def start_fix_exist_aliases_for_aliases_type(self, alias_type):
pass
self.logger = Logger(self.logger_file_name).get_log()
self.logger.info("-----------------------start-----------------------")
self.logger.info("generate api aliases for alias type=%d", alias_type)
session = self.get_session()
def start_import(self, graphClient):
self.logger = Logger(self.logger_file_name).get_log()
if not self.session:
self.session = EngineFactory.create_session()
self.graphClient = graphClient
all_relation_list = self.session.query(APIRelation).all()
for api_relation in all_relation_list:
self.import_one_relation(api_relation)
print("import api entity relation complete")
def start_import(self, graphClient):
self.logger = Logger(self.logger_file_name).get_log()
if not self.session:
self.session = EngineFactory.create_session()
self.graphClient = graphClient
all_apis = self.session.query(APIEntity).all()
for api_entity in all_apis:
self.import_one_api_entity(api_entity)
print("import api entity complete")
def start_import(self, graphClient):
self.logger = Logger(self.logger_file_name).get_log()
if not self.session:
self.session = EngineFactory.create_session()
self.graphClient = graphClient
all_apis = self.session.query(APIEntity).all()
for api_entity in all_apis:
api_id = api_entity.id
api_document_website_list = APIDocumentWebsite.get_document_website_list_by_api_id(
self.session, api_id)
self.import_document_website_to_one_entity(
api_id, api_document_website_list)
print("import api doc url complete")
def init(self, vector_dir_path="./model/"):
self.kg_models = KnowledgeGraphFeafureModels()
self.kg_models.init(vector_dir_path=vector_dir_path)
self._session = EngineFactory.create_session(echo=False)
self._entity_extractor = EntityExtractor()
# self._tf_idf_model = TFIDFModel()
# self._tf_idf_model.load(dict_type=2)
self.qa_searcher = QAEntitySearcher()
client = GraphClient(server_number=4)
self.semanticSearchAccessor = SemanticSearchAccessor(client)
self.defaultAccessor = DefaultGraphAccessor(client)
self._logger = Logger("QAResultSearch").get_log()
def __init__(self, sentence_list, logger=None):
self._api_searcher = APISearcher()
if logger is None:
self.logger = Logger("TreeView").get_log()
else:
self.logger = logger
self._tree = self.get_api_tree_from_sentence_list(sentence_list)
def start_import(self):
self.logger = Logger(self.logger_file_name).get_log()
if not self.session:
self.session = EngineFactory.create_session()
self.init_knowledge_table()
cur = ConnectionFactory.create_cursor_by_knowledge_table(
self.data_source_knowledge_table)
select_sql = "select {primary_key_name},{html_column} from {table}".format(
primary_key_name=self.primary_key_name,
html_column=self.html_column,
table=self.table)
cur.execute(select_sql)
data_list = cur.fetchall()
result_tuples = []
for i in range(0, len(data_list)):
row_data = data_list[i]
primary_key = row_data[0]
html_text = row_data[1]
if KnowledgeTableColumnMapRecord.exist_import_record(
session=self.session,
start_knowledge_table=self.data_source_knowledge_table,
end_knowledge_table=self.api_html_table,
start_row_id=primary_key,
start_row_name=self.html_column):
self.logger.info("%d has been import to new table",
primary_key)
continue
api_html_text = self.create_from_one_row_data(
primary_key, html_text)
if api_html_text:
api_html_text = api_html_text.create(self.session,
autocommit=False)
result_tuples.append((api_html_text, primary_key))
else:
self.logger.warn("None api_html_text fot %s", str(row_data))
continue
if len(result_tuples) > self.commit_step:
self.commit_to_server_for_column_map(map_tuples=result_tuples)
result_tuples = []
self.commit_to_server_for_column_map(map_tuples=result_tuples)
self.logger.info("import api html completed!")
cur.close()
def start_generate_aliases_for_api_type(self,
alias_type,
api_type=ALL_API):
self.logger = Logger(self.logger_file_name).get_log()
self.logger.info("-----------------------start-----------------------")
self.logger.info("generate api aliases for api type=%d alias type=%d",
api_type, alias_type)
session = self.get_session()
api_alias_generator = APIAliasGeneratorFactory.create_generator(
alias_type)
if api_alias_generator is None:
self.logger.error("Not Implemented Generator for %d ", alias_type)
return
if api_type == APIAliasesTableFuller.ALL_API:
count_api = session.query(APIEntity).count()
api_list_query = session.query(APIEntity)
else:
count_api = session.query(APIEntity).filter(
APIEntity.api_type == api_type).count()
api_list_query = session.query(APIEntity).filter(
APIEntity.api_type == api_type)
start_index_list = range(0, count_api, self.commit_step)
for start_index in start_index_list:
end_index = min(start_index + self.commit_step, count_api)
for api in api_list_query.all()[start_index:end_index]:
try:
api_alias_list = api_alias_generator.generate_aliases(api)
self.add_aliases_to_api_entity(api, api_alias_list,
session)
except Exception:
traceback.print_exc()
self.logger.info("complete %d-%d", start_index, end_index)
session.commit()
self.logger.info("complete all")
class APIRelationImporter:
def __init__(self):
self.logger_file_name = "import_api_relation_to_neo4j"
self.logger = None
self.graphClient = None
self.session = None
def start_import(self, graphClient):
self.logger = Logger(self.logger_file_name).get_log()
if not self.session:
self.session = EngineFactory.create_session()
self.graphClient = graphClient
all_relation_list = self.session.query(APIRelation).all()
for api_relation in all_relation_list:
self.import_one_relation(api_relation)
print("import api entity relation complete")
def import_one_relation(self, api_relation):
if api_relation is not None:
relation_type = APIRelation.get_type_string(
api_relation.relation_type)
start_api_id = api_relation.start_api_id
end_api_id = api_relation.end_api_id
start_node = self.graphClient.find_node_by_api_id(start_api_id)
end_node = self.graphClient.find_node_by_api_id(end_api_id)
if start_node is not None and end_node is not None:
if relation_type == "belong to":
relation_type = self.transfer_belong_to_type(start_api_id)
relationship = Relationship(end_node, relation_type,
start_node)
self.graphClient.graph.merge(relationship)
else:
relationship = Relationship(start_node, relation_type,
end_node)
self.graphClient.graph.merge(relationship)
self.logger.info("create or merge relation" +
str(relationship))
else:
self.logger.warn(
"fail create relation because start node or end node is none."
