dagster-datacontract 0.3.0__tar.gz → 0.3.1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/PKG-INFO +1 -1
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract/__init__.py +18 -12
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract/metadata/server_information.py +22 -13
- dagster_datacontract-0.3.1/dagster_datacontract/utils/__init__.py +28 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract.egg-info/PKG-INFO +1 -1
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract.egg-info/SOURCES.txt +2 -1
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/pyproject.toml +1 -1
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/LICENSE +0 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/README.md +0 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract/description/__init__.py +0 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract/description/description.py +0 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract/metadata/__init__.py +0 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract/metadata/table_colums.py +0 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract/tags/__init__.py +0 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract/tags/tags.py +0 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract.egg-info/dependency_links.txt +0 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract.egg-info/requires.txt +0 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract.egg-info/top_level.txt +0 -0
- {dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/setup.cfg +0 -0
@@ -14,6 +14,7 @@ from dagster_datacontract.metadata import (
|
|
14
14
|
get_table_column,
|
15
15
|
)
|
16
16
|
from dagster_datacontract.tags import get_tags
|
17
|
+
from dagster_datacontract.utils import normalize_path
|
17
18
|
|
18
19
|
|
19
20
|
class DataContractLoader:
|
@@ -41,6 +42,15 @@ class DataContractLoader:
|
|
41
42
|
def _load_metadata(
|
42
43
|
self,
|
43
44
|
) -> dict[str, TableColumnLineage | TableSchema | Any] | None:
|
45
|
+
metadata = (
|
46
|
+
{
|
47
|
+
"data contract path": dg.MetadataValue.url(
|
48
|
+
normalize_path(self.data_contract._data_contract_file)
|
49
|
+
),
|
50
|
+
}
|
51
|
+
if self.data_contract._data_contract_file
|
52
|
+
else {}
|
53
|
+
)
|
44
54
|
columns = []
|
45
55
|
deps_by_column = {}
|
46
56
|
|
@@ -53,19 +63,19 @@ class DataContractLoader:
|
|
53
63
|
table_column_lineage = get_column_lineage(column_field)
|
54
64
|
deps_by_column[column_name] = table_column_lineage
|
55
65
|
|
66
|
+
metadata["dagster/column_schema"] = dg.TableSchema(columns=columns)
|
67
|
+
metadata["dagster/column_lineage"] = dg.TableColumnLineage(
|
68
|
+
deps_by_column=deps_by_column
|
69
|
+
)
|
70
|
+
|
56
71
|
server_information = get_server_information(
|
57
72
|
self.data_contract_specification,
|
58
73
|
self.data_contract._server,
|
59
74
|
self.asset_name,
|
60
75
|
)
|
76
|
+
metadata.update(server_information)
|
61
77
|
|
62
|
-
return
|
63
|
-
"dagster/column_schema": dg.TableSchema(columns=columns),
|
64
|
-
"dagster/column_lineage": dg.TableColumnLineage(
|
65
|
-
deps_by_column=deps_by_column
|
66
|
-
),
|
67
|
-
**server_information,
|
68
|
-
}
|
78
|
+
return metadata
|
69
79
|
|
70
80
|
def _load_owner(self) -> list[str] | None:
|
71
81
|
owner = self.data_contract_specification.info.owner
|
@@ -108,11 +118,7 @@ class DataContractLoader:
|
|
108
118
|
blocking=True,
|
109
119
|
)
|
110
120
|
def check_asset():
|
111
|
-
|
112
|
-
data_contract=self.data_contract_specification,
|
113
|
-
server=self.server_name,
|
114
|
-
)
|
115
|
-
run = data_contract.test()
|
121
|
+
run = self.data_contract.test()
|
116
122
|
|
117
123
|
return dg.AssetCheckResult(
|
118
124
|
passed=run.result == ResultEnum.passed,
|
@@ -1,17 +1,6 @@
|
|
1
|
-
import os
|
2
|
-
import urllib.parse
|
3
|
-
|
4
1
|
from datacontract.data_contract import DataContractSpecification
|
5
2
|
|
6
|
-
|
7
|
-
def _normalize_path(path: str) -> str:
|
8
|
-
parsed = urllib.parse.urlparse(path)
|
9
|
-
|
10
|
-
if not parsed.scheme or parsed.scheme == "file":
|
11
|
-
full_path = os.path.abspath(os.path.expanduser(path))
|
12
|
-
return f"file://{full_path}"
|
13
|
-
else:
|
14
|
-
return path
|
3
|
+
from dagster_datacontract.utils import normalize_path
|
15
4
|
|
16
5
|
|
17
6
|
def get_server_information(
|
@@ -19,6 +8,26 @@ def get_server_information(
|
|
19
8
|
server_name: str | None,
|
20
9
|
asset_name: str,
|
21
10
|
) -> dict[str, str]:
|
11
|
+
"""Returns a dictionary containing server-specific information to be used
|
12
|
+
by Dagster for identifying asset locations or connections.
