|
|
#!/usr/bin/python
|
|
|
# -*- coding: UTF-8 -*-
|
|
|
|
|
|
"""
|
|
|
Authors : Jean-Damien Généro, Bertrand Dumenieu
|
|
|
Affiliation : French National Center for Scientific Research (CNRS), École des hautes études en sciences sociales (EHESS)
|
|
|
Assigned at the Centre de recherches historiques (CRH, UMR 8558)
|
|
|
Date : 2021-12-31
|
|
|
Update : 2022-01-05
|
|
|
|
|
|
Regex dans les ODT :
|
|
|
- j'enlève tous les sauts de page (ctrl+A, puis Format, Paragraphe, onglet Enchainements, décocher Saut / Insérer.)
|
|
|
- je vérifie que tous les séparateurs sont sur une seule ligne : ` +\*\*` >> `\n$1`
|
|
|
- je transforme les séparateurs : `\*{3}` >> `-*-`
|
|
|
"""
|
|
|
|
|
|
|
|
|
import csv
|
|
|
import os
|
|
|
import re
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
|
|
|
|
|
def beautiful_clean_up(path):
|
|
|
with open(path, 'r', encoding='utf-8') as opened:
|
|
|
reading = opened.read()
|
|
|
# acts
|
|
|
separator = r'<p rend=".+">\n +<seg rend="Aucun"><hi rend="sub">-\*<\/hi>-<\/seg>\n +<\/p>'
|
|
|
reading = re.sub(separator, '</div><div>', reading)
|
|
|
reading = re.sub(r'<body>\n +<figure>', '<body>\n<div>', reading)
|
|
|
reading = reading.replace(r'<\/figure>\n +<\/body>', '</div>\n</body>')
|
|
|
reading = reading.replace('<figure>', '')
|
|
|
reading = reading.replace('</figure>', '')
|
|
|
reading = reading.replace('<ident>', '')
|
|
|
reading = reading.replace('</ident>', '')
|
|
|
reading = reading.replace("’", "'")
|
|
|
soup = BeautifulSoup(reading, 'xml')
|
|
|
# titre
|
|
|
titleStmt = soup.titleStmt
|
|
|
# title = soup.new_tag('title')
|
|
|
author = soup.new_tag('author')
|
|
|
# title.string = 'Actes de Charles Ier'
|
|
|
author.string = 'Jean-Damien Généro'
|
|
|
# titleStmt.append(title)
|
|
|
titleStmt.append(author)
|
|
|
# publicationStmt
|
|
|
# publicationStmt = soup.publicationStmt
|
|
|
# date = soup.new_tag('date')
|
|
|
# date['when'] = '2022'
|
|
|
# date.string = '2022'
|
|
|
# publisher = soup.new_tag('publisher')
|
|
|
# publisher.string = 'Laboratoire de Médiévistique occidentale de Paris (UMR 8589), Centres de recherches historiques (UMR 8558)'
