mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-12-14 02:12:21 +00:00
rewrite support alias
This commit is contained in:
JackyWoo
parent
1d022fe593
commit
a33a6dafac
@ -127,9 +127,8 @@ class IColumn;
|
||||
\
|
||||
M(Bool, optimize_move_to_prewhere, true, "Allows disabling WHERE to PREWHERE optimization in SELECT queries from MergeTree.", 0) \
|
||||
M(Bool, optimize_move_to_prewhere_if_final, false, "If query has `FINAL`, the optimization `move_to_prewhere` is not always correct and it is enabled only if both settings `optimize_move_to_prewhere` and `optimize_move_to_prewhere_if_final` are turned on", 0) \
|
||||
M(Bool, move_all_conditions_to_prewhere, true, "Move all viable conditions from WHERE to PREWHERE", 0) \
|
||||
M(Bool, enable_multiple_prewhere_read_steps, true, "Move more conditions from WHERE to PREWHERE and do reads from disk and filtering in multiple steps if there are multiple conditions combined with AND", 0) \
|
||||
M(Bool, move_primary_key_columns_to_end_of_prewhere, true, "Move PREWHERE conditions containing primary key columns to the end of AND chain. It is likely that these conditions are taken into account during primary key analysis and thus will not contribute a lot to PREWHERE filtering.", 0) \
|
||||
M(Bool, move_all_conditions_to_prewhere, false, "Move all viable conditions from WHERE to PREWHERE", 0) \
|
||||
M(Bool, enable_multiple_prewhere_read_steps, false, "Move more conditions from WHERE to PREWHERE and do reads from disk and filtering in multiple steps if there are multiple conditions combined with AND", 0) \
|
||||
\
|
||||
M(UInt64, alter_sync, 1, "Wait for actions to manipulate the partitions. 0 - do not wait, 1 - wait for execution only of itself, 2 - wait for everyone.", 0) ALIAS(replication_alter_partitions_sync) \
|
||||
M(Int64, replication_wait_for_inactive_replica_timeout, 120, "Wait for inactive replica to execute ALTER/OPTIMIZE. Time in seconds, 0 - do not wait, negative - wait for unlimited time.", 0) \
|
||||
@ -276,7 +275,7 @@ class IColumn;
|
||||
\
|
||||
M(UInt64, http_headers_progress_interval_ms, 100, "Do not send HTTP headers X-ClickHouse-Progress more frequently than at each specified interval.", 0) \
|
||||
M(Bool, http_wait_end_of_query, false, "Enable HTTP response buffering on the server-side.", 0) \
|
||||
M(UInt64, http_response_buffer_size, 0, "The number of bytes to buffer in the server memory before sending a HTTP response to the client or flushing to disk (when http_wait_end_of_query is enabled).", 0) \
|
||||
M(UInt64, http_response_buffer_size, false, "The number of bytes to buffer in the server memory before sending a HTTP response to the client or flushing to disk (when http_wait_end_of_query is enabled).", 0) \
|
||||
\
|
||||
M(Bool, fsync_metadata, true, "Do fsync after changing metadata for tables and databases (.sql files). Could be disabled in case of poor latency on server with high load of DDL queries and high load of disk subsystem.", 0) \
|
||||
\
|
||||
@ -534,6 +533,7 @@ class IColumn;
|
||||
M(Bool, convert_query_to_cnf, false, "Convert SELECT query to CNF", 0) \
|
||||
M(Bool, optimize_or_like_chain, false, "Optimize multiple OR LIKE into multiMatchAny. This optimization should not be enabled by default, because it defies index analysis in some cases.", 0) \
|
||||
M(Bool, optimize_arithmetic_operations_in_aggregate_functions, true, "Move arithmetic operations out of aggregation functions", 0) \
|
||||
M(Bool, optimize_duplicate_order_by_and_distinct, false, "Remove duplicate ORDER BY and DISTINCT if it's possible", 0) \
|
||||
M(Bool, optimize_redundant_functions_in_order_by, true, "Remove functions from ORDER BY if its argument is also in ORDER BY", 0) \
|
||||
M(Bool, optimize_if_chain_to_multiif, false, "Replace if(cond1, then1, if(cond2, ...)) chains to multiIf. Currently it's not beneficial for numeric types.", 0) \
|
||||
M(Bool, optimize_multiif_to_if, true, "Replace 'multiIf' with only one condition to 'if'.", 0) \
