRank",
+    "http://rs.tdwg.org/dwc/terms/verbatimSRS",
+    "http://rs.tdwg.org/dwc/terms/order",
+    "http://rs.tdwg.org/dwc/terms/georeferenceProtocol",
+    "http://rs.tdwg.org/dwc/terms/locationAccordingTo",
+    "http://rs.tdwg.org/dwc/terms/originalNameUsage",
+    "http://rs.tdwg.org/dwc/terms/geodeticDatum",
+    "http://rs.tdwg.org/dwc/terms/Occurrence",
+    "http://rs.tdwg.org/dwc/terms/establishmentMeans",
+    "http://rs.tdwg.org/dwc/terms/parentNameUsage",
+    "http://rs.tdwg.org/dwc/terms/taxonRemarks",
+    "http://rs.tdwg.org/dwc/terms/footprintSRS",
+    "http://rs.tdwg.org/dwc/terms/collectionCode",
+    "http://rs.tdwg.org/dwc/terms/class",
+    "http://rs.tdwg.org/dwc/terms/family",
+    "http://rs.tdwg.org/dwc/terms/footprintWKT",
+    "http://rs.tdwg.org/dwc/terms/georeferenceRemarks",
+    "http://rs.tdwg.org/dwc/terms/lithostratigraphicTerms",
+    "http://rs.tdwg.org/dwc/terms/geologicalContextID",
+    "http://rs.tdwg.org/dwc/terms/dateIdentified",
+    "http://rs.tdwg.org/dwc/terms/higherGeographyID",
+    "http://rs.tdwg.org/dwc/terms/pointRadiusSpatialFit",
+    "http://rs.tdwg.org/dwc/terms/dynamicProperties",
+    "http://rs.tdwg.org/dwc/terms/verbatimLocality",
+    "http://purl.org/dc/terms/modified",
+    "http://rs.tdwg.org/dwc/terms/month",
+    "http://rs.tdwg.org/dwc/terms/earliestEraOrLowestErathem",
+    "http://rs.tdwg.org/dwc/terms/samplingProtocol",
+    "http://rs.tdwg.org/dwc/terms/infraspecificEpithet",
+    "http://rs.tdwg.org/dwc/terms/footprintSpatialFit",
+    "http://rs.tdwg.org/dwc/terms/namePublishedIn",
+    "http://rs.tdwg.org/dwc/terms/georeferenceSources",
+    "http://rs.tdwg.org/dwc/terms/identificationRemarks",
+    "http://rs.tdwg.org/dwc/terms/taxonConceptID",
+    "http://purl.org/dc/terms/accessRights",
+    "http://rs.tdwg.org/dwc/terms/lifeStage",
+    "http://rs.tdwg.org/dwc/terms/acceptedNameUsage",
+    "http://rs.tdwg.org/dwc/terms/verbatimEventDate",
+    "http://rs.tdwg.org/dwc/terms/typeStatus",
+    "http://rs.tdwg.org/dwc/terms/maximumDepthInMeters",
+    "http://rs.tdwg.org/dwc/terms/preparations",
+    "http://rs.tdwg.org/dwc/terms/georeferencedDate",
+    "http://rs.tdwg.org/dwc/terms/institutionID",
+    "http://rs.tdwg.org/dwc/terms/verbatimCoordinates",
+    "http://rs.tdwg.org/dwc/terms/vernacularName",
+    "http://rs.tdwg.org/dwc/terms/bed",
+    "http://rs.tdwg.org/dwc/terms/materialSampleID",
+    "http://rs.tdwg.org/dwc/terms/maximumElevationInMeters",
+    "http://purl.org/dc/terms/rights",
+    "http://rs.tdwg.org/dwc/terms/scientificName",
+    "http://rs.tdwg.org/dwc/terms/identificationReferences",
+    "http://rs.tdwg.org/dwc/terms/day",
+    "http://rs.tdwg.org/dwc/terms/fieldNumber",
