From 8e82fafefe8cbea9ffbd0f89ec64eb49358c8504 Mon Sep 17 00:00:00 2001 From: Hyukjin Kwon Date: Thu, 19 Nov 2026 16:55:14 +0000 Subject: [PATCH] [SPARK-62101][CONNECT][PYTHON] Give the Connect Column, WindowSpec, TableArg, DataFrameNaFunctions, DataFrameStatFunctions and functions modules PySpark's docstrings as help() shows them, and compare the docstrings of every module A sweep of the docstrings of both clients, on master daacf3d1, of the modules of pyspark.sql and pyspark.errors, found 65 of Spark Connect not PySpark's: - 59 of the Column, the WindowSpec, the TableArg, the DataFrameNaFunctions and the DataFrameStatFunctions and their members, of which 55 inherit their docstrings in PySpark and 4 have none (Column.astype, Column.name, Column.to_plan and TableArg.to_plan); - the module docstrings of pyspark.sql.connect.column, window, table_arg, functions and functions.builtin; - Read.print of pyspark.sql.connect.plan, which inherits its docstring in PySpark. PySpark Connect's classes there are subclasses of the classic ones, and neither they nor their members have docstrings of their own: their __doc__ is None, and inspect.getdoc and help() show those of the classic class, of their MRO. The drop-in's classes are native, virtual subclasses of the classic ones, which are not in their MRO, and their docstrings were their own doc comments, or none. - gen_connect_docstrings.py generates the docstrings that inspect.getdoc finds of the classes of INHERITING and of their members in PySpark, of the classic class (connect_doc!(Column.alias) is that of the classic Column.alias), but of an alias, of none (Column.name and Column.astype): the native Column, WindowSpec, TableArg, DataFrameNaFunctions and DataFrameStatFunctions (column.rs, window.rs, tablearg.rs, the NA functions of dataframe.rs, stat.rs) and their members take them. So inspect.getdoc and help() show PySpark's text, and their __doc__ is that text, where PySpark Connect's own is None. Their doc comments are plain comments now. - The modules connect/column.py, window.py, table_arg.py and functions/builtin.py have no docstring, as PySpark Connect's, of which their text stays as a comment; connect/functions/__init__.py has PySpark Connect's. - Read.print has the docstring of PySpark Connect's LogicalPlan.print, which inspect.getdoc finds of its own of none, as the drop-in's LogicalPlan has no print. - tests/golden/runtime_docstrings.json covers every module of pyspark.sql and pyspark.errors now: 5137 docstrings of 125 modules, of 3854 of 111. Each is of its kind, which its note gives: of the __doc__ of the object, or, of an object of no docstring of its own that inherits one (677 of them), {"getdoc": digest} of its inspect.getdoc, which help() shows. It leaves out the docstrings that are not all PySpark's yet: the DataFrame class of both DataFrame modules, and the modules of the session and its client (pyspark.sql.connect.session and pyspark.sql.connect.client). With the DataFrame class, it leaves out the docstrings that can only match PySpark's once those of the class do: the module docstrings of both DataFrame modules, and the 9 members of the classic DataFrameNaFunctions and DataFrameStatFunctions that copy the DataFrame's (drop.__doc__ = DataFrame.dropna.__doc__). The test compares at least 3500 docstrings now (3993). - known-differences.md describes the docstrings of the native classes, and docs/compatibility.md which docstrings the golden holds and leaves out. Co-authored-by: Isaac --- crates/pyspark-rs/src/column.rs | 115 +- .../pyspark-rs/src/connect_docs_generated.rs | 2082 ++++++++- crates/pyspark-rs/src/dataframe.rs | 16 +- crates/pyspark-rs/src/stat.rs | 35 +- crates/pyspark-rs/src/tablearg.rs | 22 +- crates/pyspark-rs/src/window.rs | 15 +- dev/parity/known-differences.md | 9 + docs/compatibility.md | 13 +- python/pyspark/sql/connect/column.py | 2 +- .../pyspark/sql/connect/functions/__init__.py | 5 +- .../pyspark/sql/connect/functions/builtin.py | 15 +- python/pyspark/sql/connect/plan.py | 15 + python/pyspark/sql/connect/table_arg.py | 8 +- python/pyspark/sql/connect/window.py | 12 +- python/tests/_runtime_docstrings.py | 102 +- .../test_dropin_class_modules_offline.py | 19 +- scripts/capture_runtime_docstrings_golden.py | 14 +- scripts/gen_connect_docstrings.py | 86 +- tests/golden/runtime_docstrings.json | 3887 ++++++++++++++--- 19 files changed, 5722 insertions(+), 750 deletions(-) diff --git a/crates/pyspark-rs/src/column.rs b/crates/pyspark-rs/src/column.rs index 2a51bbcc6..d850b4714 100644 --- a/crates/pyspark-rs/src/column.rs +++ b/crates/pyspark-rs/src/column.rs @@ -36,7 +36,8 @@ pub(crate) fn column_reference_name(column: PyRef<'_, PyColumn>) -> Option, column: &Column) -> PyResult, @@ -363,7 +365,7 @@ impl PyColumn { ))) } - /// Alias for `alias` (pyspark `Column.name`). + // Alias for `alias` (pyspark `Column.name`). #[pyo3(signature = (*alias, **kwargs))] fn name( &self, @@ -375,23 +377,26 @@ impl PyColumn { self.alias(py, alias, kwargs) } - /// Apply a transformation function to this column. Mirrors `Column.transform(f)`, - /// which is simply `f(self)`. + // Apply a transformation function to this column. Mirrors `Column.transform(f)`, + // which is simply `f(self)`. + #[doc = connect_doc!(Column.transform)] fn transform<'py>(slf: Bound<'py, Self>, f: Bound<'py, PyAny>) -> PyResult> { let _origin = crate::origin::with_origin("transform")?; f.call1((slf,)) } - /// Mark this column as an outer reference (for correlated subqueries / lateral - /// joins). Mirrors `Column.outer()`, which returns the same expression — outer - /// resolution is performed server-side via the plan id. + // Mark this column as an outer reference (for correlated subqueries / lateral + // joins). Mirrors `Column.outer()`, which returns the same expression — outer + // resolution is performed server-side via the plan id. + #[doc = connect_doc!(Column.outer)] fn outer(&self) -> PyResult { let _origin = crate::origin::with_origin("outer")?; Ok(PyColumn::new(self.column.clone())) } - /// Cast to a different type. Accepts a `DataType` or a DDL type string, - /// matching `pyspark.sql.Column.cast`. + // Cast to a different type. Accepts a `DataType` or a DDL type string, + // matching `pyspark.sql.Column.cast`. + #[doc = connect_doc!(Column.cast)] fn cast(&self, dataType: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("cast")?; // As PySpark's, of a DataType or a str. @@ -405,15 +410,16 @@ impl PyColumn { cast_column(&self.column, dataType, false) } - /// Alias for `cast` (pyspark `Column.astype`). + // Alias for `cast` (pyspark `Column.astype`). fn astype(&self, dataType: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("astype")?; self.cast(dataType) } - /// Try to cast, yielding NULL on failure. Accepts a `DataType` or DDL string. - /// Mirrors `pyspark.sql.Column.try_cast`. + // Try to cast, yielding NULL on failure. Accepts a `DataType` or DDL string. + // Mirrors `pyspark.sql.Column.try_cast`. #[pyo3(name = "try_cast")] + #[doc = connect_doc!(Column.try_cast)] fn try_cast(&self, dataType: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("try_cast")?; // As PySpark's: a DataType or a str, else NOT_EXPECTED_TYPE. @@ -429,10 +435,11 @@ impl PyColumn { cast_column(&self.column, dataType, true) } - /// Get an item from a list/map by key (pyspark `Column.getItem`), with PySpark's - /// FutureWarning for a Column as the key, of the line of its `warnings.warn` in - /// `pyspark.sql.connect.column` (see `warn_as_pyspark`). + // Get an item from a list/map by key (pyspark `Column.getItem`), with PySpark's + // FutureWarning for a Column as the key, of the line of its `warnings.warn` in + // `pyspark.sql.connect.column` (see `warn_as_pyspark`). #[pyo3(name = "getItem")] + #[doc = connect_doc!(Column.getItem)] fn get_item(&self, key: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("getItem")?; if key.extract::>().is_ok() { @@ -454,21 +461,24 @@ impl PyColumn { self.__getitem__(key) } - /// Check if NULL. + // Check if NULL. #[pyo3(name = "isNull")] + #[doc = connect_doc!(Column.isNull)] fn is_null(&self) -> PyResult { let _origin = crate::origin::with_origin("isNull")?; Ok(PyColumn::new(self.column.clone().is_null())) } - /// Check if NOT NULL. + // Check if NOT NULL. #[pyo3(name = "isNotNull")] + #[doc = connect_doc!(Column.isNotNull)] fn is_not_null(&self) -> PyResult { let _origin = crate::origin::with_origin("isNotNull")?; Ok(PyColumn::new(self.column.clone().is_not_null())) } - /// Substring extraction (start and length as columns). + // Substring extraction (start and length as columns). + #[doc = connect_doc!(Column.substr)] fn substr(&self, startPos: &Bound<'_, PyAny>, length: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("substr")?; // As PySpark: the arguments, as values of an Enum, must be of one type, a Column or @@ -514,79 +524,91 @@ impl PyColumn { )) } - /// Pattern matching with LIKE, of any value, as PySpark's `_bin_op("like", ...)`. + // Pattern matching with LIKE, of any value, as PySpark's `_bin_op("like", ...)`. + #[doc = connect_doc!(Column.like)] fn like(&self, other: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("like")?; binary_function("like", &self.column, other) } - /// Pattern matching with RLIKE (regex). + // Pattern matching with RLIKE (regex). + #[doc = connect_doc!(Column.rlike)] fn rlike(&self, other: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("rlike")?; binary_function("rlike", &self.column, other) } - /// Check if contains another column value. + // Check if contains another column value. + #[doc = connect_doc!(Column.contains)] fn contains(&self, other: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("contains")?; let other_col = operand_column(other)?; Ok(PyColumn::new(self.column.clone().contains(other_col))) } - /// Check if starts with another column value. + // Check if starts with another column value. + #[doc = connect_doc!(Column.startswith)] fn startswith(&self, other: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("startswith")?; let other_col = operand_column(other)?; Ok(PyColumn::new(self.column.clone().startswith(other_col))) } - /// Check if ends with another column value. + // Check if ends with another column value. + #[doc = connect_doc!(Column.endswith)] fn endswith(&self, other: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("endswith")?; let other_col = operand_column(other)?; Ok(PyColumn::new(self.column.clone().endswith(other_col))) } - /// Ascending sort. + // Ascending sort. + #[doc = connect_doc!(Column.asc)] fn asc(&self) -> PyResult { let _origin = crate::origin::with_origin("asc")?; // As PySpark's `asc`, which is its `asc_nulls_first`, of the origin of that. self.asc_nulls_first() } - /// Ascending sort with nulls first. + // Ascending sort with nulls first. + #[doc = connect_doc!(Column.asc_nulls_first)] fn asc_nulls_first(&self) -> PyResult { let _origin = crate::origin::with_origin("asc_nulls_first")?; Ok(PyColumn::new(self.column.clone().asc_nulls_first())) } - /// Ascending sort with nulls last. + // Ascending sort with nulls last. + #[doc = connect_doc!(Column.asc_nulls_last)] fn asc_nulls_last(&self) -> PyResult { let _origin = crate::origin::with_origin("asc_nulls_last")?; Ok(PyColumn::new(self.column.clone().asc_nulls_last())) } - /// Descending sort. + // Descending sort. + #[doc = connect_doc!(Column.desc)] fn desc(&self) -> PyResult { let _origin = crate::origin::with_origin("desc")?; // As PySpark's `desc`, which is its `desc_nulls_last`, of the origin of that. self.desc_nulls_last() } - /// Descending sort with nulls first. + // Descending sort with nulls first. + #[doc = connect_doc!(Column.desc_nulls_first)] fn desc_nulls_first(&self) -> PyResult { let _origin = crate::origin::with_origin("desc_nulls_first")?; Ok(PyColumn::new(self.column.clone().desc_nulls_first())) } - /// Descending sort with nulls last. + // Descending sort with nulls last. + #[doc = connect_doc!(Column.desc_nulls_last)] fn desc_nulls_last(&self) -> PyResult { let _origin = crate::origin::with_origin("desc_nulls_last")?; Ok(PyColumn::new(self.column.clone().desc_nulls_last())) } - /// A branch more of a CASE WHEN. Mirrors `Column.when`: the condition is a Column, and - /// the column a `when()` without `otherwise()` (`INVALID_WHEN_USAGE`). + // A branch more of a CASE WHEN. Mirrors `Column.when`: the condition is a Column, and + // the column a `when()` without `otherwise()` (`INVALID_WHEN_USAGE`). + #[doc = connect_doc!(Column.when)] fn when(&self, condition: &Bound<'_, PyAny>, value: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("when")?; let py = condition.py(); @@ -620,8 +642,9 @@ impl PyColumn { )) } - /// The value of a CASE WHEN when no branch holds. Mirrors `Column.otherwise`, which - /// raises PySparkTypeError for a column that is not a `when()`, or one that has one. + // The value of a CASE WHEN when no branch holds. Mirrors `Column.otherwise`, which + // raises PySparkTypeError for a column that is not a `when()`, or one that has one. + #[doc = connect_doc!(Column.otherwise)] fn otherwise(&self, value: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("otherwise")?; let message = match self.column.expression().node() { @@ -825,8 +848,9 @@ impl PyColumn { Ok(PyColumn::new(self.column.clone().neg())) } - /// Get field by name (for struct/nested types). + // Get field by name (for struct/nested types). #[pyo3(name = "getField")] + #[doc = connect_doc!(Column.getField)] fn get_field(&self, name: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("getField")?; // As PySpark's, `self[name]`, with a FutureWarning for a Column, of the line of its @@ -848,7 +872,8 @@ impl PyColumn { self.__getitem__(name) } - /// Apply a window function over a window specification. + // Apply a window function over a window specification. + #[doc = connect_doc!(Column.over)] fn over(&self, window: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("over")?; let Ok(window) = window.extract::>() else { @@ -875,8 +900,8 @@ impl PyColumn { PyColumnExpression::new(self.column.clone()) } - /// The `spark.connect.Expression` of this column, as PySpark Connect's `Column.to_plan`: that - /// of its expression, of `pyspark.sql.connect.proto`. + // The `spark.connect.Expression` of this column, as PySpark Connect's `Column.to_plan`: that + // of its expression, of `pyspark.sql.connect.proto`. fn to_plan(&self, py: Python<'_>, session: &Bound<'_, PyAny>) -> PyResult> { self._expr().to_plan(py, session) } @@ -1245,6 +1270,7 @@ impl PyColumn { } // --- named Column methods (PySpark camelCase) --- + #[doc = connect_doc!(Column.between)] fn between( &self, py: Python<'_>, @@ -1259,39 +1285,46 @@ impl PyColumn { lower.__and__(py, upper) } #[pyo3(name = "bitwiseAND")] + #[doc = connect_doc!(Column.bitwiseAND)] fn bitwise_and(&self, py: Python<'_>, other: Py) -> PyResult { let _origin = crate::origin::with_origin("bitwiseAND")?; let o = operand_column(other.bind(py))?; Ok(PyColumn::new(self.column.clone().bitwise_and(o))) } #[pyo3(name = "bitwiseOR")] + #[doc = connect_doc!(Column.bitwiseOR)] fn bitwise_or(&self, py: Python<'_>, other: Py) -> PyResult { let _origin = crate::origin::with_origin("bitwiseOR")?; let o = operand_column(other.bind(py))?; Ok(PyColumn::new(self.column.clone().bitwise_or(o))) } #[pyo3(name = "bitwiseXOR")] + #[doc = connect_doc!(Column.bitwiseXOR)] fn bitwise_xor(&self, py: Python<'_>, other: Py) -> PyResult { let _origin = crate::origin::with_origin("bitwiseXOR")?; let o = operand_column(other.bind(py))?; Ok(PyColumn::new(self.column.clone().bitwise_xor(o))) } + #[doc = connect_doc!(Column.ilike)] fn ilike(&self, other: &Bound<'_, PyAny>) -> PyResult { let _origin = crate::origin::with_origin("ilike")?; binary_function("ilike", &self.column, other) } #[pyo3(name = "isNaN")] + #[doc = connect_doc!(Column.isNaN)] fn is_nan(&self) -> PyResult { let _origin = crate::origin::with_origin("isNaN")?; Ok(PyColumn::new(self.column.clone().is_nan())) } #[pyo3(name = "eqNullSafe")] + #[doc = connect_doc!(Column.eqNullSafe)] fn eq_null_safe(&self, py: Python<'_>, other: Py) -> PyResult { let _origin = crate::origin::with_origin("eqNullSafe")?; let o = operand_column(other.bind(py))?; Ok(PyColumn::new(self.column.clone().eq_null_safe(o))) } #[pyo3(signature = (*cols))] + #[doc = connect_doc!(Column.isin)] fn isin(&self, py: Python<'_>, cols: Vec>) -> PyResult { let _origin = crate::origin::with_origin("isin")?; // As pyspark's, a single DataFrame makes an IN subquery of it. @@ -1328,6 +1361,7 @@ impl PyColumn { Ok(PyColumn::new(self.column.clone().isin(vals))) } #[pyo3(name = "withField")] + #[doc = connect_doc!(Column.withField)] fn with_field( &self, fieldName: &Bound<'_, PyAny>, @@ -1353,6 +1387,7 @@ impl PyColumn { )) } #[pyo3(name = "dropFields", signature = (*fieldNames))] + #[doc = connect_doc!(Column.dropFields)] fn drop_fields(&self, py: Python<'_>, fieldNames: Vec>) -> PyResult { let _origin = crate::origin::with_origin("dropFields")?; // As PySpark's, of strings, at least one, which each `DropField` sets when it builds the diff --git a/crates/pyspark-rs/src/connect_docs_generated.rs b/crates/pyspark-rs/src/connect_docs_generated.rs index ab2310f07..3d229ee49 100644 --- a/crates/pyspark-rs/src/connect_docs_generated.rs +++ b/crates/pyspark-rs/src/connect_docs_generated.rs @@ -4,7 +4,10 @@ //! The docstrings that PySpark Connect's modules give the methods of their classes of //! PySpark's classic classes (`format.__doc__ = PySparkDataStreamReader.format.__doc__`), //! of the classes of those modules that are native here, which take them of their `#[doc]` -//! attributes. +//! attributes; those of the native types of `pyspark.sql.types`; and those that +//! `inspect.getdoc` finds of the classic classes of PySpark Connect's subclasses of them, +//! of no docstrings of their own (`Column.alias`), of which the native classes are virtual +//! subclasses. /// The docstring of the object `$name` of PySpark Connect's module, as PySpark has it at /// run time: `connect_doc!(DataStreamReader.format)`, of the textual scope of the modules @@ -8010,4 +8013,2081 @@ macro_rules! connect_doc { True "# }; + (Column) => { + r#" + A column in a DataFrame. + + .. versionadded:: 1.3.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Examples + -------- + Column instances can be created by + + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + + Select a column out of a DataFrame + >>> df.name + Column<'name'> + >>> df["name"] + Column<'name'> + + Create from an expression + + >>> df.age + 1 + Column<...> + >>> 1 / df.age + Column<...> + "# + }; + (Column . eqNullSafe) => { + r#" + Equality test that is safe for null values. + + .. versionadded:: 2.3.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + other + a value or :class:`Column` + + Examples + -------- + >>> from pyspark.sql import Row + >>> df1 = spark.createDataFrame([ + ... Row(id=1, value='foo'), + ... Row(id=2, value=None) + ... ]) + >>> df1.select( + ... df1['value'] == 'foo', + ... df1['value'].eqNullSafe('foo'), + ... df1['value'].eqNullSafe(None) + ... ).show() + +-------------+---------------+----------------+ + |(value = foo)|(value <=> foo)|(value <=> NULL)| + +-------------+---------------+----------------+ + | true| true| false| + | NULL| false| true| + +-------------+---------------+----------------+ + >>> df2 = spark.createDataFrame([ + ... Row(value = 'bar'), + ... Row(value = None) + ... ]) + >>> df1.join(df2, df1["value"] == df2["value"]).count() + 0 + >>> df1.join(df2, df1["value"].eqNullSafe(df2["value"])).count() + 1 + >>> df2 = spark.createDataFrame([ + ... Row(id=1, value=float('NaN')), + ... Row(id=2, value=42.0), + ... Row(id=3, value=None) + ... ]) + >>> df2.select( + ... df2['value'].eqNullSafe(None), + ... df2['value'].eqNullSafe(float('NaN')), + ... df2['value'].eqNullSafe(42.0) + ... ).show() + +----------------+---------------+----------------+ + |(value <=> NULL)|(value <=> NaN)|(value <=> 42.0)| + +----------------+---------------+----------------+ + | false| true| false| + | false| false| true| + | true| false| false| + +----------------+---------------+----------------+ + + Notes + ----- + Unlike Pandas, PySpark doesn't consider NaN values to be NULL. See the + `NaN Semantics `_ + for details. + "# + }; + (Column . bitwiseOR) => { + r#" + Compute bitwise OR of this expression with another expression. + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + other + a value or :class:`Column` to calculate bitwise or(|) with + this :class:`Column`. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame([Row(a=170, b=75)]) + >>> df.select(df.a.bitwiseOR(df.b)).collect() + [Row((a | b)=235)] + "# + }; + (Column . bitwiseAND) => { + r#" + Compute bitwise AND of this expression with another expression. + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + other + a value or :class:`Column` to calculate bitwise and(&) with + this :class:`Column`. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame([Row(a=170, b=75)]) + >>> df.select(df.a.bitwiseAND(df.b)).collect() + [Row((a & b)=10)] + "# + }; + (Column . bitwiseXOR) => { + r#" + Compute bitwise XOR of this expression with another expression. + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + other + a value or :class:`Column` to calculate bitwise xor(^) with + this :class:`Column`. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame([Row(a=170, b=75)]) + >>> df.select(df.a.bitwiseXOR(df.b)).collect() + [Row((a ^ b)=225)] + "# + }; + (Column . isNull) => { + r#" + True if the current expression is null. + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame([Row(name='Tom', height=80), Row(name='Alice', height=None)]) + >>> df.filter(df.height.isNull()).collect() + [Row(name='Alice', height=None)] + "# + }; + (Column . isNotNull) => { + r#" + True if the current expression is NOT null. + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame([Row(name='Tom', height=80), Row(name='Alice', height=None)]) + >>> df.filter(df.height.isNotNull()).collect() + [Row(name='Tom', height=80)] + "# + }; + (Column . isNaN) => { + r#" + True if the current expression is NaN. + + .. versionadded:: 4.0.0 + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame( + ... [Row(name='Tom', height=80.0), Row(name='Alice', height=float('nan'))]) + >>> df.filter(df.height.isNaN()).collect() + [Row(name='Alice', height=nan)] + "# + }; + (Column . contains) => { + r#" + Contains the other element. Returns a boolean :class:`Column` based on a string match. + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + other + string in line. A value as a literal or a :class:`Column`. + + Examples + -------- + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.filter(df.name.contains('o')).collect() + [Row(age=5, name='Bob')] + "# + }; + (Column . startswith) => { + r#" + String starts with. Returns a boolean :class:`Column` based on a string match. + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + other : :class:`Column` or str + string at start of line (do not use a regex `^`) + + Examples + -------- + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.filter(df.name.startswith('Al')).collect() + [Row(age=2, name='Alice')] + >>> df.filter(df.name.startswith('^Al')).collect() + [] + "# + }; + (Column . endswith) => { + r#" + String ends with. Returns a boolean :class:`Column` based on a string match. + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + other : :class:`Column` or str + string at end of line (do not use a regex `$`) + + Examples + -------- + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.filter(df.name.endswith('ice')).collect() + [Row(age=2, name='Alice')] + >>> df.filter(df.name.endswith('ice$')).collect() + [] + "# + }; + (Column . when) => { + r#" + Evaluates a list of conditions and returns one of multiple possible result expressions. + If :func:`Column.otherwise` is not invoked, None is returned for unmatched conditions. + + .. versionadded:: 1.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + condition : :class:`Column` + a boolean :class:`Column` expression. + value + a literal value, or a :class:`Column` expression. + + Returns + ------- + :class:`Column` + Column representing whether each element of Column is in conditions. + + Examples + -------- + Example 1: Using :func:`when` with conditions and values to create a new Column + + >>> from pyspark.sql import functions as sf + >>> df = spark.createDataFrame([(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> result = df.select(df.name, sf.when(df.age > 4, 1).when(df.age < 3, -1).otherwise(0)) + >>> result.show() + +-----+------------------------------------------------------------+ + | name|CASE WHEN (age > 4) THEN 1 WHEN (age < 3) THEN -1 ELSE 0 END| + +-----+------------------------------------------------------------+ + |Alice| -1| + | Bob| 1| + +-----+------------------------------------------------------------+ + + Example 2: Chaining multiple :func:`when` conditions + + >>> from pyspark.sql import functions as sf + >>> df = spark.createDataFrame([(1, "Alice"), (4, "Bob"), (6, "Charlie")], ["age", "name"]) + >>> result = df.select( + ... df.name, + ... sf.when(df.age < 3, "Young").when(df.age < 5, "Middle-aged").otherwise("Old") + ... ) + >>> result.show() + +-------+---------------------------------------------------------------------------+ + | name|CASE WHEN (age < 3) THEN Young WHEN (age < 5) THEN Middle-aged ELSE Old END| + +-------+---------------------------------------------------------------------------+ + | Alice| Young| + | Bob| Middle-aged| + |Charlie| Old| + +-------+---------------------------------------------------------------------------+ + + Example 3: Using literal values as conditions + + >>> from pyspark.sql import functions as sf + >>> df = spark.createDataFrame([(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> result = df.select( + ... df.name, sf.when(sf.lit(True), 1).otherwise( + ... sf.raise_error("unreachable")).alias("when")) + >>> result.show() + +-----+----+ + | name|when| + +-----+----+ + |Alice| 1| + | Bob| 1| + +-----+----+ + + See Also + -------- + pyspark.sql.functions.when + "# + }; + (Column . otherwise) => { + r#" + Evaluates a list of conditions and returns one of multiple possible result expressions. + If :func:`Column.otherwise` is not invoked, None is returned for unmatched conditions. + + .. versionadded:: 1.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + value + a literal value, or a :class:`Column` expression. + + Returns + ------- + :class:`Column` + Column representing whether each element of Column is unmatched conditions. + + Examples + -------- + >>> from pyspark.sql import functions as sf + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.select(df.name, sf.when(df.age > 3, 1).otherwise(0)).show() + +-----+-------------------------------------+ + | name|CASE WHEN (age > 3) THEN 1 ELSE 0 END| + +-----+-------------------------------------+ + |Alice| 0| + | Bob| 1| + +-----+-------------------------------------+ + + See Also + -------- + pyspark.sql.functions.when + "# + }; + (Column . like) => { + r#" + SQL like expression. Returns a boolean :class:`Column` based on a SQL LIKE match. + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + other : str + a SQL LIKE pattern + + See Also + -------- + pyspark.sql.Column.rlike + + Returns + ------- + :class:`Column` + Column of booleans showing whether each element + in the Column is matched by SQL LIKE pattern. + + Examples + -------- + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.filter(df.name.like('Al%')).collect() + [Row(age=2, name='Alice')] + "# + }; + (Column . rlike) => { + r#" + SQL RLIKE expression (LIKE with Regex). Returns a boolean :class:`Column` based on a regex + match. + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + other : str + an extended regex expression + + Returns + ------- + :class:`Column` + Column of booleans showing whether each element + in the Column is matched by extended regex expression. + + Examples + -------- + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.filter(df.name.rlike('ice$')).collect() + [Row(age=2, name='Alice')] + "# + }; + (Column . ilike) => { + r#" + SQL ILIKE expression (case insensitive LIKE). Returns a boolean :class:`Column` + based on a case insensitive match. + + .. versionadded:: 3.3.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + other : str + a SQL LIKE pattern + + See Also + -------- + pyspark.sql.Column.rlike + + Returns + ------- + :class:`Column` + Column of booleans showing whether each element + in the Column is matched by SQL LIKE pattern. + + Examples + -------- + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.filter(df.name.ilike('%Ice')).collect() + [Row(age=2, name='Alice')] + "# + }; + (Column . substr) => { + r#" + Return a :class:`Column` which is a substring of the column. + + .. versionadded:: 1.3.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + startPos : :class:`Column` or int + start position + length : :class:`Column` or int + length of the substring + + Returns + ------- + :class:`Column` + Column representing whether each element of Column is substr of origin Column. + + Examples + -------- + + Example 1. Using integers for the input arguments. + + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.select(df.name.substr(1, 3).alias("col")).collect() + [Row(col='Ali'), Row(col='Bob')] + + Example 2. Using columns for the input arguments. + + >>> df = spark.createDataFrame( + ... [(3, 4, "Alice"), (2, 3, "Bob")], ["sidx", "eidx", "name"]) + >>> df.select(df.name.substr(df.sidx, df.eidx).alias("col")).collect() + [Row(col='ice'), Row(col='ob')] + "# + }; + (Column . alias) => { + r#" + Returns this column aliased with a new name or names (in the case of expressions that + return more than one column, such as explode). + + .. versionadded:: 1.3.