snowpark-connect 0.20.2__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.
Potentially problematic release.
This version of snowpark-connect might be problematic. Click here for more details.
- snowflake/snowpark_connect/__init__.py +23 -0
- snowflake/snowpark_connect/analyze_plan/__init__.py +3 -0
- snowflake/snowpark_connect/analyze_plan/map_tree_string.py +38 -0
- snowflake/snowpark_connect/column_name_handler.py +735 -0
- snowflake/snowpark_connect/config.py +576 -0
- snowflake/snowpark_connect/constants.py +47 -0
- snowflake/snowpark_connect/control_server.py +52 -0
- snowflake/snowpark_connect/dataframe_name_handler.py +54 -0
- snowflake/snowpark_connect/date_time_format_mapping.py +399 -0
- snowflake/snowpark_connect/empty_dataframe.py +18 -0
- snowflake/snowpark_connect/error/__init__.py +11 -0
- snowflake/snowpark_connect/error/error_mapping.py +6174 -0
- snowflake/snowpark_connect/error/error_utils.py +321 -0
- snowflake/snowpark_connect/error/exceptions.py +24 -0
- snowflake/snowpark_connect/execute_plan/__init__.py +3 -0
- snowflake/snowpark_connect/execute_plan/map_execution_command.py +204 -0
- snowflake/snowpark_connect/execute_plan/map_execution_root.py +173 -0
- snowflake/snowpark_connect/execute_plan/utils.py +183 -0
- snowflake/snowpark_connect/expression/__init__.py +3 -0
- snowflake/snowpark_connect/expression/literal.py +90 -0
- snowflake/snowpark_connect/expression/map_cast.py +343 -0
- snowflake/snowpark_connect/expression/map_expression.py +293 -0
- snowflake/snowpark_connect/expression/map_extension.py +104 -0
- snowflake/snowpark_connect/expression/map_sql_expression.py +633 -0
- snowflake/snowpark_connect/expression/map_udf.py +142 -0
- snowflake/snowpark_connect/expression/map_unresolved_attribute.py +241 -0
- snowflake/snowpark_connect/expression/map_unresolved_extract_value.py +85 -0
- snowflake/snowpark_connect/expression/map_unresolved_function.py +9450 -0
- snowflake/snowpark_connect/expression/map_unresolved_star.py +218 -0
- snowflake/snowpark_connect/expression/map_update_fields.py +164 -0
- snowflake/snowpark_connect/expression/map_window_function.py +258 -0
- snowflake/snowpark_connect/expression/typer.py +125 -0
- snowflake/snowpark_connect/includes/__init__.py +0 -0
- snowflake/snowpark_connect/includes/jars/antlr4-runtime-4.9.3.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-cli-1.5.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-codec-1.16.1.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-collections-3.2.2.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-collections4-4.4.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-compiler-3.1.9.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-compress-1.26.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-crypto-1.1.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-dbcp-1.4.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-io-2.16.1.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-lang-2.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-lang3-3.12.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-logging-1.1.3.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-math3-3.6.1.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-pool-1.5.4.jar +0 -0
- snowflake/snowpark_connect/includes/jars/commons-text-1.10.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/hadoop-client-api-3.3.4.jar +0 -0
- snowflake/snowpark_connect/includes/jars/jackson-annotations-2.15.2.jar +0 -0
- snowflake/snowpark_connect/includes/jars/jackson-core-2.15.2.jar +0 -0
- snowflake/snowpark_connect/includes/jars/jackson-core-asl-1.9.13.jar +0 -0
- snowflake/snowpark_connect/includes/jars/jackson-databind-2.15.2.jar +0 -0
- snowflake/snowpark_connect/includes/jars/jackson-dataformat-yaml-2.15.2.jar +0 -0
- snowflake/snowpark_connect/includes/jars/jackson-datatype-jsr310-2.15.2.jar +0 -0
- snowflake/snowpark_connect/includes/jars/jackson-mapper-asl-1.9.13.jar +0 -0
- snowflake/snowpark_connect/includes/jars/jackson-module-scala_2.12-2.15.2.jar +0 -0
- snowflake/snowpark_connect/includes/jars/json4s-ast_2.12-3.7.0-M11.jar +0 -0
- snowflake/snowpark_connect/includes/jars/json4s-core_2.12-3.7.0-M11.jar +0 -0
- snowflake/snowpark_connect/includes/jars/json4s-jackson_2.12-3.7.0-M11.jar +0 -0
- snowflake/snowpark_connect/includes/jars/json4s-scalap_2.12-3.7.0-M11.jar +0 -0
- snowflake/snowpark_connect/includes/jars/kryo-shaded-4.0.2.jar +0 -0
- snowflake/snowpark_connect/includes/jars/log4j-1.2-api-2.20.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/log4j-api-2.20.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/log4j-core-2.20.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/log4j-slf4j2-impl-2.20.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/paranamer-2.8.jar +0 -0
- snowflake/snowpark_connect/includes/jars/scala-collection-compat_2.12-2.7.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/scala-compiler-2.12.18.jar +0 -0
- snowflake/snowpark_connect/includes/jars/scala-library-2.12.18.jar +0 -0
- snowflake/snowpark_connect/includes/jars/scala-parser-combinators_2.12-2.3.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/scala-reflect-2.12.18.jar +0 -0
- snowflake/snowpark_connect/includes/jars/scala-xml_2.12-2.1.0.jar +0 -0
- snowflake/snowpark_connect/includes/jars/slf4j-api-2.0.7.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-catalyst_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-common-utils_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-core_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-graphx_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-hive-thriftserver_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-hive_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-kubernetes_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-kvstore_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-launcher_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-mesos_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-mllib-local_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-mllib_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-network-common_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-network-shuffle_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-repl_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-sketch_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-sql-api_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-sql_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-streaming_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-tags_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-unsafe_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/jars/spark-yarn_2.12-3.5.6.jar +0 -0
- snowflake/snowpark_connect/includes/python/__init__.py +21 -0
- snowflake/snowpark_connect/includes/python/pyspark/__init__.py +173 -0
- snowflake/snowpark_connect/includes/python/pyspark/_globals.py +71 -0
- snowflake/snowpark_connect/includes/python/pyspark/_typing.pyi +43 -0
- snowflake/snowpark_connect/includes/python/pyspark/accumulators.py +341 -0
- snowflake/snowpark_connect/includes/python/pyspark/broadcast.py +383 -0
- snowflake/snowpark_connect/includes/python/pyspark/cloudpickle/__init__.py +8 -0
- snowflake/snowpark_connect/includes/python/pyspark/cloudpickle/cloudpickle.py +948 -0
- snowflake/snowpark_connect/includes/python/pyspark/cloudpickle/cloudpickle_fast.py +844 -0
- snowflake/snowpark_connect/includes/python/pyspark/cloudpickle/compat.py +18 -0
- snowflake/snowpark_connect/includes/python/pyspark/conf.py +276 -0
- snowflake/snowpark_connect/includes/python/pyspark/context.py +2601 -0
- snowflake/snowpark_connect/includes/python/pyspark/daemon.py +218 -0
- snowflake/snowpark_connect/includes/python/pyspark/errors/__init__.py +70 -0
- snowflake/snowpark_connect/includes/python/pyspark/errors/error_classes.py +889 -0
- snowflake/snowpark_connect/includes/python/pyspark/errors/exceptions/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/errors/exceptions/base.py +228 -0
- snowflake/snowpark_connect/includes/python/pyspark/errors/exceptions/captured.py +307 -0
- snowflake/snowpark_connect/includes/python/pyspark/errors/exceptions/connect.py +190 -0
- snowflake/snowpark_connect/includes/python/pyspark/errors/tests/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/errors/tests/test_errors.py +60 -0
- snowflake/snowpark_connect/includes/python/pyspark/errors/utils.py +116 -0
- snowflake/snowpark_connect/includes/python/pyspark/files.py +165 -0
- snowflake/snowpark_connect/includes/python/pyspark/find_spark_home.py +95 -0
- snowflake/snowpark_connect/includes/python/pyspark/install.py +203 -0
- snowflake/snowpark_connect/includes/python/pyspark/instrumentation_utils.py +190 -0
- snowflake/snowpark_connect/includes/python/pyspark/java_gateway.py +248 -0
- snowflake/snowpark_connect/includes/python/pyspark/join.py +118 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/__init__.py +71 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/_typing.pyi +84 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/base.py +414 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/classification.py +4332 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/clustering.py +2188 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/common.py +146 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/connect/__init__.py +44 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/connect/base.py +346 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/connect/classification.py +382 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/connect/evaluation.py +291 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/connect/feature.py +258 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/connect/functions.py +77 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/connect/io_utils.py +335 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/connect/pipeline.py +262 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/connect/summarizer.py +120 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/connect/tuning.py +579 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/connect/util.py +173 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/deepspeed/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/deepspeed/deepspeed_distributor.py +165 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/deepspeed/tests/test_deepspeed_distributor.py +306 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/dl_util.py +150 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/evaluation.py +1166 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/feature.py +7474 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/fpm.py +543 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/functions.py +842 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/image.py +271 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/linalg/__init__.py +1382 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/model_cache.py +55 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/param/__init__.py +602 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/param/_shared_params_code_gen.py +368 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/param/shared.py +878 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/pipeline.py +451 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/recommendation.py +748 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/regression.py +3335 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/stat.py +523 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_connect_classification.py +53 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_connect_evaluation.py +50 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_connect_feature.py +43 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_connect_function.py +114 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_connect_pipeline.py +47 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_connect_summarizer.py +43 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_connect_tuning.py +46 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_legacy_mode_classification.py +238 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_legacy_mode_evaluation.py +194 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_legacy_mode_feature.py +156 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_legacy_mode_pipeline.py +184 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_legacy_mode_summarizer.py +78 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_legacy_mode_tuning.py +292 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_parity_torch_data_loader.py +50 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_parity_torch_distributor.py +152 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_algorithms.py +456 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_base.py +96 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_dl_util.py +186 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_evaluation.py +77 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_feature.py +401 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_functions.py +528 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_image.py +82 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_linalg.py +409 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_model_cache.py +55 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_param.py +441 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_persistence.py +546 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_pipeline.py +71 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_stat.py +52 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_training_summary.py +494 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_util.py +85 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/test_wrapper.py +138 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/tuning/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/tuning/test_cv_io_basic.py +151 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/tuning/test_cv_io_nested.py +97 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/tuning/test_cv_io_pipeline.py +143 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/tuning/test_tuning.py +551 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/tuning/test_tvs_io_basic.py +137 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/tuning/test_tvs_io_nested.py +96 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tests/tuning/test_tvs_io_pipeline.py +142 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/torch/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/torch/data.py +100 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/torch/distributor.py +1133 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/torch/log_communication.py +198 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/torch/tests/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/torch/tests/test_data_loader.py +137 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/torch/tests/test_distributor.py +561 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/torch/tests/test_log_communication.py +172 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/torch/torch_run_process_wrapper.py +83 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tree.py +434 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/tuning.py +1741 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/util.py +749 -0
- snowflake/snowpark_connect/includes/python/pyspark/ml/wrapper.py +465 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/__init__.py +44 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/_typing.pyi +33 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/classification.py +989 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/clustering.py +1318 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/common.py +174 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/evaluation.py +691 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/feature.py +1085 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/fpm.py +233 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/linalg/__init__.py +1653 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/linalg/distributed.py +1662 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/random.py +698 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/recommendation.py +389 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/regression.py +1067 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/stat/KernelDensity.py +59 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/stat/__init__.py +34 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/stat/_statistics.py +409 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/stat/distribution.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/stat/test.py +86 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/tests/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/tests/test_algorithms.py +353 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/tests/test_feature.py +192 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/tests/test_linalg.py +680 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/tests/test_stat.py +206 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/tests/test_streaming_algorithms.py +471 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/tests/test_util.py +108 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/tree.py +888 -0
- snowflake/snowpark_connect/includes/python/pyspark/mllib/util.py +659 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/__init__.py +165 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/_typing.py +52 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/accessors.py +989 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/base.py +1804 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/categorical.py +822 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/config.py +539 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/correlation.py +262 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/base.py +519 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/binary_ops.py +98 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/boolean_ops.py +426 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/categorical_ops.py +141 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/complex_ops.py +145 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/date_ops.py +127 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/datetime_ops.py +171 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/null_ops.py +83 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/num_ops.py +588 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/string_ops.py +154 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/timedelta_ops.py +101 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/data_type_ops/udt_ops.py +29 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/datetimes.py +891 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/exceptions.py +150 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/extensions.py +388 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/frame.py +13738 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/generic.py +3560 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/groupby.py +4448 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/indexes/__init__.py +21 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/indexes/base.py +2783 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/indexes/category.py +773 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/indexes/datetimes.py +843 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/indexes/multi.py +1323 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/indexes/numeric.py +210 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/indexes/timedelta.py +197 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/indexing.py +1862 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/internal.py +1680 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/missing/__init__.py +48 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/missing/common.py +76 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/missing/frame.py +63 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/missing/general_functions.py +43 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/missing/groupby.py +93 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/missing/indexes.py +184 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/missing/resample.py +101 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/missing/scalars.py +29 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/missing/series.py +69 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/missing/window.py +168 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/mlflow.py +238 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/namespace.py +3807 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/numpy_compat.py +260 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/plot/__init__.py +17 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/plot/core.py +1213 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/plot/matplotlib.py +928 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/plot/plotly.py +261 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/resample.py +816 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/series.py +7440 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/sql_formatter.py +308 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/sql_processor.py +394 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/strings.py +2371 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/supported_api_gen.py +378 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_any_all.py +177 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_apply_func.py +575 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_binary_ops.py +235 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_combine.py +653 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_compute.py +463 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_corrwith.py +86 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_cov.py +151 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_cumulative.py +139 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_describe.py +458 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_eval.py +86 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_melt.py +202 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_missing_data.py +520 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/computation/test_pivot.py +361 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_any_all.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_apply_func.py +42 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_binary_ops.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_combine.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_compute.py +60 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_corrwith.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_cov.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_cumulative.py +90 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_describe.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_eval.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_melt.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_missing_data.py +42 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/computation/test_parity_pivot.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_base.py +36 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_binary_ops.py +42 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_boolean_ops.py +47 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_categorical_ops.py +55 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_complex_ops.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_date_ops.py +47 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_datetime_ops.py +47 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_null_ops.py +42 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_num_arithmetic.py +43 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_num_ops.py +47 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_num_reverse.py +43 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_string_ops.py +47 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_timedelta_ops.py +47 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/test_parity_udt_ops.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/data_type_ops/testing_utils.py +226 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/diff_frames_ops/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/diff_frames_ops/test_parity_align.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/diff_frames_ops/test_parity_basic_slow.py +55 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/diff_frames_ops/test_parity_cov_corrwith.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/diff_frames_ops/test_parity_dot_frame.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/diff_frames_ops/test_parity_dot_series.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/diff_frames_ops/test_parity_index.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/diff_frames_ops/test_parity_series.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/diff_frames_ops/test_parity_setitem_frame.py +43 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/diff_frames_ops/test_parity_setitem_series.py +43 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/frame/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/frame/test_parity_attrs.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/frame/test_parity_constructor.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/frame/test_parity_conversion.py +42 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/frame/test_parity_reindexing.py +42 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/frame/test_parity_reshaping.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/frame/test_parity_spark.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/frame/test_parity_take.py +42 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/frame/test_parity_time_series.py +48 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/frame/test_parity_truncate.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/groupby/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/groupby/test_parity_aggregate.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/groupby/test_parity_apply_func.py +41 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/groupby/test_parity_cumulative.py +67 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/groupby/test_parity_describe.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/groupby/test_parity_groupby.py +55 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/groupby/test_parity_head_tail.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/groupby/test_parity_index.py +38 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/groupby/test_parity_missing_data.py +55 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/groupby/test_parity_split_apply.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/groupby/test_parity_stat.py +38 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/indexes/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/indexes/test_parity_align.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/indexes/test_parity_base.py +50 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/indexes/test_parity_category.py +73 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/indexes/test_parity_datetime.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/indexes/test_parity_indexing.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/indexes/test_parity_reindex.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/indexes/test_parity_rename.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/indexes/test_parity_reset_index.py +48 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/indexes/test_parity_timedelta.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/io/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/io/test_parity_io.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/plot/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot.py +45 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot_matplotlib.py +45 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/plot/test_parity_frame_plot_plotly.py +49 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/plot/test_parity_series_plot.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/plot/test_parity_series_plot_matplotlib.py +53 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/plot/test_parity_series_plot_plotly.py +45 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_all_any.py +38 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_arg_ops.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_as_of.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_as_type.py +38 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_compute.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_conversion.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_cumulative.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_index.py +38 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_missing_data.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_series.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_sort.py +38 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/series/test_parity_stat.py +38 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_categorical.py +66 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_config.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_csv.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_dataframe_conversion.py +42 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_dataframe_spark_io.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_default_index.py +49 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_ewm.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_expanding.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_extension.py +49 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_frame_spark.py +53 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_generic_functions.py +43 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_indexing.py +49 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_indexops_spark.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_internal.py +41 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_namespace.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_numpy_compat.py +60 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames.py +48 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby_expanding.py +44 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_ops_on_diff_frames_groupby_rolling.py +84 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_repr.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_resample.py +45 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_reshape.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_rolling.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_scalars.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_series_conversion.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_series_datetime.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_series_string.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_spark_functions.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_sql.py +43 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_stats.