|
|
|
|
@ -11,47 +11,37 @@ def make_soup(file: str):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def split_div(xml_file: str, prince: str)-> dict:
|
|
|
|
|
"""1) read xml file with function make_soup
|
|
|
|
|
2) make a list with all //div if //div/@n == True
|
|
|
|
|
3) make actes' ids with param <prince> + date
|
|
|
|
|
manage double dates : each //docDate/date must have
|
|
|
|
|
a @n with 'a', 'b', etc... the commented scrip may
|
|
|
|
|
help you to check if there is double date.
|
|
|
|
|
4) merge actes' ids list with div list"""
|
|
|
|
|
# 1
|
|
|
|
|
soup = make_soup(xml_file)
|
|
|
|
|
# 2
|
|
|
|
|
actes = [div for div in soup.find_all('div', {'n': True})]
|
|
|
|
|
# 3
|
|
|
|
|
actes_id =[]
|
|
|
|
|
for acte in actes:
|
|
|
|
|
date = acte.div.docDate.date["when"]
|
|
|
|
|
date_nb = acte.div.docDate.date["n"]
|
|
|
|
|
actes_id.append(prince + date.replace("-", "_") + date_nb)
|
|
|
|
|
"""
|
|
|
|
|
# script to get all double dates
|
|
|
|
|
prev_acte = None
|
|
|
|
|
for id_acte in actes_id:
|
|
|
|
|
if prev_acte == id_acte:
|
|
|
|
|
print(prev_acte, id_acte)
|
|
|
|
|
prev_acte = id_acte
|
|
|
|
|
"""read xml file with function make_soup
|
|
|
|
|
& make a list for each acte with : id, date
|
|
|
|
|
(YYYY-MM-DD), date (string), sourceDesc,
|
|
|
|
|
analysis, the whole div.
|
|
|
|
|
"""
|
|
|
|
|
# 4
|
|
|
|
|
if len(actes_id) == len(actes):
|
|
|
|
|
dict_actes = {actes_id[item]: actes[item] for item in range(len(actes_id))}
|
|
|
|
|
else:
|
|
|
|
|
print(f"""** ERROR **\nactes_id == {len(actes_id)}\nactes == {len(actes)}""")
|
|
|
|
|
return dict_actes
|
|
|
|
|
|
|
|
|
|
def create_file(actes, house, folder, tei_canvas):
|
|
|
|
|
for acte in actes:
|
|
|
|
|
filename = os.path.join("..", "static", "xml", house, folder, acte + '.xml')
|
|
|
|
|
with open(filename, 'w', encoding='utf-8') as writting:
|
|
|
|
|
writting.write(str(actes[acte]))
|
|
|
|
|
with open(filename, 'r', encoding='utf-8') as xml:
|
|
|
|
|
soup = BeautifulSoup(xml, "xml")
|
|
|
|
|
print(soup)
|
|
|
|
|
soup = make_soup(xml_file)
|
|
|
|
|
actes = []
|
|
|
|
|
for div in soup.find_all('div', {'n': True}):
|
|
|
|
|
when = div.docDate.date["when"]
|
|
|
|
|
nb = div.docDate.date["n"]
|
|
|
|
|
acte_id = prince + when.replace("-", "_") + nb
|
|
|
|
|
date = div.docDate.date.text
|
|
|
|
|
trad_table = div.listWit
|
|
|
|
|
analysis = div.argument.p.string
|
|
|
|
|
acte = [acte_id, when, date, trad_table, analysis, div]
|
|
|
|
|
actes.append(acte)
|
|
|
|
|
return actes
|
|
|
|
|
|
|
|
|
|
def tei_maker(lst_acte, house, folder, tei_canvas):
|
|
|
|
|
"""write the acte in an xml file"""
|
|
|
|
|
for acte in lst_acte:
|
|
|
|
|
filename = os.path.join("..", "static", "xml", house, folder, acte[0] + '.xml')
|
|
|
|
|
soup = BeautifulSoup(tei_canvas, 'xml')
|
|
|
|
|
title = soup.find("title", {"level":"a"})
|
|
|
|
|
title.string = "Acte " + acte[0]
|
|
|
|
|
soup.sourceDesc.append(acte[-3])
|
|
|
|
|
soup.body.append(acte[-1])
|
|
|
|
|
tradition = soup.find("div", {"type": "tradition"})
|
|
|
|
|
tradition.decompose()
|
|
|
|
|
with open(filename, 'w', encoding="utf-8") as writting:
|
|
|
|
|
writting.write(str(soup))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
canvas = f"""<?xml version="1.0" encoding="utf-8"?>
|
|
|
|
|
@ -94,7 +84,6 @@ canvas = f"""<?xml version="1.0" encoding="utf-8"?>
|
|
|
|
|
</teiHeader>
|
|
|
|
|
<text>
|
|
|
|
|
<body>
|
|
|
|
|
++ACTE++
|
|
|
|
|
</body>
|
|
|
|
|
</text>
|
|
|
|
|
</TEI>"""
|
|
|
|
|
@ -102,4 +91,4 @@ canvas = f"""<?xml version="1.0" encoding="utf-8"?>
|
|
|
|
|
|
|
|
|
|
corpus = "../../bourbon-latex/charles-actes-latex.xml"
|
|
|
|
|
|
|
|
|
|
create_file(split_div(corpus, "brb_ch_i_"), "Bourbon", "Brb_5_Charles_Ier", canvas)
|
|
|
|
|
tei_maker(split_div(corpus, "brb_ch_i_"), "Bourbon", "Brb_5_Charles_Ier", canvas)
|
|
|
|
|
|
jgenero
3 years ago