From 04b8b1e76c467ae527202a75141ac8981a1c4ac5 Mon Sep 17 00:00:00 2001 From: yariks5s Date: Tue, 2 Jul 2024 14:01:19 +0000 Subject: [PATCH] initial commit for Hive-style partitioning --- src/Core/Settings.h | 5 + src/Core/SettingsChangesHistory.h | 5 + .../ObjectStorage/StorageObjectStorage.cpp | 32 ++- .../StorageObjectStorageSource.cpp | 14 +- src/Storages/StorageFile.cpp | 39 +++- src/Storages/StorageURL.cpp | 16 +- src/Storages/VirtualColumnUtils.cpp | 52 ++++- src/Storages/VirtualColumnUtils.h | 7 +- .../__init__.py | 0 .../configs/cluster_azure.xml | 39 ++++ .../configs/cluster_hdfs.xml | 33 +++ .../configs/disable_profilers_azure.xml | 9 + .../configs/macro_hdfs.xml | 5 + .../configs/named_collections_azure.xml | 14 ++ .../configs/schema_cache_azure.xml | 3 + .../configs/schema_cache_hdfs.xml | 3 + .../configs/users_azure.xml | 9 + .../test_azure.py | 204 ++++++++++++++++++ .../test_hdfs.py | 81 +++++++ .../03203_hive_style_partitioning.reference | 96 +++++++++ .../03203_hive_style_partitioning.sh | 93 ++++++++ .../column1=Gordon/sample.parquet | Bin 0 -> 1308 bytes .../column1=Schmidt/sample.parquet | Bin 0 -> 1308 bytes .../column0=Elizabeth/sample.parquet | Bin 0 -> 1308 bytes .../sample.parquet | Bin 0 -> 1308 bytes .../column1=Gordon/sample.parquet | Bin 0 -> 1308 bytes .../column1=Schmidt/sample.parquet | Bin 0 -> 1308 bytes .../coumn0=Elizabeth/sample.parquet | Bin 0 -> 1308 bytes .../sample.parquet | Bin 0 -> 1308 bytes 29 files changed, 749 insertions(+), 10 deletions(-) create mode 100644 tests/integration/test_hive_style_partitioning_hdfs_azure/__init__.py create mode 100644 tests/integration/test_hive_style_partitioning_hdfs_azure/configs/cluster_azure.xml create mode 100644 tests/integration/test_hive_style_partitioning_hdfs_azure/configs/cluster_hdfs.xml create mode 100644 tests/integration/test_hive_style_partitioning_hdfs_azure/configs/disable_profilers_azure.xml create mode 100644 tests/integration/test_hive_style_partitioning_hdfs_azure/configs/macro_hdfs.xml create mode 100644 tests/integration/test_hive_style_partitioning_hdfs_azure/configs/named_collections_azure.xml create mode 100644 tests/integration/test_hive_style_partitioning_hdfs_azure/configs/schema_cache_azure.xml create mode 100644 tests/integration/test_hive_style_partitioning_hdfs_azure/configs/schema_cache_hdfs.xml create mode 100644 tests/integration/test_hive_style_partitioning_hdfs_azure/configs/users_azure.xml create mode 100644 tests/integration/test_hive_style_partitioning_hdfs_azure/test_azure.py create mode 100644 tests/integration/test_hive_style_partitioning_hdfs_azure/test_hdfs.py create mode 100644 tests/queries/0_stateless/03203_hive_style_partitioning.reference create mode 100755 tests/queries/0_stateless/03203_hive_style_partitioning.sh create mode 100644 tests/queries/0_stateless/data_hive/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet create mode 100644 tests/queries/0_stateless/data_hive/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet create mode 100644 tests/queries/0_stateless/data_hive/partitioning/column0=Elizabeth/sample.parquet create mode 100644 tests/queries/0_stateless/data_hive/partitioning/non_existing_column=Elizabeth/sample.parquet create mode 100644 tests/queries/0_stateless/data_minio/hive_partitioning/coumn0=Elizabeth/column1=Gordon/sample.parquet create mode 100644 tests/queries/0_stateless/data_minio/hive_partitioning/coumn0=Elizabeth/column1=Schmidt/sample.parquet create mode 100644 tests/queries/0_stateless/data_minio/hive_partitioning/coumn0=Elizabeth/sample.parquet create mode 100644 tests/queries/0_stateless/data_minio/hive_partitioning/non_existing_column=Elizabeth/sample.parquet diff --git a/src/Core/Settings.h b/src/Core/Settings.h index 14fe0924b40..738c0129d2d 100644 --- a/src/Core/Settings.h +++ b/src/Core/Settings.h @@ -1106,6 +1106,11 @@ class IColumn; M(Bool, input_format_tsv_skip_trailing_empty_lines, false, "Skip trailing empty lines in TSV format", 0) \ M(Bool, input_format_custom_skip_trailing_empty_lines, false, "Skip trailing empty lines in CustomSeparated format", 0) \ M(Bool, input_format_tsv_crlf_end_of_line, false, "If it is set true, file function will read TSV format with \\r\\n instead of \\n.", 0) \ + M(Bool, file_hive_partitioning, false, "Allows to use hive partitioning for file format", 0)\ + M(Bool, url_hive_partitioning, false, "Allows to use hive partitioning for url format", 0)\ + M(Bool, s3_hive_partitioning, false, "Allows to use hive partitioning for s3 format", 0)\ + M(Bool, azure_blob_storage_hive_partitioning, false, "Allows to use hive partitioning for AzureBlobStorage format", 0)\ + M(Bool, hdfs_hive_partitioning, false, "Allows to use hive partitioning for hdfs format", 0)\ \ M(Bool, input_format_native_allow_types_conversion, true, "Allow data types conversion in Native input format", 0) \ \ diff --git a/src/Core/SettingsChangesHistory.h b/src/Core/SettingsChangesHistory.h index 4ac25a649b7..dd778149674 100644 --- a/src/Core/SettingsChangesHistory.h +++ b/src/Core/SettingsChangesHistory.h @@ -118,6 +118,11 @@ static const std::map +#include #include #include @@ -32,6 +33,19 @@ namespace ErrorCodes extern const int LOGICAL_ERROR; } + +bool checkIfHiveSettingEnabled(const ContextPtr & context, const std::string & storage_type_name) +{ + if (storage_type_name == "s3") + return context->getSettings().s3_hive_partitioning; + else if (storage_type_name == "hdfs") + return context->getSettings().hdfs_hive_partitioning; + else if (storage_type_name == "azure") + return context->getSettings().azure_blob_storage_hive_partitioning; + else + throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Unsupported storage type: {}", storage_type_name); +} + StorageObjectStorage::StorageObjectStorage( ConfigurationPtr configuration_, ObjectStoragePtr object_storage_, @@ -60,7 +74,23 @@ StorageObjectStorage::StorageObjectStorage( metadata.setConstraints(constraints_); metadata.setComment(comment); - setVirtuals(VirtualColumnUtils::getVirtualsForFileLikeStorage(metadata.getColumns())); + auto file_iterator = StorageObjectStorageSource::createFileIterator( + configuration, + object_storage, + distributed_processing_, + context, + {}, // predicate + metadata.getColumns().getAll(), // virtual_columns + nullptr, // read_keys + {} // file_progress_callback + ); + + Strings paths; + + if (checkIfHiveSettingEnabled(context, configuration->getTypeName())) + if (auto file = file_iterator->next(0)) + paths = {file->getPath()}; + setVirtuals(VirtualColumnUtils::getVirtualsForFileLikeStorage(metadata.getColumns(), paths)); setInMemoryMetadata(metadata); } diff --git a/src/Storages/ObjectStorage/StorageObjectStorageSource.cpp b/src/Storages/ObjectStorage/StorageObjectStorageSource.cpp index aef783fc3c4..2741cfecf6b 100644 --- a/src/Storages/ObjectStorage/StorageObjectStorageSource.cpp +++ b/src/Storages/ObjectStorage/StorageObjectStorageSource.cpp @@ -13,6 +13,7 @@ #include #include #include +#include namespace fs = std::filesystem; @@ -195,13 +196,24 @@ Chunk StorageObjectStorageSource::generate() const auto & object_info = reader.getObjectInfo(); const auto & filename = object_info->getFileName(); chassert(object_info->metadata); + + auto hive_map = VirtualColumnUtils::parsePartitionMapFromPath(object_info->getPath()); + bool contains_virtual_column = std::any_of(hive_map.begin(), hive_map.end(), + [&](const auto& pair) { + return read_from_format_info.requested_virtual_columns.contains(pair.first); + }); + + if (!contains_virtual_column) + hive_map.clear(); // If we cannot find any virual column in requested, we don't add any of them to chunk + VirtualColumnUtils::addRequestedFileLikeStorageVirtualsToChunk( chunk, read_from_format_info.requested_virtual_columns, { .path = getUniqueStoragePathIdentifier(*configuration, *object_info, false), .size = object_info->metadata->size_bytes, .filename = &filename, - .last_modified = object_info->metadata->last_modified + .last_modified = object_info->metadata->last_modified, + .hive_partitioning_map = hive_map }); return chunk; } diff --git a/src/Storages/StorageFile.cpp b/src/Storages/StorageFile.cpp index 7f39ff615f0..0c32f29cb34 100644 --- a/src/Storages/StorageFile.cpp +++ b/src/Storages/StorageFile.cpp @@ -52,6 +52,7 @@ #include #include #include +#include #include #include @@ -1095,7 +1096,11 @@ void StorageFile::setStorageMetadata(CommonArguments args) storage_metadata.setConstraints(args.constraints); storage_metadata.setComment(args.comment); setInMemoryMetadata(storage_metadata); - setVirtuals(VirtualColumnUtils::getVirtualsForFileLikeStorage(storage_metadata.getColumns())); + + Strings paths_for_virtuals; + if (args.getContext()->getSettingsRef().file_hive_partitioning) + paths_for_virtuals = paths; + setVirtuals(VirtualColumnUtils::getVirtualsForFileLikeStorage(storage_metadata.getColumns(), paths_for_virtuals)); } @@ -1437,6 +1442,15 @@ Chunk StorageFileSource::generate() chunk_size = input_format->getApproxBytesReadForChunk(); progress(num_rows, chunk_size ? chunk_size : chunk.bytes()); + std::map hive_map; + if (getContext()->getSettingsRef().file_hive_partitioning) + { + hive_map = VirtualColumnUtils::parsePartitionMapFromPath(current_path); + + for (const auto& item : hive_map) + requested_virtual_columns.push_back(NameAndTypePair(item.first, std::make_shared())); + } + /// Enrich with virtual columns. VirtualColumnUtils::addRequestedFileLikeStorageVirtualsToChunk( chunk, requested_virtual_columns, @@ -1444,7 +1458,8 @@ Chunk StorageFileSource::generate() .path = current_path, .size = current_file_size, .filename = (filename_override.has_value() ? &filename_override.value() : nullptr), - .last_modified = current_file_last_modified + .last_modified = current_file_last_modified, + .hive_partitioning_map = hive_map }); return chunk; @@ -1621,6 +1636,16 @@ void ReadFromFile::createIterator(const ActionsDAG::Node * predicate) storage->distributed_processing); } +void addPartitionColumnsToInfoHeader(Strings paths, ReadFromFormatInfo & info) +{ + for (const auto& path : paths) + { + auto map = VirtualColumnUtils::parsePartitionMapFromPath(path); + for (const auto& item : map) + info.source_header.insertUnique(ColumnWithTypeAndName(std::make_shared(), item.first)); + } +} + void ReadFromFile::initializePipeline(QueryPipelineBuilder & pipeline, const BuildQueryPipelineSettings &) { createIterator(nullptr); @@ -1628,10 +1653,20 @@ void ReadFromFile::initializePipeline(QueryPipelineBuilder & pipeline, const Bui size_t num_streams = max_num_streams; size_t files_to_read = 0; + Strings paths; if (storage->archive_info) + { files_to_read = storage->archive_info->paths_to_archives.size(); + paths = storage->archive_info->paths_to_archives; + } else + { files_to_read = storage->paths.size(); + paths = storage->paths; + } + + if (getContext()->getSettingsRef().file_hive_partitioning) + addPartitionColumnsToInfoHeader(paths, info); if (max_num_streams > files_to_read) num_streams = files_to_read; diff --git a/src/Storages/StorageURL.cpp b/src/Storages/StorageURL.cpp index 895da028fc2..f6374701fc2 100644 --- a/src/Storages/StorageURL.cpp +++ b/src/Storages/StorageURL.cpp @@ -36,6 +36,7 @@ #include #include #include +#include #include #include @@ -151,7 +152,11 @@ IStorageURLBase::IStorageURLBase( storage_metadata.setConstraints(constraints_); storage_metadata.setComment(comment); setInMemoryMetadata(storage_metadata); - setVirtuals(VirtualColumnUtils::getVirtualsForFileLikeStorage(storage_metadata.getColumns())); + + Strings uri_for_partitioning; + if (context_->getSettingsRef().url_hive_partitioning) + uri_for_partitioning = {uri}; + setVirtuals(VirtualColumnUtils::getVirtualsForFileLikeStorage(storage_metadata.getColumns(), uri_for_partitioning)); } @@ -410,12 +415,17 @@ Chunk StorageURLSource::generate() size_t chunk_size = 0; if (input_format) chunk_size = input_format->getApproxBytesReadForChunk(); + std::map hive_map; + if (getContext()->getSettingsRef().url_hive_partitioning) + hive_map = VirtualColumnUtils::parsePartitionMapFromPath(curr_uri.getPath()); + progress(num_rows, chunk_size ? chunk_size : chunk.bytes()); VirtualColumnUtils::addRequestedFileLikeStorageVirtualsToChunk( chunk, requested_virtual_columns, { .path = curr_uri.getPath(), - .size = current_file_size + .size = current_file_size, + .hive_partitioning_map = hive_map }); return chunk; } @@ -1170,6 +1180,7 @@ void ReadFromURL::createIterator(const ActionsDAG::Node * predicate) void ReadFromURL::initializePipeline(QueryPipelineBuilder & pipeline, const BuildQueryPipelineSettings &) { createIterator(nullptr); + const auto & settings = context->getSettingsRef(); if (is_empty_glob) { @@ -1180,7 +1191,6 @@ void ReadFromURL::initializePipeline(QueryPipelineBuilder & pipeline, const Buil Pipes pipes; pipes.reserve(num_streams); - const auto & settings = context->getSettingsRef(); const size_t max_parsing_threads = num_streams >= settings.max_parsing_threads ? 