def view_get_slack_dataset_info(dataset_id, **kwargs):
citation_only = kwargs.get('citation', False)
dsv = get_latest_dataset_version(dataset_id)
if dsv is None:
return "Sorry, no Dataset found for id: %s" % dataset_id
dataset_dict = DatasetSerializer(dsv).as_json()
ref_url = '%s/dataset.xhtml?id=%s' % (\
settings.DATAVERSE_INSTALLATION_URL,
dataset_id)
if citation_only:
citation_block = dataset_dict.get('metadata_blocks',
{}).get('citation')
return """%s\n\nreference: %s""" %\
(json.dumps(citation_block, indent=4), ref_url)
return """%s\n\nreference: %s""" %\
(json.dumps(dataset_dict, indent=4), ref_url)
def view_single_dataset(request, dataset_id):
"""Dataset view test. Given dataset id, get latest version"""
dsv = get_latest_dataset_version(dataset_id)
if dsv is None:
raise Http404('dataset_id not found')
return view_dataset_by_version(request, dsv.id)
def view_single_dataset(request, dataset_id):
"""Dataset view test. Given dataset id, get latest version"""
dsv = get_latest_dataset_version(dataset_id)
if dsv is None:
raise Http404('dataset_id not found')
return view_dataset_by_version(request, dsv.id)
def view_dataset_by_persistent_id(request):
persistent_id = request.GET.get('persistentId', None)
if persistent_id is None:
raise Http404('persistentId not found: %s' % persistent_id)
ds = Dataset.get_dataset_by_persistent_id(persistent_id)
if ds is None:
raise Http404('persistentId not found: %s' % persistent_id)
dsv = get_latest_dataset_version(ds.dvobject.id)
if dsv is None:
raise Http404('dataset_id not found')
return view_dataset_by_version(request, dsv.id)
def view_dataset_by_persistent_id(request):
persistent_id = request.GET.get('persistentId', None)
if persistent_id is None:
raise Http404('persistentId not found: %s' % persistent_id)
ds = Dataset.get_dataset_by_persistent_id(persistent_id)
if ds is None:
raise Http404('persistentId not found: %s' % persistent_id)
dsv = get_latest_dataset_version(ds.dvobject.id)
if dsv is None:
raise Http404('dataset_id not found')
return view_dataset_by_version(request, dsv.id)
def get_stats_result(self, request):
"""Return the StatsResult object for this statistic"""
dv_id = self.kwargs.get('ds_id', None)
if dv_id is None:
return StatsResult.build_error_result("No Dataset id specified", 400)
# Get the latest version
dataset_version = get_latest_dataset_version(dv_id)
if dataset_version is None:
return StatsResult.build_error_result('No published Dataset with id: %s' % dv_id, 404)
dataset_as_json = DatasetSerializer(dataset_version).as_json()
return StatsResult.build_success_result(dataset_as_json)
def get_stats_result(self, request):
"""Return the StatsResult object for this statistic"""
dv_id = self.kwargs.get('ds_id', None)
if dv_id is None:
return StatsResult.build_error_result("No Dataset id specified",
400)
# Get the latest version
dataset_version = get_latest_dataset_version(dv_id)
if dataset_version is None:
return StatsResult.build_error_result(
'No published Dataset with id: %s' % dv_id, 404)
dataset_as_json = DatasetSerializer(dataset_version).as_json()
return StatsResult.build_success_result(dataset_as_json)
def get_stats_result(self, request):