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + alias : str + desired column names (collects all positional arguments passed) + + Other Parameters + ---------------- + metadata: dict + a dict of information to be stored in ``metadata`` attribute of the + corresponding :class:`StructField ` (optional, keyword + only argument) + + .. versionchanged:: 2.2.0 + Added optional ``metadata`` argument. + + Returns + ------- + :class:`Column` + Column representing whether each element of Column is aliased with new name or names. + + Examples + -------- + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.select(df.age.alias("age2")).collect() + [Row(age2=2), Row(age2=5)] + >>> df.select(df.age.alias("age3", metadata={'max': 99})).schema['age3'].metadata['max'] + 99 + "# + }; + (Column . asc) => { + r#" + Returns a sort expression based on the ascending order of the column. + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame([('Tom', 80), ('Alice', None)], ["name", "height"]) + >>> df.select(df.name).orderBy(df.name.asc()).collect() + [Row(name='Alice'), Row(name='Tom')] + "# + }; + (Column . asc_nulls_first) => { + r#" + Returns a sort expression based on ascending order of the column, and null values + return before non-null values. + + .. versionadded:: 2.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame( + ... [('Tom', 80), (None, 60), ('Alice', None)], ["name", "height"]) + >>> df.select(df.name).orderBy(df.name.asc_nulls_first()).collect() + [Row(name=None), Row(name='Alice'), Row(name='Tom')] + + "# + }; + (Column . asc_nulls_last) => { + r#" + Returns a sort expression based on ascending order of the column, and null values + appear after non-null values. + + .. versionadded:: 2.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame( + ... [('Tom', 80), (None, 60), ('Alice', None)], ["name", "height"]) + >>> df.select(df.name).orderBy(df.name.asc_nulls_last()).collect() + [Row(name='Alice'), Row(name='Tom'), Row(name=None)] + + "# + }; + (Column . desc) => { + r#" + Returns a sort expression based on the descending order of the column. + + .. versionadded:: 2.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame([('Tom', 80), ('Alice', None)], ["name", "height"]) + >>> df.select(df.name).orderBy(df.name.desc()).collect() + [Row(name='Tom'), Row(name='Alice')] + "# + }; + (Column . desc_nulls_first) => { + r#" + Returns a sort expression based on the descending order of the column, and null values + appear before non-null values. + + .. versionadded:: 2.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame( + ... [('Tom', 80), (None, 60), ('Alice', None)], ["name", "height"]) + >>> df.select(df.name).orderBy(df.name.desc_nulls_first()).collect() + [Row(name=None), Row(name='Tom'), Row(name='Alice')] + + "# + }; + (Column . desc_nulls_last) => { + r#" + Returns a sort expression based on the descending order of the column, and null values + appear after non-null values. + + .. versionadded:: 2.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame( + ... [('Tom', 80), (None, 60), ('Alice', None)], ["name", "height"]) + >>> df.select(df.name).orderBy(df.name.desc_nulls_last()).collect() + [Row(name='Tom'), Row(name='Alice'), Row(name=None)] + "# + }; + (Column . cast) => { + r#" + Casts the column into type ``dataType``. + + .. versionadded:: 1.3.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + dataType : :class:`DataType` or str + a DataType or Python string literal with a DDL-formatted string + to use when parsing the column to the same type. + + Returns + ------- + :class:`Column` + Column representing whether each element of Column is cast into new type. + + Examples + -------- + >>> from pyspark.sql.types import StringType + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.select(df.age.cast("string").alias('ages')).collect() + [Row(ages='2'), Row(ages='5')] + >>> df.select(df.age.cast(StringType()).alias('ages')).collect() + [Row(ages='2'), Row(ages='5')] + "# + }; + (Column . try_cast) => { + r#" + This is a special version of `cast` that performs the same operation, but returns a NULL + value instead of raising an error if the invoke method throws exception. + + .. versionadded:: 4.0.0 + + Parameters + ---------- + dataType : :class:`DataType` or str + a DataType or Python string literal with a DDL-formatted string + to use when parsing the column to the same type. + + Returns + ------- + :class:`Column` + Column representing whether each element of Column is cast into new type. + + Examples + -------- + Example 1: Cast with a Datatype + + >>> from pyspark.sql.types import LongType + >>> df = spark.createDataFrame( + ... [(2, "123"), (5, "Bob"), (3, None)], ["age", "name"]) + >>> df.select(df.name.try_cast(LongType())).show() + +----+ + |name| + +----+ + | 123| + |NULL| + |NULL| + +----+ + + Example 2: Cast with a DDL string + + >>> df = spark.createDataFrame( + ... [(2, "123"), (5, "Bob"), (3, None)], ["age", "name"]) + >>> df.select(df.name.try_cast("double")).show() + +-----+ + | name| + +-----+ + |123.0| + | NULL| + | NULL| + +-----+ + "# + }; + (Column . over) => { + r#" + Define a windowing column. + + .. versionadded:: 1.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + window : :class:`WindowSpec` + + Returns + ------- + :class:`Column` + + Examples + -------- + >>> from pyspark.sql import Window + >>> window = ( + ... Window.partitionBy("name") + ... .orderBy("age") + ... .rowsBetween(Window.unboundedPreceding, Window.currentRow) + ... ) + >>> from pyspark.sql.functions import rank, min, desc + >>> df = spark.createDataFrame( + ... [(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.withColumn( + ... "rank", rank().over(window) + ... ).withColumn( + ... "min", min('age').over(window) + ... ).sort(desc("age")).show() + +---+-----+----+---+ + |age| name|rank|min| + +---+-----+----+---+ + | 5| Bob| 1| 5| + | 2|Alice| 1| 2| + +---+-----+----+---+ + "# + }; + (Column . transform) => { + r#" + Applies a transformation function to this column. + + This method allows you to apply a function that takes a Column and returns a Column, + enabling method chaining and functional transformations. + + .. versionadded:: 4.1.0 + + Parameters + ---------- + f : callable + A function that takes a :class:`Column` and returns a :class:`Column`. + + Returns + ------- + :class:`Column` + The result of applying the function to this column. + + Examples + -------- + Example 1: Chain built-in functions + + >>> from pyspark.sql.functions import trim, upper + >>> df = spark.createDataFrame([(" hello ",), (" world ",)], ["text"]) + >>> df.select(df.text.transform(trim).transform(upper).alias("result")).show() + +------+ + |result| + +------+ + | HELLO| + | WORLD| + +------+ + + Example 2: Use lambda functions + + >>> df = spark.createDataFrame([(10,), (20,), (30,)], ["value"]) + >>> df.select( + ... df.value.transform(lambda c: c + 5) + ... .transform(lambda c: c * 2) + ... .transform(lambda c: c - 10).alias("result") + ... ).show() + +------+ + |result| + +------+ + | 20| + | 40| + | 60| + +------+ + "# + }; + (Column . outer) => { + r#" + Mark this column as an outer column if its expression refers to columns from an outer query. + + This is used to trigger lazy analysis of Spark Classic DataFrame, so that we can use it + to build subquery expressions. Spark Connect DataFrame is always lazily analyzed and + does not need to use this function. + + .. versionadded:: 4.0.0 + + See Also + -------- + pyspark.sql.DataFrame.scalar + pyspark.sql.DataFrame.exists + + Examples + -------- + >>> from pyspark.sql import functions as sf + >>> employees = spark.createDataFrame( + ... [ + ... (1, "Alice", 45000, 101), (2, "Bob", 54000, 101), (3, "Charlie", 29000, 102), + ... (4, "David", 61000, 102), (5, "Eve", 48000, 101), + ... ], + ... ["id", "name", "salary", "department_id"], + ... ) + >>> employees.alias("e1").where( + ... sf.col("salary") > employees.alias("e2").where( + ... sf.col("e2.department_id") == sf.col("e1.department_id").outer() + ... ).select(sf.avg("salary")).scalar() + ... ).select("name", "salary", "department_id").orderBy("name").show() + +-----+------+-------------+ + | name|salary|department_id| + +-----+------+-------------+ + | Bob| 54000| 101| + |David| 61000| 102| + +-----+------+-------------+ + "# + }; + (Column . isin) => { + r#" + A boolean expression that is evaluated to true if the value of this + expression is contained by the evaluated values of the arguments. + + .. versionadded:: 1.5.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + .. versionchanged:: 4.1.0 + Also takes a single :class:`DataFrame` to be used as IN subquery. + + Parameters + ---------- + cols : Any + The values to compare with the column values. The result will only be true at a location + if any value matches in the Column. + + Returns + ------- + :class:`Column` + Column of booleans showing whether each element in the Column is contained in cols. + + Examples + -------- + >>> df = spark.createDataFrame([(2, "Alice"), (5, "Bob"), (8, "Mike")], ["age", "name"]) + + Example 1: Filter rows with names in the specified values + + >>> df[df.name.isin("Bob", "Mike")].orderBy("age").show() + +---+----+ + |age|name| + +---+----+ + | 5| Bob| + | 8|Mike| + +---+----+ + + Example 2: Filter rows with ages in the specified list + + >>> df[df.age.isin([1, 2, 3])].show() + +---+-----+ + |age| name| + +---+-----+ + | 2|Alice| + +---+-----+ + + Example 3: Filter rows with names not in the specified values + + >>> df[~df.name.isin("Alice", "Bob")].show() + +---+----+ + |age|name| + +---+----+ + | 8|Mike| + +---+----+ + + Example 4: Take a :class:`DataFrame` and work as IN subquery + + >>> df.where(df.age.isin(spark.range(6))).orderBy("age").show() + +---+-----+ + |age| name| + +---+-----+ + | 2|Alice| + | 5| Bob| + +---+-----+ + + Example 5: Multiple values for IN subquery + + >>> from pyspark.sql.functions import lit, struct + >>> df.where(struct(df.age, df.name).isin(spark.range(6).select("id", lit("Bob")))).show() + +---+----+ + |age|name| + +---+----+ + | 5| Bob| + +---+----+ + "# + }; + (Column . between) => { + r#" + Check if the current column's values are between the specified lower and upper + bounds, inclusive. + + .. versionadded:: 1.3.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + lowerBound : :class:`Column`, int, float, string, bool, datetime, date or Decimal + The lower boundary value, inclusive. + upperBound : :class:`Column`, int, float, string, bool, datetime, date or Decimal + The upper boundary value, inclusive. + + Returns + ------- + :class:`Column` + A new column of boolean values indicating whether each element in the original + column is within the specified range (inclusive). + + Examples + -------- + Using between with integer values. + + >>> df = spark.createDataFrame([(2, "Alice"), (5, "Bob")], ["age", "name"]) + >>> df.select(df.name, df.age.between(2, 4)).show() + +-----+---------------------------+ + | name|((age >= 2) AND (age <= 4))| + +-----+---------------------------+ + |Alice| true| + | Bob| false| + +-----+---------------------------+ + + Using between with string values. + + >>> df = spark.createDataFrame([("Alice", "A"), ("Bob", "B")], ["name", "initial"]) + >>> df.select(df.name, df.initial.between("A", "B")).show() + +-----+-----------------------------------+ + | name|((initial >= A) AND (initial <= B))| + +-----+-----------------------------------+ + |Alice| true| + | Bob| true| + +-----+-----------------------------------+ + + Using between with float values. + + >>> df = spark.createDataFrame( + ... [(2.5, "Alice"), (5.5, "Bob")], ["height", "name"]) + >>> df.select(df.name, df.height.between(2.0, 5.0)).show() + +-----+-------------------------------------+ + | name|((height >= 2.0) AND (height <= 5.0))| + +-----+-------------------------------------+ + |Alice| true| + | Bob| false| + +-----+-------------------------------------+ + + Using between with date values. + + >>> import pyspark.sql.functions as sf + >>> df = spark.createDataFrame( + ... [("Alice", "2023-01-01"), ("Bob", "2023-02-01")], ["name", "date"]) + >>> df = df.withColumn("date", sf.to_date(df.date)) + >>> df.select(df.name, df.date.between("2023-01-01", "2023-01-15")).show() + +-----+-----------------------------------------------+ + | name|((date >= 2023-01-01) AND (date <= 2023-01-15))| + +-----+-----------------------------------------------+ + |Alice| true| + | Bob| false| + +-----+-----------------------------------------------+ + >>> from datetime import date + >>> df.select(df.name, df.date.between(date(2023, 1, 1), date(2023, 1, 15))).show() + +-----+-------------------------------------------------------------+ + | name|((date >= DATE '2023-01-01') AND (date <= DATE '2023-01-15'))| + +-----+-------------------------------------------------------------+ + |Alice| true| + | Bob| false| + +-----+-------------------------------------------------------------+ + + Using between with timestamp values. + + >>> import pyspark.sql.functions as sf + >>> df = spark.createDataFrame( + ... [("Alice", "2023-01-01 10:00:00"), ("Bob", "2023-02-01 10:00:00")], + ... schema=["name", "timestamp"]) + >>> df = df.withColumn("timestamp", sf.to_timestamp(df.timestamp)) + >>> df.select(df.name, df.timestamp.between("2023-01-01", "2023-02-01")).show() + +-----+---------------------------------------------------------+ + | name|((timestamp >= 2023-01-01) AND (timestamp <= 2023-02-01))| + +-----+---------------------------------------------------------+ + |Alice| true| + | Bob| false| + +-----+---------------------------------------------------------+ + >>> df.select(df.name, df.timestamp.between("2023-01-01", "2023-02-01 12:00:00")).show() + +-----+------------------------------------------------------------------+ + | name|((timestamp >= 2023-01-01) AND (timestamp <= 2023-02-01 12:00:00))| + +-----+------------------------------------------------------------------+ + |Alice| true| + | Bob| true| + +-----+------------------------------------------------------------------+ + "# + }; + (Column . getItem) => { + r#" + An expression that gets an item at position ``ordinal`` out of a list, + or gets an item by key out of a dict. + + .. versionadded:: 1.3.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + key + a literal value, or a :class:`Column` expression. + The result will only be true at a location if the item matches in the column. + + .. deprecated:: 3.0.0 + :class:`Column` as a parameter is deprecated. + + Returns + ------- + :class:`Column` + Column representing the item(s) got at position out of a list or by key out of a dict. + + Examples + -------- + >>> df = spark.createDataFrame([([1, 2], {"key": "value"})], ["l", "d"]) + >>> df.select(df.l.getItem(0), df.d.getItem("key")).show() + +----+------+ + |l[0]|d[key]| + +----+------+ + | 1| value| + +----+------+ + "# + }; + (Column . getField) => { + r#" + An expression that gets a field by name in a :class:`StructType`. + + .. versionadded:: 1.3.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + name + a literal value, or a :class:`Column` expression. + The result will only be true at a location if the field matches in the Column. + + .. deprecated:: 3.0.0 + :class:`Column` as a parameter is deprecated. + Returns + ------- + :class:`Column` + Column representing whether each element of Column got by name. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame([Row(r=Row(a=1, b="b"))]) + >>> df.select(df.r.getField("b")).show() + +---+ + |r.b| + +---+ + | b| + +---+ + >>> df.select(df.r.a).show() + +---+ + |r.a| + +---+ + | 1| + +---+ + "# + }; + (Column . withField) => { + r#" + An expression that adds/replaces a field in :class:`StructType` by name. + + .. versionadded:: 3.1.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + fieldName : str + a literal value. + The result will only be true at a location if any field matches in the Column. + col : :class:`Column` + A :class:`Column` expression for the column with `fieldName`. + + Returns + ------- + :class:`Column` + Column representing whether each element of Column + which field was added/replaced by fieldName. + + Examples + -------- + >>> from pyspark.sql import Row + >>> from pyspark.sql.functions import lit + >>> df = spark.createDataFrame([Row(a=Row(b=1, c=2))]) + >>> df.withColumn('a', df['a'].withField('b', lit(3))).select('a.b').show() + +---+ + | b| + +---+ + | 3| + +---+ + >>> df.withColumn('a', df['a'].withField('d', lit(4))).select('a.d').show() + +---+ + | d| + +---+ + | 4| + +---+ + "# + }; + (Column . dropFields) => { + r#" + An expression that drops fields in :class:`StructType` by name. + This is a no-op if the schema doesn't contain field name(s). + + .. versionadded:: 3.1.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + fieldNames : str + Desired field names (collects all positional arguments passed) + The result will drop at a location if any field matches in the Column. + + Returns + ------- + :class:`Column` + Column representing whether each element of Column with field dropped by fieldName. + + Examples + -------- + >>> from pyspark.sql import Row + >>> from pyspark.sql.functions import col, lit + >>> df = spark.createDataFrame([ + ... Row(a=Row(b=1, c=2, d=3, e=Row(f=4, g=5, h=6)))]) + >>> df.withColumn('a', df['a'].dropFields('b')).show() + +-----------------+ + | a| + +-----------------+ + |{2, 3, {4, 5, 6}}| + +-----------------+ + + >>> df.withColumn('a', df['a'].dropFields('b', 'c')).show() + +--------------+ + | a| + +--------------+ + |{3, {4, 5, 6}}| + +--------------+ + + This method supports dropping multiple nested fields directly e.g. + + >>> df.withColumn("a", col("a").dropFields("e.g", "e.h")).show() + +--------------+ + | a| + +--------------+ + |{1, 2, 3, {4}}| + +--------------+ + + However, if you are going to add/replace multiple nested fields, + it is preferred to extract out the nested struct before + adding/replacing multiple fields e.g. + + >>> df.select(col("a").withField( + ... "e", col("a.e").dropFields("g", "h")).alias("a") + ... ).show() + +--------------+ + | a| + +--------------+ + |{1, 2, 3, {4}}| + +--------------+ + + "# + }; + (WindowSpec) => { + r#" + A window specification that defines the partitioning, ordering, + and frame boundaries. + + Use the static methods in :class:`Window` to create a :class:`WindowSpec`. + + .. versionadded:: 1.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + "# + }; + (WindowSpec . partitionBy) => { + r#" + Defines the partitioning columns in a :class:`WindowSpec`. + + .. versionadded:: 1.4.0 + + Parameters + ---------- + cols : str, :class:`Column` or list + names of columns or expressions + "# + }; + (WindowSpec . orderBy) => { + r#" + Defines the ordering columns in a :class:`WindowSpec`. + + .. versionadded:: 1.4.0 + + Parameters + ---------- + cols : str, :class:`Column` or list + names of columns or expressions + "# + }; + (WindowSpec . rowsBetween) => { + r#" + Defines the frame boundaries, from `start` (inclusive) to `end` (inclusive). + + Both `start` and `end` are relative positions from the current row. + For example, "0" means "current row", while "-1" means the row before + the current row, and "5" means the fifth row after the current row. + + We recommend users use ``Window.unboundedPreceding``, ``Window.unboundedFollowing``, + and ``Window.currentRow`` to specify special boundary values, rather than using integral + values directly. + + .. versionadded:: 1.4.0 + + Parameters + ---------- + start : int + boundary start, inclusive. + The frame is unbounded if this is ``Window.unboundedPreceding``, or + any value less than or equal to max(-sys.maxsize, -9223372036854775808). + end : int + boundary end, inclusive. + The frame is unbounded if this is ``Window.unboundedFollowing``, or + any value greater than or equal to min(sys.maxsize, 9223372036854775807). + "# + }; + (WindowSpec . rangeBetween) => { + r#" + Defines the frame boundaries, from `start` (inclusive) to `end` (inclusive). + + Both `start` and `end` are relative from the current row. For example, + "0" means "current row", while "-1" means one off before the current row, + and "5" means the five off after the current row. + + We recommend users use ``Window.unboundedPreceding``, ``Window.unboundedFollowing``, + and ``Window.currentRow`` to specify special boundary values, rather than using integral + values directly. + + .. versionadded:: 1.4.0 + + Parameters + ---------- + start : int + boundary start, inclusive. + The frame is unbounded if this is ``Window.unboundedPreceding``, or + any value less than or equal to max(-sys.maxsize, -9223372036854775808). + end : int + boundary end, inclusive. + The frame is unbounded if this is ``Window.unboundedFollowing``, or + any value greater than or equal to min(sys.maxsize, 9223372036854775807). + "# + }; + (TableArg) => { + r#" + Represents a table argument in PySpark. + + This class provides methods to specify partitioning, ordering, and + single-partition constraints when passing a DataFrame as a table argument + to TVF(Table-Valued Function)s including UDTF(User-Defined Table Function)s. + "# + }; + (TableArg . partitionBy) => { + r#" + Partitions the data based on the specified columns. + + This method partitions the table argument data by the specified columns. + It must be called before `orderBy()` and cannot be called after + `withSinglePartition()` has been called. + + Parameters + ---------- + cols : str, :class:`Column`, or list + Column names or :class:`Column` objects to partition by. + + Returns + ------- + :class:`TableArg` + A new `TableArg` instance with partitioning applied. + + Examples + -------- + >>> from pyspark.sql.functions import udtf + >>> + >>> @udtf(returnType="key: int, value: string") + ... class ProcessUDTF: + ... def eval(self, row): + ... yield row["key"], row["value"] + ... + >>> df = spark.createDataFrame( + ... [(1, "a"), (1, "b"), (2, "c"), (2, "d")], ["key", "value"] + ... ) + >>> + >>> # Partition by a single column + >>> result = ProcessUDTF(df.asTable().partitionBy("key")) + >>> result.show() + +---+-----+ + |key|value| + +---+-----+ + | 1| a| + | 1| b| + | 2| c| + | 2| d| + +---+-----+ + >>> + >>> # Partition by multiple columns + >>> df2 = spark.createDataFrame( + ... [(1, "x", 10), (1, "x", 20), (2, "y", 30)], ["key", "category", "value"] + ... ) + >>> result2 = ProcessUDTF(df2.asTable().partitionBy("key", "category")) + >>> result2.show() + +---+-----+ + |key|value| + +---+-----+ + | 1| x| + | 1| x| + | 2| y| + +---+-----+ + "# + }; + (TableArg . orderBy) => { + r#" + Orders the data within each partition by the specified columns. + + This method orders the data within partitions. It must be called after + `partitionBy()` or `withSinglePartition()` has been called. + + Parameters + ---------- + cols : str, :class:`Column`, or list + Column names or :class:`Column` objects to order by. Columns can be + ordered in ascending or descending order using :meth:`Column.asc` or + :meth:`Column.desc`. + + Returns + ------- + :class:`TableArg` + A new `TableArg` instance with ordering applied. + + Examples + -------- + >>> from pyspark.sql.functions import udtf + >>> + >>> @udtf(returnType="key: int, value: string") + ... class ProcessUDTF: + ... def eval(self, row): + ... yield row["key"], row["value"] + ... + >>> df = spark.createDataFrame( + ... [(1, "b"), (1, "a"), (2, "d"), (2, "c")], ["key", "value"] + ... ) + >>> + >>> # Order by a single column within partitions + >>> result = ProcessUDTF(df.asTable().partitionBy("key").orderBy("value")) + >>> result.show() + +---+-----+ + |key|value| + +---+-----+ + | 1| a| + | 1| b| + | 2| c| + | 2| d| + +---+-----+ + >>> + >>> # Order by multiple columns + >>> df2 = spark.createDataFrame( + ... [(1, "a", 2), (1, "a", 1), (1, "b", 3)], ["key", "value", "num"] + ... ) + >>> result2 = ProcessUDTF(df2.asTable().partitionBy("key").orderBy("value", "num")) + >>> result2.show() + +---+-----+ + |key|value| + +---+-----+ + | 1| a| + | 1| a| + | 1| b| + +---+-----+ + >>> + >>> # Order by descending order + >>> result3 = ProcessUDTF(df.asTable().partitionBy("key").orderBy(df.value.desc())) + >>> result3.show() + +---+-----+ + |key|value| + +---+-----+ + | 1| b| + | 1| a| + | 2| d| + | 2| c| + +---+-----+ + "# + }; + (TableArg . withSinglePartition) => { + r#" + Forces the data to be processed in a single partition. + + This method indicates that all data should be treated as a single partition. + It cannot be called after `partitionBy()` has been called. `orderBy()` can + be called after this method to order the data within the single partition. + + Returns + ------- + :class:`TableArg` + A new `TableArg` instance with single partition constraint applied. + + Examples + -------- + >>> from pyspark.sql.functions import udtf + >>> + >>> @udtf(returnType="key: int, value: string") + ... class ProcessUDTF: + ... def eval(self, row): + ... yield row["key"], row["value"] + ... + >>> df = spark.createDataFrame( + ... [(1, "a"), (2, "b"), (3, "c")], ["key", "value"] + ... ) + >>> + >>> # Process all data in a single partition + >>> result = ProcessUDTF(df.asTable().withSinglePartition()) + >>> result.show() + +---+-----+ + |key|value| + +---+-----+ + | 1| a| + | 2| b| + | 3| c| + +---+-----+ + >>> + >>> # Use withSinglePartition and orderBy together + >>> df2 = spark.createDataFrame( + ... [(3, "c"), (1, "a"), (2, "b")], ["key", "value"] + ... ) + >>> result2 = ProcessUDTF(df2.asTable().withSinglePartition().orderBy("key")) + >>> result2.show() + +---+-----+ + |key|value| + +---+-----+ + | 1| a| + | 2| b| + | 3| c| + +---+-----+ + "# + }; + (DataFrameNaFunctions) => { + r#"Functionality for working with missing data in :class:`DataFrame`. + + .. versionadded:: 1.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + "# + }; + (DataFrameNaFunctions . fill) => { + r#"Returns a new :class:`DataFrame` which null values are filled with new value. + :func:`DataFrame.fillna` and :func:`DataFrameNaFunctions.fill` are + aliases of each other. + + .. versionadded:: 1.3.1 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + value : int, float, string, bool or dict, the value to replace null values with. + If the value is a dict, then `subset` is ignored and `value` must be a mapping + from column name (string) to replacement value. The replacement value must be + an int, float, boolean, or string. + subset : str, tuple or list, optional + optional list of column names to consider. + Columns specified in subset that do not have matching data types are ignored. + For example, if `value` is a string, and subset contains a non-string column, + then the non-string column is simply ignored. + + Returns + ------- + :class:`DataFrame` + DataFrame with replaced null values. + + Examples + -------- + >>> df = spark.createDataFrame([ + ... (10, 80.5, "Alice", None), + ... (5, None, "Bob", None), + ... (None, None, "Tom", None), + ... (None, None, None, True)], + ... schema=["age", "height", "name", "bool"]) + + Example 1: Fill all null values with 50 for numeric columns. + + >>> df.na.fill(50).show() + +---+------+-----+----+ + |age|height| name|bool| + +---+------+-----+----+ + | 10| 80.5|Alice|NULL| + | 5| 50.0| Bob|NULL| + | 50| 50.0| Tom|NULL| + | 50| 50.0| NULL|true| + +---+------+-----+----+ + + Example 2: Fill all null values with ``False`` for boolean columns. + + >>> df.na.fill(False).show() + +----+------+-----+-----+ + | age|height| name| bool| + +----+------+-----+-----+ + | 10| 80.5|Alice|false| + | 5| NULL| Bob|false| + |NULL| NULL| Tom|false| + |NULL| NULL| NULL| true| + +----+------+-----+-----+ + + Example 3: Fill all null values with to 50 and "unknown" for + 'age' and 'name' column respectively. + + >>> df.na.fill({'age': 50, 'name': 'unknown'}).show() + +---+------+-------+----+ + |age|height| name|bool| + +---+------+-------+----+ + | 10| 80.5| Alice|NULL| + | 5| NULL| Bob|NULL| + | 50| NULL| Tom|NULL| + | 50| NULL|unknown|true| + +---+------+-------+----+ + + Example 4: Fill all null values with "Spark" for 'name' column. + + >>> df.na.fill(value = 'Spark', subset = 'name').show() + +----+------+-----+----+ + | age|height| name|bool| + +----+------+-----+----+ + | 10| 80.5|Alice|NULL| + | 5| NULL| Bob|NULL| + |NULL| NULL| Tom|NULL| + |NULL| NULL|Spark|true| + +----+------+-----+----+ + "# + }; + (DataFrameNaFunctions . drop) => { + r#"Returns a new :class:`DataFrame` omitting rows with null or NaN values. + :func:`DataFrame.dropna` and :func:`DataFrameNaFunctions.drop` are + aliases of each other. + + .. versionadded:: 1.3.1 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + how : str, optional, the values that can be 'any' or 'all', default 'any'. + If 'any', drop a row if it contains any nulls. + If 'all', drop a row only if all its values are null. + thresh: int, optional, default None. + If specified, drop rows that have less than `thresh` non-null values. + This overwrites the `how` parameter. + subset : str, tuple or list, optional + optional list of column names to consider. + + Returns + ------- + :class:`DataFrame` + DataFrame with null only rows excluded. + + Examples + -------- + >>> from pyspark.sql import Row + >>> df = spark.createDataFrame([ + ... Row(age=10, height=80.0, name="Alice"), + ... Row(age=5, height=float("nan"), name="Bob"), + ... Row(age=None, height=None, name="Tom"), + ... Row(age=None, height=float("nan"), name=None), + ... ]) + + Example 1: Drop the row if it contains any null or NaN. + + >>> df.na.drop().show() + +---+------+-----+ + |age|height| name| + +---+------+-----+ + | 10| 80.0|Alice| + +---+------+-----+ + + Example 2: Drop the row only if all its values are null or NaN. + + >>> df.na.drop(how='all').show() + +----+------+-----+ + | age|height| name| + +----+------+-----+ + | 10| 80.0|Alice| + | 5| NaN| Bob| + |NULL| NULL| Tom| + +----+------+-----+ + + Example 3: Drop rows that have less than `thresh` non-null and non-NaN values. + + >>> df.na.drop(thresh=2).show() + +---+------+-----+ + |age|height| name| + +---+------+-----+ + | 10| 80.0|Alice| + | 5| NaN| Bob| + +---+------+-----+ + + Example 4: Drop rows with null and NaN values in the specified columns. + + >>> df.na.drop(subset=['age', 'name']).show() + +---+------+-----+ + |age|height| name| + +---+------+-----+ + | 10| 80.0|Alice| + | 5| NaN| Bob| + +---+------+-----+ + "# + }; + (DataFrameNaFunctions . replace) => { + r#"Returns a new :class:`DataFrame` replacing a value with another value. + :func:`DataFrame.replace` and :func:`DataFrameNaFunctions.replace` are + aliases of each other. + Values to_replace and value must have the same type and can only be numerics, booleans, + or strings. Value can have None. When replacing, the new value will be cast + to the type of the existing column. + For numeric replacements all values to be replaced should have unique + floating point representation. In case of conflicts (for example with `{42: -1, 42.0: 1}`) + and arbitrary replacement will be used. + + .. versionadded:: 1.