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_typedef.py +36 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_utils.py +37 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/connect/test_parity_window.py +39 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_base.py +107 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_binary_ops.py +224 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_boolean_ops.py +825 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_categorical_ops.py +562 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_complex_ops.py +368 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_date_ops.py +257 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_datetime_ops.py +260 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_null_ops.py +178 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_num_arithmetic.py +184 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_num_ops.py +497 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_num_reverse.py +140 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_string_ops.py +354 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_timedelta_ops.py +219 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/test_udt_ops.py +192 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/data_type_ops/testing_utils.py +228 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/diff_frames_ops/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/diff_frames_ops/test_align.py +118 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/diff_frames_ops/test_basic_slow.py +198 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/diff_frames_ops/test_cov_corrwith.py +181 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/diff_frames_ops/test_dot_frame.py +103 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/diff_frames_ops/test_dot_series.py +141 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/diff_frames_ops/test_index.py +109 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/diff_frames_ops/test_series.py +136 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/diff_frames_ops/test_setitem_frame.py +125 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/diff_frames_ops/test_setitem_series.py +217 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/frame/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/frame/test_attrs.py +384 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/frame/test_constructor.py +598 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/frame/test_conversion.py +73 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/frame/test_reindexing.py +869 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/frame/test_reshaping.py +487 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/frame/test_spark.py +309 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/frame/test_take.py +156 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/frame/test_time_series.py +149 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/frame/test_truncate.py +163 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/groupby/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/groupby/test_aggregate.py +311 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/groupby/test_apply_func.py +524 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/groupby/test_cumulative.py +419 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/groupby/test_describe.py +144 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/groupby/test_groupby.py +979 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/groupby/test_head_tail.py +234 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/groupby/test_index.py +206 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/groupby/test_missing_data.py +421 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/groupby/test_split_apply.py +187 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/groupby/test_stat.py +397 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/indexes/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/indexes/test_align.py +100 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/indexes/test_base.py +2743 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/indexes/test_category.py +484 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/indexes/test_datetime.py +276 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/indexes/test_indexing.py +432 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/indexes/test_reindex.py +310 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/indexes/test_rename.py +257 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/indexes/test_reset_index.py +160 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/indexes/test_timedelta.py +128 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/io/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/io/test_io.py +137 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/plot/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/plot/test_frame_plot.py +170 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/plot/test_frame_plot_matplotlib.py +547 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/plot/test_frame_plot_plotly.py +285 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/plot/test_series_plot.py +106 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/plot/test_series_plot_matplotlib.py +409 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/plot/test_series_plot_plotly.py +247 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_all_any.py +105 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_arg_ops.py +197 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_as_of.py +137 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_as_type.py +227 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_compute.py +634 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_conversion.py +88 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_cumulative.py +139 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_index.py +475 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_missing_data.py +265 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_series.py +818 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_sort.py +162 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/series/test_stat.py +780 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_categorical.py +741 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_config.py +160 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_csv.py +453 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_dataframe_conversion.py +281 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_dataframe_spark_io.py +487 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_default_index.py +109 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_ewm.py +434 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_expanding.py +253 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_extension.py +152 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_frame_spark.py +162 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_generic_functions.py +234 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_indexing.py +1339 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_indexops_spark.py +82 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_internal.py +124 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_namespace.py +638 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_numpy_compat.py +200 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_ops_on_diff_frames.py +1355 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_ops_on_diff_frames_groupby.py +655 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_ops_on_diff_frames_groupby_expanding.py +113 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_ops_on_diff_frames_groupby_rolling.py +118 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_repr.py +192 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_resample.py +346 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_reshape.py +495 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_rolling.py +263 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_scalars.py +59 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_series_conversion.py +85 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_series_datetime.py +364 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_series_string.py +362 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_spark_functions.py +46 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_sql.py +123 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_stats.py +581 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_typedef.py +447 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_utils.py +301 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/tests/test_window.py +465 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/typedef/__init__.py +18 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/typedef/typehints.py +874 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/usage_logging/__init__.py +143 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/usage_logging/usage_logger.py +132 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/utils.py +1063 -0
- snowflake/snowpark_connect/includes/python/pyspark/pandas/window.py +2702 -0
- snowflake/snowpark_connect/includes/python/pyspark/profiler.py +489 -0
- snowflake/snowpark_connect/includes/python/pyspark/py.typed +1 -0
- snowflake/snowpark_connect/includes/python/pyspark/python/pyspark/shell.py +123 -0
- snowflake/snowpark_connect/includes/python/pyspark/rdd.py +5518 -0
- snowflake/snowpark_connect/includes/python/pyspark/rddsampler.py +115 -0
- snowflake/snowpark_connect/includes/python/pyspark/resource/__init__.py +38 -0
- snowflake/snowpark_connect/includes/python/pyspark/resource/information.py +69 -0
- snowflake/snowpark_connect/includes/python/pyspark/resource/profile.py +317 -0
- snowflake/snowpark_connect/includes/python/pyspark/resource/requests.py +539 -0
- snowflake/snowpark_connect/includes/python/pyspark/resource/tests/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/resource/tests/test_resources.py +83 -0
- snowflake/snowpark_connect/includes/python/pyspark/resultiterable.py +45 -0
- snowflake/snowpark_connect/includes/python/pyspark/serializers.py +681 -0
- snowflake/snowpark_connect/includes/python/pyspark/shell.py +123 -0
- snowflake/snowpark_connect/includes/python/pyspark/shuffle.py +854 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/__init__.py +75 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/_typing.pyi +80 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/avro/__init__.py +18 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/avro/functions.py +188 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/catalog.py +1270 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/column.py +1431 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/conf.py +99 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/__init__.py +18 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/_typing.py +90 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/avro/__init__.py +18 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/avro/functions.py +107 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/catalog.py +356 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/client/__init__.py +22 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/client/artifact.py +412 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/client/core.py +1689 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/client/reattach.py +340 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/column.py +514 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/conf.py +128 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/conversion.py +490 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/dataframe.py +2172 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/expressions.py +1056 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/functions.py +3937 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/group.py +418 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/plan.py +2289 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/__init__.py +25 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/base_pb2.py +203 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/base_pb2.pyi +2718 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/base_pb2_grpc.py +423 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/catalog_pb2.py +109 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/catalog_pb2.pyi +1130 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/commands_pb2.py +141 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/commands_pb2.pyi +1766 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/common_pb2.py +47 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/common_pb2.pyi +123 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/example_plugins_pb2.py +53 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/example_plugins_pb2.pyi +112 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/expressions_pb2.py +107 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/expressions_pb2.pyi +1507 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/relations_pb2.py +195 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/relations_pb2.pyi +3613 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/types_pb2.py +95 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/proto/types_pb2.pyi +980 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/protobuf/__init__.py +18 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/protobuf/functions.py +166 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/readwriter.py +861 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/session.py +952 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/streaming/__init__.py +22 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/streaming/query.py +295 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/streaming/readwriter.py +618 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/streaming/worker/__init__.py +18 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/streaming/worker/foreach_batch_worker.py +87 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/streaming/worker/listener_worker.py +100 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/types.py +301 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/udf.py +296 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/udtf.py +200 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/utils.py +58 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/connect/window.py +266 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/context.py +818 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/dataframe.py +5973 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/functions.py +15889 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/group.py +547 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/observation.py +152 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/__init__.py +21 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/_typing/__init__.pyi +344 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/_typing/protocols/__init__.pyi +17 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/_typing/protocols/frame.pyi +20 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/_typing/protocols/series.pyi +20 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/conversion.py +671 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/functions.py +480 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/functions.pyi +132 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/group_ops.py +523 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/map_ops.py +216 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/serializers.py +1019 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/typehints.py +172 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/types.py +972 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/pandas/utils.py +86 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/protobuf/__init__.py +18 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/protobuf/functions.py +334 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/readwriter.py +2159 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/session.py +2088 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/sql_formatter.py +84 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/streaming/__init__.py +21 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/streaming/listener.py +1050 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/streaming/query.py +746 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/streaming/readwriter.py +1652 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/streaming/state.py +288 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/client/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/client/test_artifact.py +420 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/client/test_client.py +358 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/streaming/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/streaming/test_parity_foreach.py +36 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/streaming/test_parity_foreach_batch.py +44 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/streaming/test_parity_listener.py +116 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/streaming/test_parity_streaming.py +35 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_connect_basic.py +3612 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_connect_column.py +1042 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_connect_function.py +2381 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_connect_plan.py +1060 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_arrow.py +163 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_arrow_map.py +38 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_arrow_python_udf.py +48 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_catalog.py +36 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_column.py +55 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_conf.py +36 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_dataframe.py +96 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_datasources.py +44 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_errors.py +36 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_functions.py +59 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_group.py +36 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_pandas_cogrouped_map.py +59 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_pandas_grouped_map.py +74 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_pandas_grouped_map_with_state.py +62 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_pandas_map.py +58 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_pandas_udf.py +70 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_pandas_udf_grouped_agg.py +50 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_pandas_udf_scalar.py +68 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_pandas_udf_window.py +40 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_readwriter.py +46 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_serde.py +44 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_types.py +100 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_udf.py +100 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_parity_udtf.py +163 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_session.py +181 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/connect/test_utils.py +42 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/pandas/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/pandas/test_pandas_cogrouped_map.py +623 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/pandas/test_pandas_grouped_map.py +869 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/pandas/test_pandas_grouped_map_with_state.py +342 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/pandas/test_pandas_map.py +436 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/pandas/test_pandas_udf.py +363 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/pandas/test_pandas_udf_grouped_agg.py +592 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/pandas/test_pandas_udf_scalar.py +1503 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/pandas/test_pandas_udf_typehints.py +392 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/pandas/test_pandas_udf_typehints_with_future_annotations.py +375 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/pandas/test_pandas_udf_window.py +411 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/streaming/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/streaming/test_streaming.py +401 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/streaming/test_streaming_foreach.py +295 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/streaming/test_streaming_foreach_batch.py +106 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/streaming/test_streaming_listener.py +558 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_arrow.py +1346 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_arrow_map.py +182 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_arrow_python_udf.py +202 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_catalog.py +503 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_column.py +225 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_conf.py +83 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_context.py +201 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_dataframe.py +1931 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_datasources.py +256 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_errors.py +69 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_functions.py +1349 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_group.py +53 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_pandas_sqlmetrics.py +68 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_readwriter.py +283 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_serde.py +155 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_session.py +412 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_types.py +1581 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_udf.py +961 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_udf_profiler.py +165 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_udtf.py +1456 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/tests/test_utils.py +1686 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/types.py +2558 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/udf.py +714 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/udtf.py +325 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/utils.py +339 -0
- snowflake/snowpark_connect/includes/python/pyspark/sql/window.py +492 -0
- snowflake/snowpark_connect/includes/python/pyspark/statcounter.py +165 -0
- snowflake/snowpark_connect/includes/python/pyspark/status.py +112 -0
- snowflake/snowpark_connect/includes/python/pyspark/storagelevel.py +97 -0
- snowflake/snowpark_connect/includes/python/pyspark/streaming/__init__.py +22 -0
- snowflake/snowpark_connect/includes/python/pyspark/streaming/context.py +471 -0
- snowflake/snowpark_connect/includes/python/pyspark/streaming/dstream.py +933 -0
- snowflake/snowpark_connect/includes/python/pyspark/streaming/kinesis.py +205 -0
- snowflake/snowpark_connect/includes/python/pyspark/streaming/listener.py +83 -0
- snowflake/snowpark_connect/includes/python/pyspark/streaming/tests/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/streaming/tests/test_context.py +184 -0
- snowflake/snowpark_connect/includes/python/pyspark/streaming/tests/test_dstream.py +706 -0
- snowflake/snowpark_connect/includes/python/pyspark/streaming/tests/test_kinesis.py +118 -0
- snowflake/snowpark_connect/includes/python/pyspark/streaming/tests/test_listener.py +160 -0
- snowflake/snowpark_connect/includes/python/pyspark/streaming/util.py +168 -0
- snowflake/snowpark_connect/includes/python/pyspark/taskcontext.py +502 -0
- snowflake/snowpark_connect/includes/python/pyspark/testing/__init__.py +21 -0
- snowflake/snowpark_connect/includes/python/pyspark/testing/connectutils.py +199 -0
- snowflake/snowpark_connect/includes/python/pyspark/testing/mllibutils.py +30 -0
- snowflake/snowpark_connect/includes/python/pyspark/testing/mlutils.py +275 -0
- snowflake/snowpark_connect/includes/python/pyspark/testing/objects.py +121 -0
- snowflake/snowpark_connect/includes/python/pyspark/testing/pandasutils.py +714 -0
- snowflake/snowpark_connect/includes/python/pyspark/testing/sqlutils.py +168 -0
- snowflake/snowpark_connect/includes/python/pyspark/testing/streamingutils.py +178 -0
- snowflake/snowpark_connect/includes/python/pyspark/testing/utils.py +636 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/__init__.py +16 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_appsubmit.py +306 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_broadcast.py +196 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_conf.py +44 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_context.py +346 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_daemon.py +89 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_install_spark.py +124 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_join.py +69 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_memory_profiler.py +167 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_pin_thread.py +194 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_profiler.py +168 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_rdd.py +939 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_rddbarrier.py +52 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_rddsampler.py +66 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_readwrite.py +368 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_serializers.py +257 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_shuffle.py +267 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_stage_sched.py +153 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_statcounter.py +130 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_taskcontext.py +350 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_util.py +97 -0
- snowflake/snowpark_connect/includes/python/pyspark/tests/test_worker.py +271 -0
- snowflake/snowpark_connect/includes/python/pyspark/traceback_utils.py +81 -0
- snowflake/snowpark_connect/includes/python/pyspark/util.py +416 -0
- snowflake/snowpark_connect/includes/python/pyspark/version.py +19 -0
- snowflake/snowpark_connect/includes/python/pyspark/worker.py +1307 -0
- snowflake/snowpark_connect/includes/python/pyspark/worker_util.py +46 -0
- snowflake/snowpark_connect/proto/__init__.py +10 -0
- snowflake/snowpark_connect/proto/control_pb2.py +35 -0
- snowflake/snowpark_connect/proto/control_pb2.pyi +38 -0
- snowflake/snowpark_connect/proto/control_pb2_grpc.py +183 -0
- snowflake/snowpark_connect/proto/snowflake_expression_ext_pb2.py +35 -0
- snowflake/snowpark_connect/proto/snowflake_expression_ext_pb2.pyi +53 -0
- snowflake/snowpark_connect/proto/snowflake_rdd_pb2.pyi +39 -0
- snowflake/snowpark_connect/proto/snowflake_relation_ext_pb2.py +47 -0
- snowflake/snowpark_connect/proto/snowflake_relation_ext_pb2.pyi +111 -0
- snowflake/snowpark_connect/relation/__init__.py +3 -0
- snowflake/snowpark_connect/relation/catalogs/__init__.py +12 -0
- snowflake/snowpark_connect/relation/catalogs/abstract_spark_catalog.py +287 -0
- snowflake/snowpark_connect/relation/catalogs/snowflake_catalog.py +467 -0
- snowflake/snowpark_connect/relation/catalogs/utils.py +51 -0
- snowflake/snowpark_connect/relation/io_utils.py +76 -0
- snowflake/snowpark_connect/relation/map_aggregate.py +322 -0
- snowflake/snowpark_connect/relation/map_catalog.py +151 -0
- snowflake/snowpark_connect/relation/map_column_ops.py +1068 -0
- snowflake/snowpark_connect/relation/map_crosstab.py +48 -0
- snowflake/snowpark_connect/relation/map_extension.py +412 -0
- snowflake/snowpark_connect/relation/map_join.py +341 -0
- snowflake/snowpark_connect/relation/map_local_relation.py +326 -0
- snowflake/snowpark_connect/relation/map_map_partitions.py +146 -0
- snowflake/snowpark_connect/relation/map_relation.py +253 -0
- snowflake/snowpark_connect/relation/map_row_ops.py +716 -0
- snowflake/snowpark_connect/relation/map_sample_by.py +35 -0
- snowflake/snowpark_connect/relation/map_show_string.py +50 -0
- snowflake/snowpark_connect/relation/map_sql.py +1874 -0
- snowflake/snowpark_connect/relation/map_stats.py +324 -0
- snowflake/snowpark_connect/relation/map_subquery_alias.py +32 -0
- snowflake/snowpark_connect/relation/map_udtf.py +288 -0
- snowflake/snowpark_connect/relation/read/__init__.py +7 -0
- snowflake/snowpark_connect/relation/read/jdbc_read_dbapi.py +668 -0
- snowflake/snowpark_connect/relation/read/map_read.py +367 -0
- snowflake/snowpark_connect/relation/read/map_read_csv.py +142 -0
- snowflake/snowpark_connect/relation/read/map_read_jdbc.py +108 -0
- snowflake/snowpark_connect/relation/read/map_read_json.py +344 -0
- snowflake/snowpark_connect/relation/read/map_read_parquet.py +194 -0
- snowflake/snowpark_connect/relation/read/map_read_socket.py +59 -0
- snowflake/snowpark_connect/relation/read/map_read_table.py +109 -0
- snowflake/snowpark_connect/relation/read/map_read_text.py +106 -0
- snowflake/snowpark_connect/relation/read/reader_config.py +399 -0
- snowflake/snowpark_connect/relation/read/utils.py +155 -0
- snowflake/snowpark_connect/relation/stage_locator.py +161 -0
- snowflake/snowpark_connect/relation/utils.py +219 -0
- snowflake/snowpark_connect/relation/write/__init__.py +3 -0
- snowflake/snowpark_connect/relation/write/jdbc_write_dbapi.py +339 -0
- snowflake/snowpark_connect/relation/write/map_write.py +436 -0
- snowflake/snowpark_connect/relation/write/map_write_jdbc.py +48 -0
- snowflake/snowpark_connect/resources/java_udfs-1.0-SNAPSHOT.jar +0 -0
- snowflake/snowpark_connect/resources_initializer.py +75 -0
- snowflake/snowpark_connect/server.py +1136 -0
- snowflake/snowpark_connect/start_server.py +32 -0
- snowflake/snowpark_connect/tcm.py +8 -0
- snowflake/snowpark_connect/type_mapping.py +1003 -0
- snowflake/snowpark_connect/typed_column.py +94 -0
- snowflake/snowpark_connect/utils/__init__.py +3 -0
- snowflake/snowpark_connect/utils/artifacts.py +48 -0
- snowflake/snowpark_connect/utils/attribute_handling.py +72 -0
- snowflake/snowpark_connect/utils/cache.py +84 -0
- snowflake/snowpark_connect/utils/concurrent.py +124 -0
- snowflake/snowpark_connect/utils/context.py +390 -0
- snowflake/snowpark_connect/utils/describe_query_cache.py +231 -0
- snowflake/snowpark_connect/utils/interrupt.py +85 -0
- snowflake/snowpark_connect/utils/io_utils.py +35 -0
- snowflake/snowpark_connect/utils/pandas_udtf_utils.py +117 -0
- snowflake/snowpark_connect/utils/profiling.py +47 -0
- snowflake/snowpark_connect/utils/session.py +180 -0
- snowflake/snowpark_connect/utils/snowpark_connect_logging.py +38 -0
- snowflake/snowpark_connect/utils/telemetry.py +513 -0
- snowflake/snowpark_connect/utils/udf_cache.py +392 -0
- snowflake/snowpark_connect/utils/udf_helper.py +328 -0
- snowflake/snowpark_connect/utils/udf_utils.py +310 -0
- snowflake/snowpark_connect/utils/udtf_helper.py +420 -0
- snowflake/snowpark_connect/utils/udtf_utils.py +799 -0
- snowflake/snowpark_connect/utils/xxhash64.py +247 -0
- snowflake/snowpark_connect/version.py +6 -0
- snowpark_connect-0.20.2.data/scripts/snowpark-connect +71 -0
- snowpark_connect-0.20.2.data/scripts/snowpark-session +11 -0
- snowpark_connect-0.20.2.data/scripts/snowpark-submit +354 -0
- snowpark_connect-0.20.2.dist-info/METADATA +37 -0
- snowpark_connect-0.20.2.dist-info/RECORD +879 -0
- snowpark_connect-0.20.2.dist-info/WHEEL +5 -0
- snowpark_connect-0.20.2.dist-info/licenses/LICENSE.txt +202 -0
- snowpark_connect-0.20.2.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,1874 @@
