def test_normal_json(self, url, format_name):
responses.add(
responses.GET,
url,
body=dedent(
"""\
[
{"attr_a": 1},
{"attr_b": 2.1, "attr_c": "bb"}
]"""
),
content_type="text/plain; charset=utf-8",
status=200,
)
expected_list = [
TableData(
"url_loader",
["attr_a", "attr_b", "attr_c"],
[{"attr_a": 1}, {"attr_b": 2.1, "attr_c": "bb"}],
)
]
loader = ptr.TableUrlLoader(url, format_name)
assert loader.format_name == "json"
loader.table_name = "url_loader"
for table_data in loader.load():
print("{} {}".format(table_data, dumps_tabledata(table_data)))
print(table_data.rows)
print("[expected]")
for expected in expected_list:
print(dumps_tabledata(expected))
assert table_data.in_tabledata_list(expected_list)
def io_test():
# prepare data ---
file_path = "sample_data.csv"
csv_text = "\n".join([
'"attr_a","attr_b","attr_c"',
'1,4,"a"',
'2,2.1,"bb"',
'3,120.9,"ccc"',
])
with open(file_path, "w") as f:
f.write(csv_text)
# load from a csv text ---
loader = ptr.CsvTableTextLoader(csv_text)
for table_data in loader.load():
print("\n".join([
"load from text",
"==============",
"{:s}".format(ptw.dumps_tabledata(table_data)),
]))
# load from a csv file ---
loader = ptr.CsvTableFileLoader(file_path)
for table_data in loader.load():
print("\n".join([
"load from file",
"==============",
"{:s}".format(ptw.dumps_tabledata(modify(table_data))),
]))
def test_normal_json(self):
text = dedent(
"""\
[
{"attr_a": 1},
{"attr_b": 2.1, "attr_c": "bb"}
]"""
)
expected_list = [
TableData(
"json1",
["attr_a", "attr_b", "attr_c"],
[{"attr_a": 1}, {"attr_b": 2.1, "attr_c": "bb"}],
)
]
loader = ptr.TableTextLoader(text, format_name="json")
assert loader.format_name == "json"
for table_data, expected in zip(loader.load(), expected_list):
print(dumps_tabledata(expected))
print(dumps_tabledata(table_data))
assert table_data.equals(expected)
def test_normal_csv(self, tmpdir, file_path, format_name):
filename = pv.replace_symbol(file_path, "")
p_file_path = Path(
six.text_type(tmpdir.join(filename + Path(file_path).ext)))
p_file_path.parent.makedirs_p()
with open(p_file_path, "w") as f:
f.write(
dedent("""\
"attr_a","attr_b","attr_c"
1,4,"a"
2,2.1,"bb"
3,120.9,"ccc"
"""))
expeced_list = [
TableData(
filename,
["attr_a", "attr_b", "attr_c"],
[[1, 4, "a"], [2, "2.1", "bb"], [3, "120.9", "ccc"]],
)
]
loader = ptr.TableFileLoader(p_file_path, format_name=format_name)
assert loader.format_name == "csv"
for tabledata, expected in zip(loader.load(), expeced_list):
print(dumps_tabledata(expected))
print(dumps_tabledata(tabledata))
assert tabledata.equals(expected)
def test_normal_csv(self):
text = dedent(
"""\
"attr_a","attr_b","attr_c"
1,4,"a"
2,2.1,"bb"
3,120.9,"ccc"
"""
)
expected_list = [
TableData(
"csv1",
["attr_a", "attr_b", "attr_c"],
[[1, 4, "a"], [2, "2.1", "bb"], [3, "120.9", "ccc"]],
)
]
loader = ptr.TableTextLoader(text, format_name="csv")
assert loader.format_name == "csv"
for tabledata, expected in zip(loader.load(), expected_list):
print(dumps_tabledata(expected))
print(dumps_tabledata(tabledata))
assert tabledata.equals(expected)
def test_normal(self, table_text, table_name, expected):
loader = ptr.LtsvTableTextLoader(table_text)
loader.table_name = table_name
for tabledata in loader.load():
print("[expected]: {}".format(dumps_tabledata(expected)))
print("[actual]: {}".format(dumps_tabledata(tabledata)))
assert tabledata.equals(expected)
def test_normal(self, provider_list, rows, table_name, expected):
faker = TableFaker(seed=1)
out = faker.generate(provider_list, rows, table_name=table_name)
out_table = dumps_tabledata(out, **dump_opts)
expected_table = dumps_tabledata(expected, **dump_opts)
print_test_result(expected=expected_table, actual=out_table)
assert expected_table == out_table
assert out == expected
def test_normal(self, table_text, table_name, headers, expected):
loader = ptr.TsvTableTextLoader(table_text)
loader.table_name = table_name
loader.headers = headers
for tabledata in loader.load():
print(dumps_tabledata(tabledata))
for e in expected:
print(dumps_tabledata(e))
assert tabledata.in_tabledata_list(expected)
