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()
# Add these columns
new_data['remove'] = ''
new_data['uri'] = ''
new_data['display_name'] = ''
new_data['first'] = ''
new_data['last'] = ''
new_data['middle'] = ''
new_data['suffix'] = ''
new_data['corresponding'] = ''
new_data['uf'] = ''
# Delete everything not in the keep_names set
for name in new_data.keys():
if name not in keep_names:
del new_data[name]
for author in author_data:
row_out += 1
data_out[row_out] = dict(new_data)
for key in author.keys():
data_out[row_out][key] = author[key]
if key == 'display_name':
data_out[row_out][key] = improve_display_name(author[key])
column_names_out = data_out[1].keys()
print_err("==> {} columns in the output: {}"
.format(len(column_names_out), column_names_out))
write_csv_fp(sys.stdout, data_out)
# Add these columns
new_data['remove'] = ''
new_data['uri'] = ''
new_data['display_name'] = ''
new_data['first'] = ''
new_data['last'] = ''
new_data['middle'] = ''
new_data['suffix'] = ''
new_data['corresponding'] = ''
new_data['uf'] = ''
# Delete everything not in the keep_names set
for name in new_data.keys():
if name not in keep_names:
del new_data[name]
for author in author_data:
row_out += 1
data_out[row_out] = dict(new_data)
for key in author.keys():
data_out[row_out][key] = author[key]
if key == 'display_name':
data_out[row_out][key] = improve_display_name(author[key])
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_standard_case(self):
in_name = "CONLON,MIKE"
out_name = improve_display_name(in_name)
self.assertEqual("Conlon, Mike", out_name)
def test_no_op(self):
in_name = "Conlon, Mike"
out_name = improve_display_name(in_name)
self.assertEqual(in_name, out_name)
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()
