def test_01_read_01(self):
# Check that reading the gold standard file gives the right object
clcsv = ClCsv(self.gold_csv.name)
assert clcsv.get_column(1) == ('issn1', ['i1a1', 'i1a2', 'i1a3', 'i1a4'])
assert clcsv.get_column('issn1') == ('issn1', ['i1a1', 'i1a2', 'i1a3', 'i1a4'])
assert clcsv.get_column(0) == ('', ['q1', 'q2', 'q3', 'q4'])
assert clcsv.get_column('issn4') == ('issn4', ['19', '', 'i4a3', 'i4a4'])
def test_08_read_unicode(self):
# Check that reading the gold standard file gives the right object
clcsv = ClCsv(self.gold_csv_unicode.name)
assert clcsv.get_column(1) == ('иссн1',
['ила1', 'ила2', 'ила3', 'ила4'])
assert clcsv.get_column('иссн1') == ('иссн1',
['ила1', 'ила2', 'ила3', 'ила4'])
assert clcsv.get_column(0) == ('', ['в1', 'в2', 'в3', 'в4'])
def test_06_gets(self):
# test the functions which get
rd_csv = ClCsv(self.gold_csv.name)
assert rd_csv.get_colnumber('issn3') == 3
assert rd_csv.get_colnumber('pineapple') == None
assert rd_csv.get_rownumber('q4') == 4
assert rd_csv.get_rownumber('nothing') == None
def make_csv(path, reapps):
cols = {}
for r in reapps:
assert isinstance(r, models.Suggestion) # for pycharm type inspection
bj = r.bibjson()
issn = bj.get_one_identifier(idtype=bj.P_ISSN)
if issn is None:
issn = bj.get_one_identifier(idtype=bj.E_ISSN)
if issn is None:
continue
kvs = Suggestion2QuestionXwalk.suggestion2question(r)
cols[issn] = kvs
issns = cols.keys()
issns.sort()
sheet = ClCsv(path)
qs = None
for i in issns:
if qs is None:
qs = [q for q, _ in cols[i]]
sheet.set_column("", qs)
vs = [v for _, v in cols[i]]
sheet.set_column(i, vs)
sheet.save()
def open_csv(path):
try:
sheet = ClCsv(path)
except:
raise CsvValidationException(
"Unable to open CSV - may be corrupt or a different file format.")
return sheet
def _wrong_questions(self):
sheet = ClCsv("wrong_questions.csv")
sheet.set_column("", ["Q" + str(i) for i in range(56)])
c1 = deepcopy(APPLICATION_COL)
c1[0] = "First Title"
c1[3] = "1234-5678"
c1[4] = "9876-5432"
sheet.set_column(c1[3], c1)
sheet.save()
def test_07_write_unicode(self):
# write an object to a file, and check against pre-bult one
wr_csv = ClCsv(self.PRFX + 'test_write_csv')
wr_csv.set_column(u'', [u'в1', u'в2', u'в3', u'в4'])
wr_csv.set_column(u'иссн1', [u'ила1', u'ила2', u'ила3', u'ила4'])
wr_csv.save()
wr_lines = open(wr_csv.file_object.name, 'rb').readlines()
gold_lines_unicode = open(self.gold_csv_unicode.name, 'rb').readlines()
assert gold_lines_unicode == wr_lines
def make_csv(path, reapps):
cols = {}
for r in reapps:
assert isinstance(r, models.Suggestion) # for pycharm type inspection
bj = r.bibjson()
issn = bj.get_one_identifier(idtype=bj.P_ISSN)
if issn is None:
issn = bj.get_one_identifier(idtype=bj.E_ISSN)
if issn is None:
continue
kvs = Suggestion2QuestionXwalk.suggestion2question(r)
cols[issn] = kvs
issns = cols.keys()
issns.sort()
sheet = ClCsv(path)
qs = None
for i in issns:
if qs is None:
qs = [q for q, _ in cols[i]]
sheet.set_column("", qs)
vs = [v for _, v in cols[i]]
sheet.set_column(i, vs)
sheet.save()
def _wrong_issn(self):
sheet = ClCsv("wrong_issn.csv")
qs = reapplication.Suggestion2QuestionXwalk.question_list()
sheet.set_column("", qs)
c1 = deepcopy(APPLICATION_COL)
c1[0] = "First Title"
c1[3] = "6754-0000"
c1[4] = "8776-0998"
sheet.set_column(c1[3], c1)
sheet.save()
def _wrong_questions(self):
sheet = ClCsv("wrong_questions.csv")
sheet.set_column("", ["Q" + str(i) for i in range(56)])
c1 = deepcopy(APPLICATION_COL)
c1[0] = "First Title"
c1[3] = "1234-5678"
c1[4] = "9876-5432"
sheet.set_column(c1[3], c1)
sheet.save()
def test_07_write_unicode(self):
# write an object to a file, and check against pre-bult one
wr_csv = ClCsv(self.PRFX + 'test_write_csv')
wr_csv.set_column(u'', [u'в1', u'в2', u'в3', u'в4'])
