collate-data-diff 0.11.3__tar.gz → 0.11.5__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.
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/PKG-INFO +17 -7
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/README.md +11 -2
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/__init__.py +25 -2
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/presto.py +3 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/snowflake.py +2 -2
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/pyproject.toml +11 -5
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/LICENSE +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/__main__.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/abcs/__init__.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/abcs/compiler.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/abcs/database_types.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/cloud/__init__.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/cloud/data_source.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/cloud/datafold_api.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/config.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/__init__.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/_connect.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/base.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/bigquery.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/clickhouse.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/databricks.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/duckdb.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/mssql.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/mysql.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/oracle.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/postgresql.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/redshift.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/trino.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/databases/vertica.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/dbt.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/dbt_config_validators.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/dbt_parser.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/diff_tables.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/errors.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/format.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/hashdiff_tables.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/info_tree.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/joindiff_tables.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/lexicographic_space.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/parse_time.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/py.typed +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/queries/__init__.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/queries/api.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/queries/ast_classes.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/queries/base.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/queries/extras.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/query_utils.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/schema.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/table_segment.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/thread_utils.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/tracking.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/utils.py +0 -0
- {collate_data_diff-0.11.3 → collate_data_diff-0.11.5}/data_diff/version.py +0 -0
|
@@ -1,8 +1,7 @@
|
|
|
1
|
-
Metadata-Version: 2.
|
|
1
|
+
Metadata-Version: 2.3
|
|
2
2
|
Name: collate-data-diff
|
|
3
|
-
Version: 0.11.
|
|
3
|
+
Version: 0.11.5
|
|
4
4
|
Summary: Command-line tool and Python library to efficiently diff rows across two different databases.
|
|
5
|
-
Home-page: https://github.com/datafold/data-diff
|
|
6
5
|
License: MIT
|
|
7
6
|
Author: Collate
|
|
8
7
|
Author-email: info@getcollate.io
|
|
@@ -19,6 +18,7 @@ Classifier: Programming Language :: Python :: 3.9
|
|
|
19
18
|
Classifier: Programming Language :: Python :: 3.10
|
|
20
19
|
Classifier: Programming Language :: Python :: 3.11
|
|
21
20
|
Classifier: Programming Language :: Python :: 3.12
|
|
21
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
22
22
|
Classifier: Topic :: Database :: Database Engines/Servers
|
|
23
23
|
Classifier: Typing :: Typed
|
|
24
24
|
Provides-Extra: all-dbs
|
|
@@ -43,7 +43,8 @@ Requires-Dist: dsnparse (<0.2.0)
|
|
|
43
43
|
Requires-Dist: duckdb ; extra == "duckdb" or extra == "all-dbs"
|
|
44
44
|
Requires-Dist: keyring
|
|
45
45
|
Requires-Dist: mashumaro[msgpack] (>=2.9,<3.11.0)
|
|
46
|
-
Requires-Dist: mysql-connector-python (>=8.0.29) ; extra == "mysql" or extra == "all-dbs"
|
|
46
|
+
Requires-Dist: mysql-connector-python (>=8.0.29) ; (python_version < "3.9") and (extra == "mysql" or extra == "all-dbs")
|
|
47
|
+
Requires-Dist: mysql-connector-python (>=9.1) ; (python_version >= "3.9") and (extra == "mysql" or extra == "all-dbs")
|
|
47
48
|
Requires-Dist: oracledb ; extra == "oracle" or extra == "all-dbs"
|
|
48
49
|
Requires-Dist: preql (>=0.2.19) ; extra == "preql" or extra == "all-dbs"
|
|
49
50
|
Requires-Dist: presto-python-client ; extra == "presto" or extra == "all-dbs"
|
|
@@ -51,7 +52,7 @@ Requires-Dist: psycopg2 ; extra == "postgresql" or extra == "redshift" or extra
|
|
|
51
52
|
Requires-Dist: pydantic (>=1.10.12)
|
|
52
53
|
Requires-Dist: pyodbc (>=4.0.39) ; extra == "mssql" or extra == "all-dbs"
|
|
53
54
|
Requires-Dist: rich
|
|
54
|
-
Requires-Dist: snowflake-connector-python (>=3.
