def test_row_in_file_filter(self):
r1 = pe.load("testcsv1.csv")
r2 = pe.load("testcsv2.csv")
r2.filter(pe.filters.ColumnFilter([2]))
r1.filter(pe.filters.RowInFileFilter(r2))
result = [1, 'a', 2, 'b', 3, 'c', 8, 'h']
actual = pe.utils.to_array(r1.enumerate())
self.assertEqual(result, actual)
def test_row_value_filter(self):
r1 = pe.load("testcsv1.csv")
r2 = pe.load("testcsv2.csv")
filter_func = lambda array: r2.contains((lambda row: array[0] == row[0] and array[1] == row[1]))
r1.filter(pe.filters.RowValueFilter(filter_func).invert())
result = ['1', 'a', '2', 'b', '3', 'c', '8', 'h']
actual = pe.utils.to_array(r1.enumerate())
assert result == actual
def test_row_in_file_filter(self):
r1 = pe.load("testcsv1.csv")
r2 = pe.load("testcsv2.csv")
r2.filter(pe.filters.ColumnFilter([2]))
r1.filter(pe.filters.RowInFileFilter(r2))
result = ['1', 'a', '2', 'b', '3', 'c', '8', 'h']
actual = pe.utils.to_array(r1.enumerate())
assert result == actual
def test_row_value_filter(self):
r1 = pe.load("testcsv1.csv")
r2 = pe.load("testcsv2.csv")
filter_func = lambda array: r2.contains((lambda row: array[0] == row[0] and array[1] == row[1]))
r1.filter(pe.filters.RowValueFilter(filter_func).invert())
result = ['1', 'a', '2', 'b', '3', 'c', '8', 'h']
actual = pe.utils.to_array(r1.enumerate())
assert result == actual
def test_row_in_file_filter(self):
r1 = pe.load("testcsv1.csv")
r2 = pe.load("testcsv2.csv")
r2.filter(pe.sheets.filters.ColumnFilter([2]))
r1.filter(pe.sheets.filters.RowInFileFilter(r2))
result = [1, 'a', 2, 'b', 3, 'c', 8, 'h']
actual = pe.utils.to_array(r1.enumerate())
self.assertEqual(result, actual)
def test_row_in_file_filter(self):
r1 = pe.load("testcsv1.csv")
r2 = pe.load("testcsv2.csv")
r2.filter(pe.filters.ColumnFilter([2]))
r1.filter(pe.filters.RowInFileFilter(r2))
result = ['1', 'a', '2', 'b', '3', 'c', '8', 'h']
actual = pe.utils.to_array(r1.enumerate())
assert result == actual
def test_pyexcel_issue_5(self):
"""pyexcel issue #5
datetime is not properly parsed
"""
s = pe.load(
os.path.join("tests", "test-fixtures", "test-date-format.xls"))
s.save_as("issue5.xlsx")
s2 = pe.load("issue5.xlsx")
assert s[0, 0] == datetime.datetime(2015, 11, 11, 11, 12, 0)
assert s2[0, 0] == datetime.datetime(2015, 11, 11, 11, 12, 0)
def test_row_value_filter(self):
r1 = pe.load("testcsv1.csv")
r2 = pe.load("testcsv2.csv")
def filter_func(array):
def func(row): return array[0] == row[0] and array[1] == row[1]
return r2.contains(func)
r1.filter(pe.filters.RowValueFilter(filter_func).invert())
result = [1, 'a', 2, 'b', 3, 'c', 8, 'h']
actual = pe.utils.to_array(r1.enumerate())
self.assertEqual(result, actual)
def test_pyexcel_issue_5(self):
"""pyexcel issue #5
datetime is not properly parsed
"""
s = pe.load(
os.path.join("tests", "test-fixtures", "test-date-format.xls")
)
s.save_as("issue5.xlsx", library="pyexcel-libxlsxw")
s2 = pe.load("issue5.xlsx")
eq_(s[0, 0], datetime.datetime(2015, 11, 11, 11, 12, 0))
eq_(s2[0, 0], datetime.datetime(2015, 11, 11, 11, 12, 0))
def test_pyexcel_issue_5(self):
"""pyexcel issue #5
datetime is not properly parsed
"""
s = pe.load(os.path.join("tests",
"test-fixtures",
"test-date-format.xls"))
s.save_as("issue5.xlsx")
s2 = pe.load("issue5.xlsx")
print(s[0,0])
assert s[0,0] == datetime.datetime(2015, 11, 11, 11, 12, 0)
assert s2[0,0] == datetime.datetime(2015, 11, 11, 11, 12, 0)
def test_row_value_filter(self):
r1 = pe.load("testcsv1.csv")
r2 = pe.load("testcsv2.csv")
def filter_func(array):
def func(row):
return array[0] == row[0] and array[1] == row[1]
return r2.contains(func)
r1.filter(pe.sheets.filters.RowValueFilter(filter_func).invert())
result = [1, 'a', 2, 'b', 3, 'c', 8, 'h']
actual = pe.utils.to_array(r1.enumerate())
self.assertEqual(result, actual)
def test_pyexcel_issue_5():
"""pyexcel issue #5
datetime is not properly parsed
"""
s = pe.load(get_fixture("test-date-format.xls"))
assert s[0, 0] == datetime.datetime(2015, 11, 11, 11, 12, 0)
def process_erke_triage(rf_name, wf_name, clinic_folder):
"""
加载Excel文件
:param rf_name 读取文件
:param wf_name 写入文件
:param clinic_folder 科室文件夹
:return:
"""