|
||||
@ -577,7 +577,6 @@ class IColumn;
|
||||
M(Bool, optimize_skip_merged_partitions, false, "Skip partitions with one part with level > 0 in optimize final", 0) \
|
||||
M(Bool, optimize_on_insert, true, "Do the same transformation for inserted block of data as if merge was done on this block.", 0) \
|
||||
M(Bool, optimize_use_projections, true, "Automatically choose projections to perform SELECT query", 0) ALIAS(allow_experimental_projection_optimization) \
|
||||
M(Bool, optimize_use_implicit_projections, true, "Automatically choose implicit projections to perform SELECT query", 0) \
|
||||
M(Bool, force_optimize_projection, false, "If projection optimization is enabled, SELECT queries need to use projection", 0) \
|
||||
M(Bool, async_socket_for_remote, true, "Asynchronously read from socket executing remote query", 0) \
|
||||
M(Bool, async_query_sending_for_remote, true, "Asynchronously create connections and send query to shards in remote query", 0) \
|
||||
@ -622,7 +621,6 @@ class IColumn;
|
||||
M(Bool, engine_file_allow_create_multiple_files, false, "Enables or disables creating a new file on each insert in file engine tables if format has suffix.", 0) \
|
||||
M(Bool, engine_file_skip_empty_files, false, "Allows to skip empty files in file table engine", 0) \
|
||||
M(Bool, engine_url_skip_empty_files, false, "Allows to skip empty files in url table engine", 0) \
|
||||
M(Bool, disable_url_encoding, false, " Allows to disable decoding/encoding path in uri in URL table engine", 0) \
|
||||
M(Bool, allow_experimental_database_replicated, false, "Allow to create databases with Replicated engine", 0) \
|
||||
M(UInt64, database_replicated_initial_query_timeout_sec, 300, "How long initial DDL query should wait for Replicated database to precess previous DDL queue entries", 0) \
|
||||
M(Bool, database_replicated_enforce_synchronous_settings, false, "Enforces synchronous waiting for some queries (see also database_atomic_wait_for_drop_and_detach_synchronously, mutation_sync, alter_sync). Not recommended to enable these settings.", 0) \
|
||||
@ -631,7 +629,7 @@ class IColumn;
|
||||
M(Bool, database_replicated_allow_only_replicated_engine, false, "Allow to create only Replicated tables in database with engine Replicated", 0) \
|
||||
M(Bool, database_replicated_allow_replicated_engine_arguments, true, "Allow to create only Replicated tables in database with engine Replicated with explicit arguments", 0) \
|
||||
M(DistributedDDLOutputMode, distributed_ddl_output_mode, DistributedDDLOutputMode::THROW, "Format of distributed DDL query result", 0) \
|
||||
M(UInt64, distributed_ddl_entry_format_version, 5, "Compatibility version of distributed DDL (ON CLUSTER) queries", 0) \
|
||||
M(UInt64, distributed_ddl_entry_format_version, 3, "Compatibility version of distributed DDL (ON CLUSTER) queries", 0) \
|
||||
\
|
||||
M(UInt64, external_storage_max_read_rows, 0, "Limit maximum number of rows when table with external engine should flush history data. Now supported only for MySQL table engine, database engine, dictionary and MaterializedMySQL. If equal to 0, this setting is disabled", 0) \
|
||||
M(UInt64, external_storage_max_read_bytes, 0, "Limit maximum number of bytes when table with external engine should flush history data. Now supported only for MySQL table engine, database engine, dictionary and MaterializedMySQL. If equal to 0, this setting is disabled", 0) \
|
||||
@ -659,8 +657,7 @@ class IColumn;
|
||||
M(UInt64, limit, 0, "Limit on read rows from the most 'end' result for select query, default 0 means no limit length", 0) \
|
||||
M(UInt64, offset, 0, "Offset on read rows from the most 'end' result for select query", 0) \
|
||||
\
|
||||
M(UInt64, function_range_max_elements_in_block, 500000000, "Maximum number of values generated by function `range` per block of data (sum of array sizes for every row in a block, see also 'max_block_size' and 'min_insert_block_size_rows'). It is a safety threshold.", 0) \
