§ q-PhÛ6ãó”—ddlmZddlmZddlmZddlmZddlm Z ddl m Z erddl m Z ddlmZmZmZmZmZGd „d ¦«Zd S) é)Ú annotations)Ú TYPE_CHECKING)Úparse_into_expression)Ú scale_bytes)Ú wrap_expr)Úparse_into_dtype)ÚExpr)Ú EndiannessÚIntoExprÚPolarsDataTypeÚSizeUnitÚTransferEncodingcód—eZdZdZdZd#d„Zd$d „Zd%d „Zd&d„Zddœd'd„Z d(d„Z d)d*d„Z ddœd+d!„Z d"S),ÚExprBinaryNameSpacez&Namespace for bin related expressions.ÚbinÚexprr ÚreturnÚNonecó—|j|_dS)N)Ú_pyexpr)Úselfrs úR/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/polars/expr/binary.pyÚ__init__zExprBinaryNameSpace.__init__s€Ø”|ˆŒ ˆ ˆ óÚliteralr cór—t|d¬¦«}t|j |¦«¦«S)u€ Check if binaries in Series contain a binary substring. Parameters ---------- literal The binary substring to look for Returns ------- Expr Expression of data type :class:`Boolean`. See Also -------- starts_with : Check if the binary substring exists at the start ends_with : Check if the binary substring exists at the end Examples -------- >>> colors = pl.DataFrame( ... { ... "name": ["black", "yellow", "blue"], ... "code": [b"\x00\x00\x00", b"\xff\xff\x00", b"\x00\x00\xff"], ... "lit": [b"\x00", b"\xff\x00", b"\xff\xff"], ... } ... ) >>> colors.select( ... "name", ... pl.col("code").bin.contains(b"\xff").alias("contains_with_lit"), ... pl.col("code").bin.contains(pl.col("lit")).alias("contains_with_expr"), ... ) shape: (3, 3) ┌────────┬───────────────────┬────────────────────┠│ name ┆ contains_with_lit ┆ contains_with_expr │ │ --- ┆ --- ┆ --- │ │ str ┆ bool ┆ bool │ â•žâ•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•¡ │ black ┆ false ┆ true │ │ yellow ┆ true ┆ true │ │ blue ┆ true ┆ false │ └────────┴───────────────────┴────────────────────┘ T©Ú str_as_lit)rrrÚ bin_contains)rrs rÚcontainszExprBinaryNameSpace.containss5€õX(¨¸DÐAÑAÔAˆÝ˜œ×2Ò2°7Ñ;Ô;Ñ<Ô<Ð>> colors = pl.DataFrame( ... { ... "name": ["black", "yellow", "blue"], ... "code": [b"\x00\x00\x00", b"\xff\xff\x00", b"\x00\x00\xff"], ... "suffix": [b"\x00", b"\xff\x00", b"\x00\x00"], ... } ... ) >>> colors.select( ... "name", ... pl.col("code").bin.ends_with(b"\xff").alias("ends_with_lit"), ... pl.col("code").bin.ends_with(pl.col("suffix")).alias("ends_with_expr"), ... ) shape: (3, 3) ┌────────┬───────────────┬────────────────┠│ name ┆ ends_with_lit ┆ ends_with_expr │ │ --- ┆ --- ┆ --- │ │ str ┆ bool ┆ bool │ â•žâ•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•¡ │ black ┆ false ┆ true │ │ yellow ┆ false ┆ true │ │ blue ┆ true ┆ false │ └────────┴───────────────┴────────────────┘ Tr)rrrÚ bin_ends_with)rr!s rÚ ends_withzExprBinaryNameSpace.ends_withLs5€õX' v¸$Ð?Ñ?Ô?