You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

109 lines
3.3 KiB
Python

#!/usr/bin/python
# -*- coding: UTF-8 -*-
"""
Authors : Jean-Damien Généro
Affiliation : French National Center for Scientific Research (CNRS)
Assigned at the Centre de recherches historiques (CRH, UMR 8558)
Date : 2022-10-11
Update :
"""
import os
from bs4 import BeautifulSoup
from collections import OrderedDict
from peewee import *
from tqdm import tqdm
from modeles.princes_db_tables import db, Institution, State, Production_place, Diplo_type, Document, Acte
from data.institution_data import institution
from data.state_data import state
from data.diplo_type_data import diplomatic_type
def make_soup(file):
"""open a xml file and return a BeautifulSoup object"""
with open(file, 'r', encoding="utf-8") as opening:
xml = BeautifulSoup(opening, 'xml')
return xml
def _create_institution(data_lst: list)-> None:
for data in tqdm(data_lst, desc="Populating Institution..."):
Institution.create(**data)
def _create_state(data_lst: list)-> None:
for data in tqdm(data_lst, desc="Populating State..."):
State.create(**data)
def _create_diplo_type(data_lst: list)-> None:
for data in tqdm(data_lst, desc="Populating Diplo_type..."):
Diplo_type.create(**data)
def _create_produc_place(xml_file: str, folder: str)-> None:
places_xtract = []
production_places = []
for acte in os.listdir(folder):
soup = make_soup(os.path.join(folder, acte))
for place in soup.find('placeName', {'type': 'production_place'}):
places_xtract.append(place)
production_places = [{"placename": xtraction} for xtraction in set(places_xtract)]
for data in tqdm(production_places, desc="Populating Place..."):
Production_place.create(**data)
def _create_doc(xml_file: str, folder: str)-> None:
details_doc = {}
infos_doc = []
for acte in os.listdir(folder):
soup = make_soup(os.path.join(folder, acte))
# doc_id = soup.TEI["xml:id"]
inst_doc = soup.repository
nb_doc_1 = soup.msIdentifier.find_all("idno", {"n": "1"})
diplo_state = soup.body.div["type"]
# details_doc.append([inst_doc, nb_doc_1, diplo_state])
details_doc[nb_doc_1]= [inst_doc, diplo_state]
print(details_doc)
"""
for item in details_doc:
inst_query = [t.id_institution for t in Institution.select().where(
Institution.full_label == item[0].text)]
state_query = [t.id_state for t in State.select().where(
State.state_label == item[2])]
if len(item[1]) > 0:
# if there is a collection
infos_doc.append({
"inst_doc": inst_query[0],
"collection_doc": item[1][0].text,
"state_doc": state_query[0],
})
else:
# if collection is missing
infos_doc.append({
"inst_doc": inst_query[0],
"collection_doc": "",
"state_doc": state_query[0],
})
for data in tqdm(infos_doc, desc="Populating Document..."):
print(data)
Document.create(**data)
"""
def init():
db.connect()
print("Dropping existing DB...")
db.drop_tables([Institution, State, Production_place, Diplo_type, Document, Acte])
print("Re-creating schema...")
db.create_tables([Institution, State, Production_place, Diplo_type, Document, Acte])
_create_institution(institution)
_create_state(state)
_create_diplo_type(diplomatic_type)
_create_produc_place(xml, "./static/xml/Bourbon/Brb_5_Charles_Ier")
print("ok")
_create_doc(xml, "./static/xml/Bourbon/Brb_5_Charles_Ier")
xml = "../bourbon-latex/charles-actes-latex.xml"
# init()
_create_doc(xml, "./static/xml/Bourbon/Brb_5_Charles_Ier")