wr_csv.set_column(u'иссн1', [u'ила1', u'ила2', u'ила3', u'ила4'])
wr_csv.save()
wr_lines = open(wr_csv.file_object.name, 'rb').readlines()
gold_lines_unicode = open(self.gold_csv_unicode.name, 'rb').readlines()
assert gold_lines_unicode == wr_lines
def test_06_gets(self):
# test the functions which get
rd_csv = ClCsv(self.gold_csv.name)
assert rd_csv.get_colnumber('issn3') == 3
assert rd_csv.get_colnumber('pineapple') == None
assert rd_csv.get_rownumber('q4') == 4
assert rd_csv.get_rownumber('nothing') == None
def test_01_read_01(self):
# Check that reading the gold standard file gives the right object
clcsv = ClCsv(self.gold_csv.name)
assert clcsv.get_column(1) == ('issn1',
['i1a1', 'i1a2', 'i1a3', 'i1a4'])
assert clcsv.get_column('issn1') == ('issn1',
['i1a1', 'i1a2', 'i1a3', 'i1a4'])
assert clcsv.get_column(0) == ('', ['q1', 'q2', 'q3', 'q4'])
assert clcsv.get_column('issn4') == ('issn4',
['19', '', 'i4a3', 'i4a4'])
def test_03_read_03(self):
# When the file object is closed
assert self.gold_csv.closed
clcsv = ClCsv(self.gold_csv)
assert clcsv.get_column(3) == ('issn3',
['i3a1', 'i3a2', 'i3a3', 'i3a4'])
def test_02_read_02(self):
# Create an open file object first and pass it in (a different form of CSV creation)
f = open(self.gold_csv.name, 'rb')
clcsv = ClCsv(f)
assert clcsv.get_column(3) == ('issn3',
['i3a1', 'i3a2', 'i3a3', 'i3a4'])
def test_08_read_unicode(self):
# Check that reading the gold standard file gives the right object
clcsv = ClCsv(self.gold_csv_unicode.name)
assert clcsv.get_column(1) == (u'иссн1', [u'ила1', u'ила2', u'ила3', u'ила4'])
assert clcsv.get_column(u'иссн1') == (u'иссн1', [u'ила1', u'ила2', u'ила3', u'ила4'])
assert clcsv.get_column(0) == (u'', [u'в1', u'в2', u'в3', u'в4'])
def _invalid_content(self):
sheet = ClCsv("invalid.csv")
# first column is the questions
qs = reapplication.Suggestion2QuestionXwalk.question_list()
sheet.set_column("", qs)
# add 3 columns of results for testing purposes
c1 = deepcopy(APPLICATION_COL)
c1[0] = "First Title"
c1[1] = "This isn't a URL (but it should be)"
c1[3] = "1234-5678"
c1[4] = "9876-5432"
sheet.set_column(c1[3], c1)
c2 = deepcopy(APPLICATION_COL)
c2[0] = "Second Title"
c2[3] = "2345-6789"
c2[4] = "8765-4321"
c2[11] = "" # This field is required (country)
sheet.set_column(c2[3], c2)
c3 = deepcopy(APPLICATION_COL)
c3[0] = "Third Title"
c3[3] = "3456-7890"
c3[4] = "7654-3210"
sheet.set_column(c3[3], c3)
sheet.save()
def test_02_read_02(self):
# Create an open file object first and pass it in (a different form of CSV creation)
f = open(self.gold_csv.name, 'rb')
clcsv = ClCsv(f)
assert clcsv.get_column(3) == ('issn3', ['i3a1', 'i3a2', 'i3a3', 'i3a4'])
def _invalid_content(self):
sheet = ClCsv("invalid.csv")
# first column is the questions
qs = reapplication.Suggestion2QuestionXwalk.question_list()
sheet.set_column("", qs)
# add 3 columns of results for testing purposes
c1 = deepcopy(APPLICATION_COL)
c1[0] = "First Title"
c1[1] = "This isn't a URL (but it should be)"
c1[3] = "1234-5678"
c1[4] = "9876-5432"
sheet.set_column(c1[3], c1)
c2 = deepcopy(APPLICATION_COL)
c2[0] = "Second Title"
c2[3] = "2345-6789"
c2[4] = "8765-4321"
c2[11] = "" # This field is required (country)
sheet.set_column(c2[3], c2)
c3 = deepcopy(APPLICATION_COL)
c3[0] = "Third Title"
c3[3] = "3456-7890"
c3[4] = "7654-3210"
sheet.set_column(c3[3], c3)
c4 = deepcopy(APPLICATION_COL)
c4[0] = "Fourth Title"
c4[3] = "4567-8901"
c4[4] = "6543-2109"
c4[54] = "invalid url"
sheet.set_column(c4[3], c4)
for c_num in range(5, 80): # columns 1-4 are defined already, and we need, say, 26 * 3 columns for test 16 (so we can comfortably pick one from the middle and have it be > 27th column), so roughly 78, so why not 79?