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + to_replace : bool, int, float, string, list or dict, the value to be replaced. + If the value is a dict, then `value` is ignored or can be omitted, and `to_replace` + must be a mapping between a value and a replacement. + value : bool, int, float, string or None, optional + The replacement value must be a bool, int, float, string or None. If `value` is a + list, `value` should be of the same length and type as `to_replace`. + If `value` is a scalar and `to_replace` is a sequence, then `value` is + used as a replacement for each item in `to_replace`. + subset : list, optional + optional list of column names to consider. + Columns specified in subset that do not have matching data types are ignored. + For example, if `value` is a string, and subset contains a non-string column, + then the non-string column is simply ignored. + + Returns + ------- + :class:`DataFrame` + DataFrame with replaced values. + + Examples + -------- + >>> df = spark.createDataFrame([ + ... (10, 80, "Alice"), + ... (5, None, "Bob"), + ... (None, 10, "Tom"), + ... (None, None, None)], + ... schema=["age", "height", "name"]) + + Example 1: Replace 10 to 20 in all columns. + + >>> df.na.replace(10, 20).show() + +----+------+-----+ + | age|height| name| + +----+------+-----+ + | 20| 80|Alice| + | 5| NULL| Bob| + |NULL| 20| Tom| + |NULL| NULL| NULL| + +----+------+-----+ + + Example 2: Replace 'Alice' to null in all columns. + + >>> df.na.replace('Alice', None).show() + +----+------+----+ + | age|height|name| + +----+------+----+ + | 10| 80|NULL| + | 5| NULL| Bob| + |NULL| 10| Tom| + |NULL| NULL|NULL| + +----+------+----+ + + Example 3: Replace 'Alice' to 'A', and 'Bob' to 'B' in the 'name' column. + + >>> df.na.replace(['Alice', 'Bob'], ['A', 'B'], 'name').show() + +----+------+----+ + | age|height|name| + +----+------+----+ + | 10| 80| A| + | 5| NULL| B| + |NULL| 10| Tom| + |NULL| NULL|NULL| + +----+------+----+ + + Example 4: Replace 10 to 18 in the 'age' column. + + >>> df.na.replace(10, 18, 'age').show() + +----+------+-----+ + | age|height| name| + +----+------+-----+ + | 18| 80|Alice| + | 5| NULL| Bob| + |NULL| 10| Tom| + |NULL| NULL| NULL| + +----+------+-----+ + "# + }; + (DataFrameStatFunctions) => { + r#"Functionality for statistic functions with :class:`DataFrame`. + + .. versionadded:: 1.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + "# + }; + (DataFrameStatFunctions . cov) => { + r#" + Calculate the sample covariance for the given columns, specified by their names, as a + double value. :func:`DataFrame.cov` and :func:`DataFrameStatFunctions.cov` are aliases. + + .. versionadded:: 1.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + col1 : str + The name of the first column + col2 : str + The name of the second column + + Returns + ------- + float + Covariance of two columns. + + Examples + -------- + >>> df = spark.createDataFrame([(1, 12), (10, 1), (19, 8)], ["c1", "c2"]) + >>> df.cov("c1", "c2") + -18.0 + >>> df = spark.createDataFrame([(11, 12), (10, 11), (9, 10)], ["small", "bigger"]) + >>> df.cov("small", "bigger") + 1.0 + + "# + }; + (DataFrameStatFunctions . corr) => { + r#" + Calculates the correlation of two columns of a :class:`DataFrame` as a double value. + Currently only supports the Pearson Correlation Coefficient. + :func:`DataFrame.corr` and :func:`DataFrameStatFunctions.corr` are aliases of each other. + + .. versionadded:: 1.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + col1 : str + The name of the first column + col2 : str + The name of the second column + method : str, optional + The correlation method. Currently only supports "pearson" + + Returns + ------- + float + Pearson Correlation Coefficient of two columns. + + Examples + -------- + >>> df = spark.createDataFrame([(1, 12), (10, 1), (19, 8)], ["c1", "c2"]) + >>> df.corr("c1", "c2") + -0.3592106040535498 + >>> df = spark.createDataFrame([(11, 12), (10, 11), (9, 10)], ["small", "bigger"]) + >>> df.corr("small", "bigger") + 1.0 + + "# + }; + (DataFrameStatFunctions . approxQuantile) => { + r#" + Calculates the approximate quantiles of numerical columns of a + :class:`DataFrame`. + + The result of this algorithm has the following deterministic bound: + If the :class:`DataFrame` has N elements and if we request the quantile at + probability `p` up to error `err`, then the algorithm will return + a sample `x` from the :class:`DataFrame` so that the *exact* rank of `x` is + close to (p * N). More precisely, + + floor((p - err) * N) <= rank(x) <= ceil((p + err) * N). + + This method implements a variation of the Greenwald-Khanna + algorithm (with some speed optimizations). The algorithm was first + present in [[https://doi.org/10.1145/375663.375670 + Space-efficient Online Computation of Quantile Summaries]] + by Greenwald and Khanna. + + .. versionadded:: 2.0.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + col: str, tuple or list + Can be a single column name, or a list of names for multiple columns. + + .. versionchanged:: 2.2.0 + Added support for multiple columns. + probabilities : list or tuple of floats + a list of quantile probabilities + Each number must be a float in the range [0, 1]. + For example 0.0 is the minimum, 0.5 is the median, 1.0 is the maximum. + relativeError : float + The relative target precision to achieve + (>= 0). If set to zero, the exact quantiles are computed, which + could be very expensive. Note that values greater than 1 are + accepted but gives the same result as 1. + + Returns + ------- + list + the approximate quantiles at the given probabilities. + + * If the input `col` is a string, the output is a list of floats. + + * If the input `col` is a list or tuple of strings, the output is also a + list, but each element in it is a list of floats, i.e., the output + is a list of list of floats. + + Notes + ----- + Null values will be ignored in numerical columns before calculation. + For columns only containing null values, an empty list is returned. + + Examples + -------- + Example 1: Calculating quantiles for a single column + + >>> data = [(1,), (2,), (3,), (4,), (5,)] + >>> df = spark.createDataFrame(data, ["values"]) + >>> quantiles = df.approxQuantile("values", [0.0, 0.5, 1.0], 0.05) + >>> quantiles + [1.0, 3.0, 5.0] + + Example 2: Calculating quantiles for multiple columns + + >>> data = [(1, 10), (2, 20), (3, 30), (4, 40), (5, 50)] + >>> df = spark.createDataFrame(data, ["col1", "col2"]) + >>> quantiles = df.approxQuantile(["col1", "col2"], [0.0, 0.5, 1.0], 0.05) + >>> quantiles + [[1.0, 3.0, 5.0], [10.0, 30.0, 50.0]] + + Example 3: Handling null values + + >>> data = [(1,), (None,), (3,), (4,), (None,)] + >>> df = spark.createDataFrame(data, ["values"]) + >>> quantiles = df.approxQuantile("values", [0.0, 0.5, 1.0], 0.05) + >>> quantiles + [1.0, 3.0, 4.0] + + Example 4: Calculating quantiles with low precision + + >>> data = [(1,), (2,), (3,), (4,), (5,)] + >>> df = spark.createDataFrame(data, ["values"]) + >>> quantiles = df.approxQuantile("values", [0.0, 0.2, 1.0], 0.1) + >>> quantiles + [1.0, 1.0, 5.0] + "# + }; + (DataFrameStatFunctions . crosstab) => { + r#" + Computes a pair-wise frequency table of the given columns. Also known as a contingency + table. + The first column of each row will be the distinct values of `col1` and the column names + will be the distinct values of `col2`. The name of the first column will be `$col1_$col2`. + Pairs that have no occurrences will have zero as their counts. + :func:`DataFrame.crosstab` and :func:`DataFrameStatFunctions.crosstab` are aliases. + + .. versionadded:: 1.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + col1 : str + The name of the first column. Distinct items will make the first item of + each row. + col2 : str + The name of the second column. Distinct items will make the column names + of the :class:`DataFrame`. + + Returns + ------- + :class:`DataFrame` + Frequency matrix of two columns. + + Examples + -------- + >>> df = spark.createDataFrame([(1, 11), (1, 11), (3, 10), (4, 8), (4, 8)], ["c1", "c2"]) + >>> df.crosstab("c1", "c2").sort("c1_c2").show() + +-----+---+---+---+ + |c1_c2| 10| 11| 8| + +-----+---+---+---+ + | 1| 0| 2| 0| + | 3| 1| 0| 0| + | 4| 0| 0| 2| + +-----+---+---+---+ + + "# + }; + (DataFrameStatFunctions . freqItems) => { + r#" + Finding frequent items for columns, possibly with false positives. Using the + frequent element count algorithm described in + "https://doi.org/10.1145/762471.762473, proposed by Karp, Schenker, and Papadimitriou". + :func:`DataFrame.freqItems` and :func:`DataFrameStatFunctions.freqItems` are aliases. + + .. versionadded:: 1.4.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + cols : list or tuple + Names of the columns to calculate frequent items for as a list or tuple of + strings. + support : float, optional + The frequency with which to consider an item 'frequent'. Default is 1%. + The support must be greater than 1e-4. + + Returns + ------- + :class:`DataFrame` + DataFrame with frequent items. + + Notes + ----- + This function is meant for exploratory data analysis, as we make no + guarantee about the backward compatibility of the schema of the resulting + :class:`DataFrame`. + + Examples + -------- + >>> from pyspark.sql import functions as sf + >>> df = spark.createDataFrame([(1, 11), (1, 11), (3, 10), (4, 8), (4, 8)], ["c1", "c2"]) + >>> df = df.freqItems(["c1", "c2"]) + >>> df.select([sf.sort_array(c).alias(c) for c in df.columns]).show() + +------------+------------+ + |c1_freqItems|c2_freqItems| + +------------+------------+ + | [1, 3, 4]| [8, 10, 11]| + +------------+------------+ + "# + }; + (DataFrameStatFunctions . sampleBy) => { + r#" + Returns a stratified sample without replacement based on the + fraction given on each stratum. + + .. versionadded:: 1.5.0 + + .. versionchanged:: 3.4.0 + Supports Spark Connect. + + Parameters + ---------- + col : :class:`Column` or str + column that defines strata + + .. versionchanged:: 3.0.0 + Added sampling by a column of :class:`Column` + fractions : dict + sampling fraction for each stratum. If a stratum is not + specified, we treat its fraction as zero. + seed : int, optional + random seed + + Returns + ------- + a new :class:`DataFrame` that represents the stratified sample + + Examples + -------- + >>> from pyspark.sql import functions as sf + >>> dataset = spark.range(0, 100, 1, 5).select((sf.col("id") % 3).alias("key")) + >>> sampled = dataset.sampleBy("key", fractions={0: 0.1, 1: 0.2}, seed=0) + >>> sampled.groupBy("key").count().orderBy("key").show() + +---+-----+ + |key|count| + +---+-----+ + | 0| 4| + | 1| 9| + +---+-----+ + + >>> dataset.sampleBy(sf.col("key"), fractions={2: 1.0}, seed=0).count() + 33 + "# + }; } diff --git a/crates/pyspark-rs/src/dataframe.rs b/crates/pyspark-rs/src/dataframe.rs index abd82f4ab..62777ad50 100644 --- a/crates/pyspark-rs/src/dataframe.rs +++ b/crates/pyspark-rs/src/dataframe.rs @@ -4163,7 +4163,8 @@ impl PyDataFrame { } } -/// Python wrapper for `DataFrameNaFunctions` (`df.na`). +// Python wrapper for `DataFrameNaFunctions` (`df.na`). +#[doc = connect_doc!(DataFrameNaFunctions)] #[pyclass( name = "DataFrameNaFunctions", module = "pyspark.sql.connect.dataframe", @@ -4245,12 +4246,13 @@ impl PyDataFrameNaFunctions { self.frame.clone_ref(py) } - /// Drop rows containing nulls, as PySpark's `DataFrameNaFunctions.drop`, which is - /// `DataFrame.dropna`. + // Drop rows containing nulls, as PySpark's `DataFrameNaFunctions.drop`, which is + // `DataFrame.dropna`. #[pyo3( signature = (how=None, thresh=None, subset=None), text_signature = "($self, how='any', thresh=None, subset=None)" )] + #[doc = connect_doc!(DataFrameNaFunctions.drop)] fn drop( &self, how: Option<&Bound<'_, PyAny>>, @@ -4260,8 +4262,9 @@ impl PyDataFrameNaFunctions { crate::stat_arguments::dropna(&self.df, how, thresh, subset) } - /// Fill nulls, as PySpark's `DataFrameNaFunctions.fill`, which is `DataFrame.fillna`. + // Fill nulls, as PySpark's `DataFrameNaFunctions.fill`, which is `DataFrame.fillna`. #[pyo3(signature = (value, subset=None))] + #[doc = connect_doc!(DataFrameNaFunctions.fill)] fn fill( &self, value: &Bound<'_, PyAny>, @@ -4270,9 +4273,10 @@ impl PyDataFrameNaFunctions { crate::stat_arguments::fillna(&self.df, value, subset) } - /// Replace values, as PySpark's `DataFrameNaFunctions.replace`, which is - /// `DataFrame.replace`. + // Replace values, as PySpark's `DataFrameNaFunctions.replace`, which is + // `DataFrame.replace`. #[pyo3(signature = (to_replace, value=ReplaceValue::Omitted, subset=None))] + #[doc = connect_doc!(DataFrameNaFunctions.replace)] fn replace( &self, to_replace: &Bound<'_, PyAny>, diff --git a/crates/pyspark-rs/src/stat.rs b/crates/pyspark-rs/src/stat.rs index 94ea8a269..11baa27f5 100644 --- a/crates/pyspark-rs/src/stat.rs +++ b/crates/pyspark-rs/src/stat.rs @@ -6,7 +6,8 @@ use spark_connect::group::StatFunctions; use crate::dataframe::{python_random_seed, PyDataFrame}; use crate::errors::ResultExt; -/// Python wrapper for DataFrame statistical functions. +// Python wrapper for DataFrame statistical functions. +#[doc = connect_doc!(DataFrameStatFunctions)] #[pyclass( name = "DataFrameStatFunctions", module = "pyspark.sql.connect.dataframe", @@ -86,13 +87,14 @@ impl PyStatFunctions { } } - /// Pearson correlation between two numeric columns, as PySpark's, whose `method` is only - /// "pearson". - /// - /// `corr`/`cov` execute a plan (server round-trip via `scalar()`), so they release - /// the GIL across the call - otherwise a Python thread is blocked for the whole - /// RPC. + // Pearson correlation between two numeric columns, as PySpark's, whose `method` is only + // "pearson". + // + // `corr`/`cov` execute a plan (server round-trip via `scalar()`), so they release + // the GIL across the call - otherwise a Python thread is blocked for the whole + // RPC. #[pyo3(signature = (col1, col2, method=None))] + #[doc = connect_doc!(DataFrameStatFunctions.corr)] fn corr( &self, py: Python<'_>, @@ -103,7 +105,8 @@ impl PyStatFunctions { crate::stat_arguments::corr(py, &self.stat, col1, col2, method) } - /// Sample covariance between two numeric columns. + // Sample covariance between two numeric columns. + #[doc = connect_doc!(DataFrameStatFunctions.cov)] fn cov( &self, py: Python<'_>, @@ -113,13 +116,15 @@ impl PyStatFunctions { crate::stat_arguments::cov(py, &self.stat, col1, col2) } - /// Contingency table (cross-tabulation) of two columns. + // Contingency table (cross-tabulation) of two columns. + #[doc = connect_doc!(DataFrameStatFunctions.crosstab)] fn crosstab(&self, col1: &Bound<'_, PyAny>, col2: &Bound<'_, PyAny>) -> PyResult { crate::stat_arguments::crosstab(&self.stat, col1, col2) } - /// Frequent items for the given columns. + // Frequent items for the given columns. #[pyo3(name = "freqItems", signature = (cols, support=None))] + #[doc = connect_doc!(DataFrameStatFunctions.freqItems)] fn freq_items( &self, cols: &Bound<'_, PyAny>, @@ -128,9 +133,10 @@ impl PyStatFunctions { crate::stat_arguments::freq_items(&self.stat, cols, support) } - /// Stratified sample without replacement. Mirrors `DataFrameStatFunctions.sampleBy( - /// col, fractions, seed)`; `fractions` maps stratum values to sampling fractions. + // Stratified sample without replacement. Mirrors `DataFrameStatFunctions.sampleBy( + // col, fractions, seed)`; `fractions` maps stratum values to sampling fractions. #[pyo3(name = "sampleBy", signature = (col, fractions, seed=None))] + #[doc = connect_doc!(DataFrameStatFunctions.sampleBy)] fn sample_by( &self, col: &Bound<'_, PyAny>, @@ -151,9 +157,10 @@ impl PyStatFunctions { })) } - /// Approximate quantiles of a column, or of each of a list or tuple of columns, at the - /// given probabilities, as PySpark's `DataFrameStatFunctions.approxQuantile`. + // Approximate quantiles of a column, or of each of a list or tuple of columns, at the + // given probabilities, as PySpark's `DataFrameStatFunctions.approxQuantile`. #[pyo3(name = "approxQuantile")] + #[doc = connect_doc!(DataFrameStatFunctions.approxQuantile)] fn approx_quantile( &self, py: Python<'_>, diff --git a/crates/pyspark-rs/src/tablearg.rs b/crates/pyspark-rs/src/tablearg.rs index 1c5681696..6218c5480 100644 --- a/crates/pyspark-rs/src/tablearg.rs +++ b/crates/pyspark-rs/src/tablearg.rs @@ -9,9 +9,10 @@ use crate::errors::ResultExt; use crate::group::copy_instance_state; use crate::window::window_columns; -/// A table argument for a table-valued function, mirroring -/// `pyspark.sql.connect.table_arg.TableArg`. Built via `df.asTable()`, then optionally -/// `partitionBy`/`orderBy`/`withSinglePartition` (each returns a new TableArg). +// A table argument for a table-valued function, mirroring +// `pyspark.sql.connect.table_arg.TableArg`. Built via `df.asTable()`, then optionally +// `partitionBy`/`orderBy`/`withSinglePartition` (each returns a new TableArg). +#[doc = connect_doc!(TableArg)] #[pyclass( name = "TableArg", module = "pyspark.sql.connect.table_arg", @@ -47,9 +48,10 @@ impl PyTableArg { #[pymethods] impl PyTableArg { - /// Partition the table argument by the given columns. + // Partition the table argument by the given columns. #[pyo3(signature = (*cols))] #[allow(non_snake_case)] + #[doc = connect_doc!(TableArg.partitionBy)] fn partitionBy(&self, cols: Vec>) -> PyResult { // PySpark checks the partitioning before it converts the columns. self.inner.check_partition_by().to_pyerr()?; @@ -57,9 +59,10 @@ impl PyTableArg { Ok(self.of_same_session(self.inner.clone().partition_by(columns).to_pyerr()?)) } - /// Order the (partitioned) table argument by the given columns. + // Order the (partitioned) table argument by the given columns. #[pyo3(signature = (*cols))] #[allow(non_snake_case)] + #[doc = connect_doc!(TableArg.orderBy)] fn orderBy(&self, cols: Vec>) -> PyResult { // PySpark checks the partitioning before it converts the columns. self.inner.check_order_by().to_pyerr()?; @@ -67,9 +70,9 @@ impl PyTableArg { Ok(self.of_same_session(self.inner.clone().order_by(columns).to_pyerr()?)) } - /// The `spark.connect.Expression` of the table argument, as PySpark Connect's - /// `TableArg.to_plan`: that of its subquery expression, of `pyspark.sql.connect.proto`, of - /// its plan ID, its partitioning, its ordering and its single partition. + // The `spark.connect.Expression` of the table argument, as PySpark Connect's + // `TableArg.to_plan`: that of its subquery expression, of `pyspark.sql.connect.proto`, of + // its plan ID, its partitioning, its ordering and its single partition. fn to_plan(&self, py: Python<'_>, session: &Bound<'_, PyAny>) -> PyResult> { let _ = session; crate::column::expression_message(py, &self.inner.to_column()) @@ -90,8 +93,9 @@ impl PyTableArg { self.inner.is_partitioned() } - /// Mark the table argument as requiring a single partition. + // Mark the table argument as requiring a single partition. #[allow(non_snake_case)] + #[doc = connect_doc!(TableArg.withSinglePartition)] fn withSinglePartition(&self) -> PyResult { Ok(self.of_same_session(self.inner.clone().with_single_partition().to_pyerr()?)) } diff --git a/crates/pyspark-rs/src/window.rs b/crates/pyspark-rs/src/window.rs index 4a5fb9bd9..51814d8cf 100644 --- a/crates/pyspark-rs/src/window.rs +++ b/crates/pyspark-rs/src/window.rs @@ -277,7 +277,8 @@ impl PyFrameBound { } } -/// Python wrapper for a WindowSpec. +// Python wrapper for a WindowSpec. +#[doc = connect_doc!(WindowSpec)] #[pyclass( name = "WindowSpec", module = "pyspark.sql.connect.window", @@ -311,21 +312,24 @@ impl Clone for PyWindowSpec { #[pymethods] impl PyWindowSpec { - /// Partition the window by the given columns. + // Partition the window by the given columns. #[pyo3(signature = (*cols))] + #[doc = connect_doc!(WindowSpec.partitionBy)] fn partitionBy(&self, cols: Vec>) -> PyResult { let new_spec = self.spec.clone().partition_by(to_partition_exprs(cols)?); Ok(PyWindowSpec::new(new_spec)) } - /// Order the window by the given columns. + // Order the window by the given columns. #[pyo3(signature = (*cols))] + #[doc = connect_doc!(WindowSpec.orderBy)] fn orderBy(&self, cols: Vec>) -> PyResult { let new_spec = self.spec.clone().order_by(to_sort_orders(cols)?); Ok(PyWindowSpec::new(new_spec)) } - /// Define a ROWS frame between start and end bounds (ints or FrameBounds). + // Define a ROWS frame between start and end bounds (ints or FrameBounds). + #[doc = connect_doc!(WindowSpec.rowsBetween)] fn rowsBetween( &self, py: Python<'_>, @@ -337,7 +341,8 @@ impl PyWindowSpec { Ok(PyWindowSpec::new(new_spec)) } - /// Define a RANGE frame between start and end bounds (ints or FrameBounds). + // Define a RANGE frame between start and end bounds (ints or FrameBounds). + #[doc = connect_doc!(WindowSpec.rangeBetween)] fn rangeBetween( &self, py: Python<'_>, diff --git a/dev/parity/known-differences.md b/dev/parity/known-differences.md index 84575b411..8c5b5f960 100644 --- a/dev/parity/known-differences.md +++ b/dev/parity/known-differences.md @@ -789,3 +789,12 @@ mypy and pyright type an application as with `pyspark-client` (see `docs/compati PySpark's is that of its Python function: None, or of a docstring that PySpark Connect's modules copy (`__init__.__doc__ = PySparkRuntimeConfig.__init__.__doc__`). The other docstrings of the modules of `pyspark.sql` and `pyspark.errors` are PySpark's (see `docs/compatibility.md`). +- **The docstrings of the native Column, WindowSpec, TableArg, `DataFrameNaFunctions` and + `DataFrameStatFunctions` of Spark Connect** (inherent; a virtual subclass inherits no docstring). + PySpark Connect's classes are subclasses of the classic ones, and neither they nor their members + have docstrings of their own, so `inspect.getdoc` and `help()` show those of the classic class. + The native classes are virtual subclasses of the classic ones, which are not in their MRO: they + and their members carry the classic docstrings, so that `inspect.getdoc` and `help()` show + PySpark's text, as `pyspark-client`'s inherited ones do. Their `__doc__` is that text, where + PySpark Connect's own is None. So is that of `Read.print` of `pyspark.sql.connect.plan`, of + PySpark Connect's `LogicalPlan.print`, which the drop-in's `LogicalPlan` does not have. diff --git a/docs/compatibility.md b/docs/compatibility.md index 0b93de76a..691cd9018 100644 --- a/docs/compatibility.md +++ b/docs/compatibility.md @@ -2205,10 +2205,15 @@ and the `PandasCogroupedOps`, the `MergeIntoWriter` and its clauses, the `Observ native classes are built with them, of the source of PySpark at the tracked tag (`scripts/gen_connect_docstrings.py`), but for the `__init__` of a native class, the slot of CPython, whose docstring is CPython's (see `dev/parity/known-differences.md`). -`tests/golden/runtime_docstrings.json` holds the digests of PySpark's, which a test compares with -the drop-in's. The modules of the DataFrame, the Column, the window, the table argument, the session -and its client, and of the functions are left out of it: not all of their docstrings are PySpark's -yet. +The Column, the WindowSpec, the TableArg, the `DataFrameNaFunctions` and the +`DataFrameStatFunctions` of Spark Connect and their members have the docstrings of PySpark's classic +classes, which `inspect.getdoc` and `help()` show of PySpark Connect's, whose own are None (see +`dev/parity/known-differences.md`). `tests/golden/runtime_docstrings.json` holds the digests of +PySpark's, which a test compares with the drop-in's: of the `__doc__` of each object, or of the +`inspect.getdoc` of one of no docstring of its own that inherits one. The DataFrame class of the +two DataFrame modules, with the docstrings of these modules and those that the classic +`DataFrameNaFunctions` and `DataFrameStatFunctions` copy of the DataFrame's, and the modules of the +session and its client are left out of it: not all of their docstrings are PySpark's yet. A default of an object, which the text signature of a native method cannot hold (`inspect` takes only literals there), shows as `Ellipsis`: the `StorageLevel(True, True, False, True, 1)` of `DataFrame.persist`, and the `` (`pyspark._globals._NoValue`) of the `value` of diff --git a/python/pyspark/sql/connect/column.py b/python/pyspark/sql/connect/column.py index 8a1266b7d..ab5934929 100644 --- a/python/pyspark/sql/connect/column.py +++ b/python/pyspark/sql/connect/column.py @@ -14,7 +14,7 @@ # See the License for the specific language governing permissions and # limitations under the License. # -"""Rust-backed Column under the connect import path (pandas-on-Spark and connect tests import ConnectColumn from here).""" +# Rust-backed Column under the connect import path (pandas-on-Spark and connect tests import ConnectColumn from here). from typing import Any, Callable, Optional from pyspark import cloudpickle as _cloudpickle diff --git a/python/pyspark/sql/connect/functions/__init__.py b/python/pyspark/sql/connect/functions/__init__.py index 7210c1ea2..81274fc31 100644 --- a/python/pyspark/sql/connect/functions/__init__.py +++ b/python/pyspark/sql/connect/functions/__init__.py @@ -14,7 +14,8 @@ # See the License for the specific language governing permissions and # limitations under the License. # -"""The functions of PySpark Connect, ``pyspark.sql.connect.functions``: those of its modules -``builtin`` and ``partitioning``, as PySpark Connect's.""" +# The functions of PySpark Connect, ``pyspark.sql.connect.functions``: those of its modules +# ``builtin`` and ``partitioning``, as PySpark Connect's. +"""PySpark Functions with Spark Connect""" from pyspark.sql.connect.functions.builtin import * # noqa: F401,F403 from pyspark.sql.connect.functions import partitioning # noqa: F401 diff --git a/python/pyspark/sql/connect/functions/builtin.py b/python/pyspark/sql/connect/functions/builtin.py index 2bb75fe3b..c6446af42 100644 --- a/python/pyspark/sql/connect/functions/builtin.py +++ b/python/pyspark/sql/connect/functions/builtin.py @@ -14,14 +14,13 @@ # See the License for the specific language governing permissions and # limitations under the License. # -"""The functions of Spark Connect, as PySpark Connect's ``pyspark.sql.connect.functions.builtin``, -which the Rust core builds. - -As in PySpark, ``pyspark.sql.functions`` is PySpark's package, whose functions run these when the -session is remote (``try_remote_functions`` of ``pyspark.sql.utils``). The functions that -scripts/gen_fn_dispatch.py generates in ``_generated.py`` are defined in this module, which runs -the code of that file; see its header. -""" +# The functions of Spark Connect, as PySpark Connect's ``pyspark.sql.connect.functions.builtin``, +# which the Rust core builds. +# +# As in PySpark, ``pyspark.sql.functions`` is PySpark's package, whose functions run these when the +# session is remote (``try_remote_functions`` of ``pyspark.sql.utils``). The functions that +# scripts/gen_fn_dispatch.py generates in ``_generated.py`` are defined in this module, which runs +# the code of that file; see its header. # sys and random as py_random: of PySpark Connect's module, whose namespace the official doctests # of the functions take as their globals, and whose examples use them (try_add, try_multiply, ...). diff --git a/python/pyspark/sql/connect/plan.py b/python/pyspark/sql/connect/plan.py index bc0383b91..d4bd71e94 100644 --- a/python/pyspark/sql/connect/plan.py +++ b/python/pyspark/sql/connect/plan.py @@ -194,7 +194,22 @@ def plan(self, session: Any) -> "proto.Relation": plan.read.named_table.options[k] = v return plan + # The docstring of PySpark Connect's `LogicalPlan.print`, which `inspect.getdoc` and `help()` + # find of its `Read.print`, of none