class FACCToMongo(object):
def __init__(self, config):
"""Inserts FACC surface forms to Mongo."""
self.__check_config(config)
self.__collection = config[KEY_COLLECTION]
self.__path = config[KEY_PATH]
self.__predicate = config[KEY_PREDICATE]
self.__lowercase = config[KEY_LOWERCASE]
self.__mongo = None
@staticmethod
def __check_config(config):
"""Checks config parameters and sets default values."""
try:
if KEY_COLLECTION not in config:
raise Exception(KEY_COLLECTION + " is missing")
if KEY_PATH not in config:
raise Exception(KEY_PATH + " is missing")
if KEY_PREDICATE not in config:
raise Exception(KEY_PREDICATE + " is missing")
if KEY_LOWERCASE not in config:
config[KEY_LOWERCASE] = True
except Exception as e:
PLOGGER.error("Error in config file: ", e)
sys.exit(1)
def __add_surface_form(self, surface_form, freebase_uri, count):
"""Adds a surface form."""
if self.__lowercase:
surface_form = surface_form.lower()
# Increases count; if the id is not associated with the surface form yet, it adds it with count.
freebase_id = self.__convert_to_fb_id(freebase_uri)
self.__mongo.inc_in_dict(surface_form, self.__predicate, freebase_id,
count)
def __convert_to_fb_id(self, fb_uri):
"""Converts /m/047b9p0 to <fb:m.047b9p0>"""
fb_id = fb_uri.replace("/", ".")
return "<fb:" + fb_id[1:] + ">"
def __add_file(self, tsv_filename):
"""Adds name variants from an FACC tsv file."""
PLOGGER.info("Adding name variants from '" + tsv_filename + "'...")
infile = open(tsv_filename, "r")
for line in infile:
f = line.rstrip().split("\t")
self.__add_surface_form(f[0], f[1], int(f[2]))
infile.close()
def build(self):
"""Builds surface form collection from FACC annotations."""
self.__mongo = Mongo(MONGO_HOST, MONGO_DB, self.__collection)
self.__mongo.drop()
for path, dirs, files in os.walk(self.__path):
for fn in files:
if fn.endswith(".tsv"):
self.__add_file(os.path.join(path, fn))
PLOGGER.info("Collection " + self.__collection + " is built.")
def build_collection(self, mappings):
"""Builds Mongo collection"""
mongo = Mongo(MONGO_HOST, MONGO_DB, self.__collection)
mongo.drop()
predicate = "!<owl:sameAs>"
i = 0
for fb_id, dbp_ids in mappings.items():
for dbp_id in dbp_ids:
mongo.append_set(fb_id, predicate, [dbp_id])
i += 1
if i % 1000 == 0:
print(str(i // 1000) + "K entities are added!")
class Word2VecToMongo(object):
def __init__(self, config):
self.__check_config(config)
self.__collection = config[KEY_COLLECTION]
self.__w2v_fname = config[KEY_MAPPING_FILE]
self.__mongo = None
@staticmethod
def __check_config(config):
"""Checks params and set default values."""
try:
if KEY_COLLECTION not in config:
raise Exception(KEY_COLLECTION + " is missing")
if KEY_MAPPING_FILE not in config:
raise Exception(KEY_MAPPING_FILE + " is missing")
if not op.exists(config[KEY_MAPPING_FILE]):
raise Exception("Mapping file path does not exist.")
except Exception as e:
print("Error in config file: ", e)
exit(1)
return config
def __parse_line(self, line):
"""
Parses a line of the plain-text GoogleNews 300-dim pre-trained corpus.
:param line:
:type line: string
:return: a (word, vector) tuple.
"""
word, vec_str = line.rstrip().split(maxsplit=1)
vector = [float(x) for x in vec_str.split()]
return word, vector
def build(self):
"""Builds word2vec collection from GoogleNews 300-dim pre-trained corpus."""
self.__mongo = Mongo(MONGO_HOST, MONGO_DB, self.__collection)
self.__mongo.drop()
infile = FileUtils.open_file_by_type(self.__w2v_fname)
i = 0
for line in infile:
term, vector = self.__parse_line(line)
self.__mongo.add(term, {'vector': vector})
i += 1
if i % 1000 == 0:
print(str(i / 1000) + "K lines are loaded.")
# break
pass
class NTriplesToMongoDB(object):
def __init__(self, host, db, collection):
self.__mongo = Mongo(host, db, collection)
self.__prefix = URIPrefix()
self.__m_id = None
self.__m_contents = None
logging.basicConfig(level="ERROR") # no warnings from the rdf parser
def _next_triple(self, subj, pred, obj):
"""Processes a triple.
- Appends to previous triple if it's the same subject.
- Otherwise inserts last triple and creates a new one.