def test_normal_(self, table_name, headers, dup_col_handler, expected):
new_tabledata = SQLiteTableDataSanitizer(
TableData(table_name, headers, []),
dup_col_handler=dup_col_handler).normalize()
try:
from pytablewriter import dumps_tabledata
print_test_result(expected=dumps_tabledata(expected),
actual=dumps_tabledata(new_tabledata))
except ImportError:
pass
assert new_tabledata.equals(expected)
def test_normal(self, tmpdir, test_id, table_text, filename, expected):
file_path = Path(str(tmpdir.join(filename)))
file_path.parent.makedirs_p()
with io.open(file_path, "w", encoding="utf-8") as f:
f.write(table_text)
loader = ptr.LtsvTableFileLoader(file_path)
for tabledata in loader.load():
print("test-id={}".format(test_id))
print("[expected]\n{}".format(dumps_tabledata(expected)))
print("[actual]\n{}".format(dumps_tabledata(tabledata)))
assert tabledata.equals(expected)
def test_normal_specify_header_list(self):
faker = TableFaker(seed=1)
provider_list = ("file_name", "file_path")
out = faker.generate(provider_list,
1,
table_name="with headers",
headers=("input", "output"))
expected = TableData("with headers", ("input", "output"),
[("shake.wav", "/prepare/last.jpeg")])
out_table = dumps_tabledata(out, **dump_opts)
expected_table = dumps_tabledata(expected, **dump_opts)
print_test_result(expected=expected_table, actual=out_table)
assert expected_table == out_table
assert out == expected
def test_normal_excel(self, tmpdir):
file_path = "/tmp/valid/test/data/validdata.xlsx"
p_file_path = Path(str(tmpdir.join(file_path)))
p_file_path.parent.makedirs_p()
tabledata_list = [
TableData(
"testsheet1",
["a1", "b1", "c1"],
[["aa1", "ab1", "ac1"], [1.0, 1.1, "a"], [2.0, 2.2, "bb"],
[3.0, 3.3, 'cc"dd"']],
),
TableData(
"testsheet3",
["a3", "b3", "c3"],
[["aa3", "ab3", "ac3"], [4.0, 1.1, "a"], [5.0, "", "bb"],
[6.0, 3.3, ""]],
),
]
writer = ExcelXlsxTableWriter()
writer.open(p_file_path)
for tabledata in tabledata_list:
writer.from_tabledata(tabledata)
writer.write_table()
writer.close()
loader = ptr.TableFileLoader(p_file_path)
assert loader.format_name == "excel"
for tabledata in loader.load():
print(dumps_tabledata(tabledata))
assert tabledata in tabledata_list
def test_normal(self, table_text, table_name, expected_tabletuple_list):
self.LOADER_CLASS.clear_table_count()
loader = self.LOADER_CLASS(table_text)
loader.table_name = table_name
load = False
for tabledata in loader.load():
print("[actual]\n{}".format(dumps_tabledata(tabledata)))
print("[expected]")
for expected in expected_tabletuple_list:
print("{}".format(dumps_tabledata(tabledata)))
assert tabledata.in_tabledata_list(expected_tabletuple_list)
load = True
assert load
def test_normal(self, table_text, table_name, expected_tabletuple_list):
loader = self.LOADER_CLASS(table_text)
loader.table_name = table_name
for table_data in loader.load():
print("[actual]\n{}".format(dumps_tabledata(table_data)))
assert table_data.in_tabledata_list(expected_tabletuple_list)
def test_normal(self, valid_excel_file_path, table_name, start_row, expected_list):
loader = ptr.ExcelTableFileLoader(valid_excel_file_path)
loader.table_name = table_name
loader.start_row = start_row
for table_data in loader.load():
print("[actual]\n{}".format(dumps_tabledata(table_data)))
assert table_data.in_tabledata_list(expected_list)
def test_normal_ssv(self):
text = dedent(
"""\
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 1 0.0 0.4 77664 8784 ? Ss May11 0:02 /sbin/init
root 2 0.0 0.0 0 0 ? S May11 0:00 [kthreadd]
root 4 0.0 0.0 0 0 ? I< May11 0:00 [kworker/0:0H]
root 6 0.0 0.0 0 0 ? I< May11 0:00 [mm_percpu_wq]
root 7 0.0 0.0 0 0 ? S May11 0:01 [ksoftirqd/0]
"""
)
expected_list = [
TableData(
"csv1",
[
"USER",
"PID",
"%CPU",
"%MEM",
"VSZ",
"RSS",
"TTY",
"STAT",
"START",
"TIME",
"COMMAND",
],
[
["root", 1, 0, 0.4, 77664, 8784, "?", "Ss", "May11", "0:02", "/sbin/init"],
["root", 2, 0, 0, 0, 0, "?", "S", "May11", "0:00", "[kthreadd]"],
["root", 4, 0, 0, 0, 0, "?", "I<", "May11", "0:00", "[kworker/0:0H]"],
["root", 6, 0, 0, 0, 0, "?", "I<", "May11", "0:00", "[mm_percpu_wq]"],