print "\t读取文件: %s" % rf_name
print "\t写入文件: %s" % wf_name
print "\t科室文件夹: %s" % clinic_folder
create_file(wf_name)
excel_data = pyexcel.load(read_file) # 读取文件
lines = excel_data.get_internal_array()
clinic_words_trie = load_clinic_words_trie(clinic_folder) # 处理科室文件夹
workbook = xlsxwriter.Workbook(wf_name) # 创建Excel
worksheet = workbook.add_worksheet() # 添加Sheet
worksheet.write_row(
0, 0, lines[1] + [u'第一细分', u'词数', u'匹配词', u'第二细分', u'词数', u'匹配词'])
count = 1
for index in range(2, len(lines)):
problem_info = unicode(lines[index][1])
data_line = lines[index] + parse_problem_info(problem_info,
clinic_words_trie)
worksheet.write_row(count, 0, data_line)
count += 1
if count % 10000 == 0:
print "\t count %s" % count
print "写入行数: %s" % count
def choose():
#open xls
link_file = dg.askopenfilename(type="xls")
sheet = exel.load("{}".format(link_file))
#mysql
_host = "localhost"
_passoword = ""
_user = "******"
_db = "sgda"
conn = mysql.Connection(host=_host,
db=_db,
password=_passoword,
user=_user)
exe = conn.cursor()
exe.execute(
"""CREATE TABLE main(%s VARCHAR(32) DEFAULT '' not null,%s INT DEFAULT '0' ,%s INT DEFAULT '0' ,%s INT DEFAULT '0' ,%s INT DEFAULT '0' ,%s INT DEFAULT '0',%s INT DEFAULT '0') """
% ("name", "price", "numper_i_buy", "numper_of_fragment_in_unit",
"numper_unit_sold", "numper_unit_fragment_sold", "total"))
conn.commit()
print("the table created")
for n in sheet.row_range():
exe.execute(""" INSERT INTO main(name) VALUES("%s")""" % (sheet[n, 0]))
conn.commit()
for n in sheet.row_range():
exe.execute(""" UPDATE `main` SET `price`="%s" WHERE `name`="%s" """ %
(sheet[n, 1], sheet[n, 0]))
conn.commit()
exe.execute(
"""CREATE TABLE sell_today(%s VARCHAR(32) DEFAULT '' not null,%s INT DEFAULT '0' ,%s INT DEFAULT '0' ,%s INT DEFAULT '0',%s VARCHAR(32) DEFAULT '' not null,%s VARCHAR(32) DEFAULT '' not null,%s INT DEFAULT '0') """
% ("name", "unit", "fregment", "price", "date", "bill_link",
"bill_numper"))
conn.commit()
conn.close()
def test_pyexcel_issue_8_with_memory_file(self):
"""pyexcel issue #8
formular got lost
"""
tmp_file = "issue_8_save_as.xlsx"
f = open(os.path.join("tests",
"test-fixtures",
"test8.xlsx"),
"rb")
s = pe.load_from_memory('xlsx', f.read())
s.save_as(tmp_file)
s2 = pe.load(tmp_file)
assert str(s) == str(s2)
content = dedent("""
Sheet Name: CNY
+----------+----------+------+---+--------+
| 01/09/13 | 02/09/13 | 1000 | 5 | 13.890 |
+----------+----------+------+---+--------+
| 02/09/13 | 03/09/13 | 2000 | 6 | 33.330 |
+----------+----------+------+---+--------+
| 03/09/13 | 04/09/13 | 3000 | 7 | 58.330 |
+----------+----------+------+---+--------+""").strip("\n")
assert str(s2) == content
os.unlink(tmp_file)
def main(base_dir):
sheet = pe.load(os.path.join(base_dir, "tutorial_datatype_01.xls"),
name_columns_by_row=0)
print(sheet.to_dict())
#{u'userid': [10120.0, 10121.0, 10122.0], u'name': [u'Adam', u'Bella', u'Cedar']}
sheet.column.format(0, str)
print(sheet.to_dict())
def test_pyexcel_issue_5():
"""pyexcel issue #5
datetime is not properly parsed
"""
s = pe.load(get_fixture("test-date-format.xls"))
assert s[0, 0] == datetime.datetime(2015, 11, 11, 11, 12, 0)
def test_pyexcel_issue_8_with_memory_file(self):
"""pyexcel issue #8
formular got lost
"""
tmp_file = "issue_8_save_as.xlsx"
f = open(os.path.join("tests",
"test-fixtures",
"test8.xlsx"),
"rb")
s = pe.load_from_memory('xlsx', f.read())
s.save_as(tmp_file)
s2 = pe.load(tmp_file)
self.assertEqual(str(s), str(s2))
content = dedent("""
CNY:
+----------+----------+------+---+-------+
| 01/09/13 | 02/09/13 | 1000 | 5 | 13.89 |
+----------+----------+------+---+-------+
| 02/09/13 | 03/09/13 | 2000 | 6 | 33.33 |
+----------+----------+------+---+-------+
| 03/09/13 | 04/09/13 | 3000 | 7 | 58.33 |
+----------+----------+------+---+-------+""").strip("\n")
self.assertEqual(str(s2), content)
os.unlink(tmp_file)
def test_odd_row_filter(self):
r = pe.load(self.test_tuple)
r.filter(pe.filters.OddRowFilter())
assert r.number_of_rows() == 1
assert r.number_of_columns() == 4
