def test_resource_write(tmpdir):
path1 = "data/table.csv"
path2 = str(tmpdir.join("table.csv"))
source = Resource(path=path1)
source.write(path2)
target = Resource(path=path2, trusted=True)
assert target.read_header() == ["id", "name"]
assert target.read_rows() == [
{
"id": 1,
"name": "english"
},
{
"id": 2,
"name": "中国人"
},
]
def test_xls_parser_sheet_by_index():
source = "data/sheet2.xls"
dialect = ExcelDialect(sheet=2)
with Resource(source, dialect=dialect) as resource:
assert resource.header == ["id", "name"]
assert resource.read_rows() == [
{
"id": 1,
"name": "english"
},
{
"id": 2,
"name": "中国人"
},
]
def test_resource_expand_with_dialect():
dialect = {"delimiter": "custom"}
resource = Resource({
"name": "name",
"path": "data/table.csv",
"dialect": dialect
})
resource.expand()
assert resource == {
"name": "name",
"path": "data/table.csv",
"profile": "data-resource",
"dialect": {
"header": True,
"headerRows": [1],
"headerJoin": " ",
"headerCase": True,
"delimiter": "custom",
"lineTerminator": "\r\n",
"doubleQuote": True,
"quoteChar": '"',
"skipInitialSpace": False,
},
}
def test_step_field_add_with_formula():
source = Resource(path="data/transform.csv")
target = transform(
source,
steps=[
steps.table_normalize(),
steps.field_add(name="calc", formula="id * 100 + population"),
],
)
assert target.schema == {
"fields": [
{
"name": "id",
"type": "integer"
},
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
{
"name": "calc"
},
]
}
assert target.read_rows() == [
{
"id": 1,
"name": "germany",
"population": 83,
"calc": 183
},
{
"id": 2,
"name": "france",
"population": 66,
"calc": 266
},
{
"id": 3,
"name": "spain",
"population": 47,
"calc": 347
},
]
def test_step_field_add():
source = Resource(path="data/transform.csv")
target = transform(
source,
steps=[
steps.field_add(name="note", type="string", value="eu"),
],
)
assert target.schema == {
"fields": [
{
"name": "id",
"type": "integer"
},
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
{
"name": "note",
"type": "string"
},
]
}
assert target.read_rows() == [
{
"id": 1,
"name": "germany",
"population": 83,
"note": "eu"
},
{
"id": 2,
"name": "france",
"population": 66,
"note": "eu"
},
{
"id": 3,
"name": "spain",
"population": 47,
"note": "eu"
},
]
def test_step_row_ungroup_last():
source = Resource("data/transform-groups.csv")
target = transform(
source,
steps=[
steps.row_ungroup(group_name="name", selection="last"),
],
)
assert target.schema == {
"fields": [
{
"name": "id",
"type": "integer"
},
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
{
"name": "year",
"type": "integer"
},
]
}
assert target.read_rows() == [
{
"id": 4,
"name": "france",
"population": 54,
"year": 1920
},
{
"id": 2,
"name": "germany",
"population": 77,
"year": 1920
},
{
"id": 6,
"name": "spain",
"population": 33,
"year": 1920
},
]
def test_resource_source_non_tabular_remote():
path = BASEURL % "data/text.txt"
with Resource(path) as resource:
assert resource.path == path
assert resource.data is None
assert resource.memory is False
assert resource.tabular is False
assert resource.multipart is False
assert resource.basepath == ""
assert resource.fullpath == path
if IS_UNIX:
assert resource.read_bytes() == b"text\n"
assert resource.stats == {
"hash": "e1cbb0c3879af8347246f12c559a86b5",
"bytes": 5,
}
def test_resource_relative_parent_path_with_trusted_option_issue_171():
# trusted=false (default)
resource = Resource(path="data/../data/table.csv")
with pytest.raises(exceptions.FrictionlessException) as excinfo:
resource.read_rows()
error = excinfo.value.error
assert error.code == "resource-error"
assert error.note.count("data/table.csv")
# trusted=true
resource = Resource(path="data/../data/table.csv", trusted=True)
assert resource.read_rows() == [
{"id": 1, "name": "english"},
{"id": 2, "name": "中国人"},
]
def test_resource_to_zip(tmpdir):
# Write
target = os.path.join(tmpdir, "dataresource.zip")
resource = Resource("data/resource.json")