)
else:
self.logger.warn(
"fail create relation because api relation is none.")
def transfer_belong_to_type(self, start_api_id):
if start_api_id is not None:
start_api_entity = APIEntity.find_by_id(self.session, start_api_id)
if start_api_entity is not None:
start_api_type = start_api_entity.api_type
type_str = APIEntity.get_simple_type_string(start_api_type)
type_str = type_str.replace("api", "")
relation_str = "has" + type_str
return relation_str
return None
def init_importer(self, client=None):
if client is None:
return
self.logger = Logger(self.logger_file_name).get_log()
self.wikidata_accessor = WikiDataGraphAccessor(client)
property_name_dict = {}
session = EngineFactory.create_session()
wikidata_property_list = session.query(
WikiDataProperty.wd_item_id, WikiDataProperty.property_name).all()
for wikipedia_property in wikidata_property_list:
property_name_dict[wikipedia_property.
wd_item_id] = wikipedia_property.property_name
print("load all property name")
self.wiki_creator = WikiDataNodeCreator(
wikidata_graph_accessor=self.wikidata_accessor,
init_property_from_file=False)
self.wiki_creator.init_property_clean_Util(
property_name_dict=property_name_dict)
print("init wiki_creator")
class APIDocumentWebsiteImporter:
def __init__(self):
self.logger_file_name = "import_api_document_website_to_neo4j"
self.logger = None
self.graphClient = None
self.session = None
def start_import(self, graphClient):
self.logger = Logger(self.logger_file_name).get_log()
if not self.session:
self.session = EngineFactory.create_session()
self.graphClient = graphClient
all_apis = self.session.query(APIEntity).all()
for api_entity in all_apis:
api_id = api_entity.id
api_document_website_list = APIDocumentWebsite.get_document_website_list_by_api_id(
self.session, api_id)
self.import_document_website_to_one_entity(
api_id, api_document_website_list)
print("import api doc url complete")
def import_document_website_to_one_entity(self, api_id,
api_document_website_list):
if api_id is not None and api_document_website_list is not None:
node = self.graphClient.find_node_by_api_id(api_id)
if node is not None:
index = 1
for each in api_document_website_list:
website = each[0]
key = "api_document_website#" + str(index)
index += 1
if key not in dict(node).keys():
node[key] = website
self.graphClient.push_node(node)
self.logger.info("add document website property " + str(node))
else:
self.logger.warn(
"fail to add document property because node is none")
else:
self.logger.warn(
"fail to add document property because api id is none")
class AllAPIEntityImporter:
def __init__(self):
self.logger_file_name = "import_api_entity_to_neo4j"
self.logger = None
self.graphClient = None
self.session = None
def start_import(self, graphClient):
self.logger = Logger(self.logger_file_name).get_log()
if not self.session:
self.session = EngineFactory.create_session()
self.graphClient = graphClient
all_apis = self.session.query(APIEntity).all()
for api_entity in all_apis:
self.import_one_api_entity(api_entity)
print("import api entity complete")
def import_one_api_entity(self, api_entity):
api_type = APIEntity.get_simple_type_string(api_entity.api_type)
print(api_type)
property_dict = api_entity.__dict__
property_dict.pop("_sa_instance_state")
property_dict["api_id"] = property_dict.pop("id")
builder = NodeBuilder()
builder.add_entity_label().add_property(
**property_dict).add_api_label().add_label(api_type)
node = builder.build()
# when the node's qualifier name is "byte","int", the print will cause ValueError: Invalid identifier error
# print node
try:
self.graphClient.create_or_update_api_node(node=node)
self.logger.info('create node for api entity %s',
property_dict['api_id'])
except Exception, error:
self.logger.warn('-%s- fail for create node for api entity ',
property_dict['api_id'])
self.logger.exception('this is an exception message')
from db.engine_factory import ConnectionFactory, EngineFactory
from db.model import KnowledgeTableRowMapRecord, APIRelation, KnowledgeTableColumnMapRecord
from db.model_factory import KnowledgeTableFactory
from shared.logger_util import Logger
logger = Logger("import_belong_to_relation_for_jdk_method").get_log()
cur = ConnectionFactory.create_cursor_for_jdk_importer()
session = EngineFactory.create_session()
jdk_method_knowledge_table = KnowledgeTableFactory.get_jdk_method_table(
session)
jdk_class_knowledge_table = KnowledgeTableFactory.get_jdk_class_table(session)
api_knowledge_table = KnowledgeTableFactory.get_api_entity_table(session)
api_relation_table = KnowledgeTableFactory.get_api_relation_table(session)
COMMIT_STEP = 5000
def is_imported(row_id):
if KnowledgeTableColumnMapRecord.exist_import_record(
session, jdk_method_knowledge_table, api_relation_table, row_id,
"class_id"):
return True
else:
return False
def create_method_belong_to_relation(old_method_id, old_class_id):
logger.info("old_method_id=%d old_class_id=%d", old_method_id,
from shared.logger_util import Logger
from skgraph.graph.accessor.graph_accessor import GraphAccessor
_logger = Logger("QAGraphAccessor").get_log()
class QAGraphAccessor(GraphAccessor):
def entity_linking_by_fulltext_search(self, name, top_number=50):
"""
linking a name to a node
:param name: the name search
:param top_number: the top number of search result,defalt is top 10
:return value is a list,each element is a dict d,
get the node from d['node'],get the score of the result from d['weight']
"""
try:
query = "call apoc.index.search('entity', '{name}', {top_number}) YIELD node, weight return node,weight"
query = query.format(name=name, top_number=top_number)
record_list = self.graph.run(query)
result_tuple = []
for record in record_list:
result_tuple.append({
"node": record["node"],
"weight": record["weight"]
})
return result_tuple
except Exception, error:
_logger.exception("parameters=%r", name)
return []
import codecs
import json
import os
import random
from WikiDataSPARQLWrapper import WikiDataSPARQLWrapper
from WikiDataEntityIDStorage import WikiDataEntityIDStorage
from shared.logger_util import Logger
_logger = Logger(logger="wikidata_item_id_selector").get_log()
class WikiDataItemSelector:
wikiDataEntityIDStorage = WikiDataEntityIDStorage()
seed_property_id_set = set(['P31', 'P279', 'P361', ])
'''
'P31', # instance of
'P279', # subclass of
'P361', # part of
'''
def __init__(self):
self.logger = _logger
self.wikiDataEntityIDStorage.load()
start_deny_id_list_path = os.path.join('.', 'start_deny_id_list.txt')
if os.path.isfile(start_deny_id_list_path):
print "start deny id file exist"
self.seed_deny_id_set = set(json.load(codecs.open(start_deny_id_list_path, 'r', 'utf-8')))
else:
print "start deny id file not exist"
class SentenceLevelSemanticSearch:
SORT_FUNCTION_ENTITIES_BRIDGE = 3
SORT_FUNCTION_AVERAGE_ENTITY_GRAPH_SIMILAR = 4
SORT_FUNCTION_AVERAGE_VECTOR = 2
SORT_FUNCTION_NOT_AVERAGE_GRAPH_VECTOR = 1
SORT_FUNCTION_SELECT_PART_ENTITY_LINK = 5
def __init__(self, ):
self._session = None