of its own: the `LogicalPlan` here has no `print`. def print(self, indent: int = 0) -> str: + """ + Print the simple string representation of the current :class:`LogicalPlan`. + + Parameters + ---------- + indent : int + The number of leading spaces for the output string. + + Returns + ------- + str + Simple string representation of this :class:`LogicalPlan`. + """ return f"{' ' * indent}\n" diff --git a/python/pyspark/sql/connect/table_arg.py b/python/pyspark/sql/connect/table_arg.py index 7470385a4..885f3f447 100644 --- a/python/pyspark/sql/connect/table_arg.py +++ b/python/pyspark/sql/connect/table_arg.py @@ -14,9 +14,9 @@ # See the License for the specific language governing permissions and # limitations under the License. # -"""The table argument under the connect import path, as PySpark Connect's -``pyspark.sql.connect.table_arg``: the native ``TableArg`` of ``DataFrame.asTable()``, a virtual -subclass of PySpark's classic ``pyspark.sql.table_arg.TableArg``, as PySpark Connect's is its -subclass (pyspark.sql._classic_bases).""" +# The table argument under the connect import path, as PySpark Connect's +# ``pyspark.sql.connect.table_arg``: the native ``TableArg`` of ``DataFrame.asTable()``, a virtual +# subclass of PySpark's classic ``pyspark.sql.table_arg.TableArg``, as PySpark Connect's is its +# subclass (pyspark.sql._classic_bases). from pyspark._pyspark import TableArg # noqa: F401 diff --git a/python/pyspark/sql/connect/window.py b/python/pyspark/sql/connect/window.py index e0ac9ed7c..fecf74cfb 100644 --- a/python/pyspark/sql/connect/window.py +++ b/python/pyspark/sql/connect/window.py @@ -14,12 +14,12 @@ # See the License for the specific language governing permissions and # limitations under the License. # -"""Window / WindowSpec under the connect import path, as PySpark Connect's -``pyspark.sql.connect.window``: its ``Window`` is a class of its own, a subclass of PySpark's -classic ``pyspark.sql.window.Window``, and its ``WindowSpec`` is the native class of the window -specifications (whose ``_frame`` is a ``WindowFrame``), a virtual subclass of the classic -``pyspark.sql.window.WindowSpec``, as PySpark Connect's is its subclass -(pyspark.sql._classic_bases).""" +# Window / WindowSpec under the connect import path, as PySpark Connect's +# ``pyspark.sql.connect.window``: its ``Window`` is a class of its own, a subclass of PySpark's +# classic ``pyspark.sql.window.Window``, and its ``WindowSpec`` is the native class of the window +# specifications (whose ``_frame`` is a ``WindowFrame``), a virtual subclass of the classic +# ``pyspark.sql.window.WindowSpec``, as PySpark Connect's is its subclass +# (pyspark.sql._classic_bases). from collections.abc import Sequence from typing import TYPE_CHECKING, Union diff --git a/python/tests/_runtime_docstrings.py b/python/tests/_runtime_docstrings.py index 67f36faa1..5fb141238 100644 --- a/python/tests/_runtime_docstrings.py +++ b/python/tests/_runtime_docstrings.py @@ -3,7 +3,11 @@ exact text, of scripts/capture_runtime_docstrings_golden.py (of official PySpark) and of the test of the drop-in's (test_dropin_class_modules_offline.py): of each module, of each public class and function that the module defines, and of each public member (and ``__init__``) of such a class, -as Python finds it on the class, by "module", "module:Name" and "module:Class.member". +as Python finds it on the class, by "module", "module:Name" and "module:Class.member". The digest +is of the kind ``doc``, of ``__doc__`` (None of none), but of an object of no ``__doc__`` of its own +that inherits a docstring, of the kind ``getdoc``, of ``inspect.getdoc``, which ``help()`` shows +(``{"getdoc": digest}``): such as of a member of PySpark Connect's ``Column``, a subclass of the +classic ``Column``, of no docstring of its own, which finds that of the classic class (``KINDS``). The sweep imports every module of them, some of which keep the state of the process at their import, such as the ``sys.stdout`` that ``pyspark.sql.connect.shell.progress`` binds as the default @@ -19,23 +23,48 @@ import types import warnings -# The modules of others' work, which the golden leaves out: pyspark.sql.functions (and its -# modules), and those of the classes of the session, the client, the DataFrame, the Column, the -# window and the table argument, whose docstrings are not all PySpark's yet. +# The golden leaves out the docstrings that are not all PySpark's yet: those of the DataFrame class +# of both DataFrame modules, and of the modules of the session and its client +# (pyspark.sql.connect.session and pyspark.sql.connect.client), which are left out here as a whole. EXCLUDED = ( - "pyspark.sql.functions", - "pyspark.sql.connect.functions", - "pyspark.sql.column", - "pyspark.sql.connect.column", - "pyspark.sql.dataframe", - "pyspark.sql.connect.dataframe", - "pyspark.sql.window", - "pyspark.sql.connect.window", - "pyspark.sql.table_arg", - "pyspark.sql.connect.table_arg", "pyspark.sql.connect.session", "pyspark.sql.connect.client", ) +# Of the two DataFrame modules, the golden leaves out the DataFrame class, and the docstrings that +# can only match PySpark's once those of the class do: the docstrings of both modules, and those +# that the classic `DataFrameNaFunctions` and `DataFrameStatFunctions` copy of the class +# (`drop.__doc__ = DataFrame.dropna.__doc__`). Their other docstrings are compared. +DATAFRAME_MODULES = ("pyspark.sql.dataframe", "pyspark.sql.connect.dataframe") +COPIES_OF_THE_DATAFRAME = { + "DataFrameNaFunctions.drop", + "DataFrameNaFunctions.fill", + "DataFrameNaFunctions.replace", + "DataFrameStatFunctions.approxQuantile", + "DataFrameStatFunctions.corr", + "DataFrameStatFunctions.cov", + "DataFrameStatFunctions.crosstab", + "DataFrameStatFunctions.freqItems", + "DataFrameStatFunctions.sampleBy", +} + + +def of_the_dataframe(module_name, rest): + """Whether the key of `rest` of the module `module_name` is of the DataFrame class, of a + DataFrame module: the module, the class, its members, and the classic copies of them.""" + if module_name not in DATAFRAME_MODULES: + return False + if rest in ("", "DataFrame") or rest.startswith("DataFrame."): + return True + return module_name == "pyspark.sql.dataframe" and rest in COPIES_OF_THE_DATAFRAME + +# The kinds of the digests of the golden, which its note gives. +KINDS = { + "doc": "a digest, or null: of the __doc__ of the object", + "getdoc": ( + '{"getdoc": digest}: of the inspect.getdoc of an object of no __doc__ of its own that ' + "inherits a docstring, which help() shows" + ), +} def digest(doc): @@ -47,6 +76,18 @@ def digest(doc): return hashlib.sha256(doc.encode("utf-8", "surrogatepass")).hexdigest()[:16] +def entry(obj): + """The digest of the docstring of `obj` of the golden, of its kind (``KINDS``): of its + ``__doc__``, or ``{"getdoc": digest}`` of ``inspect.getdoc`` of one of no ``__doc__`` of its own + that inherits a docstring.""" + doc = getattr(obj, "__doc__", None) + if doc is None: + found = inspect.getdoc(obj) + if found is not None: + return {"getdoc": digest(found)} + return digest(doc) + + def module_names(): """The modules of pyspark.sql and pyspark.errors, but the excluded and the test modules.""" found = {"pyspark.sql", "pyspark.errors"} @@ -65,7 +106,17 @@ def module_names(): def docstrings(module_name): - """The digests of the docstrings of the module `module_name`, by their keys.""" + """The digests of the docstrings of the module `module_name`, by their keys, but those of the + DataFrame class (``of_the_dataframe``).""" + out = _docstrings(module_name) + return { + key: value + for key, value in out.items() + if not of_the_dataframe(module_name, key.partition(":")[2]) + } + + +def _docstrings(module_name): warnings.simplefilter("ignore") module = importlib.import_module(module_name) out = {module_name: digest(module.__doc__)} @@ -76,7 +127,7 @@ def docstrings(module_name): continue if getattr(obj, "__module__", None) != module_name: continue - out[f"{module_name}:{attr}"] = digest(getattr(obj, "__doc__", None)) + out[f"{module_name}:{attr}"] = entry(obj) if not inspect.isclass(obj): continue for member in sorted(set(dir(obj))): @@ -86,10 +137,10 @@ def docstrings(module_name): if member != "__init__" and (definer is None or definer.__module__ in ("builtins", "abc", "typing", "enum", "collections")): continue try: - doc = getattr(obj, member).__doc__ + found = entry(getattr(obj, member)) except Exception as e: # noqa: BLE001 - doc = "error: " + type(e).__name__ - out[f"{module_name}:{attr}.{member}"] = digest(doc) + found = digest("error: " + type(e).__name__) + out[f"{module_name}:{attr}.{member}"] = found return out @@ -106,9 +157,10 @@ def resolve(key): def compare(golden): """The comparison of the drop-in's docstrings with those of `golden`, the golden of - capture_runtime_docstrings_golden.py: the number compared, the keys that differ, and the - modules of the golden that do not import. The `__init__` of a native class is CPython's slot, - of CPython's docstring, and a name that the drop-in does not have is not compared.""" + capture_runtime_docstrings_golden.py, each of its kind: the number compared, the keys that + differ, and the modules of the golden that do not import. The `__init__` of a native class is + CPython's slot, of CPython's docstring, and a name that the drop-in does not have is not + compared.""" compared, differ, unimported = 0, [], [] for module, entries in golden["modules"].items(): try: @@ -125,7 +177,11 @@ def compare(golden): if rest.endswith(".__init__") and isinstance(found, types.WrapperDescriptorType): continue compared += 1 - if digest(found.__doc__) != expected: + if isinstance(expected, dict): + doc, expected = inspect.getdoc(found), expected["getdoc"] + else: + doc = found.__doc__ + if digest(doc) != expected: differ.append(key) return {"compared": compared, "differ": differ, "unimported": unimported} diff --git a/python/tests/test_dropin_class_modules_offline.py b/python/tests/test_dropin_class_modules_offline.py index 435ecc185..39abf5590 100644 --- a/python/tests/test_dropin_class_modules_offline.py +++ b/python/tests/test_dropin_class_modules_offline.py @@ -956,13 +956,16 @@ def test_the_connect_objects_have_the_docstrings_that_pyspark_connect_copies( def test_the_docstrings_of_the_modules_are_pysparks(): # As official PySpark's, of tests/golden/runtime_docstrings.json: the docstrings of the modules - # of pyspark.sql and pyspark.errors (but those of others' work), of their classes and functions - # and of the members of the classes, which the native classes are built with (of - # scripts/gen_connect_docstrings.py) and the Python ones have. The `__init__` of a native - # class is CPython's slot, of CPython's docstring; a name that the drop-in does not have is not - # compared. The sweep imports every module, so it runs in a child interpreter: this process - # imports none of them, as a module that keeps the state of its import (the `sys.stdout` of - # the progress bar of pyspark.sql.connect.shell.progress) would keep that of this test. + # of pyspark.sql and pyspark.errors (but those of the DataFrame class and of the session and its + # client, of `EXCLUDED` of the helper), of their classes and functions and of the members of + # the classes, which the native classes are built with (of scripts/gen_connect_docstrings.py) + # and the Python ones have: their `__doc__`, or the `inspect.getdoc` that `help()` shows of one + # of no docstring of its own that inherits one, such as a member of PySpark Connect's Column, + # of the classic Column's. The `__init__` of a native class is CPython's slot, of CPython's + # docstring; a name that the drop-in does not have is not compared. The sweep imports every + # module, so it runs in a child interpreter: this process imports none of them, as a module + # that keeps the state of its import (the `sys.stdout` of the progress bar of + # pyspark.sql.connect.shell.progress) would keep that of this test. import json import subprocess import sys @@ -981,7 +984,7 @@ def test_the_docstrings_of_the_modules_are_pysparks(): result = json.loads(run.stdout.strip().splitlines()[-1]) assert set(result["unimported"]) <= MODULES_OF_PYSPARK_ONLY, result["unimported"] differ = result["differ"] - assert result["compared"] > 2500 and not differ, (result["compared"], len(differ), differ[:20]) + assert result["compared"] > 3500 and not differ, (result["compared"], len(differ), differ[:20]) def test_the_spatial_types_convert_of_their_own_methods_as_pysparks(): diff --git a/scripts/capture_runtime_docstrings_golden.py b/scripts/capture_runtime_docstrings_golden.py index 567ad1408..66c7bb919 100644 --- a/scripts/capture_runtime_docstrings_golden.py +++ b/scripts/capture_runtime_docstrings_golden.py @@ -1,10 +1,12 @@ # SPDX-License-Identifier: Apache-2.0 """Capture official PySpark 4.3.0's docstrings of the modules of pyspark.sql and pyspark.errors at run time, as digests of their exact text: of each module, of each public class and function that it -defines, and of each public member of such a class, as Python finds it on the class -(python/tests/_runtime_docstrings.py). python/tests/test_dropin_class_modules_offline.py compares -the drop-in's with them. The modules of others' work, whose docstrings are not all PySpark's yet, -are left out (``EXCLUDED`` of the helper). +defines, and of each public member of such a class, as Python finds it on the class, of the +``__doc__`` of each, or of the ``inspect.getdoc`` of one of no docstring of its own that inherits +one (python/tests/_runtime_docstrings.py). python/tests/test_dropin_class_modules_offline.py +compares the drop-in's with them. The DataFrame class of both DataFrame modules and the modules of +the session and its client, whose docstrings are not all PySpark's yet, are left out +(``EXCLUDED`` and ``of_the_dataframe`` of the helper). Run with official PySpark 4.3.0 (``pyspark-client``), without a server, from the repository:: @@ -28,7 +30,7 @@ def main(argv=None) -> int: sys.path.insert(0, str(ROOT / "python" / "tests")) import pyspark import pyspark.sql.connect.session # noqa: F401 (as PySpark's modules import it) - from _runtime_docstrings import docstrings, module_names + from _runtime_docstrings import KINDS, docstrings, module_names modules = {} for name in module_names(): @@ -39,7 +41,7 @@ def main(argv=None) -> int: continue # By the rest of the key after the module ("" for the module itself). modules[name] = {key.partition(":")[2]: value for key, value in sorted(found.items())} - golden = {"pyspark": pyspark.__version__, "modules": modules} + golden = {"pyspark": pyspark.__version__, "kinds": KINDS, "modules": modules} Path(args.out).write_text(json.dumps(golden, indent=1, sort_keys=True) + "\n") count = sum(len(v) for v in modules.values()) print(f"{count} docstrings of {len(modules)} modules of PySpark {pyspark.__version__}") diff --git a/scripts/gen_connect_docstrings.py b/scripts/gen_connect_docstrings.py index 29ddade94..e906b41b7 100644 --- a/scripts/gen_connect_docstrings.py +++ b/scripts/gen_connect_docstrings.py @@ -14,8 +14,13 @@ ``CLASS_MODULES``, whose classes are native here too (``pyspark.sql.types``), and of each public member of it, its own or of a base of it in PySpark, as Python finds it on the class (``connect_doc!(IntegerType.fromInternal)`` is that of ``DataType.fromInternal``); an object of no -docstring has none, of which the Rust definitions take no ``#[doc]``. The docstrings are worked out -of PySpark's source as scripts/gen_type_stubs.py works them out for the stubs (its ``Docs``). +docstring has none, of which the Rust definitions take no ``#[doc]``. Last, it gives each class of +``INHERITING`` and each public member of it the docstring that ``inspect.getdoc`` and ``help()`` +find of it in PySpark: PySpark Connect's class is a subclass of the classic one, and neither has a +docstring of its own, so they find that of the classic class (``connect_doc!(Column.alias)`` is that +of the classic ``Column.alias``), which the native class, a virtual subclass of it, does not +inherit. The docstrings are worked out of PySpark's source as scripts/gen_type_stubs.py works them +out for the stubs (its ``Docs``). Usage, from anywhere: @@ -61,6 +66,17 @@ # classes and public members, as Python finds them on each class. CLASS_MODULES = ("pyspark.sql.types",) +# The classes of PySpark Connect, by their modules, that are subclasses of PySpark's classic +# classes and whose classes are native in the drop-in, virtual subclasses of the classic ones: of +# the docstrings that `inspect.getdoc` and `help()` find of them and of their members in PySpark, +# those of the classic class. +INHERITING = { + "pyspark.sql.connect.column": ("Column",), + "pyspark.sql.connect.window": ("WindowSpec",), + "pyspark.sql.connect.table_arg": ("TableArg",), + "pyspark.sql.connect.dataframe": ("DataFrameNaFunctions", "DataFrameStatFunctions"), +} + def docstrings(pyspark_src: str) -> dict[str, str]: """The docstring of each object that a module of ``MODULES`` assigns one, by its qualified @@ -147,6 +163,56 @@ def class_docstrings(pyspark_src: str) -> dict[str, str]: return found +def _first_docstring(docs: Docs, classes: list[tuple[str, str]], member: str) -> str | None: + """The docstring of `member` (the class itself of "") of the first of `classes`, (module, + class) of an MRO, that defines it with one, as ``inspect.getdoc`` looks the classes up.""" + for module, cls in classes: + qualname = f"{cls}.{member}" if member else cls + if member and qualname not in docs.source(module).defs: + continue + doc = docs.raw(module, qualname) + if doc is not None: + return doc + return None + + +def inherited_docstrings(pyspark_src: str) -> dict[str, str]: + """The docstring that ``inspect.getdoc`` finds in PySpark of each class of ``INHERITING`` and of + each public member of it, as Python finds the member on the class: its own, or of the first + class of the MRO of the class that defines it that has one, of the classic class. An alias of a + member (``name = alias`` of PySpark Connect's Column) has none: the decorator of the class wraps + it apart from the member whose name it keeps, of which ``inspect.getdoc`` finds no docstring. + An object of no docstring is left out.""" + docs = Docs(Path(pyspark_src)) + found: dict[str, str] = {} + for module, classes in INHERITING.items(): + if docs.source(module) is None: + raise SystemExit(f"error: {module} not found in {pyspark_src}") + for cls in classes: + mro = docs.mro(module, cls) + doc = _first_docstring(docs, mro, "") + if doc is not None: + found[cls] = doc + seen: set[str] = set() + for i, (base_module, base) in enumerate(mro): + for qualname, node in docs.source(base_module).defs.items(): + member = qualname[len(base) + 1 :] + if ( + not qualname.startswith(base + ".") + or "." in member + or member.startswith("_") + or member in seen + ): + continue + seen.add(member) + if i == 0 and isinstance(node, ast.Assign): + continue # an alias, of no docstring + doc = _first_docstring(docs, mro[i:], member) + if doc is not None: + found[f"{cls}.{member}"] = doc + return found + + def _raw_string(text: str) -> str: """`text` as a Rust raw string literal, of as few hashes as it needs.""" hashes = 1 @@ -166,7 +232,10 @@ def generate(pyspark_src: str) -> str: "//! The docstrings that PySpark Connect's modules give the methods of their classes of", "//! PySpark's classic classes (`format.__doc__ = PySparkDataStreamReader.format.__doc__`),", "//! of the classes of those modules that are native here, which take them of their `#[doc]`", - "//! attributes.", + "//! attributes; those of the native types of `pyspark.sql.types`; and those that", + "//! `inspect.getdoc` finds of the classic classes of PySpark Connect's subclasses of them,", + "//! of no docstrings of their own (`Column.alias`), of which the native classes are virtual", + "//! subclasses.", "", "/// The docstring of the object `$name` of PySpark Connect's module, as PySpark has it at", "/// run time: `connect_doc!(DataStreamReader.format)`, of the textual scope of the modules", @@ -175,7 +244,16 @@ def generate(pyspark_src: str) -> str: "#[rustfmt::skip]", "macro_rules! connect_doc {", ] - for qualname, doc in [*docstrings(pyspark_src).items(), *of_classes.items()]: + arms = [ + *docstrings(pyspark_src).items(), + *of_classes.items(), + *inherited_docstrings(pyspark_src).items(), + ] + names = [qualname for qualname, _ in arms] + if len(set(names)) != len(names): + twice = sorted({name for name in names if names.count(name) > 1}) + raise SystemExit(f"error: the docstrings of {twice} of two sources") + for qualname, doc in arms: pattern = " . ".join(qualname.split(".")) if doc.startswith("@"): # A member that the class inherits, or an alias, of the docstring of the member that diff --git a/tests/golden/runtime_docstrings.json b/tests/golden/runtime_docstrings.json index 0d61c6328..c2d28c925 100644 --- a/tests/golden/runtime_docstrings.json +++ b/tests/golden/runtime_docstrings.json @@ -1,4 +1,8 @@ { + "kinds": { + "doc": "a digest, or null: of the __doc__ of the object", + "getdoc": "{\"getdoc\": digest}: of the inspect.getdoc of an object of no __doc__ of its own that inherits a docstring, which help() shows" + }, "modules": { "pyspark.errors": { "": "9ba7679809a30a0a" @@ -12,7 +16,9 @@ "pyspark.errors.exceptions.base": { "": null, "AnalysisException": "9f7feba89849ce80", - "AnalysisException.__init__": null, + "AnalysisException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "AnalysisException.getBreakingChangeInfo": "c74d523cbc44b583", "AnalysisException.getCondition": "b71053e8b9c04869", "AnalysisException.getErrorClass": "2eee106e2c88b903", @@ -21,7 +27,9 @@ "AnalysisException.getQueryContext": "76f247536e5b1406", "AnalysisException.getSqlState": "3ce23032caba4e17", "ArithmeticException": "76714b74e108b8e8", - "ArithmeticException.__init__": null, + "ArithmeticException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ArithmeticException.getBreakingChangeInfo": "c74d523cbc44b583", "ArithmeticException.getCondition": "b71053e8b9c04869", "ArithmeticException.getErrorClass": "2eee106e2c88b903", @@ -30,7 +38,9 @@ "ArithmeticException.getQueryContext": "76f247536e5b1406", "ArithmeticException.getSqlState": "3ce23032caba4e17", "ArrayIndexOutOfBoundsException": "62b00c14e056a954", - "ArrayIndexOutOfBoundsException.__init__": null, + "ArrayIndexOutOfBoundsException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ArrayIndexOutOfBoundsException.getBreakingChangeInfo": "c74d523cbc44b583", "ArrayIndexOutOfBoundsException.getCondition": "b71053e8b9c04869", "ArrayIndexOutOfBoundsException.getErrorClass": "2eee106e2c88b903", @@ -39,7 +49,9 @@ "ArrayIndexOutOfBoundsException.getQueryContext": "76f247536e5b1406", "ArrayIndexOutOfBoundsException.getSqlState": "3ce23032caba4e17", "DateTimeException": "9f1a9e2f1115a5da", - "DateTimeException.__init__": null, + "DateTimeException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DateTimeException.getBreakingChangeInfo": "c74d523cbc44b583", "DateTimeException.getCondition": "b71053e8b9c04869", "DateTimeException.getErrorClass": "2eee106e2c88b903", @@ -48,7 +60,9 @@ "DateTimeException.getQueryContext": "76f247536e5b1406", "DateTimeException.getSqlState": "3ce23032caba4e17", "IllegalArgumentException": "20909fbfc8408102", - "IllegalArgumentException.__init__": null, + "IllegalArgumentException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "IllegalArgumentException.getBreakingChangeInfo": "c74d523cbc44b583", "IllegalArgumentException.getCondition": "b71053e8b9c04869", "IllegalArgumentException.getErrorClass": "2eee106e2c88b903", @@ -57,7 +71,9 @@ "IllegalArgumentException.getQueryContext": "76f247536e5b1406", "IllegalArgumentException.getSqlState": "3ce23032caba4e17", "NumberFormatException": "1f7883988b3a0a36", - "NumberFormatException.__init__": null, + "NumberFormatException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "NumberFormatException.getBreakingChangeInfo": "c74d523cbc44b583", "NumberFormatException.getCondition": "b71053e8b9c04869", "NumberFormatException.getErrorClass": "2eee106e2c88b903", @@ -66,7 +82,9 @@ "NumberFormatException.getQueryContext": "76f247536e5b1406", "NumberFormatException.getSqlState": "3ce23032caba4e17", "ParseException": "9c6c784b66254e9c", - "ParseException.__init__": null, + "ParseException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ParseException.getBreakingChangeInfo": "c74d523cbc44b583", "ParseException.getCondition": "b71053e8b9c04869", "ParseException.getErrorClass": "2eee106e2c88b903", @@ -75,7 +93,9 @@ "ParseException.getQueryContext": "76f247536e5b1406", "ParseException.getSqlState": "3ce23032caba4e17", "PickleException": "1be1c14b487977d6", - "PickleException.__init__": null, + "PickleException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PickleException.getBreakingChangeInfo": "c74d523cbc44b583", "PickleException.getCondition": "b71053e8b9c04869", "PickleException.getErrorClass": "2eee106e2c88b903", @@ -84,7 +104,9 @@ "PickleException.getQueryContext": "76f247536e5b1406", "PickleException.getSqlState": "3ce23032caba4e17", "PySparkAssertionError": "3279a0d660a2a873", - "PySparkAssertionError.__init__": null, + "PySparkAssertionError.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkAssertionError.getBreakingChangeInfo": "c74d523cbc44b583", "PySparkAssertionError.getCondition": "b71053e8b9c04869", "PySparkAssertionError.getErrorClass": "2eee106e2c88b903", @@ -93,7 +115,9 @@ "PySparkAssertionError.getQueryContext": "76f247536e5b1406", "PySparkAssertionError.getSqlState": "3ce23032caba4e17", "PySparkAttributeError": "443aa28ca8e9a7ff", - "PySparkAttributeError.__init__": null, + "PySparkAttributeError.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkAttributeError.getBreakingChangeInfo": "c74d523cbc44b583", "PySparkAttributeError.getCondition": "b71053e8b9c04869", "PySparkAttributeError.getErrorClass": "2eee106e2c88b903", @@ -102,7 +126,9 @@ "PySparkAttributeError.getQueryContext": "76f247536e5b1406", "PySparkAttributeError.getSqlState": "3ce23032caba4e17", "PySparkException": "1529714ffe237705", - "PySparkException.__init__": null, + "PySparkException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkException.getBreakingChangeInfo": "c74d523cbc44b583", "PySparkException.getCondition": "b71053e8b9c04869", "PySparkException.getErrorClass": "2eee106e2c88b903", @@ -111,7 +137,9 @@ "PySparkException.getQueryContext": "76f247536e5b1406", "PySparkException.getSqlState": "3ce23032caba4e17", "PySparkImportError": "e323b8c1b691acc7", - "PySparkImportError.__init__": null, + "PySparkImportError.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkImportError.getBreakingChangeInfo": "c74d523cbc44b583", "PySparkImportError.getCondition": "b71053e8b9c04869", "PySparkImportError.getErrorClass": "2eee106e2c88b903", @@ -120,7 +148,9 @@ "PySparkImportError.getQueryContext": "76f247536e5b1406", "PySparkImportError.getSqlState": "3ce23032caba4e17", "PySparkIndexError": "18c8e4e052c823df", - "PySparkIndexError.__init__": null, + "PySparkIndexError.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkIndexError.getBreakingChangeInfo": "c74d523cbc44b583", "PySparkIndexError.getCondition": "b71053e8b9c04869", "PySparkIndexError.getErrorClass": "2eee106e2c88b903", @@ -129,7 +159,9 @@ "PySparkIndexError.getQueryContext": "76f247536e5b1406", "PySparkIndexError.getSqlState": "3ce23032caba4e17", "PySparkKeyError": "9ce47f4f44270ac7", - "PySparkKeyError.__init__": null, + "PySparkKeyError.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkKeyError.getBreakingChangeInfo": "c74d523cbc44b583", "PySparkKeyError.getCondition": "b71053e8b9c04869", "PySparkKeyError.getErrorClass": "2eee106e2c88b903", @@ -138,7 +170,9 @@ "PySparkKeyError.getQueryContext": "76f247536e5b1406", "PySparkKeyError.getSqlState": "3ce23032caba4e17", "PySparkNotImplementedError": "cfd6886096f51922", - "PySparkNotImplementedError.__init__": null, + "PySparkNotImplementedError.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkNotImplementedError.getBreakingChangeInfo": "c74d523cbc44b583", "PySparkNotImplementedError.getCondition": "b71053e8b9c04869", "PySparkNotImplementedError.getErrorClass": "2eee106e2c88b903", @@ -147,7 +181,9 @@ "PySparkNotImplementedError.getQueryContext": "76f247536e5b1406", "PySparkNotImplementedError.getSqlState": "3ce23032caba4e17", "PySparkPicklingError": "7effc504a80058e5", - "PySparkPicklingError.__init__": null, + "PySparkPicklingError.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkPicklingError.getBreakingChangeInfo": "c74d523cbc44b583", "PySparkPicklingError.getCondition": "b71053e8b9c04869", "PySparkPicklingError.getErrorClass": "2eee106e2c88b903", @@ -156,7 +192,9 @@ "PySparkPicklingError.getQueryContext": "76f247536e5b1406", "PySparkPicklingError.getSqlState": "3ce23032caba4e17", "PySparkRuntimeError": "98dbbdcd7f08cd52", - "PySparkRuntimeError.__init__": null, + "PySparkRuntimeError.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkRuntimeError.getBreakingChangeInfo": "c74d523cbc44b583", "PySparkRuntimeError.getCondition": "b71053e8b9c04869", "PySparkRuntimeError.getErrorClass": "2eee106e2c88b903", @@ -165,7 +203,9 @@ "PySparkRuntimeError.getQueryContext": "76f247536e5b1406", "PySparkRuntimeError.getSqlState": "3ce23032caba4e17", "PySparkTypeError": "847a847479c5b218", - "PySparkTypeError.__init__": null, + "PySparkTypeError.