"""Return the StatsResult object for this statistic"""
persistent_id = request.GET.get('persistentId', None)
if persistent_id is None:
return StatsResult.build_error_result("No Dataset persistent id specified", 400)
ds = Dataset.get_dataset_by_persistent_id(persistent_id)
err_404 = 'No published dataset found for persistentId: %s' % persistent_id
if ds is None or not ds.dvobject.publicationdate:
return StatsResult.build_error_result(err_404, 404)
# Get the latest version
dataset_version = get_latest_dataset_version(ds.dvobject.id)
if dataset_version is None:
return StatsResult.build_error_result(err_404, 404)
dataset_as_json = DatasetSerializer(dataset_version).as_json()
return StatsResult.build_success_result(dataset_as_json)
def get_stats_result(self, request):
"""Return the StatsResult object for this statistic"""
persistent_id = request.GET.get('persistentId', None)
if persistent_id is None:
return StatsResult.build_error_result(
"No Dataset persistent id specified", 400)
ds = Dataset.get_dataset_by_persistent_id(persistent_id)
err_404 = 'No published dataset found for persistentId: %s' % persistent_id
if ds is None or not ds.dvobject.publicationdate:
return StatsResult.build_error_result(err_404, 404)
# Get the latest version
dataset_version = get_latest_dataset_version(ds.dvobject.id)
if dataset_version is None:
return StatsResult.build_error_result(err_404, 404)
dataset_as_json = DatasetSerializer(dataset_version).as_json()
return StatsResult.build_success_result(dataset_as_json)
def view_get_slack_dataset_info(dataset_id, **kwargs):
citation_only = kwargs.get('citation', False)
dsv = get_latest_dataset_version(dataset_id)
if dsv is None:
return "Sorry, no Dataset found for id: %s" % dataset_id
dataset_dict = DatasetSerializer(dsv).as_json()
ref_url = '%s/dataset.xhtml?id=%s' % (\
settings.DATAVERSE_INSTALLATION_URL,
dataset_id)
if citation_only:
citation_block = dataset_dict.get('metadata_blocks', {}).get('citation')
return """%s\n\nreference: %s""" %\
(json.dumps(citation_block, indent=4), ref_url)
return """%s\n\nreference: %s""" %\
(json.dumps(dataset_dict, indent=4), ref_url)
def make_json_files(self):
# Set publication status
#
filters = {}
if self.published_only:
filters.update(query_helper.get_is_published_filter_param())
# Query for dataset ids
#
ds_id_query = Dataset.objects.filter(**filters\
).annotate(ds_id=F('dvobject__id')\
).values_list('ds_id', flat=True\
).order_by('ds_id')
# Iterate through dataset ids
#
#start_time = datetime.now()
start_time = int(time.time()) # epoch seconds
cnt = 0
no_versions_found_list = [45900]
for ds_id in ds_id_query:
cnt += 1
msgt('(%d) Checking dataset id %s' % (cnt, ds_id))
if ds_id < self.dataset_start_id:
msg('skipping...(start at dataset id: %d)' %
self.dataset_start_id)
continue
# Create file name
#
fname = 'ds_%s.json' % (str(ds_id).zfill(8))
full_fname = join(OUTPUT_DIR, fname)
# Should we overwrite the existing file?
#
if isfile(full_fname) and not self.overwrite_existing_files:
msg('skipping...file already exists')
continue
dataset_version = get_latest_dataset_version(ds_id)
if dataset_version is None:
msg("Could not find dataset_version!")