self.kg_models = None
self._entity_extractor = None
# self._tf_idf_model = None
self.qa_searcher = None
self.semanticSearchAccessor = None
self.defaultAccessor = None
self._logger = None
def init(self, vector_dir_path="./model/"):
self.kg_models = KnowledgeGraphFeafureModels()
self.kg_models.init(vector_dir_path=vector_dir_path)
self._session = EngineFactory.create_session(echo=False)
self._entity_extractor = EntityExtractor()
# self._tf_idf_model = TFIDFModel()
# self._tf_idf_model.load(dict_type=2)
self.qa_searcher = QAEntitySearcher()
client = GraphClient(server_number=4)
self.semanticSearchAccessor = SemanticSearchAccessor(client)
self.defaultAccessor = DefaultGraphAccessor(client)
self._logger = Logger("QAResultSearch").get_log()
def semantic_search(self,
query_text,
each_np_candidate_entity_num=50,
sort_function=SORT_FUNCTION_SELECT_PART_ENTITY_LINK,
sentence_limit=20,
weight_context_sim=0.6,
weight_graph_sim=0.4,
):
try:
qa_info_manager = self.get_candidate_sentences(query_text,
each_np_candidate_entity_num=each_np_candidate_entity_num)
# sentence_list=qa_info_manager.get_candidate_sentence_list()
#
# entity_for_qa_set
# entity_for_qa_set.print_informat()
# entity_list = entity_for_qa_set.get_entity_node_list()
# chunk_to_related_entity_list_map = entity_for_qa_set.keyword_2_entitynodemap
self._logger.info("entity_list =%d sentence_list=%d" % (
qa_info_manager.get_entity_size(), qa_info_manager.get_sentence_size()))
# for n in entity_list:
# print("entity", n)
new_sentence_list = []
# if sort_function == SentenceLevelSemanticSearch.SORT_FUNCTION_NOT_AVERAGE_GRAPH_VECTOR:
# new_sentence_list = self.sort_sentence_by_build_graph_vector_for_query_in_semantic_weight(query_text,
# sentence_list=sentence_list,
# entity_list=entity_list,
# weight_context_sim=weight_context_sim,
# weight_graph_sim=weight_graph_sim)
#
# if sort_function == SentenceLevelSemanticSearch.SORT_FUNCTION_AVERAGE_VECTOR:
# new_sentence_list = self.sort_sentence_by_build_average_graph_vector_for_query(query_text,
# sentence_list=sentence_list,
# entity_list=entity_list,
# weight_context_sim=weight_context_sim,
# weight_graph_sim=weight_graph_sim
# )
#
# if sort_function == SentenceLevelSemanticSearch.SORT_FUNCTION_ENTITIES_BRIDGE:
# new_sentence_list = self.sort_sentence_by_entities_as_bridge(query_text,
# sentence_list=sentence_list,
# entity_list=entity_list,
# weight_context_sim=weight_context_sim,
# weight_graph_sim=weight_graph_sim)
#
# if sort_function == SentenceLevelSemanticSearch.SORT_FUNCTION_AVERAGE_ENTITY_GRAPH_SIMILAR:
# new_sentence_list = self.sort_sentence_by_entities_for_graph_similarity_as_bridge(query_text,
# sentence_list=sentence_list,
# entity_list=entity_list,
# weight_context_sim=weight_context_sim,
# weight_graph_sim=weight_graph_sim)
if sort_function == SentenceLevelSemanticSearch.SORT_FUNCTION_SELECT_PART_ENTITY_LINK:
new_sentence_list = self.sort_sentence_by_select_part_entity_as_bridge(query_text,
qa_info_manager=qa_info_manager,
weight_context_sim=weight_context_sim,
weight_graph_sim=weight_graph_sim,
)
result_list = qa_info_manager.fill_api_id_in_result_list(new_sentence_list[:sentence_limit])
self._logger.info("result_list =%d " % len(result_list))
return result_list
except Exception:
self._logger.exception("----qaexception----")
traceback.print_exc()
return []
def get_candidate_sentences(self, query_text, each_np_candidate_entity_num=20):
chunk_list = self.get_chunk_from_text(query_text)
print("chunk num=%d %s" % (len(chunk_list), ",".join(chunk_list)))
qa_info_manager = self.search_entity_by_fulltext(chunk_list, each_np_candidate_entity_num)
qa_info_manager.start_create_node_info_collection()
print("related entity for qa", qa_info_manager)
entity_for_qa_list = qa_info_manager.get_all_entity_for_qa_list()
print("entity_for_qa_list num=%d" % len(entity_for_qa_list))
sentence_list = self.search_sentence_by_entity_for_qa_list(entity_for_qa_list)
print("sentence_list num=%d" % len(sentence_list))
qa_info_manager.add_sentence_node_list(sentence_list)
return qa_info_manager
def expand_the_chunk_by_words(self, final_chunk_list):
final_set = []
for chunk in final_chunk_list:
final_set.append(chunk)
for word in chunk.split(" "):
final_set.append(word)
print("word set", final_set)
return list(set(final_set))
def get_chunk_from_text(self, text):
final_chunk_list = self._entity_extractor.get_all_possible_key_word_from_text(text)
return final_chunk_list
def search_entity_by_fulltext(self, chunk_list, each_np_candidate_entity_num=20):
qa_info_manager = QACacheInfoManager(semanticSearchAccessor=self.semanticSearchAccessor,
defaultSearchAccessor=self.defaultAccessor,
kg_models=self.kg_models)
for chunk in chunk_list:
related_entity_list = self.qa_searcher.search_related_entity(chunk, each_np_candidate_entity_num)
qa_info_manager.add(chunk, related_entity_list)
related_entity_for_api = self.qa_searcher.search_related_entity_for_api(chunk, each_np_candidate_entity_num)
qa_info_manager.add(chunk, related_entity_for_api)
return qa_info_manager
def search_all_entity_by_fulltext_by_half(self, chunk, each_np_candidate_entity_num=20):
qa_info_manager = QACacheInfoManager(semanticSearchAccessor=self.semanticSearchAccessor,
defaultSearchAccessor=self.defaultAccessor,
kg_models=self.kg_models)
related_entity_for_api = self.qa_searcher.search_related_entity_for_api(chunk, each_np_candidate_entity_num/2)
qa_info_manager.add(chunk, related_entity_for_api)
related_entity_list = self.qa_searcher.search_related_entity(chunk, each_np_candidate_entity_num/2)
qa_info_manager.add(chunk, related_entity_list)
return qa_info_manager
def search_sentence_by_entity_for_qa_list(self, entity_for_qa_list):
entity_id_string_list = [str(entity_for_qa.kg_id) for entity_for_qa in entity_for_qa_list]
entity_id_string_list = list(set(entity_id_string_list))
return self.semanticSearchAccessor.search_sentence_by_entity_list(entity_id_string_list=entity_id_string_list)
def get_relation_by_nodes(self, node_list):
return self.semanticSearchAccessor.get_nodes_relation(node_list)
def sort_sentence_by_entities_as_bridge(self, question,
sentence_list,
entity_list,
weight_context_sim=0.5,
weight_graph_sim=0.5
):
self._logger.info("run sort_sentence_by_entities_as_bridge get result=%d" % len(sentence_list))
question_vec = self.kg_models.get_question_entity_vector(question)
entity_vec_list, entity_graph_vec_list = self.kg_models.get_vectors_for_entity_list(entity_list)
sentence_vec_list, sentence_graph_vec_list = self.kg_models.get_vectors_for_entity_list(sentence_list)
qe_sim_np = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_vec, entity_vec_list)
qe_sim_np = qe_sim_np / qe_sim_np.sum()
kg_context_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(entity_vec_list,
sentence_vec_list)
kg_graph_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(entity_graph_vec_list,
sentence_graph_vec_list)
qs_context_sim = weight_context_sim * qe_sim_np * kg_context_sim
qs_graph_sim = weight_graph_sim * qe_sim_np * kg_graph_sim