1 : (settings.max_parsing_threads / num_streams); for (size_t i = 0; i < num_streams; ++i) diff --git a/src/Storages/VirtualColumnUtils.cpp b/src/Storages/VirtualColumnUtils.cpp index 778c9e13adb..0b79e3b7a16 100644 --- a/src/Storages/VirtualColumnUtils.cpp +++ b/src/Storages/VirtualColumnUtils.cpp @@ -1,4 +1,3 @@ -#include #include #include #include @@ -37,6 +36,7 @@ #include #include +#include #include #include "Functions/FunctionsLogical.h" #include "Functions/IFunction.h" @@ -115,7 +115,22 @@ NameSet getVirtualNamesForFileLikeStorage() return {"_path", "_file", "_size", "_time"}; } -VirtualColumnsDescription getVirtualsForFileLikeStorage(const ColumnsDescription & storage_columns) +Strings parseVirtualColumnNameFromPath(const std::string & path) +{ + std::string pattern = "/([^/]+)=([^/]+)"; + // Map to store the key-value pairs + std::map key_values; + + re2::StringPiece input_piece(path); + std::string key; + Strings result; + while (RE2::FindAndConsume(&input_piece, pattern, &key)) + result.push_back(key); + + return result; +} + +VirtualColumnsDescription getVirtualsForFileLikeStorage(const ColumnsDescription & storage_columns, Strings paths) { VirtualColumnsDescription desc; @@ -132,6 +147,13 @@ VirtualColumnsDescription getVirtualsForFileLikeStorage(const ColumnsDescription add_virtual("_size", makeNullable(std::make_shared())); add_virtual("_time", makeNullable(std::make_shared())); + for (const auto& path : paths) + { + auto names = parseVirtualColumnNameFromPath(path); + for (const auto& name : names) + add_virtual("_" + name, std::make_shared(std::make_shared())); + } + return desc; } @@ -178,6 +200,8 @@ ColumnPtr getFilterByPathAndFileIndexes(const std::vector & paths, const { if (column.name == "_file" || column.name == "_path") block.insert({column.type->createColumn(), column.type, column.name}); + if (!getVirtualNamesForFileLikeStorage().contains(column.name)) + block.insert({column.type->createColumn(), column.type, column.name}); } block.insert({ColumnUInt64::create(), std::make_shared(), "_idx"}); @@ -189,6 +213,21 @@ ColumnPtr getFilterByPathAndFileIndexes(const std::vector & paths, const return block.getByName("_idx").column; } +std::map parsePartitionMapFromPath(const std::string & path) +{ + std::string pattern = "/([^/]+)=([^/]+)"; // Regex to capture key=value pairs + // Map to store the key-value pairs + std::map key_values; + + re2::StringPiece input_piece(path); + std::string key; + std::string value; + while (RE2::FindAndConsume(&input_piece, pattern, &key, &value)) + key_values["_" + key] = value; + + return key_values; +} + void addRequestedFileLikeStorageVirtualsToChunk( Chunk & chunk, const NamesAndTypesList & requested_virtual_columns, VirtualsForFileLikeStorage virtual_values) @@ -226,6 +265,15 @@ void addRequestedFileLikeStorageVirtualsToChunk( else chunk.addColumn(virtual_column.type->createColumnConstWithDefaultValue(chunk.getNumRows())->convertToFullColumnIfConst()); } + else + { + auto it = virtual_values.hive_partitioning_map.find(virtual_column.getNameInStorage()); + if (it != virtual_values.hive_partitioning_map.end()) + { + chunk.addColumn(virtual_column.getTypeInStorage()->createColumnConst(chunk.getNumRows(), it->second)->convertToFullColumnIfConst()); + virtual_values.hive_partitioning_map.erase(it); + } + } } } diff --git a/src/Storages/VirtualColumnUtils.h b/src/Storages/VirtualColumnUtils.h index fbfbdd6c6cc..a03d4c7447f 100644 --- a/src/Storages/VirtualColumnUtils.h +++ b/src/Storages/VirtualColumnUtils.h @@ -6,6 +6,8 @@ #include #include +#include +#include #include @@ -47,7 +49,7 @@ auto extractSingleValueFromBlock(const Block & block, const String & name) } NameSet getVirtualNamesForFileLikeStorage(); -VirtualColumnsDescription getVirtualsForFileLikeStorage(const ColumnsDescription & storage_columns); +VirtualColumnsDescription getVirtualsForFileLikeStorage(const ColumnsDescription & storage_columns, Strings paths = {}); ActionsDAGPtr createPathAndFileFilterDAG(const ActionsDAG::Node * predicate, const NamesAndTypesList & virtual_columns); @@ -74,9 +76,12 @@ struct VirtualsForFileLikeStorage std::optional size { std::nullopt }; const String * filename { nullptr }; std::optional last_modified { std::nullopt }; + std::map hive_partitioning_map; }; +std::map parsePartitionMapFromPath(const std::string & path); + void addRequestedFileLikeStorageVirtualsToChunk( Chunk & chunk, const NamesAndTypesList & requested_virtual_columns, VirtualsForFileLikeStorage virtual_values); diff --git a/tests/integration/test_hive_style_partitioning_hdfs_azure/__init__.py b/tests/integration/test_hive_style_partitioning_hdfs_azure/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/cluster_azure.xml b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/cluster_azure.xml new file mode 100644 index 00000000000..ffa4673c9ee --- /dev/null +++ b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/cluster_azure.xml @@ -0,0 +1,39 @@ + + + + + + node_0 + 9000 + + + node_1 + 9000 + + + node_2 + 9000 + + + + + + + + node_0 + 9000 + + + + + node_1 + 19000 + + + + + + + simple_cluster + + \ No newline at end of file diff --git a/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/cluster_hdfs.xml b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/cluster_hdfs.xml new file mode 100644 index 00000000000..b99b21ea40b --- /dev/null +++ b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/cluster_hdfs.xml @@ -0,0 +1,33 @@ + + + + + + node1 + 9000 + + + + + node1 + 19000 + + + + + + + + 127.0.0.1 + 9000 + + + + + 127.0.0.2 + 9000 + + + + + diff --git a/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/disable_profilers_azure.xml b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/disable_profilers_azure.xml new file mode 100644 index 00000000000..a39badbf8ec --- /dev/null +++ b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/disable_profilers_azure.xml @@ -0,0 +1,9 @@ + + + + + 0 + 0 + + + diff --git a/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/macro_hdfs.xml b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/macro_hdfs.xml new file mode 100644 index 00000000000..c2e11b47a5e --- /dev/null +++ b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/macro_hdfs.xml @@ -0,0 +1,5 @@ + + + test_cluster_two_shards + + \ No newline at end of file diff --git a/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/named_collections_azure.xml b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/named_collections_azure.xml