import education
import location
import other_contexts
import occupation
# import personname
# import lifeInfo
import birthDeath
"""
This is a possible temporary main script that creates the biography related triples
TODO:
add documentation
implement personname
"""
logger = utilities.config_logger("biography")
def main():
file_dict = utilities.parse_args(__file__,
"Majority of biography related data")
entry_num = 1
uber_graph = utilities.create_graph()
highest_triples = 0
least_triples = 0
smallest_person = None
largest_person = None
logger.info("Time started: " + utilities.get_current_time() + "\n")
from rdflib import Literal
from Utils import utilities
from Utils.context import Context
from Utils.event import Event
from Utils.organizations import get_org_uri
"""
Status: ~75%
TODO:
- review unmapped instances
- revise method of capturing failed mappings to be similar to culturalforms
"""
# temp log library for debugging
# --> to be eventually replaced with proper logging library
logger = utilities.config_logger("occupation")
uber_graph = utilities.create_graph()
context_count = 0
event_count = 0
class Occupation(object):
"""docstring for Occupation
"""
def __init__(self, job_tag, predicate=None, other_attributes=None):
super(Occupation, self).__init__()
if predicate:
self.predicate = predicate
self.value = self.get_mapped_term(job_tag)
else:
#!/usr/bin/python3
from biography import Biography
from Utils.context import Context
from Utils.event import Event
from Utils.place import Place
from Utils import utilities
"""
Status: ~80%
"""
logger = utilities.config_logger("location")
uber_graph = utilities.create_graph()
location_occurences = {}
location_count = {
"VISITED": 0,
"UNKNOWN": 0,
"TRAVELLED": 0,
"LIVED": 0,
"MIGRATED": 0,
"MOVED": 0,
}
location_event_count = {
"VISITED": 0,
"UNKNOWN": 0,
"TRAVELLED": 0,
"LIVED": 0,
from Utils.organizations import get_org, get_org_uri
from Utils.place import Place
from Utils.event import Event
from Utils.context import Context
"""
Status: ~90%
Most of cultural forms have been mapped
TODO: Review missing religions & PAs
Forebear still needs to be handled/attempted with a query
--> load up gurjap's produced graph and query it for forebear info to test
temp solution until endpoint is active
"""
logger = utilities.config_logger("culturalform")
uber_graph = utilities.create_graph()
class CulturalForm(object):
"""docstring for CulturalForm
NOTE: mapping is done prior to creation of cf instance,
no need to include class type then
using other_attributes to handle extra predicates
that may come up for cfs
Ex. Organizations
other_attributes=utilities.NS_DICT["org"].memberOf
This being the uri rather the typical cf one
"""
def __init__(self, predicate, reported, value, other_attributes=None):
from Utils import utilities
from Utils.context import Context
from Utils.place import Place
from Utils.event import get_date_tag, Event, format_date
# TODO: clean up imports post death
# Should be matched up to deb's contexts somehow
# otherwise we're looking at duplicate contexts
# two unique id'd contexts but with the same text and different triples
# attached but this might fine if we're distinguishing between
# death context vs cause of death context
# TODO
# - once resolved: https://github.com/cwrc/ontology/issues/462
# - handle multiple DEATH/BIRTH tags
logger = utilities.config_logger("birthdeath")
class Birth:
def __init__(self, date, positions, birthplace):
self.date = date
self.position = []
self.place = birthplace
for birth_position in positions:
if birth_position == "ONLY":
self.position.append(utilities.NS_DICT["cwrc"].onlyChild)
elif birth_position == "ELDEST":
self.position.append(utilities.NS_DICT["cwrc"].eldestChild)
elif birth_position == "YOUNGEST":
self.position.append(utilities.NS_DICT["cwrc"].youngestChild)
from biography import Biography
from Utils import utilities
from Utils.context import Context
from Utils.event import Event
"""
Status: ~89%
extraction of health context will possibly accompanied by health factors at a later point
only identifying contexts being created
"""
logger = utilities.config_logger("other_contexts")
uber_graph = utilities.create_graph()
def extract_health_contexts_data(bio, person):
issue_map = {
"PHYSICAL": "PhysicalHealthContext",
"MENTAL": "MentalHealthContext",
"FEMALEBODY": "WomensHealthContext",
}
contexts = bio.find_all("HEALTH")
count = 1
event_count = 1
for context in contexts:
context_type = context.get("ISSUE")
if context_type:
context_type = issue_map[context_type]
else:
context_type = "HealthContext"
paragraphs = context.find_all("P")
for paragraph in paragraphs:
context_id = person.id + "_" + context_type + str(count)
for thisTag in name.find_all(tagname):
newPerson = makePerson(basic_layout_dict[tagname],
thisTag,
personNameList,
personName=person.name)
if newPerson:
personNameList.append(newPerson)
person.name_list = personNameList
context_id = person.id + "_PersonNameContext" + str(0)
tempContext = Context(context_id, personNameTags[0], "PersonNameContext")
tempContext.link_triples(person.name_list[1:])
person.context_list.append(tempContext)
logger = utilities.config_logger("personname")
def main():
from bs4 import BeautifulSoup
import culturalForm
from biography import Biography
file_dict = utilities.parse_args(__file__, "Personname")
print("-" * 200)
entry_num = 1
uber_graph = utilities.create_graph()
for filename in file_dict.keys():
with open(filename) as f:
soup = BeautifulSoup(f, 'lxml-xml')