def test_validate():
report = validate("data/schema.json")
assert report.valid
def test_validate_duplicate_headers():
report = validate("data/duplicate-headers.csv")
assert report.flatten(["rowPosition", "fieldPosition", "code"]) == [
[None, 3, "duplicate-header"],
[None, 5, "duplicate-header"],
]
def test_validate_skip_rows_and_fields():
query = Query(skip_rows=[2, "41"], skip_fields=[1, "f4"])
report = validate("data/matrix.csv", query=query)
assert report.table["header"] == ["f2", "f3"]
assert report.table.stats["rows"] == 2
assert report.table.valid
def test_validate_offset_fields():
query = Query(offset_fields=3)
report = validate("data/matrix.csv", query=query)
assert report.table["header"] == ["f4"]
assert report.table.stats["rows"] == 4
assert report.table.valid
def test_validate_pick_rows():
query = Query(pick_rows=[1, 3, "31"])
report = validate("data/matrix.csv", query=query)
assert report.table["header"] == ["f1", "f2", "f3", "f4"]
assert report.table.stats["rows"] == 2
assert report.table.valid
def test_validate_dialect_delimiter():
report = validate("data/delimiter.csv", dialect={"delimiter": ";"})
assert report.valid
assert report.table.stats["rows"] == 2
def test_validate_blank_headers():
report = validate("data/blank-headers.csv")
assert report.flatten(["rowPosition", "fieldPosition", "code"]) == [
[None, 2, "blank-header"],
]
def test_validate_headers_none():
report = validate("data/without-headers.csv", headers=False)
assert report.valid
assert report.table.stats["rows"] == 3
assert report.table["dialect"]["header"] is False
assert report.table["header"] == []
def test_validate_inline_not_a_binary_issue_349():
with open("data/table.csv") as source:
report = validate(source)
assert report.flatten(["code", "note"]) == [
["scheme-error", "only byte streams are supported"],
]
def test_validate_infer_fields_issue_223():
source = [["name1", "name2"], ["123", "abc"], ["456", "def"],
["789", "ghi"]]
patch_schema = {"fields": {"name": {"type": "string"}}}
report = validate(source, patch_schema=patch_schema)
assert report.valid
def test_validate_fails_with_wrong_encoding_issue_274():
# For now, by default encoding is detected incorectly by chardet
report = validate("data/encoding-issue-274.csv", encoding="utf-8")
assert report.valid
def test_validate_source_pathlib_path_table():
report = validate(pathlib.Path("data/table.csv"))
assert report.valid
def test_validate_source_invalid():
# Reducing sample size to get raise on iter, not on open
report = validate([["h"], [1], "bad"], infer_volume=1)
assert report.flatten(["rowPosition", "fieldPosition", "code"]) == [
[None, None, "source-error"],
]
def test_validate():
report = validate("data/table.csv")
assert report.valid
def test_validate_compression_explicit():
report = validate("data/table.csv.zip", compression="zip")
assert report.valid
def test_validate_headers_number():
report = validate("data/matrix.csv", headers=2)
assert report.table["header"] == ["11", "12", "13", "14"]
assert report.valid
def test_validate_compression_invalid():
report = validate("data/table.csv.zip", compression="bad")
assert report.flatten(["code", "note"]) == [
["compression-error", 'compression "bad" is not supported'],
]
def test_validate_headers_list_of_numbers():
report = validate("data/matrix.csv", headers=[2, 3, 4])
assert report.table["header"] == [
"11 21 31", "12 22 32", "13 23 33", "14 24 34"
]
assert report.valid
def test_validate_pick_fields():
query = Query(pick_fields=[2, "f3"])
report = validate("data/matrix.csv", query=query)
assert report.table["header"] == ["f2", "f3"]
assert report.table.stats["rows"] == 4
assert report.table.valid
def test_validate_headers_list_of_numbers_and_headers_join():
report = validate("data/matrix.csv", headers=[[2, 3, 4], "."])
assert report.table["header"] == [
"11.21.31", "12.22.32", "13.23.33", "14.24.34"
]
assert report.valid
def test_validate_skip_fields_regex():
query = Query(skip_fields=["<regex>f[14]"])
report = validate("data/matrix.csv", query=query)
assert report.table["header"] == ["f2", "f3"]
assert report.table.stats["rows"] == 4
assert report.table.valid
def test_validate_scheme():
report = validate("data/table.csv", scheme="file")
assert report.valid
def test_validate_limit_and_offset_fields():
query = Query(limit_fields=2, offset_fields=1)
report = validate("data/matrix.csv", query=query)
assert report.table["header"] == ["f2", "f3"]
assert report.table.stats["rows"] == 4
assert report.table.valid
def test_validate_format():
report = validate("data/table.csv", format="csv")
assert report.valid
def test_validate_skip_rows_regex():
query = Query(skip_rows=["<regex>[14]1"])
report = validate("data/matrix.csv", query=query)
assert report.table["header"] == ["f1", "f2", "f3", "f4"]
assert report.table.stats["rows"] == 2
assert report.table.valid
def test_validate_encoding():
report = validate("data/table.csv", encoding="utf-8")
assert report.valid
def test_validate_skip_rows_blank():
query = Query(skip_rows=["<blank>"])
report = validate("data/blank-rows.csv", query=query)
assert report.table["header"] == ["id", "name", "age"]
assert report.table.stats["rows"] == 2
assert report.table.valid
def test_validate_compression():
report = validate("data/table.csv.zip")
assert report.valid
def test_validate_limit_rows():
query = Query(limit_rows=1)
report = validate("data/matrix.csv", query=query)
assert report.table["header"] == ["f1", "f2", "f3", "f4"]
assert report.table.stats["rows"] == 1
assert report.table.valid
def test_validate_duplicate_row():
report = validate("data/duplicate-rows.csv", checks=[checks.duplicate_row()])
assert report.flatten(["rowPosition", "fieldPosition", "code"]) == [
[4, None, "duplicate-row"],
]