new file mode 100644 index 00000000000..bd7f9ff97f1 --- /dev/null +++ b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/named_collections_azure.xml @@ -0,0 +1,14 @@ + + + + cont + test_simple_write_named.csv + key UInt64, data String + CSV + + + devstoreaccount1 + Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw== + + + diff --git a/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/schema_cache_azure.xml b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/schema_cache_azure.xml new file mode 100644 index 00000000000..e2168ecd06d --- /dev/null +++ b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/schema_cache_azure.xml @@ -0,0 +1,3 @@ + + 2 + \ No newline at end of file diff --git a/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/schema_cache_hdfs.xml b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/schema_cache_hdfs.xml new file mode 100644 index 00000000000..37639649b5f --- /dev/null +++ b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/schema_cache_hdfs.xml @@ -0,0 +1,3 @@ + + 2 + \ No newline at end of file diff --git a/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/users_azure.xml b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/users_azure.xml new file mode 100644 index 00000000000..4b6ba057ecb --- /dev/null +++ b/tests/integration/test_hive_style_partitioning_hdfs_azure/configs/users_azure.xml @@ -0,0 +1,9 @@ + + + + + default + 1 + + + diff --git a/tests/integration/test_hive_style_partitioning_hdfs_azure/test_azure.py b/tests/integration/test_hive_style_partitioning_hdfs_azure/test_azure.py new file mode 100644 index 00000000000..c9b2c9fec2e --- /dev/null +++ b/tests/integration/test_hive_style_partitioning_hdfs_azure/test_azure.py @@ -0,0 +1,204 @@ +#!/usr/bin/env python3 + +import pytest +import time + +from helpers.cluster import ClickHouseCluster, is_arm +import re + +from azure.storage.blob import BlobServiceClient +from helpers.cluster import ClickHouseCluster, ClickHouseInstance + +if is_arm(): + pytestmark = pytest.mark.skip + +@pytest.fixture(scope="module") +def cluster(): + try: + cluster = ClickHouseCluster(__file__) + cluster.add_instance( + "node", + main_configs=["configs/named_collections_azure.xml", "configs/schema_cache_azure.xml"], + user_configs=["configs/disable_profilers_azure.xml", "configs/users_azure.xml"], + with_azurite=True, + ) + cluster.start() + container_client = cluster.blob_service_client.get_container_client("cont") + container_client.create_container() + yield cluster + finally: + cluster.shutdown() + + +def azure_query( + node, query, expect_error=False, try_num=10, settings={}, query_on_retry=None +): + for i in range(try_num): + try: + if expect_error: + return node.query_and_get_error(query, settings=settings) + else: + return node.query(query, settings=settings) + except Exception as ex: + retriable_errors = [ + "DB::Exception: Azure::Core::Http::TransportException: Connection was closed by the server while trying to read a response", + "DB::Exception: Azure::Core::Http::TransportException: Connection closed before getting full response or response is less than expected", + "DB::Exception: Azure::Core::Http::TransportException: Connection was closed by the server while trying to read a response", + "DB::Exception: Azure::Core::Http::TransportException: Error while polling for socket ready read", + "Azure::Core::Http::TransportException, e.what() = Connection was closed by the server while trying to read a response", + "Azure::Core::Http::TransportException, e.what() = Connection closed before getting full response or response is less than expected", + "Azure::Core::Http::TransportException, e.what() = Connection was closed by the server while trying to read a response", + "Azure::Core::Http::TransportException, e.what() = Error while polling for socket ready read", + ] + retry = False + for error in retriable_errors: + if error in str(ex): + retry = True + print(f"Try num: {i}. Having retriable error: {ex}") + time.sleep(i) + break + if not retry or i == try_num - 1: + raise Exception(ex) + if query_on_retry is not None: + node.query(query_on_retry) + continue + + +def get_azure_file_content(filename, port): + container_name = "cont" + connection_string = ( + f"DefaultEndpointsProtocol=http;AccountName=devstoreaccount1;" + f"AccountKey=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==;" + f"BlobEndpoint=http://127.0.0.1:{port}/devstoreaccount1;" + ) + blob_service_client = BlobServiceClient.from_connection_string( + str(connection_string) + ) + container_client = blob_service_client.get_container_client(container_name) + blob_client = container_client.get_blob_client(filename) + download_stream = blob_client.download_blob() + return download_stream.readall().decode("utf-8") + + +@pytest.fixture(autouse=True, scope="function") +def delete_all_files(cluster): + port = cluster.env_variables["AZURITE_PORT"] + connection_string = ( + f"DefaultEndpointsProtocol=http;AccountName=devstoreaccount1;" + f"AccountKey=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==;" + f"BlobEndpoint=http://127.0.0.1:{port}/devstoreaccount1;" + ) + blob_service_client = BlobServiceClient.from_connection_string(connection_string) + containers = blob_service_client.list_containers() + for container in containers: + container_client = blob_service_client.get_container_client(container) + blob_list = container_client.list_blobs() + for blob in blob_list: + print(blob) + blob_client = container_client.get_blob_client(blob) + blob_client.delete_blob() + + assert len(list(container_client.list_blobs())) == 0 + + yield + + +def test_azure_partitioning_with_one_parameter(cluster): + # type: (ClickHouseCluster) -> None + node = cluster.instances["node"] # type: ClickHouseInstance + table_format = "column1 String, column2 String" + values = f"('Elizabeth', 'Gordon')" + path = "a/column1=Elizabeth/sample.csv" + + azure_query( + node, + f"INSERT INTO TABLE FUNCTION azureBlobStorage(azure_conf2, storage_account_url = '{cluster.env_variables['AZURITE_STORAGE_ACCOUNT_URL']}'," + f" container='cont', blob_path='{path}', format='CSV', compression='auto', structure='{table_format}') VALUES {values}", + ) + + query = ( + f"SELECT column1, column2, _file, _path, _column1 FROM azureBlobStorage(azure_conf2, " + f"storage_account_url = '{cluster.env_variables['AZURITE_STORAGE_ACCOUNT_URL']}', container='cont', " + f"blob_path='{path}', format='CSV', structure='{table_format}')" + ) + assert