|
|
55
|
+
Requires-Dist: snowflake-connector-python (>=3.13.1,<4.0.0) ; extra == "snowflake" or extra == "all-dbs"
|
|
55
56
|
Requires-Dist: tabulate (>=0.9.0)
|
|
56
57
|
Requires-Dist: toml (>=0.10.2)
|
|
57
58
|
Requires-Dist: trino (>=0.314.0) ; extra == "trino" or extra == "all-dbs"
|
|
@@ -66,6 +67,17 @@ Forked from the archived repository [datafold/data-diff](https://github.com/data
|
|
|
66
67
|
|
|
67
68
|
# data-diff: Compare datasets fast, within or across SQL databases
|
|
68
69
|
|
|
70
|
+
## Publishing
|
|
71
|
+
|
|
72
|
+
To publish a new version of the package, follow these steps:
|
|
73
|
+
|
|
74
|
+
1. Bump the version number in the [`pyproject.toml`](https://github.com/open-metadata/collate-data-diff/blob/main/pyproject.toml#L3) file.
|
|
75
|
+
2. Trigger the [publish action](https://github.com/open-metadata/collate-data-diff/actions/workflows/publish.yml).
|
|
76
|
+
|
|
77
|
+
To publish to Test PyPI, set the "test" input to "true" when triggering the action.
|
|
78
|
+
|
|
79
|
+
To publish a dev release, set the "dev" input to "true" when triggering the action.
|
|
80
|
+
|
|
69
81
|
## Contributors
|
|
70
82
|
|
|
71
83
|
<a href="https://github.com/datafold/data-diff/graphs/contributors">
|
|
@@ -76,5 +88,3 @@ Forked from the archived repository [datafold/data-diff](https://github.com/data
|
|
|
76
88
|
|
|
77
89
|
This project is licensed under the terms of the [MIT License](https://github.com/datafold/data-diff/blob/master/LICENSE).
|
|
78
90
|
|
|
79
|
-
## Publishing
|
|
80
|
-
|
|
@@ -3,6 +3,17 @@ Forked from the archived repository [datafold/data-diff](https://github.com/data
|
|
|
3
3
|
|
|
4
4
|
# data-diff: Compare datasets fast, within or across SQL databases
|
|
5
5
|
|
|
6
|
+
## Publishing
|
|
7
|
+
|
|
8
|
+
To publish a new version of the package, follow these steps:
|
|
9
|
+
|
|
10
|
+
1. Bump the version number in the [`pyproject.toml`](https://github.com/open-metadata/collate-data-diff/blob/main/pyproject.toml#L3) file.
|
|
11
|
+
2. Trigger the [publish action](https://github.com/open-metadata/collate-data-diff/actions/workflows/publish.yml).
|
|
12
|
+
|
|
13
|
+
To publish to Test PyPI, set the "test" input to "true" when triggering the action.
|
|
14
|
+
|
|
15
|
+
To publish a dev release, set the "dev" input to "true" when triggering the action.
|
|
16
|
+
|
|
6
17
|
## Contributors
|
|
7
18
|
|
|
8
19
|
<a href="https://github.com/datafold/data-diff/graphs/contributors">
|
|
@@ -12,5 +23,3 @@ Forked from the archived repository [datafold/data-diff](https://github.com/data
|
|
|
12
23
|
## License
|
|
13
24
|
|
|
14
25
|
This project is licensed under the terms of the [MIT License](https://github.com/datafold/data-diff/blob/master/LICENSE).
