q-Ph#ddlmZddlZddlmZmZmZddlmZm Z ddl m Z ddl m Z ddlmZer ddlmZdd lmZd'dZd(dZd)dZe ddddeddd*d&ZdS)+) annotationsN)IterableMappingSequence) TYPE_CHECKINGAny)unstable) DataFrame)N_INFER_DEFAULT) JSONEncoder)Schemadata/dict[Any, Any] | Sequence[dict[Any, Any] | Any] separatorstr max_levelintencoderr return+dict[Any, Any] | list[dict[Any, Any]] | AnycdkrTi}t|trt|}n't|trfd|D}|S|S|S)Nr)rrrrc6g|]}t|S)rrr)_simple_json_normalize).0rowrrrs X/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/polars/convert/normalize.py z*_simple_json_normalize..#sF$$$ '''# $$$) isinstancedict_normalize_json_orderedlist)rrrrnormalized_json_objectnormalized_json_lists ``` rrrs 1}}!# dD ! ! (%<## &&& " " d # # ($$$$$$ $$$ ( '%% rr key_stringnormalized_dictdict[str, Any]c t|tr_|dkrI|r||nd}|dz }|D]$\}} |r||n|} t| | ||||%n||||<|S|||<|S)a Main recursive function. Designed for the most basic use case of `pl.json_normalize(data)`, intended as a performance improvement. Parameters ---------- data : Any Type dependent on types contained within nested Json key_string : str New key (with separator(s) in) for data normalized_dict : dict The new normalized/flattened Json dict separator : str, default '.' Nested records will generate names separated by sep, e.g., for sep='.', { 'foo' : { 'bar' : 0 } } -> foo.bar max_level recursion depth encoder Custom JSON encoder; if not given, `json.dumps` is used. rrr&r'rrr)r r!items_normalize_json) rr&r'rrrkey_rootnested_max_levelkeyvaluenew_keys rr.r.2s<$+ q==5?G*1i111RH(1} "jjll   U08AX,s,,,c&$3'.#  +2'$--OJ '" "&* # rcii}}|D]%\}}t|tr|||< |||<&t|di|||}i||S)a Order the top level keys and then recursively go to depth. Parameters ---------- data Deserialized JSON objects (dict or list of dicts) separator Nested records will generate names separated by sep. e.g., for `separator=".", {"foo": {"bar": 0}}` -> foo.bar. max_level Max number of levels(depth of dict) to normalize. encoder Custom JSON encoder; if not given, `json.dumps` is used. Returns ------- dict or list of dicts, matching `normalized_json_object` r*r,)r-r r!r.) rrrrtop_ nested_datakvnested_s rr"r"gs2B+D 1 a   KNNDGG  G d g r.T)rrschemastrictinfer_schema_lengthr int | Noner; Schema | Noner<boolr=JSONEncoder | Noner c|d}|dz }t|tr#t|dkrt|St|tr|g}nKt|t r%t|t st|}nd}t|| tj }tt|||||||S) u Normalize semi-structured deserialized JSON data into a flat table. Dictionary objects that will not be unnested/normalized are encoded as json string data. Unlike it pandas' counterpart, this function will not encode dictionaries as objects at any level. .. warning:: This functionality is considered **unstable**. It may be changed at any point without it being considered a breaking change. Parameters ---------- data Deserialized JSON objects. separator Nested records will generate names separated by sep. e.g., for `separator=".", {"foo": {"bar": 0}}` -> foo.bar. max_level Max number of levels(depth of dict) to normalize. If None, normalizes all levels. schema Overwrite the `Schema` when the normalized data is passed to the `DataFrame` constructor. strict Whether Polars should be strict when constructing the DataFrame. infer_schema_length Number of rows to take into consideration to determine the schema. encoder Custom JSON encoder function; if not given, `json.dumps` is used. Examples -------- >>> data = [ ... { ... "id": 1, ... "name": "Cole Volk", ... "fitness": {"height": 180, "weight": 85}, ... }, ... { ... "id": 2, ... "name": "Faye Raker", ... "fitness": {"height": 155, "weight": 58}, ... }, ... { ... "name": "Mark Reg", ... "fitness": {"height": 170, "weight": 78}, ... }, ... ] >>> pl.json_normalize(data, max_level=1) shape: (3, 4) ┌──────┬────────────┬────────────────┬────────────────┐ │ id ┆ name ┆ fitness.height ┆ fitness.weight │ │ --- ┆ --- ┆ --- ┆ --- │ │ i64 ┆ str ┆ i64 ┆ i64 │ ╞══════╪════════════╪════════════════╪════════════════╡ │ 1 ┆ Cole Volk ┆ 180 ┆ 85 │ │ 2 ┆ Faye Raker ┆ 155 ┆ 58 │ │ null ┆ Mark Reg ┆ 170 ┆ 78 │ └──────┴────────────┴────────────────┴────────────────┘ Normalize to a specific depth, using a custom JSON encoder (note that `orson.dumps` encodes to bytes, not str). >>> import orjson >>> pl.json_normalize(data, max_level=0, encoder=orjson.dumps) shape: (3, 3) ┌──────┬────────────┬───────────────────────────────┐ │ id ┆ name ┆ fitness │ │ --- ┆ --- ┆ --- │ │ i64 ┆ str ┆ binary │ ╞══════╪════════════╪═══════════════════════════════╡ │ 1 ┆ Cole Volk ┆ b"{"height":180,"weight":85}" │ │ 2 ┆ Faye Raker ┆ b"{"height":155,"weight":58}" │ │ null ┆ Mark Reg ┆ b"{"height":170,"weight":78}" │ └──────┴────────────┴───────────────────────────────┘ Nlr+r)r;z expected list or dict of objectsr)r;r<r=) r rlenr rrrr# ValueErrorjsondumpsr)rrrr;r<r=rmsgs rjson_normalizerHsp  NI$!!c$ii1nn'''' D' " "v D( # #JtS,A,ADzz0oo*      /    r) rrrrrrrr rr)rrr&rr'r(rrrrrr rr() rr(rrrrrr rr()rrrrrr>r;r?r<r@r=r>rrArr ) __future__rrEcollections.abcrrrtypingrrpolars._utils.unstabler polars.dataframer polars.datatypes.constantsr polars._typingr polars.schemar rr.r"rHrrrRsO#""""" 7777777777%%%%%%%%++++++&&&&&&666666%******$$$$$$@2222j((((V   &5"&rrrrr rrrr