qs_sim = qs_context_sim + qs_graph_sim
qs_sim = qs_sim.tolist()[0]
qs_context_sim = qs_context_sim.tolist()[0]
qs_graph_sim = qs_graph_sim.tolist()[0]
for sum_sim, sentence, context_sim, graph_sim in zip(qs_sim, sentence_list, qs_context_sim, qs_graph_sim):
sentence["qs_sim"] = sum_sim
sentence["qs_context_sim"] = context_sim
sentence["qs_graph_sim"] = graph_sim
result = []
for sentence in sentence_list:
result.append({
"kg_id": self.defaultAccessor.get_id_for_node(sentence),
"sentence_id": sentence["sentence_id"],
"sentence_type": sentence["sentence_type_code"],
"text": sentence["sentence_text"],
"qs_sim": sentence["qs_sim"],
"qs_context_sim": sentence["qs_context_sim"],
"qs_graph_sim": sentence["qs_graph_sim"]
})
self._logger.info("run sort_sentence_by_entities_as_bridge get result num=%d" % len(result))
result.sort(key=lambda k: (k.get('qs_sim', 0)), reverse=True)
return result
def sort_sentence_by_entities_for_graph_similarity_as_bridge(self, question,
sentence_list,
entity_list,
weight_context_sim=0.5,
weight_graph_sim=0.5
):
self._logger.info(
"run sort_sentence_by_entities_for_graph_similarity_as_bridge get result=%d" % len(sentence_list))
question_context_vec = self.kg_models.get_question_entity_vector(question)
entity_vec_list, entity_graph_vec_list = self.kg_models.get_vectors_for_entity_list(entity_list)
sentence_vec_list, sentence_graph_vec_list = self.kg_models.get_vectors_for_entity_list(sentence_list)
qe_sim_np = np.ones((1, len(entity_list)))
qe_sim_np = qe_sim_np / qe_sim_np.sum()
qs_context_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
sentence_vec_list)
kg_graph_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(entity_graph_vec_list,
sentence_graph_vec_list)
qs_context_sim = weight_context_sim * qs_context_sim
qs_graph_sim = weight_graph_sim * qe_sim_np * kg_graph_sim
qs_sim = qs_context_sim + qs_graph_sim
qs_sim = qs_sim.tolist()[0]
qs_context_sim = qs_context_sim.tolist()[0]
qs_graph_sim = qs_graph_sim.tolist()[0]
for sum_sim, sentence, context_sim, graph_sim in zip(qs_sim, sentence_list, qs_context_sim, qs_graph_sim):
sentence["qs_sim"] = sum_sim
sentence["qs_context_sim"] = context_sim
sentence["qs_graph_sim"] = graph_sim
result = []
for sentence in sentence_list:
result.append({
"kg_id": self.defaultAccessor.get_id_for_node(sentence),
"sentence_id": sentence["sentence_id"],
"sentence_type": sentence["sentence_type_code"],
"text": sentence["sentence_text"],
"qs_sim": sentence["qs_sim"],
"qs_context_sim": sentence["qs_context_sim"],
"qs_graph_sim": sentence["qs_graph_sim"]
})
self._logger.info("run sort_sentence_by_entities_as_bridge get result num=%d" % len(result))
result.sort(key=lambda k: (k.get('qs_sim', 0)), reverse=True)
print("sorted result")
for t in result:
print("test sort", t)
print(result[:100])
return result
def sort_sentence_by_build_average_graph_vector_for_query(self, question, sentence_list, entity_list,
weight_context_sim=0.5, weight_graph_sim=0.5
):
self._logger.info(
"run sort_sentence_by_build_average_graph_vector_for_query get sentence_list=%d" % len(sentence_list))
kg_models = self.kg_models
question_context_vec = kg_models.get_question_entity_vector(question)
entity_vec_list, entity_graph_vec_list = self.kg_models.get_vectors_for_entity_list(entity_list)
sentence_vec_list, sentence_graph_vec_list = self.kg_models.get_vectors_for_entity_list(sentence_list)
entity_list, entity_vec_list, entity_graph_vec_list = self.remove_the_not_related_entity(entity_graph_vec_list,
entity_list,
entity_vec_list,
question_context_vec)
query_graph_vector = kg_models.get_question_graph_vector_by_average_all_entities(
question=question,
entity_graph_vec_list=entity_graph_vec_list)
qs_context_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
sentence_vec_list)
qs_graph_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(query_graph_vector,
sentence_graph_vec_list)
qs_context_sim = weight_context_sim * qs_context_sim
qs_graph_sim = weight_graph_sim * qs_graph_sim
qs_sim = qs_context_sim + qs_graph_sim
qs_sim = qs_sim.tolist()[0]
qs_context_sim = qs_context_sim.tolist()[0]
qs_graph_sim = qs_graph_sim.tolist()[0]
for sum_sim, sentence, context_sim, graph_sim in zip(qs_sim, sentence_list, qs_context_sim, qs_graph_sim):
sentence["qs_sim"] = sum_sim
sentence["qs_context_sim"] = context_sim
sentence["qs_graph_sim"] = graph_sim
result = []
for sentence in sentence_list:
result.append({
"kg_id": self.defaultAccessor.get_id_for_node(sentence),
"sentence_id": sentence["sentence_id"],
"text": sentence["sentence_text"],
"sentence_type": sentence["sentence_type_code"],
"qs_sim": sentence["qs_sim"],
"qs_context_sim": sentence["qs_context_sim"],
"qs_graph_sim": sentence["qs_graph_sim"]
})
self._logger.info("run sort_sentence_by_build_average_graph_vector_for_query get result num=%d" % len(result))
result.sort(key=lambda k: (k.get('qs_sim', 0)), reverse=True)
return result
def sort_sentence_by_select_part_entity_as_bridge(self, question,
qa_info_manager,
# sentence_list,
# entity_list,
weight_context_sim=0.6,
weight_graph_sim=0.4,
# chunk_to_related_entity_list_map=None,
):
self._logger.info(
"run sort part entity result=%d" % qa_info_manager.get_sentence_size())
print("entity for node")
qa_info_manager.print_entities()
print("sentence for node")
# qa_info_manager.print_sentences()
entity_info_collection = qa_info_manager.get_entity_info_collection()
sentence_info_collection = qa_info_manager.get_sentence_info_collection()
entity_info_collection.init_vectors(self.kg_models)
sentence_info_collection.init_vectors(self.kg_models)
sentence_list = sentence_info_collection.get_entity_list()
entity_vec_list = entity_info_collection.get_entity_context_list()
entity_graph_vec_list = entity_info_collection.get_entity_graph_list()
entity_list = entity_info_collection.get_entity_list()
sentence_vec_list = sentence_info_collection.get_entity_context_list()
sentence_graph_vec_list = sentence_info_collection.get_entity_graph_list()
question_context_vec = self.kg_models.get_question_entity_vector(question)
entity_list, entity_vec_list, entity_graph_vec_list = self.get_top_related_entity_info_list(
question_context_vec=question_context_vec, qa_info_manager=qa_info_manager)
# entity_list, entity_vec_list, entity_graph_vec_list = self.remove_the_not_related_entity_by_only_save_one_for_each(
# entity_graph_vec_list=entity_graph_vec_list, entity_vec_list=entity_vec_list, entity_list=entity_list,
# question_context_vec=question_context_vec,
# qa_info_manager=qa_info_manager
#
# )
qs_context_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
sentence_vec_list)
# todo:change to the average graph similarity
# qs_graph_sim = self.get_graph_similarity_by_average_entity_graph_vector(entity_graph_vec_list, question,
# sentence_graph_vec_list)
qs_graph_sim = self.get_query_to_sentence_graph_sim_by_select_top_enttity(entity_graph_vec_list, entity_list,
entity_vec_list,
sentence_graph_vec_list,
sentence_vec_list)