["root", 7, 0, 0, 0, 0, "?", "S", "May11", "0:01", "[ksoftirqd/0]"],
],
)
]
loader = ptr.TableTextLoader(text, format_name="ssv")
assert loader.format_name == "csv"
for tabledata, expected in zip(loader.load(), expected_list):
print(dumps_tabledata(expected))
print(dumps_tabledata(tabledata))
assert tabledata.equals(expected)
def test_normal_locale(self):
faker = TableFaker(locale="ja_JP", seed=1)
out = faker.generate(("name", "address"), rows=2)
expected = TableData(
None,
("name", "address"),
[("山岸 裕樹", "三重県荒川区明石町14丁目4番16号"),
("村山 拓真", "北海道荒川区白金台15丁目19番4号 コート所野806")],
)
out_table = dumps_tabledata(out, **dump_opts)
expected_table = dumps_tabledata(expected, **dump_opts)
print_test_result(expected=expected_table, actual=out_table)
assert expected_table == out_table
assert out == expected
assert out != faker.generate(("name", "address"), rows=2)
def test_normal(self, table_name, headers, records, expected):
new_tabledata = SQLiteTableDataSanitizer(
TableData(table_name, headers, records)).normalize()
try:
from pytablewriter import dumps_tabledata
print_test_result(expected=dumps_tabledata(expected),
actual=dumps_tabledata(new_tabledata))
except ImportError:
pass
con = connect_memdb()
con.create_table_from_tabledata(new_tabledata)
assert con.select_as_tabledata(new_tabledata.table_name) == expected
assert new_tabledata.equals(expected)
def test_normal(self, tmpdir, table, header, value, expected):
test_file_path = tmpdir.join("test.sqlite")
writer = ptw.SqliteTableWriter()
writer.open(str(test_file_path))
writer.table_name = table
writer.headers = header
writer.value_matrix = value
writer.write_table()
writer.close()
for table_data in SqliteFileLoader(str(test_file_path)).load():
expected_dump = ptw.dumps_tabledata(expected)
actual_dump = ptw.dumps_tabledata(table_data)
print_test_result(expected=expected_dump, actual=actual_dump)
assert actual_dump == expected_dump
def test_normal(self, tmpdir, table, header, value, expected):
test_file_path = tmpdir.join("test.sqlite")
writer = ptw.SqliteTableWriter()
writer.open(str(test_file_path))
writer.table_name = table
writer.headers = header
writer.value_matrix = value
writer.write_table()
writer.close()
for table_data in SqliteFileLoader(str(test_file_path)).load():
expected_dump = ptw.dumps_tabledata(expected)
actual_dump = ptw.dumps_tabledata(table_data)
print_test_result(expected=expected_dump, actual=actual_dump)
assert actual_dump == expected_dump
def test_normal(self, tmpdir, writer_class, table, header, value, expected):
if writer_class == ptw.ExcelXlsTableWriter and not HAS_XLWT:
pytest.skip()
test_file_path = tmpdir.join("test.xlsx")
writer = writer_class()
writer.open(str(test_file_path))
writer.make_worksheet(table)
writer.headers = header
writer.value_matrix = value
writer.write_table()
writer.close()
for table_data in ExcelTableFileLoader(str(test_file_path)).load():
expected_dump = ptw.dumps_tabledata(expected)
actual_dump = ptw.dumps_tabledata(table_data)
print_test_result(expected=expected_dump, actual=actual_dump)
assert actual_dump == expected_dump
def test_normal(self, tmpdir, table, header, value, expected):
test_filepath = tmpdir.join("test1.pkl")
writer = ptw.PandasDataFramePickleWriter(
table_name=table,
headers=header,
value_matrix=value,
)
writer.open(str(test_filepath))
writer.write_table()
print(expected, file=sys.stderr)
actual = ptw.PandasDataFramePickleWriter()
actual.from_dataframe(pd.read_pickle(test_filepath))
actual.table_name = expected.table_name
print_test_result(expected=ptw.dumps_tabledata(expected),
actual=ptw.dumps_tabledata(actual.tabledata))
assert ptw.dumps_tabledata(
actual.tabledata) == ptw.dumps_tabledata(expected)
def test_normal(self, table_text, table_name, expected_tabletuple_list):
ptr.JsonTableFileLoader.clear_table_count()
loader = ptr.JsonTableTextLoader(table_text)
loader.table_name = table_name
load = False
for tabledata in loader.load():
print("[actual]\n{}".format(dumps_tabledata(tabledata)))
assert tabledata.in_tabledata_list(expected_tabletuple_list)
load = True
assert load
def test_normal_fifo(self, tmpdir, table_text, fifo_name, expected):