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkTypeError.getBreakingChangeInfo": "c74d523cbc44b583", "PySparkTypeError.getCondition": "b71053e8b9c04869", "PySparkTypeError.getErrorClass": "2eee106e2c88b903", @@ -174,7 +214,9 @@ "PySparkTypeError.getQueryContext": "76f247536e5b1406", "PySparkTypeError.getSqlState": "3ce23032caba4e17", "PySparkValueError": "37c0a62bf5ae2ed8", - "PySparkValueError.__init__": null, + "PySparkValueError.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkValueError.getBreakingChangeInfo": "c74d523cbc44b583", "PySparkValueError.getCondition": "b71053e8b9c04869", "PySparkValueError.getErrorClass": "2eee106e2c88b903", @@ -183,7 +225,9 @@ "PySparkValueError.getQueryContext": "76f247536e5b1406", "PySparkValueError.getSqlState": "3ce23032caba4e17", "PythonException": "d3c0647735ba84a6", - "PythonException.__init__": null, + "PythonException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PythonException.getBreakingChangeInfo": "c74d523cbc44b583", "PythonException.getCondition": "b71053e8b9c04869", "PythonException.getErrorClass": "2eee106e2c88b903", @@ -205,7 +249,9 @@ "QueryContextType.DataFrame": "13877446245f01f9", "QueryContextType.SQL": "13877446245f01f9", "QueryExecutionException": "29db94254fcaa0f6", - "QueryExecutionException.__init__": null, + "QueryExecutionException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "QueryExecutionException.getBreakingChangeInfo": "c74d523cbc44b583", "QueryExecutionException.getCondition": "b71053e8b9c04869", "QueryExecutionException.getErrorClass": "2eee106e2c88b903", @@ -214,7 +260,9 @@ "QueryExecutionException.getQueryContext": "76f247536e5b1406", "QueryExecutionException.getSqlState": "3ce23032caba4e17", "SessionNotSameException": "da90d2481135f697", - "SessionNotSameException.__init__": null, + "SessionNotSameException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SessionNotSameException.getBreakingChangeInfo": "c74d523cbc44b583", "SessionNotSameException.getCondition": "b71053e8b9c04869", "SessionNotSameException.getErrorClass": "2eee106e2c88b903", @@ -223,7 +271,9 @@ "SessionNotSameException.getQueryContext": "76f247536e5b1406", "SessionNotSameException.getSqlState": "3ce23032caba4e17", "SparkNoSuchElementException": "086bc898ae4127f2", - "SparkNoSuchElementException.__init__": null, + "SparkNoSuchElementException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkNoSuchElementException.getBreakingChangeInfo": "c74d523cbc44b583", "SparkNoSuchElementException.getCondition": "b71053e8b9c04869", "SparkNoSuchElementException.getErrorClass": "2eee106e2c88b903", @@ -232,7 +282,9 @@ "SparkNoSuchElementException.getQueryContext": "76f247536e5b1406", "SparkNoSuchElementException.getSqlState": "3ce23032caba4e17", "SparkRuntimeException": "ec936d5115f71c19", - "SparkRuntimeException.__init__": null, + "SparkRuntimeException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkRuntimeException.getBreakingChangeInfo": "c74d523cbc44b583", "SparkRuntimeException.getCondition": "b71053e8b9c04869", "SparkRuntimeException.getErrorClass": "2eee106e2c88b903", @@ -241,7 +293,9 @@ "SparkRuntimeException.getQueryContext": "76f247536e5b1406", "SparkRuntimeException.getSqlState": "3ce23032caba4e17", "SparkUpgradeException": "c77faacaaf03e9aa", - "SparkUpgradeException.__init__": null, + "SparkUpgradeException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkUpgradeException.getBreakingChangeInfo": "c74d523cbc44b583", "SparkUpgradeException.getCondition": "b71053e8b9c04869", "SparkUpgradeException.getErrorClass": "2eee106e2c88b903", @@ -250,7 +304,9 @@ "SparkUpgradeException.getQueryContext": "76f247536e5b1406", "SparkUpgradeException.getSqlState": "3ce23032caba4e17", "StreamingPythonRunnerInitializationException": "37b367b19a90b3ea", - "StreamingPythonRunnerInitializationException.__init__": null, + "StreamingPythonRunnerInitializationException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingPythonRunnerInitializationException.getBreakingChangeInfo": "c74d523cbc44b583", "StreamingPythonRunnerInitializationException.getCondition": "b71053e8b9c04869", "StreamingPythonRunnerInitializationException.getErrorClass": "2eee106e2c88b903", @@ -259,7 +315,9 @@ "StreamingPythonRunnerInitializationException.getQueryContext": "76f247536e5b1406", "StreamingPythonRunnerInitializationException.getSqlState": "3ce23032caba4e17", "StreamingQueryException": "ad22cfb490a0c59c", - "StreamingQueryException.__init__": null, + "StreamingQueryException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingQueryException.getBreakingChangeInfo": "c74d523cbc44b583", "StreamingQueryException.getCondition": "b71053e8b9c04869", "StreamingQueryException.getErrorClass": "2eee106e2c88b903", @@ -268,7 +326,9 @@ "StreamingQueryException.getQueryContext": "76f247536e5b1406", "StreamingQueryException.getSqlState": "3ce23032caba4e17", "TempTableAlreadyExistsException": "6bcb2869d576b469", - "TempTableAlreadyExistsException.__init__": null, + "TempTableAlreadyExistsException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "TempTableAlreadyExistsException.getBreakingChangeInfo": "c74d523cbc44b583", "TempTableAlreadyExistsException.getCondition": "b71053e8b9c04869", "TempTableAlreadyExistsException.getErrorClass": "2eee106e2c88b903", @@ -277,7 +337,9 @@ "TempTableAlreadyExistsException.getQueryContext": "76f247536e5b1406", "TempTableAlreadyExistsException.getSqlState": "3ce23032caba4e17", "UnknownException": "b8fb75278c3acf27", - "UnknownException.__init__": null, + "UnknownException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnknownException.getBreakingChangeInfo": "c74d523cbc44b583", "UnknownException.getCondition": "b71053e8b9c04869", "UnknownException.getErrorClass": "2eee106e2c88b903", @@ -286,7 +348,9 @@ "UnknownException.getQueryContext": "76f247536e5b1406", "UnknownException.getSqlState": "3ce23032caba4e17", "UnsupportedOperationException": "876c5b1552bd01a3", - "UnsupportedOperationException.__init__": null, + "UnsupportedOperationException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnsupportedOperationException.getBreakingChangeInfo": "c74d523cbc44b583", "UnsupportedOperationException.getCondition": "b71053e8b9c04869", "UnsupportedOperationException.getErrorClass": "2eee106e2c88b903", @@ -299,169 +363,435 @@ "pyspark.errors.exceptions.captured": { "": null, "AnalysisException": "9f7feba89849ce80", - "AnalysisException.__init__": null, + "AnalysisException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "AnalysisException.getBreakingChangeInfo": "c74d523cbc44b583", - "AnalysisException.getCondition": null, - "AnalysisException.getErrorClass": null, - "AnalysisException.getMessage": null, - "AnalysisException.getMessageParameters": null, - "AnalysisException.getQueryContext": null, - "AnalysisException.getSqlState": null, + "AnalysisException.getCondition": { + "getdoc": "459988c1de421639" + }, + "AnalysisException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "AnalysisException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "AnalysisException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "AnalysisException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "AnalysisException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "ArithmeticException": "b0a75e2bcb9bf872", - "ArithmeticException.__init__": null, + "ArithmeticException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ArithmeticException.getBreakingChangeInfo": "c74d523cbc44b583", - "ArithmeticException.getCondition": null, - "ArithmeticException.getErrorClass": null, - "ArithmeticException.getMessage": null, - "ArithmeticException.getMessageParameters": null, - "ArithmeticException.getQueryContext": null, - "ArithmeticException.getSqlState": null, + "ArithmeticException.getCondition": { + "getdoc": "459988c1de421639" + }, + "ArithmeticException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "ArithmeticException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "ArithmeticException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "ArithmeticException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "ArithmeticException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "ArrayIndexOutOfBoundsException": "845636c004cea93f", - "ArrayIndexOutOfBoundsException.__init__": null, + "ArrayIndexOutOfBoundsException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ArrayIndexOutOfBoundsException.getBreakingChangeInfo": "c74d523cbc44b583", - "ArrayIndexOutOfBoundsException.getCondition": null, - "ArrayIndexOutOfBoundsException.getErrorClass": null, - "ArrayIndexOutOfBoundsException.getMessage": null, - "ArrayIndexOutOfBoundsException.getMessageParameters": null, - "ArrayIndexOutOfBoundsException.getQueryContext": null, - "ArrayIndexOutOfBoundsException.getSqlState": null, - "CapturedException": null, - "CapturedException.__init__": null, + "ArrayIndexOutOfBoundsException.getCondition": { + "getdoc": "459988c1de421639" + }, + "ArrayIndexOutOfBoundsException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "ArrayIndexOutOfBoundsException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "ArrayIndexOutOfBoundsException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "ArrayIndexOutOfBoundsException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "ArrayIndexOutOfBoundsException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, + "CapturedException": { + "getdoc": "eb76a31902370bc2" + }, + "CapturedException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "CapturedException.getBreakingChangeInfo": "c74d523cbc44b583", - "CapturedException.getCondition": null, - "CapturedException.getErrorClass": null, - "CapturedException.getMessage": null, - "CapturedException.getMessageParameters": null, - "CapturedException.getQueryContext": null, - "CapturedException.getSqlState": null, - "DataFrameQueryContext": null, - "DataFrameQueryContext.__init__": null, - "DataFrameQueryContext.callSite": null, - "DataFrameQueryContext.contextType": null, - "DataFrameQueryContext.fragment": null, - "DataFrameQueryContext.objectName": null, - "DataFrameQueryContext.objectType": null, - "DataFrameQueryContext.startIndex": null, - "DataFrameQueryContext.stopIndex": null, - "DataFrameQueryContext.summary": null, + "CapturedException.getCondition": { + "getdoc": "459988c1de421639" + }, + "CapturedException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "CapturedException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "CapturedException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "CapturedException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "CapturedException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, + "DataFrameQueryContext": { + "getdoc": "d8ea5cec38ab277c" + }, + "DataFrameQueryContext.__init__": { + "getdoc": "15432c8b93cc48ea" + }, + "DataFrameQueryContext.callSite": { + "getdoc": "9ce65f6ad4f2ea2f" + }, + "DataFrameQueryContext.contextType": { + "getdoc": "72dfb0ab066186aa" + }, + "DataFrameQueryContext.fragment": { + "getdoc": "4556ce2f250cdba7" + }, + "DataFrameQueryContext.objectName": { + "getdoc": "4f462ffa3964c9e7" + }, + "DataFrameQueryContext.objectType": { + "getdoc": "9db567a795e903f6" + }, + "DataFrameQueryContext.startIndex": { + "getdoc": "a8f9f6f28804437a" + }, + "DataFrameQueryContext.stopIndex": { + "getdoc": "913fdfcf2192dc31" + }, + "DataFrameQueryContext.summary": { + "getdoc": "3493573c8da04a52" + }, "DateTimeException": "4adfb2776f79696f", - "DateTimeException.__init__": null, + "DateTimeException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DateTimeException.getBreakingChangeInfo": "c74d523cbc44b583", - "DateTimeException.getCondition": null, - "DateTimeException.getErrorClass": null, - "DateTimeException.getMessage": null, - "DateTimeException.getMessageParameters": null, - "DateTimeException.getQueryContext": null, - "DateTimeException.getSqlState": null, + "DateTimeException.getCondition": { + "getdoc": "459988c1de421639" + }, + "DateTimeException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "DateTimeException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "DateTimeException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "DateTimeException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "DateTimeException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "IllegalArgumentException": "20909fbfc8408102", - "IllegalArgumentException.__init__": null, + "IllegalArgumentException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "IllegalArgumentException.getBreakingChangeInfo": "c74d523cbc44b583", - "IllegalArgumentException.getCondition": null, - "IllegalArgumentException.getErrorClass": null, - "IllegalArgumentException.getMessage": null, - "IllegalArgumentException.getMessageParameters": null, - "IllegalArgumentException.getQueryContext": null, - "IllegalArgumentException.getSqlState": null, + "IllegalArgumentException.getCondition": { + "getdoc": "459988c1de421639" + }, + "IllegalArgumentException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "IllegalArgumentException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "IllegalArgumentException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "IllegalArgumentException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "IllegalArgumentException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "NumberFormatException": "5b98d4ab789b8341", - "NumberFormatException.__init__": null, + "NumberFormatException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "NumberFormatException.getBreakingChangeInfo": "c74d523cbc44b583", - "NumberFormatException.getCondition": null, - "NumberFormatException.getErrorClass": null, - "NumberFormatException.getMessage": null, - "NumberFormatException.getMessageParameters": null, - "NumberFormatException.getQueryContext": null, - "NumberFormatException.getSqlState": null, + "NumberFormatException.getCondition": { + "getdoc": "459988c1de421639" + }, + "NumberFormatException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "NumberFormatException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "NumberFormatException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "NumberFormatException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "NumberFormatException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "ParseException": "9c6c784b66254e9c", - "ParseException.__init__": null, + "ParseException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ParseException.getBreakingChangeInfo": "c74d523cbc44b583", - "ParseException.getCondition": null, - "ParseException.getErrorClass": null, - "ParseException.getMessage": null, - "ParseException.getMessageParameters": null, - "ParseException.getQueryContext": null, - "ParseException.getSqlState": null, + "ParseException.getCondition": { + "getdoc": "459988c1de421639" + }, + "ParseException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "ParseException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "ParseException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "ParseException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "ParseException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "PythonException": "d3c0647735ba84a6", - "PythonException.__init__": null, + "PythonException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PythonException.getBreakingChangeInfo": "c74d523cbc44b583", - "PythonException.getCondition": null, - "PythonException.getErrorClass": null, - "PythonException.getMessage": null, - "PythonException.getMessageParameters": null, - "PythonException.getQueryContext": null, - "PythonException.getSqlState": null, + "PythonException.getCondition": { + "getdoc": "459988c1de421639" + }, + "PythonException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "PythonException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "PythonException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "PythonException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "PythonException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "QueryExecutionException": "29db94254fcaa0f6", - "QueryExecutionException.__init__": null, + "QueryExecutionException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "QueryExecutionException.getBreakingChangeInfo": "c74d523cbc44b583", - "QueryExecutionException.getCondition": null, - "QueryExecutionException.getErrorClass": null, - "QueryExecutionException.getMessage": null, - "QueryExecutionException.getMessageParameters": null, - "QueryExecutionException.getQueryContext": null, - "QueryExecutionException.getSqlState": null, - "SQLQueryContext": null, - "SQLQueryContext.__init__": null, - "SQLQueryContext.callSite": null, - "SQLQueryContext.contextType": null, - "SQLQueryContext.fragment": null, - "SQLQueryContext.objectName": null, - "SQLQueryContext.objectType": null, - "SQLQueryContext.startIndex": null, - "SQLQueryContext.stopIndex": null, - "SQLQueryContext.summary": null, + "QueryExecutionException.getCondition": { + "getdoc": "459988c1de421639" + }, + "QueryExecutionException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "QueryExecutionException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "QueryExecutionException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "QueryExecutionException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "QueryExecutionException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, + "SQLQueryContext": { + "getdoc": "d8ea5cec38ab277c" + }, + "SQLQueryContext.__init__": { + "getdoc": "15432c8b93cc48ea" + }, + "SQLQueryContext.callSite": { + "getdoc": "9ce65f6ad4f2ea2f" + }, + "SQLQueryContext.contextType": { + "getdoc": "72dfb0ab066186aa" + }, + "SQLQueryContext.fragment": { + "getdoc": "4556ce2f250cdba7" + }, + "SQLQueryContext.objectName": { + "getdoc": "4f462ffa3964c9e7" + }, + "SQLQueryContext.objectType": { + "getdoc": "9db567a795e903f6" + }, + "SQLQueryContext.startIndex": { + "getdoc": "a8f9f6f28804437a" + }, + "SQLQueryContext.stopIndex": { + "getdoc": "913fdfcf2192dc31" + }, + "SQLQueryContext.summary": { + "getdoc": "3493573c8da04a52" + }, "SparkNoSuchElementException": "965efda1f72c9b82", - "SparkNoSuchElementException.__init__": null, + "SparkNoSuchElementException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkNoSuchElementException.getBreakingChangeInfo": "c74d523cbc44b583", - "SparkNoSuchElementException.getCondition": null, - "SparkNoSuchElementException.getErrorClass": null, - "SparkNoSuchElementException.getMessage": null, - "SparkNoSuchElementException.getMessageParameters": null, - "SparkNoSuchElementException.getQueryContext": null, - "SparkNoSuchElementException.getSqlState": null, + "SparkNoSuchElementException.getCondition": { + "getdoc": "459988c1de421639" + }, + "SparkNoSuchElementException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "SparkNoSuchElementException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "SparkNoSuchElementException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "SparkNoSuchElementException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "SparkNoSuchElementException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "SparkRuntimeException": "f831b8be12589953", - "SparkRuntimeException.__init__": null, + "SparkRuntimeException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkRuntimeException.getBreakingChangeInfo": "c74d523cbc44b583", - "SparkRuntimeException.getCondition": null, - "SparkRuntimeException.getErrorClass": null, - "SparkRuntimeException.getMessage": null, - "SparkRuntimeException.getMessageParameters": null, - "SparkRuntimeException.getQueryContext": null, - "SparkRuntimeException.getSqlState": null, + "SparkRuntimeException.getCondition": { + "getdoc": "459988c1de421639" + }, + "SparkRuntimeException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "SparkRuntimeException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "SparkRuntimeException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "SparkRuntimeException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "SparkRuntimeException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "SparkUpgradeException": "c77faacaaf03e9aa", - "SparkUpgradeException.__init__": null, + "SparkUpgradeException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkUpgradeException.getBreakingChangeInfo": "c74d523cbc44b583", - "SparkUpgradeException.getCondition": null, - "SparkUpgradeException.getErrorClass": null, - "SparkUpgradeException.getMessage": null, - "SparkUpgradeException.getMessageParameters": null, - "SparkUpgradeException.getQueryContext": null, - "SparkUpgradeException.getSqlState": null, + "SparkUpgradeException.getCondition": { + "getdoc": "459988c1de421639" + }, + "SparkUpgradeException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "SparkUpgradeException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "SparkUpgradeException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "SparkUpgradeException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "SparkUpgradeException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "StreamingQueryException": "ad22cfb490a0c59c", - "StreamingQueryException.__init__": null, + "StreamingQueryException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingQueryException.getBreakingChangeInfo": "c74d523cbc44b583", - "StreamingQueryException.getCondition": null, - "StreamingQueryException.getErrorClass": null, - "StreamingQueryException.getMessage": null, - "StreamingQueryException.getMessageParameters": null, - "StreamingQueryException.getQueryContext": null, - "StreamingQueryException.getSqlState": null, + "StreamingQueryException.getCondition": { + "getdoc": "459988c1de421639" + }, + "StreamingQueryException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "StreamingQueryException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "StreamingQueryException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "StreamingQueryException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "StreamingQueryException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "UnknownException": "b8fb75278c3acf27", - "UnknownException.__init__": null, + "UnknownException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnknownException.getBreakingChangeInfo": "c74d523cbc44b583", - "UnknownException.getCondition": null, - "UnknownException.getErrorClass": null, - "UnknownException.getMessage": null, - "UnknownException.getMessageParameters": null, - "UnknownException.getQueryContext": null, - "UnknownException.getSqlState": null, + "UnknownException.getCondition": { + "getdoc": "459988c1de421639" + }, + "UnknownException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "UnknownException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "UnknownException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "UnknownException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "UnknownException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "UnsupportedOperationException": "c7f7d84ed6f1cbc7", - "UnsupportedOperationException.__init__": null, + "UnsupportedOperationException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnsupportedOperationException.getBreakingChangeInfo": "c74d523cbc44b583", - "UnsupportedOperationException.getCondition": null, - "UnsupportedOperationException.getErrorClass": null, - "UnsupportedOperationException.getMessage": null, - "UnsupportedOperationException.getMessageParameters": null, - "UnsupportedOperationException.getQueryContext": null, - "UnsupportedOperationException.getSqlState": null, + "UnsupportedOperationException.getCondition": { + "getdoc": "459988c1de421639" + }, + "UnsupportedOperationException.getErrorClass": { + "getdoc": "5875920bf33fa211" + }, + "UnsupportedOperationException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, + "UnsupportedOperationException.getMessageParameters": { + "getdoc": "e43ee972cd8cd860" + }, + "UnsupportedOperationException.getQueryContext": { + "getdoc": "448bb091f00ac24f" + }, + "UnsupportedOperationException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "capture_sql_exception": null, "convert_exception": null, "install_exception_handler": "42c4f949a8362712", @@ -470,159 +800,267 @@ "pyspark.errors.exceptions.connect": { "": null, "AnalysisException": "e8b4a2b6b4d26ee7", - "AnalysisException.__init__": null, + "AnalysisException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "AnalysisException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "AnalysisException.getCondition": "b71053e8b9c04869", "AnalysisException.getErrorClass": "2eee106e2c88b903", "AnalysisException.getGrpcStatusCode": null, - "AnalysisException.getMessage": null, + "AnalysisException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "AnalysisException.getMessageParameters": "2e8d1b0ddd81c53c", "AnalysisException.getQueryContext": "76f247536e5b1406", - "AnalysisException.getSqlState": null, + "AnalysisException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "AnalysisException.getStackTrace": null, "AnalysisException.operation_id": "4a7c4a83357b04f4", "ArithmeticException": "f6d111aa841094b7", - "ArithmeticException.__init__": null, + "ArithmeticException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ArithmeticException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "ArithmeticException.getCondition": "b71053e8b9c04869", "ArithmeticException.getErrorClass": "2eee106e2c88b903", "ArithmeticException.getGrpcStatusCode": null, - "ArithmeticException.getMessage": null, + "ArithmeticException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "ArithmeticException.getMessageParameters": "2e8d1b0ddd81c53c", "ArithmeticException.getQueryContext": "76f247536e5b1406", - "ArithmeticException.getSqlState": null, + "ArithmeticException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "ArithmeticException.getStackTrace": null, "ArithmeticException.operation_id": "4a7c4a83357b04f4", "ArrayIndexOutOfBoundsException": "87155de527003833", - "ArrayIndexOutOfBoundsException.__init__": null, + "ArrayIndexOutOfBoundsException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ArrayIndexOutOfBoundsException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "ArrayIndexOutOfBoundsException.getCondition": "b71053e8b9c04869", "ArrayIndexOutOfBoundsException.getErrorClass": "2eee106e2c88b903", "ArrayIndexOutOfBoundsException.getGrpcStatusCode": null, - "ArrayIndexOutOfBoundsException.getMessage": null, + "ArrayIndexOutOfBoundsException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "ArrayIndexOutOfBoundsException.getMessageParameters": "2e8d1b0ddd81c53c", "ArrayIndexOutOfBoundsException.getQueryContext": "76f247536e5b1406", - "ArrayIndexOutOfBoundsException.getSqlState": null, + "ArrayIndexOutOfBoundsException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "ArrayIndexOutOfBoundsException.getStackTrace": null, "ArrayIndexOutOfBoundsException.operation_id": "4a7c4a83357b04f4", - "DataFrameQueryContext": null, - "DataFrameQueryContext.__init__": null, - "DataFrameQueryContext.callSite": null, - "DataFrameQueryContext.contextType": null, - "DataFrameQueryContext.fragment": null, - "DataFrameQueryContext.objectName": null, - "DataFrameQueryContext.objectType": null, - "DataFrameQueryContext.startIndex": null, - "DataFrameQueryContext.stopIndex": null, - "DataFrameQueryContext.summary": null, + "DataFrameQueryContext": { + "getdoc": "d8ea5cec38ab277c" + }, + "DataFrameQueryContext.__init__": { + "getdoc": "15432c8b93cc48ea" + }, + "DataFrameQueryContext.callSite": { + "getdoc": "9ce65f6ad4f2ea2f" + }, + "DataFrameQueryContext.contextType": { + "getdoc": "72dfb0ab066186aa" + }, + "DataFrameQueryContext.fragment": { + "getdoc": "4556ce2f250cdba7" + }, + "DataFrameQueryContext.objectName": { + "getdoc": "4f462ffa3964c9e7" + }, + "DataFrameQueryContext.objectType": { + "getdoc": "9db567a795e903f6" + }, + "DataFrameQueryContext.startIndex": { + "getdoc": "a8f9f6f28804437a" + }, + "DataFrameQueryContext.stopIndex": { + "getdoc": "913fdfcf2192dc31" + }, + "DataFrameQueryContext.summary": { + "getdoc": "3493573c8da04a52" + }, "DateTimeException": "dcc42a71d095be5e", - "DateTimeException.__init__": null, + "DateTimeException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DateTimeException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "DateTimeException.getCondition": "b71053e8b9c04869", "DateTimeException.getErrorClass": "2eee106e2c88b903", "DateTimeException.getGrpcStatusCode": null, - "DateTimeException.getMessage": null, + "DateTimeException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "DateTimeException.getMessageParameters": "2e8d1b0ddd81c53c", "DateTimeException.getQueryContext": "76f247536e5b1406", - "DateTimeException.getSqlState": null, + "DateTimeException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "DateTimeException.getStackTrace": null, "DateTimeException.operation_id": "4a7c4a83357b04f4", "IllegalArgumentException": "f97dba9bd31a3a6b", - "IllegalArgumentException.__init__": null, + "IllegalArgumentException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "IllegalArgumentException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "IllegalArgumentException.getCondition": "b71053e8b9c04869", "IllegalArgumentException.getErrorClass": "2eee106e2c88b903", "IllegalArgumentException.getGrpcStatusCode": null, - "IllegalArgumentException.getMessage": null, + "IllegalArgumentException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "IllegalArgumentException.getMessageParameters": "2e8d1b0ddd81c53c", "IllegalArgumentException.getQueryContext": "76f247536e5b1406", - "IllegalArgumentException.getSqlState": null, + "IllegalArgumentException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "IllegalArgumentException.getStackTrace": null, "IllegalArgumentException.operation_id": "4a7c4a83357b04f4", "InvalidPlanInput": "a07d195e670eb2c8", - "InvalidPlanInput.