def save_document(categories, data):
primary = get_field(data, './/Bestand')
secondary = get_field(data, './/Klassifikation')
if not primary or not secondary:
return
category = categories[primary]['children'][secondary]
uid = get_field(data, './/Signatur')
document = get_document(uid, category)
if not document:
document = Document()
document.category = [category]
document.uid = uid
extra_fields = {}
document.title = get_field(data, './/Titel')
document.description = get_field(data, './/Enthaelt')
document.order_id = uid
for key in ['Altsignatur', 'Sachbegriffe', 'Personen']:
item = get_field(data, './/%s' % key)
if item:
extra_fields[key] = item
document.extra_fields = extra_fields
# save document
document.save()
logger.info('dataimport.eadddb.document',
'document %s saved' % document.id)
return document
def save_document(category, data):
uid = get_field(data, './/Inventar-Nummer')
document = get_document(uid, category)
if not document:
document = Document()
document.category = [category]
document.uid = uid
extra_fields = {}
document.title = get_field(data, './/Titel')
document.description = get_field(data, './/Beschreibung_Inhalt/Inhalt')
document.order_id = uid
document.licence = get_field(data, './/Rechteerklaerung/Rechtsstatus')
document.author = get_field(data, './/Rechteerklaerung/creditline')
document.date_text = get_field(
data, './/Entstehung/Datierung_Herstellung/Dat_Begriff')
date_addon_text = get_field(
data, './/Entstehung/Datierung_Herstellung/DatZusatz')
if date_addon_text:
if document.date_text:
document.date_text += '; ' + date_addon_text
else:
document.date_text = date_addon_text
date_str = get_field(data,
'.//Beschreibung_Inhalt/Zeitbezuege/Zeitbezug_norm')
if date_str:
if len(date_str) == 4:
document.date_begin = '%s-01-01' % date_str
document.date_end = '%s-12-31' % date_str
elif len(date_str) == 10:
document.date = datetime.strptime(date_str, '%Y-%m-%d').date()
elif len(date_str) == 21:
date_arr = date_str.split('/')
if len(date_arr) == 2:
document.date_begin = datetime.strptime(
date_arr[0], '%Y-%m-%d').date()
document.date_end = datetime.strptime(date_arr[1],
'%Y-%m-%d').date()
for key in [
'Sachgebiet', 'Objektname', 'Objektklasse', 'Sachgebiet',
'Material', 'Beschreibung_Inhalt/Objektgeschichte'
]:
item = get_field(data, './/%s' % key)
if item:
if '/' in key:
extra_fields[key.split('/')[-1]] = item
else:
extra_fields[key] = item
document.extra_fields = extra_fields
# save document
document.save()
logger.info('dataimport.eadddb.document',
'document %s saved' % document.id)
for file_raw in data.xpath('.//Image'):
if not file_raw.get('Abbildung'):
continue
file = File.objects(externalId=file_raw.get('Abbildung'),
document=document).first()
if file:
continue
file = File()
file.document = document
file.externalId = file_raw.get('Abbildung')
file.fileName = file_raw.get('Abbildung')
file.binary_exists = False
file.save()
return document
def get_document(uid, parent):
return Document.objects(category=[parent], uid=uid).first()
def save_document(data, parent, nsmap):
document_id = get_identifier(data, nsmap)
if not document_id:
return document_id
document = get_document(data, parent, nsmap)
if not document:
document = Document()
document.uid = data.get('id')
document.category = [parent]
# title
title = data.xpath('./ns:did/ns:unittitle', namespaces=nsmap)
title = clean_text(title[0].text) if len(title) else ''
if '§§ unbekannte Darstellung' in title:
title = title.replace('§§ unbekannte Darstellung', '')
document.help_required = 1
document.title = title.strip()
# restricted
restricted = data.xpath('./ns:accessrestrict', namespaces=nsmap)
if len(restricted):
return False, False
# order_id
order_id = data.xpath('./ns:did/ns:unitid', namespaces=nsmap)
document.order_id = clean_text(order_id[0].text) if len(order_id) else ''
# origination
origination = data.xpath('./ns:did/ns:origination', namespaces=nsmap)
document.origination = clean_text(
origination[0].text) if len(origination) else ''
# description (findbuch-specific?)
description = data.xpath("./ns:did/ns:abstract[@type='Enthält']",
namespaces=nsmap)
document.description = clean_text(
description[0].text) if len(description) else ''
# note
note = data.xpath('./ns:did/ns:note', namespaces=nsmap)
document.note = clean_text(etree.tostring(
note[0]).text) if len(note) else ''
date = data.xpath('./ns:did/ns:unitdate', namespaces=nsmap)
if len(date):
date_result = {}
if date[0].text:
document.date_text = date[0].text
if 'normal' in date[0].attrib:
date_normalized = date[0].attrib['normal']
if '/' in date_normalized:
date_normalized = date_normalized.split('/')
if date_normalized[0] == date_normalized[1]:
date_result['date'] = datetime.strptime(
date_normalized[0], '%Y-%m-%d')
else:
date_result['begin'] = datetime.strptime(
date_normalized[0], '%Y-%m-%d')
date_result['end'] = datetime.strptime(
date_normalized[1], '%Y-%m-%d')
else:
date_result['date'] = datetime.strptime(
date_normalized, '%Y-%m-%d')
if 'date' in date_result:
document.date = date_result['date']
if 'begin' in date_result:
document.date_begin = date_result['begin']
if 'end' in date_result:
document.date_end = date_result['end']
# files
files = []
files_xml = data.xpath('./ns:daogrp/ns:daodesc/ns:list/ns:item',
namespaces=nsmap)
for file_xml in files_xml:
file_name = file_xml.xpath('./ns:name', namespaces=nsmap)
if not len(file_name):
continue
file_name = file_name[0].text
if not file_name:
continue
file_upsert_values = {
'set__externalId': data.get('id') + '-' + file_name,
'set__fileName': file_name
}
file = File.objects(externalId=data.get('id') + '-' +
file_name).upsert_one(**file_upsert_values)
files.append(file)
document.files = files
# all other values
extra_fields = {}
for extra_field_raw in data.xpath('./ns:odd', namespaces=nsmap):
field_title = extra_field_raw.xpath('./ns:head', namespaces=nsmap)
field_value = extra_field_raw.xpath('./ns:p', namespaces=nsmap)
if len(field_title) and len(field_value) and len(
clean_text(field_title[0].text)):
extra_fields[clean_text(field_title[0].text)] = clean_text(
field_value[0].text)
if len(extra_fields.keys()):
document.extra_fields = extra_fields
# save document
document.save()
logger.info('dataimport.eadddb.document',
'document %s saved' % document.id)
return document
def get_document(data, parent, nsmap):
return Document.objects(category=[parent],
uid=get_identifier(data, nsmap)).first()