def search_titles_results(request):
page_title = 'US Newspaper Directory Search Results'
crumbs = list(settings.BASE_CRUMBS)
crumbs.extend([{'label': 'Search Newspaper Directory',
'href': reverse('openoni_search_titles')},
])
def prep_title_for_return(t):
title = {}
title.update(t.solr_doc)
title['oclc'] = t.oclc
return title
format = request.GET.get('format', None)
# check if requested format is CSV before building pages for response. CSV
# response does not make use of pagination, instead all matching titles from
# SOLR are returned at once
if format == 'csv':
query = request.GET.copy()
q, fields, sort_field, sort_order, facets = index.get_solr_request_params_from_query(query)
# return all titles in csv format. * May hurt performance. Assumption is that this
# request is not made often.
# TODO: revisit if assumption is incorrect
solr_response = index.execute_solr_query(q, fields, sort_field,
sort_order, index.title_count(), 0)
titles = index.get_titles_from_solr_documents(solr_response)
csv_header_labels = ('lccn', 'title', 'place_of_publication', 'start_year',
'end_year', 'publisher', 'edition', 'frequency', 'subject',
'state', 'city', 'country', 'language', 'oclc',
'holding_type',)
response = HttpResponse(content_type='text/csv')
response['Content-Disposition'] = 'attachment; filename="openoni_titles.csv"'
writer = csv.writer(response)
writer.writerow(csv_header_labels)
for title in titles:
writer.writerow(map(lambda val: smart_str(val or '--'),
(title.lccn, title.name, title.place_of_publication,
title.start_year, title.end_year, title.publisher,
title.edition, title.frequency,
map(str, title.subjects.all()),
set(map(lambda p: p.state, title.places.all())),
map(lambda p: p.city, title.places.all()),
str(title.country), map(str, title.languages.all()),
title.oclc, title.holding_types)))
return response
try:
curr_page = int(request.REQUEST.get('page', 1))
except ValueError, e:
curr_page = 1
def status(request):
page_title = 'System Status'
page_count = models.Page.objects.all().count()
issue_count = models.Issue.objects.all().count()
batch_count = models.Batch.objects.all().count()
title_count = models.Title.objects.all().count()
holding_count = models.Holding.objects.all().count()
essay_count = models.Essay.objects.all().count()
pages_indexed = index.page_count()
titles_indexed = index.title_count()
return render_to_response('reports/status.html', dictionary=locals(),
context_instance=RequestContext(request))
def handle(self, **options):
if not (
models.Title.objects.all().count() == 0
and models.Holding.objects.all().count() == 0
and models.Essay.objects.all().count() == 0
and models.Batch.objects.all().count() == 0
and models.Issue.objects.all().count() == 0
and models.Page.objects.all().count() == 0
and index.page_count() == 0
and index.title_count() == 0
):
_logger.warn("Database or index not empty as expected.")
return
start = datetime.now()
management.call_command("loaddata", "languages.json")
management.call_command("loaddata", "institutions.json")
management.call_command("loaddata", "ethnicities.json")
management.call_command("loaddata", "labor_presses.json")
management.call_command("loaddata", "countries.json")
bib_in_settings = validate_bib_dir()
if bib_in_settings:
# look in BIB_STORAGE for original titles to load
for filename in os.listdir(bib_in_settings):
if filename.startswith("titles-") and filename.endswith(".xml"):
filepath = os.path.join(bib_in_settings, filename)
management.call_command("load_titles", filepath, skip_index=True)
management.call_command("title_sync", pull_title_updates=options["pull_title_updates"])
end = datetime.now()
total_time = end - start
_logger.info("start time: %s" % start)
_logger.info("end time: %s" % end)
_logger.info("total time: %s" % total_time)
_logger.info("openoni_sync done.")
