def get_office_as_es_doc(office):
"""
Return the office as a JSON document suitable for indexation in ElasticSearch.
The `office` parameter can be an `Office` or an `OfficeAdminAdd` instance.
"""
# The `headcount` field of an `OfficeAdminAdd` instance has a `code` attribute.
if hasattr(office.headcount, 'code'):
headcount = office.headcount.code
else:
headcount = office.headcount
try:
headcount = int(headcount)
except (ValueError, TypeError):
headcount = 0
# Cleanup exotic characters.
sanitized_name = encoding_util.sanitize_string(office.office_name)
sanitized_email = encoding_util.sanitize_string(office.email)
sanitized_website = encoding_util.sanitize_string(office.website)
doc = {
'naf': office.naf,
'siret': office.siret,
'score': office.score,
'score_alternance': office.score_alternance,
'headcount': headcount,
'name': sanitized_name,
'email': sanitized_email,
'tel': office.tel,
'website': sanitized_website,
'department': office.departement,
'flag_alternance': int(office.flag_alternance),
'flag_junior': int(office.flag_junior),
'flag_senior': int(office.flag_senior),
'flag_handicap': int(office.flag_handicap),
'flag_pmsmp': int(office.flag_pmsmp),
}
if office.y and office.x:
# Use an array to allow multiple locations per document, see https://goo.gl/fdTaEM
# Multiple locations may be added later via the admin UI.
doc['locations'] = [
{
'lat': office.y,
'lon': office.x
},
]
scores_by_rome, scores_alternance_by_rome, boosted_romes, boosted_alternance_romes = get_scores_by_rome_and_boosted_romes(
office)
if scores_by_rome:
doc['scores_by_rome'] = scores_by_rome
doc['boosted_romes'] = boosted_romes
if scores_alternance_by_rome:
doc['scores_alternance_by_rome'] = scores_alternance_by_rome
doc['boosted_alternance_romes'] = boosted_alternance_romes
return doc
def name(self):
if self.office_name:
result = self.office_name.upper()
elif self.company_name:
result = self.company_name.upper()
else:
result = 'sans nom'
return encoding_util.sanitize_string(result)
def get_fields_from_csv_line(line, delimiter='|'):
# get rid of invisible space characters (\xc2) if present
line = line.strip().replace('\xc2', '')
fields = [encoding_util.sanitize_string(f) for f in line.split(delimiter)]
# The CSV files which are now extracted can contain either '' OR 'NULL' when there are null values.
# We need to replace 'NULL' values with an empty string
fields = ['' if field == 'NULL' else field for field in fields]
return fields
def get_fields_from_csv_line(line):
# get rid of invisible space characters (\xc2) if present
line = line.strip().replace('\xc2', '')
# ignore enclosing quotes if present
if (line[0] in ["'", '"']):
line = line[1:]
if (line[-1] in ["'", '"']):
line = line[:-1]
# split using delimiter special character \xa5
fields = [encoding_util.sanitize_string(f) for f in line.split('\xa5')]
return fields
def get_fields_from_csv_line(line, delimiter='|'):
# get rid of invisible space characters (\xc2) if present
line = line.strip().replace('\xc2', '')
fields = [encoding_util.sanitize_string(f) for f in line.split(delimiter)]
return fields