def import_data(self, user, upload, external_id_field_index=None):
"""
Import data into this ``Dataset`` from a given ``DataUpload``.
"""
self.lock()
try:
if upload.imported:
raise DataImportError('This file has already been imported.')
task_type = get_import_task_type_for_upload(upload)
if not task_type:
# This is normally caught on the client.
raise DataImportError('This file type is not supported for data import.')
if self.column_schema:
# This is normally caught on the client.
if upload.columns != [c['name'] for c in self.column_schema]:
raise DataImportError('The columns in this file do not match those in the dataset.')
else:
self.column_schema = []
for i, c in enumerate(upload.columns):
self.column_schema.append({
'name': c,
'indexed': False,
'type': upload.guessed_types[i],
'indexed_name': None,
'min': None,
'max': None
})
if self.sample_data is None:
self.sample_data = upload.sample_data
# If this is the first import and the API hasn't been used, save that information
if self.initial_upload is None and self.row_count is None:
self.initial_upload = upload
self.current_task = TaskStatus.objects.create(task_name=task_type.name, creator=user)
self.save()
task_type.apply_async(
args=[self.slug, upload.id],
kwargs={ 'external_id_field_index': external_id_field_index },
task_id=self.current_task.id
)
except:
self.unlock()
raise
def import_data(self, user, upload, external_id_field_index=None):
"""
Import data into this ``Dataset`` from a given ``DataUpload``.
"""
self.lock()
try:
if upload.imported:
raise DataImportError(
_('This file has already been imported.'))
task_type = get_import_task_type_for_upload(upload)
if not task_type:
# This is normally caught on the client.
raise DataImportError(
_('This file type is not supported for data import.'))
if self.column_schema:
# This is normally caught on the client.
if upload.columns != [c['name'] for c in self.column_schema]:
raise DataImportError(
_('The columns in this file do not match those in the dataset.'
))
else:
self.column_schema = make_column_schema(
upload.columns, types=upload.guessed_types)
if self.sample_data is None:
self.sample_data = upload.sample_data
# If this is the first import and the API hasn't been used, save that information
if self.initial_upload is None and self.row_count is None:
self.initial_upload = upload
self.current_task = TaskStatus.objects.create(
task_name=task_type.name,
task_description=_('Import data from %(filename)s into %(slug)s.') \
% {'filename': upload.filename, 'slug': self.slug},
creator=user
)
self.save()
task_type.apply_async(
args=[self.slug, upload.id],
kwargs={'external_id_field_index': external_id_field_index},
task_id=self.current_task.id)
except:
self.unlock()
raise
def import_data(self, user, upload, external_id_field_index=None, schema_overrides = {}):
"""
Import data into this ``Dataset`` from a given ``DataUpload``.
"""
self.lock()
try:
if upload.imported:
raise DataImportError(_('This file has already been imported.'))
task_type = get_import_task_type_for_upload(upload)
if not task_type:
# This is normally caught on the client.
raise DataImportError(_('This file type is not supported for data import.'))
if self.column_schema:
# This is normally caught on the client.
if upload.columns != [c['name'] for c in self.column_schema]:
raise DataImportError(_('The columns in this file do not match those in the dataset.'))
else:
self.column_schema = make_column_schema(upload.columns, types=upload.guessed_types, overrides=schema_overrides)
if self.sample_data is None:
self.sample_data = upload.sample_data
# If this is the first import and the API hasn't been used, save that information
if self.initial_upload is None and self.row_count is None:
self.initial_upload = upload
self.current_task = TaskStatus.objects.create(
task_name=task_type.name,
task_description=_('Import data from %(filename)s into %(slug)s.') \
% {'filename': upload.filename, 'slug': self.slug},
creator=user
)
self.save()
task_type.apply_async(
args=[self.slug, upload.id],
kwargs={ 'external_id_field_index': external_id_field_index },
task_id=self.current_task.id
)
except:
self.unlock()
raise
def import_data(self, user, upload, external_id_field_index=None):
"""
Import data into this ``Dataset`` from a given ``DataUpload``.
"""
if upload.imported:
raise DataImportError('This file has already been imported.')
task_type = get_import_task_type_for_upload(upload)
if not task_type:
# This is normally caught on the client.
raise DataImportError('This file type is not supported for data import.')
if self.columns:
# This is normally caught on the client.
if upload.columns != self.columns:
raise DataImportError('The columns in this file do not match those in the dataset.')
else:
self.columns = upload.columns
if self.sample_data is None:
self.sample_data = upload.sample_data
else:
# TODO - extend?
pass
# If this is the first import and the API hasn't been used, save that information
if self.initial_upload is None and self.row_count is None:
self.initial_upload = upload
self.current_task = TaskStatus.objects.create(task_name=task_type.name, creator=user)
self.save()
task_type.apply_async(
args=[self.slug, upload.id],
kwargs={ 'external_id_field_index': external_id_field_index },
task_id=self.current_task.id
)
