def test_table_csv_delimiter():
source = '"header1";"header2"\n"value1";"value2"\n"value3";"value4"'
dialect = CsvDialect(delimiter=";")
with Table(source, scheme="text", format="csv", dialect=dialect) as table:
assert table.header == ["header1", "header2"]
assert table.read_data() == [["value1", "value2"],
["value3", "value4"]]
def test_table_csv_excel_tab():
source = "header1\theader2\nvalue1\tvalue2\nvalue3\tvalue4"
dialect = CsvDialect(delimiter="\t")
with Table(source, scheme="text", format="csv", dialect=dialect) as table:
assert table.header == ["header1", "header2"]
assert table.read_data() == [["value1", "value2"],
["value3", "value4"]]
def test_table_csv_skipinitialspace():
source = "header1, header2\nvalue1, value2\nvalue3, value4"
dialect = CsvDialect(skip_initial_space=False)
with Table(source, scheme="text", format="csv", dialect=dialect) as table:
assert table.header == ["header1", "header2"]
assert table.read_data() == [["value1", " value2"],
["value3", " value4"]]
def test_csv_parser_quotechar_is_empty_string():
source = b'header1,header2",header3\nvalue1,value2",value3'
dialect = CsvDialect(quote_char="")
with Resource(source, format="csv", dialect=dialect) as resource:
resource.header == ["header1", 'header2"', "header3"]
assert resource.read_rows() == [
{"header1": "value1", 'header2"': 'value2"', "header3": "value3"},
]
def test_csv_parser_dialect_should_not_persist_if_sniffing_fails_issue_goodtables_228():
source1 = b"a;b;c\n#comment"
source2 = b"a,b,c\n#comment"
dialect = CsvDialect(delimiter=";")
with Resource(source1, format="csv", dialect=dialect) as resource:
assert resource.header == ["a", "b", "c"]
with Resource(source2, format="csv") as resource:
assert resource.header == ["a", "b", "c"]
def test_csv_parser_delimiter():
source = b'"header1";"header2"\n"value1";"value2"\n"value3";"value4"'
dialect = CsvDialect(delimiter=";")
with Resource(source, format="csv", dialect=dialect) as resource:
assert resource.header == ["header1", "header2"]
assert resource.read_rows() == [
{"header1": "value1", "header2": "value2"},
{"header1": "value3", "header2": "value4"},
]
def test_csv_parser_escaping():
dialect = CsvDialect(escape_char="\\")
with Resource("data/escaping.csv", dialect=dialect) as resource:
assert resource.header == ["ID", "Test"]
assert resource.read_rows() == [
{"ID": 1, "Test": "Test line 1"},
{"ID": 2, "Test": 'Test " line 2'},
{"ID": 3, "Test": 'Test " line 3'},
]
def test_csv_parser_excel_tab():
source = b"header1\theader2\nvalue1\tvalue2\nvalue3\tvalue4"
dialect = CsvDialect(delimiter="\t")
with Resource(source, format="csv", dialect=dialect) as resource:
assert resource.header == ["header1", "header2"]
assert resource.read_rows() == [
{"header1": "value1", "header2": "value2"},
{"header1": "value3", "header2": "value4"},
]
def test_csv_parser_skipinitialspace():
source = b"header1, header2\nvalue1, value2\nvalue3, value4"
dialect = CsvDialect(skip_initial_space=False)
with Resource(source, format="csv", dialect=dialect) as resource:
assert resource.header == ["header1", "header2"]
assert resource.read_rows() == [
{"header1": "value1", "header2": " value2"},
{"header1": "value3", "header2": " value4"},
]
def test_csv_parser_quotechar():
source = b"%header1,header2%\n%value1,value2%\n%value3,value4%"
dialect = CsvDialect(quote_char="%")
with Resource(source, format="csv", dialect=dialect) as resource:
assert resource.header == ["header1,header2"]
assert resource.read_rows() == [
{"header1,header2": "value1,value2"},