ˆÝ˜œ×3Ò3°FÑ;Ô;Ñ<Ô<Ð>> colors = pl.DataFrame( ... { ... "name": ["black", "yellow", "blue"], ... "code": [b"\x00\x00\x00", b"\xff\xff\x00", b"\x00\x00\xff"], ... "prefix": [b"\x00", b"\xff\x00", b"\x00\x00"], ... } ... ) >>> colors.select( ... "name", ... pl.col("code").bin.starts_with(b"\xff").alias("starts_with_lit"), ... pl.col("code") ... .bin.starts_with(pl.col("prefix")) ... .alias("starts_with_expr"), ... ) shape: (3, 3) ┌────────┬─────────────────┬──────────────────┠│ name ┆ starts_with_lit ┆ starts_with_expr │ │ --- ┆ --- ┆ --- │ │ str ┆ bool ┆ bool │ â•žâ•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•¡ │ black ┆ false ┆ true │ │ yellow ┆ true ┆ false │ │ blue ┆ false ┆ true │ └────────┴─────────────────┴──────────────────┘ Tr)rrrÚbin_starts_with)rr%s rÚ starts_withzExprBinaryNameSpace.starts_with{s5€õ\' v¸$Ð?Ñ?Ô?ˆÝ˜œ×5Ò5°fÑ=Ô=Ñ>Ô>Ð>rT)ÚstrictÚencodingrr)ÚboolcóÞ—|dkr't|j |¦«¦«S|dkr't|j |¦«¦«Sd|›}t |¦«‚)uç Decode values using the provided encoding. Parameters ---------- encoding : {'hex', 'base64'} The encoding to use. strict Raise an error if the underlying value cannot be decoded, otherwise mask out with a null value. Returns ------- Expr Expression of data type :class:`Binary`. Examples -------- >>> colors = pl.DataFrame( ... { ... "name": ["black", "yellow", "blue"], ... "encoded": [b"000000", b"ffff00", b"0000ff"], ... } ... ) >>> colors.with_columns( ... pl.col("encoded").bin.decode("hex").alias("code"), ... ) shape: (3, 3) ┌────────┬───────────┬─────────────────┠│ name ┆ encoded ┆ code │ │ --- ┆ --- ┆ --- │ │ str ┆ binary ┆ binary │ â•žâ•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•¡ │ black ┆ b"000000" ┆ b"\x00\x00\x00" │ │ yellow ┆ b"ffff00" ┆ b"\xff\xff\x00" │ │ blue ┆ b"0000ff" ┆ b"\x00\x00\xff" │ └────────┴───────────┴─────────────────┘ ÚhexÚbase64ú1`encoding` must be one of {'hex', 'base64'}, got )rrÚbin_hex_decodeÚbin_base64_decodeÚ ValueError)rr*r)Úmsgs rÚdecodezExprBinaryNameSpace.decode¬sp€ðN uÒ Ð Ý˜Tœ\×8Ò8¸Ñ@Ô@ÑAÔAÐ AØ ˜Ò !Ð !ݘTœ\×;Ò;¸FÑCÔCÑDÔDÐ DàTÈÐTÐTˆCݘS‘/”/Ð !rcóÚ—|dkr&t|j ¦«¦«S|dkr&t|j ¦«¦«Sd|›}t |¦«‚)uS Encode a value using the provided encoding. Parameters ---------- encoding : {'hex', 'base64'} The encoding to use. Returns ------- Expr Expression of data type :class:`Binary`. Examples -------- >>> colors = pl.DataFrame( ... { ... "color": ["black", "yellow", "blue"], ... "code": [b"\x00\x00\x00", b"\xff\xff\x00", b"\x00\x00\xff"], ... } ... ) >>> colors.with_columns( ... pl.col("code").bin.encode("hex").alias("encoded"), ... ) shape: (3, 3) ┌────────┬─────────────────┬─────────┠│ color ┆ code ┆ encoded │ │ --- ┆ --- ┆ --- │ │ str ┆ binary ┆ str │ â•žâ•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•¡ │ black ┆ b"\x00\x00\x00" ┆ 000000 │ │ yellow ┆ b"\xff\xff\x00" ┆ ffff00 │ │ blue ┆ b"\x00\x00\xff" ┆ 0000ff │ └────────┴─────────────────┴─────────┘ r-r.r/)rrÚbin_hex_encodeÚbin_base64_encoder2)rr*r3s rÚencodezExprBinaryNameSpace.encodeÛsl€ðH uÒ Ð Ý˜Tœ\×8Ò8Ñ:Ô:Ñ;Ô;Ð ;Ø ˜Ò !