result = [5, 6, 7, 8]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_single_column_filter_double_invert(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.filters.SingleColumnFilter(0).invert().invert())
assert r.number_of_rows() == 3
assert r.number_of_columns() == 3
result = [2, 3, 4, 6, 7, 8, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_single_column_filter_double_invert(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.sheets.filters.SingleColumnFilter(0).invert().invert())
assert r.number_of_rows() == 3
assert r.number_of_columns() == 3
result = [2, 3, 4, 6, 7, 8, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_column_filter_with_invalid_indices(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.sheets.filters.ColumnFilter([11, -1]))
assert r.number_of_rows() == 3
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_single_row_filter(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.sheets.filters.SingleRowFilter(1))
assert r.number_of_rows() == 2
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_odd_row_filter(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.filters.OddRowFilter())
assert r.number_of_rows() == 1
assert r.number_of_columns() == 4
result = [5, 6, 7, 8]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_odd_row_filter(self):
r = pe.load(self.test_tuple)
r.filter(pe.sheets.filters.OddRowFilter())
assert r.number_of_rows() == 1
assert r.number_of_columns() == 4
result = [5, 6, 7, 8]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def main(base_dir):
# "example.csv","example.ods","example.xls", "example.xlsm"
spreadsheet = pe.load(os.path.join(base_dir, "example.xlsx"))
# columns() returns column based iterator, meaning it can be iterated
# column by column
for value in spreadsheet.columns():
print(value)
def test_write_and_read(self):
data = [[11, 112], [312, 534]]
sheet = pe.Sheet(data)
sheet.save_as(self.testfile)
sheet2 = pe.load(self.testfile)
sheet2.format(int)
result = sheet2.to_array()
assert data == result
def test_row_filter_with_invalid_indices(self):
r = pe.load(self.test_tuple)
r.filter(pe.filters.RowFilter([11, -1]))
assert r.number_of_rows() == 3
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_odd_column_filter(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.filters.OddColumnFilter())
assert r.number_of_rows() == 3
assert r.number_of_columns() == 2
result = [2, 4, 6, 8, 10, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_even_column_filter(self):
r = pe.load(self.test_tuple)
r.filter(pe.sheets.filters.EvenColumnFilter())
assert r.number_of_rows() == 3
assert r.number_of_columns() == 2
result = [1, 3, 5, 7, 9, 11]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_even_column_filter(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.filters.EvenColumnFilter())
assert r.number_of_rows() == 3
assert r.number_of_columns() == 2
result = [1, 3, 5, 7, 9, 11]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_odd_column_filter(self):
r = pe.load(self.test_tuple)
r.filter(pe.sheets.filters.OddColumnFilter())
assert r.number_of_rows() == 3
assert r.number_of_columns() == 2
result = [2, 4, 6, 8, 10, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_row_filter_with_invalid_indices(self):
r = pe.load(self.test_tuple)
r.filter(pe.sheets.filters.RowFilter([11, -1]))
assert r.number_of_rows() == 3
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_even_row_filter(self):
r = pe.load(self.test_tuple)
r.filter(pe.filters.EvenRowFilter())
assert r.number_of_rows() == 2
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def main(base_dir):
# "example.csv","example.ods","example.xls", "example.xlsm"
spreadsheet = pe.load(os.path.join(base_dir,"example.xlsx"))
# columns() returns column based iterator, meaning it can be iterated
# column by column
for value in spreadsheet.columns():
print(value)
def test_odd_column_filter(self):
r = pe.load(self.test_tuple)
r.filter(pe.filters.OddColumnFilter())
assert r.number_of_rows() == 3
assert r.number_of_columns() == 2
result = [2, 4, 6, 8, 10, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_single_row_filter(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.filters.SingleRowFilter(1))