azure_query(node, query, settings={"azure_blob_storage_hive_partitioning": 1}).splitlines() == [ + "Elizabeth\tGordon\tsample.csv\t{bucket}/{max_path}\tElizabeth".format( + bucket="cont", max_path=path + ) + ] + + query = ( + f"SELECT column2 FROM azureBlobStorage(azure_conf2, " + f"storage_account_url = '{cluster.env_variables['AZURITE_STORAGE_ACCOUNT_URL']}', container='cont', " + f"blob_path='{path}', format='CSV', structure='{table_format}') WHERE column1=_column1;" + ) + assert azure_query(node, query, settings={"azure_blob_storage_hive_partitioning": 1}).splitlines() == [ + "Gordon" + ] + +def test_azure_partitioning_with_two_parameters(cluster): + # type: (ClickHouseCluster) -> None + node = cluster.instances["node"] # type: ClickHouseInstance + table_format = "column1 String, column2 String" + values_1 = f"('Elizabeth', 'Gordon')" + values_2 = f"('Emilia', 'Gregor')" + path = "a/column1=Elizabeth/column2=Gordon/sample.csv" + + azure_query( + node, + f"INSERT INTO TABLE FUNCTION azureBlobStorage(azure_conf2, storage_account_url = '{cluster.env_variables['AZURITE_STORAGE_ACCOUNT_URL']}'," + f" container='cont', blob_path='{path}', format='CSV', compression='auto', structure='{table_format}') VALUES {values_1}, {values_2}", + ) + + query = ( + f"SELECT column1, column2, _file, _path, _column1, _column2 FROM azureBlobStorage(azure_conf2, " + f"storage_account_url = '{cluster.env_variables['AZURITE_STORAGE_ACCOUNT_URL']}', container='cont', " + f"blob_path='{path}', format='CSV', structure='{table_format}') WHERE column1=_column1;" + ) + assert azure_query(node, query, settings={"azure_blob_storage_hive_partitioning": 1}).splitlines() == [ + "Elizabeth\tGordon\tsample.csv\t{bucket}/{max_path}\tElizabeth\tGordon".format( + bucket="cont", max_path=path + ) + ] + + query = ( + f"SELECT column1 FROM azureBlobStorage(azure_conf2, " + f"storage_account_url = '{cluster.env_variables['AZURITE_STORAGE_ACCOUNT_URL']}', container='cont', " + f"blob_path='{path}', format='CSV', structure='{table_format}') WHERE column2=_column2;" + ) + assert azure_query(node, query, settings={"azure_blob_storage_hive_partitioning": 1}).splitlines() == [ + "Elizabeth" + ] + + query = ( + f"SELECT column1 FROM azureBlobStorage(azure_conf2, " + f"storage_account_url = '{cluster.env_variables['AZURITE_STORAGE_ACCOUNT_URL']}', container='cont', " + f"blob_path='{path}', format='CSV', structure='{table_format}') WHERE column2=_column2 AND column1=_column1;" + ) + assert azure_query(node, query, settings={"azure_blob_storage_hive_partitioning": 1}).splitlines() == [ + "Elizabeth" + ] + +def test_azure_partitioning_without_setting(cluster): + # type: (ClickHouseCluster) -> None + node = cluster.instances["node"] # type: ClickHouseInstance + table_format = "column1 String, column2 String" + values_1 = f"('Elizabeth', 'Gordon')" + values_2 = f"('Emilia', 'Gregor')" + path = "a/column1=Elizabeth/column2=Gordon/sample.csv" + + azure_query( + node, + f"INSERT INTO TABLE FUNCTION azureBlobStorage(azure_conf2, storage_account_url = '{cluster.env_variables['AZURITE_STORAGE_ACCOUNT_URL']}'," + f" container='cont', blob_path='{path}', format='CSV', compression='auto', structure='{table_format}') VALUES {values_1}, {values_2}", + ) + + query = ( + f"SELECT column1, column2, _file, _path, _column1, _column2 FROM azureBlobStorage(azure_conf2, " + f"storage_account_url = '{cluster.env_variables['AZURITE_STORAGE_ACCOUNT_URL']}', container='cont', " + f"blob_path='{path}', format='CSV', structure='{table_format}') WHERE column1=_column1;" + ) + pattern = re.compile(r"DB::Exception: Unknown expression identifier '.*' in scope.*", re.DOTALL) + + with pytest.raises(Exception, match=pattern): + azure_query(node, query, settings={"azure_blob_storage_hive_partitioning": 0}) diff --git a/tests/integration/test_hive_style_partitioning_hdfs_azure/test_hdfs.py b/tests/integration/test_hive_style_partitioning_hdfs_azure/test_hdfs.py new file mode 100644 index 00000000000..38641b63960 --- /dev/null +++ b/tests/integration/test_hive_style_partitioning_hdfs_azure/test_hdfs.py @@ -0,0 +1,81 @@ +#!/usr/bin/env python3 + +import pytest + +from helpers.client import QueryRuntimeException +from helpers.cluster import ClickHouseCluster, is_arm +import re + +from helpers.cluster import ClickHouseCluster + +if is_arm(): + pytestmark = pytest.mark.skip + +cluster = ClickHouseCluster(__file__) +node1 = cluster.add_instance( + "node1", + main_configs=[ + "configs/macro_hdfs.xml", + "configs/schema_cache_hdfs.xml", + "configs/cluster_hdfs.xml", + ], + with_hdfs=True, +) + + +@pytest.fixture(scope="module") +def started_cluster(): + try: + cluster.start() + yield cluster + finally: + cluster.shutdown() + +def test_hdfs_partitioning_with_one_parameter(started_cluster): + hdfs_api = started_cluster.hdfs_api + hdfs_api.write_data( + f"/column0=Elizabeth/parquet_1", f"Elizabeth\tGordon\n" + ) + assert ( + hdfs_api.read_data(f"/column0=Elizabeth/parquet_1") + == f"Elizabeth\tGordon\n" + ) + + r = node1.query( + "SELECT _column0 FROM hdfs('hdfs://hdfs1:9000/column0=Elizabeth/parquet_1', 'TSV')", settings={"hdfs_hive_partitioning": 1} + ) + assert (r == f"Elizabeth\n") + +def test_hdfs_partitioning_with_two_parameters(started_cluster): + hdfs_api = started_cluster.hdfs_api + hdfs_api.write_data( + f"/column0=Elizabeth/column1=Gordon/parquet_2", f"Elizabeth\tGordon\n" + ) + assert ( + hdfs_api.read_data(f"/column0=Elizabeth/column1=Gordon/parquet_2") + == f"Elizabeth\tGordon\n" + ) + + r = node1.query( + "SELECT _column1 FROM hdfs('hdfs://hdfs1:9000/column0=Elizabeth/column1=Gordon/parquet_2', 'TSV');", settings={"hdfs_hive_partitioning": 1} + ) + assert (r == f"Gordon\n") + +def test_hdfs_partitioning_without_setting(started_cluster): + hdfs_api = started_cluster.hdfs_api + hdfs_api.write_data( + f"/column0=Elizabeth/column1=Gordon/parquet_2", f"Elizabeth\tGordon\n" + ) + assert ( + hdfs_api.read_data(f"/column0=Elizabeth/column1=Gordon/parquet_2") + == f"Elizabeth\tGordon\n" + ) + pattern = re.compile(r"DB::Exception: Unknown expression identifier '.*' in scope.