|
|
|
1
|
+
#
|
|
2
|
+
# Copyright (c) 2012-2025 Snowflake Computing Inc. All rights reserved.
|
|
3
|
+
#
|
|
4
|
+
|
|
5
|
+
import re
|
|
6
|
+
from collections.abc import MutableMapping, MutableSequence
|
|
7
|
+
from contextlib import contextmanager
|
|
8
|
+
from contextvars import ContextVar
|
|
9
|
+
from functools import reduce
|
|
10
|
+
|
|
11
|
+
import jpype
|
|
12
|
+
import pandas
|
|
13
|
+
import pyspark.sql.connect.proto.expressions_pb2 as expressions_proto
|
|
14
|
+
import pyspark.sql.connect.proto.relations_pb2 as relation_proto
|
|
15
|
+
import sqlglot
|
|
16
|
+
from google.protobuf.any_pb2 import Any
|
|
17
|
+
from pyspark.errors.exceptions.base import AnalysisException
|
|
18
|
+
from sqlglot.expressions import ColumnDef, DataType, FileFormatProperty, Identifier
|
|
19
|
+
|
|
20
|
+
import snowflake.snowpark.functions as snowpark_fn
|
|
21
|
+
import snowflake.snowpark_connect.proto.snowflake_expression_ext_pb2 as snowflake_exp_proto
|
|
22
|
+
import snowflake.snowpark_connect.proto.snowflake_relation_ext_pb2 as snowflake_proto
|
|
23
|
+
from snowflake import snowpark
|
|
24
|
+
from snowflake.snowpark._internal.analyzer.analyzer_utils import (
|
|
25
|
+
quote_name_without_upper_casing,
|
|
26
|
+
unquote_if_quoted,
|
|
27
|
+
)
|
|
28
|
+
from snowflake.snowpark._internal.type_utils import convert_sp_to_sf_type
|
|
29
|
+
from snowflake.snowpark._internal.utils import is_sql_select_statement
|
|
30
|
+
from snowflake.snowpark.functions import when_matched, when_not_matched
|
|
31
|
+
from snowflake.snowpark_connect.config import (
|
|
32
|
+
auto_uppercase_ddl,
|
|
33
|
+
get_boolean_session_config_param,
|
|
34
|
+
global_config,
|
|
35
|
+
set_config_param,
|
|
36
|
+
unset_config_param,
|
|
37
|
+
)
|
|
38
|
+
from snowflake.snowpark_connect.expression.map_expression import (
|
|
39
|
+
ColumnNameMap,
|
|
40
|
+
map_single_column_expression,
|
|
41
|
+
)
|
|
42
|
+
from snowflake.snowpark_connect.expression.typer import ExpressionTyper
|
|
43
|
+
from snowflake.snowpark_connect.relation.catalogs.utils import (
|
|
44
|
+
CURRENT_CATALOG_NAME,
|
|
45
|
+
_get_current_temp_objects,
|
|
46
|
+
)
|
|
47
|
+
from snowflake.snowpark_connect.relation.map_relation import (
|
|
48
|
+
NATURAL_JOIN_TYPE_BASE,
|
|
49
|
+
map_relation,
|
|
50
|
+
)
|
|
51
|
+
from snowflake.snowpark_connect.type_mapping import map_snowpark_to_pyspark_types
|
|
52
|
+
from snowflake.snowpark_connect.utils.context import (
|
|
53
|
+
_accessing_temp_object,
|
|
54
|
+
gen_sql_plan_id,
|
|
55
|
+
get_session_id,
|
|
56
|
+
push_evaluating_sql_scope,
|
|
57
|
+
push_sql_scope,
|
|
58
|
+
set_plan_id_map,
|
|
59
|
+
set_sql_args,
|
|
60
|
+
set_sql_plan_name,
|
|
61
|
+
)
|
|
62
|
+
from snowflake.snowpark_connect.utils.session import get_or_create_snowpark_session
|
|
63
|
+
from snowflake.snowpark_connect.utils.telemetry import (
|
|
64
|
+
SnowparkConnectNotImplementedError,
|
|
65
|
+
)
|
|
66
|
+
|
|
67
|
+
from .. import column_name_handler
|
|
68
|
+
from ..expression.map_sql_expression import (
|
|
69
|
+
_window_specs,
|
|
70
|
+
as_java_list,
|
|
71
|
+
as_java_map,
|
|
72
|
+
map_logical_plan_expression,
|
|
73
|
+
sql_parser,
|
|
74
|
+
)
|
|
75
|
+
|
|
76
|
+
_ctes = ContextVar[dict[str, relation_proto.Relation]]("_ctes", default={})
|
|
77
|
+
|
|
78
|
+
|
|
79
|
+
def _is_sql_select_statement_helper(sql_string: str) -> bool:
|
|
80
|
+
"""
|
|
81
|
+
Determine if a SQL string is a SELECT or CTE query statement, even when it starts with comments or whitespace.
|
|
82
|
+
"""
|
|
83
|
+
if not sql_string:
|
|
84
|
+
return False
|
|
85
|
+
|
|
86
|
+
trimmed = sql_string.lstrip()
|
|
87
|
+
|
|
88
|
+
while trimmed:
|
|
89
|
+
if trimmed.startswith("--"):
|
|
90
|
+
newline_pos = trimmed.find("\n")
|
|
91
|
+
if newline_pos == -1:
|
|
92
|
+
return False
|
|
93
|
+
trimmed = trimmed[newline_pos + 1 :].lstrip()
|
|
94
|
+
continue
|
|
95
|
+
elif trimmed.startswith("/*"):
|
|
96
|
+
end_pos = trimmed.find("*/")
|
|
97
|
+
if end_pos == -1:
|
|
98
|
+
return False
|
|
99
|
+
trimmed = trimmed[end_pos + 2 :].lstrip()
|
|
100
|
+
continue
|
|
101
|
+
break
|
|
102
|
+
|
|
103
|
+
if not trimmed:
|
|
104
|
+
return False
|
|
105
|
+
|
|
106
|
+
return is_sql_select_statement(trimmed)
|
|
107
|
+
|
|
108
|
+
|
|
109
|
+
@contextmanager
|
|
110
|
+
def _push_cte_scope():
|
|
111
|
+
"""
|
|
112
|
+
Creates a new CTE scope when evaluating nested WITH clauses.
|
|
113
|
+
"""
|
|
114
|
+
cur = _ctes.get()
|
|
115
|
+
token = _ctes.set(cur.copy())
|
|
116
|
+
try:
|
|
117
|
+
yield
|
|
118
|
+
finally:
|
|
119
|
+
_ctes.reset(token)
|
|
120
|
+
|
|
121
|
+
|
|
122
|
+
@contextmanager
|
|
123
|
+
def _push_window_specs_scope():
|
|
124
|
+
"""
|
|
125
|
+
Creates a new window specs scope when evaluating nested clauses.
|
|
126
|
+
"""
|
|
127
|
+
cur = _window_specs.get()
|
|
128
|
+
token = _window_specs.set(cur.copy())
|
|
129
|
+
try:
|
|
130
|
+
yield
|
|
131
|
+
finally:
|
|
132
|
+
_window_specs.reset(token)
|
|
133
|
+
|
|
134
|
+
|
|
135
|
+
def _find_pos_args(node, positions: list[int]):
|
|
136
|
+
if str(node.nodeName()) == "PosParameter":
|
|
137
|
+
positions.append(node.pos())
|
|
138
|
+
else:
|
|
139
|
+
for child in as_java_list(node.children()):
|
|
140
|
+
_find_pos_args(child, positions)
|
|
141
|
+
if hasattr(node, "expressions"):
|
|
142
|
+
for child in as_java_list(node.expressions()):
|
|
143
|
+
_find_pos_args(child, positions)
|
|
144
|
+
|
|
145
|
+
|
|
146
|
+
def parse_pos_args(
|
|
147
|
+
logical_plan,
|
|
148
|
+
pos_args: MutableSequence[expressions_proto.Expression.Literal],
|
|
149
|
+
) -> dict[int, expressions_proto.Expression]:
|
|
150
|
+
# Spark Connect gives us positional parameters as a regular list,
|
|
151
|
+
# while Spark parser refers to them by their character indexes in the query.
|
|
152
|
+
# Therefore, we need to find all positional parameters, sort their locations,
|
|
153
|
+
# and match them to the list from Spark Connect.
|
|
154
|
+
if not pos_args:
|
|
155
|
+
return {}
|
|
156
|
+
|
|
157
|
+
positions: list[int] = []
|
|
158
|
+
_find_pos_args(logical_plan, positions)
|
|
159
|
+
return dict(zip(sorted(positions), pos_args))
|
|
160
|
+
|
|
161
|
+
|
|
162
|
+
def execute_logical_plan(logical_plan) -> snowpark.DataFrame:
|
|
163
|
+
proto = map_logical_plan_relation(logical_plan)
|
|
164
|
+
with push_evaluating_sql_scope():
|
|
165
|
+
return map_relation(proto)
|
|
166
|
+
|
|
167
|
+
|
|
168
|
+
def _spark_to_snowflake_single_id(name: str) -> str:
|
|
169
|
+
name = quote_name_without_upper_casing(name)
|
|
170
|
+
return name.upper() if auto_uppercase_ddl() else name
|
|
171
|
+
|
|
172
|
+
|
|
173
|
+
def _spark_to_snowflake(multipart_id: jpype.JObject) -> str:
|
|
174
|
+
return ".".join(
|
|
175
|
+
_spark_to_snowflake_single_id(str(part)) for part in as_java_list(multipart_id)
|
|
176
|
+
)
|
|
177
|
+
|
|
178
|
+
|
|
179
|
+
def _rename_columns(
|
|
180
|
+
df: snowpark.DataFrame, user_specified_columns
|
|
181
|
+
) -> snowpark.DataFrame:
|
|
182
|
+
user_columns = [str(col._1()) for col in as_java_list(user_specified_columns)]
|
|
183
|
+
|
|
184
|
+
if user_columns:
|
|
185
|
+
columns = zip(df.columns, user_columns)
|
|
186
|
+
else:
|
|
187
|
+
columns = df._column_map.snowpark_to_spark_map().items()
|
|
188
|
+
|
|
189
|
+
for orig_column, user_column in columns:
|
|
190
|
+
df = df.with_column_renamed(
|
|
191
|
+
orig_column, _spark_to_snowflake_single_id(user_column)
|
|
192
|
+
)
|
|
193
|
+
|
|
194
|
+
return df
|
|
195
|
+
|
|
196
|
+
|
|
197
|
+
def _create_table_as_select(logical_plan, mode: str) -> None:
|
|
198
|
+
# TODO: for as select create tables we'd map multi layer identifier here
|
|
199
|
+
name = get_relation_identifier_name(logical_plan.name())
|
|
200
|
+
comment = logical_plan.tableSpec().comment()
|
|
201
|
+
|
|
202
|
+
df = execute_logical_plan(logical_plan.query())
|
|
203
|
+
columns = df._column_map.snowpark_to_spark_map().items()
|
|
204
|
+
for orig_column, user_column in columns:
|
|
205
|
+
df = df.with_column_renamed(
|
|
206
|
+
orig_column, _spark_to_snowflake_single_id(user_column)
|
|
207
|
+
)
|
|
208
|
+
|
|
209
|
+
# TODO escaping should be handled by snowpark. remove when SNOW-2210271 is done
|
|
210
|
+
def _escape(comment: str) -> str:
|
|
211
|
+
return comment.replace("\\", "\\\\")
|
|
212
|
+
|
|
213
|
+
df.write.save_as_table(
|
|
214
|
+
name,
|
|
215
|
+
comment=None if comment.isEmpty() else _escape(comment.get()),
|
|
216
|
+
mode=mode,
|
|
217
|
+
)
|
|
218
|
+
|
|
219
|
+
|
|
220
|
+
def _spark_field_to_sql(field: jpype.JObject, is_column: bool) -> str:
|
|
221
|
+
# Column names will be uppercased according to "snowpark.connect.auto-uppercase.ddl",
|
|
222
|
+
# and struct fields will be left as is. This should allow users to use the same names
|
|
223
|
+
# in spark and Snowflake in most cases.
|
|
224
|
+
if is_column:
|
|
225
|
+
name = _spark_to_snowflake_single_id(str(field.name()))
|
|
226
|
+
else:
|
|
227
|
+
name = quote_name_without_upper_casing(str(field.name()))
|
|
228
|
+
data_type_str = _spark_datatype_to_sql(field.dataType())
|
|
229
|
+
# TODO: Support comments
|
|
230
|
+
return f"{name} {data_type_str}"
|
|
231
|
+
|
|
232
|
+
|
|
233
|
+
def _spark_datatype_to_sql(data_type: jpype.JObject) -> str:
|
|
234
|
+
match data_type.typeName():
|
|
235
|
+
case "array":
|
|
236
|
+
element_type_str = _spark_datatype_to_sql(data_type.elementType())
|
|
237
|
+
return f"ARRAY({element_type_str})"
|
|
238
|
+
case "map":
|
|
239
|
+
key_type_str = _spark_datatype_to_sql(data_type.keyType())
|
|
240
|
+
value_type_str = _spark_datatype_to_sql(data_type.valueType())
|
|
241
|
+
return f"MAP({key_type_str}, {value_type_str})"
|
|
242
|
+
case "struct":
|
|
243
|
+
field_types_str = ", ".join(
|
|
244
|
+
_spark_field_to_sql(f, False) for f in data_type.fields()
|
|
245
|
+
)
|
|
246
|
+
return f"OBJECT({field_types_str})"
|
|
247
|
+
case _:
|
|
248
|
+
return data_type.sql()
|
|
249
|
+
|
|
250
|
+
|
|
251
|
+
def _normalize_identifiers(node):
|
|
252
|
+
"""
|
|
253
|
+
Fix spark-quoted identifiers parsed with sqlglot.
|
|
254
|
+
|
|
255
|
+
sqlglot detects quoted spark identifiers which makes them quoted in the Snowflake SQL string.
|
|
256
|
+
This behaviour is not consistent with Spark, where non-column identifiers are case insensitive.
|
|
257
|
+
The identifiers need to be uppercased to match Snowflake's behaviour. Users can disable this by setting
|
|
258
|
+
the `snowpark.connect.auto_uppercase_ddl` config to False.
|
|
259
|
+
"""
|
|
260
|
+
if isinstance(node, Identifier):
|
|
261
|
+
fixed = node.this.upper() if auto_uppercase_ddl() else node.this
|
|
262
|
+
return Identifier(this=fixed, quoted=True)
|
|
263
|
+
return node
|
|
264
|
+
|
|
265
|
+
|
|
266
|
+
def _remove_file_format_property(node):
|
|
267
|
+
"""
|
|
268
|
+
Fix spark-quoted identifiers parsed with sqlglot.
|
|
269
|
+
|
|
270
|
+
sqlglot detects quoted spark identifiers which makes them quoted in the Snowflake SQL string.
|
|
271
|
+
This behaviour is not consistent with Spark, where non-column identifiers are case insensitive.
|
|
272
|
+
The identifiers need to be uppercased to match Snowflake's behaviour. Users can disable this by setting
|
|
273
|
+
the `snowpark.connect.auto_uppercase_ddl` config to False.
|
|
274
|
+
"""
|
|
275
|
+
if isinstance(node, FileFormatProperty):
|
|
276
|
+
return None
|
|
277
|
+
return node
|
|
278
|
+
|
|
279
|
+
|
|
280
|
+
def _remove_column_data_type(node):
|
|
281
|
+
"""
|
|
282
|
+
Fix spark-quoted identifiers parsed with sqlglot.
|
|
283
|
+
|
|
284
|
+
sqlglot detects quoted spark identifiers which makes them quoted in the Snowflake SQL string.
|
|
285
|
+
This behaviour is not consistent with Spark, where non-column identifiers are case insensitive.
|
|
286
|
+
The identifiers need to be uppercased to match Snowflake's behaviour. Users can disable this by setting
|
|
287
|
+
the `snowpark.connect.auto_uppercase_ddl` config to False.
|
|
288
|
+
"""
|
|
289
|
+
if isinstance(node, DataType) and isinstance(node.parent, ColumnDef):
|
|
290
|
+
return None
|
|
291
|
+
return node
|
|
292
|
+
|
|
293
|
+
|
|
294
|
+
def map_sql_to_pandas_df(
|
|
295
|
+
sql_string: str,
|
|
296
|
+
named_args: MutableMapping[str, expressions_proto.Expression.Literal],
|
|
297
|
+
pos_args: MutableSequence[expressions_proto.Expression.Literal],
|
|
298
|
+
) -> tuple[pandas.DataFrame, str] | tuple[None, None]:
|
|
299
|
+
"""
|
|
300
|
+
Convert a sql string into a pandas DataFrame and its json schema.