|
||||
M(UInt64, function_sleep_max_microseconds_per_block, 3000000, "Maximum number of microseconds the function `sleep` is allowed to sleep for each block. If a user called it with a larger value, it throws an exception. It is a safety threshold.", 0) \
|
||||
M(UInt64, function_range_max_elements_in_block, 500000000, "Maximum number of values generated by function 'range' per block of data (sum of array sizes for every row in a block, see also 'max_block_size' and 'min_insert_block_size_rows'). It is a safety threshold.", 0) \
|
||||
M(ShortCircuitFunctionEvaluation, short_circuit_function_evaluation, ShortCircuitFunctionEvaluation::ENABLE, "Setting for short-circuit function evaluation configuration. Possible values: 'enable' - use short-circuit function evaluation for functions that are suitable for it, 'disable' - disable short-circuit function evaluation, 'force_enable' - use short-circuit function evaluation for all functions.", 0) \
|
||||
\
|
||||
M(LocalFSReadMethod, storage_file_read_method, LocalFSReadMethod::pread, "Method of reading data from storage file, one of: read, pread, mmap. The mmap method does not apply to clickhouse-server (it's intended for clickhouse-local).", 0) \
|
||||
@ -674,8 +671,8 @@ class IColumn;
|
||||
M(UInt64, remote_read_min_bytes_for_seek, 4 * DBMS_DEFAULT_BUFFER_SIZE, "Min bytes required for remote read (url, s3) to do seek, instead of read with ignore.", 0) \
|
||||
M(UInt64, merge_tree_min_bytes_per_task_for_remote_reading, 4 * DBMS_DEFAULT_BUFFER_SIZE, "Min bytes to read per task.", 0) \
|
||||
M(Bool, merge_tree_use_const_size_tasks_for_remote_reading, true, "Whether to use constant size tasks for reading from a remote table.", 0) \
|
||||
M(Bool, merge_tree_determine_task_size_by_prewhere_columns, true, "Whether to use only prewhere columns size to determine reading task size.", 0) \
|
||||
\
|
||||
M(UInt64, async_insert_threads, 16, "Maximum number of threads to actually parse and insert data in background. Zero means asynchronous mode is disabled", 0) \
|
||||
M(Bool, async_insert, false, "If true, data from INSERT query is stored in queue and later flushed to table in background. If wait_for_async_insert is false, INSERT query is processed almost instantly, otherwise client will wait until data will be flushed to table", 0) \
|
||||
M(Bool, wait_for_async_insert, true, "If true wait for processing of asynchronous insertion", 0) \
|
||||
M(Seconds, wait_for_async_insert_timeout, DBMS_DEFAULT_LOCK_ACQUIRE_TIMEOUT_SEC, "Timeout for waiting for processing asynchronous insertion", 0) \
|
||||
@ -739,7 +736,7 @@ class IColumn;
|
||||
M(String, workload, "default", "Name of workload to be used to access resources", 0) \
|
||||
M(Milliseconds, storage_system_stack_trace_pipe_read_timeout_ms, 100, "Maximum time to read from a pipe for receiving information from the threads when querying the `system.stack_trace` table. This setting is used for testing purposes and not meant to be changed by users.", 0) \
|
||||
\
|
||||
M(String, rename_files_after_processing, "", "Rename successfully processed files according to the specified pattern; Pattern can include the following placeholders: `%a` (full original file name), `%f` (original filename without extension), `%e` (file extension with dot), `%t` (current timestamp in µs), and `%%` (% sign)", 0) \
|
||||
M(String, rename_files_after_processing, "", "Rename successfully processed files according to the specified pattern; Pattern can include the following placeholders: `%f` (original filename without extension), `%e` (file extension with dot), `%t` (current timestamp in µs), and `%%` (% sign)", 0) \
|
||||
\
|
||||
M(Bool, parallelize_output_from_storages, true, "Parallelize output for reading step from storage. It allows parallelizing query processing right after reading from storage if possible", 0) \
|
||||
M(String, insert_deduplication_token, "", "If not empty, used for duplicate detection instead of data digest", 0) \
