def lookup_and_save(new, debug=False):
"""Merge new docket info into the database.
Start by attempting to lookup an existing Docket. If that's not found,
create a new one. Either way, merge all the attributes of `new` into the
Docket found, and then save the Docket.
Returns None if an error occurs, else, return the new or updated Docket.
"""
try:
d = Docket.objects.get(pacer_case_id=new.pacer_case_id,
court=new.court)
except (Docket.DoesNotExist, Docket.MultipleObjectsReturned):
d = None
if d is None:
ds = Docket.objects.filter(docket_number=new.docket_number,
court=new.court).order_by('-date_filed')
count = ds.count()
if count < 1:
# Can't find it by pacer_case_id or docket_number. Make a new item.
d = Docket(source=Docket.RECAP)
elif count == 1:
# Nailed it!
d = ds[0]
elif count > 1:
# Too many dockets returned. Disambiguate.
logger.error("Got multiple results while attempting save.")
def is_different(x):
return x.pacer_case_id and x.pacer_case_id != new.pacer_case_id
if all([is_different(d) for d in ds]):
# All the dockets found match on docket number, but have
# different pacer_case_ids. This means that the docket has
# multiple pacer_case_ids in PACER, and we should mirror that
# in CL by creating a new docket for the new item.
d = Docket(source=Docket.RECAP)
else:
# Just use the most recent docket. Looking at the data, this is
# OK. Nearly all of these are dockets associated with clusters
# that can be merged (however, that's a project for clusters).
d = ds[0]
# Add RECAP as a source if it's not already.
if d.source in [Docket.DEFAULT, Docket.SCRAPER]:
d.source = Docket.RECAP_AND_SCRAPER
elif d.source == Docket.COLUMBIA:
d.source = Docket.COLUMBIA_AND_RECAP
elif d.source == Docket.COLUMBIA_AND_SCRAPER:
d.source = Docket.COLUMBIA_AND_RECAP_AND_SCRAPER
for attr, v in new.__dict__.items():
setattr(d, attr, v)
if not debug:
d.save()
logger.info("Saved as Docket %s: https://www.courtlistener.com%s" %
(d.pk, d.get_absolute_url()))
return d
def save(self, debug):
"""Save the item to the database, updating any existing items.
Returns None if an error occurs.
"""
required_fields = ['case_name', 'date_filed']
for field in required_fields:
if not getattr(self, field):
print " Missing required field: %s" % field
return None
try:
d = Docket.objects.get(
Q(pacer_case_id=self.pacer_case_id)
| Q(docket_number=self.docket_number),
court=self.court,
)
if d.source == Docket.SCRAPER:
d.source = Docket.RECAP_AND_SCRAPER
except Docket.DoesNotExist:
d = Docket(source=Docket.RECAP, )
except Docket.MultipleObjectsReturned:
print " Got multiple results while attempting save."
return None
for attr, v in self.__dict__.items():
setattr(d, attr, v)
if not debug:
d.save()
print " Saved as Docket %s: https://www.courtlistener.com%s" % (
d.pk, d.get_absolute_url())
return d
def lookup_and_save(new, debug=False):
"""Merge new docket info into the database.
Start by attempting to lookup an existing Docket. If that's not found,
create a new one. Either way, merge all the attributes of `new` into the
Docket found, and then save the Docket.
Returns None if an error occurs, else, return the new or updated Docket.
"""
try:
d = Docket.objects.get(pacer_case_id=new.pacer_case_id,
court=new.court)
except (Docket.DoesNotExist, Docket.MultipleObjectsReturned):
d = None
if d is None:
ds = Docket.objects.filter(docket_number=new.docket_number,
court=new.court).order_by('-date_filed')
count = ds.count()
if count < 1:
# Can't find it by pacer_case_id or docket_number. Make a new item.
d = Docket(source=Docket.RECAP)
elif count == 1:
# Nailed it!
d = ds[0]
elif count > 1:
# Too many dockets returned. Disambiguate.
logger.error("Got multiple results while attempting save.")
def is_different(x):
return x.pacer_case_id and x.pacer_case_id != new.pacer_case_id
if all([is_different(d) for d in ds]):
# All the dockets found match on docket number, but have
# different pacer_case_ids. This means that the docket has
# multiple pacer_case_ids in PACER, and we should mirror that
# in CL by creating a new docket for the new item.
d = Docket(source=Docket.RECAP)
else:
# Just use the most recent docket. Looking at the data, this is
# OK. Nearly all of these are dockets associated with clusters
# that can be merged (however, that's a project for clusters).
d = ds[0]
# Add RECAP as a source if it's not already.
if d.source in [Docket.DEFAULT, Docket.SCRAPER]:
d.source = Docket.RECAP_AND_SCRAPER
elif d.source == Docket.COLUMBIA:
d.source = Docket.COLUMBIA_AND_RECAP
elif d.source == Docket.COLUMBIA_AND_SCRAPER:
d.source = Docket.COLUMBIA_AND_RECAP_AND_SCRAPER
for attr, v in new.__dict__.items():
setattr(d, attr, v)
if not debug:
d.save()
logger.info("Saved as Docket %s: https://www.courtlistener.com%s" %
(d.pk, d.get_absolute_url()))
return d
def save(self, debug):
"""Save the item to the database, updating any existing items.
Returns None if an error occurs.
"""
required_fields = ['case_name', 'date_filed']
for field in required_fields:
if not getattr(self, field):
print " Missing required field: %s" % field
return None
try:
d = Docket.objects.get(
Q(pacer_case_id=self.pacer_case_id) |
Q(docket_number=self.docket_number),
court=self.court,
)
if d.source == Docket.SCRAPER:
d.source = Docket.RECAP_AND_SCRAPER
except Docket.DoesNotExist:
d = Docket(
source=Docket.RECAP,
)
except Docket.MultipleObjectsReturned:
print " Got multiple results while attempting save."
return None
for attr, v in self.__dict__.items():
setattr(d, attr, v)
if not debug:
d.save()
print " Saved as Docket %s: https://www.courtlistener.com%s" % (
d.pk,
d.get_absolute_url()
)
return d