|
|
15
|
-
|
|
16
|
-
## Publishing
|
|
@@ -32,12 +32,35 @@ def connect_to_table(
|
|
|
32
32
|
if isinstance(key_columns, str):
|
|
33
33
|
key_columns = (key_columns,)
|
|
34
34
|
|
|
35
|
-
|
|
35
|
+
kw, kwargs = _get_table_segment_args(**kwargs)
|
|
36
|
+
|
|
37
|
+
db: Database = connect(db_info, thread_count=thread_count, **kwargs)
|
|
36
38
|
|
|
37
39
|
if isinstance(table_name, str):
|
|
38
40
|
table_name = db.dialect.parse_table_name(table_name)
|
|
39
41
|
|
|
40
|
-
return TableSegment(db, table_name, key_columns, **
|
|
42
|
+
return TableSegment(db, table_name, key_columns, **kw)
|
|
43
|
+
|
|
44
|
+
def _get_table_segment_args(**kwargs):
|
|
45
|
+
accepted_kwargs = {
|
|
46
|
+
"update_column",
|
|
47
|
+
"extra_columns",
|
|
48
|
+
"min_key",
|
|
49
|
+
"max_key",
|
|
50
|
+
"min_update",
|
|
51
|
+
"max_update",
|
|
52
|
+
"where",
|
|
53
|
+
"case_sensitive",
|
|
54
|
+
}
|
|
55
|
+
kw = {}
|
|
56
|
+
copy_kwargs = dict(kwargs)
|
|
57
|
+
for k, v in copy_kwargs.items():
|
|
58
|
+
if k in accepted_kwargs:
|
|
59
|
+
kw[k] = kwargs.pop(k)
|
|
60
|
+
if v is None and k not in accepted_kwargs:
|
|
61
|
+
kwargs.pop(k)
|
|
62
|
+
|
|
63
|
+
return kw, kwargs
|
|
41
64
|
|
|
42
65
|
|
|
43
66
|
def diff_tables(
|
|
@@ -139,11 +139,11 @@ class Snowflake(Database):
|
|
|
139
139
|
with open(key, "rb") as f:
|
|
140
140
|
key_bytes = f.read()
|
|
141
141
|
if key_content:
|
|
142
|
-
key_bytes =
|
|
142
|
+
key_bytes = bytes(key_content, "utf-8")
|
|
143
143
|
|
|
144
144
|
# If a private key is used, read it from the specified path and pass it as "private_key" to the connector.
|
|
145
145
|
if key_bytes:
|
|
146
|
-
if "password" in kw:
|
|
146
|
+
if "password" in kw and (kw.get("password") != "" or kw.get("password") is not None):
|
|
147
147
|
raise ConnectError("Cannot use password and key at the same time")
|
|
148
148
|
if kw.get("private_key_passphrase"):
|
|
149
149
|
encoded_passphrase = kw.get("private_key_passphrase").encode()
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[tool.poetry]
|
|
2
2
|
name = "collate-data-diff"
|
|
3
|
-
version = "0.11.
|
|
3
|
+
version = "0.11.5"
|
|
4
4
|
description = "Command-line tool and Python library to efficiently diff rows across two different databases."
|
|
5
5
|
authors = ["Collate <info@getcollate.io>", "Datafold <data-diff@datafold.com>"]
|
|
6
6
|
license = "MIT"
|
|
@@ -27,9 +27,12 @@ dsnparse = "<0.2.0"
|
|
|
27
27
|
click = ">=8.1"
|
|
28
28
|
rich = "*"
|
|
29
29
|
toml = ">=0.10.2"
|
|
30
|
-
mysql-connector-python =
|
|
30
|
+
mysql-connector-python = [
|
|
31
|
+
{version=">=8.0.29", python = "<3.9", optional=true},
|
|
32
|
+
{version=">=9.1", python = ">=3.9", optional=true}
|
|
33
|
+
]
|
|
31
34
|
psycopg2 = {version="*", optional=true}
|
|
32
|
-
snowflake-connector-python = {version = ">=3.
|
|
35
|
+
snowflake-connector-python = {version = ">=3.13.1,<4.0.0", optional=true}
|
|
33
36
|
cryptography = {version="*", optional=true}
|
|
34
37
|
trino = {version=">=0.314.0", optional=true}
|
|
35
38
|
presto-python-client = {version="*", optional=true}
|
|
@@ -51,9 +54,12 @@ mashumaro = {version = ">=2.9,<3.11.0", extras = ["msgpack"]}
|
|
|
51
54
|
parameterized = "*"
|
|
52
55
|
unittest-parallel = "*"
|
|
53
56
|
preql = ">=0.2.19"
|
|
54
|
-
mysql-connector-python =
|
|
57
|
+
mysql-connector-python = [
|
|
58
|
+
{version=">=8.0.29", python = "<3.9"},
|
|
59
|
+
{version=">=9.1", python = ">=3.9"}
|
|
60
|
+
]
|
|
55
61
|
psycopg2 = "*"
|
|
56
|
-
snowflake-connector-python = ">=3.
|
|
62
|
+
snowflake-connector-python = ">=3.13.1,<4.0.0"
|
|
57
63
|
cryptography = "*"
|
|
58
64
|
trino = ">=0.314.0"
|
|
59
65
|
presto-python-client = ">=0.8.3"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|