def test_index_regex():
assert Ref('Otzar Midrashim').regex(
) == prepare_index_regex_for_dependency_process(
library.get_index('Otzar Midrashim'))
assert Ref('Zohar').regex() == prepare_index_regex_for_dependency_process(
library.get_index('Zohar'))
assert Ref(
'Genesis').regex() == prepare_index_regex_for_dependency_process(
library.get_index('Genesis'))
assert Ref('Rashi on Exodus').regex(
) == prepare_index_regex_for_dependency_process(
library.get_index('Rashi on Exodus'))
def dep_counts(name, indx):
def construct_query(attribute, queries):
query_list = [{attribute: {'$regex': query}} for query in queries]
return {'$or': query_list}
from sefaria.model.text import prepare_index_regex_for_dependency_process
patterns = prepare_index_regex_for_dependency_process(indx, as_list=True)
patterns = [
pattern.replace(re.escape(indx.title), re.escape(name))
for pattern in patterns
]
ret = {
'version title exact match':
model.VersionSet({
"title": name
}, sort=[('title', 1)]).count(),
'history title exact match':
model.HistorySet({
"title": name
}, sort=[('title', 1)]).count(),
'note match ':
model.NoteSet(construct_query("ref", patterns),
sort=[('ref', 1)]).count(),
'link match ':
model.LinkSet(construct_query("refs", patterns)).count(),
'history refs match ':
model.HistorySet(construct_query("ref", patterns),
sort=[('ref', 1)]).count(),
'history new refs match ':
model.HistorySet(construct_query("new.refs", patterns),
sort=[('new.refs', 1)]).count()
}
return ret
def process_index_title_change_in_history(indx, **kwargs):
print "Cascading History {} to {}".format(kwargs['old'], kwargs['new'])
"""
Update all history entries which reference 'old' to 'new'.
"""
from sefaria.model.text import prepare_index_regex_for_dependency_process
pattern = prepare_index_regex_for_dependency_process(indx)
pattern = pattern.replace(re.escape(indx.title), re.escape(kwargs["old"]))
title_pattern = ur'(^{}$)'.format(re.escape(kwargs["old"]))
text_hist = HistorySet({"ref": {"$regex": pattern}})
print "Cascading Text History {} to {}".format(kwargs['old'], kwargs['new'])
for h in text_hist:
h.ref = h.ref.replace(kwargs["old"], kwargs["new"], 1)
h.save()
link_hist = HistorySet({"new.refs": {"$regex": pattern}})
print "Cascading Link History {} to {}".format(kwargs['old'], kwargs['new'])
for h in link_hist:
h.new["refs"] = [r.replace(kwargs["old"], kwargs["new"], 1) for r in h.new["refs"]]
h.save()
note_hist = HistorySet({"new.ref": {"$regex": pattern}})
print "Cascading Note History {} to {}".format(kwargs['old'], kwargs['new'])
for h in note_hist:
h.new["ref"] = h.new["ref"].replace(kwargs["old"], kwargs["new"], 1)
h.save()
title_hist = HistorySet({"title": {"$regex": title_pattern}})
print "Cascading Index History {} to {}".format(kwargs['old'], kwargs['new'])
for h in title_hist:
h.title = h.title.replace(kwargs["old"], kwargs["new"], 1)
h.save()
def test_index_regex():
assert Ref('Otzar Midrashim').regex() == prepare_index_regex_for_dependency_process(library.get_index('Otzar Midrashim'))
assert Ref('Zohar').regex() == prepare_index_regex_for_dependency_process(library.get_index('Zohar'))
assert Ref('Genesis').regex() == prepare_index_regex_for_dependency_process(library.get_index('Genesis'))
assert Ref('Rashi on Exodus').regex() == prepare_index_regex_for_dependency_process(library.get_index('Rashi on Exodus'))
assert Ref('Otzar Midrashim').regex(as_list=True) == prepare_index_regex_for_dependency_process(
library.get_index('Otzar Midrashim'), as_list=True)
assert Ref('Zohar').regex(as_list=True) == prepare_index_regex_for_dependency_process(library.get_index('Zohar'), as_list=True)
assert Ref('Genesis').regex(as_list=True) == prepare_index_regex_for_dependency_process(library.get_index('Genesis'), as_list=True)
assert Ref('Rashi on Exodus').regex(as_list=True) == prepare_index_regex_for_dependency_process(
library.get_index('Rashi on Exodus'), as_list=True)
def dep_counts(name):
from sefaria.model.text import prepare_index_regex_for_dependency_process
pattern = prepare_index_regex_for_dependency_process(indx)
ret = {
'version title exact match': model.VersionSet({"title": name}).count(),
'history title exact match': model.HistorySet({"title": name}).count(),
'note match ': model.NoteSet({"ref": {"$regex": pattern}}).count(),
'link match ': model.LinkSet({"refs": {"$regex": pattern}}).count(),
'history refs match ': model.HistorySet({"ref": {"$regex": pattern}}).count(),
'history new refs match ': model.HistorySet({"new.refs": {"$regex": pattern}}).count()
}
return ret
def process_index_title_change_in_history(indx, **kwargs):
def construct_query(attribute, queries):
query_list = [{attribute: {'$regex': query}} for query in queries]
return {'$or': query_list}
print "Cascading History {} to {}".format(kwargs['old'], kwargs['new'])
"""
Update all history entries which reference 'old' to 'new'.