assert r.number_of_rows() == 2
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_column_filter_with_invalid_indices(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.filters.ColumnFilter([11, -1]))
assert r.number_of_rows() == 3
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_write_and_read(self):
data = [[11, 112], [312, 534]]
sheet = pe.Sheet(data)
sheet.save_as(self.testfile)
sheet2 = pe.load(self.testfile)
sheet2.format(int)
result = sheet2.to_array()
assert data == result
def test_even_column_filter(self):
r = pe.load(self.test_tuple)
r.filter(pe.filters.EvenColumnFilter())
assert r.number_of_rows() == 3
assert r.number_of_columns() == 2
result = [1, 3, 5, 7, 9, 11]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_even_row_filter(self):
r = pe.load(self.test_tuple)
r.filter(pe.sheets.filters.EvenRowFilter())
assert r.number_of_rows() == 2
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_pyexcel_issue_5(self):
"""pyexcel issue #5
datetime is not properly parsed
"""
s = pe.load(os.path.join("tests",
"test-fixtures",
"test-date-format.xls"))
assert s[0, 0] == datetime.datetime(2015, 11, 11, 11, 12, 0)
def test_column_index_filter(self):
r = pe.load(self.test_tuple)
def test_func(x): return x in [0, 2]
r.add_filter(pe.filters.ColumnIndexFilter(test_func))
assert r.number_of_rows() == 3
assert r.number_of_columns() == 2
result = [2, 4, 6, 8, 10, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_pyexcel_issue_5():
"""pyexcel issue #5
datetime is not properly parsed
"""
s = pe.get_sheet(file_name=get_fixtures("test-date-format.xls"))
s.save_as("issue5.xlsx")
s2 = pe.load("issue5.xlsx")
assert s[0, 0] == datetime.datetime(2015, 11, 11, 11, 12, 0)
assert s2[0, 0] == datetime.datetime(2015, 11, 11, 11, 12, 0)
def test_row_index_filter(self):
r = pe.load(self.test_tuple)
def filter_func(x): return x in [1]
r.add_filter(pe.filters.RowIndexFilter(filter_func))
assert r.number_of_rows() == 2
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_two_filters(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
f1 = pe.filters.OddRowFilter()
f2 = pe.filters.OddColumnFilter()
r.add_filter(f1)
r.add_filter(f2)
assert r.number_of_columns() == 2
assert r.number_of_rows() == 1
result = [6, 8]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_two_filters(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
f1 = pe.sheets.filters.OddRowFilter()
f2 = pe.sheets.filters.OddColumnFilter()
r.add_filter(f1)
r.add_filter(f2)
assert r.number_of_columns() == 2
assert r.number_of_rows() == 1
result = [6, 8]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def main(base_dir):
sheet = pe.load(os.path.join(base_dir, "tutorial_datatype_02.xls"))
print(sheet.array)
def cleanse_func(v):
v = v.replace(" ", "")
v = v.rstrip().strip()
return v
sheet.map(cleanse_func)
print(sheet.array)
def test_row_index_filter(self):
r = pe.load(self.test_tuple)
def filter_func(x):
return x in [1]
r.add_filter(pe.sheets.filters.RowIndexFilter(filter_func))
assert r.number_of_rows() == 2
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def main(base_dir):
sheet = pe.load(os.path.join(base_dir, "tutorial_datatype_02.xls"))
print(sheet.to_array())
def cleanse_func(v):
v = v.replace(" ", "")
v = v.rstrip().strip()
return v
sf = pe.SheetFormatter(cleanse_func)
sheet.add_formatter(sf)
print(sheet.to_array())
def test_column_index_filter(self):
r = pe.load(self.test_tuple)
def test_func(x):
return x in [0, 2]
r.add_filter(pe.sheets.filters.ColumnIndexFilter(test_func))
assert r.number_of_rows() == 3
assert r.number_of_columns() == 2
result = [2, 4, 6, 8, 10, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def main(base_dir):
sheet = pe.load(os.path.join(base_dir, "tutorial_datatype_02.ods"))
print(sheet.to_array())
def cleanse_func(v):
v = v.replace(" ", "")
v = v.rstrip().strip()
return v
sf = pe.SheetFormatter(cleanse_func)
sheet.add_formatter(sf)
print(sheet.to_array())
def test_remove_filter(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
f = pe.filters.OddRowFilter()
r.add_filter(f)