namedpipe = str(tmpdir.join(fifo_name))
os.mkfifo(namedpipe)
loader = ptr.CsvTableFileLoader(namedpipe)
with ProcessPoolExecutor() as executor:
executor.submit(fifo_writer, namedpipe, table_text)
for tabledata in loader.load():
print(dumps_tabledata(tabledata))
assert tabledata.in_tabledata_list(expected)
def test_normal_fifo(self, tmpdir, table_text, fifo_name, expected):
namedpipe = str(tmpdir.join(fifo_name))
os.mkfifo(namedpipe)
loader = self.LOADER_CLASS(namedpipe)
with ProcessPoolExecutor() as executor:
executor.submit(fifo_writer, namedpipe, table_text)
for tabledata in loader.load():
print("[actual]\n{}".format(dumps_tabledata(tabledata)))
assert tabledata.in_tabledata_list(expected)
def test_smoke(self, tmpdir, filename):
test_data_file_path = os.path.join(os.path.dirname(__file__), "data", filename)
loader = ptr.TableFileLoader(test_data_file_path)
success_count = 0
for tabledata in loader.load():
if tabledata.is_empty():
continue
assert len(dumps_tabledata(tabledata)) > 10
success_count += 1
assert success_count > 0
def test_normal(self, tmpdir, test_id, table_text, filename, table_name,
expected_tabledata_list):
file_path = Path(str(tmpdir.join(filename)))
file_path.parent.makedirs_p()
with io.open(file_path, "w", encoding="utf-8") as f:
f.write(table_text)
loader = ptr.HtmlTableFileLoader(file_path)
loader.table_name = table_name
for table_data in loader.load():
print("--- test {} ---".format(test_id))
print("[actual]\n{}\n".format(dumps_tabledata(table_data)))
assert table_data.in_tabledata_list(expected_tabledata_list)
def test_normal(self, tmpdir, test_id, tabledata, filename, headers, expected):
file_path = Path(str(tmpdir.join(filename)))
file_path.parent.makedirs_p()
con = SimpleSQLite(file_path, "w")
con.create_table_from_tabledata(tabledata)
loader = ptr.SqliteFileLoader(file_path)
loader.headers = headers
for tabledata in loader.load():
print("test-id={}".format(test_id))
print(dumps_tabledata(tabledata))
assert tabledata.in_tabledata_list(expected)
def test_normal(self, tmpdir, test_id, table_text, filename, headers,
expected):
file_path = Path(str(tmpdir.join(filename)))
file_path.parent.makedirs_p()
with open(file_path, "w", encoding="utf-8") as f:
f.write(table_text)
loader = ptr.TsvTableFileLoader(file_path)
loader.headers = headers
for tabledata in loader.load():
print("test-id={}".format(test_id))
print(dumps_tabledata(tabledata))
assert tabledata.in_tabledata_list(expected)
def test_normal(self, tmpdir, table_text, filename, table_name,
expected_tabletuple_list):
file_path = Path(str(tmpdir.join(filename)))
file_path.parent.makedirs_p()
with open(file_path, "w") as f:
f.write(table_text)
loader = ptr.JsonTableFileLoader(file_path)
load = False
for tabledata in loader.load():
print("[actual]\n{}".format(dumps_tabledata(tabledata)))
assert tabledata.in_tabledata_list(expected_tabletuple_list)
load = True
assert load
def test_smoke(self, tmpdir, filename):
try:
import pytablereader as ptr
except ImportError:
pytest.skip("requires pytablereader")
p = tmpdir.join("tmp.db")
con = SimpleSQLite(str(p), "w")
test_data_file_path = os.path.join(os.path.dirname(__file__), "data",
filename)
loader = ptr.TableFileLoader(test_data_file_path)
success_count = 0
for table_data in loader.load():
if table_data.is_empty():
continue
try:
from pytablewriter import dumps_tabledata
print(dumps_tabledata(table_data))
except ImportError:
pass
try:
con.create_table_from_tabledata(
SQLiteTableDataSanitizer(table_data).normalize())
success_count += 1
except ValueError as e:
print(e)
con.commit()
assert success_count > 0
def test_normal_format_name(self, value, format_name, expected):
out = dumps_tabledata(value, format_name=format_name)
print_test_result(expected=expected, actual=out)
assert out == expected
def test_normal_kwargs(self, value, kwargs, expected):
out = dumps_tabledata(value, **kwargs)
print_test_result(expected=expected, actual=out)
assert out == expected
def test_exception(self, value, expected):
with pytest.raises(expected):
dumps_tabledata(value)
