def lang():
f = 'original_languages'
queue = []
for w in iter_works([f, 'title']):
if f in w and w[f]:
continue
q = {
'type': '/type/edition',
'works': w['key'],
'languages': None,
'title': None,
'title_prefix': None
}
editions = [e for e in query_iter(q) if e['languages']]
title = mk_norm(w['title'])
if not editions or any(len(e['languages']) != 1 for e in editions):
continue
lang = [
e['languages'][0]['key'] for e in editions
if mk_norm(get_title(e)) == title
]
if len(lang) < 2:
continue
first = lang[0]
if any(l != first for l in lang):
continue
print((w['key'], repr(w['title']), first, len(lang)))
q = {'key': w['key'], f: {'connect': 'update_list', 'value': [first]}}
queue.append(q)
if len(queue) == 200:
print(ol.write(queue, comment='add original language'))
queue = []
print(ol.write(queue, comment='add original language'))
def lang():
f = 'original_languages'
queue = []
for w in iter_works([f, 'title']):
if f in w and w[f]:
continue
q = {
'type':'/type/edition',
'works': w['key'],
'languages': None,
'title': None,
'title_prefix': None
}
editions = [e for e in query_iter(q) if e['languages']]
title = mk_norm(w['title'])
if not editions or any(len(e['languages']) != 1 for e in editions):
continue
lang = [e['languages'][0]['key'] for e in editions if mk_norm(get_title(e)) == title]
if len(lang) < 2:
continue
first = lang[0]
if any(l != first for l in lang):
continue
print w['key'], `w['title']`, first, len(lang)
q = {
'key': w['key'],
f: { 'connect': 'update_list', 'value': [first]}
}
queue.append(q)
if len(queue) == 200:
print ol.write(queue, comment='add original language')
queue = []
print ol.write(queue, comment='add original language')
def get_books(akey):
q = {
'type':'/type/edition',
'authors': akey,
'*': None
}
for e in query_iter(q):
if not e.get('title', None):
continue
if len(e.get('authors', [])) != 1:
continue
# if 'works' in e:
# continue
if 'title_prefix' in e and e['title_prefix']:
prefix = e['title_prefix']
if prefix[-1] != ' ':
prefix += ' '
title = prefix + e['title']
else:
title = e['title']
if title.strip('. ') in ['Publications', 'Works', 'Report', \
'Letters', 'Calendar', 'Bulletin', 'Plays', 'Sermons', 'Correspondence']:
continue
m = re_parens.match(title)
if m:
title = m.group(1)
n = mk_norm(title)
book = {
'title': title,
'norm_title': n,
'key': e['key'],
}
if 'languages' in e:
book['lang'] = [l['key'][3:] for l in e['languages']]
if e.get('table_of_contents', None):
if isinstance(e['table_of_contents'][0], basestring):
book['table_of_contents'] = e['table_of_contents']
else:
assert isinstance(e['table_of_contents'][0], dict)
if e['table_of_contents'][0]['type'] == '/type/text':
book['table_of_contents'] = [i['value'] for i in e['table_of_contents']]
if not e.get('work_titles', None):
yield book
continue
wt = e['work_titles'][0].strip('. ')
if wt in ('Works', 'Selections'):
yield book
continue
n_wt = mk_norm(wt)
book['work_title'] = wt
book['norm_wt'] = n_wt
yield book