qs_context_sim = weight_context_sim * qs_context_sim
qs_graph_sim = weight_graph_sim * qs_graph_sim
qs_sim = qs_context_sim + qs_graph_sim
qs_sim = qs_sim.tolist()[0]
qs_context_sim = qs_context_sim.tolist()[0]
qs_graph_sim = qs_graph_sim.tolist()[0]
for sum_sim, sentence, context_sim, graph_sim in zip(qs_sim, sentence_list, qs_context_sim, qs_graph_sim):
sentence["qs_sim"] = sum_sim
sentence["qs_context_sim"] = context_sim
sentence["qs_graph_sim"] = graph_sim
result = []
for sentence in sentence_list:
result.append({
"kg_id": self.defaultAccessor.get_id_for_node(sentence),
"sentence_id": sentence["sentence_id"],
"sentence_type": sentence["sentence_type_code"],
"text": sentence["sentence_text"],
"qs_sim": sentence["qs_sim"],
"qs_context_sim": sentence["qs_context_sim"],
"qs_graph_sim": sentence["qs_graph_sim"]
})
self._logger.info("run sort_sentence_by_entities_as_bridge get result num=%d" % len(result))
result.sort(key=lambda k: (k.get('qs_sim', 0)), reverse=True)
print(result[:100])
return result
def get_graph_similarity_by_average_entity_graph_vector(self, entity_graph_vec_list, question,
sentence_graph_vec_list):
query_graph_vector = self.kg_models.get_question_graph_vector_by_average_all_entities(
question=question,
entity_graph_vec_list=entity_graph_vec_list)
qs_graph_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(query_graph_vector,
sentence_graph_vec_list)
return qs_graph_sim
def get_graph_similarity_average_entity_graph_vector_similarity(self, entity_graph_vec_list, question,
sentence_graph_vec_list):
# query_graph_vector = self.kg_models.get_question_graph_vector_by_average_all_entities(
# question=question,
# entity_graph_vec_list=entity_graph_vec_list)
qs_graph_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(sentence_graph_vec_list,
entity_graph_vec_list)
return np.mean(qs_graph_sim, axis=1)
def get_query_to_sentence_graph_sim_by_select_top_enttity(self, entity_graph_vec_list, entity_list, entity_vec_list,
sentence_graph_vec_list, sentence_vec_list):
# kg_se_graph_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(sentence_graph_vec_list,
# entity_graph_vec_list,
# )
kg_se_context_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(
sentence_vec_list,
entity_vec_list)
# TODO
# kg_se_sim = 0.5 * kg_se_graph_sim + 0.5 * kg_se_context_sim
kg_se_sim = kg_se_context_sim
print("final entity list", len(entity_list), entity_list)
select_linking_entity_num = min(5, len(entity_list))
onehot_maxsim_se_matrix = MatrixCalculation.get_most_similar_top_n_entity_as_matrix(
top_n=select_linking_entity_num, s_e_similarity_matrix=kg_se_sim)
s_query_graph_vec_matrix = onehot_maxsim_se_matrix * np.matrix(
entity_graph_vec_list) / select_linking_entity_num
qs_graph_sim = MatrixCalculation.compute_cossin_for_one_to_one_in_two_list_normalize(sentence_graph_vec_list,
s_query_graph_vec_matrix.getA())
return qs_graph_sim
def remove_the_not_related_entity_by_only_save_one_for_each(self, entity_graph_vec_list, entity_list,
entity_vec_list, question_context_vec,
qa_info_manager):
chunk_to_related_entity_list_map = qa_info_manager.keyword_2_entitynodemap
qe_sim_np = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
entity_vec_list)
entity_info_sumary_list = []
for (entity, sim, entity_vec, entity_graph_vec) in zip(entity_list, qe_sim_np.getA()[0], entity_vec_list,
entity_graph_vec_list):
print("after first removing sim=", sim, "entity=", entity)
entity_info_sumary_list.append({"entity": entity,
"sim": sim,
"entity_vec": entity_vec,
"entity_graph_vec": entity_graph_vec
})
entity_info_sumary_list.sort(key=lambda k: (k.get('sim', 0)), reverse=True)
valid_word_set = set([])
word_to_related_entity_list_map = {}
for chunk, related_entity_list in chunk_to_related_entity_list_map.items():
word = chunk
if word not in valid_word_set:
valid_word_set.add(word)
word_to_related_entity_list_map[word] = related_entity_list
else:
word_to_related_entity_list_map[word].extend(related_entity_list)
# clean_entity_info_list = self.get_clean_entity_for_each_word_by_max_similarity(entity_info_sumary_list,
# word_to_related_entity_list_map)
#
clean_entity_info_list = self.get_clean_entity_for_each_word_by_max_n_similarity(entity_info_sumary_list,
word_to_related_entity_list_map)
new_entity_list = []
new_entity_graph_vec_list = []
new_entity_vec_list = []
for entity_info_sumary in clean_entity_info_list:
new_entity_list.append(entity_info_sumary["entity"])
new_entity_graph_vec_list.append(entity_info_sumary["entity_graph_vec"])
new_entity_vec_list.append(entity_info_sumary["entity_vec"])
print("final save sim=", entity_info_sumary["sim"], "entity=", entity_info_sumary["entity"])
return new_entity_list, new_entity_vec_list, new_entity_graph_vec_list
def get_top_related_entity_info_list(self, question_context_vec,
qa_info_manager):
node_info_collection = qa_info_manager.get_node_info_collection()
node_info_collection.fill_each_entity_with_similary_to_question(question_context_vec)
node_info_collection.sort_by_qe_sim()
# selected_entity_info_list = qa_info_manager.get_top_node_info_by_each_keywords_three_different_type()
selected_entity_info_list = qa_info_manager.get_top_node_info_by_each_keywords()
new_entity_list = []
new_entity_vec_list = []
new_entity_graph_vec_list = []
for node_info in selected_entity_info_list:
new_entity_list.append(node_info.entity_node)
new_entity_vec_list.append(node_info.entity_context_vec)
new_entity_graph_vec_list.append(node_info.entity_graph_vec)
return new_entity_list, new_entity_vec_list, new_entity_graph_vec_list
def get_clean_entity_for_each_word_by_max_n_similarity(self, entity_info_sumary_list,
word_to_related_entity_list_map):
clean_entity_kg_id_list = set([])
print("start get_clean_entity_infi_sumary_list ")
word_name_entity_mark = {}
for valid_word, related_entity_list in word_to_related_entity_list_map.items():
print("valid word=", valid_word)
entity_info_list = self.get_first_from_entity_info_sumary_list_and_in_related_entity_list(
entity_info_sumary_list, related_entity_list, 3)
# for entity_info in entity_info_list:
print("get candidate for word=", valid_word, entity_info_list)
word_name_entity_mark[valid_word] = entity_info_list
clean_entity_info_list = []
clean_entity_kg_id_list = set([])
for word, entity_info_list in word_name_entity_mark.items():
for entity_info in entity_info_list:
kg_id = self.defaultAccessor.get_id_for_node(entity_info["entity"])
if kg_id not in clean_entity_kg_id_list:
clean_entity_info_list.append(entity_info)
clean_entity_kg_id_list.add(kg_id)
print("valid word=", word, entity_info["entity"])
return clean_entity_info_list
def get_clean_entity_for_each_word_by_max_similarity(self, entity_info_sumary_list,
word_to_related_entity_list_map):
clean_entity_kg_id_list = set([])
print("start get_clean_entity_infi_sumary_list ")
word_name_entity_mark = {}
for valid_word, related_entity_list in word_to_related_entity_list_map.items():
print("valid word=", valid_word)
