def test_schema_change_roundtrip(gen_uuid):
old_schema = Schema([
ColumnSchema(gen_uuid(), "ID", "integer", 0),
ColumnSchema(gen_uuid(), "given_name", "text", None),
ColumnSchema(gen_uuid(), "surname", "text", None),
ColumnSchema(gen_uuid(), "date_of_birth", "date", None),
])
new_schema = Schema([
ColumnSchema(old_schema[0].id, "personnel_id", "integer", 0),
ColumnSchema(gen_uuid(), "tax_file_number", "text", None),
ColumnSchema(old_schema[2].id, "last_name", "text", None),
ColumnSchema(old_schema[1].id, "first_name", "text", None),
ColumnSchema(gen_uuid(), "middle_names", "text", None),
])
# Updating the schema without updating features is only possible
# if the old and new schemas have the same primary key columns:
assert old_schema.is_pk_compatible(new_schema)
feature_tuple = (7, "Joe", "Bloggs", "1970-01-01")
feature_dict = {
"given_name": "Joe",
"surname": "Bloggs",
"date_of_birth": "1970-01-01",
"ID": 7,
}
feature_path, feature_data = EMPTY_DATASET.encode_feature(
feature_tuple, old_schema)
feature_path2, feature_data2 = EMPTY_DATASET.encode_feature(
feature_dict, old_schema)
# Either encode method should give the same result.
assert (feature_path, feature_data) == (feature_path2, feature_data2)
# The dataset should store only the current schema, but all legends.
schema_path, schema_data = EMPTY_DATASET.encode_schema(new_schema)
new_legend_path, new_legend_data = EMPTY_DATASET.encode_legend(
new_schema.legend)
old_legend_path, old_legend_data = EMPTY_DATASET.encode_legend(
old_schema.legend)
tree = DictTree({
schema_path: schema_data,
new_legend_path: new_legend_data,
old_legend_path: old_legend_data,
feature_path: feature_data,
})
dataset2 = Dataset2(tree / DATASET_PATH, DATASET_PATH)
# Old columns that are not present in the new schema are gone.
# New columns that are not present in the old schema have 'None's.
roundtripped = dataset2.get_feature(path=feature_path, keys=False)
assert roundtripped == (7, None, "Bloggs", "Joe", None)
roundtripped = dataset2.get_feature(path=feature_path, keys=True)
assert roundtripped == {
"personnel_id": 7,
"tax_file_number": None,
"last_name": "Bloggs",
"first_name": "Joe",
"middle_names": None,
}
def test_align_schema(gen_uuid):
old_schema = Schema(
[
ColumnSchema(gen_uuid(), "ID", "integer", 0),
ColumnSchema(gen_uuid(), "first_name", "text", None),
ColumnSchema(gen_uuid(), "last_name", "text", None),
ColumnSchema(gen_uuid(), "date_of_birth", "date", None),
]
)
new_schema = Schema(
[
ColumnSchema(gen_uuid(), "personnel_id", "integer", 0),
ColumnSchema(gen_uuid(), "tax_file_number", "text", None),
ColumnSchema(gen_uuid(), "last_name", "text", None),
ColumnSchema(gen_uuid(), "first_name", "text", None),
ColumnSchema(gen_uuid(), "middle_names", "text", None),
]
)
aligned_schema = old_schema.align_to_self(new_schema)
assert [c.name for c in aligned_schema] == [
"personnel_id",
"tax_file_number",
"last_name",
"first_name",
"middle_names",
]
aligned = {}
for old_col in old_schema:
for aligned_col in aligned_schema:
if aligned_col.id == old_col.id:
aligned[old_col.name] = aligned_col.name
assert aligned == {
"ID": "personnel_id",
"first_name": "first_name",
"last_name": "last_name",
}
diff_counts = old_schema.diff_type_counts(aligned_schema)
assert diff_counts == {
"inserts": 2,
"deletes": 1,
"name_updates": 1,
"position_updates": 1,
"type_updates": 0,
"pk_updates": 0,
}
def test_feature_roundtrip(gen_uuid):
schema = Schema([
ColumnSchema(gen_uuid(), "geom", "geometry", None, **GEOM_TYPE_INFO),
ColumnSchema(gen_uuid(), "id", "integer", 1, size=64),
ColumnSchema(gen_uuid(), "artist", "text", 0, length=200),
ColumnSchema(gen_uuid(), "recording", "blob", None),
])
schema_path, schema_data = EMPTY_DATASET.encode_schema(schema)
legend_path, legend_data = EMPTY_DATASET.encode_legend(schema.legend)
# Feature tuples must be in schema order:
feature_tuple = ("010100000087BF756489EF5C4C", 7, "GIS Choir", b"MP3")
# But for feature dicts, the initialisation order is not important.
feature_dict = {
"artist": "GIS Choir",
"recording": b"MP3",
"id": 7,
"geom": "010100000087BF756489EF5C4C",
}
feature_path, feature_data = EMPTY_DATASET.encode_feature(
feature_tuple, schema)
feature_path2, feature_data2 = EMPTY_DATASET.encode_feature(
feature_dict, schema)