|
|
301
|
+
returns a tuple of empty Pandas DataFrame and schema string in case of DDL statements.
|
|
302
|
+
returns a tuple of None for SELECT queries to enable lazy evaluation
|
|
303
|
+
"""
|
|
304
|
+
|
|
305
|
+
snowpark_connect_sql_passthrough = get_sql_passthrough()
|
|
306
|
+
|
|
307
|
+
if not snowpark_connect_sql_passthrough:
|
|
308
|
+
logical_plan = sql_parser().parsePlan(sql_string)
|
|
309
|
+
parsed_pos_args = parse_pos_args(logical_plan, pos_args)
|
|
310
|
+
set_sql_args(named_args, parsed_pos_args)
|
|
311
|
+
|
|
312
|
+
session = get_or_create_snowpark_session()
|
|
313
|
+
|
|
314
|
+
rows: list | None = None
|
|
315
|
+
|
|
316
|
+
while (
|
|
317
|
+
class_name := str(logical_plan.getClass().getSimpleName())
|
|
318
|
+
) == "UnresolvedHint":
|
|
319
|
+
logical_plan = logical_plan.child()
|
|
320
|
+
|
|
321
|
+
match class_name:
|
|
322
|
+
case "AddColumns":
|
|
323
|
+
# Handle ALTER TABLE ... ADD COLUMNS (col_name data_type) -> ADD COLUMN col_name data_type
|
|
324
|
+
table_name = get_relation_identifier_name(logical_plan.table(), True)
|
|
325
|
+
|
|
326
|
+
# Get column definitions from logical plan
|
|
327
|
+
columns_to_add = logical_plan.columnsToAdd()
|
|
328
|
+
# Build Snowflake SQL from logical plan attributes
|
|
329
|
+
for col in as_java_list(columns_to_add):
|
|
330
|
+
# Follow the same pattern as AlterColumn for column name extraction
|
|
331
|
+
col_name = ".".join(str(part) for part in as_java_list(col.name()))
|
|
332
|
+
col_type = _spark_datatype_to_sql(col.dataType())
|
|
333
|
+
snowflake_sql = (
|
|
334
|
+
f"ALTER TABLE {table_name} ADD COLUMN {col_name} {col_type}"
|
|
335
|
+
)
|
|
336
|
+
session.sql(snowflake_sql).collect()
|
|
337
|
+
case "AlterColumn":
|
|
338
|
+
# Handle ALTER TABLE ... CHANGE COLUMN (translate to ALTER TABLE ... ALTER COLUMN)
|
|
339
|
+
table_name = get_relation_identifier_name(logical_plan.table(), True)
|
|
340
|
+
column_obj = logical_plan.column()
|
|
341
|
+
|
|
342
|
+
# Extract actual column name
|
|
343
|
+
column_name = ".".join(
|
|
344
|
+
str(part) for part in as_java_list(column_obj.name())
|
|
345
|
+
)
|
|
346
|
+
|
|
347
|
+
# Build ALTER COLUMN command from logical plan attributes
|
|
348
|
+
alter_parts = []
|
|
349
|
+
|
|
350
|
+
# Check for comment change - Scala Some() vs None
|
|
351
|
+
comment_obj = logical_plan.comment()
|
|
352
|
+
if (
|
|
353
|
+
comment_obj is not None
|
|
354
|
+
and str(comment_obj.getClass().getSimpleName()) == "Some"
|
|
355
|
+
):
|
|
356
|
+
comment = _escape_sql_comment(str(comment_obj.get()))
|
|
357
|
+
alter_parts.append(f"COMMENT '{comment}'")
|
|
358
|
+
|
|
359
|
+
# Check for dataType change - handle Scala Some/None
|
|
360
|
+
data_type_obj = logical_plan.dataType()
|
|
361
|
+
if (
|
|
362
|
+
data_type_obj is not None
|
|
363
|
+
and str(data_type_obj.getClass().getSimpleName()) == "Some"
|
|
364
|
+
):
|
|
365
|
+
# Extract the actual data type from Scala Some()
|
|
366
|
+
actual_data_type = data_type_obj.get()
|
|
367
|
+
data_type = _spark_datatype_to_sql(actual_data_type)
|
|
368
|
+
alter_parts.append(f"TYPE {data_type}")
|
|
369
|
+
|
|
370
|
+
if alter_parts:
|
|
371
|
+
alter_clause = ", ".join(alter_parts)
|
|
372
|
+
snowflake_sql = f"ALTER TABLE {table_name} ALTER COLUMN {column_name} {alter_clause}"
|
|
373
|
+
session.sql(snowflake_sql).collect()
|
|
374
|
+
else:
|
|
375
|
+
raise ValueError(
|
|
376
|
+
f"No alter operations found in AlterColumn logical plan for table {table_name}, column {column_name}"
|
|
377
|
+
)
|
|
378
|
+
case "CreateNamespace":
|
|
379
|
+
name = get_relation_identifier_name(logical_plan.name(), True)
|
|
380
|
+
previous_name = session.connection.schema
|
|
381
|
+
if_not_exists = "IF NOT EXISTS " if logical_plan.ifNotExists() else ""
|
|
382
|
+
session.sql(f"CREATE SCHEMA {if_not_exists}{name}").collect()
|
|
383
|
+
if previous_name is not None:
|
|
384
|
+
session.sql(
|
|
385
|
+
f"USE SCHEMA {_spark_to_snowflake_single_id(previous_name)}"
|
|
386
|
+
).collect()
|
|
387
|
+
else:
|
|
388
|
+
# TODO: Unset the schema
|
|
389
|
+
pass
|
|
390
|
+
case "CreateTable":
|
|
391
|
+
name = get_relation_identifier_name(logical_plan.name())
|
|
392
|
+
columns = ", ".join(
|
|
393
|
+
_spark_field_to_sql(f, True)
|
|
394
|
+
for f in logical_plan.tableSchema().fields()
|
|
395
|
+
)
|
|
396
|
+
if_not_exists = (
|
|
397
|
+
"IF NOT EXISTS " if logical_plan.ignoreIfExists() else ""
|
|
398
|
+
)
|
|
399
|
+
comment_opt = logical_plan.tableSpec().comment()
|
|
400
|
+
comment = (
|
|
401
|
+
f"COMMENT = '{_escape_sql_comment(str(comment_opt.get()))}'"
|
|
402
|
+
if comment_opt.isDefined()
|
|
403
|
+
else ""
|
|
404
|
+
)
|
|
405
|
+
# NOTE: We are intentionally ignoring any FORMAT=... parameters here.
|
|
406
|
+
session.sql(
|
|
407
|
+
f"CREATE TABLE {if_not_exists}{name} ({columns}) {comment}"
|
|
408
|
+
).collect()
|
|
409
|
+
case "CreateTableAsSelect":
|
|
410
|
+
mode = "ignore" if logical_plan.ignoreIfExists() else "errorifexists"
|
|
411
|
+
_create_table_as_select(logical_plan, mode=mode)
|
|
412
|
+
case "CreateTableLikeCommand":
|
|
413
|
+
source = get_relation_identifier_name(logical_plan.sourceTable())
|
|
414
|
+
name = get_relation_identifier_name(logical_plan.targetTable())
|
|
415
|
+
if_not_exists = "IF NOT EXISTS " if logical_plan.ifNotExists() else ""
|
|
416
|
+
session.sql(
|
|
417
|
+
f"CREATE TABLE {if_not_exists}{name} LIKE {source}"
|
|
418
|
+
).collect()
|
|
419
|
+
case "CreateTempViewUsing":
|
|
420
|
+
empty_select = (
|
|
421
|
+
" AS SELECT * WHERE 1 = 0"
|
|
422
|
+
if logical_plan.options().isEmpty()
|
|
423
|
+
and logical_plan.children().isEmpty()
|
|
424
|
+
else ""
|
|
425
|
+
)
|
|
426
|
+
parsed_sql = (
|
|
427
|
+
sqlglot.parse_one(sql_string, dialect="spark")
|
|
428
|
+
.transform(_normalize_identifiers)
|
|
429
|
+
.transform(_remove_column_data_type)
|
|
430
|
+
.transform(_remove_file_format_property)
|
|
431
|
+
)
|
|
432
|
+
snowflake_sql = parsed_sql.sql(dialect="snowflake")
|
|
433
|
+
session.sql(f"{snowflake_sql}{empty_select}").collect()
|
|
434
|
+
case "CreateView":
|
|
435
|
+
current_schema = session.connection.schema
|
|
436
|
+
if (
|
|
437
|
+
str(logical_plan.child().getClass().getSimpleName())
|
|
438
|
+
== "PlanWithUnresolvedIdentifier"
|
|
439
|
+
):
|
|
440
|
+
object_name: str = str(
|
|
441
|
+
logical_plan.child().identifierExpr().value()
|
|
442
|
+
)
|
|
443
|
+
else:
|
|
444
|
+
object_name: str = as_java_list(logical_plan.child().nameParts())[0]
|
|
445
|
+
_accessing_temp_object.set(False)
|
|
446
|
+
df = execute_logical_plan(logical_plan.query())
|
|
447
|
+
if _accessing_temp_object.get():
|
|
448
|
+
raise AnalysisException(
|
|
449
|
+
f"[INVALID_TEMP_OBJ_REFERENCE] Cannot create the persistent object `{CURRENT_CATALOG_NAME}`.`{current_schema}`.`{object_name}` "
|
|
450
|
+
"of the type VIEW because it references to a temporary object of the type VIEW. Please "
|
|
451
|
+
f"make the temporary object persistent, or make the persistent object `{CURRENT_CATALOG_NAME}`.`{current_schema}`.`{object_name}` temporary."
|
|
452
|
+
)
|
|
453
|
+
|
|
454
|
+
name = get_relation_identifier_name(logical_plan.child())
|
|
455
|
+
comment = logical_plan.comment()
|
|
456
|
+
|
|
457
|
+
df = _rename_columns(df, logical_plan.userSpecifiedColumns())
|
|
458
|
+
|
|
459
|
+
# TODO: Support logical_plan.replace() == False
|
|
460
|
+
df.create_or_replace_view(
|
|
461
|
+
name,
|
|
462
|
+
comment=_escape_sql_comment(str(comment.get()))
|
|
463
|
+
if comment.isDefined()
|
|
464
|
+
else None,
|
|
465
|
+
)
|
|
466
|
+
case "CreateViewCommand":
|
|
467
|
+
df = execute_logical_plan(logical_plan.plan())
|
|
468
|
+
tmp_views = _get_current_temp_objects()
|
|
469
|
+
tmp_views.add(
|
|
470
|
+
(
|
|
471
|
+
CURRENT_CATALOG_NAME,
|
|
472
|
+
session.connection.schema,
|
|
473
|
+
str(logical_plan.name().identifier()),
|
|
474
|
+
)
|
|
475
|
+
)
|
|
476
|
+
|
|
477
|
+
name = str(logical_plan.name().identifier())
|
|
478
|
+
name = _spark_to_snowflake_single_id(name)
|
|
479
|
+
if isinstance(
|
|
480
|
+
logical_plan.viewType(),
|
|
481
|
+
jpype.JClass(
|
|
482
|
+
"org.apache.spark.sql.catalyst.analysis.GlobalTempView$"
|
|
483
|
+
),
|
|
484
|
+
):
|
|
485
|
+
name = f"{global_config.spark_sql_globalTempDatabase}.{name}"
|
|
486
|
+
comment = logical_plan.comment()
|
|
487
|
+
maybe_comment = (
|
|
488
|
+
_escape_sql_comment(str(comment.get()))
|
|
489
|
+
if comment.isDefined()
|
|
490
|
+
else None
|
|
491
|
+
)
|
|
492
|
+
|
|
493
|
+
df = _rename_columns(df, logical_plan.userSpecifiedColumns())
|
|
494
|
+
|
|
495
|
+
if logical_plan.replace():
|
|
496
|
+
df.create_or_replace_temp_view(
|
|
497
|
+
name,
|
|
498
|
+
comment=maybe_comment,
|
|
499
|
+
)
|
|
500
|
+
else:
|
|
501
|
+
df.create_temp_view(
|
|
502
|
+
name,
|
|
503
|
+
comment=maybe_comment,
|
|
504
|
+
)
|
|
505
|
+
case "DescribeColumn":
|
|
506
|
+
name = get_relation_identifier_name(logical_plan.column())
|
|
507
|
+
rows = session.sql(f"DESCRIBE TABLE {name}").collect()
|
|
508
|
+
case "DescribeNamespace":
|
|
509
|
+
name = get_relation_identifier_name(logical_plan.namespace(), True)
|
|
510
|
+
rows = session.sql(f"DESCRIBE SCHEMA {name}").collect()
|
|
511
|
+
if not rows:
|
|
512
|
+
rows = None
|
|
513
|
+
case "DescribeRelation":
|
|
514
|
+
name = get_relation_identifier_name(logical_plan.relation(), True)
|
|
515
|
+
rows = session.sql(f"DESCRIBE TABLE {name}").collect()
|
|
516
|
+
if not rows:
|
|
517
|
+
rows = None
|
|
518
|
+
case "DescribeQueryCommand":
|
|
519
|
+
# Handle DESCRIBE QUERY <sql> commands
|
|
520
|
+
# Since Snowflake doesn't support DESCRIBE QUERY syntax, we use DataFrame schema analysis
|
|
521
|
+
# This gets the schema without executing the query (similar to Spark's DESCRIBE QUERY)
|
|
522
|
+
# Get the inner query plan and convert it to SQL
|
|
523
|
+
inner_query_plan = logical_plan.plan()
|
|
524
|
+
df = execute_logical_plan(inner_query_plan)
|
|
525
|
+
schema = df.schema
|
|
526
|
+
|
|
527
|
+
# Get original Spark column names using the column map from the original DataFrame
|
|
528
|
+
spark_columns = df._column_map.get_spark_columns()
|
|
529
|
+
data = []
|
|
530
|
+
for i, field in enumerate(schema.fields):
|
|
531
|
+
# Use original Spark column name from column map
|
|
532
|
+
col_name = spark_columns[i]
|
|
533
|
+
|
|
534
|
+
# Convert Snowpark data type to PySpark data type and get simpleString
|
|
535
|
+
pyspark_type = map_snowpark_to_pyspark_types(field.datatype)
|
|
536
|
+
data_type_str = pyspark_type.simpleString()
|
|
537
|
+
|
|
538
|
+
data.append(
|
|
539
|
+
{
|
|
540
|
+
"col_name": col_name,
|
|
541
|
+
"data_type": data_type_str,
|
|
542
|
+
"comment": None, # Snowflake schema doesn't include comments
|
|
543
|
+
}
|
|
544
|
+
)
|
|
545
|
+
return pandas.DataFrame(data), ""
|
|
546
|
+
case "DropFunctionCommand":
|
|
547
|
+
func_name = logical_plan.identifier().funcName().lower()
|
|
548
|
+
input_types, snowpark_name = [], ""
|
|
549
|
+
if func_name in session._udfs:
|
|
550
|
+
input_types, snowpark_name = (
|
|
551
|
+
session._udfs[func_name].input_types,
|
|
552
|
+
session._udfs[func_name].name,
|
|
553
|
+
)
|
|
554
|
+
del session._udfs[func_name]
|
|
555
|
+
elif func_name in session._udtfs:
|
|
556
|
+
input_types, snowpark_name = (
|
|
557
|
+
session._udtfs[func_name][0].input_types,
|
|
558
|
+
session._udtfs[func_name][0].name,
|
|
559
|
+
)
|
|
560
|
+
del session._udtfs[func_name]
|
|
561
|
+
else:
|
|
562
|
+
if not logical_plan.ifExists():
|
|
563
|
+
raise ValueError(
|
|
564
|
+
f"Function {func_name} not found among registered UDFs or UDTFs."
|
|
565
|
+
)
|
|
566
|
+
if snowpark_name != "":
|
|
567
|
+
argument_string = f"({', '.join(convert_sp_to_sf_type(arg) for arg in input_types)})"
|
|
568
|
+
session.sql(
|
|
569
|
+
f"DROP FUNCTION {'IF EXISTS' if logical_plan.ifExists() else ''} {snowpark_name}{argument_string}"
|
|
570
|
+
).collect()
|
|
571
|
+
case "DropNamespace":
|
|
572
|
+
name = get_relation_identifier_name(logical_plan.namespace(), True)
|
|
573
|
+
if_exists = "IF EXISTS " if logical_plan.ifExists() else ""
|
|
574
|
+
session.sql(f"DROP SCHEMA {if_exists}{name}").collect()
|
|
575
|
+
case "DropTable":
|
|
576
|
+
name = get_relation_identifier_name(logical_plan.child())
|
|
577
|
+
if_exists = "IF EXISTS " if logical_plan.ifExists() else ""
|
|
578
|
+
session.sql(f"DROP TABLE {if_exists}{name}").collect()
|
|
579
|
+
case "DropView":
|
|
580
|
+
name = get_relation_identifier_name(logical_plan.child())
|
|
581
|
+
if_exists = "IF EXISTS " if logical_plan.ifExists() else ""
|
|
582
|
+
session.sql(f"DROP VIEW {if_exists}{name}").collect()
|
|
583
|
+
case "ExplainCommand":
|
|
584
|
+
inner_plan = logical_plan.logicalPlan()
|
|
585
|
+
logical_plan_name = inner_plan.nodeName()
|
|
586
|
+
|
|
587
|
+
# Handle EXPLAIN DESCRIBE QUERY commands
|
|
588
|
+
if logical_plan_name == "DescribeQueryCommand":
|
|
589
|
+
# For EXPLAIN DESCRIBE QUERY, we should return an explanation of the describe operation itself
|
|
590
|
+
# NOT execute the inner query to get its SQL
|
|
591
|
+
query_plan = inner_plan.plan()
|
|
592
|
+
plan_description = (
|
|
593
|
+
f"Describe query plan for: {query_plan.nodeName()}"
|
|
594
|
+
)
|
|
595
|
+
rows = [snowpark.Row(plan=plan_description)]
|
|
596
|
+
elif logical_plan_name == "DescribeRelation":
|
|
597
|
+
# For EXPLAIN DESCRIBE RELATION, we should return an explanation of the describe operation itself
|
|
598
|
+
# NOT execute the inner query to get its SQL
|
|
599
|
+
relation = inner_plan.relation()
|
|
600
|
+
plan_description = (
|
|
601
|
+
f"Describe relation plan for: {relation.commandName()}"
|
|
602
|
+
)
|
|
603
|
+
rows = [snowpark.Row(plan=plan_description)]
|
|
604
|
+
elif logical_plan_name == "DescribeColumn":
|
|
605
|
+
# For EXPLAIN DESCRIBE COLUMN, we should return an explanation of the describe operation itself
|
|
606
|
+
# NOT execute the inner query to get its SQL
|
|
607
|
+
column = inner_plan.column()
|
|
608
|
+
plan_description = f"Describe column plan for: [{column.name()}]"
|
|
609
|
+
rows = [snowpark.Row(plan=plan_description)]
|
|
610
|
+
elif logical_plan_name in (
|
|
611
|
+
"Project",
|
|
612
|
+
"Aggregate",
|
|
613
|
+
"Sort",
|
|
614
|
+
"UnresolvedWith",
|
|
615
|
+
"UnresolvedHaving",
|
|
616
|
+
"Distinct",
|
|
617
|
+
):
|
|
618
|
+
expr = execute_logical_plan(logical_plan.logicalPlan()).queries[
|
|
619
|
+
"queries"
|
|
620
|
+
][0]
|
|
621
|
+
final_sql = f"EXPLAIN USING TEXT {expr}"
|
|
622
|
+
rows = session.sql(final_sql).collect()
|
|
623
|
+
elif (
|
|
624
|
+
logical_plan_name == "InsertIntoStatement"
|
|
625
|
+
or logical_plan_name == "CreateView"
|
|
626
|
+
):
|
|
627
|
+
expr = execute_logical_plan(
|
|
628
|
+
logical_plan.logicalPlan().query()
|
|
629
|
+
).queries["queries"][0]
|
|
630
|
+
final_sql = f"EXPLAIN USING TEXT {expr}"
|
|
631
|
+
rows = session.sql(final_sql).collect()
|
|
632
|
+
else:
|
|
633
|
+
# TODO: Support other logical plans
|
|
634
|
+
raise SnowparkConnectNotImplementedError(
|
|
635
|
+
f"{logical_plan_name} is not supported yet with EXPLAIN."