"""
if (self.__m_id is not None) and (self.__m_id == subj):
if pred not in self.__m_contents:
self.__m_contents[pred] = []
self.__m_contents[pred].append(obj)
else:
self._write_to_mongo()
self.__m_id = subj
self.__m_contents = {pred: [obj]}
def _write_to_mongo(self):
"""Writes triple (inserts or appends existing) to MongoDB collection."""
if self.__m_id is not None:
for field, value in self.__m_contents.items():
self.__mongo.append_set(self.__m_id, field, value)
# self.mongo.add(self.m_id, self.m_contents)
self.__m_id = None
self.__m_contents = None
def drop(self):
"""Deletes the collection."""
self.__mongo.drop()
def add_file(self, filename, reverse_triple=False, predicate_prefix=None):
"""Adds contents from an NTriples file to MongoDB.
:param filename: NTriples file.
:param reverse_triple: if set True, the subject and object values are swapped.
:param predicate_prefix: prefix to be added to predicates.
:param subjects_redirecter: redirects dict.
"""
print("Processing " + filename + "...")
t = Triple()
p = NTriplesParser(t)
self.__m_id = None # document id for MongoDB -- subj
self.__m_contents = None # document contents for MongoDB -- pred, obj
i = 0
with FileUtils.open_file_by_type(filename) as f:
for line in f:
try:
p.parsestring(line.decode("utf-8"))
except ParseError: # skip lines that couldn't be parsed
continue
if t.subject() is None: # only if parsed as a triple
continue
# subject prefixing
subj = self.__prefix.get_prefixed(t.subject())
# predicate prefixing
pred = self.__prefix.get_prefixed(t.predicate())
if predicate_prefix is not None:
pred = predicate_prefix + pred
# Object prefixing
if type(t.object()) is URIRef:
obj = self.__prefix.get_prefixed(t.object())
else:
obj = t.object()
if len(obj) == 0:
continue # skip empty objects
# write or append
if reverse_triple: # reverse subj and obj
self._next_triple(obj, pred, subj)
else: # normal mode
self._next_triple(subj, pred, obj)
i += 1
if i % 100000 == 0:
print(
str(i // 1000) + "K lines processed from " + filename)
# process last triple
self._write_to_mongo()
class DBpediaSurfaceforms2Mongo(object):
def __init__(self, config):
"""Inserts DBpedia surface forms to Mongo."""
self.__check_config(config)
self.__collection = config[KEY_COLLECTION]
self.__lowercase = config[KEY_LOWERCASE]
self.__mongo_dbpedia = Mongo(MONGO_HOST, MONGO_DB,
MONGO_COLLECTION_DBPEDIA)
self.__mongo = None
@staticmethod
def __check_config(config):
"""Checks config parameters and sets default values."""
try:
if KEY_COLLECTION not in config:
raise Exception(KEY_COLLECTION + " is missing")
if KEY_LOWERCASE not in config:
config[KEY_LOWERCASE] = True
except Exception as e:
print("Error in config file: ", e)
sys.exit(1)
def __add_surface_form(self, surface_form, predicate, entity_id):
"""Adds a surface form (removes the disambiguation part form the surface form, if exists).
:param surface_form: surface form for entity
:param predicate: predicate that entity is extracted from e.g. <rdfs:label>
:param entity_id: entity ID
"""
if sys.getsizeof(surface_form) >= 1024: # Mongo key limit
return
surface_form = surface_form.replace("(disambiguation)", "").strip()
if self.__lowercase:
surface_form = surface_form.lower()
self.__mongo.inc_in_dict(surface_form, predicate, entity_id, 1)
def build_collection(self):
"""Adds all name variants from DBpedia."""
self.__mongo = Mongo(MONGO_HOST, MONGO_DB, self.__collection)
self.__mongo.drop()
# iterate through all DBpedia entities
i = 0
for mdoc in self.__mongo_dbpedia.find_all():
entity = EntityUtils(Mongo.unescape_doc(mdoc))
# skips entities without names
if not entity.has_name():
continue
surface_form = entity.get_name()
# the entity is redirect page
if entity.is_redirect():
entity_id = entity.get_predicate(
EntityUtils.PREDICATE_REDIRECT)[0]
self.__add_surface_form(surface_form,
EntityUtils.PREDICATE_REDIRECT,
entity_id)
# the entity is disambiguation page
if entity.has_predicate(EntityUtils.PREDICATE_DISAMBIGUATE):
entity_ids = entity.get_predicate(
EntityUtils.PREDICATE_DISAMBIGUATE)
for entity_id in entity_ids:
self.__add_surface_form(surface_form,
EntityUtils.PREDICATE_DISAMBIGUATE,
entity_id)
# entity is not a redirect/disambiguation page and has name and abstract
if entity.is_entity():
entity_id = entity.get_id()
# adds entity name
self.__add_surface_form(surface_form,
EntityUtils.PREDICATE_NAME, entity_id)
# adds other entity names
foaf_name_predicate = "<foaf:name>"
if entity.has_predicate(foaf_name_predicate):
for surface_form in entity.get_predicate(
foaf_name_predicate):
self.__add_surface_form(surface_form,
foaf_name_predicate, entity_id)
i += 1
if i % 1000 == 0:
print(str(i // 1000) + "K entities processed")