"""
from sefaria.model.text import prepare_index_regex_for_dependency_process
queries = prepare_index_regex_for_dependency_process(indx, as_list=True)
queries = [
query.replace(re.escape(indx.title), re.escape(kwargs["old"]))
for query in queries
]
title_pattern = ur'(^{}$)'.format(re.escape(kwargs["old"]))
text_hist = HistorySet(construct_query('ref', queries), sort=[('ref', 1)])
print "Cascading Text History {} to {}".format(kwargs['old'],
kwargs['new'])
for h in text_hist:
h.ref = h.ref.replace(kwargs["old"], kwargs["new"], 1)
h.save()
link_hist = HistorySet(construct_query("new.refs", queries),
sort=[('new.refs', 1)])
print "Cascading Link History {} to {}".format(kwargs['old'],
kwargs['new'])
for h in link_hist:
h.new["refs"] = [
r.replace(kwargs["old"], kwargs["new"], 1) for r in h.new["refs"]
]
h.save()
note_hist = HistorySet(construct_query("new.ref", queries),
sort=[('new.ref', 1)])
print "Cascading Note History {} to {}".format(kwargs['old'],
kwargs['new'])
for h in note_hist:
h.new["ref"] = h.new["ref"].replace(kwargs["old"], kwargs["new"], 1)
h.save()
title_hist = HistorySet({"title": {
"$regex": title_pattern
}},
sort=[('title', 1)])
print "Cascading Index History {} to {}".format(kwargs['old'],
kwargs['new'])
for h in title_hist:
h.title = h.title.replace(kwargs["old"], kwargs["new"], 1)
h.save()
def dep_counts(name, indx):
def construct_query(attribute, queries):
query_list = [{attribute: {'$regex': query}} for query in queries]
return {'$or': query_list}
from sefaria.model.text import prepare_index_regex_for_dependency_process
patterns = prepare_index_regex_for_dependency_process(indx, as_list=True)
patterns = [pattern.replace(re.escape(indx.title), re.escape(name)) for pattern in patterns]
ret = {
'version title exact match': model.VersionSet({"title": name}, sort=[('title', 1)]).count(),
'history title exact match': model.HistorySet({"title": name}, sort=[('title', 1)]).count(),
'note match ': model.NoteSet(construct_query("ref", patterns), sort=[('ref', 1)]).count(),
'link match ': model.LinkSet(construct_query("refs", patterns)).count(),
'history refs match ': model.HistorySet(construct_query("ref", patterns), sort=[('ref', 1)]).count(),
'history new refs match ': model.HistorySet(construct_query("new.refs", patterns), sort=[('new.refs', 1)]).count()
}
return ret
def process_index_title_change_in_history(indx, **kwargs):
print "Cascading History {} to {}".format(kwargs['old'], kwargs['new'])
"""
Update all history entries which reference 'old' to 'new'.