|
|
636
|
+
)
|
|
637
|
+
case "InsertIntoStatement":
|
|
638
|
+
df = execute_logical_plan(logical_plan.query())
|
|
639
|
+
queries = df.queries["queries"]
|
|
640
|
+
if len(queries) != 1:
|
|
641
|
+
raise SnowparkConnectNotImplementedError(
|
|
642
|
+
f"Unexpected number of queries: {len(queries)}"
|
|
643
|
+
)
|
|
644
|
+
|
|
645
|
+
name = get_relation_identifier_name(logical_plan.table(), True)
|
|
646
|
+
|
|
647
|
+
user_columns = [
|
|
648
|
+
_spark_to_snowflake_single_id(str(col))
|
|
649
|
+
for col in as_java_list(logical_plan.userSpecifiedCols())
|
|
650
|
+
]
|
|
651
|
+
overwrite_str = "OVERWRITE" if logical_plan.overwrite() else ""
|
|
652
|
+
cols_str = "(" + ", ".join(user_columns) + ")" if user_columns else ""
|
|
653
|
+
|
|
654
|
+
try:
|
|
655
|
+
target_table = session.table(name)
|
|
656
|
+
target_schema = target_table.schema
|
|
657
|
+
|
|
658
|
+
# Modify df with NaN → NULL conversion for DECIMAL columns
|
|
659
|
+
modified_columns = []
|
|
660
|
+
for source_field, target_field in zip(
|
|
661
|
+
df.schema.fields, target_schema.fields
|
|
662
|
+
):
|
|
663
|
+
col_name = source_field.name
|
|
664
|
+
if isinstance(
|
|
665
|
+
target_field.datatype, snowpark.types.DecimalType
|
|
666
|
+
) and isinstance(
|
|
667
|
+
source_field.datatype,
|
|
668
|
+
(snowpark.types.FloatType, snowpark.types.DoubleType),
|
|
669
|
+
):
|
|
670
|
+
# Add CASE WHEN to convert NaN to NULL for DECIMAL targets
|
|
671
|
+
# Only apply this to floating-point source columns
|
|
672
|
+
modified_col = (
|
|
673
|
+
snowpark_fn.when(
|
|
674
|
+
snowpark_fn.equal_nan(snowpark_fn.col(col_name)),
|
|
675
|
+
snowpark_fn.lit(None),
|
|
676
|
+
)
|
|
677
|
+
.otherwise(snowpark_fn.col(col_name))
|
|
678
|
+
.alias(col_name)
|
|
679
|
+
)
|
|
680
|
+
modified_columns.append(modified_col)
|
|
681
|
+
else:
|
|
682
|
+
modified_columns.append(snowpark_fn.col(col_name))
|
|
683
|
+
|
|
684
|
+
df = df.select(modified_columns)
|
|
685
|
+
except Exception:
|
|
686
|
+
pass
|
|
687
|
+
queries = df.queries["queries"]
|
|
688
|
+
final_query = queries[0]
|
|
689
|
+
session.sql(
|
|
690
|
+
f"INSERT {overwrite_str} INTO {name} {cols_str} {final_query}",
|
|
691
|
+
).collect()
|
|
692
|
+
case "MergeIntoTable":
|
|
693
|
+
|
|
694
|
+
def _get_condition_from_action(action, column_mapping, typer):
|
|
695
|
+
condition = None
|
|
696
|
+
if action.condition().isDefined():
|
|
697
|
+
(_, condition_typed_col,) = map_single_column_expression(
|
|
698
|
+
map_logical_plan_expression(
|
|
699
|
+
matched_action.condition().get()
|
|
700
|
+
),
|
|
701
|
+
column_mapping,
|
|
702
|
+
typer,
|
|
703
|
+
)
|
|
704
|
+
condition = condition_typed_col.col
|
|
705
|
+
return condition
|
|
706
|
+
|
|
707
|
+
def _get_assignments_from_action(
|
|
708
|
+
action,
|
|
709
|
+
column_mapping_source,
|
|
710
|
+
column_mapping_target,
|
|
711
|
+
typer_source,
|
|
712
|
+
typer_target,
|
|
713
|
+
):
|
|
714
|
+
assignments = dict()
|
|
715
|
+
if (
|
|
716
|
+
action.getClass().getSimpleName() == "InsertAction"
|
|
717
|
+
or action.getClass().getSimpleName() == "UpdateAction"
|
|
718
|
+
):
|
|
719
|
+
incoming_assignments = as_java_list(action.assignments())
|
|
720
|
+
for assignment in incoming_assignments:
|
|
721
|
+
(key_name, _) = map_single_column_expression(
|
|
722
|
+
map_logical_plan_expression(assignment.key()),
|
|
723
|
+
column_mapping=column_mapping_target,
|
|
724
|
+
typer=typer_source,
|
|
725
|
+
)
|
|
726
|
+
|
|
727
|
+
(_, val_typ_col) = map_single_column_expression(
|
|
728
|
+
map_logical_plan_expression(assignment.value()),
|
|
729
|
+
column_mapping=column_mapping_source,
|
|
730
|
+
typer=typer_target,
|
|
731
|
+
)
|
|
732
|
+
|
|
733
|
+
assignments[key_name] = val_typ_col.col
|
|
734
|
+
elif (
|
|
735
|
+
action.getClass().getSimpleName() == "InsertStarAction"
|
|
736
|
+
or action.getClass().getSimpleName() == "UpdateStarAction"
|
|
737
|
+
):
|
|
738
|
+
if len(column_mapping_source.columns) != len(
|
|
739
|
+
column_mapping_target.columns
|
|
740
|
+
):
|
|
741
|
+
raise ValueError(
|
|
742
|
+
"source and target must have the same number of columns for InsertStarAction or UpdateStarAction"
|
|
743
|
+
)
|
|
744
|
+
for i, col in enumerate(column_mapping_target.columns):
|
|
745
|
+
if assignments.get(col.snowpark_name) is not None:
|
|
746
|
+
raise SnowparkConnectNotImplementedError(
|
|
747
|
+
"UpdateStarAction or InsertStarAction is not supported with duplicate columns."
|
|
748
|
+
)
|
|
749
|
+
assignments[col.snowpark_name] = snowpark_fn.col(
|
|
750
|
+
column_mapping_source.columns[i].snowpark_name
|
|
751
|
+
)
|
|
752
|
+
return assignments
|
|
753
|
+
|
|
754
|
+
source_df = map_relation(
|
|
755
|
+
map_logical_plan_relation(logical_plan.sourceTable())
|
|
756
|
+
)
|
|
757
|
+
|
|
758
|
+
plan_id = gen_sql_plan_id()
|
|
759
|
+
|
|
760
|
+
target_df = map_relation(
|
|
761
|
+
map_logical_plan_relation(logical_plan.targetTable(), plan_id)
|
|
762
|
+
)
|
|
763
|
+
for col in target_df._column_map.columns:
|
|
764
|
+
target_df = target_df.with_column_renamed(
|
|
765
|
+
col.snowpark_name, _spark_to_snowflake_single_id(col.spark_name)
|
|
766
|
+
)
|
|
767
|
+
target_df = column_name_handler.with_column_map(
|
|
768
|
+
target_df, target_df.columns, target_df.columns
|
|
769
|
+
)
|
|
770
|
+
|
|
771
|
+
set_plan_id_map(plan_id, target_df)
|
|
772
|
+
|
|
773
|
+
joined_df_before_condition: snowpark.DataFrame = source_df.join(
|
|
774
|
+
target_df
|
|
775
|
+
)
|
|
776
|
+
|
|
777
|
+
column_mapping_for_conditions = column_name_handler.JoinColumnNameMap(
|
|
778
|
+
source_df,
|
|
779
|
+
target_df,
|
|
780
|
+
)
|
|
781
|
+
typer_for_expressions = ExpressionTyper(joined_df_before_condition)
|
|
782
|
+
|
|
783
|
+
(_, merge_condition_typed_col,) = map_single_column_expression(
|
|
784
|
+
map_logical_plan_expression(logical_plan.mergeCondition()),
|
|
785
|
+
column_mapping=column_mapping_for_conditions,
|
|
786
|
+
typer=typer_for_expressions,
|
|
787
|
+
)
|
|
788
|
+
|
|
789
|
+
clauses = []
|
|
790
|
+
|
|
791
|
+
for matched_action in as_java_list(logical_plan.matchedActions()):
|
|
792
|
+
condition = _get_condition_from_action(
|
|
793
|
+
matched_action,
|
|
794
|
+
column_mapping_for_conditions,
|
|
795
|
+
typer_for_expressions,
|
|
796
|
+
)
|
|
797
|
+
if matched_action.getClass().getSimpleName() == "DeleteAction":
|
|
798
|
+
clauses.append(when_matched(condition).delete())
|
|
799
|
+
elif (
|
|
800
|
+
matched_action.getClass().getSimpleName() == "UpdateAction"
|
|
801
|
+
or matched_action.getClass().getSimpleName()
|
|
802
|
+
== "UpdateStarAction"
|
|
803
|
+
):
|
|
804
|
+
assignments = _get_assignments_from_action(
|
|
805
|
+
matched_action,
|
|
806
|
+
source_df._column_map,
|
|
807
|
+
target_df._column_map,
|
|
808
|
+
ExpressionTyper(source_df),
|
|
809
|
+
ExpressionTyper(target_df),
|
|
810
|
+
)
|
|
811
|
+
clauses.append(when_matched(condition).update(assignments))
|
|
812
|
+
|
|
813
|
+
for not_matched_action in as_java_list(
|
|
814
|
+
logical_plan.notMatchedActions()
|
|
815
|
+
):
|
|
816
|
+
condition = _get_condition_from_action(
|
|
817
|
+
not_matched_action,
|
|
818
|
+
column_mapping_for_conditions,
|
|
819
|
+
typer_for_expressions,
|
|
820
|
+
)
|
|
821
|
+
if (
|
|
822
|
+
not_matched_action.getClass().getSimpleName() == "InsertAction"
|
|
823
|
+
or not_matched_action.getClass().getSimpleName()
|
|
824
|
+
== "InsertStarAction"
|
|
825
|
+
):
|
|
826
|
+
assignments = _get_assignments_from_action(
|
|
827
|
+
not_matched_action,
|
|
828
|
+
source_df._column_map,
|
|
829
|
+
target_df._column_map,
|
|
830
|
+
ExpressionTyper(source_df),
|
|
831
|
+
ExpressionTyper(target_df),
|
|
832
|
+
)
|
|
833
|
+
clauses.append(when_not_matched(condition).insert(assignments))
|
|
834
|
+
|
|
835
|
+
if not as_java_list(logical_plan.notMatchedBySourceActions()).isEmpty():
|
|
836
|
+
raise SnowparkConnectNotImplementedError(
|
|
837
|
+
"Snowflake does not support 'not matched by source' actions in MERGE statements."
|
|
838
|
+
)
|
|
839
|
+
|
|
840
|
+
if (
|
|
841
|
+
logical_plan.targetTable().getClass().getSimpleName()
|
|
842
|
+
== "UnresolvedRelation"
|
|
843
|
+
):
|
|
844
|
+
target_table_name = _spark_to_snowflake(
|
|
845
|
+
logical_plan.targetTable().multipartIdentifier()
|
|
846
|
+
)
|
|
847
|
+
else:
|
|
848
|
+
target_table_name = _spark_to_snowflake(
|
|
849
|
+
logical_plan.targetTable().child().multipartIdentifier()
|
|
850
|
+
)
|
|
851
|
+
session.table(target_table_name).merge(
|
|
852
|
+
source_df, merge_condition_typed_col.col, clauses
|
|
853
|
+
)
|
|
854
|
+
case "DeleteFromTable":
|
|
855
|
+
df = map_relation(map_logical_plan_relation(logical_plan.table()))
|
|
856
|
+
for col in df._column_map.columns:
|
|
857
|
+
df = df.with_column_renamed(
|
|
858
|
+
col.snowpark_name, _spark_to_snowflake_single_id(col.spark_name)
|
|
859
|
+
)
|
|
860
|
+
df = column_name_handler.with_column_map(df, df.columns, df.columns)
|
|
861
|
+
|
|
862
|
+
name = get_relation_identifier_name(logical_plan.table(), True)
|
|
863
|
+
(
|
|
864
|
+
condition_column_name,
|
|
865
|
+
condition_typed_col,
|
|
866
|
+
) = map_single_column_expression(
|
|
867
|
+
map_logical_plan_expression(logical_plan.condition()),
|
|
868
|
+
df._column_map,
|
|
869
|
+
ExpressionTyper(df),
|
|
870
|
+
)
|
|
871
|
+
session.table(name).delete(condition_typed_col.col)
|
|
872
|
+
case "RenameColumn":
|
|
873
|
+
table_name = get_relation_identifier_name(logical_plan.table(), True)
|
|
874
|
+
column_obj = logical_plan.column()
|
|
875
|
+
old_column_name = ".".join(
|
|
876
|
+
str(part) for part in as_java_list(column_obj.name())
|
|
877
|
+
)
|
|
878
|
+
new_column_name = str(logical_plan.newName())
|
|
879
|
+
|
|
880
|
+
# Pass through to Snowflake
|
|
881
|
+
snowflake_sql = f"ALTER TABLE {table_name} RENAME COLUMN {old_column_name} TO {new_column_name}"
|
|
882
|
+
session.sql(snowflake_sql).collect()
|
|
883
|
+
case "RenameTable":
|
|
884
|
+
name = get_relation_identifier_name(logical_plan.child(), True)
|
|
885
|
+
new_name = _spark_to_snowflake(logical_plan.newName())
|
|
886
|
+
|
|
887
|
+
try:
|
|
888
|
+
session.sql(f"ALTER TABLE {name} RENAME TO {new_name}").collect()
|
|
889
|
+
except Exception as e:
|
|
890
|
+
# This is a trick to rename iceberg tables without having to first sacrifice a query to determine
|
|
891
|
+
# whether the source table is an iceberg table.
|
|
892
|
+
# TODO(SNOW-2118744): such keyword is required for other ALTER TABLE commands against Iceberg tables
|
|
893
|
+
# too.
|
|
894
|
+
if str(e).find("is an Iceberg table") >= 0:
|
|
895
|
+
session.sql(
|
|
896
|
+
f"ALTER ICEBERG TABLE {name} RENAME TO {new_name}"
|
|
897
|
+
).collect()
|
|
898
|
+
else:
|
|
899
|
+
raise e
|
|
900
|
+
case "ReplaceTableAsSelect":
|
|
901
|
+
_create_table_as_select(logical_plan, mode="overwrite")
|
|
902
|
+
case "ResetCommand":
|
|
903
|
+
key = logical_plan.config().get()
|
|
904
|
+
unset_config_param(get_session_id(), key, session)
|
|
905
|
+
case "SetCatalogAndNamespace":
|
|
906
|
+
# TODO: add catalog setting here
|
|
907
|
+
name = get_relation_identifier_name(logical_plan.child(), True)
|
|
908
|
+
session.sql(f"USE SCHEMA {name}").collect()
|
|
909
|
+
case "SetCommand":
|
|
910
|
+
kv_result_tuple = logical_plan.kv().get()
|
|
911
|
+
key = kv_result_tuple._1()
|
|
912
|
+
val = kv_result_tuple._2().get()
|
|
913
|
+
set_config_param(get_session_id(), key, val, session)
|
|
914
|
+
case "SetNamespaceCommand":
|
|
915
|
+
name = _spark_to_snowflake(logical_plan.namespace())
|
|
916
|
+
session.sql(f"USE SCHEMA {name}").collect()
|
|
917
|
+
case "SetNamespaceLocation" | "SetNamespaceProperties":
|
|
918
|
+
raise SnowparkConnectNotImplementedError(
|
|
919
|
+
"Altering databases is not currently supported."