|
||||
@ -762,7 +759,7 @@ class IColumn;
|
||||
/** Experimental functions */ \
|
||||
M(Bool, allow_experimental_funnel_functions, false, "Enable experimental functions for funnel analysis.", 0) \
|
||||
M(Bool, allow_experimental_nlp_functions, false, "Enable experimental functions for natural language processing.", 0) \
|
||||
M(Bool, allow_experimental_hash_functions, false, "Enable experimental hash functions", 0) \
|
||||
M(Bool, allow_experimental_hash_functions, false, "Enable experimental hash functions (hashid, etc)", 0) \
|
||||
M(Bool, allow_experimental_object_type, false, "Allow Object and JSON data types", 0) \
|
||||
M(Bool, allow_experimental_annoy_index, false, "Allows to use Annoy index. Disabled by default because this feature is experimental", 0) \
|
||||
M(UInt64, max_limit_for_ann_queries, 1'000'000, "SELECT queries with LIMIT bigger than this setting cannot use ANN indexes. Helps to prevent memory overflows in ANN search indexes.", 0) \
|
||||
@ -776,8 +773,8 @@ class IColumn;
|
||||
M(Bool, allow_experimental_undrop_table_query, false, "Allow to use undrop query to restore dropped table in a limited time", 0) \
|
||||
M(Bool, keeper_map_strict_mode, false, "Enforce additional checks during operations on KeeperMap. E.g. throw an exception on an insert for already existing key", 0) \
|
||||
M(UInt64, extract_kvp_max_pairs_per_row, 1000, "Max number pairs that can be produced by extractKeyValuePairs function. Used to safeguard against consuming too much memory.", 0) \
|
||||
M(Timezone, session_timezone, "", "This setting can be removed in the future due to potential caveats. It is experimental and is not suitable for production usage. The default timezone for current session or query. The server default timezone if empty.", 0) \
|
||||
M(Bool, allow_create_index_without_type, false, "Allow CREATE INDEX query without TYPE. Query will be ignored. Made for SQL compatibility tests.", 0)\
|
||||
M(Timezone, session_timezone, "", "The default timezone for current session or query. The server default timezone if empty.", 0) \
|
||||
M(Bool, optimize_uniq_to_count, false, "Rewrite uniq and its variants(except uniqUpTo) to count if subquery has distinct or group by clause, it is a RBO based optimization.", 0)
|
||||
// End of COMMON_SETTINGS
|
||||
// Please add settings related to formats into the FORMAT_FACTORY_SETTINGS and move obsolete settings to OBSOLETE_SETTINGS.
|
||||
|
||||
@ -821,7 +818,6 @@ class IColumn;
|
||||
MAKE_DEPRECATED_BY_SERVER_CONFIG(M, UInt64, background_distributed_schedule_pool_size, 16) \
|
||||
MAKE_DEPRECATED_BY_SERVER_CONFIG(M, UInt64, max_remote_read_network_bandwidth_for_server, 0) \
|
||||
MAKE_DEPRECATED_BY_SERVER_CONFIG(M, UInt64, max_remote_write_network_bandwidth_for_server, 0) \
|
||||
MAKE_DEPRECATED_BY_SERVER_CONFIG(M, UInt64, async_insert_threads, 16) \
|
||||
MAKE_DEPRECATED_BY_SERVER_CONFIG(M, UInt64, max_replicated_fetches_network_bandwidth_for_server, 0) \
|
||||
MAKE_DEPRECATED_BY_SERVER_CONFIG(M, UInt64, max_replicated_sends_network_bandwidth_for_server, 0) \
|
||||
/* ---- */ \
|
||||
@ -833,7 +829,6 @@ class IColumn;
|
||||
MAKE_OBSOLETE(M, Seconds, drain_timeout, 3) \
|
||||
MAKE_OBSOLETE(M, UInt64, backup_threads, 16) \
|
||||
MAKE_OBSOLETE(M, UInt64, restore_threads, 16) \
|
||||
MAKE_OBSOLETE(M, Bool, optimize_duplicate_order_by_and_distinct, false) \
|
||||
|
||||
/** The section above is for obsolete settings. Do not add anything there. */
|
||||
|
||||
@ -878,7 +873,6 @@ class IColumn;
|
||||
M(Bool, input_format_csv_detect_header, true, "Automatically detect header with names and types in CSV format", 0) \
|
||||
M(Bool, input_format_csv_allow_whitespace_or_tab_as_delimiter, false, "Allow to use spaces and tabs(\\t) as field delimiter in the CSV strings", 0) \
|
||||
M(Bool, input_format_csv_trim_whitespaces, true, "Trims spaces and tabs (\\t) characters at the beginning and end in CSV strings", 0) \
|
||||
