o $if: @s ddlmZddlmZmZzddlmZmZmZm Z m Z m Z m Z m Z mZWney=Zz edeedddZ[wwzddlmZddlmZWney^Gdd d ZeZYnwdd d Zddd d efddZd efddZddZefddZdddZdS))Table) Expressionfield) DeclarationExecNodeOptionsTableSourceNodeOptionsFilterNodeOptionsProjectNodeOptionsAggregateNodeOptionsOrderByNodeOptionsHashJoinNodeOptionsAsofJoinNodeOptionsz@The pyarrow installation is not built with support for 'acero' ()N)ScanNodeOptionsc@s(eZdZGdddZGdddZdS)DatasetModuleStubc@ eZdZdS)zDatasetModuleStub.DatasetN__name__ __module__ __qualname__rrF/var/www/html/corbot_env/lib/python3.10/site-packages/pyarrow/acero.pyDataset3rc@r)z!DatasetModuleStub.InMemoryDatasetNrrrrrInMemoryDataset6rrN)rrrrrrrrrr2srTcCsltdt||d}dd|jjD}t|tdt|g}|jd}|dur4t|tdt|g}|S)Nscan use_threadscSsg|]}t|qSr)r).0frrr @sz$_dataset_to_decl..projectfilter) rrschemanames from_sequencer _scan_optionsgetr)datasetrdecl projections filter_exprrrr_dataset_to_decl;s r,Fc  s~t|ttjfstdt|t|ttjfs"tdt|it|ttfs.|g}t|D]\} } | | <q2it|ttfsG|g}t|D]\} } | | <qK|j j } |j j } |dksd|dkrgg} n*|dkso|dkrrg} n|dksz|dkrfdd | D} n |d krfd d | D} i}t| D] \} }||vr| ||<qi}t| D] \} }||vr| ||<qt|tjrt ||d }nt d t |}t|tjrt ||d }nt d t |}|rt|||| | |pd|pdd}n t||||pd|pdd}t d|||gd}|r|dkrt| }t| }t| }g}g}t| | D]n\} }| t| krW||vrW|||||}|tdt| t||gq%| |krc||vrcq%|rt| |krt||vrt||7}|r| |kr||vr||7}|||t| q%t dt||}t ||g}|j|d }| tkr|S| tjkrt|Std)a\ Perform join of two tables or datasets. The result will be an output table with the result of the join operation Parameters ---------- join_type : str One of supported join types. left_operand : Table or Dataset The left operand for the join operation. left_keys : str or list[str] The left key (or keys) on which the join operation should be performed. right_operand : Table or Dataset The right operand for the join operation. right_keys : str or list[str] The right key (or keys) on which the join operation should be performed. left_suffix : str, default None Which suffix to add to left column names. This prevents confusion when the columns in left and right operands have colliding names. right_suffix : str, default None Which suffix to add to the right column names. This prevents confusion when the columns in left and right operands have colliding names. use_threads : bool, default True Whether to use multithreading or not. coalesce_keys : bool, default False If the duplicated keys should be omitted from one of the sides in the join result. output_type: Table or InMemoryDataset The output type for the exec plan result. Returns ------- result_table : Table or InMemoryDataset Expected Table or Dataset, got z left semiz left antiz right semiz right antiinnerz left outercg|]}|vr|qSrrrcol)right_keys_orderrrr z!_perform_join..z right outercr/rrr0)left_keys_orderrrr r3r table_source)output_suffix_for_leftoutput_suffix_for_righthashjoinoptionsinputsz full outercoalescer!Unsupported output type) isinstancerdsr TypeErrortypetuplelist enumerater#r$r,rrr setlenappendr_call_fieldr r%to_tabler) join_type left_operand left_keys right_operand right_keys left_suffix right_suffixr coalesce_keys output_typeidxkey left_columns right_columnsleft_column_keys_indicescolnameright_column_keys_indices left_source right_source join_optsr)left_columns_setright_columns_setright_operand_indexprojected_col_namesr*r1right_key_index projection result_tabler)r4r2r _perform_joinPs(                     rfc sPt|ttjfstdt|t|ttjfs"tdt|t|ttfs,|g}tttfs6gfdd|jj D} t |jj t | @} | rUt d | t|tjrbt ||d} ntdt|} t|tjrvt ||d} ntdt|} t|||} td| | | gd}|j|d}|tkr|S|tjkrt|Std ) a- Perform asof join of two tables or datasets. The result will be an output table with the result of the join operation Parameters ---------- left_operand : Table or Dataset The left operand for the join operation. left_on : str The left key (or keys) on which the join operation should be performed. left_by: str or list[str] The left key (or keys) on which the join operation should be performed. right_operand : Table or Dataset The right operand for the join operation. right_on : str or list[str] The right key (or keys) on which the join operation should be performed. right_by: str or list[str] The right key (or keys) on which the join operation should be performed. tolerance : int The tolerance to use for the asof join. The tolerance is interpreted in the same units as the "on" key. output_type: Table or InMemoryDataset The output type for the exec plan result. Returns ------- result_table : Table or InMemoryDataset r-csg|] }|gvr|qSrrr0right_byright_onrrr -s z&_perform_join_asof..zOColumns {} present in both tables. AsofJoin does not support column collisions.rr5asofjoinr:r>)r?rr@rrArBrCrDr#r$rF ValueErrorformatr,rrr rKr)rMleft_onleft_byrOrirh tolerancerrTrXcolumns_collisionsr\r]r^r)rerrgr_perform_join_asofsN!        rqcCs2ttdt|dtdt|dg}|jddS)aFilter rows of a table based on the provided expression. The result will be an output table with only the rows matching the provided expression. Parameters ---------- table : Table or Dataset Table or Dataset that should be filtered. expression : Expression The expression on which rows should be filtered. Returns ------- Table r5)r;r"Tr)rr%rrrK)table expressionr)rrr _filter_tableWs  rtcKst|tjr t|dd}ntdt|}tdt|fi|}t||g}|jdd}|t kr2|S|tj kr) r?r@rr,rrr r%rKrrrA)table_or_dataset sort_keysrTkwargs data_sourcerur)rerrr _sort_sourceos    rzc Cs2ttdt|tdt||dg}|j|dS)Nr5 aggregate)keysr)rr%rr rK)rr aggregatesr|rr)rrr _group_bys   r~)T) pyarrow.librpyarrow.computerrpyarrow._acerorrrrr r r r r ImportErrorexcstrpyarrow.datasetr(r@pyarrow._datasetrrr,rfrqrtrzr~rrrrs> 0     4 V