*", re.DOTALL) + + with pytest.raises(QueryRuntimeException, match=pattern): + node1.query(f"SELECT _column1 FROM hdfs('hdfs://hdfs1:9000/column0=Elizabeth/column1=Gordon/parquet_2', 'TSV');", settings={"hdfs_hive_partitioning": 0}) + +if __name__ == "__main__": + cluster.start() + input("Cluster created, press any key to destroy...") + cluster.shutdown() diff --git a/tests/queries/0_stateless/03203_hive_style_partitioning.reference b/tests/queries/0_stateless/03203_hive_style_partitioning.reference new file mode 100644 index 00000000000..6ef1fcdf652 --- /dev/null +++ b/tests/queries/0_stateless/03203_hive_style_partitioning.reference @@ -0,0 +1,96 @@ +TESTING THE FILE HIVE PARTITIONING +first last Elizabeth +Jorge Frank Elizabeth +Hunter Moreno Elizabeth +Esther Guzman Elizabeth +Dennis Stephens Elizabeth +Nettie Franklin Elizabeth +Stanley Gibson Elizabeth +Eugenia Greer Elizabeth +Jeffery Delgado Elizabeth +Clara Cross Elizabeth +Elizabeth Gordon Elizabeth +Eva Schmidt Elizabeth Schmidt +Samuel Schmidt Elizabeth Schmidt +Eva Schmidt Elizabeth +Samuel Schmidt Elizabeth +Elizabeth Gordon Elizabeth Gordon +Elizabeth Gordon Elizabeth +Elizabeth Gordon Elizabeth Gordon +Elizabeth Gordon Elizabeth +first last Elizabeth +Jorge Frank Elizabeth +Hunter Moreno Elizabeth +Esther Guzman Elizabeth +Dennis Stephens Elizabeth +Nettie Franklin Elizabeth +Stanley Gibson Elizabeth +Eugenia Greer Elizabeth +Jeffery Delgado Elizabeth +Clara Cross Elizabeth +Elizabeth Gordon Elizabeth +1 +TESTING THE URL PARTITIONING +first last Elizabeth +Jorge Frank Elizabeth +Hunter Moreno Elizabeth +Esther Guzman Elizabeth +Dennis Stephens Elizabeth +Nettie Franklin Elizabeth +Stanley Gibson Elizabeth +Eugenia Greer Elizabeth +Jeffery Delgado Elizabeth +Clara Cross Elizabeth +Elizabeth Gordon Elizabeth +Eva Schmidt Elizabeth Schmidt +Samuel Schmidt Elizabeth Schmidt +Eva Schmidt Elizabeth +Samuel Schmidt Elizabeth +Elizabeth Gordon Elizabeth Gordon +Elizabeth Gordon Elizabeth +Elizabeth Gordon Elizabeth Gordon +Elizabeth Gordon Elizabeth +first last Elizabeth +Jorge Frank Elizabeth +Hunter Moreno Elizabeth +Esther Guzman Elizabeth +Dennis Stephens Elizabeth +Nettie Franklin Elizabeth +Stanley Gibson Elizabeth +Eugenia Greer Elizabeth +Jeffery Delgado Elizabeth +Clara Cross Elizabeth +Elizabeth Gordon Elizabeth +1 +TESTING THE S3 PARTITIONING +first last Elizabeth +Jorge Frank Elizabeth +Hunter Moreno Elizabeth +Esther Guzman Elizabeth +Dennis Stephens Elizabeth +Nettie Franklin Elizabeth +Stanley Gibson Elizabeth +Eugenia Greer Elizabeth +Jeffery Delgado Elizabeth +Clara Cross Elizabeth +Elizabeth Gordon Elizabeth +Eva Schmidt Elizabeth Schmidt +Samuel Schmidt Elizabeth Schmidt +Eva Schmidt Elizabeth +Samuel Schmidt Elizabeth +Elizabeth Gordon Elizabeth Gordon +Elizabeth Gordon Elizabeth +Elizabeth Gordon Elizabeth Gordon +Elizabeth Gordon Elizabeth +first last Elizabeth +Jorge Frank Elizabeth +Hunter Moreno Elizabeth +Esther Guzman Elizabeth +Dennis Stephens Elizabeth +Nettie Franklin Elizabeth +Stanley Gibson Elizabeth +Eugenia Greer Elizabeth +Jeffery Delgado Elizabeth +Clara Cross Elizabeth +Elizabeth Gordon Elizabeth +1 diff --git a/tests/queries/0_stateless/03203_hive_style_partitioning.sh b/tests/queries/0_stateless/03203_hive_style_partitioning.sh new file mode 100755 index 00000000000..a5d4c85a33b --- /dev/null +++ b/tests/queries/0_stateless/03203_hive_style_partitioning.sh @@ -0,0 +1,93 @@ +#!/usr/bin/env bash +# Tags: no-fasttest + +CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd) +# shellcheck source=../shell_config.sh +. "$CURDIR"/../shell_config.sh + +$CLICKHOUSE_LOCAL -q "SELECT 'TESTING THE FILE HIVE PARTITIONING'" + + +$CLICKHOUSE_LOCAL -n -q """set file_hive_partitioning = 1; + +SELECT *, _column0 FROM file('$CURDIR/data_hive/partitioning/column0=Elizabeth/sample.parquet') LIMIT 10; + +SELECT *, _column0 FROM file('$CURDIR/data_hive/partitioning/column0=Elizabeth/sample.parquet') WHERE column0 = _column0; + +SELECT *, _column0, _column1 FROM file('$CURDIR/data_hive/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column1 = _column1; +SELECT *, _column0 FROM file('$CURDIR/data_hive/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column1 = _column1; + +SELECT *, _column0, _column1 FROM file('$CURDIR/data_hive/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; +SELECT *, _column0 FROM file('$CURDIR/data_hive/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; + +SELECT *, _column0, _column1 FROM file('$CURDIR/data_hive/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column1 = _column1; +SELECT *, _column0 FROM file('$CURDIR/data_hive/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column1 = _column1; + +SELECT *, _column0, _column1 FROM file('$CURDIR/data_hive/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; +SELECT *, _column0 FROM file('$CURDIR/data_hive/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; + +SELECT *, _non_existing_column FROM file('$CURDIR/data_hive/partitioning/non_existing_column=Elizabeth/sample.parquet') LIMIT 10; +SELECT *, _column0 FROM file('$CURDIR/data_hive/partitioning/column0=*/sample.parquet') WHERE column0 = _column0;""" + +$CLICKHOUSE_LOCAL -n -q """set file_hive_partitioning = 0; + +SELECT *, _column0 FROM file('$CURDIR/data_hive/partitioning/column0=Elizabeth/sample.parquet') LIMIT 10;""" 2>&1 | grep -c "UNKNOWN_IDENTIFIER" + + +$CLICKHOUSE_LOCAL -q "SELECT 'TESTING THE URL PARTITIONING'" + + +$CLICKHOUSE_LOCAL -n -q """set url_hive_partitioning = 1; + +SELECT *, _column0 FROM url('http://localhost:11111/test/partitioning/column0=Elizabeth/sample.parquet') LIMIT 10; + +SELECT *, _column0 FROM url('http://localhost:11111/test/partitioning/column0=Elizabeth/sample.parquet') WHERE column0 = _column0; + +SELECT *, _column0, _column1 FROM url('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column1 = _column1; +SELECT *, _column0 FROM url('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column1 = _column1; + +SELECT *, _column0, _column1 FROM url('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; +SELECT *, _column0 FROM url('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; + +SELECT *, _column0, _column1 FROM url('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column1 = _column1; +SELECT *, _column0 FROM url('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column1 = _column1; + +SELECT *, _column0, _column1 FROM url('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; +SELECT *, _column0 FROM url('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; + +SELECT *, _non_existing_column FROM url('http://localhost:11111/test/partitioning/non_existing_column=Elizabeth/sample.parquet') LIMIT 10; +SELECT *, _column0 FROM url('http://localhost:11111/test/partitioning/column0=*/sample.parquet') WHERE column0 = _column0;""" + +$CLICKHOUSE_LOCAL -n -q """set url_hive_partitioning = 0; + +SELECT *, _column0 FROM url('http://localhost:11111/test/partitioning/column0=Elizabeth/sample.parquet') LIMIT 10;""" 2>&1 | grep -c "UNKNOWN_IDENTIFIER" + + +$CLICKHOUSE_LOCAL -q "SELECT 'TESTING THE S3 PARTITIONING'" + + +$CLICKHOUSE_LOCAL -n -q """set s3_hive_partitioning = 1; + +SELECT *, _column0 FROM s3('http://localhost:11111/test/partitioning/column0=Elizabeth/sample.parquet') LIMIT 10; + +SELECT *, _column0 FROM s3('http://localhost:11111/test/partitioning/column0=Elizabeth/sample.parquet') WHERE column0 = _column0; + +SELECT *, _column0, _column1 FROM s3('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column1 = _column1; +SELECT *, _column0 FROM s3('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column1 = _column1; + +SELECT *, _column0, _column1 FROM s3('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; +SELECT *, _column0 FROM s3('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; + +SELECT *, _column0, _column1 FROM s3('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column1 = _column1; +SELECT *, _column0 FROM s3('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column1 = _column1; + +SELECT *, _column0, _column1 FROM s3('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; +SELECT *, _column0 FROM s3('http://localhost:11111/test/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet') WHERE column0 = _column0 AND column1 = _column1; + +SELECT *, _non_existing_column FROM s3('http://localhost:11111/test/partitioning/non_existing_column=Elizabeth/sample.parquet') LIMIT 10; +SELECT *, _column0 FROM s3('http://localhost:11111/test/partitioning/column0=*/sample.parquet') WHERE column0 = _column0;""" + +$CLICKHOUSE_LOCAL -n -q """set s3_hive_partitioning = 0; + +SELECT *, _column0 FROM s3('http://localhost:11111/test/partitioning/column0=Elizabeth/sample.parquet') LIMIT 10;""" 2>&1 | grep -c "UNKNOWN_IDENTIFIER" + diff --git a/tests/queries/0_stateless/data_hive/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet b/tests/queries/0_stateless/data_hive/partitioning/column0=Elizabeth/column1=Gordon/sample.parquet new file mode 100644 index 0000000000000000000000000000000000000000..9b6a78cf8cc7cd3ece15e13c9b2f222c8f09b81e GIT binary patch literal 1308 zcmWG=3^EjD5Z%Hr`iosh^b{kI%_hpmz#!kv!2kyTLxU6Z9~tnZHa*@opEc(Au?K1g zOD4aYo#~scS*oJ`_R8gD$~^!1^Jl8v?6d#uZT@&1Z&h*OEsK+iS@vM( z^NvMD|`UJH2qG^xTWJ-dT6$7G6DVTky7Woy5#*nvWVEJpR{CJ{Fy0- zE8ux@_5^8x!?dEIRau&2MyW=j!5h*xtj<|H$T%nI_ zrsjz?W}YW@dt8{DRBI|`*(jU(m2ZmM@u#NQ!s{)z%{yLgtZF$)cAddC?xOT5D^_mz z-x7J9sr1v$v$K{(^`5h;Sz-1gc2*AGUh7}8F0R?}-B&E(IrH;G`GUhY z?q@1K*wQW0otd;iYI&}N?~AIE{%tkCroWN7t$#4bGw~KP0|PJ-eBc+|z=1tM#0JF{ zU3TEfTh6OHr)jl`=8?k_CV5&tiR=x1?{{sI`|Af*?oUEIqS_tiuleY8e||}EY3bMB zzp9qaKhIf|e>9xYs^&t{(WWC|y8X+=Uc{}=?T>Xh_5JxVk(1Vsywf&)T&i$tu2}yJ zsTDW>>9!Q_yZT7oEaCof4t43QdkFv1JFG`q9?h6g zxTpBgk6%&qwlli6{)!hkc#l_C=)}P;-Ys+NvjP>bYG~cCGCw}YQ1x-0z@w1)u@}^n zTV#|>Z7-{GtbTT=rr=<)~?``+iTxh4l+3|MS-tdVRHm+9w`h0!z=3knV zrSnX_{WmK}KJ?@4(a#30zmF(AmC{eNN7s8Lx}H>x1pMHFk2oys;%$ zvXN_R)m$dd8M|y^7q?Bh-x;&%icdYm3!CL}KR{`PNz%rYL4r4>G&wsZDZV&4BQ-Zs zl!ZZ*N0mu}Jvl$8G&j!xn4o|vkwidc4g-VODMm>dNgXu?8BrcdQ3gqbdKRFR7=zd% z4mA!N3D&gCqT&(>R>!2I%v3Q34HQ1GkiyV!C<@hogF|f<&;XY3{QMLNR)w6z;u4^K eWG+xU(4JF_Y8(t2Y%V}QxHvIf1_}lM%S8a*|2_@? literal 0 HcmV?d00001 diff --git a/tests/queries/0_stateless/data_hive/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet b/tests/queries/0_stateless/data_hive/partitioning/column0=Elizabeth/column1=Schmidt/sample.parquet new file mode 100644 index 0000000000000000000000000000000000000000..9b6a78cf8cc7cd3ece15e13c9b2f222c8f09b81e GIT binary patch literal 1308 zcmWG=3^EjD5Z%Hr`iosh^b{kI%_hpmz#!kv!2kyTLxU6Z9~tnZHa*@opEc(Au?K1g zOD4aYo#~scS*oJ`_R8gD$~^!1^Jl8v?6d#uZT@&1Z&h*OEsK+iS@vM( z^NvMD|`UJH2qG^xTWJ-dT6$7G6DVTky7Woy5#*nvWVEJpR{CJ{Fy0- zE8ux@_5^8x!?dEIRau&2MyW=j!5h*xtj<|H$T%nI_ zrsjz?W}YW@dt8{DRBI|`*(jU(m2ZmM@u#NQ!s{)z%{yLgtZF$)cAddC?xOT5D^_mz z-x7J9sr1v$v$K{(^`5h;Sz-1gc2*AGUh7}8F0R?}-B&E(IrH;G`GUhY z?q@1K*wQW0otd;iYI&}N?~AIE{%tkCroWN7t$#4bGw~KP0|PJ-eBc+|z=1tM#0JF{ zU3TEfTh6OHr)jl`=8?k_CV5&tiR=x1?{{sI`|Af*?oUEIqS_tiuleY8e||}EY3bMB zzp9qaKhIf|e>9xYs^&t{(WWC|y8X+=Uc{}=?T>Xh_5JxVk(1Vsywf&)T&i$tu2}yJ zsTDW>>9!Q_yZT7oEaCof4t43QdkFv1JFG`q9?h6g zxTpBgk6%&qwlli6{)!hkc#l_C=)}P;-Ys+NvjP>bYG~cCGCw}YQ1x-0z@w1)u@}^n zTV#|>Z7-{GtbTT=rr=<)~?``+iTxh4l+3|MS-tdVRHm+9w`h0!z=3knV zrSnX_{WmK}KJ?@4(a#30zmF(AmC{eNN7s8Lx}H>x1pMHFk2oys;%$ zvXN_R)m$dd8M|y^7q?Bh-x;&%icdYm3!CL}KR{`PNz%rYL4r4>G&wsZDZV&4BQ-Zs zl!ZZ*N0mu}Jvl$8G&j!xn4o|vkwidc4g-VODMm>dNgXu?8BrcdQ3gqbdKRFR7=zd% z4mA!N3D&gCqT&(>R>!2I%v3Q34HQ1GkiyV!C<@hogF|f<&;XY3{QMLNR)w6z;u4^K eWG+xU(4JF_Y8(t2Y%V}QxHvIf1_}lM%S8a*|2_@? literal 0 HcmV?d00001 diff --git a/tests/queries/0_stateless/data_hive/partitioning/column0=Elizabeth/sample.parquet b/tests/queries/0_stateless/data_hive/partitioning/column0=Elizabeth/sample.parquet new file mode 100644 index 0000000000000000000000000000000000000000..9b6a78cf8cc7cd3ece15e13c9b2f222c8f09b81e GIT binary patch literal 1308 zcmWG=3^EjD5Z%Hr`iosh^b{kI%_hpmz#!kv!2kyTLxU6Z9~tnZHa*@opEc(Au?K1g zOD4aYo#~scS*oJ`_R8gD$~^!1^Jl8v?6d#uZT@&1Z&h*OEsK+iS@vM( z^NvMD|`UJH2qG^xTWJ-dT6$7G6DVTky7Woy5#*nvWVEJpR{CJ{Fy0- zE8ux@_5^8x!?dEIRau&2MyW=j!5h*xtj<|H$T%nI_ zrsjz?W}YW@dt8{DRBI|`*(jU(m2ZmM@u#NQ!s{)z%{yLgtZF$)cAddC?xOT5D^_mz z-x7J9sr1v$v$K{(^`5h;Sz-1gc2*AGUh7}8F0R?}-B&E(IrH;G`GUhY z?q@1K*wQW0otd;iYI&}N?~AIE{%tkCroWN7t$#4bGw~KP0|PJ-eBc+|z=1tM#0JF{ zU3TEfTh6OHr)jl`=8?k_CV5&tiR=x1?{{sI`|Af*?oUEIqS_tiuleY8e||}EY3bMB zzp9qaKhIf|e>9xYs^&t{(WWC|y8X+=Uc{}=?T>Xh_5JxVk(1Vsywf&)T&i$tu2}yJ zsTDW>>9!Q_yZT7oEaCof4t43QdkFv1JFG`q9?h6g zxTpBgk6%&qwlli6{)!hkc#l_C=)}P;-Ys+NvjP>bYG~cCGCw}YQ1x-0z@w1)u@}^n zTV#|>Z7-{GtbTT=rr=<)~?``+iTxh4l+3|MS-tdVRHm+9w`h0!z=3knV zrSnX_{WmK}KJ?@4(a#30zmF(AmC{eNN7s8Lx}H>x1pMHFk2oys;%$ zvXN_R)m$dd8M|y^7q?Bh-x;&%icdYm3!CL}KR{`PNz%rYL4r4>G&wsZDZV&4BQ-Zs zl!ZZ*N0mu}Jvl$8G&j!xn4o|vkwidc4g-VODMm>dNgXu?8BrcdQ3gqbdKRFR7=zd% z4mA!N3D&gCqT&(>R>!2I%v3Q34HQ1GkiyV!C<@hogF|f<&;XY3{QMLNR)w6z;u4^K eWG+xU(4JF_Y8(t2Y%V}QxHvIf1_}lM%S8a*|2_@? literal 0 HcmV?d00001 diff --git a/tests/queries/0_stateless/data_hive/partitioning/non_existing_column=Elizabeth/sample.parquet b/tests/queries/0_stateless/data_hive/partitioning/non_existing_column=Elizabeth/sample.parquet new file mode 100644 index 0000000000000000000000000000000000000000..9b6a78cf8cc7cd3ece15e13c9b2f222c8f09b81e GIT binary patch literal 1308 zcmWG=3^EjD5Z%Hr`iosh^b{kI%_hpmz#!kv!2kyTLxU6Z9~tnZHa*@opEc(Au?K1g zOD4aYo#~scS*oJ`_R8gD$~^!1^Jl8v?6d#uZT@&1Z&h*OEsK+iS@vM( z^NvMD|`UJH2qG^xTWJ-dT6$7G6DVTky7Woy5#*nvWVEJpR{CJ{Fy0- zE8ux@_5^8x!?dEIRau&2MyW=j!5h*xtj<|H$T%nI_ zrsjz?W}YW@dt8{DRBI|`*(jU(m2ZmM@u#NQ!s{)z%{yLgtZF$)cAddC?xOT5D^_mz z-x7J9sr1v$v$K{(^`5h;Sz-1gc2*AGUh7}8F0R?