entity_info_list = self.get_first_from_entity_info_sumary_list_and_in_related_entity_list(
entity_info_sumary_list, related_entity_list)
for entity_info in entity_info_list:
print("get candidate for word=", valid_word, entity_info["entity"])
word_name_entity_mark[valid_word] = entity_info
clean_entity_info_list = []
clean_entity_kg_id_list = set([])
for word, entity_info in word_name_entity_mark.items():
kg_id = self.defaultAccessor.get_id_for_node(entity_info["entity"])
if kg_id not in clean_entity_kg_id_list:
clean_entity_info_list.append(entity_info)
clean_entity_kg_id_list.add(kg_id)
print("valid word=", word, entity_info["entity"])
return clean_entity_info_list
def get_clean_entity_infi_sumary_list(self, entity_info_sumary_list, word_to_related_entity_list_map):
clean_entity_kg_id_list = set([])
print("start get_clean_entity_infi_sumary_list ")
word_name_entity_mark = {}
for valid_word, related_entity_list in word_to_related_entity_list_map.items():
print("valid word=", valid_word)
entity_info_list = self.get_first_from_entity_info_sumary_list_and_in_related_entity_list(
entity_info_sumary_list, related_entity_list)
for entity_info in entity_info_list:
kg_id = self.defaultAccessor.get_id_for_node(entity_info["entity"])
print("get candidate for word=", valid_word, entity_info["entity"])
if kg_id not in clean_entity_kg_id_list:
if valid_word not in word_name_entity_mark.keys():
word_name_entity_mark[valid_word] = entity_info
else:
old_entity_info = word_name_entity_mark[valid_word]
if entity_info["sim"] > old_entity_info["sim"]:
word_name_entity_mark[valid_word] = entity_info
for seperate_name in valid_word.split(" "):
if seperate_name not in word_name_entity_mark.keys():
word_name_entity_mark[seperate_name] = entity_info
else:
old_entity_info = word_name_entity_mark[seperate_name]
if entity_info["sim"] > old_entity_info["sim"]:
word_name_entity_mark[seperate_name] = entity_info
clean_entity_kg_id_list.add(kg_id)
clean_entity_info_list = []
clean_entity_kg_id_list = set([])
for word, entity_info in word_name_entity_mark.items():
kg_id = self.defaultAccessor.get_id_for_node(entity_info["entity"])
if kg_id not in clean_entity_kg_id_list:
clean_entity_info_list.append(entity_info)
clean_entity_kg_id_list.add(kg_id)
print("valid word=", word, entity_info["entity"])
return clean_entity_info_list
def remove_the_not_related_entity(self, entity_graph_vec_list, entity_list, entity_vec_list, question_context_vec):
qe_sim_np = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
entity_vec_list)
print("qeustion to entity similary")
new_entity_list = []
new_entity_vec_list = []
new_entity_graph_vec_list = []
qe_sim_clean = []
for (entity, sim, entity_vec, entity_graph_vec) in zip(entity_list, qe_sim_np.getA()[0], entity_vec_list,
entity_graph_vec_list):
print("sim=", sim, "entity=", entity)
if sim > MIN_RELATED_ENTITY_SIMILARITY:
print("adding ", entity)
new_entity_list.append(entity)
new_entity_vec_list.append(entity_vec)
new_entity_graph_vec_list.append(entity_graph_vec)
qe_sim_clean.append(sim)
entity_list = new_entity_list
entity_vec_list = new_entity_vec_list
entity_graph_vec_list = new_entity_graph_vec_list
new_entity_list = []
new_entity_vec_list = []
new_entity_graph_vec_list = []
entity_info_sumary_list = []
for (entity, sim, entity_vec, entity_graph_vec) in zip(entity_list, qe_sim_clean, entity_vec_list,
entity_graph_vec_list):
print("after first removing sim=", sim, "entity=", entity)
entity_info_sumary_list.append({"entity": entity,
"sim": sim,
"entity_vec": entity_vec,
"entity_graph_vec": entity_graph_vec
})
entity_info_sumary_list.sort(key=lambda k: (k.get('sim', 0)), reverse=True)
api_class_name_set = set([])
new_entity_info_sumary_list = []
for entity_info_sumary in entity_info_sumary_list:
if entity_info_sumary["entity"].has_label("api"):
qualified_name = entity_info_sumary["entity"]["qualified_name"]
if qualified_name in api_class_name_set:
continue
if "(" in qualified_name:
simple_name = qualified_name.split("(")[0]
class_name = ".".join(simple_name.split(".")[:-1])
if class_name in api_class_name_set:
continue
else:
api_class_name_set.add(class_name)
new_entity_info_sumary_list.append(entity_info_sumary)
else:
api_class_name_set.add(qualified_name)
new_entity_info_sumary_list.append(entity_info_sumary)
else:
new_entity_info_sumary_list.append(entity_info_sumary)
for entity_info_sumary in new_entity_info_sumary_list:
new_entity_list.append(entity_info_sumary["entity"])
new_entity_graph_vec_list.append(entity_info_sumary["entity_graph_vec"])
new_entity_vec_list.append(entity_info_sumary["entity_vec"])
print("final save sim=", entity_info_sumary["sim"], "entity=", entity_info_sumary["entity"])
return new_entity_list, new_entity_vec_list, new_entity_graph_vec_list
def sort_sentence_by_build_graph_vector_for_query_in_semantic_weight(self, question, sentence_list, entity_list,
weight_context_sim=0.5, weight_graph_sim=0.5
):
self._logger.info(
"run sort_sentence_by_build_graph_vector_for_query_in_semantic_weight get sentence_list=%d" % len(
sentence_list))
kg_models = self.kg_models
question_context_vec = kg_models.get_question_entity_vector(question)
entity_vec_list, entity_graph_vec_list = self.kg_models.get_vectors_for_entity_list(entity_list)
sentence_vec_list, sentence_graph_vec_list = self.kg_models.get_vectors_for_entity_list(sentence_list)
query_graph_vector = kg_models.get_question_graph_vector_by_semantic_weight_all_entities(
question_context_vec=question_context_vec,
entity_context_vec_list=entity_vec_list,
entity_graph_vec_list=entity_graph_vec_list)
qs_context_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
sentence_vec_list)
qs_graph_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(query_graph_vector,
sentence_graph_vec_list)
qs_context_sim = weight_context_sim * qs_context_sim
qs_graph_sim = weight_graph_sim * qs_graph_sim
qs_sim = qs_context_sim + qs_graph_sim
qs_sim = qs_sim.tolist()[0]
qs_context_sim = qs_context_sim.tolist()[0]
qs_graph_sim = qs_graph_sim.tolist()[0]
for sum_sim, sentence, context_sim, graph_sim in zip(qs_sim, sentence_list, qs_context_sim, qs_graph_sim):
sentence["qs_sim"] = sum_sim
sentence["qs_context_sim"] = context_sim
sentence["qs_graph_sim"] = graph_sim
result = []
for sentence in sentence_list:
result.append({
"kg_id": self.defaultAccessor.get_id_for_node(sentence),
"sentence_id": sentence["sentence_id"],
"text": sentence["sentence_text"],
"qs_sim": sentence["qs_sim"],
"qs_context_sim": sentence["qs_context_sim"],
"qs_graph_sim": sentence["qs_graph_sim"]
})
self._logger.info(
"run sort_sentence_by_build_graph_vector_for_query_in_semantic_weight get result=%d" % len(result))
result.sort(key=lambda k: (k.get('qs_sim', 0)), reverse=True)
return result
def get_all_entity(self, entity_for_qa_list):
entity_id_string_list = [str(entity_for_qa.kg_id) for entity_for_qa in entity_for_qa_list]
entity_id_string_list = list(set(entity_id_string_list))
return self.semanticSearchAccessor.get_all_entity(entity_id_string_list=entity_id_string_list)