+    "http://rs.tdwg.org/dwc/terms/parentNameUsageID",
+    "http://rs.tdwg.org/dwc/terms/acceptedNameUsageID",
+    "http://rs.tdwg.org/dwc/terms/identificationQualifier",
+    "http://rs.tdwg.org/dwc/terms/dataGeneralizations",
+    "http://rs.tdwg.org/dwc/terms/sex",
+    "http://rs.tdwg.org/dwc/terms/previousIdentifications",
+    "http://rs.tdwg.org/dwc/terms/georeferencedBy",
+    "http://rs.tdwg.org/dwc/terms/latestPeriodOrHighestSystem",
+    "http://rs.tdwg.org/dwc/terms/kingdom",
+    "http://rs.tdwg.org/dwc/terms/basisOfRecord",
+    "http://rs.tdwg.org/dwc/terms/institutionCode",
+    "http://rs.tdwg.org/dwc/terms/verbatimCoordinateSystem",
+    "http://rs.tdwg.org/dwc/terms/waterBody",
+    "http://rs.tdwg.org/dwc/terms/phylum",
+    "http://rs.tdwg.org/dwc/terms/ownerInstitutionCode",
+    "http://rs.tdwg.org/dwc/terms/latestAgeOrHighestStage",
+    "http://rs.tdwg.org/dwc/terms/occurrenceStatus",
+    "http://rs.tdwg.org/dwc/terms/higherClassification",
+    "http://purl.org/dc/terms/source",
+    "http://rs.tdwg.org/dwc/terms/recordedBy",
+    "http://rs.tdwg.org/dwc/terms/datasetID",
+    "http://rs.tdwg.org/dwc/terms/minimumElevationInMeters",
+    "http://rs.tdwg.org/dwc/terms/individualID",
+    "http://rs.tdwg.org/dwc/terms/samplingEffort",
+    "http://rs.tdwg.org/dwc/terms/Event",
+    "http://rs.tdwg.org/dwc/terms/member",
+    "http://rs.tdwg.org/dwc/terms/scientificNameAuthorship",
+    "http://rs.tdwg.org/dwc/terms/locationID",
+    "http://rs.tdwg.org/dwc/terms/higherGeography",
+    "http://rs.tdwg.org/dwc/terms/genus",
+    "http://rs.tdwg.org/dwc/terms/associatedOccurrences",
+    "http://rs.tdwg.org/dwc/terms/verbatimElevation",
+    "http://rs.tdwg.org/dwc/terms/maximumDistanceAboveSurfaceInMeters",
+    "http://rs.tdwg.org/dwc/terms/minimumDepthInMeters",
+    "http://rs.tdwg.org/dwc/terms/stateProvince",
+    "http://rs.tdwg.org/dwc/terms/nomenclaturalStatus",
+    "http://rs.tdwg.org/dwc/terms/taxonomicStatus",
+    "http://rs.tdwg.org/dwc/terms/specificEpithet",
+    "http://rs.tdwg.org/dwc/terms/parentEventID",
+    "http://rs.tdwg.org/dwc/terms/subgenus",
+    "http://rs.tdwg.org/dwc/terms/coordinatePrecision",
+    "http://rs.tdwg.org/dwc/terms/eventTime",
+    "http://rs.tdwg.org/dwc/terms/country",
+    "http://rs.tdwg.org/dwc/terms/coordinateUncertaintyInMeters",
+    "http://rs.tdwg.org/dwc/terms/identificationVerificationStatus",
+    "http://rs.tdwg.org/dwc/terms/otherCatalogNumbers",
+    "http://rs.tdwg.org/dwc/terms/earliestAgeOrLowestStage",
+    "http://rs.tdwg.org/dwc/terms/recordNumber",
+    "http://rs.tdwg.org/dwc/terms/reproductiveCondition",
+    "http://rs.tdwg.org/dwc/terms/locationRemarks",
+    "http://rs.tdwg.org/dwc/terms/namePublishedInID",
+]