}-B&E(IrH;G`GUhY z?q@1K*wQW0otd;iYI&}N?~AIE{%tkCroWN7t$#4bGw~KP0|PJ-eBc+|z=1tM#0JF{ zU3TEfTh6OHr)jl`=8?k_CV5&tiR=x1?{{sI`|Af*?oUEIqS_tiuleY8e||}EY3bMB zzp9qaKhIf|e>9xYs^&t{(WWC|y8X+=Uc{}=?T>Xh_5JxVk(1Vsywf&)T&i$tu2}yJ zsTDW>>9!Q_yZT7oEaCof4t43QdkFv1JFG`q9?h6g zxTpBgk6%&qwlli6{)!hkc#l_C=)}P;-Ys+NvjP>bYG~cCGCw}YQ1x-0z@w1)u@}^n zTV#|>Z7-{GtbTT=rr=<)~?``+iTxh4l+3|MS-tdVRHm+9w`h0!z=3knV zrSnX_{WmK}KJ?@4(a#30zmF(AmC{eNN7s8Lx}H>x1pMHFk2oys;%$ zvXN_R)m$dd8M|y^7q?Bh-x;&%icdYm3!CL}KR{`PNz%rYL4r4>G&wsZDZV&4BQ-Zs zl!ZZ*N0mu}Jvl$8G&j!xn4o|vkwidc4g-VODMm>dNgXu?8BrcdQ3gqbdKRFR7=zd% z4mA!N3D&gCqT&(>R>!2I%v3Q34HQ1GkiyV!C<@hogF|f<&;XY3{QMLNR)w6z;u4^K eWG+xU(4JF_Y8(t2Y%V}QxHvIf1_}lM%S8a*|2_@? literal 0 HcmV?d00001 diff --git a/tests/queries/0_stateless/data_minio/hive_partitioning/coumn0=Elizabeth/column1=Gordon/sample.parquet b/tests/queries/0_stateless/data_minio/hive_partitioning/coumn0=Elizabeth/column1=Gordon/sample.parquet new file mode 100644 index 0000000000000000000000000000000000000000..9b6a78cf8cc7cd3ece15e13c9b2f222c8f09b81e GIT binary patch literal 1308 zcmWG=3^EjD5Z%Hr`iosh^b{kI%_hpmz#!kv!2kyTLxU6Z9~tnZHa*@opEc(Au?K1g zOD4aYo#~scS*oJ`_R8gD$~^!1^Jl8v?6d#uZT@&1Z&h*OEsK+iS@vM( z^NvMD|`UJH2qG^xTWJ-dT6$7G6DVTky7Woy5#*nvWVEJpR{CJ{Fy0- zE8ux@_5^8x!?dEIRau&2MyW=j!5h*xtj<|H$T%nI_ zrsjz?W}YW@dt8{DRBI|`*(jU(m2ZmM@u#NQ!s{)z%{yLgtZF$)cAddC?xOT5D^_mz z-x7J9sr1v$v$K{(^`5h;Sz-1gc2*AGUh7}8F0R?}-B&E(IrH;G`GUhY z?q@1K*wQW0otd;iYI&}N?~AIE{%tkCroWN7t$#4bGw~KP0|PJ-eBc+|z=1tM#0JF{ zU3TEfTh6OHr)jl`=8?k_CV5&tiR=x1?{{sI`|Af*?oUEIqS_tiuleY8e||}EY3bMB zzp9qaKhIf|e>9xYs^&t{(WWC|y8X+=Uc{}=?T>Xh_5JxVk(1Vsywf&)T&i$tu2}yJ zsTDW>>9!Q_yZT7oEaCof4t43QdkFv1JFG`q9?h6g zxTpBgk6%&qwlli6{)!hkc#l_C=)}P;-Ys+NvjP>bYG~cCGCw}YQ1x-0z@w1)u@}^n zTV#|>Z7-{GtbTT=rr=<)~?``+iTxh4l+3|MS-tdVRHm+9w`h0!z=3knV zrSnX_{WmK}KJ?@4(a#30zmF(AmC{eNN7s8Lx}H>x1pMHFk2oys;%$ zvXN_R)m$dd8M|y^7q?Bh-x;&%icdYm3!CL}KR{`PNz%rYL4r4>G&wsZDZV&4BQ-Zs zl!ZZ*N0mu}Jvl$8G&j!xn4o|vkwidc4g-VODMm>dNgXu?8BrcdQ3gqbdKRFR7=zd% z4mA!N3D&gCqT&(>R>!2I%v3Q34HQ1GkiyV!C<@hogF|f<&;XY3{QMLNR)w6z;u4^K eWG+xU(4JF_Y8(t2Y%V}QxHvIf1_}lM%S8a*|2_@? literal 0 HcmV?d00001 diff --git a/tests/queries/0_stateless/data_minio/hive_partitioning/coumn0=Elizabeth/column1=Schmidt/sample.parquet b/tests/queries/0_stateless/data_minio/hive_partitioning/coumn0=Elizabeth/column1=Schmidt/sample.parquet new file mode 100644 index 0000000000000000000000000000000000000000..9b6a78cf8cc7cd3ece15e13c9b2f222c8f09b81e GIT binary patch literal 1308 zcmWG=3^EjD5Z%Hr`iosh^b{kI%_hpmz#!kv!2kyTLxU6Z9~tnZHa*@opEc(Au?K1g zOD4aYo#~scS*oJ`_R8gD$~^!1^Jl8v?6d#uZT@&1Z&h*OEsK+iS@vM( z^NvMD|`UJH2qG^xTWJ-dT6$7G6DVTky7Woy5#*nvWVEJpR{CJ{Fy0- zE8ux@_5^8x!?dEIRau&2MyW=j!5h*xtj<|H$T%nI_ zrsjz?W}YW@dt8{DRBI|`*(jU(m2ZmM@u#NQ!s{)z%{yLgtZF$)cAddC?xOT5D^_mz z-x7J9sr1v$v$K{(^`5h;Sz-1gc2*AGUh7}8F0R?}-B&E(IrH;G`GUhY z?q@1K*wQW0otd;iYI&}N?~AIE{%tkCroWN7t$#4bGw~KP0|PJ-eBc+|z=1tM#0JF{ zU3TEfTh6OHr)jl`=8?k_CV5&tiR=x1?{{sI`|Af*?oUEIqS_tiuleY8e||}EY3bMB zzp9qaKhIf|e>9xYs^&t{(WWC|y8X+=Uc{}=?T>Xh_5JxVk(1Vsywf&)T&i$tu2}yJ zsTDW>>9!Q_yZT7oEaCof4t43QdkFv1JFG`q9?h6g zxTpBgk6%&qwlli6{)!hkc#l_C=)}P;-Ys+NvjP>bYG~cCGCw}YQ1x-0z@w1)u@}^n zTV#|>Z7-{GtbTT=rr=<)~?``+iTxh4l+3|MS-tdVRHm+9w`h0!z=3knV zrSnX_{WmK}KJ?@4(a#30zmF(AmC{eNN7s8Lx}H>x1pMHFk2oys;%$ zvXN_R)m$dd8M|y^7q?Bh-x;&%icdYm3!CL}KR{`PNz%rYL4r4>G&wsZDZV&4BQ-Zs zl!ZZ*N0mu}Jvl$8G&j!xn4o|vkwidc4g-VODMm>dNgXu?8BrcdQ3gqbdKRFR7=zd% z4mA!N3D&gCqT&(>R>!2I%v3Q34HQ1GkiyV!C<@hogF|f<&;XY3{QMLNR)w6z;u4^K eWG+xU(4JF_Y8(t2Y%V}QxHvIf1_}lM%S8a*|2_@? literal 0 HcmV?d00001 diff --git a/tests/queries/0_stateless/data_minio/hive_partitioning/coumn0=Elizabeth/sample.parquet b/tests/queries/0_stateless/data_minio/hive_partitioning/coumn0=Elizabeth/sample.parquet new file mode 100644 index 0000000000000000000000000000000000000000..9b6a78cf8cc7cd3ece15e13c9b2f222c8f09b81e GIT binary patch literal 1308 zcmWG=3^EjD5Z%Hr`iosh^b{kI%_hpmz#!kv!2kyTLxU6Z9~tnZHa*@opEc(Au?K1g zOD4aYo#~scS*oJ`_R8gD$~^!1^Jl8v?6d#uZT@&1Z&h*OEsK+iS@vM( z^NvMD|`UJH2qG^xTWJ-dT6$7G6DVTky7Woy5#*nvWVEJpR{CJ{Fy0- zE8ux@_5^8x!?dEIRau&2MyW=j!5h*xtj<|H$T%nI_ zrsjz?W}YW@dt8{DRBI|`*(jU(m2ZmM@u#NQ!s{)z%{yLgtZF$)cAddC?xOT5D^_mz z-x7J9sr1v$v$K{(^`5h;Sz-1gc2*AGUh7}8F0R?}-B&E(IrH;G`GUhY z?q@1K*wQW0otd;iYI&}N?~AIE{%tkCroWN7t$#4bGw~KP0|PJ-eBc+|z=1tM#0JF{ zU3TEfTh6OHr)jl`=8?k_CV5&tiR=x1?{{sI`|Af*?oUEIqS_tiuleY8e||}EY3bMB zzp9qaKhIf|e>9xYs^&t{(WWC|y8X+=Uc{}=?T>Xh_5JxVk(1Vsywf&)T&i$tu2}yJ zsTDW>>9!Q_yZT7oEaCof4t43QdkFv1JFG`q9?h6g zxTpBgk6%&qwlli6{)!hkc#l_C=)}P;-Ys+NvjP>bYG~cCGCw}YQ1x-0z@w1)u@}^n zTV#|>Z7-{GtbTT=rr=<)~?``+iTxh4l+3|MS-tdVRHm+9w`h0!z=3knV zrSnX_{WmK}KJ?@4(a#30zmF(AmC{eNN7s8Lx}H>x1pMHFk2oys;%$ zvXN_R)m$dd8M|y^7q?Bh-x;&%icdYm3!CL}KR{`PNz%rYL4r4>G&wsZDZV&4BQ-Zs zl!ZZ*N0mu}Jvl$8G&j!xn4o|vkwidc4g-VODMm>dNgXu?8BrcdQ3gqbdKRFR7=zd% z4mA!N3D&gCqT&(>R>!2I%v3Q34HQ1GkiyV!C<@hogF|f<&;XY3{QMLNR)w6z;u4^K eWG+xU(4JF_Y8(t2Y%V}QxHvIf1_}lM%S8a*|2_@? literal 0 HcmV?d00001 diff --git a/tests/queries/0_stateless/data_minio/hive_partitioning/non_existing_column=Elizabeth/sample.parquet b/tests/queries/0_stateless/data_minio/hive_partitioning/non_existing_column=Elizabeth/sample.parquet new file mode 100644 index 0000000000000000000000000000000000000000..9b6a78cf8cc7cd3ece15e13c9b2f222c8f09b81e GIT binary patch literal 1308 zcmWG=3^EjD5Z%Hr`iosh^b{kI%_hpmz#!kv!2kyTLxU6Z9~tnZHa*@opEc(Au?K1g zOD4aYo#~scS*oJ`_R8gD$~^!1^Jl8v?6d#uZT@&1Z&h*OEsK+iS@vM( z^NvMD|`UJH2qG^xTWJ-dT6$7G6DVTky7Woy5#*nvWVEJpR{CJ{Fy0- zE8ux@_5^8x!?dEIRau&2MyW=j!5h*xtj<|H$T%nI_ zrsjz?W}YW@dt8{DRBI|`*(jU(m2ZmM@u#NQ!s{)z%{yLgtZF$)cAddC?xOT5D^_mz z-x7J9sr1v$v$K{(^`5h;Sz-1gc2*AGUh7}8F0R?}-B&E(IrH;G`GUhY z?q@1K*wQW0otd;iYI&}N?~AIE{%tkCroWN7t$#4bGw~KP0|PJ-eBc+|z=1tM#0JF{ zU3TEfTh6OHr)jl`=8?k_CV5&tiR=x1?{{sI`|Af*?oUEIqS_tiuleY8e||}EY3bMB zzp9qaKhIf|e>9xYs^&t{(WWC|y8X+=Uc{}=?T>Xh_5JxVk(1Vsywf&)T&i$tu2}yJ zsTDW>>9!Q_yZT7oEaCof4t43QdkFv1JFG`q9?h6g zxTpBgk6%&qwlli6{)!hkc#l_C=)}P;-Ys+NvjP>bYG~cCGCw}YQ1x-0z@w1)u@}^n zTV#|>Z7-{GtbTT=rr=<)~?``+iTxh4l+3|MS-tdVRHm+9w`h0!z=3knV zrSnX_{WmK}KJ?@4(a#30zmF(AmC{eNN7s8Lx}H>x1pMHFk2oys;%$ zvXN_R)m$dd8M|y^7q?Bh-x;&%icdYm3!CL}KR{`PNz%rYL4r4>G&wsZDZV&4BQ-Zs zl!ZZ*N0mu}Jvl$8G&j!xn4o|vkwidc4g-VODMm>dNgXu?8BrcdQ3gqbdKRFR7=zd% z4mA!N3D&gCqT&(>R>!2I%v3Q34HQ1GkiyV!C<@hogF|f<&;XY3{QMLNR)w6z;u4^K eWG+xU(4JF_Y8(t2Y%V}QxHvIf1_}lM%S8a*|2_@? literal 0 HcmV?d00001