def search(query, params, off, num_results_wanted):
off = int(off)
# query and params both come from sidebar, so should have exactly one.
if not query and not params:
return Result(0, off), get_empty_parameters()
elif query and params:
print "artstor 34, shouldn't have reached here... Have both query (%s) and params (%s)" % (
query, params)
raise NotImplementedError
elif query:
query_terms = Query_Language(identifier).searcher_translator(query)
else:
query_terms = parse_parameters(params)
print "artstor 48 query_terms %s" % query_terms
# return empty result if no search terms (submitting an empty query breaks artstor)
if len(query_terms) is 0:
return Result(0, 0), get_empty_parameters()
"""
Caching of results, uncomment and fix if supported in other searchers TODO
cached, created = HitCount.current_objects.get_or_create(
source=self.get_source_id(), query='%s [%s:%s]' % (keyword, page, pagesize),
defaults=dict(hits=0, valid_until=datetime.datetime.now() + datetime.timedelta(1)))
if not created and cached.results:
return simplejson.loads(cached.results)
"""
pagesize = num_results_wanted
url = _get_url(query_terms, pagesize, off)
html_page = _get_html_page(url)
try:
results = ElementTree(file=html_page)
print "artstor 61 \n\tfile %s\n\tresults %s\n" % (html_page, results)
num_results = int(
results.findtext(
'{http://www.loc.gov/zing/srw/}numberOfRecords')) or 0
except ExpatError: # XML parsing error
num_results = 0
if not num_results: # other type of error or no results found
return Result(0, off), _build_returnable_parameters(query_terms)
#pages = int(math.ceil(float(total) / pagesize))
result = Result(num_results, num_results + off)
image_divs = results.findall('.//{info:srw/schema/1/dc-v1.1}dc')
print "artstor 77 query_terms %s" % query_terms
for div in image_divs:
(url, thumb, image_identifier, title) = _get_image(div)
result.addImage(ResultImage(url, thumb, title, image_identifier))
# TODO cope with full image not actually giving result (timeout error)
return result, _build_returnable_parameters(query_terms)
def search(query, params, off, num_results_wanted):
off = int(off)
# query and params both come from sidebar, so should have exactly one.
if not query and not params:
return Result(0, off), get_empty_parameters()
elif query and params:
print "artstor 34, shouldn't have reached here... Have both query (%s) and params (%s)" %(query, params)
raise NotImplementedError
elif query:
query_terms = Query_Language(identifier).searcher_translator(query)
else:
query_terms = parse_parameters(params)
print "artstor 48 query_terms %s" %query_terms
# return empty result if no search terms (submitting an empty query breaks artstor)
if len(query_terms) is 0:
return Result(0, 0), get_empty_parameters()
"""
Caching of results, uncomment and fix if supported in other searchers TODO
cached, created = HitCount.current_objects.get_or_create(
source=self.get_source_id(), query='%s [%s:%s]' % (keyword, page, pagesize),
defaults=dict(hits=0, valid_until=datetime.datetime.now() + datetime.timedelta(1)))
if not created and cached.results:
return simplejson.loads(cached.results)
"""
pagesize = num_results_wanted
url = _get_url(query_terms, pagesize, off)
html_page = _get_html_page(url)
try:
results = ElementTree(file=html_page)
print "artstor 61 \n\tfile %s\n\tresults %s\n" %(html_page, results)
num_results = int(results.findtext('{http://www.loc.gov/zing/srw/}numberOfRecords')) or 0
except ExpatError: # XML parsing error
num_results = 0
if not num_results: # other type of error or no results found
return Result(0, off), _build_returnable_parameters(query_terms)
#pages = int(math.ceil(float(total) / pagesize))
result = Result(num_results, num_results+off)
image_divs = results.findall('.//{info:srw/schema/1/dc-v1.1}dc')
print "artstor 77 query_terms %s" %query_terms
for div in image_divs:
(url, thumb, image_identifier, title) = _get_image(div)
result.addImage(ResultImage(url, thumb, title, image_identifier))
# TODO cope with full image not actually giving result (timeout error)
return result, _build_returnable_parameters(query_terms)
def search(query, params, off, num_results_wanted):
off = int(off)
# query and params both come from sidebar, so should have exactly one.
if not query and not params:
return Result(0, off), get_empty_parameters()
elif query and params:
raise NotImplementedError
elif query:
query_terms = Query_Language(identifier).searcher_translator(query)
else:
query_terms = parse_parameters(params)
for key in query_terms:
query_terms[key] = list_to_str(query_terms[key])
"""
Disable modifiers and adv search for now
Todo: Work out if artstor can process adv search and modifiers
Adding Adv sidebar if possible
"""
del_list = []
for key in query_terms:
if not key == "":
del_list.append(key)
for key in del_list:
if key in query_terms:
del query_terms[key]
if "query_string" in query_terms:
del query_terms["query_string"]
# return empty result if no search terms (submitting an empty query breaks artstor)
if len(query_terms) is 0:
return Result(0, 0), get_empty_parameters()
"""
Caching of results, uncomment and fix if supported in other searchers TODO
cached, created = HitCount.current_objects.get_or_create(
source=self.get_source_id(), query='%s [%s:%s]' % (keyword, page, pagesize),
defaults=dict(hits=0, valid_until=datetime.datetime.now() + datetime.timedelta(1)))
if not created and cached.results:
return simplejson.loads(cached.results)
"""
pagesize = num_results_wanted
url = _get_url(query_terms, pagesize, off)
#html_page = _get_html_page(url)
try:
html_page = _get_html_page(url)
if not html_page:
print "ArtStor did not get any data from server, make sure MDID can reach the server through the firewall"
return Result(0, off), _build_returnable_parameters(query_terms)
results = ElementTree(file=html_page)
num_results = int(results.findtext('{http://www.loc.gov/zing/srw/}numberOfRecords')) or 0
except: # XML parsing error
print "ArtStor XML parsing error"
num_results = 0
if not num_results: # other type of error or no results found
return Result(0, off), _build_returnable_parameters(query_terms)
#pages = int(math.ceil(float(total) / pagesize))
result = Result(num_results, off+50)
image_divs = results.findall('.//{info:srw/schema/1/dc-v1.1}dc')
for div in image_divs:
(url, thumb, image_identifier, title) = _get_image(div)
result.addImage(ResultImage(url, thumb, title, image_identifier))
# TODO cope with full image not actually giving result (timeout error)
return result, _build_returnable_parameters(query_terms)