__init__": null, + "InvalidPlanInput.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "InvalidPlanInput.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "InvalidPlanInput.getCondition": "b71053e8b9c04869", "InvalidPlanInput.getErrorClass": "2eee106e2c88b903", "InvalidPlanInput.getGrpcStatusCode": null, - "InvalidPlanInput.getMessage": null, + "InvalidPlanInput.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "InvalidPlanInput.getMessageParameters": "2e8d1b0ddd81c53c", "InvalidPlanInput.getQueryContext": "76f247536e5b1406", - "InvalidPlanInput.getSqlState": null, + "InvalidPlanInput.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "InvalidPlanInput.getStackTrace": null, "InvalidPlanInput.operation_id": "4a7c4a83357b04f4", "NumberFormatException": "dbb741a7fea6a490", - "NumberFormatException.__init__": null, + "NumberFormatException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "NumberFormatException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "NumberFormatException.getCondition": "b71053e8b9c04869", "NumberFormatException.getErrorClass": "2eee106e2c88b903", "NumberFormatException.getGrpcStatusCode": null, - "NumberFormatException.getMessage": null, + "NumberFormatException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "NumberFormatException.getMessageParameters": "2e8d1b0ddd81c53c", "NumberFormatException.getQueryContext": "76f247536e5b1406", - "NumberFormatException.getSqlState": null, + "NumberFormatException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "NumberFormatException.getStackTrace": null, "NumberFormatException.operation_id": "4a7c4a83357b04f4", "ParseException": "b8ae5030e935f014", - "ParseException.__init__": null, + "ParseException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ParseException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "ParseException.getCondition": "b71053e8b9c04869", "ParseException.getErrorClass": "2eee106e2c88b903", "ParseException.getGrpcStatusCode": null, - "ParseException.getMessage": null, + "ParseException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "ParseException.getMessageParameters": "2e8d1b0ddd81c53c", "ParseException.getQueryContext": "76f247536e5b1406", - "ParseException.getSqlState": null, + "ParseException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "ParseException.getStackTrace": null, "ParseException.operation_id": "4a7c4a83357b04f4", "PickleException": "1be1c14b487977d6", - "PickleException.__init__": null, + "PickleException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PickleException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "PickleException.getCondition": "b71053e8b9c04869", "PickleException.getErrorClass": "2eee106e2c88b903", "PickleException.getGrpcStatusCode": null, - "PickleException.getMessage": null, + "PickleException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "PickleException.getMessageParameters": "2e8d1b0ddd81c53c", "PickleException.getQueryContext": "76f247536e5b1406", - "PickleException.getSqlState": null, + "PickleException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "PickleException.getStackTrace": null, "PickleException.operation_id": "4a7c4a83357b04f4", "PythonException": "12147dcf520a8a2d", - "PythonException.__init__": null, + "PythonException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PythonException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "PythonException.getCondition": "b71053e8b9c04869", "PythonException.getErrorClass": "2eee106e2c88b903", "PythonException.getGrpcStatusCode": null, - "PythonException.getMessage": null, + "PythonException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "PythonException.getMessageParameters": "2e8d1b0ddd81c53c", "PythonException.getQueryContext": "76f247536e5b1406", - "PythonException.getSqlState": null, + "PythonException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "PythonException.getStackTrace": null, "PythonException.operation_id": "4a7c4a83357b04f4", "QueryExecutionException": "b190773485a0da5e", - "QueryExecutionException.__init__": null, + "QueryExecutionException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "QueryExecutionException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "QueryExecutionException.getCondition": "b71053e8b9c04869", "QueryExecutionException.getErrorClass": "2eee106e2c88b903", "QueryExecutionException.getGrpcStatusCode": null, - "QueryExecutionException.getMessage": null, + "QueryExecutionException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "QueryExecutionException.getMessageParameters": "2e8d1b0ddd81c53c", "QueryExecutionException.getQueryContext": "76f247536e5b1406", - "QueryExecutionException.getSqlState": null, + "QueryExecutionException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "QueryExecutionException.getStackTrace": null, "QueryExecutionException.operation_id": "4a7c4a83357b04f4", - "SQLQueryContext": null, - "SQLQueryContext.__init__": null, - "SQLQueryContext.callSite": null, - "SQLQueryContext.contextType": null, - "SQLQueryContext.fragment": null, - "SQLQueryContext.objectName": null, - "SQLQueryContext.objectType": null, - "SQLQueryContext.startIndex": null, - "SQLQueryContext.stopIndex": null, - "SQLQueryContext.summary": null, + "SQLQueryContext": { + "getdoc": "d8ea5cec38ab277c" + }, + "SQLQueryContext.__init__": { + "getdoc": "15432c8b93cc48ea" + }, + "SQLQueryContext.callSite": { + "getdoc": "9ce65f6ad4f2ea2f" + }, + "SQLQueryContext.contextType": { + "getdoc": "72dfb0ab066186aa" + }, + "SQLQueryContext.fragment": { + "getdoc": "4556ce2f250cdba7" + }, + "SQLQueryContext.objectName": { + "getdoc": "4f462ffa3964c9e7" + }, + "SQLQueryContext.objectType": { + "getdoc": "9db567a795e903f6" + }, + "SQLQueryContext.startIndex": { + "getdoc": "a8f9f6f28804437a" + }, + "SQLQueryContext.stopIndex": { + "getdoc": "913fdfcf2192dc31" + }, + "SQLQueryContext.summary": { + "getdoc": "3493573c8da04a52" + }, "SparkConnectException": "584cefc3ad7e05c5", - "SparkConnectException.__init__": null, + "SparkConnectException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkConnectException.getBreakingChangeInfo": "c74d523cbc44b583", "SparkConnectException.getCondition": "b71053e8b9c04869", "SparkConnectException.getErrorClass": "2eee106e2c88b903", @@ -632,111 +1070,165 @@ "SparkConnectException.getSqlState": "3ce23032caba4e17", "SparkConnectException.operation_id": "4a7c4a83357b04f4", "SparkConnectGrpcException": "c2f7386dddaacb79", - "SparkConnectGrpcException.__init__": null, + "SparkConnectGrpcException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkConnectGrpcException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "SparkConnectGrpcException.getCondition": "b71053e8b9c04869", "SparkConnectGrpcException.getErrorClass": "2eee106e2c88b903", "SparkConnectGrpcException.getGrpcStatusCode": null, - "SparkConnectGrpcException.getMessage": null, + "SparkConnectGrpcException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "SparkConnectGrpcException.getMessageParameters": "2e8d1b0ddd81c53c", "SparkConnectGrpcException.getQueryContext": "76f247536e5b1406", - "SparkConnectGrpcException.getSqlState": null, + "SparkConnectGrpcException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "SparkConnectGrpcException.getStackTrace": null, "SparkConnectGrpcException.operation_id": "4a7c4a83357b04f4", "SparkException": "36a9e7f1c95b82ff", - "SparkException.__init__": null, + "SparkException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "SparkException.getCondition": "b71053e8b9c04869", "SparkException.getErrorClass": "2eee106e2c88b903", "SparkException.getGrpcStatusCode": null, - "SparkException.getMessage": null, + "SparkException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "SparkException.getMessageParameters": "2e8d1b0ddd81c53c", "SparkException.getQueryContext": "76f247536e5b1406", - "SparkException.getSqlState": null, + "SparkException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "SparkException.getStackTrace": null, "SparkException.operation_id": "4a7c4a83357b04f4", "SparkNoSuchElementException": "965efda1f72c9b82", - "SparkNoSuchElementException.__init__": null, + "SparkNoSuchElementException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkNoSuchElementException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "SparkNoSuchElementException.getCondition": "b71053e8b9c04869", "SparkNoSuchElementException.getErrorClass": "2eee106e2c88b903", "SparkNoSuchElementException.getGrpcStatusCode": null, - "SparkNoSuchElementException.getMessage": null, + "SparkNoSuchElementException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "SparkNoSuchElementException.getMessageParameters": "2e8d1b0ddd81c53c", "SparkNoSuchElementException.getQueryContext": "76f247536e5b1406", - "SparkNoSuchElementException.getSqlState": null, + "SparkNoSuchElementException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "SparkNoSuchElementException.getStackTrace": null, "SparkNoSuchElementException.operation_id": "4a7c4a83357b04f4", "SparkRuntimeException": "fa89d6d60ad8e849", - "SparkRuntimeException.__init__": null, + "SparkRuntimeException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkRuntimeException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "SparkRuntimeException.getCondition": "b71053e8b9c04869", "SparkRuntimeException.getErrorClass": "2eee106e2c88b903", "SparkRuntimeException.getGrpcStatusCode": null, - "SparkRuntimeException.getMessage": null, + "SparkRuntimeException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "SparkRuntimeException.getMessageParameters": "2e8d1b0ddd81c53c", "SparkRuntimeException.getQueryContext": "76f247536e5b1406", - "SparkRuntimeException.getSqlState": null, + "SparkRuntimeException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "SparkRuntimeException.getStackTrace": null, "SparkRuntimeException.operation_id": "4a7c4a83357b04f4", "SparkUpgradeException": "62a29fb6ecf2745a", - "SparkUpgradeException.__init__": null, + "SparkUpgradeException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkUpgradeException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "SparkUpgradeException.getCondition": "b71053e8b9c04869", "SparkUpgradeException.getErrorClass": "2eee106e2c88b903", "SparkUpgradeException.getGrpcStatusCode": null, - "SparkUpgradeException.getMessage": null, + "SparkUpgradeException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "SparkUpgradeException.getMessageParameters": "2e8d1b0ddd81c53c", "SparkUpgradeException.getQueryContext": "76f247536e5b1406", - "SparkUpgradeException.getSqlState": null, + "SparkUpgradeException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "SparkUpgradeException.getStackTrace": null, "SparkUpgradeException.operation_id": "4a7c4a83357b04f4", "StreamingPythonRunnerInitializationException": "37b367b19a90b3ea", - "StreamingPythonRunnerInitializationException.__init__": null, + "StreamingPythonRunnerInitializationException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingPythonRunnerInitializationException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "StreamingPythonRunnerInitializationException.getCondition": "b71053e8b9c04869", "StreamingPythonRunnerInitializationException.getErrorClass": "2eee106e2c88b903", "StreamingPythonRunnerInitializationException.getGrpcStatusCode": null, - "StreamingPythonRunnerInitializationException.getMessage": null, + "StreamingPythonRunnerInitializationException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "StreamingPythonRunnerInitializationException.getMessageParameters": "2e8d1b0ddd81c53c", "StreamingPythonRunnerInitializationException.getQueryContext": "76f247536e5b1406", - "StreamingPythonRunnerInitializationException.getSqlState": null, + "StreamingPythonRunnerInitializationException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "StreamingPythonRunnerInitializationException.getStackTrace": null, "StreamingPythonRunnerInitializationException.operation_id": "4a7c4a83357b04f4", "StreamingQueryException": "6b404b3430cac264", - "StreamingQueryException.__init__": null, + "StreamingQueryException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingQueryException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "StreamingQueryException.getCondition": "b71053e8b9c04869", "StreamingQueryException.getErrorClass": "2eee106e2c88b903", "StreamingQueryException.getGrpcStatusCode": null, - "StreamingQueryException.getMessage": null, + "StreamingQueryException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "StreamingQueryException.getMessageParameters": "2e8d1b0ddd81c53c", "StreamingQueryException.getQueryContext": "76f247536e5b1406", - "StreamingQueryException.getSqlState": null, + "StreamingQueryException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "StreamingQueryException.getStackTrace": null, "StreamingQueryException.operation_id": "4a7c4a83357b04f4", "UnknownException": "355f24badd84bce5", - "UnknownException.__init__": null, + "UnknownException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnknownException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "UnknownException.getCondition": "b71053e8b9c04869", "UnknownException.getErrorClass": "2eee106e2c88b903", "UnknownException.getGrpcStatusCode": null, - "UnknownException.getMessage": null, + "UnknownException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "UnknownException.getMessageParameters": "2e8d1b0ddd81c53c", "UnknownException.getQueryContext": "76f247536e5b1406", - "UnknownException.getSqlState": null, + "UnknownException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "UnknownException.getStackTrace": null, "UnknownException.operation_id": "4a7c4a83357b04f4", "UnsupportedOperationException": "59f2da2f28f86203", - "UnsupportedOperationException.__init__": null, + "UnsupportedOperationException.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnsupportedOperationException.getBreakingChangeInfo": "ce7e8bf95dec2c4d", "UnsupportedOperationException.getCondition": "b71053e8b9c04869", "UnsupportedOperationException.getErrorClass": "2eee106e2c88b903", "UnsupportedOperationException.getGrpcStatusCode": null, - "UnsupportedOperationException.getMessage": null, + "UnsupportedOperationException.getMessage": { + "getdoc": "c19bf5a60f24f159" + }, "UnsupportedOperationException.getMessageParameters": "2e8d1b0ddd81c53c", "UnsupportedOperationException.getQueryContext": "76f247536e5b1406", - "UnsupportedOperationException.getSqlState": null, + "UnsupportedOperationException.getSqlState": { + "getdoc": "4626520b46c5e04a" + }, "UnsupportedOperationException.getStackTrace": null, "UnsupportedOperationException.operation_id": "4a7c4a83357b04f4", "convert_exception": null, @@ -745,16 +1237,22 @@ "pyspark.errors.exceptions.tblib": { "": "7b8a77afb1e0ca39", "Code": "816277060905b32f", - "Code.__init__": null, + "Code.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "Code.co_code": null, "Frame": "64d29b2826665857", - "Frame.__init__": null, + "Frame.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "Frame.clear": "647246e45c0d612b", "LineCacheEntry": "63758ef00c842645", "LineCacheEntry.__init__": "15432c8b93cc48ea", "LineCacheEntry.set_line": null, "Traceback": "d1db853e87915e8e", - "Traceback.__init__": null, + "Traceback.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "Traceback.as_dict": "dbffd1e58e049ac3", "Traceback.as_traceback": "6d020b1c4a5d1c7d", "Traceback.from_dict": "ba1d3541068d7491", @@ -763,14 +1261,18 @@ "Traceback.tb_next": null, "Traceback.to_dict": "dbffd1e58e049ac3", "Traceback.to_traceback": "6d020b1c4a5d1c7d", - "TracebackParseError": null, + "TracebackParseError": { + "getdoc": "7584afa6407bd1fb" + }, "TracebackParseError.__init__": "15432c8b93cc48ea", "get_all_locals": null }, "pyspark.errors.utils": { "": null, "ErrorClassesReader": "49cda857d316d35d", - "ErrorClassesReader.__init__": null, + "ErrorClassesReader.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ErrorClassesReader.get_breaking_change_info": "3e468ac49b44c474", "ErrorClassesReader.get_error_message": "e1704304517ed26f", "ErrorClassesReader.get_message_template": "72f496243f6f63a0", @@ -872,6 +1374,47 @@ "TablePartition.__init__": "15432c8b93cc48ea", "TablePartition.partition": "73f36d907763d7d9" }, + "pyspark.sql.column": { + "": null, + "Column": "e0ad349a12cf6bda", + "Column.__init__": "15432c8b93cc48ea", + "Column.alias": "ec1d5963f9e743a4", + "Column.asc": "6fdc1bc3bfe1e650", + "Column.asc_nulls_first": "e074abb95e7dbe98", + "Column.asc_nulls_last": "833f63a21f7511a0", + "Column.astype": "ff20b368aa35b14c", + "Column.between": "8e390e62b6f8f278", + "Column.bitwiseAND": "29d94299684b19a4", + "Column.bitwiseOR": "3d3366e8ca3dfc00", + "Column.bitwiseXOR": "9f868230dd7eb579", + "Column.cast": "4232785c81b3737d", + "Column.contains": "7553494ac96694b2", + "Column.desc": "2477ffecf3a7449f", + "Column.desc_nulls_first": "37d68c1aa9f97844", + "Column.desc_nulls_last": "c816cb3804751ed8", + "Column.dropFields": "45244d1dd1600c65", + "Column.endswith": "2f3fa67583163e6f", + "Column.eqNullSafe": "ac5db1873443aa7d", + "Column.getField": "6a5ab9f03d86d31f", + "Column.getItem": "14f3f48d72816e01", + "Column.ilike": "3de755536f9d4eaa", + "Column.isNaN": "358d5183ce123fbb", + "Column.isNotNull": "b31af85b3b51da85", + "Column.isNull": "34b1be5d5162d888", + "Column.isin": "3ac72d578797ea8d", + "Column.like": "6c1a97753794f2a6", + "Column.name": "a4002f7cf287d74b", + "Column.otherwise": "7b85d48cca931286", + "Column.outer": "1e74f36548a574ad", + "Column.over": "7d73bd9249db2847", + "Column.rlike": "7b66331cb39cedcc", + "Column.startswith": "c02df4dff0932085", + "Column.substr": "a5331f0afcc9ec05", + "Column.transform": "8ba9cd053affb887", + "Column.try_cast": "01984a4385967c30", + "Column.when": "74530f8b4dc24cb6", + "Column.withField": "b06e56ef7a934ee3" + }, "pyspark.sql.conf": { "": null, "RuntimeConfig": "e5f89c7ade5a4006", @@ -888,9 +1431,13 @@ "pyspark.sql.connect._typing": { "": null, "GroupedMapPandasUserDefinedFunction": "8e8849bd8f92397f", - "UserDefinedFunctionCallable": null, + "UserDefinedFunctionCallable": { + "getdoc": "5b08ecf2d7e4e8a1" + }, "UserDefinedFunctionCallable.__init__": null, - "UserDefinedFunctionLike": null, + "UserDefinedFunctionLike": { + "getdoc": "5b08ecf2d7e4e8a1" + }, "UserDefinedFunctionLike.__init__": null, "UserDefinedFunctionLike.asNondeterministic": null, "UserDefinedFunctionLike.returnType": null @@ -906,7 +1453,9 @@ "pyspark.sql.connect.catalog": { "": null, "Catalog": "3817372225f987ba", - "Catalog.__init__": null, + "Catalog.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "Catalog.analyzeTable": "47ceb089f389ba3c", "Catalog.cacheTable": "980668cb53b20d3c", "Catalog.clearCache": "58555c879f8927f7", @@ -945,6 +1494,120 @@ "Catalog.truncateTable": "6e092f5fc6a54065", "Catalog.uncacheTable": "2b48252a8a8cb038" }, + "pyspark.sql.connect.column": { + "": null, + "Column": { + "getdoc": "829f3adbc15abce3" + }, + "Column.__init__": { + "getdoc": "15432c8b93cc48ea" + }, + "Column.alias": { + "getdoc": "d5ba905c35ae0ff4" + }, + "Column.asc": { + "getdoc": "0fabe69db805b745" + }, + "Column.asc_nulls_first": { + "getdoc": "87a5934b95c0759f" + }, + "Column.asc_nulls_last": { + "getdoc": "97fdc3c69a8a8a85" + }, + "Column.astype": null, + "Column.between": { + "getdoc": "6b066c3774efc45c" + }, + "Column.bitwiseAND": { + "getdoc": "6b0e32a56b849638" + }, + "Column.bitwiseOR": { + "getdoc": "7199027bdf3ede70" + }, + "Column.bitwiseXOR": { + "getdoc": "f378266664f24026" + }, + "Column.cast": { + "getdoc": "b933f65aa06713f7" + }, + "Column.contains": { + "getdoc": "1d6057b0d2f081f5" + }, + "Column.desc": { + "getdoc": "cf5e525b97051849" + }, + "Column.desc_nulls_first": { + "getdoc": "d3f01d0aa1f684fc" + }, + "Column.desc_nulls_last": { + "getdoc": "e8973a286d52c191" + }, + "Column.dropFields": { + "getdoc": "b047fd1b8ebae11a" + }, + "Column.endswith": { + "getdoc": "4c1187a4cead22fb" + }, + "Column.eqNullSafe": { + "getdoc": "1ad8f0b8d9b1b76f" + }, + "Column.getField": { + "getdoc": "4c5745506018b0b8" + }, + "Column.getItem": { + "getdoc": "d9cae82ff0f56658" + }, + "Column.ilike": { + "getdoc": "2f98e71ba93c8b4d" + }, + "Column.isNaN": { + "getdoc": "d7d9e02f2da99db3" + }, + "Column.isNotNull": { + "getdoc": "a036d48dbe551a10" + }, + "Column.isNull": { + "getdoc": "a9a186064033826d" + }, + "Column.isin": { + "getdoc": "38e4a609a3c5ac09" + }, + "Column.like": { + "getdoc": "9ecb756f22b30065" + }, + "Column.name": null, + "Column.otherwise": { + "getdoc": "0ef1731a13048672" + }, + "Column.outer": { + "getdoc": "62b47362fdf3e67a" + }, + "Column.over": { + "getdoc": "2ab279c1965945da" + }, + "Column.rlike": { + "getdoc": "5be6c9c091b38cf6" + }, + "Column.startswith": { + "getdoc": "fa192006af16854b" + }, + "Column.substr": { + "getdoc": "307abe43e6f968b7" + }, + "Column.to_plan": null, + "Column.transform": { + "getdoc": "af51f2074b900b2d" + }, + "Column.try_cast": { + "getdoc": "03e4c9f9d86b2e43" + }, + "Column.when": { + "getdoc": "d6ddf63f060922d3" + }, + "Column.withField": { + "getdoc": "ab4905ef1147d3a4" + } + }, "pyspark.sql.connect.conf": { "": null, "RuntimeConf": "e5f89c7ade5a4006", @@ -958,7 +1621,9 @@ "pyspark.sql.connect.context": { "": null, "HiveContext": "c024bf3f22b3a769", - "HiveContext.__init__": null, + "HiveContext.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "HiveContext.cacheTable": "99d2af6220d5c909", "HiveContext.clearCache": "2700b87300242d95", "HiveContext.createDataFrame": "1de75c70285fc6ff", @@ -982,7 +1647,9 @@ "HiveContext.udtf": "7ec7f6d857270d1e", "HiveContext.uncacheTable": "0093152f8d0b22c3", "SQLContext": "5c35a8e0489df275", - "SQLContext.__init__": null, + "SQLContext.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SQLContext.cacheTable": "99d2af6220d5c909", "SQLContext.clearCache": "2700b87300242d95", "SQLContext.createDataFrame": "1de75c70285fc6ff", @@ -1012,51 +1679,114 @@ "proto_to_storage_level": null, "storage_level_to_proto": null }, + "pyspark.sql.connect.dataframe": { + "DataFrameNaFunctions": { + "getdoc": "1c90589c460eebe0" + }, + "DataFrameNaFunctions.__init__": { + "getdoc": "15432c8b93cc48ea" + }, + "DataFrameNaFunctions.drop": { + "getdoc": "2c668bea08d3a1f4" + }, + "DataFrameNaFunctions.fill": { + "getdoc": "8825469cfd2a36c0" + }, + "DataFrameNaFunctions.replace": { + "getdoc": "424502702903dcc7" + }, + "DataFrameStatFunctions": { + "getdoc": "5479a785aafaf64a" + }, + "DataFrameStatFunctions.__init__": { + "getdoc": "15432c8b93cc48ea" + }, + "DataFrameStatFunctions.approxQuantile": { + "getdoc": "a05cd037782861ff" + }, + "DataFrameStatFunctions.corr": { + "getdoc": "4af1de23e84c040e" + }, + "DataFrameStatFunctions.cov": { + "getdoc": "940b8aca5d365b86" + }, + "DataFrameStatFunctions.crosstab": { + "getdoc": "aa568a4428058166" + }, + "DataFrameStatFunctions.freqItems": { + "getdoc": "ff7610a3f04a8829" + }, + "DataFrameStatFunctions.sampleBy": { + "getdoc": "657beacfdd3f8f9d" + } + }, "pyspark.sql.connect.datasource": { "": null, "DataSourceRegistration": "735dbdd97d738fbf", - "DataSourceRegistration.__init__": null, + "DataSourceRegistration.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataSourceRegistration.register": "a8937a98c811311a" }, "pyspark.sql.connect.expressions": { "": null, - "CallFunction": null, - "CallFunction.__init__": null, + "CallFunction": { + "getdoc": "ea89636480794cba" + }, + "CallFunction.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "CallFunction.alias": null, "CallFunction.children": null, "CallFunction.foreach": null, "CallFunction.name": null, "CallFunction.to_plan": null, - "CaseWhen": null, - "CaseWhen.__init__": null, + "CaseWhen": { + "getdoc": "ea89636480794cba" + }, + "CaseWhen.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "CaseWhen.alias": null, "CaseWhen.children": null, "CaseWhen.foreach": null, "CaseWhen.name": null, "CaseWhen.to_plan": null, - "CastExpression": null, - "CastExpression.__init__": null, + "CastExpression": { + "getdoc": "ea89636480794cba" + }, + "CastExpression.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "CastExpression.alias": null, "CastExpression.children": null, "CastExpression.foreach": null, "CastExpression.name": null, "CastExpression.to_plan": null, - "ColumnAlias": null, - "ColumnAlias.__init__": null, + "ColumnAlias": { + "getdoc": "ea89636480794cba" + }, + "ColumnAlias.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ColumnAlias.alias": null, "ColumnAlias.children": null, "ColumnAlias.foreach": null, "ColumnAlias.name": null, "ColumnAlias.to_plan": null, "ColumnReference": "549d36615a068822", - "ColumnReference.__init__": null, + "ColumnReference.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ColumnReference.alias": null, "ColumnReference.children": null, "ColumnReference.foreach": null, "ColumnReference.name": "9f68d621f052fe2d", "ColumnReference.to_plan": "2523c897b603fa2e", "CommonInlineUserDefinedFunction": "4135e02708130085", - "CommonInlineUserDefinedFunction.__init__": null, + "CommonInlineUserDefinedFunction.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "CommonInlineUserDefinedFunction.alias": null, "CommonInlineUserDefinedFunction.children": null, "CommonInlineUserDefinedFunction.foreach": null, @@ -1065,136 +1795,778 @@ "CommonInlineUserDefinedFunction.to_plan_judf": null, "CommonInlineUserDefinedFunction.to_plan_udf": "ea581ac0dc46acd1", "DirectShufflePartitionID": "918b7d7ce9de38ac", - "DirectShufflePartitionID.__init__": null, + "DirectShufflePartitionID.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DirectShufflePartitionID.alias": null, "DirectShufflePartitionID.children": null, "DirectShufflePartitionID.foreach": null, "DirectShufflePartitionID.name": null, "DirectShufflePartitionID.to_plan": null, - "DistributedSequenceID": null, - "DistributedSequenceID.__init__": null, + "DistributedSequenceID": { + "getdoc": "ea89636480794cba" + }, + "DistributedSequenceID.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DistributedSequenceID.alias": null, "DistributedSequenceID.children": null, "DistributedSequenceID.foreach": null, "DistributedSequenceID.name": null, "DistributedSequenceID.to_plan": null, - "DropField": null, - "DropField.__init__": null, + "DropField": { + "getdoc": "ea89636480794cba" + }, + "DropField.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DropField.alias": null, "DropField.children": null, "DropField.foreach": null, "DropField.name": null, "DropField.to_plan": null, "Expression": "7dd3f066a68d0087", - "Expression.__init__": null, + "Expression.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "Expression.alias": null, "Expression.children": null, "Expression.foreach": null, "Expression.name": null, "Expression.to_plan": null, "JavaUDF": "75329e3ceca72f27", - "JavaUDF.__init__": null, + "JavaUDF.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "JavaUDF.to_plan": null, - "LambdaFunction": null, - "LambdaFunction.__init__": null, + "LambdaFunction": { + "getdoc": "ea89636480794cba" + }, + "LambdaFunction.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "LambdaFunction.alias": null, "LambdaFunction.children": null, "LambdaFunction.foreach": null, "LambdaFunction.name": null, "LambdaFunction.to_plan": null, "LiteralExpression": "ddf00e4393138699", - "LiteralExpression.__init__": null, + "LiteralExpression.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "LiteralExpression.alias": null, "LiteralExpression.children": null, "LiteralExpression.foreach": null, "LiteralExpression.name": null, "LiteralExpression.to_plan": "0eca1f277f1177db", - "NamedArgumentExpression": null, - "NamedArgumentExpression.__init__": null, + "NamedArgumentExpression": { + "getdoc": "ea89636480794cba" + }, + "NamedArgumentExpression.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "NamedArgumentExpression.alias": null, "NamedArgumentExpression.children": null, "NamedArgumentExpression.foreach": null, "NamedArgumentExpression.name": null, "NamedArgumentExpression.to_plan": null, "PythonUDF": "2011ed4327e62cc3", - "PythonUDF.__init__": null, + "PythonUDF.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PythonUDF.to_plan": null, "SQLExpression": "056f467d1a92ab4d", - "SQLExpression.__init__": null, + "SQLExpression.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SQLExpression.alias": null, "SQLExpression.children": null, "SQLExpression.foreach": null, "SQLExpression.name": null, "SQLExpression.to_plan": "77b0a8fd7ca47965", - "SortOrder": null, - "SortOrder.__init__": null, + "SortOrder": { + "getdoc": "ea89636480794cba" + }, + "SortOrder.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SortOrder.alias": null, "SortOrder.children": null, "SortOrder.foreach": null, "SortOrder.name": null, "SortOrder.to_plan": null, - "SubqueryExpression": null, - "SubqueryExpression.__init__": null, + "SubqueryExpression": { + "getdoc": "ea89636480794cba" + }, + "SubqueryExpression.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SubqueryExpression.alias": null, "SubqueryExpression.children": null, "SubqueryExpression.foreach": null, "SubqueryExpression.name": null, "SubqueryExpression.to_plan": null, - "UnresolvedExtractValue": null, - "UnresolvedExtractValue.__init__": null, + "UnresolvedExtractValue": { + "getdoc": "ea89636480794cba" + }, + "UnresolvedExtractValue.