c_num = str(c_num)
col = deepcopy(APPLICATION_COL)
col[0] = c_num + " Title"
col[3] = "6529-540" if len(c_num) == 1 else "6529-54"
col[3] += c_num
col[54] = "invalid url"
sheet.set_column(col[3], col)
sheet.save()
def test_04_write_01(self):
# write an object to a file, and check against pre-bult one
wr_csv = ClCsv(self.PRFX + 'test_write_csv')
wr_csv.set_column('', ['q1', 'q2', 'q3', 'q4'])
wr_csv.set_column('issn1', ['i1a1', 'i1a2', 'i1a3', 'i1a4'])
wr_csv.set_column('issn2', ['i2a1', 'i2a2', 'i2a3', 'i2a4'])
wr_csv.set_column('issn3', ['i3a1', 'i3a2', 'i3a3', 'i3a4'])
wr_csv.set_column('issn4', [19, None, 'i4a3', 'i4a4'])
wr_csv.save()
wr_lines = open(wr_csv.file_object.name, 'rb').readlines()
gold_lines = open(self.gold_csv.name, 'rb').readlines()
assert gold_lines == wr_lines
def test_05_write_02(self):
# Check we can overwrite an existing column.
ow_csv = ClCsv(self.PRFX + 'test_overwrite_csv')
ow_csv.set_column('', ['q1', 'q2', 'q3', 'q4'])
ow_csv.set_column('issn1', ['i1a1', 'i1a2', 'i1a3', 'i1a4'])
ow_csv.set_column('issn2', ['i2a1', 'i2a2', 'i2a3', 'WRONG'])
ow_csv.set_column('issn3', ['i3a1', 'i3a2', 'i3a3', 'i3a4'])
ow_csv.set_column('issnX', ['iXa1', 'iXa2', 'iXa3', 'iXa4'])
ow_csv.save()
ow_csv = ClCsv(ow_csv.file_object.name)
ow_csv.set_column('issn2', ['i2a1', 'i2a2', 'i2a3', 'i2a4'])
ow_csv.set_column(4, ('issn4', [19, None, 'i4a3', 'i4a4']))
ow_csv.save()
# The changes above should make the file the same as our gold standard
ow_lines = open(ow_csv.file_object.name, 'rb').readlines()
gold_lines = open(self.gold_csv.name, 'rb').readlines()
assert gold_lines == ow_lines
def test_04_write_01(self):
# write an object to a file, and check against pre-bult one
wr_csv = ClCsv(self.PRFX + 'test_write_csv')
wr_csv.set_column('', ['q1', 'q2', 'q3', 'q4'])
wr_csv.set_column('issn1', ['i1a1', 'i1a2', 'i1a3', 'i1a4'])
wr_csv.set_column('issn2', ['i2a1', 'i2a2', 'i2a3', 'i2a4'])
wr_csv.set_column('issn3', ['i3a1', 'i3a2', 'i3a3', 'i3a4'])
wr_csv.set_column('issn4', [19, None, 'i4a3', 'i4a4'])
wr_csv.save()
wr_lines = open(wr_csv.file_object.name, 'rb').readlines()
gold_lines = open(self.gold_csv.name, 'rb').readlines()
assert gold_lines == wr_lines
il = [s.strip() for s in i.split(',')]
j = Journal.find_by_issn(il, in_doaj=False)
if len(j) == 0:
subjects_column.append('Error: not found')
elif len(j) == 1:
subj = j[0].bibjson().subjects()
subjects_column.append(', '.join(
[f"{s['scheme']}:{s['code']} - {s['term']}" for s in subj]))
else:
subjects_column.append(
'Error: multiple records found for that ISSN')
return subjects_column
if __name__ == '__main__':