# Either encode method should give the same result.
assert (feature_path, feature_data) == (feature_path2, feature_data2)
tree = DictTree({
schema_path: schema_data,
legend_path: legend_data,
feature_path: feature_data
})
dataset2 = Dataset2(tree / DATASET_PATH, DATASET_PATH)
roundtripped_tuple = dataset2.get_feature(path=feature_path, keys=False)
assert roundtripped_tuple is not feature_tuple
assert roundtripped_tuple == feature_tuple
roundtripped_dict = dataset2.get_feature(path=feature_path, keys=True)
assert roundtripped_dict is not feature_dict
assert roundtripped_dict == feature_dict
def test_schema_roundtrip(gen_uuid):
orig = Schema([
ColumnSchema(gen_uuid(), "geom", "geometry", None, **GEOM_TYPE_INFO),
ColumnSchema(gen_uuid(), "id", "integer", 1, size=64),
ColumnSchema(gen_uuid(), "artist", "text", 0, length=200),
ColumnSchema(gen_uuid(), "recording", "blob", None),
])
roundtripped = Schema.loads(orig.dumps())
assert roundtripped is not orig
assert roundtripped == orig
path, data = EMPTY_DATASET.encode_schema(orig)
tree = DictTree({path: data})
dataset2 = Dataset2(tree / DATASET_PATH, DATASET_PATH)
roundtripped = dataset2.schema
assert roundtripped is not orig
assert roundtripped == orig
def test_schema_diff_as_text(gen_uuid):
old_schema = Schema(
[
ColumnSchema(gen_uuid(), "fid", "integer", 0, size=64),
ColumnSchema(
gen_uuid(),
"geom",
"geometry",
None,
geometryType="MULTIPOLYGON",
geometryCRS="EPSG:2193",
),
ColumnSchema(gen_uuid(), "building_id", "integer", None, size=32),
ColumnSchema(gen_uuid(), "name", "text", None),
ColumnSchema(gen_uuid(), "use", "text", None),
ColumnSchema(gen_uuid(), "suburb_locality", "text", None),
ColumnSchema(gen_uuid(), "town_city", "text", None),
ColumnSchema(gen_uuid(), "territorial_authority", "text", None),
ColumnSchema(gen_uuid(), "last_modified", "date", None),
]
)
new_schema = Schema(
[
ColumnSchema(gen_uuid(), "fid", "integer", 0, size=64),
ColumnSchema(gen_uuid(), "building_id", "integer", None, size=64),
ColumnSchema(gen_uuid(), "name", "text", None, size=40),
ColumnSchema(gen_uuid(), "territorial_authority", "text", None),
ColumnSchema(gen_uuid(), "use", "text", None),
ColumnSchema(gen_uuid(), "colour", "integer", None, size=32),
ColumnSchema(gen_uuid(), "town_city", "text", None),
ColumnSchema(
gen_uuid(),
"geom",
"geometry",
None,
geometryType="MULTIPOLYGON",
geometryCRS="EPSG:2193",
),
ColumnSchema(gen_uuid(), "last_modified", "date", None),
]
)
aligned_schema = old_schema.align_to_self(new_schema)
output = schema_diff_as_text(old_schema, aligned_schema)
assert click.unstyle(output).splitlines() == [
" [",
" {",
' "id": "b11ea716-6b85-f672-741f-8281aaa04bef",',
' "name": "fid",',
' "dataType": "integer",',
' "primaryKeyIndex": 0,',
' "size": 64',
" },",
"- {",
'- "id": "0d167b8b-294f-c2be-4747-bc947672d3a0",',
'- "name": "geom",',
'- "dataType": "geometry",',
'- "primaryKeyIndex": null,',
'- "geometryType": "MULTIPOLYGON",',
'- "geometryCRS": "EPSG:2193"',
"- },",
" {",
' "id": "0f28f35f-89d8-2b93-40d7-30abe42c69ea",',
' "name": "building_id",',
' "dataType": "integer",',
' "primaryKeyIndex": null,',
'- "size": 32,',
'+ "size": 64,',
" },",
" {",
' "id": "b5c69fa8-f48f-59bb-7aab-95225daf4774",',
' "name": "name",',
' "dataType": "text",',
' "primaryKeyIndex": null,',
'+ "size": 40,',
" },",
"+ {",
'+ "id": "d087bf39-1c76-fdd9-1315-0e81c6bd360f",',
'+ "name": "territorial_authority",',
'+ "dataType": "text",',
'+ "primaryKeyIndex": null',
"+ },",
" {",
' "id": "9f1924ac-097a-fc0a-b168-a06e8db32af7",',
' "name": "use",',
' "dataType": "text",',
' "primaryKeyIndex": null',
" },",
"- {",
'- "id": "1bcf7a4a-19e9-9752-6264-0fd1d387633b",',
'- "name": "suburb_locality",',
'- "dataType": "text",',
'- "primaryKeyIndex": null',
"- },",
"+ {",
'+ "id": "0f4e1e5b-9adb-edbe-6cbd-0ee0140448e6",',
'+ "name": "colour",',
'+ "dataType": "integer",',
'+ "primaryKeyIndex": null,',
'+ "size": 32',
"+ },",
" {",
' "id": "1777c850-baa2-6d52-dfcd-309f1741ff51",',
' "name": "town_city",',
' "dataType": "text",',
' "primaryKeyIndex": null',
" },",
"- {",
'- "id": "d087bf39-1c76-fdd9-1315-0e81c6bd360f",',
'- "name": "territorial_authority",',
'- "dataType": "text",',
'- "primaryKeyIndex": null',
"- },",
"+ {",
'+ "id": "0d167b8b-294f-c2be-4747-bc947672d3a0",',
'+ "name": "geom",',
'+ "dataType": "geometry",',
'+ "primaryKeyIndex": null,',
'+ "geometryType": "MULTIPOLYGON",',
'+ "geometryCRS": "EPSG:2193"',
"+ },",
" {",
' "id": "db82ba8c-c997-4bf1-87ef-b5108bdccde7",',
' "name": "last_modified",',
' "dataType": "date",',
' "primaryKeyIndex": null',
" },",
" ]",
]
def _pki(pk_index):
# Returns an arbitrary ColumnSchema, but with the given pk_index property.
id = gen_uuid()
return ColumnSchema(id, id[:8], "integer", pk_index)