dcs-sdk 1.6.5__py3-none-any.whl

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.
Files changed (159) hide show
  1. data_diff/__init__.py +221 -0
  2. data_diff/__main__.py +517 -0
  3. data_diff/abcs/__init__.py +13 -0
  4. data_diff/abcs/compiler.py +27 -0
  5. data_diff/abcs/database_types.py +402 -0
  6. data_diff/config.py +141 -0
  7. data_diff/databases/__init__.py +38 -0
  8. data_diff/databases/_connect.py +323 -0
  9. data_diff/databases/base.py +1417 -0
  10. data_diff/databases/bigquery.py +376 -0
  11. data_diff/databases/clickhouse.py +217 -0
  12. data_diff/databases/databricks.py +262 -0
  13. data_diff/databases/duckdb.py +207 -0
  14. data_diff/databases/mssql.py +343 -0
  15. data_diff/databases/mysql.py +189 -0
  16. data_diff/databases/oracle.py +238 -0
  17. data_diff/databases/postgresql.py +293 -0
  18. data_diff/databases/presto.py +222 -0
  19. data_diff/databases/redis.py +93 -0
  20. data_diff/databases/redshift.py +233 -0
  21. data_diff/databases/snowflake.py +222 -0
  22. data_diff/databases/sybase.py +720 -0
  23. data_diff/databases/trino.py +73 -0
  24. data_diff/databases/vertica.py +174 -0
  25. data_diff/diff_tables.py +489 -0
  26. data_diff/errors.py +17 -0
  27. data_diff/format.py +369 -0
  28. data_diff/hashdiff_tables.py +1026 -0
  29. data_diff/info_tree.py +76 -0
  30. data_diff/joindiff_tables.py +434 -0
  31. data_diff/lexicographic_space.py +253 -0
  32. data_diff/parse_time.py +88 -0
  33. data_diff/py.typed +0 -0
  34. data_diff/queries/__init__.py +13 -0
  35. data_diff/queries/api.py +213 -0
  36. data_diff/queries/ast_classes.py +811 -0
  37. data_diff/queries/base.py +38 -0
  38. data_diff/queries/extras.py +43 -0
  39. data_diff/query_utils.py +70 -0
  40. data_diff/schema.py +67 -0
  41. data_diff/table_segment.py +583 -0
  42. data_diff/thread_utils.py +112 -0
  43. data_diff/utils.py +1022 -0
  44. data_diff/version.py +15 -0
  45. dcs_core/__init__.py +13 -0
  46. dcs_core/__main__.py +17 -0
  47. dcs_core/__version__.py +15 -0
  48. dcs_core/cli/__init__.py +13 -0
  49. dcs_core/cli/cli.py +165 -0
  50. dcs_core/core/__init__.py +19 -0
  51. dcs_core/core/common/__init__.py +13 -0
  52. dcs_core/core/common/errors.py +50 -0
  53. dcs_core/core/common/models/__init__.py +13 -0
  54. dcs_core/core/common/models/configuration.py +284 -0
  55. dcs_core/core/common/models/dashboard.py +24 -0
  56. dcs_core/core/common/models/data_source_resource.py +75 -0
  57. dcs_core/core/common/models/metric.py +160 -0
  58. dcs_core/core/common/models/profile.py +75 -0
  59. dcs_core/core/common/models/validation.py +216 -0
  60. dcs_core/core/common/models/widget.py +44 -0
  61. dcs_core/core/configuration/__init__.py +13 -0
  62. dcs_core/core/configuration/config_loader.py +139 -0
  63. dcs_core/core/configuration/configuration_parser.py +262 -0
  64. dcs_core/core/configuration/configuration_parser_arc.py +328 -0
  65. dcs_core/core/datasource/__init__.py +13 -0
  66. dcs_core/core/datasource/base.py +62 -0
  67. dcs_core/core/datasource/manager.py +112 -0
  68. dcs_core/core/datasource/search_datasource.py +421 -0
  69. dcs_core/core/datasource/sql_datasource.py +1094 -0
  70. dcs_core/core/inspect.py +163 -0
  71. dcs_core/core/logger/__init__.py +13 -0
  72. dcs_core/core/logger/base.py +32 -0
  73. dcs_core/core/logger/default_logger.py +94 -0