resource.to_zip(target)
# Read
resource = Resource(target)
assert resource == {"name": "name", "path": "table.csv"}
assert resource.read_rows() == [
{"id": 1, "name": "english"},
{"id": 2, "name": "中国人"},
]
def test_xlsx_parser_preserve_formatting_number_multicode():
source = "data/number-format-multicode.xlsx"
dialect = ExcelDialect(preserve_formatting=True)
layout = Layout(skip_fields=["<blank>"])
with Resource(source, dialect=dialect, layout=layout) as resource:
assert resource.read_rows() == [
{
"col1": Decimal("4.5")
},
{
"col1": Decimal("-9.032")
},
{
"col1": Decimal("15.8")
},
]
def test_type_custom(custom_plugin):
schema = Schema(fields=[
Field(name="integer", type="integer"),
Field(name="custom", type="custom"),
])
with Resource(path="data/table.csv", schema=schema) as resource:
assert resource.read_rows() == [
{
"integer": 1,
"custom": ["english"]
},
{
"integer": 2,
"custom": ["中国人"]
},
]
def test_csv_parser_excel_tab():
source = "header1\theader2\nvalue1\tvalue2\nvalue3\tvalue4"
dialect = CsvDialect(delimiter="\t")
with Resource(source, scheme="text", 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 = "header1, header2\nvalue1, value2\nvalue3, value4"
dialect = CsvDialect(skip_initial_space=False)
with Resource(source, scheme="text", 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_delimiter():
source = '"header1";"header2"\n"value1";"value2"\n"value3";"value4"'
dialect = CsvDialect(delimiter=";")
with Resource(source, scheme="text", 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_inline_parser_keyed_with_keys_provided():
source = [{"id": "1", "name": "english"}, {"id": "2", "name": "中国人"}]
dialect = InlineDialect(keys=["name", "id"])
with Resource(source, format="inline", dialect=dialect) as resource:
assert resource.dialect.keyed is True
assert resource.header == ["name", "id"]
assert resource.read_rows() == [
{
"id": 1,
"name": "english"
},
{
"id": 2,
"name": "中国人"
},
]
def test_json_parser_from_buffer_keyed():
source = '[{"id": 1, "name": "english" }, {"id": 2, "name": "中国人" }]'.encode(
"utf-8")
with Resource(source, format="json") as resource:
assert resource.dialect.keyed is True
assert resource.header == ["id", "name"]
assert resource.read_rows() == [
{
"id": 1,
"name": "english"
},
{
"id": 2,
"name": "中国人"
},
]
def test_resource_layout_header_csv_multiline_headers_duplicates():
source = b"k1\nk1\nv1\nv2\nv3"
layout = Layout(header_rows=[1, 2])
with Resource(source, format="csv", layout=layout) as resource:
assert resource.header == ["k1"]
assert resource.read_rows() == [
{
"k1": "v1"
},
{
"k1": "v2"
},
{
"k1": "v3"
},
]
def test_step_row_subset_conflicts():
source = Resource("data/transform.csv")
target = transform(
source,
steps=[
steps.row_subset(subset="conflicts", field_name="id"),
],
)
assert target.schema == {
"fields": [
{"name": "id", "type": "integer"},
{"name": "name", "type": "string"},
{"name": "population", "type": "integer"},
]
}
assert target.read_rows() == []
def test_resource_official_hash_bytes_rows_with_hashing_algorithm():
resource = Resource({
"path": "path",
"hash": "sha256:hash",
"bytes": 1,
"rows": 1
})
assert resource == {
"path": "path",
"hashing": "sha256",
"stats": {
"hash": "hash",
"bytes": 1,
"rows": 1,
},
}
def test_resource_open_without_rows():
with Resource("data/without-rows.csv") as resource:
assert resource.header == ["id", "name"]
assert resource.read_rows() == []
assert resource.schema == {
"fields": [
{
"name": "id",
"type": "any"
},
{
"name": "name",
"type": "any"
},
]
}
def test_step_row_subset_conflicts_from_descriptor_issue_996():
source = Resource("data/transform.csv")
target = transform(
source,
steps=[
steps.row_subset({"subset": "conflicts", "fieldName": "id"}),
],
)
assert target.schema == {
"fields": [
{"name": "id", "type": "integer"},
{"name": "name", "type": "string"},
{"name": "population", "type": "integer"},
]
}
assert target.read_rows() == []
def test_step_field_unpack():