|
|
920
|
+
)
|
|
921
|
+
case "ShowCreateTable":
|
|
922
|
+
# Handle SHOW CREATE TABLE command
|
|
923
|
+
# Spark: SHOW CREATE TABLE table_name
|
|
924
|
+
# Snowflake: SELECT get_ddl('table', 'table_name')
|
|
925
|
+
table_relation = logical_plan.child()
|
|
926
|
+
table_name = _spark_to_snowflake(table_relation.multipartIdentifier())
|
|
927
|
+
|
|
928
|
+
# Convert to Snowflake get_ddl function
|
|
929
|
+
snowflake_sql = f"SELECT get_ddl('table', '{table_name}') AS ddl"
|
|
930
|
+
rows = session.sql(snowflake_sql).collect()
|
|
931
|
+
|
|
932
|
+
case "ShowCurrentNamespaceCommand":
|
|
933
|
+
name = session.get_current_schema()
|
|
934
|
+
unquoted_name = unquote_if_quoted(name)
|
|
935
|
+
sql = f"SHOW SCHEMAS LIKE '{unquoted_name}'"
|
|
936
|
+
rows = session.sql(sql).collect()
|
|
937
|
+
if not rows:
|
|
938
|
+
rows = None
|
|
939
|
+
case "ShowNamespaces":
|
|
940
|
+
name = get_relation_identifier_name(logical_plan.namespace(), True)
|
|
941
|
+
if name:
|
|
942
|
+
raise SnowparkConnectNotImplementedError(
|
|
943
|
+
"'IN' clause is not supported while listing databases"
|
|
944
|
+
)
|
|
945
|
+
if logical_plan.pattern().isDefined():
|
|
946
|
+
# Snowflake SQL requires a "%" pattern.
|
|
947
|
+
# Snowpark catalog requires a regex and does client-side filtering.
|
|
948
|
+
# Spark, however, uses a regex-like pattern that treats '*' and '|' differently.
|
|
949
|
+
raise SnowparkConnectNotImplementedError(
|
|
950
|
+
"'LIKE' clause is not supported while listing databases"
|
|
951
|
+
)
|
|
952
|
+
rows = session.sql("SHOW SCHEMAS").collect()
|
|
953
|
+
if not rows:
|
|
954
|
+
rows = None
|
|
955
|
+
case "ShowTables" | "ShowTableExtended":
|
|
956
|
+
name = get_relation_identifier_name(logical_plan.namespace(), True)
|
|
957
|
+
|
|
958
|
+
# Get the pattern for filtering
|
|
959
|
+
pattern = None
|
|
960
|
+
if class_name == "ShowTables" and logical_plan.pattern().isDefined():
|
|
961
|
+
pattern = logical_plan.pattern().get()
|
|
962
|
+
elif (
|
|
963
|
+
class_name == "ShowTableExtended"
|
|
964
|
+
and len(logical_plan.pattern()) != 0
|
|
965
|
+
):
|
|
966
|
+
pattern = logical_plan.pattern()
|
|
967
|
+
|
|
968
|
+
# Execute SHOW TABLES command
|
|
969
|
+
if name:
|
|
970
|
+
rows = session.sql(f"SHOW TABLES IN {name}").collect()
|
|
971
|
+
else:
|
|
972
|
+
rows = session.sql("SHOW TABLES").collect()
|
|
973
|
+
|
|
974
|
+
# Apply pattern filtering if pattern is provided
|
|
975
|
+
# This is workaround to filter using Python regex.
|
|
976
|
+
if pattern and rows:
|
|
977
|
+
rows = _filter_tables_by_pattern(rows, pattern)
|
|
978
|
+
case "ShowViews":
|
|
979
|
+
name = get_relation_identifier_name(logical_plan.namespace(), True)
|
|
980
|
+
|
|
981
|
+
# Get the pattern for filtering
|
|
982
|
+
pattern = (
|
|
983
|
+
logical_plan.pattern().get()
|
|
984
|
+
if logical_plan.pattern().isDefined()
|
|
985
|
+
else None
|
|
986
|
+
)
|
|
987
|
+
|
|
988
|
+
# Execute SHOW VIEWS command
|
|
989
|
+
if name:
|
|
990
|
+
rows = session.sql(f"SHOW VIEWS IN {name}").collect()
|
|
991
|
+
else:
|
|
992
|
+
rows = session.sql("SHOW VIEWS").collect()
|
|
993
|
+
|
|
994
|
+
# Apply pattern filtering if pattern is provided
|
|
995
|
+
if pattern and rows:
|
|
996
|
+
rows = _filter_tables_by_pattern(rows, pattern)
|
|
997
|
+
case "ShowColumns":
|
|
998
|
+
# Handle Spark SQL: SHOW COLUMNS IN table_name FROM database_name
|
|
999
|
+
# Convert to Snowflake SQL: SHOW COLUMNS IN TABLE database_name.table_name
|
|
1000
|
+
|
|
1001
|
+
# Extract table name from ShowColumns logical plan
|
|
1002
|
+
# The child() is an UnresolvedTable object, use the existing helper function
|
|
1003
|
+
table_relation = logical_plan.child()
|
|
1004
|
+
db_and_table_name = as_java_list(table_relation.multipartIdentifier())
|
|
1005
|
+
multi_part_len = len(db_and_table_name)
|
|
1006
|
+
table_name = _spark_to_snowflake(table_relation.multipartIdentifier())
|
|
1007
|
+
|
|
1008
|
+
db_name = None
|
|
1009
|
+
# Get database name if specified in namespace
|
|
1010
|
+
if logical_plan.namespace().isDefined():
|
|
1011
|
+
db_namespace = logical_plan.namespace().get()
|
|
1012
|
+
db_name = _spark_to_snowflake(db_namespace)
|
|
1013
|
+
|
|
1014
|
+
# Build the Snowflake SHOW COLUMNS command
|
|
1015
|
+
if db_name and multi_part_len == 1:
|
|
1016
|
+
# Full qualified table name: db.table
|
|
1017
|
+
full_table_name = f"{db_name}.{table_name}"
|
|
1018
|
+
snowflake_cmd = f"SHOW COLUMNS IN TABLE {full_table_name}"
|
|
1019
|
+
else:
|
|
1020
|
+
if db_name and multi_part_len == 2:
|
|
1021
|
+
# Check db_name is same as in the full table name
|
|
1022
|
+
if (
|
|
1023
|
+
_spark_to_snowflake_single_id(
|
|
1024
|
+
str(db_and_table_name[0])
|
|
1025
|
+
).casefold()
|
|
1026
|
+
!= db_name.casefold()
|
|
1027
|
+
):
|
|
1028
|
+
raise AnalysisException(
|
|
1029
|
+
f"database name is not matching:{db_name} and {db_and_table_name[0]}"
|
|
1030
|
+
)
|
|
1031
|
+
|
|
1032
|
+
# Just table name
|
|
1033
|
+
snowflake_cmd = f"SHOW COLUMNS IN TABLE {table_name}"
|
|
1034
|
+
|
|
1035
|
+
rows = session.sql(snowflake_cmd).collect()
|
|
1036
|
+
case "TruncateTable":
|
|
1037
|
+
name = get_relation_identifier_name(logical_plan.table(), True)
|
|
1038
|
+
session.sql(f"TRUNCATE TABLE {name}").collect()
|
|
1039
|
+
|
|
1040
|
+
case command if (
|
|
1041
|
+
command.startswith("Alter")
|
|
1042
|
+
or command.startswith("Create")
|
|
1043
|
+
or command.startswith("Drop")
|
|
1044
|
+
or command.startswith("Rename")
|
|
1045
|
+
or command.startswith("Replace")
|
|
1046
|
+
or command.startswith("Set")
|
|
1047
|
+
or command.startswith("Truncate")
|
|
1048
|
+
or command.startswith("AddColumns")
|
|
1049
|
+
):
|
|
1050
|
+
parsed_sql = sqlglot.parse_one(sql_string, dialect="spark").transform(
|
|
1051
|
+
_normalize_identifiers
|
|
1052
|
+
)
|
|
1053
|
+
snowflake_sql = parsed_sql.sql(dialect="snowflake")
|
|
1054
|
+
session.sql(snowflake_sql).collect()
|
|
1055
|
+
case command if command.startswith("Describe") or command.startswith(
|
|
1056
|
+
"Show"
|
|
1057
|
+
):
|
|
1058
|
+
parsed_sql = sqlglot.parse_one(sql_string, dialect="spark").transform(
|
|
1059
|
+
_normalize_identifiers
|
|
1060
|
+
)
|
|
1061
|
+
snowflake_sql = parsed_sql.sql(dialect="snowflake")
|
|
1062
|
+
if command.startswith("Show"):
|
|
1063
|
+
if snowflake_sql.startswith("SHOW TBLPROPERTIES"):
|
|
1064
|
+
# Snowflake doesn't support TBLPROPERTIES, EXTENDED.
|
|
1065
|
+
return pandas.DataFrame({"": [""]}), ""
|
|
1066
|
+
|
|
1067
|
+
rows = session.sql(snowflake_sql).collect()
|
|
1068
|
+
case _:
|
|
1069
|
+
execute_logical_plan(logical_plan)
|
|
1070
|
+
return None, None
|
|
1071
|
+
else:
|
|
1072
|
+
# spark.sql("select or cte+select") queries should be executed lazily.
|
|
1073
|
+
# This returns an empty dataframe and empty schema.
|
|
1074
|
+
# if is_sql_select_statement(_trim_sql_string(sql_string)):
|
|
1075
|
+
if _is_sql_select_statement_helper(sql_string):
|
|
1076
|
+
return None, None
|
|
1077
|
+
session = snowpark.Session.get_active_session()
|
|
1078
|
+
sql_df = session.sql(sql_string)
|
|
1079
|
+
columns = sql_df.columns
|
|
1080
|
+
column_name_handler.with_column_map(sql_df, columns, columns)
|
|
1081
|
+
rows = sql_df.collect()
|
|
1082
|
+
|
|
1083
|
+
if rows:
|
|
1084
|
+
return pandas.DataFrame(rows), ""
|
|
1085
|
+
return pandas.DataFrame({"": [""]}), ""
|
|
1086
|
+
|
|
1087
|
+
|
|
1088
|
+
def get_sql_passthrough() -> bool:
|
|
1089
|
+
return get_boolean_session_config_param("snowpark.connect.sql.passthrough")
|
|
1090
|
+
|
|
1091
|
+
|
|
1092
|
+
def map_sql(rel: relation_proto.Relation) -> snowpark.DataFrame:
|
|
1093
|
+
"""
|
|
1094
|
+
Map a SQL string to a DataFrame.
|
|
1095
|
+
|
|
1096
|
+
The SQL string is executed and the resulting DataFrame is returned.
|
|
1097
|
+
|
|
1098
|
+
In passthough mode as True, SAS calls session.sql() and not calling Spark Parser.
|
|
1099
|
+
This is to mitigate any issue not covered by spark logical plan to protobuf conversion.
|
|
1100
|
+
"""
|
|
1101
|
+
|
|
1102
|
+
snowpark_connect_sql_passthrough = get_sql_passthrough()
|
|
1103
|
+
|
|
1104
|
+
if not snowpark_connect_sql_passthrough:
|
|
1105
|
+
logical_plan = sql_parser().parseQuery(rel.sql.query)
|
|
1106
|
+
|
|
1107
|
+
parsed_pos_args = parse_pos_args(logical_plan, rel.sql.pos_args)
|
|
1108
|
+
set_sql_args(rel.sql.args, parsed_pos_args)
|
|
1109
|
+
|
|
1110
|
+
return execute_logical_plan(logical_plan)
|
|
1111
|
+
else:
|
|
1112
|
+
session = snowpark.Session.get_active_session()
|
|
1113
|
+
sql_df = session.sql(rel.sql.query)
|
|
1114
|
+
columns = sql_df.columns
|
|
1115
|
+
return column_name_handler.with_column_map(sql_df, columns, columns)
|
|
1116
|
+
|
|
1117
|
+
|
|
1118
|
+
def map_logical_plan_relation(
|
|
1119
|
+
rel, plan_id: int | None = None
|
|
1120
|
+
) -> relation_proto.Relation:
|
|
1121
|
+
if plan_id is None:
|
|
1122
|
+
plan_id = gen_sql_plan_id()
|
|
1123
|
+
session = get_or_create_snowpark_session()
|
|
1124
|
+
|
|
1125
|
+
class_name = str(rel.getClass().getSimpleName())
|
|
1126
|
+
match class_name:
|
|
1127
|
+
case "Aggregate":
|
|
1128
|
+
with push_sql_scope():
|
|
1129
|
+
input = map_logical_plan_relation(rel.child())
|
|
1130
|
+
|
|
1131
|
+
# For LCA support in GROUP BY, we need to extract aliases from the aggregate expressions
|
|
1132
|
+
# In Spark SQL, when you write "SELECT a as k, COUNT(b) FROM table GROUP BY k",
|
|
1133
|
+
# the aliases are defined in the aggregateExpressions, not in a separate Project node
|
|
1134
|
+
alias_map = {}
|
|
1135
|
+
|
|
1136
|
+
# Extract aliases from the aggregate expressions (SELECT clause)
|
|
1137
|
+
alias_map = {}
|
|
1138
|
+
for agg_expr in as_java_list(rel.aggregateExpressions()):
|
|
1139
|
+
if str(agg_expr.getClass().getSimpleName()) == "Alias":
|
|
1140
|
+
alias_map[str(agg_expr.name())] = agg_expr.child()
|
|
1141
|
+
|
|
1142
|
+
def substitute_lca_in_grouping_expr(expr):
|
|
1143
|
+
"""Substitute LCA references with original expressions and handle ordinal references"""
|
|
1144
|
+
expr_class = str(expr.getClass().getSimpleName())
|
|
1145
|
+
|
|
1146
|
+
# Handle ordinal references (e.g., GROUP BY 1, GROUP BY 2)
|
|
1147
|
+
# Note: Quoted column names like GROUP BY "1" come through as UnresolvedAttribute,
|
|
1148
|
+
# while unquoted ordinals like GROUP BY 1 come through as Literal with integer type
|
|
1149
|
+
if expr_class == "Literal":
|
|
1150
|
+
# Check if this is an integer literal (ordinal reference)
|
|
1151
|
+
if hasattr(expr, "dataType") and str(
|
|
1152
|
+
expr.dataType().typeName()
|
|
1153
|
+
) in ["integer", "long"]:
|
|
1154
|
+
ordinal_pos = expr.value()
|
|
1155
|
+
agg_expressions = as_java_list(rel.aggregateExpressions())
|
|
1156
|
+
|
|
1157
|
+
# Validate ordinal is in valid range (1-based indexing)
|
|
1158
|
+
if isinstance(ordinal_pos, int) and 1 <= ordinal_pos <= len(
|
|
1159
|
+
agg_expressions
|
|
1160
|
+
):
|
|
1161
|
+
# Return the expression from the SELECT clause at the ordinal position
|
|
1162
|
+
target_expr = agg_expressions[
|
|
1163
|
+
ordinal_pos - 1
|
|
1164
|
+
] # Convert to 0-based index
|
|
1165
|
+
|
|
1166
|
+
# If the target expression is an alias, return the underlying expression
|
|
1167
|
+
if (
|
|
1168
|
+
str(target_expr.getClass().getSimpleName())
|
|
1169
|
+
== "Alias"
|
|
1170
|
+
):
|
|
1171
|
+
return target_expr.child()
|
|
1172
|
+
else:
|
|
1173
|
+
return target_expr
|
|
1174
|
+
# If ordinal is out of range, let it fall through to generate an error later
|
|
1175
|
+
|
|
1176
|
+
# Handle named LCA references (existing logic)
|
|
1177
|
+
# This handles cases like GROUP BY "1" (quoted column names)
|
|
1178
|
+
if expr_class != "UnresolvedAttribute":
|
|
1179
|
+
return expr
|
|
1180
|
+
|
|
1181
|
+
attr_parts = as_java_list(expr.nameParts())
|
|
1182
|
+
if len(attr_parts) == 1:
|
|
1183
|
+
attr_name = str(attr_parts[0])
|
|
1184
|
+
return alias_map.get(attr_name, expr)
|
|
1185
|
+
|
|
1186
|
+
return expr
|
|
1187
|
+
|
|
1188
|
+
group_type = snowflake_proto.Aggregate.GROUP_TYPE_GROUPBY
|
|
1189
|
+
|
|
1190
|
+
grouping_sets: list[snowflake_proto.Aggregate.GroupingSets] = []
|
|
1191
|
+
|
|
1192
|
+
group_expression_list = as_java_list(rel.groupingExpressions())
|
|
1193
|
+
for exp in group_expression_list:
|
|
1194
|
+
match str(exp.getClass().getSimpleName()):
|
|
1195
|
+
case "Rollup":
|
|
1196
|
+
group_type = snowflake_proto.Aggregate.GROUP_TYPE_ROLLUP
|
|
1197
|
+
case "Cube":
|
|
1198
|
+
group_type = snowflake_proto.Aggregate.GROUP_TYPE_CUBE
|
|
1199
|
+
case "GroupingSets":
|
|
1200
|
+
if not exp.userGivenGroupByExprs().isEmpty():
|
|
1201
|
+
raise SnowparkConnectNotImplementedError(
|
|
1202
|
+
"User-defined group by expressions are not supported"
|
|
1203
|
+
)
|
|
1204
|
+
group_type = (
|
|
1205
|
+
snowflake_proto.Aggregate.GROUP_TYPE_GROUPING_SETS
|
|
1206
|
+
)
|
|
1207
|
+
grouping_sets = [
|
|
1208
|
+
snowflake_proto.Aggregate.GroupingSets(
|
|
1209
|
+
grouping_set=[
|
|
1210
|
+
map_logical_plan_expression(e)
|
|
1211
|
+
for e in as_java_list(grouping_set)
|
|
1212
|
+
]
|
|
1213
|
+
)
|
|
1214
|
+
for grouping_set in as_java_list(exp.groupingSets())
|
|
1215
|
+
]
|
|
1216
|
+
|
|
1217
|
+
if group_type != snowflake_proto.Aggregate.GROUP_TYPE_GROUPBY:
|
|
1218
|
+
if len(group_expression_list) != 1:
|
|
1219
|
+
raise SnowparkConnectNotImplementedError(
|
|
1220
|
+
"Multiple grouping expressions are not supported"
|
|
1221
|
+
)
|
|
1222
|
+
if group_type == snowflake_proto.Aggregate.GROUP_TYPE_GROUPING_SETS:
|
|
1223
|
+
group_expression_list = [] # TODO: exp.userGivenGroupByExprs()?