|
|
|
# availability = soup.new_tag('availability')
|
|
|
# licence = soup.new_tag('licence')
|
|
|
# licence['source'] = 'https://github.com/etalab/licence-ouverte/blob/master/open-licence.md'
|
|
|
# licence.string = 'Distributed under an Open License 2.0'
|
|
|
# availability.append(licence)
|
|
|
# publicationStmt.append(publisher)
|
|
|
# publicationStmt.append(date)
|
|
|
# publicationStmt.append(availability)
|
|
|
# sourceDesc
|
|
|
# sourceDesc = soup.sourceDesc
|
|
|
# sourceDesc_p = soup.new_tag('p')
|
|
|
# sourceDesc_p.string = 'Les actes ci-dessous sont issus de plusieurs dépôts d\'archives.'
|
|
|
# sourceDesc.append(sourceDesc_p)
|
|
|
# removing all empty tags
|
|
|
for empty_tag in soup.find_all():
|
|
|
if len(empty_tag.get_text(strip=True)) == 0:
|
|
|
empty_tag.extract()
|
|
|
# number
|
|
|
for match in soup.findAll('ident'):
|
|
|
match.replaceWithChildren()
|
|
|
for match in soup.findAll('seg'):
|
|
|
match.replaceWithChildren()
|
|
|
for match in soup.findAll('emph'):
|
|
|
match.replaceWithChildren()
|
|
|
for match in soup.findAll('name'):
|
|
|
match.replaceWithChildren()
|
|
|
for match in soup.find_all('div'):
|
|
|
match['xml:id'] = 'charles_ier_' + match.p.string.replace(' ', '')
|
|
|
match['n'] = match.p.string.replace(' ', '')
|
|
|
# witness
|
|
|
for tag in soup.find_all('p'):
|
|
|
try:
|
|
|
tag['rend']
|
|
|
except KeyError:
|
|
|
continue
|
|
|
if tag['rend'] == 'Corps':
|
|
|
del tag['rend']
|
|
|
# for match in soup.find_all('p'):
|
|
|
# if re.search(r'([A-Z])\. [OC]', match.text):
|
|
|
# witness = soup.new_tag('witness')
|
|
|
# witness.contents = match.contents
|
|
|
# witness['n'] = re.search(r'([A-Z])\. +[OC]', match.text).group(1)
|
|
|
# match.replaceWith(witness)
|
|
|
result = str(soup)
|
|
|
result = result.replace('p rend="Corps ', 'p rend="')
|
|
|
result = result.replace(' ', ' ')
|
|
|
result = result.replace('\n', '')
|
|
|
result = result.replace('.replace(' ', '')', '')
|
|
|
newsoup = BeautifulSoup(result, 'xml')
|
|
|
# with open('../static/xml/Bourbon/5-Charles-Ier/corpus2.xml', 'w', encoding='utf-8') as op:
|
|
|
# op.write(newsoup.prettify())
|
|
|
body = newsoup.body
|
|
|
for div in body.find_all('div'):
|
|
|
#print("\n\n" + div['xml:id'])
|
|
|
filename = 'charles_ier_' + div['n'] + '.xml'
|
|
|
with open(os.path.join("../static/xml/Bourbon/5-Charles-Ier", filename), 'r', encoding='utf-8') as opening:
|
|
|
soup_act = BeautifulSoup(opening, 'xml')
|
|
|
soup_act.body.append(div)
|
|
|
with open(os.path.join("../static/xml/Bourbon/5-Charles-Ier", filename), 'w', encoding='utf-8') as writting:
|
|
|
writting.write(soup_act.prettify())
|
|
|
|
|
|
|
|
|
def teiheader_making(file, tei_canvas):
|
|
|
soup = BeautifulSoup(tei_canvas, 'xml')
|
|
|
p_sourceDesc = soup.new_tag('p')
|
|
|
with open(file, 'r', encoding='utf-8') as opening:
|
|
|
csvfile = csv.reader(opening, delimiter=";")
|
|
|
for line in csvfile:
|
|
|
filename = 'charles_ier_' + line[0] + ".xml"
|
|
|
soup.title.string = 'Acte {} de Charles Ier de Bourbon ({})'.format(line[0], line[4])
|
|
|
p_sourceDesc.string = f"""Ce fichier contient l'acte n°{line[0]} de Charles Ier de Bourbon, {line[9]} ({line[2]}, {line[1]}) daté du {line[4]} à {line[5]}."""
|
|
|
soup.sourceDesc.append(p_sourceDesc)
|
|
|
with open(os.path.join("../static/xml/Bourbon/5-Charles-Ier", filename), 'w', encoding="utf-8") as writting:
|
|
|
writting.write(str(soup))
|
|
|
|
|
|
|
|
|
canvas = f"""<?xml version="1.0" encoding="utf-8"?>
|
|
|
<TEI xmlns="http://www.tei-c.org/ns/1.0">
|
|
|
<teiHeader>
|
|
|
<fileDesc>
|
|
|
<titleStmt>
|
|
|
<title></title>
|
|
|
<author></author>
|
|
|
</titleStmt>
|
|
|
<publicationStmt>
|
|
|
<publisher>Laboratoire de Médiévistique occidentale de Paris (UMR 8589), Centre de recherches historiques (UMR 8558)</publisher>
|
|
|
<date when="2022">2022</date>
|
|
|
<availability><licence source="https://github.com/etalab/licence-ouverte/blob/master/open-licence.md">Distributed under an Open License 2.0</licence></availability>
|
|
|
</publicationStmt>
|
|
|
<sourceDesc>
|
|
|
</sourceDesc>
|
|
|
</fileDesc>
|
|
|
</teiHeader>
|
|
|
<text>
|
|
|
<body>
|
|
|
</body>
|
|
|
</text>
|
|
|
</TEI>"""
|
|
|
|
|
|
teiheader_making("../static/csv/corpus-charles-i.csv", canvas)
|
|
|
|
|
|
beautiful_clean_up("../static/xml/Bourbon/5-Charles-Ier/corpus-charles-i.xml")
|