source = Resource(path="data/transform.csv")
target = transform(
source,
steps=[
steps.field_update(name="id", type="array", value=[1, 1]),
steps.field_unpack(name="id", to_names=["id2", "id3"]),
],
)
assert target.schema == {
"fields": [
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
{
"name": "id2"
},
{
"name": "id3"
},
]
}
assert target.read_rows() == [
{
"name": "germany",
"population": 83,
"id2": 1,
"id3": 1
},
{
"name": "france",
"population": 66,
"id2": 1,
"id3": 1
},
{
"name": "spain",
"population": 47,
"id2": 1,
"id3": 1
},
]
def test_step_field_add_with_incremental():
source = Resource(path="data/transform.csv")
target = transform(
source,
steps=[
steps.field_add(name="number", incremental=True),
],
)
assert target.schema == {
"fields": [
{
"name": "number"
},
{
"name": "id",
"type": "integer"
},
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
]
}
assert target.read_rows() == [
{
"number": 1,
"id": 1,
"name": "germany",
"population": 83
},
{
"number": 2,
"id": 2,
"name": "france",
"population": 66
},
{
"number": 3,
"id": 3,
"name": "spain",
"population": 47
},
]
def test_csv_parser_detect_delimiter_tab():
source = "a1\tb1\tc1A,c1B\na2\tb2\tc2\n"
layout = Layout(header=False)
with Resource(source, scheme="text", format="csv",
layout=layout) as resource:
assert resource.read_rows() == [
{
"field1": "a1",
"field2": "b1",
"field3": "c1A,c1B"
},
{
"field1": "a2",
"field2": "b2",
"field3": "c2"
},
]
def test_resource_schema_from_path_remote():
resource = Resource(BASE_URL % "data/resource-with-dereferencing.json")
assert resource == {
"name": "name",
"path": "table.csv",
"dialect": "dialect.json",
"schema": "schema-simple.json",
}
assert resource.schema == {
"fields": [{
"name": "id",
"type": "integer"
}, {
"name": "name",
"type": "string"
}]
}
def test_resource_schema_unique_error():
source = [["name"], [1], [2], [2]]
detector = Detector(
schema_patch={"fields": {
"name": {
"constraints": {
"unique": True
}
}
}})
with Resource(source, detector=detector) as resource:
for row in resource:
if row.row_number == 3:
assert row.valid is False
assert row.errors[0].code == "unique-error"
continue
assert row.valid
def test_step_table_join_from_dict():
source = Resource("data/transform.csv")
target = transform(
source,
steps=[
steps.table_normalize(),
steps.table_join(
resource=dict(data=[["id", "note"], [1, "beer"], [2, "vine"]]),
field_name="id",
),
],
)
assert target.schema == {
"fields": [
{
"name": "id",
"type": "integer"
},
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
{
"name": "note",
"type": "string"
},
]
}
assert target.read_rows() == [
{
"id": 1,
"name": "germany",
"population": 83,
"note": "beer"
},
{
"id": 2,
"name": "france",
"population": 66,
"note": "vine"
},
]
def test_resource_to_zip_source_remote(tmpdir):
# Write
path = BASE_URL % "data/table.csv"
target = os.path.join(tmpdir, "datapackage.zip")
resource = Resource(name="name", path=path)
resource.to_zip(target)
# Read
resource = Resource(target)
assert resource == {"name": "name", "path": path}
assert resource.read_rows() == [
{"id": 1, "name": "english"},
{"id": 2, "name": "中国人"},
]
def test_resource_to_zip_source_inline(tmpdir):
# Write
target = os.path.join(tmpdir, "dataresource.zip")
data = [["id", "name"], ["1", "english"], ["2", "中国人"]]
resource = Resource(name="name", data=data)
resource.to_zip(target)
# Read
resource = Resource(target)
assert resource == {"name": "name", "data": data}
assert resource.read_rows() == [
{"id": 1, "name": "english"},
{"id": 2, "name": "中国人"},
]
def test_step_row_subset_unique_with_name():
source = Resource("data/transform.csv")
target = transform(
source,
steps=[
steps.field_update(name="id", value=1),
steps.row_subset(subset="unique", field_name="id"),
],
)
assert target.schema == {
"fields": [
{"name": "id", "type": "integer"},
{"name": "name", "type": "string"},
{"name": "population", "type": "integer"},
]
}
assert target.read_rows() == []