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnresolvedExtractValue.alias": null, "UnresolvedExtractValue.children": null, "UnresolvedExtractValue.foreach": null, "UnresolvedExtractValue.name": null, "UnresolvedExtractValue.to_plan": null, - "UnresolvedFunction": null, - "UnresolvedFunction.__init__": null, + "UnresolvedFunction": { + "getdoc": "ea89636480794cba" + }, + "UnresolvedFunction.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnresolvedFunction.alias": null, "UnresolvedFunction.children": null, "UnresolvedFunction.foreach": null, "UnresolvedFunction.name": null, "UnresolvedFunction.to_plan": null, - "UnresolvedNamedLambdaVariable": null, - "UnresolvedNamedLambdaVariable.__init__": null, + "UnresolvedNamedLambdaVariable": { + "getdoc": "ea89636480794cba" + }, + "UnresolvedNamedLambdaVariable.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnresolvedNamedLambdaVariable.alias": null, "UnresolvedNamedLambdaVariable.children": null, "UnresolvedNamedLambdaVariable.foreach": null, "UnresolvedNamedLambdaVariable.fresh_var_name": null, "UnresolvedNamedLambdaVariable.name": null, "UnresolvedNamedLambdaVariable.to_plan": null, - "UnresolvedRegex": null, - "UnresolvedRegex.__init__": null, + "UnresolvedRegex": { + "getdoc": "ea89636480794cba" + }, + "UnresolvedRegex.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnresolvedRegex.alias": null, "UnresolvedRegex.children": null, "UnresolvedRegex.foreach": null, "UnresolvedRegex.name": null, "UnresolvedRegex.to_plan": null, - "UnresolvedStar": null, - "UnresolvedStar.__init__": null, + "UnresolvedStar": { + "getdoc": "ea89636480794cba" + }, + "UnresolvedStar.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnresolvedStar.alias": null, "UnresolvedStar.children": null, "UnresolvedStar.foreach": null, "UnresolvedStar.name": null, "UnresolvedStar.to_plan": null, - "WindowExpression": null, - "WindowExpression.__init__": null, + "WindowExpression": { + "getdoc": "ea89636480794cba" + }, + "WindowExpression.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "WindowExpression.alias": null, "WindowExpression.children": null, "WindowExpression.foreach": null, "WindowExpression.name": null, "WindowExpression.to_plan": null, - "WithField": null, - "WithField.__init__": null, + "WithField": { + "getdoc": "ea89636480794cba" + }, + "WithField.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "WithField.alias": null, "WithField.children": null, "WithField.foreach": null, "WithField.name": null, "WithField.to_plan": null }, + "pyspark.sql.connect.functions": { + "": "3a10f7311f800ec3" + }, + "pyspark.sql.connect.functions.builtin": { + "": null, + "abs": "d94169d2dd6fc879", + "acos": "32004d165d37b4a1", + "acosh": "3de06e46b21ed2a3", + "add_months": "cf534577a5b261ef", + "aes_decrypt": "5bc1adfdaa03a135", + "aes_encrypt": "043a835e50af3aa6", + "aggregate": "57e13fbd0367796c", + "any_value": "75c9186701b2a50f", + "approxCountDistinct": "3d6b9a3ed2204dab", + "approx_count_distinct": "dab07eca16a4e7e2", + "approx_percentile": "a5360faac4baa897", + "array": "433062d78cb3eda9", + "array_agg": "2836fa0ba49b7066", + "array_append": "7c36d1a76b99a245", + "array_compact": "054ef088f113e27c", + "array_contains": "100db46b8f0e04f9", + "array_distinct": "7a35e29cdb65a662", + "array_except": "ce40e72fe4cb7f7a", + "array_insert": "4dc32f4ebe00957e", + "array_intersect": "bd2312cc5171d3dc", + "array_join": "82573764fd4a37bc", + "array_max": "031d2b2b4f1f7c56", + "array_min": "097881c9b10a610d", + "array_position": "36ff47fa44885f9a", + "array_prepend": "7f890c7ccf99fa90", + "array_remove": "b9d47c1f5fae7717", + "array_repeat": "1dc8f5e9c96eccd7", + "array_size": "485276937cf15323", + "array_sort": "2ceb9093d4551a39", + "array_union": "cd9e5442ba03e5d3", + "arrays_overlap": "47e77d7d6f171724", + "arrays_zip": "b5e054b6d3e082c2", + "arrow_udtf": "16cbe618746447d8", + "asc": "ac476a415e2682e9", + "asc_nulls_first": "77fb8b72e8089f1f", + "asc_nulls_last": "609125df53172800", + "ascii": "e61ec50d0bea8b2a", + "asin": "74eb1d420f590b97", + "asinh": "6104f37ba0068d61", + "assert_true": "666f998eba70935c", + "atan": "8a37a0be357bca44", + "atan2": "b175bfab6e28fba5", + "atanh": "aa71c4d7039c5f3f", + "avg": "61e8590cf6d2687a", + "base64": "1a58ac15148cbcbf", + "bin": "6062f00c9dfb2143", + "bit_and": "d060566ba9549bab", + "bit_count": "5e89ee234a6b4cb2", + "bit_get": "9bca394ecd31ee25", + "bit_length": "e4fae46036b7fd7d", + "bit_or": "99912ffeabbfe003", + "bit_xor": "4d8953e6f19253cf", + "bitmap_and_agg": "d47b8be51fffc509", + "bitmap_bit_position": "46c7ce0b6b710509", + "bitmap_bucket_number": "5a174121093ff776", + "bitmap_construct_agg": "23c457c53cf9740f", + "bitmap_count": "02054cbca8f04482", + "bitmap_or_agg": "9690e80ed7565c93", + "bitwiseNOT": "e87e7c44363fe15a", + "bitwise_not": "b70e60bfda3c13a9", + "bool_and": "1c17bdb24f085c93", + "bool_or": "94d75f08fd338f99", + "broadcast": "9a7140202718320d", + "bround": "6a31bb4395e5d111", + "btrim": "1827112e6567cdba", + "bucket": "14189cc5686f7e66", + "call_function": "1e98618b1cabd541", + "call_udf": "03a59af6fc8fd020", + "cardinality": "493d28b836c5932b", + "cbrt": "9def3e4e4dc81e35", + "ceil": "4c7931ddaf1658ce", + "ceiling": "7dac5e7cd2de693f", + "char": "a0b270c4172dd4a0", + "char_length": "09f2236c73166e22", + "character_length": "59fce8182074f51e", + "chr": "3895244511d37bd1", + "coalesce": "0688a6e11e5f6dca", + "col": "e852ec474b2dd3ca", + "collate": "627045507a217d4e", + "collation": "16c0f24be06f339e", + "collect_list": "a85f9d7484d56915", + "collect_set": "8430d46915cfb23a", + "collect_union": "74368e7f1e2d5c96", + "column": "e852ec474b2dd3ca", + "concat": "057b29b4b18c130b", + "concat_ws": "9f07de6d30947b7d", + "contains": "664636c704fdd055", + "conv": "87fc93e52d0989d7", + "convert_timezone": "1682aa5bce84afa7", + "corr": "2ed70768c1fda1c3", + "cos": "631b7df34e7b8795", + "cosh": "3a8ee4b535dc9392", + "cot": "a8291889ce0dfba3", + "count": "03989ba1e4e6dbbe", + "countDistinct": "a4e31806e102437b", + "count_distinct": "1cd6bf79762b2add", + "count_if": "fd775fbae65abb36", + "count_min_sketch": "9a18c65bec4dc187", + "counter_diff": "47e2aeb0785e7cc8", + "covar_pop": "8bd5af2bc520eb71", + "covar_samp": "3b9103c58fbead70", + "crc32": "3a0fc4250512de91", + "create_map": "265edc48b7e13798", + "csc": "984c53b0db3e192e", + "cume_dist": "da7394e2fa8d2621", + "curdate": "e1022076edab285e", + "current_catalog": "81e9d1b69b4d3b96", + "current_database": "276a6a3396e2195e", + "current_date": "fadbae5dd9865289", + "current_path": "04265fe16f40af5a", + "current_schema": "3f1b2d67845df45e", + "current_time": "53709557112c2e84", + "current_timestamp": "8599b9b3db5d9db9", + "current_timezone": "2cd203c8736fe23f", + "current_user": "d649c5038593a176", + "date_add": "9f507ce9a3c9d419", + "date_diff": "dddf7e7d146303e7", + "date_format": "882a038205b1c186", + "date_from_unix_date": "1a0e14f983e948eb", + "date_part": null, + "date_sub": "85be38a4c0a8ebeb", + "date_trunc": "b23555b913e49600", + "dateadd": "184afb11cf432a75", + "datediff": "617b10035a4b4faa", + "datepart": null, + "day": "8f69762d1c8a8498", + "dayname": "6c1bdc1631c7b51c", + "dayofmonth": "c01d615fe363026d", + "dayofweek": "fa0d01239042b584", + "dayofyear": "667f6fc04cb75e51", + "days": "05224fbea3f2735d", + "decode": "84c03d976824e27d", + "degrees": "4af0bfd99e6e8f61", + "dense_rank": "289f218b14b2efd6", + "desc": "36397d042f9e0b76", + "desc_nulls_first": "0d6fdfd6e440a2f1", + "desc_nulls_last": "0eea59eb9a4304a8", + "e": "308005749d2f236c", + "element_at": "eb0f01672c442d9c", + "elt": "38039aed5d14caf2", + "encode": "d546456ecedbc309", + "endswith": "7983de5e6b9272d4", + "equal_null": "156a60f7e35cae6c", + "every": "5055d039f77e02a4", + "exists": "3e16c7a8f6d1bdd2", + "exp": "875e231e1a777b42", + "explode": "ade946e06908c79a", + "explode_outer": "a2826f43cfafe537", + "expm1": "33c99e9771fbb8bd", + "expr": "c067e5d66ded13cd", + "extract": "71ddeda9ddb8dfbc", + "factorial": "a21b0c5bc072b73d", + "filter": "ef34e6c2788df310", + "find_in_set": "9893f21bf05cd1d2", + "first": "61fb0ee856f00850", + "first_value": "b038293197088b4f", + "flatten": "87d3daf6f1496f18", + "floor": "d0df0bb0f3895138", + "forall": "e0fb55480d34cf8c", + "format_number": "4cf87dbf0f6b9c87", + "format_string": "19db07ea55cbb99c", + "from_base32": "37899356d15ba2e3", + "from_csv": "f6832849626d9ccb", + "from_json": "fcbce7c6ed5035a5", + "from_unixtime": "74939340a798bd0a", + "from_utc_timestamp": "287af1ead35b82b4", + "from_xml": "737364f25bc1bc0e", + "get": "b1f7f3e40960663c", + "get_json_object": "8bdaf44aaddf8604", + "getbit": "f1f1d57ebd4d76d9", + "greatest": "12a7f332a577b11e", + "grouping": "cf7ce129ec71d94f", + "grouping_id": "55c81a20223d078c", + "hash": "a4fbd5e917ce3fe4", + "hex": "4d661545d7be93ee", + "histogram_numeric": "b1667fba06d58ea7", + "hll_sketch_agg": "70b7937881aa7f94", + "hll_sketch_estimate": "33575a52dcfaa92d", + "hll_union": "910a3bf0ff877fd7", + "hll_union_agg": "65ee252e9e105089", + "hmac": "1d477007f621ba0d", + "hour": "b089dc804034f37e", + "hours": "627f7cd339d5cef6", + "hypot": "9da63e28204ef87d", + "ifnull": "e6bcd9bb46e05b9c", + "ilike": "4f4e3930db948bb2", + "initcap": "f34adec0d5ea10bf", + "inline": "6d5d2034c1d421e5", + "inline_outer": "91d028fd086ccaf1", + "input_file_block_length": "2d6f5dd460dd4582", + "input_file_block_start": "f9d56b335d646647", + "input_file_name": "630dac746449fd9d", + "instr": "640d8850fd99af8c", + "is_valid_utf8": "127f90b223ba2e0b", + "is_valid_variant": "005fc013df1d5ff4", + "is_variant_null": "312a8bd012e61adc", + "isnan": "eb893e24a348ee96", + "isnotnull": "7ed1dde5479d422a", + "isnull": "82ee67fbb2c90ee5", + "jaro_winkler_similarity": "38da1cc3189c42d4", + "java_method": "0b408a6ab4f04747", + "json_array_length": "bf64522844ac19d6", + "json_object_keys": "0e7c6521e8a14d9f", + "json_tuple": "85b1ea7047dd605c", + "kll_merge_agg_bigint": "5c6271e2cbaacd63", + "kll_merge_agg_double": "49f918f7e8a1a256", + "kll_merge_agg_float": "459622dcdffdd46f", + "kll_sketch_agg_bigint": "829abf4cb11886cc", + "kll_sketch_agg_double": "3b520c39f9c252b3", + "kll_sketch_agg_float": "278f25eb54e144e6", + "kll_sketch_get_n_bigint": "d0d52d7cb33caa55", + "kll_sketch_get_n_double": "8cd6f784bafe347e", + "kll_sketch_get_n_float": "69dba7b50620f972", + "kll_sketch_get_quantile_bigint": "03227993dbe5712c", + "kll_sketch_get_quantile_double": "5448c4f8031029af", + "kll_sketch_get_quantile_float": "066b897feccccd50", + "kll_sketch_get_rank_bigint": "a69677e836587821", + "kll_sketch_get_rank_double": "b4dd02276d00391e", + "kll_sketch_get_rank_float": "a16bbb1174e1589d", + "kll_sketch_merge_bigint": "ec7adfcbdbb44d03", + "kll_sketch_merge_double": "087396b12f6b19b8", + "kll_sketch_merge_float": "72601b74937ba504", + "kll_sketch_to_string_bigint": "fc09aec11dc74f90", + "kll_sketch_to_string_double": "e1c06eea0e7c344f", + "kll_sketch_to_string_float": "7c32920e28490c23", + "kurtosis": "15c8e6a328a47326", + "lag": "2d976cdfcfd98ce1", + "last": "1d9ee3d434e174e9", + "last_day": "fea2b4fb73e1e3ff", + "last_value": "81c14feee3c7db6d", + "lcase": "d4bfff940a00a12d", + "lead": "a40dc991a0b57ee2", + "least": "6515e7579c31d375", + "left": "c34a19a9dab381b7", + "length": "ae65f027a5fbea3b", + "levenshtein": "49b2de8360f91f71", + "like": "0f9e9c0bb6b45721", + "listagg": "6d97096121531ebc", + "listagg_distinct": "5c140551a35d22c0", + "lit": "24e8198c7bfa35a7", + "ln": "4efb6a00e3021309", + "localtimestamp": "3d546583b48882b9", + "locate": "115ba75cdc97818b", + "log": "f9675d05a1f2874e", + "log10": "799360f0d4e0b1f6", + "log1p": "c27dc0e668f2c4c7", + "log2": "702c01a658b8c407", + "lower": "28e67f95d8382e00", + "lpad": "4665c198dc4c16fb", + "ltrim": "233e43ad319276fc", + "make_date": "c97a7c1a00acc35b", + "make_dt_interval": "90c3130b3d59b5a6", + "make_interval": "a6f367b1d24159de", + "make_time": "8e8b15723224f22c", + "make_timestamp": "a5420f0eb90899cd", + "make_timestamp_ltz": "cb6a4e03dd5e755f", + "make_timestamp_ntz": "c9d75c794fd25f93", + "make_valid_utf8": "fd2b068d45200927", + "make_ym_interval": "d4a213be9d15a9aa", + "map_concat": "bea522c675af4eb8", + "map_contains_key": "5540d160c37b27b9", + "map_entries": "55ff32528457180a", + "map_filter": "4be994f16e0d0ac6", + "map_from_arrays": "759b860b18f6f65d", + "map_from_entries": "09ea5f43468b1025", + "map_keys": "c0ec18cfbe8a6e59", + "map_values": "34bd51577d64fa2c", + "map_zip_with": "03dad7ec923f23a8", + "mask": "5c8a2a57fcf839a7", + "max": "1cc6f503b7b99dc9", + "max_by": "1a2fd0c3ef5bfa4f", + "md5": "1cb0bb35ddf64f21", + "mean": "6b9af09d59a9ba17", + "median": "20341cafe254066d", + "min": "93ca096a990d1fad", + "min_by": "313575513ded0448", + "minute": "69653633e2a606b1", + "mode": "f42be8142247c377", + "monotonically_increasing_id": "2ad2b4932aa2affd", + "month": "84fe8a15581bc348", + "monthname": "88097599a00ec5bc", + "months": "da37f206bd7c684b", + "months_between": "832b275e60e62753", + "named_struct": "be7e71f75c9690b6", + "nanvl": "3c11f57381be3386", + "negate": "e897ad4365aa8655", + "negative": "e897ad4365aa8655", + "next_day": "f1e71b4ac75a961e", + "now": "8d16195a89fa7303", + "nth_value": "9c29d6e117db1a70", + "ntile": "cb8f1fda23951750", + "nullif": "72a943de98bc6db3", + "nullifzero": "4799ccecc7733159", + "nvl": "110e101e28d30dce", + "nvl2": "67540b35e6e1ca6b", + "octet_length": "32283b1801a40b3a", + "overlay": "020ca7aaea7edf41", + "parse_json": "ee65def0bc67c9e8", + "parse_url": "dbcc3ffa1d7d5ca2", + "percent_rank": "badbaab1c2c3d630", + "percentile": "2d1f9eded8ffe583", + "percentile_approx": "ce1992621975d2f9", + "pi": "3e5ca062c4eb0c54", + "pmod": "6141363dd01342e0", + "posexplode": "3aed0f0d2d223697", + "posexplode_outer": "273dcf608aca9490", + "position": "d61386e748b26e92", + "positive": "0950d8153d25eee2", + "pow": "0d97805b6b4e3171", + "power": "0d97805b6b4e3171", + "printf": "1eba5b813371a4a2", + "product": "ccadfb38657287d2", + "quarter": "d208044babedda3a", + "quote": "7ad7d99f5997c024", + "radians": "abbed92f5d294723", + "raise_error": "ccca5da1fe8a688a", + "rand": "d79ae250586b5e6d", + "randn": "cff5ac7c294cc12e", + "random": "d79ae250586b5e6d", + "randstr": "b34d85401a693666", + "rank": "fa739f1aab54d30a", + "reduce": "373866c54948b1ad", + "reflect": "db0a4acb8af6d832", + "regexp": "0dffc68f2c7f04a4", + "regexp_count": "948e681154db3e3b", + "regexp_extract": "39d190471655777c", + "regexp_extract_all": "ee7223b2e37733bc", + "regexp_instr": "d28f19ee037c3283", + "regexp_like": "29831bb3b33e46ed", + "regexp_replace": "9c67324e066ce91b", + "regexp_substr": "c149a9b36a9dcec7", + "regr_avgx": "78c89102b5f91b50", + "regr_avgy": "02641c410cc99667", + "regr_count": "979ffb1f52060872", + "regr_intercept": "371e9373bbdcf53b", + "regr_r2": "a8507b986ba076b4", + "regr_slope": "62ecec8e88b7602e", + "regr_sxx": "6b07aa20249c3442", + "regr_sxy": "77422c6c1a35aa38", + "regr_syy": "32aff79154fe6173", + "repeat": "ad4809e744f57c76", + "replace": "c62e7afb3d466a88", + "reverse": "95594ea99c6dd10a", + "right": "45aca6f0830bbe4a", + "rint": "3b8a5d8af9bd8a4f", + "rlike": "af37840f6753f84a", + "round": "6348002189074593", + "row_number": "49380e26032b76b3", + "rpad": "4ce79ecc9b3bb7e7", + "rtrim": "332c0c2ac6d4581a", + "schema_of_csv": "5973cec518ceb317", + "schema_of_json": "95a4106a9bfe50c8", + "schema_of_variant": "c63aa6e732cb6727", + "schema_of_variant_agg": "5915aa42ba4717ff", + "schema_of_xml": "acf2d26857c900d8", + "sec": "8de5a7c5ad8daeab", + "second": "c794a175252cc3ae", + "sentences": "e951e704278d59d5", + "sequence": "a29375880e4cea51", + "session_user": "da762248e37d45f2", + "session_window": "497a5f8bd08f420a", + "sha": "ef799e1f0300cbc2", + "sha1": "ffbe3938d6cba771", + "sha2": "bbf51b061ee5b656", + "shiftLeft": "4a777d8e57e9cae7", + "shiftRight": "e7c2631fd55b1481", + "shiftRightUnsigned": "3b363aab1c5e55f0", + "shiftleft": "1d551f422c5eee5a", + "shiftright": "56c98814fbbf2cc1", + "shiftrightunsigned": "156753c22d0a6d84", + "shuffle": "ee927f7c57b92d7b", + "sign": "36cee609caf4052b", + "signum": "791493c89ba6c02d", + "sin": "3af94e9d7cddd076", + "sinh": "e61ccc0150e0d374", + "size": "c2d96b389d67c467", + "skewness": "d9802d472b1756a9", + "slice": "4b8fc4310edc2f52", + "some": "0c02733eb262e677", + "sort_array": "fadf5b527a8b62d6", + "soundex": "14ea077dfc7a0661", + "spark_partition_id": "f9ef158a30b48ed4", + "split": "6068b7b90ac414e8", + "split_part": "f5654f2b3ae527ef", + "sqrt": "14056fe18c284cde", + "st_asbinary": "616e9f552b2aa48c", + "st_geogfromwkb": "75fe2ed08071660d", + "st_geomfromwkb": "2fbc6c459d55decf", + "st_setsrid": "662a2486186eb8b4", + "st_srid": "8f25756dafa35fb7", + "stack": "74fdde41cacdac16", + "startswith": "a380956c4adeaefe", + "std": "2e5c921925d2b1f9", + "stddev": "2ceac986585b86ca", + "stddev_pop": "78ff13b3b92f8c94", + "stddev_samp": "3cffb6b953f9510c", + "str_to_map": "7c91c71ee70f2e78", + "string_agg": "77b4152fad69f041", + "string_agg_distinct": "a8b0c97555197f28", + "struct": "6dd3dcc1e61720b9", + "substr": "298b69b80be42ac7", + "substring": "381984a3689a8a07", + "substring_index": "3624f81481d1ec8d", + "sum": "02c1a3094057652a", + "sumDistinct": "c0b83f51e0f4c136", + "sum_distinct": "aa86f390dfc5ed2a", + "tan": "8dd44c4d4c5c99d1", + "tanh": "c77d45140318544c", + "theta_difference": "a74e0b31b4bfecb6", + "theta_intersection": "ce917848780c5d5c", + "theta_intersection_agg": "3ef41b981c21ef83", + "theta_sketch_agg": "192199ce74ee3402", + "theta_sketch_estimate": "817f99db6600e368", + "theta_union": "f6feb9adbe4c3cd4", + "theta_union_agg": "143e910295999890", + "time_bucket": "f1c47d91c4acc7be", + "time_diff": "ef570ad507ba20d6", + "time_from_micros": "586ac4f84b8584e9", + "time_from_millis": "9b1ee615f32e8606", + "time_from_seconds": "61bb395e41232777", + "time_to_micros": "3e96f32e8e94c2cc", + "time_to_millis": "be945a2eaedf4f8d", + "time_to_seconds": "a78cabbd1235d859", + "time_trunc": "0ef118220d3b2663", + "timestamp_add": "fbd55dcabc8e77e7", + "timestamp_diff": "07d402cfdd7427ba", + "timestamp_micros": "062953c15a462da7", + "timestamp_millis": "949011ac47996715", + "timestamp_nanos": "26497d9d5be6772e", + "timestamp_seconds": "b6fa35adde863fbf", + "toDegrees": "98f6de96b00640b7", + "toRadians": "d67b46ec2a4927b1", + "to_base32": "e21497df25d0be3f", + "to_binary": "60ebd4c1e845f2b4", + "to_char": "21f9d2ec2c35aa8e", + "to_csv": "2b22df5e55212ee3", + "to_date": "4db4bde885ec5ba9", + "to_json": "0690831e11177ba9", + "to_number": "ea810169e01be4bb", + "to_time": "726bd65a7ecbdc48", + "to_timestamp": "66998f4e7050c51f", + "to_timestamp_ltz": "4c176de5f0df0f83", + "to_timestamp_ntz": "d0f9b6f7caa7f3f7", + "to_unix_timestamp": "2fccfd9a66667396", + "to_utc_timestamp": "34bf8f636c6f4e29", + "to_varchar": "05cc858a6ce3f814", + "to_variant_object": "10938e516e34aa11", + "to_xml": "044ac22d0312ecfd", + "transform": "a56fd4fa5e4b37a7", + "transform_keys": "4bf5dd13fa41bb3d", + "transform_values": "860e5de5d42ed64e", + "translate": "fb94d9f5d1f280b0", + "trim": "6f5d5b410065ee92", + "trunc": "faba8f67477b5210", + "try_add": "2227ef78882ad20d", + "try_aes_decrypt": "b4f5350ea1b3ca4a", + "try_avg": "cdf5da478c3c1b39", + "try_divide": "e38cc9bc9adb016f", + "try_element_at": "1483d9ee5f7df026", + "try_make_interval": "2d5a9ec4c0135126", + "try_make_timestamp": "035859ff7468b5b3", + "try_make_timestamp_ltz": "bd94e87613383539", + "try_make_timestamp_ntz": "874b8c33721527f1", + "try_mod": "cf05020bab9a1c5b", + "try_multiply": "d654528ce929e409", + "try_parse_json": "6cee97b7d3068e9d", + "try_parse_url": "f6b7cbf26bccf05d", + "try_reflect": "95dafd7be31a4d78", + "try_subtract": "96a09e77df99e296", + "try_sum": "69c2e29f926b7a9f", + "try_to_binary": "3c3213c0cb3caccb", + "try_to_date": "b1f53484e3f321d0", + "try_to_number": "28e84d8546aa0d1f", + "try_to_time": "9785223e6b35eebd", + "try_to_timestamp": "86f90c156409abbb", + "try_url_decode": "ba56cb6c52ecf535", + "try_validate_utf8": "2de9c35e2e361be7", + "try_variant_array_append": "eb0102f7cdd9d239", + "try_variant_get": "2abc88055c634ead", + "try_variant_insert": "2dd0b393011e045d", + "try_variant_set": "c0a6dd29cbbf4191", + "tuple_difference_double": "a8f3d13f57d7a5ae", + "tuple_difference_integer": "9e54a8d9c045a901", + "tuple_difference_theta_double": "dc868b56b98063ab", + "tuple_difference_theta_integer": "268d1e354f53bfe9", + "tuple_intersection_agg_double": "6fd196f1198530e9", + "tuple_intersection_agg_integer": "2f18e529aac48cce", + "tuple_intersection_double": "9c1050bc9ff4fe99", + "tuple_intersection_integer": "9bd3676ec4ce2536", + "tuple_intersection_theta_double": "38f6a864b8657e5b", + "tuple_intersection_theta_integer": "9b33636a9d969d46", + "tuple_sketch_agg_double": "93ba360c5003abe8", + "tuple_sketch_agg_integer": "8bb0ef1a6e75ad71", + "tuple_sketch_estimate_double": "07319585172773e3", + "tuple_sketch_estimate_integer": "842b96efff301320", + "tuple_sketch_summary_double": "07bc2c80d181fc23", + "tuple_sketch_summary_integer": "09be91a7b0a0e956", + "tuple_sketch_theta_double": "88a6e27e9d5d6534", + "tuple_sketch_theta_integer": "0d960cf99f1e6d55", + "tuple_union_agg_double": "f39245da5ee4aa25", + "tuple_union_agg_integer": "a4a7dc2581abe3df", + "tuple_union_double": "2809762a399460b5", + "tuple_union_integer": "187647f533077701", + "tuple_union_theta_double": "9aca4e11e47fcbd7", + "tuple_union_theta_integer": "8b613251081c248e", + "typeof": "ce3bf7abab867017", + "ucase": "83b806742cada732", + "udf": "b99fed075406b4be", + "udtf": "4121a64f2bb59859", + "unbase64": "22c1530d7093bba3", + "unhex": "ff3a7ff1400801a6", + "uniform": "1b39777cd40d575b", + "unix_date": "20813b5eeebe6f5d", + "unix_micros": "b6c43803febc5be7", + "unix_millis": "b5100c98007a98b5", + "unix_nanos": "b55bdf8341dd3444", + "unix_seconds": "cc091f6f0d55cc62", + "unix_timestamp": "650eb1b4ede9e6d2", + "unwrap_udt": "6f7cdbfbd406d105", + "upper": "ccb592aef856b628", + "url_decode": "89d45cf75285d63d", + "url_encode": "6ce670a651bde97e", + "user": "c6cf8927af611a8e", + "uuid": null, + "validate_utf8": "c10cc7b18a0f601d", + "var_pop": "fc0be13e0065976f", + "var_samp": "d3feb5667846199d", + "variance": "8fb7e1fb4139e221", + "variant_array_append": "493a95aac3a59d52", + "variant_delete": "7f6380a9947071ea", + "variant_get": "23c4e2d1175ea1b5", + "variant_insert": "4783201bd765f96e", + "variant_set": "50ee06fc4aae2994", + "variant_strip_nulls": "8d3cb659d76606db", + "vector_avg": "d6259ba6aba4e736", + "vector_cosine_similarity": "5e6c91c5b4c9b637", + "vector_inner_product": "a29acbdb76acbeb7", + "vector_l2_distance": "656f01fcf6f06caa", + "vector_norm": "d3e426ae948cfbfa", + "vector_normalize": "5cbe1eca31d2a0ee", + "vector_sum": "d513faea14c5f5cb", + "version": "cd51fb5ab88739e6", + "weekday": "d201eea2f777ca13", + "weekofyear": "e518e42706b87a44", + "when": "1f20e0856d4a38b6", + "width_bucket": "7d4a160c4832366a", + "window": "9f1b34a7cdfd0c80", + "window_time": "efd7b305a3610723", + "xpath": "727f186711c48f1b", + "xpath_boolean": "20b198e976e043ff", + "xpath_double": "13b30f927857a89c", + "xpath_float": "52acd0cc9a5b36f0", + "xpath_int": "3e68e56675bcd1f1", + "xpath_long": "b9507c207f95c91f", + "xpath_number": "4d0e802bfa933e2b", + "xpath_short": "362bae302dadb530", + "xpath_string": "f2aeafa6d980002e", + "xxhash64": "ec809d05fb6386ad", + "year": "a7e590da777b7c9c", + "years": "ca6e1e3d49717724", + "zeroifnull": "eaad5a9432d81b92", + "zip_with": "4d60303577da9444" + }, + "pyspark.sql.connect.functions.partitioning": { + "": null, + "bucket": "56707b7d014918a9", + "days": "f967843fd17e3b67", + "hours": "399452773ecfb80a", + "months": "232f02b1378570e9", + "years": "539ba45c0d07504e" + }, "pyspark.sql.connect.group": { "": null, "GroupedData": "4a6a06a1319caa28", - "GroupedData.__init__": null, + "GroupedData.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "GroupedData.agg": "590f40c6fa987591", "GroupedData.apply": "e2f3cebe1ae08945", "GroupedData.applyInArrow": "8fb441e057226613", @@ -1211,14 +2583,18 @@ "GroupedData.transformWithState": "96b6a05a2b745100", "GroupedData.transformWithStateInPandas": "686a4f501ac02888", "PandasCogroupedOps": "50671c128a962e8d", - "PandasCogroupedOps.__init__": null, + "PandasCogroupedOps.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PandasCogroupedOps.applyInArrow": "75ab8fc23bc05d41", "PandasCogroupedOps.applyInPandas": "bda600b794baaa87" }, "pyspark.sql.connect.local_server": { "": "2229e2045b89b7b8", "Discovery": "e4606d434c07bcbc", - "Discovery.__init__": null, + "Discovery.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "Discovery.clear": null, "Discovery.daemon_pid": "0f0c9270a4175f9c", "Discovery.daemon_pid_path": null, @@ -1226,14 +2602,18 @@ "Discovery.load": "6bc14f514bc8b0a2", "Discovery.save": "52ad71b624148015", "LocalConnectServer": "bdd785f19013b497", - "LocalConnectServer.__init__": null, + "LocalConnectServer.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "LocalConnectServer.is_listening": null, "LocalConnectServer.is_reusable": null, "LocalConnectServer.reuse_or_start": null, "LocalConnectServer.stop": null, "LocalConnectServer.url": null, "ServerLauncher": "81ed5cb1eec3c5dc", - "ServerLauncher.__init__": null, + "ServerLauncher.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ServerLauncher.launch": null, "main": null, "reuse_or_start_local_connect_server": "3207e801898cc5a0", @@ -1250,7 +2630,9 @@ "MergeIntoWriter.WhenMatched": "ea003cc72784340c", "MergeIntoWriter.WhenNotMatched": "2cd0d5ee07c3ab4d", "MergeIntoWriter.WhenNotMatchedBySource": "97618580d879b28f", - "MergeIntoWriter.__init__": null, + "MergeIntoWriter.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "MergeIntoWriter.merge": "e23d36247d335212", "MergeIntoWriter.whenMatched": "e763837f75f1c868", "MergeIntoWriter.whenNotMatched": "350347531c324a8d", @@ -1267,7 +2649,9 @@ "": null, "Aggregate": null, "Aggregate.INDENT": "4072aed12b3287d8", - "Aggregate.__init__": null, + "Aggregate.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Aggregate.command": null, "Aggregate.observations": null, "Aggregate.plan": null, @@ -1275,7 +2659,9 @@ "Aggregate.to_proto": "e27bb34d5f13b97a", "AnalyzeTable": null, "AnalyzeTable.INDENT": "4072aed12b3287d8", - "AnalyzeTable.__init__": null, + "AnalyzeTable.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "AnalyzeTable.command": null, "AnalyzeTable.observations": null, "AnalyzeTable.plan": null, @@ -1283,7 +2669,9 @@ "AnalyzeTable.to_proto": "e27bb34d5f13b97a", "ApplyInPandasWithState": "800c98b30da8b532", "ApplyInPandasWithState.INDENT": "4072aed12b3287d8", - "ApplyInPandasWithState.__init__": null, + "ApplyInPandasWithState.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ApplyInPandasWithState.command": null, "ApplyInPandasWithState.observations": null, "ApplyInPandasWithState.plan": null, @@ -1291,15 +2679,21 @@ "ApplyInPandasWithState.to_proto": "e27bb34d5f13b97a", "AsOfJoin": null, "AsOfJoin.INDENT": "4072aed12b3287d8", - "AsOfJoin.__init__": null, + "AsOfJoin.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "AsOfJoin.command": null, "AsOfJoin.observations": null, "AsOfJoin.plan": null, - "AsOfJoin.print": null, + "AsOfJoin.print": { + "getdoc": "2bb2945c88af8787" + }, "AsOfJoin.to_proto": "e27bb34d5f13b97a", "BaseTransformWithStateInPySpark": "ae3544091f4aade9", "BaseTransformWithStateInPySpark.INDENT": "4072aed12b3287d8", - "BaseTransformWithStateInPySpark.__init__": null, + "BaseTransformWithStateInPySpark.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "BaseTransformWithStateInPySpark.command": null, "BaseTransformWithStateInPySpark.observations": null, "BaseTransformWithStateInPySpark.plan": null, @@ -1307,7 +2701,9 @@ "BaseTransformWithStateInPySpark.to_proto": "e27bb34d5f13b97a", "CacheTable": null, "CacheTable.INDENT": "4072aed12b3287d8", - "CacheTable.__init__": null, + "CacheTable.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CacheTable.command": null, "CacheTable.observations": null, "CacheTable.plan": null, @@ -1315,7 +2711,9 @@ "CacheTable.to_proto": "e27bb34d5f13b97a", "CachedRelation": null, "CachedRelation.INDENT": "4072aed12b3287d8", - "CachedRelation.__init__": null, + "CachedRelation.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CachedRelation.command": null, "CachedRelation.observations": null, "CachedRelation.plan": null, @@ -1323,7 +2721,9 @@ "CachedRelation.to_proto": "e27bb34d5f13b97a", "CachedRemoteRelation": "8d56797361b6bc4b", "CachedRemoteRelation.INDENT": "4072aed12b3287d8", - "CachedRemoteRelation.__init__": null, + "CachedRemoteRelation.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CachedRemoteRelation.command": null, "CachedRemoteRelation.observations": null, "CachedRemoteRelation.plan": null, @@ -1331,7 +2731,9 @@ "CachedRemoteRelation.to_proto": "e27bb34d5f13b97a", "Checkpoint": null, "Checkpoint.INDENT": "4072aed12b3287d8", - "Checkpoint.__init__": null, + "Checkpoint.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Checkpoint.command": null, "Checkpoint.observations": null, "Checkpoint.plan": null, @@ -1339,15 +2741,21 @@ "Checkpoint.to_proto": "e27bb34d5f13b97a", "ChunkedCachedLocalRelation": "3ccb0137f5f9fb7e", "ChunkedCachedLocalRelation.INDENT": "4072aed12b3287d8", - "ChunkedCachedLocalRelation.__init__": null, + "ChunkedCachedLocalRelation.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ChunkedCachedLocalRelation.command": null, "ChunkedCachedLocalRelation.observations": null, "ChunkedCachedLocalRelation.plan": null, - "ChunkedCachedLocalRelation.print": null, + "ChunkedCachedLocalRelation.print": { + "getdoc": "2bb2945c88af8787" + }, "ChunkedCachedLocalRelation.to_proto": "e27bb34d5f13b97a", "ClearCache": null, "ClearCache.INDENT": "4072aed12b3287d8", - "ClearCache.