no_versions_found_list.append(ds_id)
continue
dataset_as_json = DatasetSerializer(dataset_version).as_json()
open(full_fname, 'w').write(json.dumps(dataset_as_json, indent=4))
msg('File written: %s' % full_fname)
if cnt % 500 == 0:
self.show_elapsed_time(start_time)
#if cnt > 10:
# self.show_elapsed_time(start_time)
# break
self.show_elapsed_time(start_time)
print 'no_versions_found_list: %s' % no_versions_found_list
def view_side_by_side1(request, dataset_id):
dsv = get_latest_dataset_version(dataset_id)
if dsv is None:
raise Http404("No published datasets for id: %s" % dataset_id)
template_basename = request.GET.get(PARAM_TEMPLATE_NAME,
'title_citation.html')
template_fname = path.join('dvobject_api', template_basename)
try:
template = get_template(template_fname)
except TemplateDoesNotExist:
raise Http404('Template does not exist: %s' % template_fname)
#formatter = HtmlFormatter(linenos=True, cssclass="friendly")
formatter = HtmlFormatter(linenos=False, cssclass="friendly")
# -------------------------------
# Format raw template
# -------------------------------
template_html = open(template.origin.name, 'r').read()
django_lexer = get_lexer_by_name("django", stripall=True)
template_snippet = highlight(template_html, django_lexer, formatter)
template_name = path.basename(template.origin.name)
# -------------------------------
# Format Dataset JSON
# -------------------------------
dataset_dict = DatasetSerializer(dsv).as_json()
citation_block = dataset_dict.get('metadata_blocks', {}).get('citation')
#citation_dict = OrderedDict({'citation_block': citation_block})
json_string = json.dumps(dataset_dict, indent=4)
json_lexer = get_lexer_by_name("json", stripall=True)
dataset_json_snippet = highlight(json_string, json_lexer, formatter)
# -------------------------------
# Format Dataverse JSON
# -------------------------------
dataverse_id = dataset_dict['ownerInfo']['id']
try:
dataverse = Dataverse.objects.select_related('dvobject')\
.get(dvobject__id=dataverse_id)
except Dataverse.DoesNotExist:
raise Http404('No Dataverse with id: %s' % dataverse_id)
dataverse_dict = DataverseSerializer(dataverse).as_json()
#dataset_json_snippet = highlight(json_string, json_lexer, formatter)
# -------------------------------
# Overall pygment css
# -------------------------------
pygment_css = formatter.get_style_defs('.friendly')
# -------------------------------
# API endpoint
# -------------------------------
swagger_base_url = '%s://%s' % (settings.SWAGGER_SCHEME,
settings.SWAGGER_HOST)
lu = dict(
template_snippet=template_snippet,
template_name=template_name,
dataset_json_snippet=dataset_json_snippet,
pygment_css=pygment_css,
swagger_base_url=swagger_base_url,
dataset_id=dataset_id,
ds=dataset_dict, # for rendering chosen template
citation_block=citation_block, # for rendering chosen template
)
lu['rendered_template'] = render_to_string(template_fname, lu)
return render(request, 'composable/side_by_side.html', lu)
def make_json_files(self):
# Set publication status
#
filters = {}
if self.published_only:
filters.update(query_helper.get_is_published_filter_param())
# Query for dataset ids
#
ds_id_query = Dataset.objects.filter(**filters\
).annotate(ds_id=F('dvobject__id')\
).values_list('ds_id', flat=True\
).order_by('ds_id')
# Iterate through dataset ids
#
#start_time = datetime.now()
start_time = int(time.time()) # epoch seconds
cnt = 0
no_versions_found_list = [45900]
for ds_id in ds_id_query:
cnt += 1
msgt('(%d) Checking dataset id %s' % (cnt, ds_id))
if ds_id < self.dataset_start_id:
msg('skipping...(start at dataset id: %d)' % self.dataset_start_id)
continue
# Create file name
#
fname = 'ds_%s.json' % (str(ds_id).zfill(8))
full_fname = join(OUTPUT_DIR, fname)
# Should we overwrite the existing file?
#
if isfile(full_fname) and not self.overwrite_existing_files:
msg('skipping...file already exists')
continue
dataset_version = get_latest_dataset_version(ds_id)
if dataset_version is None:
msg("Could not find dataset_version!")
no_versions_found_list.append(ds_id)
continue
dataset_as_json = DatasetSerializer(dataset_version).as_json()
open(full_fname, 'w').write(json.dumps(dataset_as_json, indent=4))
msg('File written: %s' % full_fname)
if cnt % 500 == 0:
self.show_elapsed_time(start_time)
#if cnt > 10:
# self.show_elapsed_time(start_time)
# break
self.show_elapsed_time(start_time)
print 'no_versions_found_list: %s' % no_versions_found_list