def main():
dictionary_file = get_flag_value('-d')
postings_file = get_flag_value('-p')
queries_file = get_flag_value('-q')
output_file = get_flag_value('-o')
if dictionary_file == None or \
postings_file == None or \
queries_file == None or \
output_file == None:
usage()
sys.exit(2)
import search_index
if has_flag('-time'):
start = time.time()
search_index.search(
dictionary_file,
postings_file,
queries_file,
output_file)
if has_flag('-time'):
time_taken = time.time() - start
print '%s: Time taken = %.2f secs' % (queries_file, time_taken)
def search():
"""
Search for food truck locations given a query and a rectangular area defined by coordinates of the south west
and north east corners:
query: String to search for
southWestLat: Latitude of the south west corner
southWestLng: Longitude of the south west corner
northEastLat: Latitude of the north east corner
northEastLng: Longitude of the north east corner
jsoncallback: Name of the JSONP callback function wrapper
:return: JSONP encoded result in the following format:
jsoncallback({'success': true, 'data': [
<food_truck_data_1>,
<food_truck_data_2>
]})
Where food_truck_data is a JSON object with info fields described in http://data.sfgov.org/resource/rqzj-sfat.json
"""
logging.debug("Incoming %s" % request.args)
callback_name = request.args.get('jsoncallback')
results = search_index.search(request.args.get('query'),
float(request.args.get('southWestLat')),
float(request.args.get('southWestLng')),
float(request.args.get('northEastLat')),
float(request.args.get('northEastLng')))
return Response('%s(%s)' % (callback_name, json.dumps({'success': True, 'data': results})),
content_type='application/javascript; charset=utf-8')
def search_book(bookname, search_term=None):
""" Search for a pattern inside a book. """
if not bookname in os.listdir(BOOK_PATH):
abort(404)
if not search_term:
abort(400)
# TODO: Verify that the book has indeed been indexed
results = search_index.search(search_term, bookname=bookname)
out_dict = {
'q': search_term,
'ia': bookname,
'matches': [{'text': hit['snippet'],
'par': [{
'boxes': [
{'l': box[0], 't': box[1], 'r': box[2],
'b': box[3], 'page': hit['pagenum']}
for box in hit['highlights']],
'page': hit['pagenum']}]} for hit in results]
}
callback = request.args.get('callback', False)
if callback:
data = str(jsonify(out_dict).data)
content = str(callback) + "({0})".format(data)
mimetype = "application/javascript"
return current_app.response_class(content, mimetype=mimetype)
else:
return jsonify(out_dict)
def main():
dictionary_file = get_flag_value('-d')
postings_file = get_flag_value('-p')
queries_file = get_flag_value('-q')
output_file = get_flag_value('-o')
if dictionary_file == None or \
postings_file == None or \
queries_file == None or \
output_file == None:
usage()
sys.exit(2)
import search_index
if has_flag('-time'):
start = time.time()
search_index.search(dictionary_file, postings_file, queries_file,
output_file)
if has_flag('-time'):
time_taken = time.time() - start
print '%s: Time taken = %.2f secs' % (queries_file, time_taken)
def search_book(bookname, search_term=None):
""" Search for a pattern inside a book. """
if not bookname in os.listdir(BOOK_PATH):
abort(404)
if not search_term:
abort(400)
# TODO: Verify that the book has indeed been indexed
results = search_index.search(search_term, bookname=bookname)
out_dict = {
'q':
search_term,
'ia':
bookname,
'matches': [{
'text':
hit['snippet'],
'par': [{
'boxes': [{
'l': box[0],
't': box[1],
'r': box[2],
'b': box[3],
'page': hit['pagenum']
} for box in hit['highlights']],
'page':
hit['pagenum']
}]
} for hit in results]
}
callback = request.args.get('callback', False)
if callback:
data = str(jsonify(out_dict).data)
content = str(callback) + "({0})".format(data)
mimetype = "application/javascript"
return current_app.response_class(content, mimetype=mimetype)
else:
return jsonify(out_dict)
dict_of_token_frequency = {} # after construction, this contains the word as a key and the url:tf as a kv pair
for url in dict_of_dicts:
for word in dict_of_dicts[url]:
if word not in dict_of_token_frequency:
dict_of_token_frequency[word] = {url:dict_of_dicts[url][word]}
else:
dict_of_token_frequency[word].update({url:dict_of_dicts[url][word]})
#print(dict_of_token_frequency)
index_builder = build_index.IndexBuilder()
final_dict = index_builder.build_inverted_index(dict_of_token_frequency, driver.file_count)
final_dict = {k: unicode(v).encode("utf-8") for k,v in final_dict.iteritems()}
record1 = my_database.inverted_index_table.insert_one(final_dict)
#cursor = my_collection.find()
'''
for record in cursor:
print(record)
print("\n")
'''
url_dict = driver.url_dict
query_obj = get_input.query()
query_token = query_obj.get_query()
trimmed_query = query_obj.trim_query(query_token)
search_token = query_obj.search_query(query_token)
result_list = search_index.search(trimmed_query, my_collection, url_dict)
for link in result_list:
print(link + "\n")
def test_case_search5(self):
all_objectids = [x['objectid'] for x in search_index.all_results[1:2]]
results = search_index.search('cheese', 37.7860914634251, -122.398658184604, 37.7901490737255, -122.3934729318)
assert_equals([x['objectid'] for x in results],
all_objectids)
def test_case_search3(self):
all_objectids = [x['objectid'] for x in search_index.all_results[0:3]]
results = search_index.search('', 37.787, -122.398658184604, 37.7901490737255, -122.394)
assert_equals([x['objectid'] for x in results],
all_objectids)