  74. dcs_core/core/metric/__init__.py +13 -0
  75. dcs_core/core/metric/base.py +220 -0
  76. dcs_core/core/metric/combined_metric.py +98 -0
  77. dcs_core/core/metric/custom_metric.py +34 -0
  78. dcs_core/core/metric/manager.py +137 -0
  79. dcs_core/core/metric/numeric_metric.py +403 -0
  80. dcs_core/core/metric/reliability_metric.py +90 -0
  81. dcs_core/core/profiling/__init__.py +13 -0
  82. dcs_core/core/profiling/datasource_profiling.py +136 -0
  83. dcs_core/core/profiling/numeric_field_profiling.py +72 -0
  84. dcs_core/core/profiling/text_field_profiling.py +67 -0
  85. dcs_core/core/repository/__init__.py +13 -0
  86. dcs_core/core/repository/metric_repository.py +77 -0
  87. dcs_core/core/utils/__init__.py +13 -0
  88. dcs_core/core/utils/log.py +29 -0
  89. dcs_core/core/utils/tracking.py +105 -0
  90. dcs_core/core/utils/utils.py +44 -0
  91. dcs_core/core/validation/__init__.py +13 -0
  92. dcs_core/core/validation/base.py +230 -0
  93. dcs_core/core/validation/completeness_validation.py +153 -0
  94. dcs_core/core/validation/custom_query_validation.py +24 -0
  95. dcs_core/core/validation/manager.py +282 -0
  96. dcs_core/core/validation/numeric_validation.py +276 -0
  97. dcs_core/core/validation/reliability_validation.py +91 -0
  98. dcs_core/core/validation/uniqueness_validation.py +61 -0
  99. dcs_core/core/validation/validity_validation.py +738 -0
  100. dcs_core/integrations/__init__.py +13 -0
  101. dcs_core/integrations/databases/__init__.py +13 -0
  102. dcs_core/integrations/databases/bigquery.py +187 -0
  103. dcs_core/integrations/databases/databricks.py +51 -0
  104. dcs_core/integrations/databases/db2.py +652 -0
  105. dcs_core/integrations/databases/elasticsearch.py +61 -0
  106. dcs_core/integrations/databases/mssql.py +829 -0
  107. dcs_core/integrations/databases/mysql.py +409 -0
  108. dcs_core/integrations/databases/opensearch.py +64 -0
  109. dcs_core/integrations/databases/oracle.py +719 -0
  110. dcs_core/integrations/databases/postgres.py +482 -0
  111. dcs_core/integrations/databases/redshift.py +53 -0
  112. dcs_core/integrations/databases/snowflake.py +48 -0
  113. dcs_core/integrations/databases/spark_df.py +111 -0
  114. dcs_core/integrations/databases/sybase.py +1069 -0
  115. dcs_core/integrations/storage/__init__.py +13 -0
  116. dcs_core/integrations/storage/local_file.py +149 -0
  117. dcs_core/integrations/utils/__init__.py +13 -0
  118. dcs_core/integrations/utils/utils.py +36 -0
  119. dcs_core/report/__init__.py +13 -0
  120. dcs_core/report/dashboard.py +211 -0
  121. dcs_core/report/models.py +88 -0
  122. dcs_core/report/static/assets/fonts/DMSans-Bold.ttf +0 -0
  123. dcs_core/report/static/assets/fonts/DMSans-Medium.ttf +0 -0
  124. dcs_core/report/static/assets/fonts/DMSans-Regular.ttf +0 -0
  125. dcs_core/report/static/assets/fonts/DMSans-SemiBold.ttf +0 -0
  126. dcs_core/report/static/assets/images/docs.svg +6 -0
  127. dcs_core/report/static/assets/images/github.svg +4 -0
  128. dcs_core/report/static/assets/images/logo.svg +7 -0
  129. dcs_core/report/static/assets/images/slack.svg +13 -0
  130. dcs_core/report/static/index.js +2 -0
  131. dcs_core/report/static/index.js.LICENSE.txt +3971 -0
  132. dcs_sdk/__init__.py +13 -0
  133. dcs_sdk/__main__.py +18 -0
  134. dcs_sdk/__version__.py +15 -0
