def __init__(self):
self.appender = ReaderWriter()
self.mapper_reader = self._mapper_reader()
self.mapper_appender = ReaderWriter()
self.reader = self._reader()
self.extractor = m.EntityExtractor(
# in/output: ab_id entity-mapper: id
ref_field_map=FieldsMap.parse('id=ab_id'),
# in/output: a, b entity-mapper: a, other
fields_map=FieldsMap.parse('a,other=b'),
keep_fields=True)
def __init__(self):
self.appender = ReaderWriter()
self.mapper_reader = self._mapper_reader()
self.mapper_appender = ReaderWriter()
self.reader = self._reader()
self.extractor = m.EntityExtractor(
# in/output: ab_id entity-mapper: id
ref_field_map=FieldsMap.parse('id=ab_id'),
# in/output: a, b entity-mapper: a, other
fields_map=FieldsMap.parse('a,other=b'),
keep_fields=True)
def main():
reader = csv.reader(sys.stdin)
writer = csv.writer(sys.stdout)
entity_fields, ref_field, entity_file = sys.argv[1:]
extractor = EntityExtractor(FieldsMap.parse(ref_field),
FieldsMap.parse(entity_fields),
keep_fields=True)
has_entity_file = os.path.exists(entity_file)
with open(entity_file, 'a+') as f:
if has_entity_file:
extractor.use_existing_mapper(csv.reader(f), csv.writer(f))
else:
extractor.use_new_mapper(csv.writer(f))
extractor.extract(reader, writer)
def main():
reader = csv.reader(sys.stdin)
writer = csv.writer(sys.stdout)
entity_fields, ref_field, entity_file = sys.argv[1:]
extractor = EntityExtractor(
FieldsMap.parse(ref_field),
FieldsMap.parse(entity_fields),
keep_fields=True)
has_entity_file = os.path.exists(entity_file)
with open(entity_file, 'a+') as f:
if has_entity_file:
extractor.use_existing_mapper(csv.reader(f), csv.writer(f))
else:
extractor.use_new_mapper(csv.writer(f))
extractor.extract(reader, writer)