M(Bool, input_format_csv_use_default_on_bad_values, false, "Allow to set default value to column when CSV field deserialization failed on bad value", 0) \
|
||||
M(Bool, input_format_tsv_detect_header, true, "Automatically detect header with names and types in TSV format", 0) \
|
||||
M(Bool, input_format_custom_detect_header, true, "Automatically detect header with names and types in CustomSeparated format", 0) \
|
||||
M(Bool, input_format_parquet_skip_columns_with_unsupported_types_in_schema_inference, false, "Skip columns with unsupported types while schema inference for format Parquet", 0) \
|
||||
@ -913,7 +907,6 @@ class IColumn;
|
||||
\
|
||||
M(DateTimeInputFormat, date_time_input_format, FormatSettings::DateTimeInputFormat::Basic, "Method to read DateTime from text input formats. Possible values: 'basic', 'best_effort' and 'best_effort_us'.", 0) \
|
||||
M(DateTimeOutputFormat, date_time_output_format, FormatSettings::DateTimeOutputFormat::Simple, "Method to write DateTime to text output. Possible values: 'simple', 'iso', 'unix_timestamp'.", 0) \
|
||||
M(IntervalOutputFormat, interval_output_format, FormatSettings::IntervalOutputFormat::Numeric, "Textual representation of Interval. Possible values: 'kusto', 'numeric'.", 0) \
|
||||
\
|
||||
M(Bool, input_format_ipv4_default_on_conversion_error, false, "Deserialization of IPv4 will use default values instead of throwing exception on conversion error.", 0) \
|
||||
M(Bool, input_format_ipv6_default_on_conversion_error, false, "Deserialization of IPV6 will use default values instead of throwing exception on conversion error.", 0) \
|
||||
@ -954,10 +947,6 @@ class IColumn;
|
||||
M(ParquetVersion, output_format_parquet_version, "2.latest", "Parquet format version for output format. Supported versions: 1.0, 2.4, 2.6 and 2.latest (default)", 0) \
|
||||
M(ParquetCompression, output_format_parquet_compression_method, "lz4", "Compression method for Parquet output format. Supported codecs: snappy, lz4, brotli, zstd, gzip, none (uncompressed)", 0) \
|
||||
M(Bool, output_format_parquet_compliant_nested_types, true, "In parquet file schema, use name 'element' instead of 'item' for list elements. This is a historical artifact of Arrow library implementation. Generally increases compatibility, except perhaps with some old versions of Arrow.", 0) \
|
||||
M(Bool, output_format_parquet_use_custom_encoder, true, "Use experimental faster Parquet encoder implementation.", 0) \
|
||||
M(Bool, output_format_parquet_parallel_encoding, true, "Do Parquet encoding in multiple threads. Requires output_format_parquet_use_custom_encoder.", 0) \
|
||||
M(UInt64, output_format_parquet_data_page_size, 1024 * 1024, "Target page size in bytes, before compression.", 0) \
|
||||
M(UInt64, output_format_parquet_batch_size, 1024, "Check page size every this many rows. Consider decreasing if you have columns with average values size above a few KBs.", 0) \
|
||||
M(String, output_format_avro_codec, "", "Compression codec used for output. Possible values: 'null', 'deflate', 'snappy'.", 0) \
|
||||
M(UInt64, output_format_avro_sync_interval, 16 * 1024, "Sync interval in bytes.", 0) \
|
||||
M(String, output_format_avro_string_column_pattern, "", "For Avro format: regexp of String columns to select as AVRO string.", 0) \
|
||||
@ -1023,7 +1012,6 @@ class IColumn;
|
||||
M(Bool, regexp_dict_allow_hyperscan, true, "Allow regexp_tree dictionary using Hyperscan library.", 0) \
|
||||
\
|
||||
M(Bool, dictionary_use_async_executor, false, "Execute a pipeline for reading from a dictionary with several threads. It's supported only by DIRECT dictionary with CLICKHOUSE source.", 0) \
|
||||
M(Bool, input_format_csv_allow_variable_number_of_columns, false, "Ignore extra columns in CSV input (if file has more columns than expected) and treat missing fields in CSV input as default values", 0) \
|
||||
|
||||
// End of FORMAT_FACTORY_SETTINGS
|
||||
// Please add settings non-related to formats into the COMMON_SETTINGS above.
