def reindex_uuids(self, uuids):
""" reindexes a list of uuids
"""
if isinstance(uuids, list):
crawler = Crawler()
crawler.index_document_list(uuids)
return len(uuids)
else:
return False
def reindex_uuids(self, uuids):
""" reindexes a list of uuids
"""
self.clear_caches()
if isinstance(uuids, list):
crawler = Crawler()
if isinstance(self.max_geo_zoom, int):
if self.max_geo_zoom > 5:
# only positive integers
crawler.max_geo_zoom = self.max_geo_zoom
if isinstance(self.human_remains, int):
if self.human_remains > 0:
# we're reindexing sensitive human remains
crawler.human_remains = self.human_remains
crawler.index_document_list(uuids, self.list_size)
return len(uuids)
else:
return False
def reindex_uuids(self, uuids):
""" reindexes a list of uuids
"""
self.clear_caches()
if isinstance(uuids, list):
crawler = Crawler()
if isinstance(self.max_geo_zoom, int):
if self.max_geo_zoom > 5:
# only positive integers
crawler.max_geo_zoom = self.max_geo_zoom
if isinstance(self.human_remains, int):
if self.human_remains > 0:
# we're reindexing sensitive human remains
crawler.human_remains = self.human_remains
crawler.index_document_list(uuids, self.list_size)
return len(uuids)
else:
return False
def reindex(self):
""" Reindexes items in Solr,
with item UUIDs coming from a given source
"""
self.clear_caches()
self.iteration += 1
print('Iteration: ' + str(self.iteration))
if self.iteration <= self.max_iterations:
uuids = []
if self.solr_direct_url is not False:
print('Get uuids from solr: ' + str(self.solr_direct_url))
uuids = self.get_uuids_solr_direct(self.solr_direct_url)
elif self.oc_url is not False:
# now validate to make sure we're asking for uuids
if 'response=uuid' in self.oc_url \
and '.json' in self.oc_url:
print('Get uuids from OC-API: ' + str(self.oc_url))
uuids = self.get_uuids_oc_url(self.oc_url)
elif isinstance(self.project_uuids, list) \
and self.annotated_after is False \
and self.skip_indexed_after is False:
# now validate to make sure we're asking for uuids
print('Getting uuids for: ' + str(len(self.project_uuids)) + ' projects')
uuids = []
raw_uuids = Manifest.objects\
.filter(project_uuid__in=self.project_uuids)\
.values_list('uuid', flat=True)
for raw_uuid in raw_uuids:
uuids.append(str(raw_uuid))
elif isinstance(self.project_uuids, list)\
and self.annotated_after is False\
and self.skip_indexed_after is not False:
# index items from projects, but not items indexed after a certain
# datetime
uuids = []
raw_uuids = Manifest.objects\
.filter(project_uuid__in=self.project_uuids)\
.exclude(indexed__gte=self.skip_indexed_after)\
.values_list('uuid', flat=True)
for raw_uuid in raw_uuids:
uuids.append(str(raw_uuid))
elif self.annotated_after is not False:
self.max_iterations = 1
uuids = []
anno_list = []
if self.project_uuids is not False:
if not isinstance(self.project_uuids, list):
project_uuids = [self.project_uuids]
else:
project_uuids = self.project_uuids
anno_list = LinkAnnotation.objects\
.filter(project_uuid__in=project_uuids,
updated__gte=self.annotated_after)
else:
anno_list = LinkAnnotation.objects\
.filter(updated__gte=self.annotated_after)
for anno in anno_list:
print('Index annotation: ' + anno.subject + ' :: ' + anno.predicate_uri + ' :: ' + anno.object_uri)
if(anno.subject_type in (item[0] for item in settings.ITEM_TYPES)):
# make sure it's an Open Context item that can get indexed
if anno.subject not in uuids:
uuids.append(anno.subject)
if anno.subject_type == 'types' and self.related_annotations:
# get the
# subjects item used with this type, we need to do a lookup
# on the assertions table
assertions = Assertion.objects\
.filter(object_uuid=geo_anno.subject)
for ass in assertions:
if ass.uuid not in uuids:
uuids.append(ass.uuid)
if isinstance(uuids, list):
print('Ready to index ' + str(len(uuids)) + ' items')
crawler = Crawler()
if isinstance(self.max_geo_zoom, int):
if self.max_geo_zoom > 5:
# only positive integers
crawler.max_geo_zoom = self.max_geo_zoom
if isinstance(self.human_remains, int):
if self.human_remains > 0:
# we're reindexing sensitive human remains
crawler.human_remains = self.human_remains
crawler.index_document_list(uuids, self.list_size)
self.reindex()
else:
print('Problem with: ' + str(uuids))
def reindex(self):
""" Reindexes items in Solr,
with item UUIDs coming from a given source
"""
self.iteration += 1
print('Iteration: ' + str(self.iteration))
if self.iteration <= self.max_iterations:
uuids = []
if self.solr_direct_url is not False:
print('Get uuids from solr: ' + str(self.solr_direct_url))
uuids = self.get_uuids_solr_direct(self.solr_direct_url)
elif self.oc_url is not False:
# now validate to make sure we're asking for uuids
if 'response=uuid' in self.oc_url \
and '.json' in self.oc_url:
print('Get uuids from OC-API: ' + str(self.oc_url))
uuids = self.get_uuids_oc_url(self.oc_url)
elif isinstance(self.project_uuids, list) \
and self.annotated_after is False \
and self.skip_indexed_after is False:
# now validate to make sure we're asking for uuids
uuids = []
raw_uuids = Manifest.objects\
.filter(project_uuid__in=self.project_uuids)\
.values_list('uuid', flat=True)
for raw_uuid in raw_uuids:
uuids.append(str(raw_uuid))
elif isinstance(self.project_uuids, list)\
and self.annotated_after is False\
and self.skip_indexed_after is not False:
# index items from projects, but not items indexed after a certain
# datetime
uuids = []
raw_uuids = Manifest.objects\
.filter(project_uuid__in=self.project_uuids)\
.exclude(indexed__gte=self.skip_indexed_after)\
.values_list('uuid', flat=True)
for raw_uuid in raw_uuids:
uuids.append(str(raw_uuid))
elif self.annotated_after is not False:
self.max_iterations = 1
uuids = []
anno_list = []
if self.project_uuids is not False:
if not isinstance(self.project_uuids, list):
project_uuids = [self.project_uuids]
else:
project_uuids = self.project_uuids
anno_list = LinkAnnotation.objects\
.filter(project_uuid__in=project_uuids,
updated__gte=self.annotated_after)
else:
anno_list = LinkAnnotation.objects\
.filter(updated__gte=self.annotated_after)
for anno in anno_list:
print('Index annotation: ' + anno.subject + ' :: ' + anno.predicate_uri + ' :: ' + anno.object_uri)
if(anno.subject_type in (item[0] for item in settings.ITEM_TYPES)):
# make sure it's an Open Context item that can get indexed
if anno.subject not in uuids:
uuids.append(anno.subject)
if anno.subject_type == 'types' and self.related_annotations:
# get the
# subjects item used with this type, we need to do a lookup
# on the assertions table
assertions = Assertion.objects\
.filter(object_uuid=geo_anno.subject)
for ass in assertions:
if ass.uuid not in uuids:
uuids.append(ass.uuid)
if isinstance(uuids, list):
print('Ready to index ' + str(len(uuids)) + ' items')
crawler = Crawler()
crawler.index_document_list(uuids)
self.reindex()
else:
print('Problem with: ' + str(uuids))