{python-dwca-reader-0.16.2 → python-dwca-reader-0.16.3}/dwca/darwincore/utils.py

@@ -29,4 +29,4 @@ def qualname(short_term):
 
     """
 
-    return next(t for t in TERMS if t.endswith('/' + short_term))
+    return next(t for t in TERMS if t.endswith("/" + short_term))

{python-dwca-reader-0.16.2 → python-dwca-reader-0.16.3}/dwca/descriptors.py

@@ -28,21 +28,21 @@ class DataFileDescriptor(object):
         * :meth:`make_from_file` (created by analyzing the data file)
     """
 
-    def __init__(self,
-                 created_from_file: bool,
-                 raw_element: Element,
-                 represents_corefile: bool,
-                 datafile_type: Optional[str],
-                 file_location: str,
-                 file_encoding: str,
-                 id_index: int,
-                 coreid_index: int,
-                 fields: List[Dict],
-                 lines_terminated_by: str,
-                 fields_enclosed_by: str,
-                 fields_terminated_by: str
-                 ) -> None:
-
+    def __init__(
+        self,
+        created_from_file: bool,
+        raw_element: Element,
+        represents_corefile: bool,
+        datafile_type: Optional[str],
+        file_location: str,
+        file_encoding: str,
+        id_index: int,
+        coreid_index: int,
+        fields: List[Dict],
+        lines_terminated_by: str,
+        fields_enclosed_by: str,
+        fields_terminated_by: str,
+    ) -> None:
         #: True if this descriptor was created by analyzing the data file.
         self.created_from_file = created_from_file
         #: The <section> element describing the data file, from the metafile. None if the
@@ -108,7 +108,7 @@ class DataFileDescriptor(object):
         """
         file_encoding = "utf-8"
 
-        with io.open(datafile_path, 'r', encoding=file_encoding) as datafile:
+        with io.open(datafile_path, "r", encoding=file_encoding) as datafile:
             # Autodetect fields/lines termination
             dialect = csv.Sniffer().sniff(datafile.readline())
 
@@ -126,21 +126,26 @@ class DataFileDescriptor(object):
             columns = next(dr)
 
             fields = [
-                {'index': i, 'term': column, 'default': None} for i, column in enumerate(columns)
+                {"index": i, "term": column, "default": None}
+                for i, column in enumerate(columns)
             ]
 
-        return cls(created_from_file=True,
-                   raw_element=None,  # No metafile, so no XML section to store
-                   represents_corefile=True,  # In archives w/o metafiles, there's only core data
-                   datafile_type=None,  # No metafile => no rowType information
-                   file_location=os.path.basename(datafile_path),  # datafile_path also has the dir
-                   file_encoding=file_encoding,
-                   id_index=None,
-                   coreid_index=None,
-                   fields=fields,
-                   lines_terminated_by=lines_terminated_by,
-                   fields_enclosed_by=fields_enclosed_by,
-                   fields_terminated_by=fields_terminated_by)
+        return cls(
+            created_from_file=True,
+            raw_element=None,  # No metafile, so no XML section to store
+            represents_corefile=True,  # In archives w/o metafiles, there's only core data
+            datafile_type=None,  # No metafile => no rowType information
+            file_location=os.path.basename(
+                datafile_path
+            ),  # datafile_path also has the dir
+            file_encoding=file_encoding,
+            id_index=None,
+            coreid_index=None,
+            fields=fields,
+            lines_terminated_by=lines_terminated_by,
+            fields_enclosed_by=fields_enclosed_by,
+            fields_terminated_by=fields_terminated_by,
+        )
 
     @classmethod
     def make_from_metafile_section(cls, section_tag):
@@ -149,56 +154,66 @@ class DataFileDescriptor(object):
         :param section_tag: The XML Element section containing details about the data file.
         :type section_tag: :class:`xml.etree.ElementTree.Element`
         """
-        if section_tag.tag == 'core':
-            id_index = int(section_tag.find('id').get('index'))
+        if section_tag.tag == "core":
+            id_index = int(section_tag.find("id").get("index"))
             coreid_index = None
         else:
             id_index = None
-            coreid_index = int(section_tag.find('coreid').get('index'))
+            coreid_index = int(section_tag.find("coreid").get("index"))
 
         fields = []
-        for field_tag in section_tag.findall('field'):
-            default = field_tag.get('default', None)
+        for field_tag in section_tag.findall("field"):
+            default = field_tag.get("default", None)
 