|
|
1224
|
+
else:
|
|
1225
|
+
group_expression_list = as_java_list(
|
|
1226
|
+
group_expression_list[0].children()
|
|
1227
|
+
)
|
|
1228
|
+
|
|
1229
|
+
grouping_expressions = [
|
|
1230
|
+
map_logical_plan_expression(substitute_lca_in_grouping_expr(e))
|
|
1231
|
+
for e in group_expression_list
|
|
1232
|
+
]
|
|
1233
|
+
|
|
1234
|
+
aggregate_expressions = [
|
|
1235
|
+
map_logical_plan_expression(e)
|
|
1236
|
+
for e in as_java_list(rel.aggregateExpressions())
|
|
1237
|
+
]
|
|
1238
|
+
|
|
1239
|
+
any_proto = Any()
|
|
1240
|
+
any_proto.Pack(
|
|
1241
|
+
snowflake_proto.Extension(
|
|
1242
|
+
aggregate=snowflake_proto.Aggregate(
|
|
1243
|
+
input=input,
|
|
1244
|
+
group_type=group_type,
|
|
1245
|
+
grouping_expressions=grouping_expressions,
|
|
1246
|
+
aggregate_expressions=aggregate_expressions,
|
|
1247
|
+
grouping_sets=grouping_sets,
|
|
1248
|
+
)
|
|
1249
|
+
)
|
|
1250
|
+
)
|
|
1251
|
+
proto = relation_proto.Relation(extension=any_proto)
|
|
1252
|
+
case "Distinct":
|
|
1253
|
+
proto = relation_proto.Relation(
|
|
1254
|
+
deduplicate=relation_proto.Deduplicate(
|
|
1255
|
+
input=map_logical_plan_relation(rel.child())
|
|
1256
|
+
)
|
|
1257
|
+
)
|
|
1258
|
+
case "Except":
|
|
1259
|
+
proto = relation_proto.Relation(
|
|
1260
|
+
set_op=relation_proto.SetOperation(
|
|
1261
|
+
left_input=map_logical_plan_relation(rel.left()),
|
|
1262
|
+
right_input=map_logical_plan_relation(rel.right()),
|
|
1263
|
+
set_op_type=relation_proto.SetOperation.SET_OP_TYPE_EXCEPT,
|
|
1264
|
+
is_all=rel.isAll(),
|
|
1265
|
+
)
|
|
1266
|
+
)
|
|
1267
|
+
case "Filter":
|
|
1268
|
+
proto = relation_proto.Relation(
|
|
1269
|
+
filter=relation_proto.Filter(
|
|
1270
|
+
input=map_logical_plan_relation(rel.child()),
|
|
1271
|
+
condition=map_logical_plan_expression(rel.condition()),
|
|
1272
|
+
)
|
|
1273
|
+
)
|
|
1274
|
+
case "GlobalLimit":
|
|
1275
|
+
# TODO: What's a global limit and what's a local limit?
|
|
1276
|
+
proto = map_logical_plan_relation(rel.child())
|
|
1277
|
+
case "Intersect":
|
|
1278
|
+
proto = relation_proto.Relation(
|
|
1279
|
+
set_op=relation_proto.SetOperation(
|
|
1280
|
+
left_input=map_logical_plan_relation(rel.left()),
|
|
1281
|
+
right_input=map_logical_plan_relation(rel.right()),
|
|
1282
|
+
set_op_type=relation_proto.SetOperation.SET_OP_TYPE_INTERSECT,
|
|
1283
|
+
is_all=rel.isAll(),
|
|
1284
|
+
)
|
|
1285
|
+
)
|
|
1286
|
+
case "Join":
|
|
1287
|
+
join_type_sql = str(rel.joinType().sql())
|
|
1288
|
+
join_type_name = f"JOIN_TYPE_{join_type_sql.replace(' ', '_')}"
|
|
1289
|
+
condition = rel.condition()
|
|
1290
|
+
|
|
1291
|
+
left = map_logical_plan_relation(rel.left())
|
|
1292
|
+
right = map_logical_plan_relation(rel.right())
|
|
1293
|
+
join_condition = (
|
|
1294
|
+
map_logical_plan_expression(condition.get())
|
|
1295
|
+
if condition.isDefined()
|
|
1296
|
+
else None
|
|
1297
|
+
)
|
|
1298
|
+
|
|
1299
|
+
if "_NATURAL" in join_type_name:
|
|
1300
|
+
join_type_name = join_type_name.replace("_NATURAL", "")
|
|
1301
|
+
natural_join_base_offset = NATURAL_JOIN_TYPE_BASE
|
|
1302
|
+
else:
|
|
1303
|
+
natural_join_base_offset = 0
|
|
1304
|
+
|
|
1305
|
+
if "_USING" in join_type_name:
|
|
1306
|
+
using_columns = as_java_list(rel.joinType().usingColumns())
|
|
1307
|
+
join_type_name = join_type_name.replace("_USING", "")
|
|
1308
|
+
else:
|
|
1309
|
+
using_columns = []
|
|
1310
|
+
|
|
1311
|
+
proto = relation_proto.Relation(
|
|
1312
|
+
join=relation_proto.Join(
|
|
1313
|
+
left=left,
|
|
1314
|
+
right=right,
|
|
1315
|
+
join_condition=join_condition,
|
|
1316
|
+
join_type=getattr(relation_proto.Join.JoinType, join_type_name)
|
|
1317
|
+
+ natural_join_base_offset,
|
|
1318
|
+
using_columns=using_columns,
|
|
1319
|
+
)
|
|
1320
|
+
)
|
|
1321
|
+
case "LocalLimit":
|
|
1322
|
+
|
|
1323
|
+
if rel.limitExpr().getClass().getSimpleName() == "Literal":
|
|
1324
|
+
limit_val = rel.limitExpr().value()
|
|
1325
|
+
else:
|
|
1326
|
+
expr_proto = map_logical_plan_expression(rel.limitExpr())
|
|
1327
|
+
session = snowpark.Session.get_active_session()
|
|
1328
|
+
m = ColumnNameMap([], [], None)
|
|
1329
|
+
expr = map_single_column_expression(
|
|
1330
|
+
expr_proto, m, ExpressionTyper.dummy_typer(session)
|
|
1331
|
+
)
|
|
1332
|
+
limit_val = session.range(1).select(expr[1].col).collect()[0][0]
|
|
1333
|
+
|
|
1334
|
+
proto = relation_proto.Relation(
|
|
1335
|
+
limit=relation_proto.Limit(
|
|
1336
|
+
input=map_logical_plan_relation(rel.child()),
|
|
1337
|
+
limit=limit_val,
|
|
1338
|
+
)
|
|
1339
|
+
)
|
|
1340
|
+
case "Offset":
|
|
1341
|
+
proto = relation_proto.Relation(
|
|
1342
|
+
offset=relation_proto.Offset(
|
|
1343
|
+
input=map_logical_plan_relation(rel.child()),
|
|
1344
|
+
offset=rel.offsetExpr().value(),
|
|
1345
|
+
)
|
|
1346
|
+
)
|
|
1347
|
+
case "OneRowRelation":
|
|
1348
|
+
proto = relation_proto.Relation(project=relation_proto.Project())
|
|
1349
|
+
case "Pivot":
|
|
1350
|
+
pivot_column = map_logical_plan_expression(rel.pivotColumn())
|
|
1351
|
+
session = snowpark.Session.get_active_session()
|
|
1352
|
+
m = ColumnNameMap([], [], None)
|
|
1353
|
+
|
|
1354
|
+
pivot_values = [
|
|
1355
|
+
map_logical_plan_expression(e) for e in as_java_list(rel.pivotValues())
|
|
1356
|
+
]
|
|
1357
|
+
|
|
1358
|
+
pivot_literals = []
|
|
1359
|
+
|
|
1360
|
+
for expr_proto in pivot_values:
|
|
1361
|
+
expr = map_single_column_expression(
|
|
1362
|
+
expr_proto, m, ExpressionTyper.dummy_typer(session)
|
|
1363
|
+
)
|
|
1364
|
+
value = session.range(1).select(expr[1].col).collect()[0][0]
|
|
1365
|
+
pivot_literals.append(
|
|
1366
|
+
expressions_proto.Expression.Literal(string=str(value))
|
|
1367
|
+
)
|
|
1368
|
+
|
|
1369
|
+
aggregate_expressions = [
|
|
1370
|
+
map_logical_plan_expression(e) for e in as_java_list(rel.aggregates())
|
|
1371
|
+
]
|
|
1372
|
+
|
|
1373
|
+
proto = relation_proto.Relation(
|
|
1374
|
+
aggregate=relation_proto.Aggregate(
|
|
1375
|
+
input=map_logical_plan_relation(rel.child()),
|
|
1376
|
+
aggregate_expressions=aggregate_expressions,
|
|
1377
|
+
group_type=relation_proto.Aggregate.GroupType.GROUP_TYPE_PIVOT,
|
|
1378
|
+
pivot=relation_proto.Aggregate.Pivot(
|
|
1379
|
+
col=pivot_column, values=pivot_literals
|
|
1380
|
+
),
|
|
1381
|
+
)
|
|
1382
|
+
)
|
|
1383
|
+
|
|
1384
|
+
case "PlanWithUnresolvedIdentifier":
|
|
1385
|
+
expr_proto = map_logical_plan_expression(rel.identifierExpr())
|
|
1386
|
+
session = snowpark.Session.get_active_session()
|
|
1387
|
+
m = ColumnNameMap([], [], None)
|
|
1388
|
+
expr = map_single_column_expression(
|
|
1389
|
+
expr_proto, m, ExpressionTyper.dummy_typer(session)
|
|
1390
|
+
)
|
|
1391
|
+
value = session.range(1).select(expr[1].col).collect()[0][0]
|
|
1392
|
+
|
|
1393
|
+
proto = relation_proto.Relation(
|
|
1394
|
+
read=relation_proto.Read(
|
|
1395
|
+
named_table=relation_proto.Read.NamedTable(
|
|
1396
|
+
unparsed_identifier=value,
|
|
1397
|
+
)
|
|
1398
|
+
)
|
|
1399
|
+
)
|
|
1400
|
+
case "Project":
|
|
1401
|
+
with push_sql_scope():
|
|
1402
|
+
input = map_logical_plan_relation(rel.child())
|
|
1403
|
+
expressions = [
|
|
1404
|
+
map_logical_plan_expression(e)
|
|
1405
|
+
for e in as_java_list(rel.projectList())
|
|
1406
|
+
]
|
|
1407
|
+
proto = relation_proto.Relation(
|
|
1408
|
+
project=relation_proto.Project(
|
|
1409
|
+
input=input,
|
|
1410
|
+
expressions=expressions,
|
|
1411
|
+
)
|
|
1412
|
+
)
|
|
1413
|
+
case "Sort":
|
|
1414
|
+
proto = relation_proto.Relation(
|
|
1415
|
+
sort=relation_proto.Sort(
|
|
1416
|
+
input=map_logical_plan_relation(rel.child()),
|
|
1417
|
+
order=[
|
|
1418
|
+
map_logical_plan_expression(e).sort_order
|
|
1419
|
+
for e in as_java_list(rel.order())
|
|
1420
|
+
],
|
|
1421
|
+
)
|
|
1422
|
+
)
|
|
1423
|
+
case "SubqueryAlias":
|
|
1424
|
+
alias = str(rel.alias())
|
|
1425
|
+
proto = relation_proto.Relation(
|
|
1426
|
+
subquery_alias=relation_proto.SubqueryAlias(
|
|
1427
|
+
input=map_logical_plan_relation(rel.child()),
|
|
1428
|
+
alias=alias,
|
|
1429
|
+
)
|
|
1430
|
+
)
|
|
1431
|
+
set_sql_plan_name(alias, plan_id)
|
|
1432
|
+
case "Union":
|
|
1433
|
+
children = as_java_list(rel.children())
|
|
1434
|
+
assert len(children) == 2, len(children)
|
|
1435
|
+
|
|
1436
|
+
proto = relation_proto.Relation(
|
|
1437
|
+
set_op=relation_proto.SetOperation(
|
|
1438
|
+
left_input=map_logical_plan_relation(children[0]),
|
|
1439
|
+
right_input=map_logical_plan_relation(children[1]),
|
|
1440
|
+
set_op_type=relation_proto.SetOperation.SET_OP_TYPE_UNION,
|
|
1441
|
+
by_name=rel.byName(),
|
|
1442
|
+
allow_missing_columns=rel.allowMissingCol(),
|
|
1443
|
+
)
|
|
1444
|
+
)
|
|
1445
|
+
case "Unpivot":
|
|
1446
|
+
value_column_names = [e for e in as_java_list(rel.valueColumnNames())]
|
|
1447
|
+
variable_column_name = rel.variableColumnName()
|
|
1448
|
+
|
|
1449
|
+
values = []
|
|
1450
|
+
for e1 in as_java_list(rel.values().get()):
|
|
1451
|
+
for e in as_java_list(e1):
|
|
1452
|
+
values.append(map_logical_plan_expression(e))
|
|
1453
|
+
|
|
1454
|
+
# Need to find ids which are not part of values and remaining cols of df
|
|
1455
|
+
input_rel = map_logical_plan_relation(rel.child())
|
|
1456
|
+
input_df: snowpark.DataFrame = map_relation(input_rel)
|
|
1457
|
+
column_map = input_df._column_map
|
|
1458
|
+
typer = ExpressionTyper(input_df)
|
|
1459
|
+
unpivot_spark_names = []
|
|
1460
|
+
for v in values:
|
|
1461
|
+
spark_name, typed_column = map_single_column_expression(
|
|
1462
|
+
v, column_map, typer
|
|
1463
|
+
)
|
|
1464
|
+
unpivot_spark_names.append(spark_name)
|
|
1465
|
+
|
|
1466
|
+
id_cols = []
|
|
1467
|
+
for column in input_df.columns:
|
|
1468
|
+
spark_column = (
|
|
1469
|
+
column_map.get_spark_column_name_from_snowpark_column_name(column)
|
|
1470
|
+
)
|
|
1471
|
+
if spark_column not in unpivot_spark_names:
|
|
1472
|
+
id_cols.append(
|
|
1473
|
+
expressions_proto.Expression(
|
|
1474
|
+
unresolved_attribute=expressions_proto.Expression.UnresolvedAttribute(
|
|
1475
|
+
unparsed_identifier=spark_column
|
|
1476
|
+
)
|
|
1477
|
+
)
|
|
1478
|
+
)
|
|
1479
|
+
|
|
1480
|
+
proto = relation_proto.Relation(
|
|
1481
|
+
unpivot=relation_proto.Unpivot(
|
|
1482
|
+
input=input_rel,
|
|
1483
|
+
ids=id_cols,
|
|
1484
|
+
values=relation_proto.Unpivot.Values(values=values),
|
|
1485
|
+
variable_column_name=variable_column_name,
|
|
1486
|
+
value_column_name=value_column_names[0],
|
|
1487
|
+
)
|
|
1488
|
+
)
|
|
1489
|
+
case "UnresolvedHaving":
|
|
1490
|
+
proto = relation_proto.Relation(
|
|
1491
|
+
filter=relation_proto.Filter(
|
|
1492
|
+
input=map_logical_plan_relation(rel.child()),
|
|
1493
|
+
condition=map_logical_plan_expression(rel.havingCondition()),
|
|
1494
|
+
)
|
|
1495
|
+
)
|
|
1496
|
+
case "UnresolvedHint":
|
|
1497
|
+
proto = relation_proto.Relation(
|
|
1498
|
+
hint=relation_proto.Hint(
|
|
1499
|
+
input=map_logical_plan_relation(rel.child()),
|
|
1500
|
+
name=str(rel.name()),
|
|
1501
|
+
parameters=[
|
|
1502
|
+
map_logical_plan_expression(e)
|
|
1503
|
+
for e in as_java_list(rel.parameters())
|
|
1504
|
+
],
|
|
1505
|
+
)
|
|
1506
|
+
)
|
|
1507
|
+
case "UnresolvedInlineTable":
|
|
1508
|
+
names = [str(name) for name in as_java_list(rel.names())]
|
|
1509
|
+
rows = (
|
|
1510
|
+
relation_proto.Relation(
|
|
1511
|
+
common=relation_proto.RelationCommon(
|
|
1512
|
+
plan_id=gen_sql_plan_id(),
|
|
1513
|
+
),
|
|
1514
|
+
project=relation_proto.Project(
|
|
1515
|
+
expressions=(
|
|
1516
|
+
expressions_proto.Expression(
|
|
1517
|
+
alias=expressions_proto.Expression.Alias(
|
|
1518
|
+
expr=map_logical_plan_expression(val),
|
|
1519
|
+
name=[name],
|
|
1520
|
+
)
|
|
1521
|
+
)
|
|
1522
|
+
for name, val in zip(names, as_java_list(row))
|
|
1523
|
+
),
|
|
1524
|
+
),
|
|
1525
|
+
)
|
|
1526
|
+
for row in as_java_list(rel.rows())
|
|
1527
|
+
)
|
|
1528
|
+
|
|
1529
|
+
proto = reduce(
|
|
1530
|
+
lambda left, right: relation_proto.Relation(
|
|
1531
|
+
common=relation_proto.RelationCommon(
|
|
1532
|
+
plan_id=gen_sql_plan_id(),
|
|
1533
|
+
),
|
|
1534
|
+
set_op=relation_proto.SetOperation(
|
|
1535
|
+
left_input=left,
|
|
1536
|
+
right_input=right,
|
|
1537
|
+
set_op_type=relation_proto.SetOperation.SET_OP_TYPE_UNION,
|
|
1538
|
+
is_all=True,
|
|
1539
|
+
),
|
|
1540
|
+
),
|
|
1541
|
+
rows,
|
|
1542
|
+
)
|
|
1543
|
+
case "UnresolvedRelation":
|
|
1544
|
+
name = str(rel.name())
|
|
1545
|
+
set_sql_plan_name(name, plan_id)
|
|
1546
|
+
|
|
1547
|
+
cte_proto = _ctes.get().get(name)
|
|
1548
|
+
if cte_proto is not None:
