def make_state_judge(item, testing=False):
"""Takes the state judge data <item> and associates it with a Judge object.
Saves the judge to the DB.
"""
if pd.isnull(item['startyear']):
return
date_dob, date_granularity_dob = process_date(item['birthyear'],
item['birthmonth'],
item['birthday'])
date_dod, date_granularity_dod = process_date(item['deathyear'],
item['deathmonth'],
item['deathday'])
if item['firstname'] == '':
return
if not pd.isnull(item['midname']):
if len(item['midname']) == 1:
item['midname'] = item['midname'] + '.'
had_alias_result = False
check = Person.objects.filter(name_first=item['firstname'],
name_last=item['lastname'],
date_dob=date_dob)
name = "%s: %s %s %s" % (item['cl_id'], item['firstname'],
item['lastname'], date_dob)
if check.count() > 0:
print('Warning: %s exists.' % name)
person = check[0]
if person.is_alias:
# Grab the correct person and set our alias variable to True
person = person.is_alias_of
else:
print("Now processing: %s" % name)
person = Person(gender=item['gender'],
date_dob=date_dob,
date_granularity_dob=date_granularity_dob,
date_dod=date_dod,
date_granularity_dod=date_granularity_dod)
if not had_alias_result:
# Only set the name and ID values on non-alias results, otherwise
# you overwrite the good name with the alias name.
person.cl_id = item['cl_id']
person.name_first = item['firstname']
person.name_middle = item['midname']
person.name_last = item['lastname']
person.name_suffix = get_suffix(item['suffname'])
if not testing:
person.save()
if not pd.isnull(item['nickname']):
person_alias = Person(cl_id=item['cl_id'] + "-alias-1",
name_first=item['nickname'],
name_middle=item['midname'],
name_last=item['lastname'],
name_suffix=get_suffix(item['suffname']),
is_alias_of=person)
if not testing:
person_alias.save()
if 'colr' in item['cl_id']:
courtid = get_court_object(item['court'] + ' of ' + item['state'])
else:
courtid = get_court_object(item['court'])
if courtid is None:
print(item)
raise
# assign start date
date_start, date_granularity_start = process_date(item['startyear'],
item['startmonth'],
item['startday'])
if item['endyear'] > 2016:
item['endyear'] = None
date_termination, date_granularity_termination = process_date(
item['endyear'], item['endmonth'], item['endday'])
judgeship = Position(
person=person,
court_id=courtid,
position_type='jud',
date_start=date_start,
date_granularity_start=date_granularity_start,
date_termination=date_termination,
date_granularity_termination=date_granularity_termination,
# how_selected = get_select(courtid,item['startyear']),
termination_reason=item['howended'])
if not testing:
judgeship.save()
if not pd.isnull(item['college']):
if ';' in item['college']:
colls = [x.strip() for x in item['college'].split(';')]
else:
colls = [item['college'].strip()]
for coll in colls:
school = get_school(coll)
if school is not None:
college = Education(
person=person,
school=school,
degree_level='ba',
)
if not testing:
college.save()
if not pd.isnull(item['lawschool']):
if ';' in item['lawschool']:
lschools = [x.strip() for x in item['lawschool'].split(';')]
else:
lschools = [item['lawschool'].strip()]
for L in lschools:
lschool = get_school(L)
if lschool is not None:
lawschool = Education(
person=person,
school=lschool,
degree_level='jd',
)
if not testing:
lawschool.save()
# iterate through job variables and add to career if applicable
for jobvar in [
'prevjudge', 'prevprivate', 'prevpolitician', 'prevprof',
'postjudge', 'postprivate', 'postpolitician', 'postprof'
]:
if pd.isnull(item[jobvar]) or item[jobvar] == 0:
continue
position_type = None
if 'judge' in jobvar:
position_type = 'jud'
elif 'private' in jobvar:
position_type = 'prac'
elif 'politician' in jobvar:
position_type = 'legis'
elif 'prof' in jobvar:
position_type = 'prof'
job_start = None
job_end = None
if 'prev' in jobvar:
job_start = date_start.year - 1
job_end = date_start.year - 1
if 'post' in jobvar:
if date_termination is None:
continue
job_start = date_termination.year + 1
job_end = date_termination.year + 1
job = Position(person=person,
position_type=position_type,
date_start=date(job_start, 1, 1),
date_granularity_start='%Y',
date_termination=date(job_end, 1, 1),
date_granularity_termination='%Y')
if not testing:
job.save()
if not pd.isnull(item['politics']):
politics = PoliticalAffiliation(
person=person, political_party=item['politics'].lower())
if not testing:
politics.save()
if not pd.isnull(item['links']):
links = item['links']
if ';' in links:
urls = [x.strip() for x in links.split(';')]
else:
urls = [links]
for url in urls:
source = Source(person=person, notes=item['notes'], url=url)
if not testing:
source.save()
def make_state_judge(item, testing=False):
"""Takes the state judge data <item> and associates it with a Judge object.