             # Default fields don't have an index attribute
-            index = (int(field_tag.get('index')) if field_tag.get('index') else None)
-
-            fields.append({'term': field_tag.get('term'), 'index': index, 'default': default})
-
-        file_encoding = section_tag.get('encoding')
-
-        lines_terminated_by = _decode_xml_attribute(raw_element=section_tag,
-                                                    attribute_name='linesTerminatedBy',
-                                                    default_value='\n',
-                                                    encoding=file_encoding)
-
-        fields_terminated_by = _decode_xml_attribute(raw_element=section_tag,
-                                                     attribute_name='fieldsTerminatedBy',
-                                                     default_value='\t',
-                                                     encoding=file_encoding)
-
-        fields_enclosed_by = _decode_xml_attribute(raw_element=section_tag,
-                                                   attribute_name='fieldsEnclosedBy',
-                                                   default_value='',
-                                                   encoding=file_encoding)
-
-        return cls(created_from_file=False,
-                   raw_element=section_tag,
-                   represents_corefile=(section_tag.tag == 'core'),
-                   datafile_type=section_tag.get('rowType'),
-                   file_location=section_tag.find('files').find('location').text,
-                   file_encoding=file_encoding,
-                   id_index=id_index,
-                   coreid_index=coreid_index,
-                   fields=fields,
-                   lines_terminated_by=lines_terminated_by,
-                   fields_enclosed_by=fields_enclosed_by,
-                   fields_terminated_by=fields_terminated_by)
+            index = int(field_tag.get("index")) if field_tag.get("index") else None
+
+            fields.append(
+                {"term": field_tag.get("term"), "index": index, "default": default}
+            )
+
+        file_encoding = section_tag.get("encoding")
+
+        lines_terminated_by = _decode_xml_attribute(
+            raw_element=section_tag,
+            attribute_name="linesTerminatedBy",
+            default_value="\n",
+            encoding=file_encoding,
+        )
+
+        fields_terminated_by = _decode_xml_attribute(
+            raw_element=section_tag,
+            attribute_name="fieldsTerminatedBy",
+            default_value="\t",
+            encoding=file_encoding,
+        )
+
+        fields_enclosed_by = _decode_xml_attribute(
+            raw_element=section_tag,
+            attribute_name="fieldsEnclosedBy",
+            default_value="",
+            encoding=file_encoding,
+        )
+
+        return cls(
+            created_from_file=False,
+            raw_element=section_tag,
+            represents_corefile=(section_tag.tag == "core"),
+            datafile_type=section_tag.get("rowType"),
+            file_location=section_tag.find("files").find("location").text,
+            file_encoding=file_encoding,
+            id_index=id_index,
+            coreid_index=coreid_index,
+            fields=fields,
+            lines_terminated_by=lines_terminated_by,
+            fields_enclosed_by=fields_enclosed_by,
+            fields_terminated_by=fields_terminated_by,
+        )
 
     @property
     def terms(self) -> Set[str]:
         """Return a Python set containing all the Darwin Core terms appearing in file."""
-        return set([f['term'] for f in self.fields])
+        return set([f["term"] for f in self.fields])
 
     @property
     def headers(self) -> List[str]:
@@ -214,14 +229,16 @@ class DataFileDescriptor(object):
         columns = {}
 
         for f in self.fields:
-            if f['index']:  # Some (default values for example) don't have a corresponding col.
-                columns[f['index']] = f['term']
+            if f[
+                "index"
+            ]:  # Some (default values for example) don't have a corresponding col.
+                columns[f["index"]] = f["term"]
 
         # In addition to DwC terms, we may also have id (Core) or core_id (Extensions) columns
         if self.id_index is not None:
-            columns[self.id_index] = 'id'
+            columns[self.id_index] = "id"
         if self.coreid_index is not None:
-            columns[self.coreid_index] = 'coreid'
+            columns[self.coreid_index] = "coreid"
 
         return [columns[f] for f in sorted(columns.keys())]
 
@@ -244,7 +261,7 @@ class DataFileDescriptor(object):
             # Single-file archives always have a header line with DwC terms
             return 1
 
-        return int(self.raw_element.get('ignoreHeaderLines', 0))
+        return int(self.raw_element.get("ignoreHeaderLines", 0))
 
 
 class ArchiveDescriptor(object):
@@ -255,29 +272,35 @@ class ArchiveDescriptor(object):
             files_to_ignore = []
 
         # Let's drop the XML namespace to avoid prefixes
-        metaxml_content = re.sub(' xmlns="[^"]+"', '', metaxml_content, count=1)
+        metaxml_content = re.sub(' xmlns="[^"]+"', "", metaxml_content, count=1)
 
         #: A :class:`xml.etree.ElementTree.Element` instance containing the complete Archive Descriptor.
         self.raw_element = ET.fromstring(metaxml_content)  # type: Element
 
         #: The path (relative to archive root) of the (scientific) metadata of the archive.
-        self.metadata_filename = self.raw_element.get('metadata', None)
+        self.metadata_filename = self.raw_element.get("metadata", None)
 