# Steps for issue 2337
csv = ClCsv(
'/home/cloo/DOAJ_removed_22012020_SuspectedEditorialMisconduct.1.csv')
heading, issns = csv.get_column('ISSN')
subjects = lookup_subject_categories(issns)
newcsv = ClCsv(
'/home/cloo/DOAJ_removed_22012020_SuspectedEditorialMisconduct.2.csv')
newcsv.data = deepcopy(csv.data)
# Add subject data to new CSV as extra column
newcsv.set_column('Subjects', subjects)
newcsv.save()
def test_03_read_03(self):
# When the file object is closed
assert self.gold_csv.closed
clcsv = ClCsv(self.gold_csv)
assert clcsv.get_column(3) == ('issn3', ['i3a1', 'i3a2', 'i3a3', 'i3a4'])
def test_05_write_02(self):
# Check we can overwrite an existing column.
ow_csv = ClCsv(self.PRFX + 'test_overwrite_csv')
ow_csv.set_column('', ['q1', 'q2', 'q3', 'q4'])
ow_csv.set_column('issn1', ['i1a1', 'i1a2', 'i1a3', 'i1a4'])
ow_csv.set_column('issn2', ['i2a1', 'i2a2', 'i2a3', 'WRONG'])
ow_csv.set_column('issn3', ['i3a1', 'i3a2', 'i3a3', 'i3a4'])
ow_csv.set_column('issnX', ['iXa1', 'iXa2', 'iXa3', 'iXa4'])
ow_csv.save()
ow_csv = ClCsv(ow_csv.file_object.name)
ow_csv.set_column('issn2', ['i2a1', 'i2a2', 'i2a3', 'i2a4'])
ow_csv.set_column(4, ('issn4', [19, None, 'i4a3', 'i4a4']))
ow_csv.save()
# The changes above should make the file the same as our gold standard
ow_lines = open(ow_csv.file_object.name, 'rb').readlines()
gold_lines = open(self.gold_csv.name, 'rb').readlines()
assert gold_lines == ow_lines
def _make_valid_csv(self):
sheet = ClCsv("valid.csv")
# first column is the questions
qs = reapplication.Suggestion2QuestionXwalk.question_list()
sheet.set_column("", qs)
# add 3 columns of results for testing purposes
c1 = deepcopy(APPLICATION_COL)
c1[0] = "First Title"
c1[3] = "1234-5678"
c1[4] = "9876-5432"
sheet.set_column(c1[3], c1)
c2 = deepcopy(APPLICATION_COL)
c2[0] = "Second Title"
c2[3] = "2345-6789"
c2[4] = "8765-4321"
sheet.set_column(c2[3], c2)
c3 = deepcopy(APPLICATION_COL)
c3[0] = "Third Title"
c3[3] = "3456-7890"
c3[4] = "7654-3210"
sheet.set_column(c3[3], c3)
sheet.save()
def _make_valid_csv(self):
sheet = ClCsv("valid.csv")
# first column is the questions
qs = reapplication.Suggestion2QuestionXwalk.question_list()
sheet.set_column("", qs)
# add 3 columns of results for testing purposes
c1 = deepcopy(APPLICATION_COL)
c1[0] = "First Title"
c1[3] = "1234-5678"
c1[4] = "9876-5432"
sheet.set_column(c1[3], c1)
c2 = deepcopy(APPLICATION_COL)
c2[0] = "Second Title"
c2[3] = "2345-6789"
c2[4] = "8765-4321"
sheet.set_column(c2[3], c2)
c3 = deepcopy(APPLICATION_COL)
c3[0] = "Third Title"
c3[3] = "3456-7890"
c3[4] = "7654-3210"
sheet.set_column(c3[3], c3)
sheet.save()