|
13
|
+
|
14
|
+
This function inspects the provided `DataContractSpecification` to locate
|
15
|
+
the specified server by name and constructs a dictionary with keys such as
|
16
|
+
"dagster/uri" and "dagster/table_name" depending on the server type.
|
17
|
+
|
18
|
+
Parameters:
|
19
|
+
data_contract_specification (DataContractSpecification):
|
20
|
+
The data contract specification containing server configurations.
|
21
|
+
server_name (str | None):
|
22
|
+
The name of the server to retrieve information for. If None or not found, returns an empty dict.
|
23
|
+
asset_name (str):
|
24
|
+
The name of the asset, used for constructing fully qualified table names for certain server types.
|
25
|
+
|
26
|
+
Returns:
|
27
|
+
dict[str, str]: A dictionary with keys like "dagster/uri" and/or "dagster/table_name"
|
28
|
+
depending on the server type. Returns an empty dictionary if the server is not found
|
29
|
+
or if the server type is not recognized or unsupported.
|
30
|
+
"""
|
22
31
|
server = data_contract_specification.servers.get(server_name)
|
23
32
|
if not server:
|
24
33
|
return {}
|
@@ -37,7 +46,7 @@ def get_server_information(
|
|
37
46
|
case "kinesis":
|
38
47
|
server_information = {}
|
39
48
|
case "local":
|
40
|
-
server_information["dagster/uri"] =
|
49
|
+
server_information["dagster/uri"] = normalize_path(server.path)
|
41
50
|
case "oracle":
|
42
51
|
server_information["dagster/uri"] = f"{server.host}:{server.port}"
|
43
52
|
case "postgres":
|
@@ -0,0 +1,28 @@
|
|
1
|
+
import os
|
2
|
+
import urllib.parse
|
3
|
+
|
4
|
+
|
5
|
+
def normalize_path(path: str) -> str:
|
6
|
+
"""Normalizes a file path to ensure it is returned in a consistent URI format.
|
7
|
+
|
8
|
+
This function checks if the provided path is a local file path (with no scheme
|
9
|
+
or with the 'file' scheme) and converts it into a fully qualified file URI.
|
10
|
+
If the path already has a non-'file' scheme (e.g., 's3://', 'http://'),
|
11
|
+
it is returned unchanged.
|
12
|
+
|
13
|
+
Parameters:
|
14
|
+
path (str): The input file path. This can be a relative or absolute local path,
|
15
|
+
a path starting with `~`, or a URI with a supported scheme.
|
16
|
+
|
17
|
+
Returns:
|
18
|
+
str: A normalized path string:
|
19
|
+
- If the input is a local path or has a "file" scheme, returns it in the form "file:///absolute/path".
|
20
|
+
- If the input has another scheme (e.g., "s3://", "http://"), returns it unchanged.
|
21
|
+
"""
|
22
|
+
parsed = urllib.parse.urlparse(path)
|
23
|
+
|
24
|
+
if not parsed.scheme or parsed.scheme == "file":
|
25
|
+
full_path = os.path.abspath(os.path.expanduser(path))
|
26
|
+
return f"file://{full_path}"
|
27
|
+
else:
|
28
|
+
return path
|
{dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract.egg-info/SOURCES.txt
RENAMED
@@ -13,4 +13,5 @@ dagster_datacontract/metadata/__init__.py
|
|
13
13
|
dagster_datacontract/metadata/server_information.py
|
14
14
|
dagster_datacontract/metadata/table_colums.py
|
15
15
|
dagster_datacontract/tags/__init__.py
|
16
|
-
dagster_datacontract/tags/tags.py
|
16
|
+
dagster_datacontract/tags/tags.py
|
17
|
+
dagster_datacontract/utils/__init__.py
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract/metadata/__init__.py
RENAMED
File without changes
|
File without changes
|
{dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract/tags/__init__.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
{dagster_datacontract-0.3.0 → dagster_datacontract-0.3.1}/dagster_datacontract.egg-info/requires.txt
RENAMED
File without changes
|
File without changes
|
File without changes
|