|
||||
|
||||
@ -14,16 +14,49 @@
|
||||
namespace DB
|
||||
{
|
||||
|
||||
using Aliases = std::unordered_map<String, ASTPtr>;
|
||||
|
||||
namespace
|
||||
{
|
||||
|
||||
bool matchFnUniq(String func_name)
|
||||
{
|
||||
auto name = Poco::toLower(func_name);
|
||||
return name == "uniq" || name == "uniqHLL12" || name == "uniqExact" || name == "uniqTheta" || name == "uniqCombined" || name == "uniqCombined64";
|
||||
return name == "uniq" || name == "uniqHLL12" || name == "uniqExact" || name == "uniqTheta" || name == "uniqCombined"
|
||||
|| name == "uniqCombined64";
|
||||
}
|
||||
|
||||
bool expressionListEquals(ASTExpressionList * lhs, ASTExpressionList * rhs)
|
||||
bool expressionEquals(const ASTPtr & lhs, const ASTPtr & rhs, Aliases & alias)
|
||||
{
|
||||
if (lhs->getTreeHash() == rhs->getTreeHash())
|
||||
{
|
||||
return true;
|
||||
}
|
||||
else
|
||||
{
|
||||
auto * lhs_idf = lhs->as<ASTIdentifier>();
|
||||
auto * rhs_idf = rhs->as<ASTIdentifier>();
|
||||
if (lhs_idf && rhs_idf)
|
||||
{
|
||||
/// compound identifiers, such as: <t.name, name>
|
||||
if (lhs_idf->shortName() == rhs_idf->shortName())
|
||||
return true;
|
||||
|
||||
/// translate alias
|
||||
if (alias.find(lhs_idf->shortName()) != alias.end())
|
||||
lhs_idf = alias.find(lhs_idf->shortName())->second->as<ASTIdentifier>();
|
||||
|
||||
if (alias.find(rhs_idf->shortName()) != alias.end())
|
||||
rhs_idf = alias.find(rhs_idf->shortName())->second->as<ASTIdentifier>();
|
||||
|
||||
if (lhs_idf->shortName() == rhs_idf->shortName())
|
||||
return true;
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
bool expressionListEquals(ASTExpressionList * lhs, ASTExpressionList * rhs, Aliases & alias)
|
||||
{
|
||||
if (!lhs || !rhs)
|
||||
return false;
|
||||
@ -31,27 +64,23 @@ bool expressionListEquals(ASTExpressionList * lhs, ASTExpressionList * rhs)
|
||||
return false;
|
||||
for (size_t i = 0; i < lhs->children.size(); i++)
|
||||
{
|
||||
if (lhs->children[i]->formatForLogging() != rhs->children[i]->formatForLogging()) // TODO not a elegant way
|
||||
if (!expressionEquals(lhs->children[i], rhs->children[i], alias))
|
||||
return false;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
/// Test whether lhs contains all expr in rhs.
|
||||
bool expressionListContainsAll(ASTExpressionList * lhs, ASTExpressionList * rhs)
|
||||
/// Test whether lhs contains all expressions in rhs.