def get_first_from_entity_info_sumary_list_and_in_related_entity_list(self, entity_info_sumary_list,
related_entity_list, top_relate_entity_num=1):
return_result_list = []
for entity_info in entity_info_sumary_list:
kg_id = self.defaultAccessor.get_id_for_node(entity_info["entity"])
entity = self.get_entity_from_entity_list_by_kgid(kg_id, related_entity_list)
if entity is not None:
return_result_list.append(entity_info)
if len(return_result_list) >= top_relate_entity_num:
return return_result_list
return []
def get_entity_from_entity_list_by_kgid(self, kg_id, related_entity_list):
for related_entity in related_entity_list:
if related_entity.kg_id == kg_id:
return related_entity
return None
from db.engine_factory import EngineFactory
from db.cursor_factory import ConnectionFactory
from db.model import KnowledgeTableRowMapRecord, APIDocumentWebsite, KnowledgeTableColumnMapRecord
from db.model_factory import KnowledgeTableFactory
from shared.logger_util import Logger
logger = Logger("import_doc_website_for_jdk_package").get_log()
cur = ConnectionFactory.create_cursor_for_jdk_importer()
session = EngineFactory.create_session()
jdk_package_knowledge_table = KnowledgeTableFactory.get_jdk_package_table(
session)
api_knowledge_table = KnowledgeTableFactory.get_api_entity_table(session)
api_document_website_table = KnowledgeTableFactory.get_api_document_website_table(
session)
def create_doc_website_relation(old_package_id, doc_website):
if doc_website is None:
logger.error("no doc_website for %d", old_package_id)
return None
new_package_api_entity_id = KnowledgeTableRowMapRecord.get_end_row_id(
session=session,
start_knowledge_table=jdk_package_knowledge_table,
end_knowledge_table=api_knowledge_table,
start_row_id=old_package_id)
if new_package_api_entity_id is None:
logger.error("no new_package_api_entity_id for %d", old_package_id)
return None
from tagme import wiki_title
from factory import NodeBuilder
from graph_accessor import GraphAccessor, DefaultGraphAccessor
from shared.logger_util import Logger
_logger = Logger("WikipediaGraphAccessor").get_log()
class WikipediaGraphAccessor(GraphAccessor):
def create_wikipedia_item_entity_by_url(self, url):
if url.startswith("https://en.wikipedia.org/") == False:
return None
accessor = DefaultGraphAccessor(self)
node = accessor.get_node_by_wikipedia_link(url)
if node is None:
property_dict = {
"name": wiki_title(url.split("/")[-1]),
"url": url,
"site:enwiki": url
}
if "(" in property_dict["name"]:
alias = [(property_dict["name"].split(" ("))[0]]
property_dict["alias"] = alias
node = NodeBuilder().add_entity_label().add_label(
"wikipedia").add_property(**property_dict).build()
self.graph.merge(node)
_logger.info("create wikipedia node" + str(property_dict))
return node
from graph_accessor import DefaultGraphAccessor
from shared.logger_util import Logger
_logger = Logger("APIGraphAccessor").get_log()
class APIGraphAccessor(DefaultGraphAccessor):
"""
a GraphAccessor for API node query
"""
def get_parameter_nodes_of_method(self, method_node_id):
"""
get all parameter nodes belong to one method
:param method_node_id: method node id
:return: parameter nodes list
"""
try:
query = 'Match (n:`java method parameter`)-[r:`belong to`]->(m:`java method`) where ID(m)={method_node_id} return distinct n'.format(
method_node_id=method_node_id)
node_list = []
result = self.graph.run(query)
for n in result:
node_list.append(n['n'])
return node_list
except Exception, error:
_logger.exception()
return []
def get_parent_class_node_for_method_node(self, method_node_id):
"""
from py2neo import Relationship
from factory import NodeBuilder
from graph_accessor import GraphAccessor
from shared.logger_util import Logger
_logger = Logger("AliasGraphAccessor").get_log()
class AliasGraphAccessor(GraphAccessor):
def find_root_entity_by_alias_name(self, alias):
query = "match (n:alias)-[:alias]-(m) where n.name='{alias}' return m"
query = query.format(alias=alias)
return self.graph.run(query)
def build_alias_relation(self, alias, node):
end_node = self.find_or_create_alias_node(alias)
relation = Relationship(node, 'alias', end_node)
self.graph.merge(relation)
def find_or_create_alias_node(self, alias):
end_node = NodeBuilder().add_as_alias().add_one_property(
property_name='name', property_value=alias).build()
self.graph.merge(end_node)
return end_node
def create_alias_node_for_name(self, name, node_id):
alias_node = NodeBuilder().add_as_alias().add_one_property(
"name", name).build()
self.graph.merge(alias_node)
alias_node_link_id_list = alias_node["link_id"]
import gc
from db.engine_factory import ConnectionFactory, EngineFactory
from db.model import KnowledgeTableRowMapRecord, APIEntity, APIDocumentWebsite
from db.model_factory import KnowledgeTableFactory
from shared.logger_util import Logger
logger = Logger("import_doc_website_for_jdk_method").get_log()
cur = ConnectionFactory.create_cursor_for_jdk_importer()
session = EngineFactory.create_session()
jdk_method_knowledge_table = KnowledgeTableFactory.get_jdk_method_table(
session)
api_knowledge_table = KnowledgeTableFactory.get_api_entity_table(session)
def create_doc_website_relation(method_name, full_declaration, qualified_name,
class_website):
# print class_website
if "http://docs.oracle.com/javase/7/docs/api/" in class_website:
return None
if full_declaration:
if method_name[0] == "_":
method_name = "Z:Z" + method_name
if "(" in qualified_name and ")" in qualified_name:
left_bracket_index = qualified_name.find("(")
right_bracket_index = qualified_name.find(")")
param_str = qualified_name[left_bracket_index +
1:right_bracket_index]
if "," in param_str:
param_list = param_str.split(",")
from db.engine_factory import ConnectionFactory, EngineFactory
from db.model import KnowledgeTableRowMapRecord, APIRelation, KnowledgeTableColumnMapRecord
from db.model_factory import KnowledgeTableFactory
from shared.logger_util import Logger
logger = Logger("import_belong_to_relation_for_jdk_class").get_log()
cur = ConnectionFactory.create_cursor_for_jdk_importer()
session = EngineFactory.create_session()
jdk_package_knowledge_table = KnowledgeTableFactory.get_jdk_package_table(
session)
jdk_class_knowledge_table = KnowledgeTableFactory.get_jdk_class_table(session)
api_knowledge_table = KnowledgeTableFactory.get_api_entity_table(session)
api_relation_table = KnowledgeTableFactory.get_api_relation_table(session)
def create_class_belong_to_relation(old_class_id, old_package_id):
if old_package_id is None:
logger.error("no old_package_id for %d", old_class_id)
return None
new_class_api_entity_id = KnowledgeTableRowMapRecord.get_end_row_id(
session=session,
start_knowledge_table=jdk_class_knowledge_table,
end_knowledge_table=api_knowledge_table,
start_row_id=old_class_id)
if new_class_api_entity_id is None:
logger.error("no new_class_api_entity_id for %d", old_class_id)
return None
new_package_api_entity_id = KnowledgeTableRowMapRecord.get_end_row_id(
