def test_escape(self):
self.assertEqual(pyndri.escape('hello (world)'),
'hello world')
self.assertEqual(pyndri.escape('hello.world'),
'hello world')
self.assertEqual(pyndri.escape('hello:world'),
'hello world')
def test_tokenize(self):
self.assertEqual(pyndri.tokenize('hello world foo bar'),
('hello', 'world', 'foo', 'bar'))
self.assertEqual(pyndri.tokenize('hello-world'), ('hello', 'world'))
self.assertEqual(pyndri.tokenize('hello.world'), ('hello', ))
self.assertEqual(pyndri.tokenize(pyndri.escape('hello.world')),
('hello', 'world'))
self.assertEqual(pyndri.tokenize('hello "world"'), (
'hello',
'world',
))
self.assertRaises(OSError, lambda: pyndri.tokenize('hello (world)'))
self.assertEqual(pyndri.tokenize(pyndri.escape('hello \'world\'')), (
'hello',
'world',
))
self.assertEqual(pyndri.tokenize(pyndri.escape('hello/world')), (
'hello',
'world',
))
def search():
index, dictionary = get_index()
query_string = request.args.get('q', None)
smoothing_method = request.args.get('smoothing_method', 'dirichlet')
smoothing_param = float(request.args.get('smoothing_param', 1000))
results_requested = int(request.args.get('results_requested', 10))
documents = []
if query_string is not None:
logging.info('Query string: %s', query_string)
highlighted_token_ids = set()
if not query_string.startswith('docid:'):
for token in index.tokenize(pyndri.escape(query_string)):
if dictionary.has_token(token):
highlighted_token_ids.add(
dictionary.translate_token(token))
def _include_document(int_doc_id):
ext_doc_id, doc_token_ids = index.document(int_doc_id)
def _format_token(token_id):
term = dictionary[token_id]
if token_id in highlighted_token_ids:
term = '<strong>{}</strong>'.format(term)
return term
doc_tokens = [
_format_token(token_id) if token_id > 0 else '<unk>'
for token_id in doc_token_ids
]
documents.append((ext_doc_id, ' '.join(doc_tokens)))
if query_string.startswith('docid:'):
ext_document_id = query_string[6:]
lookup = dict(index.document_ids([ext_document_id]))
if lookup:
_include_document(lookup[ext_document_id])
else:
query_env = pyndri.QueryEnvironment(index,
rules=(build_smoothing_rule(
smoothing_method,
smoothing_param), ))
results = query_env.query(query_string,
results_requested=results_requested)
for int_doc_id, _ in results:
_include_document(int_doc_id)
return render_template('index.html',
query=query_string,
results=documents,
smoothing_method=smoothing_method,
smoothing_param=smoothing_param)
outputFile = open(join(args["<outputfolder>"],"RetrievalParameterFile_{name}.xml".format(name=args["<collection_name>"])), 'w')
outputFile.write("<parameters>\n")
tokenizer=MosesTokenizer()
prog = re.compile("[_\-\(]*([A-Z]\.)*[_\-\(]*")
tops = {}
for top in topics:
terms=topics[top].split()
toptext=""
for t in terms:
if (prog.match(t)):
t=t.replace('.','')
toptext=toptext+" "+t
toptext=escape(toptext)
tops[top]=tokenizer.tokenize(toptext,return_str=True)
topics = collections.OrderedDict(sorted(tops.items()))
for t in topics :
print("topic : {t}".format(t=t))
outputFile.write(" <query>\n <type>indri</type>\n")
outputFile.write(" <number>{num}</number>\n".format(num=int(t)))
outputFile.write(" <text>\n")
outputFile.write(" {txt}\n".format(txt=topics[t]))
outputFile.write(" </text>\n")
outputFile.write(" </query>\n")
outputFile.write("</parameters>")
print("\nEnded.")