Saves the judge to the DB.
"""
if pd.isnull(item['startyear']):
return
date_dob, date_granularity_dob = process_date(item['birthyear'],
item['birthmonth'],
item['birthday'])
date_dod, date_granularity_dod = process_date(item['deathyear'],
item['deathmonth'],
item['deathday'])
if item['firstname'] == '':
return
if not pd.isnull(item['midname']):
if len(item['midname']) == 1:
item['midname'] = item['midname'] + '.'
had_alias_result = False
check = Person.objects.filter(name_first=item['firstname'],
name_last=item['lastname'], date_dob=date_dob)
name = "%s: %s %s %s" % (item['cl_id'], item['firstname'], item['lastname'],
date_dob)
if check.count() > 0:
print('Warning: %s exists.' % name)
person = check[0]
if person.is_alias:
# Grab the correct person and set our alias variable to True
person = person.is_alias_of
else:
print("Now processing: %s" % name)
person = Person(
gender=item['gender'],
date_dob=date_dob,
date_granularity_dob=date_granularity_dob,
date_dod=date_dod,
date_granularity_dod=date_granularity_dod
)
if not had_alias_result:
# Only set the name and ID values on non-alias results, otherwise
# you overwrite the good name with the alias name.
person.cl_id = item['cl_id']
person.name_first = item['firstname']
person.name_middle = item['midname']
person.name_last = item['lastname']
person.name_suffix = get_suffix(item['suffname'])
if not testing:
person.save()
if not pd.isnull(item['nickname']):
person_alias = Person(
cl_id=item['cl_id'] + "-alias-1",
name_first=item['nickname'],
name_middle=item['midname'],
name_last=item['lastname'],
name_suffix=get_suffix(item['suffname']),
is_alias_of=person
)
if not testing:
person_alias.save()
if 'colr' in item['cl_id']:
courtid = get_court_object(item['court'] + ' of ' + item['state'])
else:
courtid = get_court_object(item['court'])
if courtid is None:
print(item)
raise
# assign start date
date_start, date_granularity_start = process_date(item['startyear'],
item['startmonth'],
item['startday'])
if item['endyear'] > 2016:
item['endyear'] = None
date_termination, date_granularity_termination = process_date(
item['endyear'],
item['endmonth'],
item['endday'])
judgeship = Position(
person=person,
court_id=courtid,
position_type='jud',
date_start=date_start,
date_granularity_start=date_granularity_start,
date_termination=date_termination,
date_granularity_termination=date_granularity_termination,
# how_selected = get_select(courtid,item['startyear']),
termination_reason=item['howended']
)
if not testing:
judgeship.save()
if not pd.isnull(item['college']):
if ';' in item['college']:
colls = [x.strip() for x in item['college'].split(';')]
else:
colls = [item['college'].strip()]
for coll in colls:
school = get_school(coll)
if school is not None:
college = Education(
person=person,
school=school,
degree_level='ba',
)
if not testing:
college.save()
if not pd.isnull(item['lawschool']):
if ';' in item['lawschool']:
lschools = [x.strip() for x in item['lawschool'].split(';')]
else:
lschools = [item['lawschool'].strip()]
for L in lschools:
lschool = get_school(L)
if lschool is not None:
lawschool = Education(
person=person,
school=lschool,
degree_level='jd',
)
if not testing:
lawschool.save()
# iterate through job variables and add to career if applicable
for jobvar in ['prevjudge', 'prevprivate', 'prevpolitician', 'prevprof',
'postjudge', 'postprivate', 'postpolitician', 'postprof']:
if pd.isnull(item[jobvar]) or item[jobvar] == 0:
continue
position_type = None
if 'judge' in jobvar:
position_type = 'jud'
elif 'private' in jobvar:
position_type = 'prac'
elif 'politician' in jobvar:
position_type = 'legis'
elif 'prof' in jobvar:
position_type = 'prof'
job_start = None
job_end = None
if 'prev' in jobvar:
job_start = date_start.year - 1
job_end = date_start.year - 1
if 'post' in jobvar:
if date_termination is None:
continue
job_start = date_termination.year + 1
job_end = date_termination.year + 1
job = Position(
person=person,
position_type=position_type,
date_start=date(job_start, 1, 1),
date_granularity_start='%Y',
date_termination=date(job_end, 1, 1),
date_granularity_termination='%Y'
)
if not testing:
job.save()
if not pd.isnull(item['politics']):
politics = PoliticalAffiliation(
person=person,
political_party=item['politics'].lower()
)
if not testing:
politics.save()
if not pd.isnull(item['links']):
links = item['links']
if ';' in links:
urls = [x.strip() for x in links.split(';')]
else:
urls = [links]
for url in urls:
source = Source(
person=person,
notes=item['notes'],
url=url
)
if not testing:
source.save()
def make_state_judge(item, testing=False):
"""Takes the state judge data <item> and associates it with a Judge object.