{"header1,header2": "value3,value4"},
]
def test_csv_parser_escapechar():
source = b"header1%,header2\nvalue1%,value2\nvalue3%,value4"
dialect = CsvDialect(escape_char="%")
with Resource(source, format="csv", dialect=dialect) as resource:
assert resource.header == ["header1,header2"]
assert resource.read_rows() == [
{"header1,header2": "value1,value2"},
{"header1,header2": "value3,value4"},
]
def test_table_csv_escaping():
dialect = CsvDialect(escape_char="\\")
with Table("data/escaping.csv", dialect=dialect) as table:
assert table.header == ["ID", "Test"]
assert table.read_data() == [
["1", "Test line 1"],
["2", 'Test " line 2'],
["3", 'Test " line 3'],
]
def test_csv_parser_write_newline_crlf(tmpdir):
dialect = CsvDialect(line_terminator="\r\n")
source = Resource("data/table.csv")
target = Resource(str(tmpdir.join("table.csv")), dialect=dialect)
source.write(target)
with target:
assert target.dialect == {"lineTerminator": "\r\n"}
with open(target.fullpath, "rb") as file:
assert file.read().decode("utf-8") == "id,name\r\n1,english\r\n2,中国人\r\n"
def test_table_csv_dialect_should_not_persist_if_sniffing_fails_issue_goodtables_228(
):
source1 = "a;b;c\n#comment"
source2 = "a,b,c\n#comment"
dialect = CsvDialect(delimiter=";")
with Table(source1, scheme="text", format="csv", dialect=dialect) as table:
assert table.header == ["a", "b", "c"]
with Table(source2, scheme="text", format="csv") as table:
assert table.header == ["a", "b", "c"]
def test_describe_whitespace_cells_with_skip_initial_space_issue_7():
source = "header1,header2\n1, \n2, \n3, \n"
dialect = CsvDialect(skip_initial_space=True)
resource = describe(source, scheme="text", format="csv", dialect=dialect)
assert resource.schema == {
"fields": [
{"name": "header1", "type": "integer"},
{"name": "header2", "type": "any"},
]
}
def test_table_csv_write_delimiter(tmpdir):
source = "data/table.csv"
target = str(tmpdir.join("table.csv"))
dialect = CsvDialect(delimiter=";")
with Table(source) as table:
table.write(target, dialect=dialect)
with Table(target, dialect=dialect) as table:
assert table.header == ["id", "name"]
assert table.read_data() == [["1", "english"], ["2", "中国人"]]
assert table.dialect == {"delimiter": ";"}
def test_csv_parser_write_delimiter(tmpdir):
dialect = CsvDialect(delimiter=";")
source = Resource("data/table.csv")
target = Resource(str(tmpdir.join("table.csv")), dialect=dialect)
source.write(target)
with target:
assert target.header == ["id", "name"]
assert target.dialect == {"delimiter": ";"}
assert target.read_rows() == [
{"id": 1, "name": "english"},
{"id": 2, "name": "中国人"},
]
def test_table_csv_quotechar_is_empty_string():
source = 'header1,header2",header3\nvalue1,value2",value3'
dialect = CsvDialect(quote_char="")
with Table(source, scheme="text", format="csv", dialect=dialect) as table:
table.header == ["header1", 'header2"', "header3"]
table.read_data() == [["value1", 'value2"', "value3"]]
def test_table_csv_escapechar():
source = "header1%,header2\nvalue1%,value2\nvalue3%,value4"
dialect = CsvDialect(escape_char="%")
with Table(source, scheme="text", format="csv", dialect=dialect) as table:
assert table.header == ["header1,header2"]
assert table.read_data() == [["value1,value2"], ["value3,value4"]]
def test_table_csv_quotechar():
source = "%header1,header2%\n%value1,value2%\n%value3,value4%"
dialect = CsvDialect(quote_char="%")
with Table(source, scheme="text", format="csv", dialect=dialect) as table:
assert table.header == ["header1,header2"]
assert table.read_data() == [["value1,value2"], ["value3,value4"]]