def test_querydocument(db):
from dlx.marc import Bib, Auth, QueryDocument, Condition, Or
from bson import SON
from json import loads
import re
query = QueryDocument(Condition(tag='245', subfields={'a': 'This'}))
assert isinstance(query.compile(), SON)
qjson = query.to_json()
qdict = loads(qjson)
assert qdict['245']['$elemMatch']['subfields']['$elemMatch']['code'] == 'a'
assert qdict['245']['$elemMatch']['subfields']['$elemMatch']['value'] == 'This'
query = QueryDocument(
Condition(tag='245', subfields={'a': re.compile(r'(This|Another)'), 'b': 'is the', 'c': 'title'}),
Condition(tag='650', modifier='exists'),
Or(
Condition(tag='710', modifier='exists'),
Condition(tag='520', modifier='not_exists')
)
)
assert len(list(Bib.find(query.compile()))) == 2
query = QueryDocument(
Condition(tag='110', subfields={'a': 'Another header'}),
)
assert len(list(Auth.find(query.compile()))) == 1
assert Auth.find_one(query.compile()).id == 2
def unbis():
'''
outputs UNBIS thesaurus subject heading records in MARCXML format /unbis?skip=n&limit=m
skip=n URL parameter is used to skip n records. Default is 0.
limit=m URL parameter is used to limit number of records returned. Default is 50.
it uses DLX bibset.to_xml serialization function to output fields 035 and 150 in MARCXML
'''
try:
skp = int(request.args.get('skip'))
except:
skp = 0
try:
limt = int(request.args.get('limit'))
except:
limt = 50
print(f"skip is {skp} and limit is {limt}")
query = QueryDocument(
Condition(tag='035', subfields={'a': re.compile('^T')}))
print(query.to_json())
authset = AuthSet.from_query(query,
projection={
'035': 1,
'150': 1
},
skip=skp,
limit=limt)
unbis = authset.to_xml()
return Response(unbis, mimetype='text/xml')
def xml(date):
'''
outputs records in MARCXML format for the date which is provided as a dynamic route in YYYYMMDD or YYYY-MM-DD formats
/YYYYMMDD/xml?skip=n&limit=m
skip=n URL parameter is used to skip n records. Default is 0.
limit=m URL parameter is used to limit number of records returned. Default is 50.
if the date is in wrong format the function returns today's records
it uses DLX bibset.to_xml serialization function to output MARCXML
'''
try:
skp = int(request.args.get('skip'))
except:
skp = 0
try:
limt = int(request.args.get('limit'))
except:
limt = 50
print(f"skip is {skp} and limit is {limt}")
str_date = date.replace('-', '')
print(f"the original str_date is {str_date}")
if len(str_date) != 8:
#date = datetime.datetime.now()
str_date = str(date.year) + str(date.month) + str(date.day)
print(f"the str_date is {str_date}")
query = QueryDocument(
Condition(tag='998', subfields={'z': re.compile('^' + str_date)}),
Condition(tag='029', subfields={'a': 'JN'}))
print(query.to_json())
start_time = datetime.now()
bibset = BibSet.from_query(query,
projection={
'029': 1,
'091': 1,
'191': 1,
'245': 1,
'269': 1,
'650': 1,
'991': 1
},
skip=skp,
limit=limt)
print(f"duration for 998z was {datetime.now()-start_time}")
start_time_xml = datetime.now()
xml = bibset.to_xml()
#removing double space from the xml; creates pbs with the job number on ODS export
xml = xml.replace(" ", " ")
print(
f"duration for xml serialization was {datetime.now()-start_time_xml}")
return Response(xml, mimetype='text/xml')
def unbis_tcode(tcode):
'''
looks up UNBIS thesaurus T codes and returns matching subject heading records
skip=n URL parameter is used to skip n records. Default is 0.
limit=m URL parameter is used to limit number of records returned. Default is 50.
it uses DLX bibset.to_xml serialization function to output fields 035 and 150 in MARCXML
'''
try:
skp = int(request.args.get('skip'))
except:
skp = 0
try:
limt = int(request.args.get('limit'))
except:
limt = 50
#print(f"skip is {skp} and limit is {limt}")
query = QueryDocument(
Condition(tag='035', subfields={'a': re.compile(str(tcode).upper())}))
print(query.to_json())
dict1 = {}
authset = AuthSet.from_query(query,
projection={
'035': 1,
'150': 1,
'993': 1,
'994': 1,
'995': 1,
'996': 1,
'997': 1
},
skip=skp,
limit=limt)
for auth in authset:
val_035a = auth.get_values('035', 'a')
#print(f"035 values are: {val_035a}")
val_035a = ''.join([str for str in val_035a if str[0] == 'T'])
#dict1[auth.get_value('035','a')]=auth.get_value('150','a')
dict1[val_035a] = {
'EN': auth.get_value('150', 'a'),
'FR': auth.get_value('993', 'a'),
'ES': auth.get_value('994', 'a'),
'AR': auth.get_value('995', 'a'),
'ZH': auth.get_value('996', 'a'),
'RU': auth.get_value('997', 'a')
}
#dict1['FR']=auth.get_value('993','a')
#unbis=authset.to_xml()
#return Response(unbis, mimetype='text/xml')
return jsonify(dict1)
def unbis_label(label):
'''
looks up UNBIS thesaurus labels and returns matching T codes
skip=n URL parameter is used to skip n records. Default is 0.