Ð !ݘTœ\×;Ò;Ñ=Ô=Ñ>Ô>Ð >àTÈÐTÐTˆCݘS‘/”/Ð !rÚbÚunitr cór—t|j ¦«¦«}t||¦«}|S)u™ Get the size of binary values in the given unit. Parameters ---------- unit : {'b', 'kb', 'mb', 'gb', 'tb'} Scale the returned size to the given unit. Returns ------- Expr Expression of data type :class:`UInt32` or `Float64`. Examples -------- >>> from os import urandom >>> df = pl.DataFrame({"data": [urandom(n) for n in (512, 256, 1024)]}) >>> df.with_columns( # doctest: +IGNORE_RESULT ... n_bytes=pl.col("data").bin.size(), ... n_kilobytes=pl.col("data").bin.size("kb"), ... ) shape: (4, 3) ┌─────────────────────────────────┬─────────┬─────────────┠│ data ┆ n_bytes ┆ n_kilobytes │ │ --- ┆ --- ┆ --- │ │ binary ┆ u32 ┆ f64 │ â•žâ•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•â•â•â•â•¡ │ b"y?~B\x83\xf4V\x07\xd3\xfb\xb… ┆ 512 ┆ 0.5 │ │ b"\xee$4@f\xc14\x07\x8e\x88\x1… ┆ 256 ┆ 0.25 │ │ b"\x80\xbd\xb9nEq;2\x99$\xf9\x… ┆ 1024 ┆ 1.0 │ └─────────────────────────────────┴─────────┴─────────────┘ )rrÚbin_size_bytesr)rr:Úszs rÚsizezExprBinaryNameSpace.sizes4€õBt”|×2Ò2Ñ4Ô4Ñ 5Ô 5ˆÝ ˜˜TÑ "Ô "ˆØˆ rÚlittle)Ú endiannessÚdtyper r@r cóp—t|¦«}t|j ||¦«¦«S)u± Interpret a buffer as a numerical Polars type. Parameters ---------- dtype : PolarsDataType Which type to interpret binary column into. endianness : {"big", "little"}, optional Which endianness to use when interpreting bytes, by default "little". Returns ------- Expr Expression of data type `dtype`. Note that if binary array is too short value will be null. If binary array is too long, remainder will be ignored. Examples -------- >>> df = pl.DataFrame({"data": [b"\x05\x00\x00\x00", b"\x10\x00\x01\x00"]}) >>> df.with_columns( # doctest: +IGNORE_RESULT ... bin2int=pl.col("data").bin.reinterpret( ... dtype=pl.Int32, endianness="little" ... ), ... ) shape: (2, 2) ┌─────────────────────┬─────────┠│ data ┆ bin2int │ │ --- ┆ --- │ │ binary ┆ i32 │ â•žâ•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•â•ªâ•â•â•â•â•â•â•â•â•â•¡ │ b"\x05\x00\x00\x00" ┆ 5 │ │ b"\x10\x00\x01\x00" ┆ 65552 │ └─────────────────────┴─────────┘ )rrrÚ from_buffer)rrAr@s rÚ reinterpretzExprBinaryNameSpace.reinterpret,s2€õL! Ñ'Ô'ˆå˜œ×1Ò1°%¸ÑDÔDÑEÔEÐErN)rr rr)rr rr )r!r rr )r%r rr )r*rr)r+rr )r*rrr )r9)r:r rr )rAr r@r rr ) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú _accessorrr r$r(r4r8r>rD©rrrrsô€€€€€Ø0Ð0à€Ið$ð$ð$ð$ð-=ð-=ð-=ð-=ð^-=ð-=ð-=ð-=ð^/?ð/?ð/?ð/?ðbDHð-"ð-"ð-"ð-"ð-"ð-"ð^*"ð*"ð*"ð*"ðX#ð#ð#ð#ð#ðLBJð(Fð(Fð(Fð(Fð(Fð(Fð(Fð(FrrN)Ú __future__rÚtypingrÚpolars._utils.parserÚpolars._utils.variousrÚpolars._utils.wraprÚpolars.datatypesrÚpolarsr Úpolars._typingr r r r rrrJrrúrSsðØ"Ð"Ð"Ð"Ð"Ð"à Ð Ð Ð Ð Ð à5Ð5Ð5Ð5Ð5Ð5Ø-Ð-Ð-Ð-Ð-Ð-Ø(Ð(Ð(Ð(Ð(Ð(Ø-Ð-Ð-Ð-Ð-Ð-àðØÐÐÐÐÐðððððððððððððððFðFðFðFðFñFôFðFðFðFr