def test_resource_source_data():
data = [["id", "name"], ["1", "english"], ["2", "中国人"]]
resource = Resource({"data": data})
assert resource.path is None
assert resource.data == data
assert resource.source == data
assert resource.basepath == ""
assert resource.inline is True
assert resource.tabular is True
assert resource.multipart is False
assert resource.read_bytes() == b""
assert resource.read_data() == data[1:]
assert resource.read_rows() == [
{
"id": 1,
"name": "english"
},
{
"id": 2,
"name": "中国人"
},
]
assert resource.read_header() == ["id", "name"]
assert resource.read_sample() == data[1:]
assert resource.read_stats() == {
"hash": "",
"bytes": 0,
"fields": 2,
"rows": 2,
}
def test_resource_infer_float_numbers():
data = [["number"], ["1.1"], ["2.2"], ["3.3"]]
resource = Resource(data=data, infer_float_numbers=True)
resource.infer()
assert resource.schema == {
"fields": [
{
"name": "number",
"type": "number",
"floatNumber": True
},
]
}
assert resource.read_header() == ["number"]
assert resource.read_rows() == [
{
"number": 1.1
},
{
"number": 2.2
},
{
"number": 3.3
},
]
def test_resource_source_path():
path = "data/table.csv"
resource = Resource({"path": path})
assert resource.path == path
assert resource.data is None
assert resource.source == path
assert resource.basepath == ""
assert resource.inline is False
assert resource.tabular is True
assert resource.multipart is False
assert (resource.read_bytes() ==
b"id,name\n1,english\n2,\xe4\xb8\xad\xe5\x9b\xbd\xe4\xba\xba\n")
assert resource.read_data() == [["1", "english"], ["2", "中国人"]]
assert resource.read_rows() == [
{
"id": 1,
"name": "english"
},
{
"id": 2,
"name": "中国人"
},
]
assert resource.read_header() == ["id", "name"]
assert resource.read_sample() == [["1", "english"], ["2", "中国人"]]
assert resource.read_stats() == {
"hash": "6c2c61dd9b0e9c6876139a449ed87933",
"bytes": 30,
"fields": 2,
"rows": 2,
}
def test_resource_infer_names():
resource = Resource(path="data/table.csv", infer_names=["new1", "new2"])
resource.infer()
assert resource.schema == {
"fields": [
{
"name": "new1",
"type": "integer"
},
{
"name": "new2",
"type": "string"
},
]
}
assert resource.read_header() == ["id", "name"]
assert resource.read_rows() == [
{
"new1": 1,
"new2": "english"
},
{
"new1": 2,
"new2": "中国人"
},
]
def test_resource_infer_type():
resource = Resource(path="data/table.csv", infer_type="string")
resource.infer()
assert resource.schema == {
"fields": [
{
"name": "id",
"type": "string"
},
{
"name": "name",
"type": "string"
},
]
}
assert resource.read_header() == ["id", "name"]
assert resource.read_rows() == [
{
"id": "1",
"name": "english"
},
{
"id": "2",
"name": "中国人"
},
]
def test_table_schema_patch_schema():
patch_schema = {"fields": {"id": {"name": "new", "type": "string"}}}
resource = Resource(path="data/table.csv", patch_schema=patch_schema)
resource.infer()
assert resource.schema == {
"fields": [
{
"name": "new",
"type": "string"
},
{
"name": "name",
"type": "string"
},
]
}
assert resource.read_header() == ["id", "name"]
assert resource.read_rows() == [
{
"new": "1",
"name": "english"
},
{
"new": "2",
"name": "中国人"
},
]
def test_resource_sync_schema():
schema = {
"fields": [{
"name": "name",
"type": "string"
}, {
"name": "id",
"type": "integer"
}]
}
resource = Resource(path="data/sync-schema.csv",
schema=schema,
sync_schema=True)
resource.infer()
assert resource.schema == schema
assert resource.read_header() == ["name", "id"]
assert resource.read_sample() == [["english", "1"], ["中国人", "2"]]
assert resource.read_rows() == [
{
"id": 1,
"name": "english"
},
{
"id": 2,
"name": "中国人"
},
]
def test_resource_multipart_write_file(tmpdir):
source = "data/table.json"
target = str(tmpdir.join("table{number}.json"))
target1 = str(tmpdir.join("table1.json"))
target2 = str(tmpdir.join("table2.json"))
# Write
resource = Resource(path=source)
resource.write(target, scheme="multipart", control={"chunkSize": 80})
# Read
resource = Resource(path=[target1, target2], trusted=True)
resource.read_header() == ["id", "name"]
assert resource.read_rows() == [
{"id": 1, "name": "english"},
{"id": 2, "name": "中国人"},
]
def test_missing_header():
schema = Schema(
fields=[Field(name="id"),
Field(name="name"),
Field(name="extra")])
resource = Resource(path="data/table.csv", schema=schema)
header = resource.read_header()
assert header == ["id", "name"]
assert header.valid is False
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_resource_respect_query_set_after_creation_issue_503():
resource = Resource(path="data/table.csv")
resource.query = Query(limit_rows=1)
assert resource.read_header() == ["id", "name"]
assert resource.read_rows() == [{"id": 1, "name": "english"}]