  135. dcs_sdk/cli/__init__.py +13 -0
  136. dcs_sdk/cli/cli.py +163 -0
  137. dcs_sdk/sdk/__init__.py +58 -0
  138. dcs_sdk/sdk/config/__init__.py +13 -0
  139. dcs_sdk/sdk/config/config_loader.py +491 -0
  140. dcs_sdk/sdk/data_diff/__init__.py +13 -0
  141. dcs_sdk/sdk/data_diff/data_differ.py +821 -0
  142. dcs_sdk/sdk/rules/__init__.py +15 -0
  143. dcs_sdk/sdk/rules/rules_mappping.py +31 -0
  144. dcs_sdk/sdk/rules/rules_repository.py +214 -0
  145. dcs_sdk/sdk/rules/schema_rules.py +65 -0
  146. dcs_sdk/sdk/utils/__init__.py +13 -0
  147. dcs_sdk/sdk/utils/serializer.py +25 -0
  148. dcs_sdk/sdk/utils/similarity_score/__init__.py +13 -0
  149. dcs_sdk/sdk/utils/similarity_score/base_provider.py +153 -0
  150. dcs_sdk/sdk/utils/similarity_score/cosine_similarity_provider.py +39 -0
  151. dcs_sdk/sdk/utils/similarity_score/jaccard_provider.py +24 -0
  152. dcs_sdk/sdk/utils/similarity_score/levenshtein_distance_provider.py +31 -0
  153. dcs_sdk/sdk/utils/table.py +475 -0
  154. dcs_sdk/sdk/utils/themes.py +40 -0
  155. dcs_sdk/sdk/utils/utils.py +349 -0
  156. dcs_sdk-1.6.5.dist-info/METADATA +150 -0
  157. dcs_sdk-1.6.5.dist-info/RECORD +159 -0
  158. dcs_sdk-1.6.5.dist-info/WHEEL +4 -0
  159. dcs_sdk-1.6.5.dist-info/entry_points.txt +4 -0
@@ -0,0 +1,61 @@
1
+ # Copyright 2022-present, the Waterdip Labs Pvt. Ltd.
2
+ #
3
+ # Licensed under the Apache License, Version 2.0 (the "License");
4
+ # you may not use this file except in compliance with the License.
5
+ # You may obtain a copy of the License at
6
+ #
7
+ # http://www.apache.org/licenses/LICENSE-2.0
8
+ #
9
+ # Unless required by applicable law or agreed to in writing, software
10
+ # distributed under the License is distributed on an "AS IS" BASIS,
11
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12
+ # See the License for the specific language governing permissions and
13
+ # limitations under the License.
14
+ from typing import Dict
15
+
16
+ from elasticsearch import Elasticsearch
17
+
18
+ from dcs_core.core.common.errors import DataChecksDataSourcesConnectionError
19
+ from dcs_core.core.datasource import SearchIndexDataSource
20
+
21
+
22
+ class ElasticSearchDataSource(SearchIndexDataSource):
23
+ """
24
+ OpenSearch data source
25
+ """
26
+
27
+ def __init__(self, data_source_name: str, data_connection: Dict):
28
+ super().__init__(data_source_name, data_connection)
29
+
30
+ def connect(self) -> Elasticsearch:
31
+ """
32
+ Connect to the data source
33
+ """
34
+ try:
35
+ auth = None
36
+ if self.data_connection.get("username") is not None:
37
+ auth = (
38
+ self.data_connection.get("username"),
39
+ self.data_connection.get("password"),
40
+ )
41
+
42
+ host = self.data_connection.get("host")
43
+ port = int(self.data_connection.get("port"))
44
+ self.client = Elasticsearch(hosts=[{"host": host, "port": port}], http_auth=auth)
45
+ if not self.client.ping():
46
+ raise Exception("Failed to connect to ElasticSearch data source")
47
+ return self.client
48
+ except Exception as e:
49
+ raise DataChecksDataSourcesConnectionError(f"Failed to connect to ElasticSearch data source: [{str(e)}]")
50
+
51
+ def close(self):
52
+ """
53
+ Close the connection
54
+ """
55
+ self.client.close()
56
+
57
+ def is_connected(self) -> bool:
58
+ """
59
+ Check if the data source is connected
60
+ """
61
+ return self.client.ping()