assert r.number_of_rows() == 1
assert r.number_of_columns() == 4
result = [5, 6, 7, 8]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
r.remove_filter(f)
result = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_pyexcel_issue_8_with_physical_file(self):
"""pyexcel issue #8
formular got lost
"""
tmp_file = "issue_8_save_as.xlsx"
s = pe.load(os.path.join("tests",
"test-fixtures",
"test8.xlsx"))
s.save_as(tmp_file)
s2 = pe.load(tmp_file)
self.assertEqual(str(s), str(s2))
content = dedent("""
CNY:
+----------+----------+------+---+-------+
| 01/09/13 | 02/09/13 | 1000 | 5 | 13.89 |
+----------+----------+------+---+-------+
| 02/09/13 | 03/09/13 | 2000 | 6 | 33.33 |
+----------+----------+------+---+-------+
| 03/09/13 | 04/09/13 | 3000 | 7 | 58.33 |
+----------+----------+------+---+-------+""").strip("\n")
self.assertEqual(str(s2), content)
os.unlink(tmp_file)
def test_row_filter(self):
r = pe.load(self.test_tuple)
r.filter(pe.filters.RowFilter([1]))
assert r.number_of_rows() == 2
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
# filter out last column and first column
r = pe.load(self.test_tuple)
r.filter(pe.filters.RowFilter([0, 2]))
assert r.number_of_rows() == 1
assert r.number_of_columns() == 4
result = [5, 6, 7, 8]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
# filter out all
r = pe.load(self.test_tuple)
r.filter(pe.filters.RowFilter([0, 1, 2]))
assert r.number_of_rows() == 0
result = []
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_row_index_filter(self):
r = pe.load(self.test_tuple)
filter_func = lambda x: x in [1]
r.add_filter(pe.filters.RowIndexFilter(filter_func))
assert r.number_of_rows() == 2
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
# test removing the filter, it prints the original one
r.clear_filters()
result = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_column_index_filter(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
test_func = lambda x: x in [0, 2]
r.add_filter(pe.filters.ColumnIndexFilter(test_func))
assert r.number_of_rows() == 3
assert r.number_of_columns() == 2
result = [2, 4, 6, 8, 10, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
# test removing the filter, it prints the original one
r.clear_filters()
result = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_column_filter(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.filters.ColumnFilter([0, 2]))
assert r.number_of_rows() == 3
assert r.number_of_columns() == 2
result = [2, 4, 6, 8, 10, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
# filter out last column and first column
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.filters.ColumnFilter([0, 3]))
assert r.number_of_rows() == 3
assert r.number_of_columns() == 2
result = [2, 3, 6, 7, 10, 11]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
# filter out all
r = pe.load((self.file_type, self.testfile.getvalue()))
r.filter(pe.filters.ColumnFilter([0, 1, 2, 3]))
assert r.number_of_columns() == 0
result = []
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def test_row_index_filter(self):
r = pe.load((self.file_type, self.testfile.getvalue()))
def filter_func(x): return x in [1]
r.add_filter(pe.filters.RowIndexFilter(filter_func))
assert r.number_of_rows() == 2
assert r.number_of_columns() == 4
result = [1, 2, 3, 4, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
# test removing the filter, it prints the original one
r.clear_filters()
result = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
actual = pe.utils.to_array(r.enumerate())
assert result == actual
def main(base_dir):
# Simple give the file name to **Reader**
# "example.xls","example.xlsx","example.ods", "example.xlsm"
spreadsheet = pe.load(os.path.join(base_dir,"example.csv"))
# row_range() gives [0 .. number of rows]
for r in spreadsheet.row_range():
# column_range() gives [0 .. number of ranges]
for c in spreadsheet.column_range():
# cell_value(row_index, column_index)
# return the value at the specified
# position
# please note that both row_index
# and column_index starts from 0
print(spreadsheet.cell_value(r, c))