AHjoUddlmZddlmZmZddlmZddlmZm Z m Z m Z ddl m Z ddlmZerQddlZddlmZdd lmZej*e5dd lmZddddd lmZdd lmZdd lmZmZddlmZddl m!Z!GddZ"GddZ#edGddZ$edGddZ%edGddZ&ee&gdfZ'de(d<edGddZ) d!d Z*y#1swYxYw)") annotations)CallableMapping) dataclass) TYPE_CHECKINGClassVarLiteral TypeAlias)parse_into_list_of_expressions)issue_unstable_warningN)Path) DataFrame)PyExpr)Sequence)IO)StorageOptionsDictSyncOnCloseMethod)Expr)CredentialProviderBuilderceZdZUded<y)_InternalPlPathProviderConfigz ClassVar[str]pl_path_provider_idN)__name__ __module__ __qualname____annotations__K/root/tools/cai/cai_env/lib/python3.12/site-packages/polars/io/partition.pyrrs&&rrc@eZdZdZdddddd ddZy) PartitionBya Configuration for writing to multiple output files. .. warning:: This functionality is currently considered **unstable**. It may be changed at any point without it being considered a breaking change. Parameters ---------- base_path Base path to write to. file_path_provider Callable for custom file output paths. key Expressions to partition by. include_key Include the partition key expression outputs in the output files. max_rows_per_file Maximum number of rows to write for each file. Note that files may have less than this amount of rows. approximate_bytes_per_file Approximate number of bytes to write to each file. This is measured as the estimated size of the DataFrame in memory. Examples -------- Split to multiple files partitioned by year: >>> pl.LazyFrame({"year": [2026, 2027, 1970], "month": [0, 0, 0]}).sink_parquet( ... pl.PartitionBy("data/", key="year") ... ) # doctest: +SKIP Split to multiple files based on size: >>> pl.LazyFrame({"year": [2026, 2027, 1970], "month": [0, 0, 0]}).sink_parquet( ... pl.PartitionBy( ... "data/", max_rows_per_file=1000, approximate_bytes_per_file=100_000_000 ... ) ... ) # doctest: +SKIP Split to multiple files partitioned by year, with limits on individual file sizes: >>> pl.LazyFrame({"year": [2026, 2027, 1970], "month": [0, 0, 0]}).sink_parquet( ... pl.PartitionBy( ... "data/", ... key="year", ... max_rows_per_file=1000, ... approximate_bytes_per_file=100_000_000, ... ) ... ) # doctest: +SKIP Nauto)file_path_providerkey include_keymax_rows_per_fileapproximate_bytes_per_filecd}t||||dk(r d}t||| d}t|t|}|dk(r|dnd}|d}t||| t |nd||||_y)Nz2`PartitionBy` functionality is considered unstabler"zlat least one of ('key', 'max_rows_per_file', 'approximate_bytes_per_file') must be specified for PartitionByz1cannot use 'include_key' without specifying 'key'll) base_pathr#r$r%r&r')r ValueErrorstr_PartitionByInner_parse_to_pyexpr_list_pl_partition_by)selfr)r#r$r%r&r'msgs r__init__zPartitionBy.__init__TsCs# K!)*f44  S/ ! ;;2ECS/ ! N % /!2!:  ' & -)6 & 11.1o%c*4#/'A ! r)r)z str | Pathr#eCallable[[FileProviderArgs], str | Path | IO[bytes] | IO[str]] | _InternalPlPathProviderConfig | Noner$z=str | Expr | Sequence[str | Expr] | Mapping[str, Expr] | Noner% bool | Noner& int | Noner'zint | Literal['auto'] | NonereturnNone)rrr__doc__r1rrrr!r!sd2xMQ#'(,CI2 2  2 K2 !2 &2 %A2  2 rr!T)kw_onlyc&eZdZUdZded<ded<y)FileProviderArgsz Holds information on the file being sinked to. .. warning:: This functionality is currently considered **unstable**. It may be changed at any point without it being considered a breaking change. intindex_in_partitionrpartition_keysNrrrr7rrrrr:r:srr:cNeZdZUdZded<ded<ded<ded <d ed <d ed <y)r,zG Holds parsed partitioned sink options. For internal use. r+r)r2r#zlist[PyExpr] | Noner$r3r%r4r&r;r'Nr>rrrr,r,s2 N  !! ##rr,ceZdZUdZded<y)SinkedPathsCallbackArgszInformation on sinked paths.z list[str]pathsNr>rrrrArAs & rrAr SinkedPathsCallbackc^eZdZUdZded<ded<dZded<dZded <dZd ed <dZd ed <y) _SinkOptionsz Holds sink options that are generic over file / target type. For internal use. Most of the options will parse into `UnifiedSinkArgs`. boolmkdirmaintain_orderNzSyncOnCloseMethod | None sync_on_closezStorageOptionsDict | Nonestorage_optionsz CredentialProviderBuilder | Nonecredential_providerzSinkedPathsCallback | Nonesinked_paths_callback) rrrr7rrIrJrKrLrrrrErEsD K.2M+226O.5<@9@8<5rds"-!>>C9   [ )'&')D V''g g T 4    4$$$& 4 "*+B*CT*I!JYJ 4==="<L<