Saves the judge to the DB.
"""
if pd.isnull(item['startyear']):
return
date_dob, date_granularity_dob = process_date(item['birthyear'],
item['birthmonth'],
item['birthday'])
date_dod, date_granularity_dod = process_date(item['deathyear'],
item['deathmonth'],
item['deathday'])
if item['firstname'] == '':
return
check = Person.objects.filter(name_first=item['firstname'],
name_last=item['lastname'],
date_dob=date_dob)
if len(check) > 0:
print('Warning: ' + item['firstname'] + ' ' + item['lastname'] + ' ' +
str(date_dob) + ' exists.')
person = check[0]
else:
person = Person(cl_id=item['cl_id'],
name_first=item['firstname'],
name_middle=item['midname'],
name_last=item['lastname'],
name_suffix=get_suffix(item['suffname']),
gender=item['gender'],
date_dob=date_dob,
date_granularity_dob=date_granularity_dob,
date_dod=date_dod,
date_granularity_dod=date_granularity_dod)
if not testing:
person.save()
courtid = get_court_object(item['court'] + ' of ' + item['state'])
if courtid is None:
raise
# assign start date
date_start, date_granularity_start = process_date(item['startyear'],
item['startmonth'],
item['startday'])
if not pd.isnull(item['endyear']) and item['endyear'] < 2016:
item['endyear'] = None
date_termination, date_granularity_termination = process_date(
item['endyear'], item['endmonth'], item['endday'])
judgeship = Position(
person=person,
court_id=courtid,
position_type='jud',
date_start=date_start,
date_granularity_start=date_granularity_start,
date_termination=date_termination,
date_granularity_termination=date_granularity_termination,
# how_selected = get_select(courtid,item['startyear']),
termination_reason=item['howended'])
if not testing:
judgeship.save()
if not pd.isnull(item['college']):
if ';' in item['college']:
colls = [x.strip() for x in item['college'].split(';')]
else:
colls = [item['college'].strip()]
for coll in colls:
school = get_school(coll)
if school is not None:
college = Education(
person=person,
school=school,
degree_level='ba',
)
if not testing:
college.save()
if not pd.isnull(item['lawschool']):
if ';' in item['lawschool']:
lschools = [x.strip() for x in item['lawschool'].split(';')]
else:
lschools = [item['lawschool'].strip()]
for L in lschools:
lschool = get_school(L)
if lschool is not None:
lawschool = Education(
person=person,
school=lschool,
degree_level='jd',
)
if not testing:
lawschool.save()
# iterate through job variables and add to career if applicable
for jobvar in [
'prevjudge', 'prevprivate', 'prevpolitician', 'prevprof',
'postjudge', 'postprivate', 'postpolitician', 'postprof'
]:
if pd.isnull(item[jobvar]) or item[jobvar] == 0:
continue
position_type = None
if 'judge' in jobvar:
position_type = 'jud'
elif 'private' in jobvar:
position_type = 'prac'
elif 'politician' in jobvar:
position_type = 'legis'
elif 'prof' in jobvar:
position_type = 'prof'
job_start = None
job_end = None
if 'prev' in jobvar:
job_start = date_start.year - 1
job_end = date_start.year - 1
if 'post' in jobvar:
if date_termination is None:
continue
job_start = date_termination.year + 1
job_end = date_termination.year + 1
job = Position(person=person,
position_type=position_type,
date_start=date(job_start, 1, 1),
date_granularity_start='%Y',
date_termination=date(job_end, 1, 1),
date_granularity_termination='%Y')
if not testing:
job.save()
if not pd.isnull(item['politics']):
politics = PoliticalAffiliation(person=person,
political_party=item['politics'])
if not testing:
politics.save()
if not pd.isnull(item['links']):
links = item['links']
if ';' in links:
urls = [x.strip() for x in links.split(';')]
else:
urls = [links]
for url in urls:
source = Source(person=person, notes=item['notes'], url=url)
if not testing:
source.save()
def test_get_court_object_from_string(self):
"""Can we get a court object from a string and filename combo?
When importing the Columbia corpus, we use a combination of regexes and
the file path to determine a match.
