data_in = read_csv_fp(sys.stdin)
print >>sys.stderr, len(data_in)
found = 0
not_found = 0
data_out = {}
for row, data in data_in.items():
new_data = dict(data)
if data['UFID'] in contact_ufids:
found += 1
contact_data = contact_shelve[data['UFID']]
for name, value in contact_data.items():
new_data[name] = value
new_data['UF_BUSINESS_FAX'] = improve_phone_number(new_data['UF_BUSINESS_FAX'])
new_data['UF_BUSINESS_PHONE'] = improve_phone_number(new_data['UF_BUSINESS_PHONE'])
new_data['DISPLAY_NAME'] = improve_display_name(new_data['DISPLAY_NAME'])
new_data['WORKINGTITLE'] = improve_jobcode_description(new_data['WORKINGTITLE'])
else:
not_found += 1
for name in contact_names:
new_data[name] = ''
data_out[row] = new_data
print >>sys.stderr, 'Found', found
print >>sys.stderr, 'Not found', not_found
write_csv_fp(sys.stdout, data_out)
contact_shelve.close()
from vivopump import read_csv_fp, write_csv_fp, improve_jobcode_description
import sys
data_in = read_csv_fp(sys.stdin)
var_names = data_in[
data_in.keys()[1]].keys() # create a list of var_names from the first row
print >> sys.stderr, "Columns in", var_names
data_out = {}
for row, data in data_in.items():
new_data = dict(data)
# Add these columns
new_data['remove'] = ''
new_data['uri'] = ''
new_data['title'] = improve_jobcode_description(
new_data['JOBCODE_DESCRIPTION'])
new_data['hr_title'] = new_data['JOBCODE_DESCRIPTION']
# Delete these columns
del new_data['JOBCODE']
del new_data['HR_POSITION']
del new_data['JOBCODE_DESCRIPTION']
data_out[row] = new_data
var_names = data_out[
data_out.keys()[1]].keys() # create a list of var_names from the first row
print >> sys.stderr, "Columns out", var_names
write_csv_fp(sys.stdout, data_out)
from vivopump import read_csv_fp, write_csv_fp, improve_jobcode_description
import sys
data_in = read_csv_fp(sys.stdin)
var_names = data_in[data_in.keys()[1]].keys() # create a list of var_names from the first row
print >>sys.stderr, "Columns in", var_names
data_out = {}
for row, data in data_in.items():
new_data =dict(data)
# Add these columns
new_data['remove'] = ''
new_data['uri'] = ''
new_data['title'] = improve_jobcode_description(new_data['JOBCODE_DESCRIPTION'])
new_data['hr_title'] = new_data['JOBCODE_DESCRIPTION']
# Delete these columns
del new_data['JOBCODE']
del new_data['HR_POSITION']
del new_data['JOBCODE_DESCRIPTION']
data_out[row] = new_data
var_names = data_out[data_out.keys()[1]].keys() # create a list of var_names from the first row
print >>sys.stderr, "Columns out", var_names
write_csv_fp(sys.stdout, data_out)
def test_preserve_unicode(self):
in_title = u"CRD TECH PRG 2"
out_title = improve_jobcode_description(in_title)
print out_title
self.assertEqual(u"Coordinator Technician Program 2", out_title)
def test_substitution_at_end(self):
in_title = "RES ASO PROF & DIR"
out_title = improve_jobcode_description(in_title)
print out_title
self.assertEqual("Research Associate Professor & Director", out_title)
def test_simple_substitution(self):
in_title = "ASST PROF"
out_title = improve_jobcode_description(in_title)
print out_title
self.assertEqual("Assistant Professor", out_title)
import sys
contact_shelve = shelve.open("contact.db")
contact_ufids = set(contact_shelve.keys()) # a set of ufids that will not be in the output
contact_names = set(contact_shelve[contact_ufids.pop()].keys())
data_in = read_csv_fp(sys.stdin)
print >>sys.stderr, len(data_in)
found = 0
not_found = 0
data_out = {}
for row, data in data_in.items():
new_data = dict(data)
if data["UFID"] in contact_ufids:
found += 1
contact_data = contact_shelve[data["UFID"]]
for name, value in contact_data.items():
new_data[name] = value
new_data["UF_BUSINESS_FAX"] = improve_phone_number(new_data["UF_BUSINESS_FAX"])
new_data["UF_BUSINESS_PHONE"] = improve_phone_number(new_data["UF_BUSINESS_PHONE"])
new_data["DISPLAY_NAME"] = improve_display_name(new_data["DISPLAY_NAME"])
new_data["WORKINGTITLE"] = improve_jobcode_description(new_data["WORKINGTITLE"])
else:
not_found += 1
for name in contact_names:
new_data[name] = ""
data_out[row] = new_data
print >>sys.stderr, "Found", found
print >>sys.stderr, "Not found", not_found
write_csv_fp(sys.stdout, data_out)
contact_shelve.close()