limit=m URL parameter is used to limit number of records returned. Default is 50.
it uses DLX authset to output fields 035 and 150
'''
try:
skp = int(request.args.get('skip'))
except:
skp = 0
try:
limt = int(request.args.get('limit'))
except:
limt = 50
print(f"skip is {skp} and limit is {limt}")
query = QueryDocument(
Condition(tag='150', subfields={'a': re.compile(str(label).upper())}))
print(query.to_json())
dict1 = {}
authset = AuthSet.from_query(query,
projection={
'035': 1,
'150': 1
},
skip=skp,
limit=limt)
'''
for auth in authset:
dict1[auth.get_value('150','a')]=auth.get_value('035','a')
#unbis=authset.to_xml()
#return Response(unbis, mimetype='text/xml')
return jsonify(dict1)
'''
for auth in authset:
val_035a = auth.get_values('035', 'a')
#print(f"035 values are: {val_035a}")
val_035a = ''.join([str for str in val_035a if str[0] == 'T'])
#dict1[auth.get_value('035','a')]=auth.get_value('150','a')
dict1[auth.get_value('150', 'a')] = val_035a
#dict1['FR']=auth.get_value('993','a')
#unbis=authset.to_xml()
#return Response(unbis, mimetype='text/xml')
return jsonify(dict1)
from bson import Regex
from dlx import DB
from dlx.marc import BibSet, QueryDocument, Condition
from config import Config
DB.connect(Config.connect_string)
query = QueryDocument(Condition(tag='191', modifier='exists'),
Condition(tag='269', subfields={'a': Regex('^1975')}))
print(query.to_json())
bibset = BibSet.from_query(query, projection={'191': True}, skip=0, limit=0)
print('There are {} results'.format(bibset.count))
bibset.cache()
for bib in bibset.records:
print('id: {}, symbol: {}'.format(bib.id, bib.get_value('191', 'a')))
print(bibset.to_xml())
def votes(topic):
'''
looks up UNBIS thesaurus labels and returns matching T codes ..
skip=n URL parameter is used to skip n records. Default is 0.
limit=m URL parameter is used to limit number of records returned. Default is 50.
it uses DLX authset to output fields 035 and 150
'''
try:
skp = int(request.args.get('skip'))
except:
skp = 0
try:
limt = int(request.args.get('limit'))
except:
limt = 50
try:
yr_from = request.args.get('year_from')
except:
yr_from = "1980"
try:
yr_to = request.args.get('year_to')
except:
yr_to = '2020'
try:
cntry = request.args.get('Country')
except:
cntry = 'CANADA'
try:
vt = request.args.get('Vote')
except:
vt = 'A'
print(f"skip is {skp} and limit is {limt}")
print(f"year_from is {yr_from} and year_to is {yr_to}")
print(f"Country is {cntry}")
print(f"Vote is {vt}")
query = QueryDocument(
Condition(tag='191', subfields={'d': re.compile(str(topic))}),
Condition(tag='191', subfields={'a': re.compile('^A')}))
print(query.to_json())
dict_auth_ids = {}
authset = AuthSet.from_query(query,
projection={
'001': 1,
'191': 1
},
skip=skp,
limit=limt)
for auth in authset:
dict_auth_ids[auth.get_value('191', 'a')] = auth.get_value('001')
#unbis=authset.to_xml()
#return Response(unbis, mimetype='text/xml')
#return jsonify(dict_auth_ids)
dict_bibs = {}
str_bibs = ''
votecountry = ''
for key, value in dict_auth_ids.items():
#sample_id=int(dict_auth_ids['A/74/251'])
print(f"the id of {key} is {value}")
query_bib = QueryDocument(
Condition(tag='991', subfields={'d': int(value)}),
Condition(tag='989',
subfields={'a': re.compile(str('Voting Data'))}))
print(query_bib.to_json())
bibset = BibSet.from_query(query_bib,
projection={
'001': 1,
'791': 1,
'967': 1
},
skip=skp,
limit=limt)
for bib in bibset:
for field in bib.get_fields('967'):
votecountry = field.get_value("d") + field.get_value("e")
#print(f'Country+Vote: {votecountry}')
if str(votecountry) == str(vt) + str(
cntry
): # for the entries matching input query parameters using AND logic
dict_bibs[bib.get_value('791', 'a')] = bib.get_value('001')
str_bibs = str_bibs + ' OR 791:[' + bib.get_value(
'791', 'a') + ']'
print(str_bibs)
return jsonify(dict_bibs)