"""
pairs = (
{
'args': (
"California Superior Court Appellate Division, Kern County.",
'california/supreme_court_opinions/documents/0dc538c63bd07a28.xml',
),
'answer': 'calappdeptsuperct'
},
{
'args': (
"California Superior Court Appellate Department, Sacramento.",
'california/supreme_court_opinions/documents/0dc538c63bd07a28.xml',
),
'answer': 'calappdeptsuperct'
},
{
'args': (
"Appellate Session of the Superior Court",
'connecticut/appellate_court_opinions/documents/0412a06c60a7c2a2.xml',
),
'answer': 'connsuperct'
},
{
'args': (
"Court of Errors and Appeals.",
'new_jersey/supreme_court_opinions/documents/0032e55e607f4525.xml',
),
'answer': 'nj'
},
{
'args': (
"Court of Chancery",
'new_jersey/supreme_court_opinions/documents/0032e55e607f4525.xml',
),
'answer': 'njch'
},
{
'args': (
"Workers' Compensation Commission",
'connecticut/workers_compensation_commission/documents/0902142af68ef9df.xml',
),
'answer': 'connworkcompcom',
},
{
'args': (
'Appellate Session of the Superior Court',
'connecticut/appellate_court_opinions/documents/00ea30ce0e26a5fd.xml'
),
'answer': 'connsuperct',
},
{
'args': (
'Superior Court New Haven County',
'connecticut/superior_court_opinions/documents/0218655b78d2135b.xml'
),
'answer': 'connsuperct',
},
{
'args': (
'Superior Court, Hartford County',
'connecticut/superior_court_opinions/documents/0218655b78d2135b.xml'
),
'answer': 'connsuperct',
},
{
'args': (
"Compensation Review Board WORKERS' COMPENSATION COMMISSION",
'connecticut/workers_compensation_commission/documents/00397336451f6659.xml',
),
'answer': 'connworkcompcom',
},
{
'args': (
'Appellate Division Of The Circuit Court',
'connecticut/superior_court_opinions/documents/03dd9ec415bf5bf4.xml',
),
'answer': 'connsuperct',
},
{
'args': (
'Superior Court for Law and Equity',
'tennessee/court_opinions/documents/01236c757d1128fd.xml',
),
'answer': 'tennsuperct',
},
{
'args': (
'Courts of General Sessions and Oyer and Terminer of Delaware',
'delaware/court_opinions/documents/108da18f9278da90.xml',
),
'answer': 'delsuperct',
},
{
'args': (
'Circuit Court of the United States of Delaware',
'delaware/court_opinions/documents/108da18f9278da90.xml',
),
'answer': 'circtdel',
},
{
'args': (
'Circuit Court of Delaware',
'delaware/court_opinions/documents/108da18f9278da90.xml',
),
'answer': 'circtdel',
},
{
'args': (
'Court of Quarter Sessions Court of Delaware, Kent County.',
'delaware/court_opinions/documents/f01f1724cc350bb9.xml',
),
'answer': 'delsuperct',
},
{
'args': (
"District Court of Appeal.",
'florida/court_opinions/documents/25ce1e2a128df7ff.xml',
),
'answer': 'fladistctapp',
},
{
'args': (
'District Court of Appeal, Lakeland, Florida.',
'florida/court_opinions/documents/25ce1e2a128df7ff.xml',
),
'answer': 'fladistctapp',
},
{
'args': (
'District Court of Appeal Florida.',
'florida/court_opinions/documents/25ce1e2a128df7ff.xml',
),
'answer': 'fladistctapp',
},
{
'args': (
'District Court of Appeal, Florida.',
'florida/court_opinions/documents/25ce1e2a128df7ff.xml',
),
'answer': 'fladistctapp',
},
{
'args': (
'District Court of Appeal of Florida, Second District.',
'florida/court_opinions/documents/25ce1e2a128df7ff.xml',
),
'answer': 'fladistctapp',
},
{
'args': (
'District Court of Appeal of Florida, Second District.',
'/data/dumps/florida/court_opinions/documents/25ce1e2a128df7ff.xml',
),
'answer': 'fladistctapp',
},
{
'args': (
'U.S. Circuit Court',
'north_carolina/court_opinions/documents/fa5b96d590ae8d48.xml',
),
'answer': 'circtnc',
},
{
'args': (
"United States Circuit Court, Delaware District.",
'delaware/court_opinions/documents/6abba852db7c12a1.xml',
),
'answer': 'circtdel',
},
{
'args': (
'Court of Common Pleas Hartford County',
'asdf',
),
'answer': 'connsuperct'
}
)
for d in pairs:
got = get_court_object(*d['args'])
self.assertEqual(
got,
d['answer'],
msg="\nDid not get court we expected: '%s'.\n"
" Instead we got: '%s'" % (d['answer'], got)
)