session=session,
from db.engine_factory import ConnectionFactory, EngineFactory
from db.model import KnowledgeTableRowMapRecord, APIEntity
from db.model_factory import KnowledgeTableFactory
from db.util.code_text_process import clean_html_text
from shared.logger_util import Logger
session = EngineFactory.create_session()
logger = Logger("import_android_class").get_log()
IMPORT_DATA_SOURCE_TABLE_NAME = "androidAPI_class"
package_knowledge_table = KnowledgeTableFactory.find_knowledge_table_by_name(
session=session, name="androidAPI_package")
class_knowledge_table = KnowledgeTableFactory.find_knowledge_table_by_name(
session=session, name=IMPORT_DATA_SOURCE_TABLE_NAME)
api_knowledge_table = KnowledgeTableFactory.find_knowledge_table_by_name(
session=session, name=APIEntity.__tablename__)
def get_package_full_name_by_old_package_id(package_id):
return KnowledgeTableRowMapRecord.get_end_row_id(
session=session,
start_knowledge_table=package_knowledge_table,
end_knowledge_table=api_knowledge_table,
start_row_id=package_id)
def get_qualified_name_of_package(package_id):
api_entity_id = get_package_full_name_by_old_package_id(
package_id=package_id)
api_entity = APIEntity.find_by_id(session, api_entity_id)
if api_entity:
from db.engine_factory import EngineFactory
from db.model import DocumentText, DocumentAnnotationStatus
from shared.logger_util import Logger
logger = Logger("import_return_value_relation_for_jdk_method").get_log()
session = EngineFactory.create_session()
def import_jdk_document_annotation_status():
doc_id_list = DocumentText.get_doc_id_list(session)
if doc_id_list is not None:
for each in doc_id_list:
doc_id = each[0]
print doc_id
document_annotation_status = DocumentAnnotationStatus(doc_id, DocumentAnnotationStatus.STATUS_TO_ANNOTATE)
print document_annotation_status
document_annotation_status.create(session, autocommit=False)
session.commit()
if __name__ == "__main__":
import_jdk_document_annotation_status()
def __init__(self, session=None, logger=None):
self.__session = session
if logger is None:
self.logger = Logger("DBSearcher").get_log()
else:
self.logger = logger
import MySQLdb
# Mysql connect
from py2neo import Relationship
from skgraph.graph.accessor.graph_accessor import GraphClient
from skgraph.graph.accessor.graph_client_for_wikidata import WikiDataGraphAccessor
from shared.logger_util import Logger
conn = None
cur = None
graphClient = WikiDataGraphAccessor(GraphClient(server_number=1))
# neo4j connect
connect_graph = graphClient.graph
logger = Logger("android_sdk_importer").get_log()
# buffer
q = Queue.Queue()
n = 0
def get_android_sdk_node():
labels = ["library"]
property_dict = {"name": "android API"}
from skgraph.graph.accessor.factory import NodeBuilder
nodeBuilder = NodeBuilder().add_labels(*labels).add_property(
**property_dict)
android_sdk_node = nodeBuilder.build()
connect_graph.merge(android_sdk_node, "library", "name")
return android_sdk_node
from py2neo import Relationship
from graph_accessor import GraphAccessor
from shared.logger_util import Logger
from skgraph.graph.accessor.factory import NodeBuilder
_logger = Logger("SentenceAccessor").get_log()
class DomainEntityAccessor(GraphAccessor):
def get_all_domain_entity(self):
try:
query = "MATCH (n:`domain entity`) return n"
result = self.graph.run(query)
node_list = []
for n in result:
node_list.append(n['n'])
return node_list
except Exception, error:
_logger.exception("------")
return []
def create_entity_to_general_concept_relation(self, entity,
wikipedia_entity):
relation = Relationship(entity, 'may link', wikipedia_entity)
self.graph.merge(relation)
def delete_all_domain_entity_to_wikipedia_relation(self):
try:
query = "MATCH (n:`domain entity`)-[r:`may link`]-(m:wikipedia) delete r"
self.graph.run(query)
from shared.logger_util import SQLAlchemyHandler
from skgraph.graph.accessor.graph_accessor import DefaultGraphAccessor, GraphClient
from skgraph.graph.apientitylinking import APIEntityLinking
from skgraph.graph.label_util import LabelUtil
from skgraph.graph.node_cleaner import GraphJsonParser
reload(sys)
sys.setdefaultencoding("utf-8")
app = Flask(__name__)
CORS(app)
db_handler = SQLAlchemyHandler()
db_handler.setLevel(logging.WARN) # Only serious messages
app.logger.addHandler(db_handler)
logger = Logger("neo4jServer").get_log()
logger.info("create logger")
graphClient = DefaultGraphAccessor(GraphClient(server_number=1))
logger.info("create graphClient")
api_entity_linker = APIEntityLinking()
logger.info("create api_entity_linker object")
questionAnswerSystem = QuestionAnswerSystem()
logger.info("create questionAnswerSystem")
dbSOPostSearcher = SOPostSearcher(EngineFactory.create_so_session(),
logger=app.logger)
logger.info("create SO POST Searcher")
import codecs
import json
from py2neo import Relationship
from skgraph.graph.accessor.graph_accessor import GraphClient
from skgraph.graph.accessor.graph_client_for_awesome import AwesomeGraphAccessor
from shared.logger_util import Logger
_logger = Logger("AwesomeImporter").get_log()
awesomeGraphAccessor = AwesomeGraphAccessor(GraphClient(server_number=0))
baseGraphClient = awesomeGraphAccessor.graph
file_name = "complete_list_of_awesome_list_collect_relation.json"
with codecs.open(file_name, 'r', 'utf-8') as f:
relation_list = json.load(f)
for relation in relation_list:
start_url = relation["start_url"]
relation_str = relation["relation"]
end_url = relation["end_url"]
start_node = awesomeGraphAccessor.find_awesome_list_entity(start_url)
end_node = awesomeGraphAccessor.find_awesome_list_entity(end_url)
if start_node is not None and end_node is not None:
relationship = Relationship(start_node, relation_str, end_node)
baseGraphClient.merge(relationship)
_logger.info("create or merge relation" + str(relation))
else:
_logger.warn("fail create relation" + str(relation))
from bs4 import BeautifulSoup
from db.engine_factory import EngineFactory
from db.cursor_factory import ConnectionFactory
from db.model import KnowledgeTableRowMapRecord, APIEntity
from db.model_factory import KnowledgeTableFactory
from db.util.code_text_process import parse_declaration_html_with_full_qualified_type, clean_declaration_html, \
clean_html_text_with_format
from shared.logger_util import Logger
session = EngineFactory.create_session()
logger = Logger("import_android_method").get_log()
IMPORT_DATA_SOURCE_TABLE_NAME = "androidAPI_method"
class_knowledge_table = KnowledgeTableFactory.find_knowledge_table_by_name(
session=session, name="androidAPI_class")
method_knowledge_table = KnowledgeTableFactory.find_knowledge_table_by_name(
session=session, name="androidAPI_method")
api_knowledge_table = KnowledgeTableFactory.find_knowledge_table_by_name(
session=session, name=APIEntity.__tablename__)
def get_api_entity_id_by_old_class_id(old_class_id):
return KnowledgeTableRowMapRecord.get_end_row_id(
session=session,
start_knowledge_table=class_knowledge_table,
end_knowledge_table=api_knowledge_table,
start_row_id=old_class_id)