"""
from sefaria.model.text import prepare_index_regex_for_dependency_process
pattern = prepare_index_regex_for_dependency_process(indx)
pattern = pattern.replace(re.escape(indx.title), re.escape(kwargs["old"]))
title_pattern = ur'(^{}$)'.format(re.escape(kwargs["old"]))
text_hist = HistorySet({"ref": {"$regex": pattern}})
print "Cascading Text History {} to {}".format(kwargs['old'],
kwargs['new'])
for h in text_hist:
h.ref = h.ref.replace(kwargs["old"], kwargs["new"], 1)
h.save()
link_hist = HistorySet({"new.refs": {"$regex": pattern}})
print "Cascading Link History {} to {}".format(kwargs['old'],
kwargs['new'])
for h in link_hist:
h.new["refs"] = [
r.replace(kwargs["old"], kwargs["new"], 1) for r in h.new["refs"]
]
h.save()
note_hist = HistorySet({"new.ref": {"$regex": pattern}})
print "Cascading Note History {} to {}".format(kwargs['old'],
kwargs['new'])
for h in note_hist:
h.new["ref"] = h.new["ref"].replace(kwargs["old"], kwargs["new"], 1)
h.save()
title_hist = HistorySet({"title": {"$regex": title_pattern}})
print "Cascading Index History {} to {}".format(kwargs['old'],
kwargs['new'])
for h in title_hist:
h.title = h.title.replace(kwargs["old"], kwargs["new"], 1)
h.save()
def process_index_title_change_in_history(indx, **kwargs):
def construct_query(attribute, queries):
query_list = [{attribute: {'$regex': query}} for query in queries]
return {'$or': query_list}
print "Cascading History {} to {}".format(kwargs['old'], kwargs['new'])
"""
Update all history entries which reference 'old' to 'new'.
"""
from sefaria.model.text import prepare_index_regex_for_dependency_process
queries = prepare_index_regex_for_dependency_process(indx, as_list=True)
queries = [query.replace(re.escape(indx.title), re.escape(kwargs["old"])) for query in queries]
title_pattern = ur'(^{}$)'.format(re.escape(kwargs["old"]))
text_hist = HistorySet(construct_query('ref', queries), sort=[('ref', 1)])
print "Cascading Text History {} to {}".format(kwargs['old'], kwargs['new'])
for h in text_hist:
h.ref = h.ref.replace(kwargs["old"], kwargs["new"], 1)
h.save()
link_hist = HistorySet(construct_query("new.refs", queries), sort=[('new.refs', 1)])
print "Cascading Link History {} to {}".format(kwargs['old'], kwargs['new'])
for h in link_hist:
h.new["refs"] = [r.replace(kwargs["old"], kwargs["new"], 1) for r in h.new["refs"]]
h.save()
note_hist = HistorySet(construct_query("new.ref", queries), sort=[{'new.ref', 1}])
print "Cascading Note History {} to {}".format(kwargs['old'], kwargs['new'])
for h in note_hist:
h.new["ref"] = h.new["ref"].replace(kwargs["old"], kwargs["new"], 1)
h.save()
title_hist = HistorySet({"title": {"$regex": title_pattern}}, sort=[('title', 1)])
print "Cascading Index History {} to {}".format(kwargs['old'], kwargs['new'])
for h in title_hist:
h.title = h.title.replace(kwargs["old"], kwargs["new"], 1)
h.save()
def process_index_delete_in_links(indx, **kwargs):
from sefaria.model.text import prepare_index_regex_for_dependency_process
pattern = prepare_index_regex_for_dependency_process(indx)
LinkSet({"refs": {"$regex": pattern}}).delete()
def process_index_delete_in_links(indx, **kwargs):
from sefaria.model.text import prepare_index_regex_for_dependency_process
pattern = prepare_index_regex_for_dependency_process(indx)
LinkSet({"refs": {"$regex": pattern}}).delete()
def process_index_delete_in_translation_requests(indx, **kwargs):
from sefaria.model.text import prepare_index_regex_for_dependency_process
pattern = prepare_index_regex_for_dependency_process(indx)
TranslationRequestSet({"refs": {"$regex": pattern}}).delete()
def process_index_delete_in_translation_requests(indx, **kwargs):
from sefaria.model.text import prepare_index_regex_for_dependency_process
pattern = prepare_index_regex_for_dependency_process(indx)
TranslationRequestSet({"refs": {"$regex": pattern}}).delete()