|
|
1549
|
+
# The name corresponds to a `WITH` alias rather than a table.
|
|
1550
|
+
# TODO: We currently evaluate the query each time its alias is used;
|
|
1551
|
+
# we should eventually start using `WITH` in Snowflake SQL.
|
|
1552
|
+
proto = cte_proto
|
|
1553
|
+
else:
|
|
1554
|
+
tmp_views = _get_current_temp_objects()
|
|
1555
|
+
current_schema = session.connection.schema
|
|
1556
|
+
from_table = (
|
|
1557
|
+
CURRENT_CATALOG_NAME,
|
|
1558
|
+
current_schema,
|
|
1559
|
+
name,
|
|
1560
|
+
)
|
|
1561
|
+
if from_table in tmp_views:
|
|
1562
|
+
_accessing_temp_object.set(True)
|
|
1563
|
+
proto = relation_proto.Relation(
|
|
1564
|
+
read=relation_proto.Read(
|
|
1565
|
+
named_table=relation_proto.Read.NamedTable(
|
|
1566
|
+
unparsed_identifier=name,
|
|
1567
|
+
)
|
|
1568
|
+
)
|
|
1569
|
+
)
|
|
1570
|
+
case "UnresolvedSubqueryColumnAliases":
|
|
1571
|
+
child = map_logical_plan_relation(rel.child())
|
|
1572
|
+
aliases = [str(a) for a in as_java_list(rel.outputColumnNames())]
|
|
1573
|
+
any_proto = Any()
|
|
1574
|
+
any_proto.Pack(
|
|
1575
|
+
snowflake_proto.Extension(
|
|
1576
|
+
subquery_column_aliases=snowflake_proto.SubqueryColumnAliases(
|
|
1577
|
+
input=child,
|
|
1578
|
+
aliases=aliases,
|
|
1579
|
+
)
|
|
1580
|
+
)
|
|
1581
|
+
)
|
|
1582
|
+
proto = relation_proto.Relation(extension=any_proto)
|
|
1583
|
+
case "UnresolvedTableValuedFunction":
|
|
1584
|
+
name = ".".join(str(part) for part in as_java_list(rel.name())).lower()
|
|
1585
|
+
args = [
|
|
1586
|
+
map_logical_plan_expression(exp)
|
|
1587
|
+
for exp in as_java_list(rel.functionArgs())
|
|
1588
|
+
]
|
|
1589
|
+
|
|
1590
|
+
match name:
|
|
1591
|
+
case "range":
|
|
1592
|
+
m = ColumnNameMap([], [], None)
|
|
1593
|
+
session = snowpark.Session.get_active_session()
|
|
1594
|
+
args = (
|
|
1595
|
+
session.range(1)
|
|
1596
|
+
.select(
|
|
1597
|
+
[
|
|
1598
|
+
map_single_column_expression(arg, m, None)[1].col
|
|
1599
|
+
for arg in args
|
|
1600
|
+
]
|
|
1601
|
+
)
|
|
1602
|
+
.collect()[0]
|
|
1603
|
+
)
|
|
1604
|
+
|
|
1605
|
+
start, step = 0, 1
|
|
1606
|
+
match args:
|
|
1607
|
+
case [_]:
|
|
1608
|
+
[end] = args
|
|
1609
|
+
case [_, _]:
|
|
1610
|
+
[start, end] = args
|
|
1611
|
+
case [_, _, _]:
|
|
1612
|
+
[start, end, step] = args
|
|
1613
|
+
|
|
1614
|
+
proto = relation_proto.Relation(
|
|
1615
|
+
range=relation_proto.Range(
|
|
1616
|
+
start=start,
|
|
1617
|
+
end=end,
|
|
1618
|
+
step=step,
|
|
1619
|
+
)
|
|
1620
|
+
)
|
|
1621
|
+
case udtf_name if udtf_name in snowpark.Session.get_active_session()._udtfs:
|
|
1622
|
+
# TODO: Table arguments are now expressions, too, so we shouldn't need to handle them here;
|
|
1623
|
+
# instead, handle SubqueryExpression.SUBQUERY_TYPE_TABLE_ARG in relation.map_extension.
|
|
1624
|
+
table_args = []
|
|
1625
|
+
non_table_args = []
|
|
1626
|
+
for i, arg in enumerate(args):
|
|
1627
|
+
extension = snowflake_exp_proto.ExpExtension()
|
|
1628
|
+
if (
|
|
1629
|
+
arg.extension.Unpack(extension)
|
|
1630
|
+
and extension.subquery_expression.subquery_type
|
|
1631
|
+
== snowflake_exp_proto.SubqueryExpression.SUBQUERY_TYPE_TABLE_ARG
|
|
1632
|
+
):
|
|
1633
|
+
table_args.append(
|
|
1634
|
+
snowflake_proto.TableArgumentInfo(
|
|
1635
|
+
table_argument=extension.subquery_expression.input,
|
|
1636
|
+
table_argument_idx=i,
|
|
1637
|
+
)
|
|
1638
|
+
)
|
|
1639
|
+
else:
|
|
1640
|
+
non_table_args.append(arg)
|
|
1641
|
+
|
|
1642
|
+
if table_args:
|
|
1643
|
+
any_proto = Any()
|
|
1644
|
+
any_proto.Pack(
|
|
1645
|
+
snowflake_proto.Extension(
|
|
1646
|
+
udtf_with_table_arguments=snowflake_proto.UDTFWithTableArguments(
|
|
1647
|
+
function_name=name,
|
|
1648
|
+
arguments=non_table_args,
|
|
1649
|
+
table_arguments=table_args,
|
|
1650
|
+
)
|
|
1651
|
+
)
|
|
1652
|
+
)
|
|
1653
|
+
proto = relation_proto.Relation(extension=any_proto)
|
|
1654
|
+
else:
|
|
1655
|
+
proto = relation_proto.Relation(
|
|
1656
|
+
project=relation_proto.Project(
|
|
1657
|
+
expressions=[
|
|
1658
|
+
expressions_proto.Expression(
|
|
1659
|
+
unresolved_function=expressions_proto.Expression.UnresolvedFunction(
|
|
1660
|
+
function_name=name,
|
|
1661
|
+
arguments=args,
|
|
1662
|
+
)
|
|
1663
|
+
)
|
|
1664
|
+
],
|
|
1665
|
+
),
|
|
1666
|
+
)
|
|
1667
|
+
case other:
|
|
1668
|
+
proto = relation_proto.Relation(
|
|
1669
|
+
project=relation_proto.Project(
|
|
1670
|
+
expressions=[
|
|
1671
|
+
expressions_proto.Expression(
|
|
1672
|
+
unresolved_function=expressions_proto.Expression.UnresolvedFunction(
|
|
1673
|
+
function_name=name,
|
|
1674
|
+
arguments=args,
|
|
1675
|
+
)
|
|
1676
|
+
)
|
|
1677
|
+
],
|
|
1678
|
+
),
|
|
1679
|
+
)
|
|
1680
|
+
case "UnresolvedWith":
|
|
1681
|
+
with _push_cte_scope():
|
|
1682
|
+
for cte in as_java_list(rel.cteRelations()):
|
|
1683
|
+
name = str(cte._1())
|
|
1684
|
+
cte_proto = map_logical_plan_relation(cte._2())
|
|
1685
|
+
_ctes.get()[name] = cte_proto
|
|
1686
|
+
|
|
1687
|
+
proto = map_logical_plan_relation(rel.child())
|
|
1688
|
+
case "LateralJoin":
|
|
1689
|
+
left = map_logical_plan_relation(rel.left())
|
|
1690
|
+
right = map_logical_plan_relation(rel.right().plan())
|
|
1691
|
+
any_proto = Any()
|
|
1692
|
+
any_proto.Pack(
|
|
1693
|
+
snowflake_proto.Extension(
|
|
1694
|
+
lateral_join=snowflake_proto.LateralJoin(
|
|
1695
|
+
left=left,
|
|
1696
|
+
right=right,
|
|
1697
|
+
)
|
|
1698
|
+
)
|
|
1699
|
+
)
|
|
1700
|
+
proto = relation_proto.Relation(extension=any_proto)
|
|
1701
|
+
case "WithWindowDefinition":
|
|
1702
|
+
map_obj = as_java_map(rel.windowDefinitions())
|
|
1703
|
+
with _push_window_specs_scope():
|
|
1704
|
+
for key, window_spec in map_obj.items():
|
|
1705
|
+
_window_specs.get()[key] = window_spec
|
|
1706
|
+
proto = map_logical_plan_relation(rel.child())
|
|
1707
|
+
case "Generate":
|
|
1708
|
+
input_relation = map_logical_plan_relation(rel.child())
|
|
1709
|
+
generator_output_list = as_java_list(rel.generatorOutput())
|
|
1710
|
+
generator_output_list_expressions = [
|
|
1711
|
+
map_logical_plan_expression(e) for e in generator_output_list
|
|
1712
|
+
]
|
|
1713
|
+
qualifier = rel.qualifier().get() if rel.qualifier().isDefined() else None
|
|
1714
|
+
function_name = rel.generator().name().toString()
|
|
1715
|
+
func_arguments = [
|
|
1716
|
+
map_logical_plan_expression(e)
|
|
1717
|
+
for e in as_java_list(rel.generator().children())
|
|
1718
|
+
]
|
|
1719
|
+
unresolved_fun_proto = expressions_proto.Expression.UnresolvedFunction(
|
|
1720
|
+
function_name=function_name, arguments=func_arguments
|
|
1721
|
+
)
|
|
1722
|
+
|
|
1723
|
+
aliased_proto = unresolved_fun_proto
|
|
1724
|
+
if generator_output_list.size() > 0:
|
|
1725
|
+
aliased_proto = expressions_proto.Expression(
|
|
1726
|
+
alias=expressions_proto.Expression.Alias(
|
|
1727
|
+
expr=expressions_proto.Expression(
|
|
1728
|
+
unresolved_function=unresolved_fun_proto,
|
|
1729
|
+
),
|
|
1730
|
+
name=[attribute.name() for attribute in generator_output_list],
|
|
1731
|
+
)
|
|
1732
|
+
)
|
|
1733
|
+
|
|
1734
|
+
# TODO: Fix the bug in snowpark where if we select posexplode with *, it would return columns
|
|
1735
|
+
# generated by posexplode two times plus all the other columns
|
|
1736
|
+
# Ideal way should have been to do this
|
|
1737
|
+
# unresolved_star_expr = expressions_proto.Expression(
|
|
1738
|
+
# unresolved_attribute=expressions_proto.Expression.UnresolvedAttribute(
|
|
1739
|
+
# unparsed_identifier="*",
|
|
1740
|
+
# )
|
|
1741
|
+
# )
|
|
1742
|
+
# generator_dataframe_proto.project.expressions.append(
|
|
1743
|
+
# unresolved_star_expr
|
|
1744
|
+
# )
|
|
1745
|
+
|
|
1746
|
+
# This is a workaround to fix the bug in snowpark where if we select posexplode with *, it would return wrong columns
|
|
1747
|
+
input_df = map_relation(input_relation)
|
|
1748
|
+
spark_columns = input_df._column_map.get_spark_columns()
|
|
1749
|
+
column_expressions = [
|
|
1750
|
+
expressions_proto.Expression(
|
|
1751
|
+
unresolved_attribute=expressions_proto.Expression.UnresolvedAttribute(
|
|
1752
|
+
unparsed_identifier=spark_column
|
|
1753
|
+
)
|
|
1754
|
+
)
|
|
1755
|
+
for spark_column in spark_columns
|
|
1756
|
+
]
|
|
1757
|
+
|
|
1758
|
+
generator_dataframe_proto = relation_proto.Relation(
|
|
1759
|
+
project=relation_proto.Project(
|
|
1760
|
+
input=input_relation,
|
|
1761
|
+
expressions=[aliased_proto, *column_expressions],
|
|
1762
|
+
)
|
|
1763
|
+
)
|
|
1764
|
+
if qualifier is not None and qualifier.lower() != "as":
|
|
1765
|
+
generator_dataframe_proto = relation_proto.Relation(
|
|
1766
|
+
with_columns=relation_proto.WithColumns(
|
|
1767
|
+
input=generator_dataframe_proto,
|
|
1768
|
+
aliases=[
|
|
1769
|
+
expressions_proto.Expression.Alias(
|
|
1770
|
+
expr=expressions_proto.Expression(
|
|
1771
|
+
unresolved_function=expressions_proto.Expression.UnresolvedFunction(
|
|
1772
|
+
function_name="struct",
|
|
1773
|
+
arguments=generator_output_list_expressions,
|
|
1774
|
+
)
|
|
1775
|
+
),
|
|
1776
|
+
name=[qualifier],
|
|
1777
|
+
)
|
|
1778
|
+
],
|
|
1779
|
+
)
|
|
1780
|
+
)
|
|
1781
|
+
proto = generator_dataframe_proto
|
|
1782
|
+
case other:
|
|
1783
|
+
raise SnowparkConnectNotImplementedError(f"Unimplemented relation: {other}")
|
|
1784
|
+
|
|
1785
|
+
proto.common.plan_id = plan_id
|
|
1786
|
+
|
|
1787
|
+
return proto
|
|
1788
|
+
|
|
1789
|
+
|
|
1790
|
+
def get_relation_identifier_name(name_obj, is_multi_part: bool = False) -> str:
|
|
1791
|
+
if name_obj.getClass().getSimpleName() == "PlanWithUnresolvedIdentifier":
|
|
1792
|
+
# IDENTIFIER(<table_name>)
|
|
1793
|
+
expr_proto = map_logical_plan_expression(name_obj.identifierExpr())
|
|
1794
|
+
session = snowpark.Session.get_active_session()
|
|
1795
|
+
m = ColumnNameMap([], [], None)
|
|
1796
|
+
expr = map_single_column_expression(
|
|
1797
|
+
expr_proto, m, ExpressionTyper.dummy_typer(session)
|
|
1798
|
+
)
|
|
1799
|
+
name = session.range(1).select(expr[1].col).collect()[0][0]
|
|
1800
|
+
else:
|
|
1801
|
+
if is_multi_part:
|
|
1802
|
+
name = _spark_to_snowflake(name_obj.multipartIdentifier())
|
|
1803
|
+
else:
|
|
1804
|
+
name = _spark_to_snowflake(name_obj.nameParts())
|
|
1805
|
+
|
|
1806
|
+
return name
|
|
1807
|
+
|
|
1808
|
+
|
|
1809
|
+
def _convert_spark_pattern_to_regex(pattern: str) -> str:
|
|
1810
|
+
"""
|
|
1811
|
+
Convert Spark LIKE pattern to Python regex pattern.
|
|
1812
|
+
|
|
1813
|
+
In Spark LIKE patterns:
|
|
1814
|
+
- '*' matches 0 or more characters (equivalent to '.*' in regex)
|
|
1815
|
+
- '|' is used to separate multiple patterns (equivalent to '|' in regex)
|
|
1816
|
+
- Everything else works like regular regex patterns
|
|
1817
|
+
|
|
1818
|
+
Args:
|
|
1819
|
+
pattern: Spark LIKE pattern string
|
|
1820
|
+
|
|
1821
|
+
Returns:
|
|
1822
|
+
Python regex pattern string
|
|
1823
|
+
"""
|
|
1824
|
+
if not pattern:
|
|
1825
|
+
return ""
|
|
1826
|
+
|
|
1827
|
+
# Split by '|' to handle multiple patterns
|
|
1828
|
+
patterns = pattern.split("|")
|
|
1829
|
+
regex_patterns = []
|
|
1830
|
+
|
|
1831
|
+
for p in patterns:
|
|
1832
|
+
p = p.strip()
|
|
1833
|
+
# Replace * with .* for wildcard matching, but preserve other regex characters
|
|
1834
|
+
# We need to be careful to only replace standalone * not part of other patterns
|
|
1835
|
+
converted = p.replace("*", ".*")
|
|
1836
|
+
regex_patterns.append(converted)
|
|
1837
|
+
|
|
1838
|
+
# Join patterns with | for OR matching
|
|
1839
|
+
return "|".join(regex_patterns)
|
|
1840
|
+
|
|
1841
|
+
|
|
1842
|
+
def _filter_tables_by_pattern(tables: list, pattern: str) -> list:
|
|
1843
|
+
"""
|
|
1844
|
+
Filter table list by Spark LIKE pattern.
|
|
1845
|
+
|
|
1846
|
+
Args:
|
|
1847
|
+
tables: List of table rows from Snowflake SHOW TABLES
|
|
1848
|
+
pattern: Spark LIKE pattern
|
|
1849
|
+
|
|
1850
|
+
Returns:
|
|
1851
|
+
Filtered list of tables matching the pattern
|
|
1852
|
+
"""
|
|
1853
|
+
if not pattern or not tables:
|
|
1854
|
+
return tables
|
|
1855
|
+
|
|
1856
|
+
regex_pattern = _convert_spark_pattern_to_regex(pattern)
|
|
1857
|
+
if not regex_pattern:
|
|
1858
|
+
return tables
|
|
1859
|
+
|
|
1860
|
+
# Compile regex for case-insensitive matching (as per Spark docs)
|
|
1861
|
+
compiled_regex = re.compile(regex_pattern, re.IGNORECASE)
|
|
1862
|
+
|
|
1863
|
+
filtered_tables = []
|
|
1864
|
+
for table in tables:
|
|
1865
|
+
# Table name is typically the second column in SHOW TABLES output
|
|
1866
|
+
table_name = table[1] if len(table) > 1 else str(table[0])
|
|
1867
|
+
if compiled_regex.search(table_name):
|
|
1868
|
+
filtered_tables.append(table)
|
|
1869
|
+
|
|
1870
|
+
return filtered_tables
|
|
1871
|
+
|
|
1872
|
+
|
|
1873
|
+
def _escape_sql_comment(comment: str) -> str:
|
|
1874
|
+
return str(comment).replace("'", "''").replace("\\", "\\\\")
|