         #: An instance of :class:`dwca.descriptors.DataFileDescriptor` describing the core data file.
-        raw_core_element = self.raw_element.find('core')
-        self.core = DataFileDescriptor.make_from_metafile_section(raw_core_element)  # type: DataFileDescriptor
+        raw_core_element = self.raw_element.find("core")
+        self.core = DataFileDescriptor.make_from_metafile_section(
+            raw_core_element
+        )  # type: DataFileDescriptor
 
         #: A list of :class:`dwca.descriptors.DataFileDescriptor` instances describing each of the archive's extension
         #: data files.
         self.extensions = []  # type: List[DataFileDescriptor]
-        for extension_tag in self.raw_element.findall('extension'):  # type: Element
-            location_tag = extension_tag.find('./files/location')
+        for extension_tag in self.raw_element.findall("extension"):  # type: Element
+            location_tag = extension_tag.find("./files/location")
             if location_tag is not None:
                 extension_filename = location_tag.text
                 if extension_filename not in files_to_ignore:
-                    self.extensions.append(DataFileDescriptor.make_from_metafile_section(extension_tag))
+                    self.extensions.append(
+                        DataFileDescriptor.make_from_metafile_section(extension_tag)
+                    )
             else:
-                raise InvalidArchive("An extension file is referenced in Metafile, but its path is not specified.")
+                raise InvalidArchive(
+                    "An extension file is referenced in Metafile, but its path is not specified."
+                )
 
         #: A list of extension (types) in use in the archive.
         #:

{python-dwca-reader-0.16.2 → python-dwca-reader-0.16.3}/dwca/files.py

@@ -79,7 +79,7 @@ class CSVDataFile(object):
         raise StopIteration
 
     @property
-    def coreid_index(self)  -> Dict[str, array]:
+    def coreid_index(self) -> Dict[str, array]:
         """An index of the core rows referenced by this data file.
 
         It is a Python dict such as:
@@ -110,11 +110,11 @@ class CSVDataFile(object):
 
         for position, row in enumerate(self):
             if self.file_descriptor.represents_corefile:
-              tmp = CoreRow(row, position, self.file_descriptor)
-              index.setdefault(tmp.id, array('L')).append(position)
+                tmp = CoreRow(row, position, self.file_descriptor)
+                index.setdefault(tmp.id, array("L")).append(position)
             else:
-              tmp = ExtensionRow(row, position, self.file_descriptor)
-              index.setdefault(tmp.core_id, array('L')).append(position)
+                tmp = ExtensionRow(row, position, self.file_descriptor)
+                index.setdefault(tmp.core_id, array("L")).append(position)
 
         return index
 

{python-dwca-reader-0.16.2 → python-dwca-reader-0.16.3}/dwca/minibench.py

@@ -8,12 +8,12 @@ import resource
 from dwca.read import DwCAReader
 
 
-def sizeof_fmt(num, suffix='B'):
-    for unit in ['', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi']:
+def sizeof_fmt(num, suffix="B"):
+    for unit in ["", "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi"]:
         if abs(num) < 1024.0:
             return "%3.1f%s%s" % (num, unit, suffix)
         num /= 1024.0
-    return "%.1f%s%s" % (num, 'Yi', suffix)
+    return "%.1f%s%s" % (num, "Yi", suffix)
 
 
 def show_memory_usage():
@@ -27,8 +27,9 @@ def show_memory_usage():
 # print "Memory before:"
 # show_memory_usage()
 
+
 def test():
-    with DwCAReader('dwca-florabank1-occurrences') as dwca:
+    with DwCAReader("dwca-florabank1-occurrences") as dwca:
         # print "Time after open:"
         # print time.ctime()
 
@@ -39,7 +40,7 @@ def test():
         for row in dwca:
             # tmp = row.data[qn('locality')]
             i = i + 1
-            if (i % 100000 == 0):
+            if i % 100000 == 0:
                 print("in loop mem: ")
                 show_memory_usage()
 
@@ -53,7 +54,8 @@ def test():
     # show_memory_usage()
 
 
-if (__name__ == '__main__'):
+if __name__ == "__main__":
     from timeit import Timer
+
     t = Timer("test()", "from __main__ import test")
     print(t.timeit(number=3))