def test_keyword(self):
solr = pysolr.Solr('http://localhost:8983/solr/unittest')
solr.add([{
"id": "Belfast",
"description": "This is about Belfast",
},
{
"id": "Lisburn",
"description": "This is about Lisburn",
},
{
"id": "Titanic",
"description": "This is about Titanic",
},])
query_generic = solr.search("about")
query_titanic = solr.search("Titanic")
generic_result_list = []
titanic_result_list = []
generic_test = ['Belfast','Lisburn','Titanic']
titanic_test = ['Titanic']
for result in query_titanic:
titanic_result_list.append(result['id'])
for result in query_generic:
generic_result_list.append(result['id'])
self.assertEqual(generic_result_list,generic_test)
self.assertEqual(titanic_result_list,titanic_test)
def search(request):
SolrGene = collections.namedtuple('SolrGene', ['species', 'species_taxid', 'sys_name', 'name', 'description', 'num_conditions', 'num_corems', 'num_gres'])
if 'search_query' in request.GET:
query = request.GET['search_query']
solr_docs, facets = solr.search(query)
print "FACETS: ", facets
search_terms = query
docs = []
for doc in solr_docs:
num_corems = 0
num_conds = 0
num_gres = 0
if 'num_conds' in doc:
num_conds = doc['num_conds']
if 'num_corems' in doc:
num_corems = doc['num_corems']
if 'num_gres' in doc:
num_gres = doc['num_gres']
docs.append(SolrGene(doc['species'],
doc['ncbi_taxonomy_id'],
doc['sys_name'],
doc['name'],
doc['description'],
num_conds,
num_corems,
num_gres))
return render_to_response('search_results.html', locals())
else:
return render_to_response('search.html', locals())
def sample(limit, trainingSetSize, *args):
def accept(doc):
haskeys = False not in [doc.has_key(field) for field in args]
if haskeys:
return 0 not in [
len(doc[field][0])
if isinstance(doc[field], list) else len(doc[field])
for field in args
]
else:
return False
fields = 'id,%s' % (','.join(args))
sort = quote('publication_date asc')
documents = []
increment = __defaultInc__ if limit > __defaultInc__ else limit
for f in range(0, limit, increment):
if f + increment > limit: increment = limit - increment
documents += solr.search({
'fl': fields,
'sort': sort,
'rows': increment,
'start': f
})
documents = filter(accept, documents)
return {
'train': documents[0:trainingSetSize],
'test': documents[trainingSetSize:len(documents)]
}
def id_ind_to_ind_name(id_industry):
query = 'id_industry:' + str(id_industry)
solr = pysolr.Solr('http://85.31.219.96:7183/solr/')
results = solr.search(query)
name = ''
for hit in results:
name = hit['industry'][0]
break
return name
def record_has_mult_topics( id_chart ):
query = 'id_chart:' + str(id_chart)
solr = pysolr.Solr('http://85.31.219.96:7183/solr/')
results = solr.search( query, fl='topic', rows='100' )
id_chart = False
for hit in results:
try:
if ( len(hit['topic']) > 1 ): id_chart = True
except KeyError:
pass
return id_chart
def industry_and_topics( id_industry ):
"""
!!! NOW USING pysolr PACKAGE INSTEAD OF solrpy !!!
"""
""" Input : id_industry
Output: dictionary of topics and their faceted counts """
query = 'id_industry:' + str(id_industry)
solr = pysolr.Solr('http://85.31.219.96:7183/solr/')
params = { 'facet.field' : 'topic', }
results = solr.search(query, facet = 'on', **params )
facets = results.facets['facet_fields']['topic']
return list_to_dict(facets)
def test_solr_return_100(self):
solr = pysolr.Solr('http://localhost:8983/solr/keyword')
root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
path_to_files = root+'/python/data/image_json.json'
with open(path_to_files) as data_file:
data = json.load(data_file)
solr.add(data)
results = solr.search("Belfast", **{
'hl': 'true',
'hl.fragsize': 100,
'rows': 100,})
self.assertEqual(len(results),100)
def sample(limit,trainingSetSize,*args):
def accept(doc):
haskeys = False not in [doc.has_key(field) for field in args]
if haskeys:
return 0 not in [len(doc[field][0])
if isinstance(doc[field],list) else len(doc[field]) for field in args]
else:
return False
fields = 'id,%s' % (','.join(args))
sort = quote('publication_date asc')
documents = []
increment = __defaultInc__ if limit > __defaultInc__ else limit
for f in range(0,limit,increment):
if f + increment > limit: increment = limit - increment
documents += solr.search(
{'fl' : fields, 'sort' : sort,
'rows' : increment, 'start' : f})
documents = filter(accept, documents)
return { 'train' : documents[0:trainingSetSize],
'test' : documents[trainingSetSize:len(documents)]}