|
||||
bool expressionListContainsAll(ASTExpressionList * lhs, ASTExpressionList * rhs, Aliases alias)
|
||||
{
|
||||
if (!lhs || !rhs)
|
||||
return false;
|
||||
if (lhs->children.size() < rhs->children.size())
|
||||
return false;
|
||||
std::vector<String> lhs_strs;
|
||||
for (const auto & le : lhs->children)
|
||||
{
|
||||
lhs_strs.emplace_back(le->formatForLogging());
|
||||
}
|
||||
for (const auto & re : rhs->children)
|
||||
{
|
||||
if (std::find(lhs_strs.begin(), lhs_strs.end(), re->formatForLogging()) != lhs_strs.end())
|
||||
auto predicate = [&re, &alias](ASTPtr & le) { return expressionEquals(le, re, alias); };
|
||||
if (std::find_if(lhs->children.begin(), lhs->children.end(), predicate) == lhs->children.end())
|
||||
return false;
|
||||
}
|
||||
return true;
|
||||
@ -72,46 +101,60 @@ void RewriteUniqToCountMatcher::visit(ASTPtr & ast, Data & /*data*/)
|
||||
return;
|
||||
if (selectq->tables()->as<ASTTablesInSelectQuery>()->children[0]->as<ASTTablesInSelectQueryElement>()->children.size() != 1)
|
||||
return;
|
||||
auto * table_expr = selectq->tables()->as<ASTTablesInSelectQuery>()->children[0]->as<ASTTablesInSelectQueryElement>()->children[0]->as<ASTTableExpression>();
|
||||
auto * table_expr = selectq->tables()
|
||||
->as<ASTTablesInSelectQuery>()
|
||||
->children[0]
|
||||
->as<ASTTablesInSelectQueryElement>()
|
||||
->children[0]
|
||||
->as<ASTTableExpression>();
|
||||
if (!table_expr || table_expr->children.size() != 1 || !table_expr->subquery)
|
||||
return;
|
||||
auto * subquery = table_expr->subquery->as<ASTSubquery>();
|
||||
if (!subquery)
|
||||
return;
|
||||
auto * sub_selectq = subquery->children[0]->as<ASTSelectWithUnionQuery>()->children[0]->as<ASTExpressionList>()->children[0]->as<ASTSelectQuery>();
|
||||
auto * sub_selectq = subquery->children[0]
|
||||
->as<ASTSelectWithUnionQuery>()->children[0]
|
||||
->as<ASTExpressionList>()->children[0]
|
||||
->as<ASTSelectQuery>();
|
||||
if (!sub_selectq)
|
||||
return;
|
||||
auto sub_expr_list = sub_selectq->select();
|
||||
if (!sub_expr_list)
|
||||
return;
|
||||
|
||||
auto match_distinct = [&]() -> bool
|
||||
/// collect subquery select expressions alias
|
||||
std::unordered_map<String, ASTPtr> alias;
|
||||
for (auto expr : sub_expr_list->children)
|
||||
{
|
||||
if (!expr->tryGetAlias().empty())
|
||||
alias.insert({expr->tryGetAlias(), expr});
|
||||
}
|
||||
|
||||
auto match_subquery_with_distinct = [&]() -> bool
|
||||
{
|
||||
if (!sub_selectq->distinct)
|
||||
return false;
|
||||
auto sub_expr_list = sub_selectq->select();
|
||||
if (!sub_expr_list)
|
||||
return false;
|
||||
/// uniq expression list == subquery group by expression list
|
||||
if (!expressionListEquals(func->children[0]->as<ASTExpressionList>(), sub_expr_list->as<ASTExpressionList>()))
|
||||
if (!expressionListEquals(func->children[0]->as<ASTExpressionList>(), sub_expr_list->as<ASTExpressionList>(), alias))
|
||||
return false;
|
||||
return true;
|
||||
};
|
||||
|
||||
auto match_group_by = [&]() -> bool
|
||||
auto match_subquery_with_group_by = [&]() -> bool
|
||||
{
|
||||
auto group_by = sub_selectq->groupBy();
|
||||
auto group_by = sub_selectq->groupBy(); // TODO group by type
|
||||
if (!group_by)
|
||||
return false;
|
||||
auto sub_expr_list = sub_selectq->select();
|
||||
if (!sub_expr_list)
|
||||
return false;
|
||||
/// uniq expression list == subquery group by expression list
|
||||
if (!expressionListEquals(func->children[0]->as<ASTExpressionList>(), group_by->as<ASTExpressionList>()))
|
||||
/// uniq expression list == subquery group by expression list
|
||||
if (!expressionListEquals(func->children[0]->as<ASTExpressionList>(), group_by->as<ASTExpressionList>(), alias))
|
||||
return false;
|
||||
/// subquery select expression list must contain all columns in uniq expression list
|
||||
expressionListContainsAll(sub_expr_list->as<ASTExpressionList>(), func->children[0]->as<ASTExpressionList>());
|
||||
if (!expressionListContainsAll(sub_expr_list->as<ASTExpressionList>(), func->children[0]->as<ASTExpressionList>(), alias))
|
||||
return false;
|
||||
return true;
|
||||
};
|
||||
|
||||
if (match_distinct() || match_group_by())
|
||||
if (match_subquery_with_distinct() || match_subquery_with_group_by())
|
||||
expr_list->children[0] = makeASTFunction("count");
|
||||
}
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user