__init__": null, + "ClearCache.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ClearCache.command": null, "ClearCache.observations": null, "ClearCache.plan": null, @@ -1355,7 +2763,9 @@ "ClearCache.to_proto": "e27bb34d5f13b97a", "CoGroupMap": "e533fdad52af4939", "CoGroupMap.INDENT": "4072aed12b3287d8", - "CoGroupMap.__init__": null, + "CoGroupMap.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CoGroupMap.command": null, "CoGroupMap.observations": null, "CoGroupMap.plan": null, @@ -1363,7 +2773,9 @@ "CoGroupMap.to_proto": "e27bb34d5f13b97a", "CollectMetrics": "0223e91120813830", "CollectMetrics.INDENT": "4072aed12b3287d8", - "CollectMetrics.__init__": null, + "CollectMetrics.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CollectMetrics.command": null, "CollectMetrics.observations": null, "CollectMetrics.plan": null, @@ -1371,7 +2783,9 @@ "CollectMetrics.to_proto": "e27bb34d5f13b97a", "CommonInlineUserDefinedDataSource": "0ad4d75f09c3483c", "CommonInlineUserDefinedDataSource.INDENT": "4072aed12b3287d8", - "CommonInlineUserDefinedDataSource.__init__": null, + "CommonInlineUserDefinedDataSource.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CommonInlineUserDefinedDataSource.command": null, "CommonInlineUserDefinedDataSource.observations": null, "CommonInlineUserDefinedDataSource.plan": null, @@ -1380,7 +2794,9 @@ "CommonInlineUserDefinedDataSource.to_proto": "e27bb34d5f13b97a", "CommonInlineUserDefinedTableFunction": "ca103e8d5a617a59", "CommonInlineUserDefinedTableFunction.INDENT": "4072aed12b3287d8", - "CommonInlineUserDefinedTableFunction.__init__": null, + "CommonInlineUserDefinedTableFunction.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CommonInlineUserDefinedTableFunction.command": null, "CommonInlineUserDefinedTableFunction.observations": null, "CommonInlineUserDefinedTableFunction.plan": null, @@ -1389,7 +2805,9 @@ "CommonInlineUserDefinedTableFunction.udtf_plan": "83ec97f1e5721d3e", "CreateDatabase": null, "CreateDatabase.INDENT": "4072aed12b3287d8", - "CreateDatabase.__init__": null, + "CreateDatabase.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CreateDatabase.command": null, "CreateDatabase.observations": null, "CreateDatabase.plan": null, @@ -1397,7 +2815,9 @@ "CreateDatabase.to_proto": "e27bb34d5f13b97a", "CreateTable": null, "CreateTable.INDENT": "4072aed12b3287d8", - "CreateTable.__init__": null, + "CreateTable.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CreateTable.command": null, "CreateTable.observations": null, "CreateTable.plan": null, @@ -1405,7 +2825,9 @@ "CreateTable.to_proto": "e27bb34d5f13b97a", "CreateView": null, "CreateView.INDENT": "4072aed12b3287d8", - "CreateView.__init__": null, + "CreateView.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CreateView.command": null, "CreateView.observations": null, "CreateView.plan": null, @@ -1413,7 +2835,9 @@ "CreateView.to_proto": "e27bb34d5f13b97a", "CurrentCatalog": null, "CurrentCatalog.INDENT": "4072aed12b3287d8", - "CurrentCatalog.__init__": null, + "CurrentCatalog.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CurrentCatalog.command": null, "CurrentCatalog.observations": null, "CurrentCatalog.plan": null, @@ -1421,7 +2845,9 @@ "CurrentCatalog.to_proto": "e27bb34d5f13b97a", "CurrentDatabase": null, "CurrentDatabase.INDENT": "4072aed12b3287d8", - "CurrentDatabase.__init__": null, + "CurrentDatabase.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "CurrentDatabase.command": null, "CurrentDatabase.observations": null, "CurrentDatabase.plan": null, @@ -1429,7 +2855,9 @@ "CurrentDatabase.to_proto": "e27bb34d5f13b97a", "DataSource": "31b37cc5cb83c78a", "DataSource.INDENT": "4072aed12b3287d8", - "DataSource.__init__": null, + "DataSource.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "DataSource.command": null, "DataSource.observations": null, "DataSource.plan": null, @@ -1437,7 +2865,9 @@ "DataSource.to_proto": "e27bb34d5f13b97a", "DatabaseExists": null, "DatabaseExists.INDENT": "4072aed12b3287d8", - "DatabaseExists.__init__": null, + "DatabaseExists.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "DatabaseExists.command": null, "DatabaseExists.observations": null, "DatabaseExists.plan": null, @@ -1445,7 +2875,9 @@ "DatabaseExists.to_proto": "e27bb34d5f13b97a", "Deduplicate": null, "Deduplicate.INDENT": "4072aed12b3287d8", - "Deduplicate.__init__": null, + "Deduplicate.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Deduplicate.command": null, "Deduplicate.observations": null, "Deduplicate.plan": null, @@ -1453,7 +2885,9 @@ "Deduplicate.to_proto": "e27bb34d5f13b97a", "Drop": null, "Drop.INDENT": "4072aed12b3287d8", - "Drop.__init__": null, + "Drop.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Drop.command": null, "Drop.observations": null, "Drop.plan": null, @@ -1461,7 +2895,9 @@ "Drop.to_proto": "e27bb34d5f13b97a", "DropDatabase": null, "DropDatabase.INDENT": "4072aed12b3287d8", - "DropDatabase.__init__": null, + "DropDatabase.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "DropDatabase.command": null, "DropDatabase.observations": null, "DropDatabase.plan": null, @@ -1469,7 +2905,9 @@ "DropDatabase.to_proto": "e27bb34d5f13b97a", "DropGlobalTempView": null, "DropGlobalTempView.INDENT": "4072aed12b3287d8", - "DropGlobalTempView.__init__": null, + "DropGlobalTempView.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "DropGlobalTempView.command": null, "DropGlobalTempView.observations": null, "DropGlobalTempView.plan": null, @@ -1477,7 +2915,9 @@ "DropGlobalTempView.to_proto": "e27bb34d5f13b97a", "DropTable": null, "DropTable.INDENT": "4072aed12b3287d8", - "DropTable.__init__": null, + "DropTable.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "DropTable.command": null, "DropTable.observations": null, "DropTable.plan": null, @@ -1485,7 +2925,9 @@ "DropTable.to_proto": "e27bb34d5f13b97a", "DropTempView": null, "DropTempView.INDENT": "4072aed12b3287d8", - "DropTempView.__init__": null, + "DropTempView.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "DropTempView.command": null, "DropTempView.observations": null, "DropTempView.plan": null, @@ -1493,7 +2935,9 @@ "DropTempView.to_proto": "e27bb34d5f13b97a", "DropView": null, "DropView.INDENT": "4072aed12b3287d8", - "DropView.__init__": null, + "DropView.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "DropView.command": null, "DropView.observations": null, "DropView.plan": null, @@ -1501,7 +2945,9 @@ "DropView.to_proto": "e27bb34d5f13b97a", "Filter": null, "Filter.INDENT": "4072aed12b3287d8", - "Filter.__init__": null, + "Filter.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Filter.command": null, "Filter.observations": null, "Filter.plan": null, @@ -1509,7 +2955,9 @@ "Filter.to_proto": "e27bb34d5f13b97a", "FunctionExists": null, "FunctionExists.INDENT": "4072aed12b3287d8", - "FunctionExists.__init__": null, + "FunctionExists.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "FunctionExists.command": null, "FunctionExists.observations": null, "FunctionExists.plan": null, @@ -1517,7 +2965,9 @@ "FunctionExists.to_proto": "e27bb34d5f13b97a", "GetCreateTableString": null, "GetCreateTableString.INDENT": "4072aed12b3287d8", - "GetCreateTableString.__init__": null, + "GetCreateTableString.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "GetCreateTableString.command": null, "GetCreateTableString.observations": null, "GetCreateTableString.plan": null, @@ -1525,7 +2975,9 @@ "GetCreateTableString.to_proto": "e27bb34d5f13b97a", "GetDatabase": null, "GetDatabase.INDENT": "4072aed12b3287d8", - "GetDatabase.__init__": null, + "GetDatabase.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "GetDatabase.command": null, "GetDatabase.observations": null, "GetDatabase.plan": null, @@ -1533,7 +2985,9 @@ "GetDatabase.to_proto": "e27bb34d5f13b97a", "GetFunction": null, "GetFunction.INDENT": "4072aed12b3287d8", - "GetFunction.__init__": null, + "GetFunction.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "GetFunction.command": null, "GetFunction.observations": null, "GetFunction.plan": null, @@ -1541,7 +2995,9 @@ "GetFunction.to_proto": "e27bb34d5f13b97a", "GetTable": null, "GetTable.INDENT": "4072aed12b3287d8", - "GetTable.__init__": null, + "GetTable.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "GetTable.command": null, "GetTable.observations": null, "GetTable.plan": null, @@ -1549,7 +3005,9 @@ "GetTable.to_proto": "e27bb34d5f13b97a", "GetTableProperties": null, "GetTableProperties.INDENT": "4072aed12b3287d8", - "GetTableProperties.__init__": null, + "GetTableProperties.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "GetTableProperties.command": null, "GetTableProperties.observations": null, "GetTableProperties.plan": null, @@ -1557,7 +3015,9 @@ "GetTableProperties.to_proto": "e27bb34d5f13b97a", "GroupMap": "c7fcaf117569f56c", "GroupMap.INDENT": "4072aed12b3287d8", - "GroupMap.__init__": null, + "GroupMap.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "GroupMap.command": null, "GroupMap.observations": null, "GroupMap.plan": null, @@ -1565,7 +3025,9 @@ "GroupMap.to_proto": "e27bb34d5f13b97a", "Hint": "a3e889ac3f42db01", "Hint.INDENT": "4072aed12b3287d8", - "Hint.__init__": null, + "Hint.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Hint.command": null, "Hint.observations": null, "Hint.plan": null, @@ -1573,7 +3035,9 @@ "Hint.to_proto": "e27bb34d5f13b97a", "HtmlString": null, "HtmlString.INDENT": "4072aed12b3287d8", - "HtmlString.__init__": null, + "HtmlString.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "HtmlString.command": null, "HtmlString.observations": null, "HtmlString.plan": null, @@ -1581,7 +3045,9 @@ "HtmlString.to_proto": "e27bb34d5f13b97a", "IsCached": null, "IsCached.INDENT": "4072aed12b3287d8", - "IsCached.__init__": null, + "IsCached.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "IsCached.command": null, "IsCached.observations": null, "IsCached.plan": null, @@ -1589,23 +3055,33 @@ "IsCached.to_proto": "e27bb34d5f13b97a", "Join": null, "Join.INDENT": "4072aed12b3287d8", - "Join.__init__": null, + "Join.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Join.command": null, "Join.observations": null, "Join.plan": null, - "Join.print": null, + "Join.print": { + "getdoc": "2bb2945c88af8787" + }, "Join.to_proto": "e27bb34d5f13b97a", "LateralJoin": null, "LateralJoin.INDENT": "4072aed12b3287d8", - "LateralJoin.__init__": null, + "LateralJoin.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "LateralJoin.command": null, "LateralJoin.observations": null, "LateralJoin.plan": null, - "LateralJoin.print": null, + "LateralJoin.print": { + "getdoc": "2bb2945c88af8787" + }, "LateralJoin.to_proto": "e27bb34d5f13b97a", "Limit": null, "Limit.INDENT": "4072aed12b3287d8", - "Limit.__init__": null, + "Limit.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Limit.command": null, "Limit.observations": null, "Limit.plan": null, @@ -1613,7 +3089,9 @@ "Limit.to_proto": "e27bb34d5f13b97a", "ListCatalogs": null, "ListCatalogs.INDENT": "4072aed12b3287d8", - "ListCatalogs.__init__": null, + "ListCatalogs.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ListCatalogs.command": null, "ListCatalogs.observations": null, "ListCatalogs.plan": null, @@ -1621,7 +3099,9 @@ "ListCatalogs.to_proto": "e27bb34d5f13b97a", "ListColumns": null, "ListColumns.INDENT": "4072aed12b3287d8", - "ListColumns.__init__": null, + "ListColumns.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ListColumns.command": null, "ListColumns.observations": null, "ListColumns.plan": null, @@ -1629,7 +3109,9 @@ "ListColumns.to_proto": "e27bb34d5f13b97a", "ListDatabases": null, "ListDatabases.INDENT": "4072aed12b3287d8", - "ListDatabases.__init__": null, + "ListDatabases.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ListDatabases.command": null, "ListDatabases.observations": null, "ListDatabases.plan": null, @@ -1637,7 +3119,9 @@ "ListDatabases.to_proto": "e27bb34d5f13b97a", "ListFunctions": null, "ListFunctions.INDENT": "4072aed12b3287d8", - "ListFunctions.__init__": null, + "ListFunctions.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ListFunctions.command": null, "ListFunctions.observations": null, "ListFunctions.plan": null, @@ -1645,7 +3129,9 @@ "ListFunctions.to_proto": "e27bb34d5f13b97a", "ListPartitions": null, "ListPartitions.INDENT": "4072aed12b3287d8", - "ListPartitions.__init__": null, + "ListPartitions.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ListPartitions.command": null, "ListPartitions.observations": null, "ListPartitions.plan": null, @@ -1653,7 +3139,9 @@ "ListPartitions.to_proto": "e27bb34d5f13b97a", "ListTables": null, "ListTables.INDENT": "4072aed12b3287d8", - "ListTables.__init__": null, + "ListTables.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ListTables.command": null, "ListTables.observations": null, "ListTables.plan": null, @@ -1661,7 +3149,9 @@ "ListTables.to_proto": "e27bb34d5f13b97a", "ListViews": null, "ListViews.INDENT": "4072aed12b3287d8", - "ListViews.__init__": null, + "ListViews.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ListViews.command": null, "ListViews.observations": null, "ListViews.plan": null, @@ -1669,11 +3159,15 @@ "ListViews.to_proto": "e27bb34d5f13b97a", "LocalRelation": "40304fb467582f97", "LocalRelation.INDENT": "4072aed12b3287d8", - "LocalRelation.__init__": null, + "LocalRelation.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "LocalRelation.command": null, "LocalRelation.observations": null, "LocalRelation.plan": null, - "LocalRelation.print": null, + "LocalRelation.print": { + "getdoc": "2bb2945c88af8787" + }, "LocalRelation.serialize": null, "LocalRelation.to_proto": "e27bb34d5f13b97a", "LogicalPlan": null, @@ -1686,7 +3180,9 @@ "LogicalPlan.to_proto": "e27bb34d5f13b97a", "MapPartitions": "f20231bad4ca8ad5", "MapPartitions.INDENT": "4072aed12b3287d8", - "MapPartitions.__init__": null, + "MapPartitions.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "MapPartitions.command": null, "MapPartitions.observations": null, "MapPartitions.plan": null, @@ -1694,7 +3190,9 @@ "MapPartitions.to_proto": "e27bb34d5f13b97a", "NADrop": null, "NADrop.INDENT": "4072aed12b3287d8", - "NADrop.__init__": null, + "NADrop.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "NADrop.command": null, "NADrop.observations": null, "NADrop.plan": null, @@ -1702,7 +3200,9 @@ "NADrop.to_proto": "e27bb34d5f13b97a", "NAFill": null, "NAFill.INDENT": "4072aed12b3287d8", - "NAFill.__init__": null, + "NAFill.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "NAFill.command": null, "NAFill.observations": null, "NAFill.plan": null, @@ -1710,7 +3210,9 @@ "NAFill.to_proto": "e27bb34d5f13b97a", "NAReplace": null, "NAReplace.INDENT": "4072aed12b3287d8", - "NAReplace.__init__": null, + "NAReplace.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "NAReplace.command": null, "NAReplace.observations": null, "NAReplace.plan": null, @@ -1718,15 +3220,21 @@ "NAReplace.to_proto": "e27bb34d5f13b97a", "NearestByJoin": null, "NearestByJoin.INDENT": "4072aed12b3287d8", - "NearestByJoin.__init__": null, + "NearestByJoin.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "NearestByJoin.command": null, "NearestByJoin.observations": null, "NearestByJoin.plan": null, - "NearestByJoin.print": null, + "NearestByJoin.print": { + "getdoc": "2bb2945c88af8787" + }, "NearestByJoin.to_proto": "e27bb34d5f13b97a", "Offset": null, "Offset.INDENT": "4072aed12b3287d8", - "Offset.__init__": null, + "Offset.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Offset.command": null, "Offset.observations": null, "Offset.plan": null, @@ -1734,7 +3242,9 @@ "Offset.to_proto": "e27bb34d5f13b97a", "Parse": "244f727490b18142", "Parse.INDENT": "4072aed12b3287d8", - "Parse.__init__": null, + "Parse.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Parse.command": null, "Parse.observations": null, "Parse.plan": null, @@ -1742,21 +3252,29 @@ "Parse.to_proto": "e27bb34d5f13b97a", "Project": "fe45417ef3195bca", "Project.INDENT": "4072aed12b3287d8", - "Project.__init__": null, + "Project.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Project.command": null, "Project.observations": null, "Project.plan": null, "Project.print": "68d9675cc7bb4386", "Project.to_proto": "e27bb34d5f13b97a", "PythonDataSource": "8d779bfb38bc936f", - "PythonDataSource.__init__": null, + "PythonDataSource.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PythonDataSource.to_plan": null, "PythonUDTF": "9f5698c011ab3cd5", - "PythonUDTF.__init__": null, + "PythonUDTF.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PythonUDTF.to_plan": null, "Range": null, "Range.INDENT": "4072aed12b3287d8", - "Range.__init__": null, + "Range.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Range.command": null, "Range.observations": null, "Range.plan": null, @@ -1764,15 +3282,21 @@ "Range.to_proto": "e27bb34d5f13b97a", "Read": null, "Read.INDENT": "4072aed12b3287d8", - "Read.__init__": null, + "Read.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Read.command": null, "Read.observations": null, "Read.plan": null, - "Read.print": null, + "Read.print": { + "getdoc": "2bb2945c88af8787" + }, "Read.to_proto": "e27bb34d5f13b97a", "RecoverPartitions": null, "RecoverPartitions.INDENT": "4072aed12b3287d8", - "RecoverPartitions.__init__": null, + "RecoverPartitions.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "RecoverPartitions.command": null, "RecoverPartitions.observations": null, "RecoverPartitions.plan": null, @@ -1780,7 +3304,9 @@ "RecoverPartitions.to_proto": "e27bb34d5f13b97a", "RefreshByPath": null, "RefreshByPath.INDENT": "4072aed12b3287d8", - "RefreshByPath.__init__": null, + "RefreshByPath.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "RefreshByPath.command": null, "RefreshByPath.observations": null, "RefreshByPath.plan": null, @@ -1788,7 +3314,9 @@ "RefreshByPath.to_proto": "e27bb34d5f13b97a", "RefreshTable": null, "RefreshTable.INDENT": "4072aed12b3287d8", - "RefreshTable.__init__": null, + "RefreshTable.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "RefreshTable.command": null, "RefreshTable.observations": null, "RefreshTable.plan": null, @@ -1796,15 +3324,21 @@ "RefreshTable.to_proto": "e27bb34d5f13b97a", "RelationChanges": null, "RelationChanges.INDENT": "4072aed12b3287d8", - "RelationChanges.__init__": null, + "RelationChanges.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "RelationChanges.command": null, "RelationChanges.observations": null, "RelationChanges.plan": null, - "RelationChanges.print": null, + "RelationChanges.print": { + "getdoc": "2bb2945c88af8787" + }, "RelationChanges.to_proto": "e27bb34d5f13b97a", "RemoveRemoteCachedRelation": null, "RemoveRemoteCachedRelation.INDENT": "4072aed12b3287d8", - "RemoveRemoteCachedRelation.__init__": null, + "RemoveRemoteCachedRelation.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "RemoveRemoteCachedRelation.command": null, "RemoveRemoteCachedRelation.observations": null, "RemoveRemoteCachedRelation.plan": null, @@ -1812,7 +3346,9 @@ "RemoveRemoteCachedRelation.to_proto": "e27bb34d5f13b97a", "Repartition": "89de8aefc3366f36", "Repartition.INDENT": "4072aed12b3287d8", - "Repartition.__init__": null, + "Repartition.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Repartition.command": null, "Repartition.observations": null, "Repartition.plan": null, @@ -1820,7 +3356,9 @@ "Repartition.to_proto": "e27bb34d5f13b97a", "RepartitionByExpression": "38dc93810a85809a", "RepartitionByExpression.INDENT": "4072aed12b3287d8", - "RepartitionByExpression.__init__": null, + "RepartitionByExpression.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "RepartitionByExpression.command": null, "RepartitionByExpression.observations": null, "RepartitionByExpression.plan": null, @@ -1828,7 +3366,9 @@ "RepartitionByExpression.to_proto": "e27bb34d5f13b97a", "SQL": null, "SQL.INDENT": "4072aed12b3287d8", - "SQL.__init__": null, + "SQL.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "SQL.command": null, "SQL.observations": null, "SQL.plan": null, @@ -1836,7 +3376,9 @@ "SQL.to_proto": "e27bb34d5f13b97a", "Sample": null, "Sample.INDENT": "4072aed12b3287d8", - "Sample.__init__": null, + "Sample.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Sample.command": null, "Sample.observations": null, "Sample.plan": null, @@ -1844,7 +3386,9 @@ "Sample.to_proto": "e27bb34d5f13b97a", "SetCurrentCatalog": null, "SetCurrentCatalog.INDENT": "4072aed12b3287d8", - "SetCurrentCatalog.__init__": null, + "SetCurrentCatalog.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "SetCurrentCatalog.command": null, "SetCurrentCatalog.observations": null, "SetCurrentCatalog.plan": null, @@ -1852,7 +3396,9 @@ "SetCurrentCatalog.to_proto": "e27bb34d5f13b97a", "SetCurrentDatabase": null, "SetCurrentDatabase.INDENT": "4072aed12b3287d8", - "SetCurrentDatabase.__init__": null, + "SetCurrentDatabase.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "SetCurrentDatabase.command": null, "SetCurrentDatabase.observations": null, "SetCurrentDatabase.plan": null, @@ -1860,15 +3406,21 @@ "SetCurrentDatabase.to_proto": "e27bb34d5f13b97a", "SetOperation": null, "SetOperation.INDENT": "4072aed12b3287d8", - "SetOperation.__init__": null, + "SetOperation.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "SetOperation.command": null, "SetOperation.observations": null, "SetOperation.plan": null, - "SetOperation.print": null, + "SetOperation.print": { + "getdoc": "2bb2945c88af8787" + }, "SetOperation.to_proto": "e27bb34d5f13b97a", "ShowString": null, "ShowString.INDENT": "4072aed12b3287d8", - "ShowString.__init__": null, + "ShowString.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ShowString.command": null, "ShowString.observations": null, "ShowString.plan": null, @@ -1876,7 +3428,9 @@ "ShowString.to_proto": "e27bb34d5f13b97a", "Sort": null, "Sort.INDENT": "4072aed12b3287d8", - "Sort.__init__": null, + "Sort.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Sort.command": null, "Sort.observations": null, "Sort.plan": null, @@ -1884,7 +3438,9 @@ "Sort.to_proto": "e27bb34d5f13b97a", "StatApproxQuantile": null, "StatApproxQuantile.INDENT": "4072aed12b3287d8", - "StatApproxQuantile.__init__": null, + "StatApproxQuantile.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "StatApproxQuantile.command": null, "StatApproxQuantile.observations": null, "StatApproxQuantile.plan": null, @@ -1892,7 +3448,9 @@ "StatApproxQuantile.to_proto": "e27bb34d5f13b97a", "StatCorr": null, "StatCorr.INDENT": "4072aed12b3287d8", - "StatCorr.__init__": null, + "StatCorr.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "StatCorr.command": null, "StatCorr.observations": null, "StatCorr.plan": null, @@ -1900,7 +3458,9 @@ "StatCorr.to_proto": "e27bb34d5f13b97a", "StatCov": null, "StatCov.INDENT": "4072aed12b3287d8", - "StatCov.__init__": null, + "StatCov.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "StatCov.command": null, "StatCov.observations": null, "StatCov.plan": null, @@ -1908,7 +3468,9 @@ "StatCov.to_proto": "e27bb34d5f13b97a", "StatCrosstab": null, "StatCrosstab.INDENT": "4072aed12b3287d8", - "StatCrosstab.__init__": null, + "StatCrosstab.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "StatCrosstab.command": null, "StatCrosstab.observations": null, "StatCrosstab.plan": null, @@ -1916,7 +3478,9 @@ "StatCrosstab.to_proto": "e27bb34d5f13b97a", "StatDescribe": null, "StatDescribe.INDENT": "4072aed12b3287d8", - "StatDescribe.__init__": null, + "StatDescribe.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "StatDescribe.command": null, "StatDescribe.observations": null, "StatDescribe.plan": null, @@ -1924,7 +3488,9 @@ "StatDescribe.to_proto": "e27bb34d5f13b97a", "StatFreqItems": null, "StatFreqItems.INDENT": "4072aed12b3287d8", - "StatFreqItems.__init__": null, + "StatFreqItems.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "StatFreqItems.command": null, "StatFreqItems.observations": null, "StatFreqItems.plan": null, @@ -1932,7 +3498,9 @@ "StatFreqItems.to_proto": "e27bb34d5f13b97a", "StatSampleBy": null, "StatSampleBy.INDENT": "4072aed12b3287d8", - "StatSampleBy.__init__": null, + "StatSampleBy.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "StatSampleBy.command": null, "StatSampleBy.observations": null, "StatSampleBy.plan": null, @@ -1940,7 +3508,9 @@ "StatSampleBy.to_proto": "e27bb34d5f13b97a", "StatSummary": null, "StatSummary.INDENT": "4072aed12b3287d8", - "StatSummary.__init__": null, + "StatSummary.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "StatSummary.command": null, "StatSummary.observations": null, "StatSummary.plan": null, @@ -1948,7 +3518,9 @@ "StatSummary.to_proto": "e27bb34d5f13b97a", "SubqueryAlias": "93d7e739ad1323de", "SubqueryAlias.INDENT": "4072aed12b3287d8", - "SubqueryAlias.__init__": null, + "SubqueryAlias.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "SubqueryAlias.command": null, "SubqueryAlias.observations": null, "SubqueryAlias.plan": null, @@ -1956,7 +3528,9 @@ "SubqueryAlias.to_proto": "e27bb34d5f13b97a", "TableExists": null, "TableExists.INDENT": "4072aed12b3287d8", - "TableExists.__init__": null, + "TableExists.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "TableExists.command": null, "TableExists.observations": null, "TableExists.plan": null, @@ -1964,7 +3538,9 @@ "TableExists.to_proto": "e27bb34d5f13b97a", "Tail": null, "Tail.INDENT": "4072aed12b3287d8", - "Tail.__init__": null, + "Tail.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Tail.command": null, "Tail.observations": null, "Tail.plan": null, @@ -1972,7 +3548,9 @@ "Tail.to_proto": "e27bb34d5f13b97a", "ToDF": null, "ToDF.INDENT": "4072aed12b3287d8", - "ToDF.__init__": null, + "ToDF.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ToDF.command": null, "ToDF.observations": null, "ToDF.plan": null, @@ -1980,7 +3558,9 @@ "ToDF.to_proto": "e27bb34d5f13b97a", "ToSchema": null, "ToSchema.INDENT": "4072aed12b3287d8", - "ToSchema.__init__": null, + "ToSchema.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "ToSchema.command": null, "ToSchema.observations": null, "ToSchema.plan": null, @@ -1988,7 +3568,9 @@ "ToSchema.to_proto": "e27bb34d5f13b97a", "TransformWithStateInPandas": "868eb41110dd56af", "TransformWithStateInPandas.INDENT": "4072aed12b3287d8", - "TransformWithStateInPandas.__init__": null, + "TransformWithStateInPandas.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "TransformWithStateInPandas.command": null, "TransformWithStateInPandas.observations": null, "TransformWithStateInPandas.plan": null, @@ -1996,7 +3578,9 @@ "TransformWithStateInPandas.to_proto": "e27bb34d5f13b97a", "TransformWithStateInPySpark": "7b6a7346bb9b3afc", "TransformWithStateInPySpark.INDENT": "4072aed12b3287d8", - "TransformWithStateInPySpark.__init__": null, + "TransformWithStateInPySpark.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "TransformWithStateInPySpark.command": null, "TransformWithStateInPySpark.observations": null, "TransformWithStateInPySpark.plan": null, @@ -2004,7 +3588,9 @@ "TransformWithStateInPySpark.to_proto": "e27bb34d5f13b97a", "Transpose": "469e377d5b7aa6f2", "Transpose.INDENT": "4072aed12b3287d8", - "Transpose.__init__": null, + "Transpose.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Transpose.command": null, "Transpose.observations": null, "Transpose.plan": null, @@ -2012,7 +3598,9 @@ "Transpose.to_proto": "e27bb34d5f13b97a", "TruncateTable": null, "TruncateTable.INDENT": "4072aed12b3287d8", - "TruncateTable.__init__": null, + "TruncateTable.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "TruncateTable.command": null, "TruncateTable.observations": null, "TruncateTable.plan": null, @@ -2020,7 +3608,9 @@ "TruncateTable.to_proto": "e27bb34d5f13b97a", "UncacheTable": null, "UncacheTable.INDENT": "4072aed12b3287d8", - "UncacheTable.__init__": null, + "UncacheTable.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "UncacheTable.command": null, "UncacheTable.observations": null, "UncacheTable.plan": null, @@ -2028,7 +3618,9 @@ "UncacheTable.to_proto": "e27bb34d5f13b97a", "Unpivot": "a786b528563b790a", "Unpivot.INDENT": "4072aed12b3287d8", - "Unpivot.__init__": null, + "Unpivot.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Unpivot.command": null, "Unpivot.observations": null, "Unpivot.plan": null, @@ -2036,7 +3628,9 @@ "Unpivot.to_proto": "e27bb34d5f13b97a", "UnresolvedTableValuedFunction": null, "UnresolvedTableValuedFunction.INDENT": "4072aed12b3287d8", - "UnresolvedTableValuedFunction.__init__": null, + "UnresolvedTableValuedFunction.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "UnresolvedTableValuedFunction.command": null, "UnresolvedTableValuedFunction.observations": null, "UnresolvedTableValuedFunction.plan": null, @@ -2044,7 +3638,9 @@ "UnresolvedTableValuedFunction.to_proto": "e27bb34d5f13b97a", "WithColumns": "2fc04dfdd1f166ff", "WithColumns.INDENT": "4072aed12b3287d8", - "WithColumns.__init__": null, + "WithColumns.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "WithColumns.command": null, "WithColumns.observations": null, "WithColumns.plan": null, @@ -2052,7 +3648,9 @@ "WithColumns.to_proto": "e27bb34d5f13b97a", "WithColumnsRenamed": null, "WithColumnsRenamed.INDENT": "4072aed12b3287d8", - "WithColumnsRenamed.__init__": null, + "WithColumnsRenamed.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "WithColumnsRenamed.command": null, "WithColumnsRenamed.observations": null, "WithColumnsRenamed.plan": null, @@ -2060,7 +3658,9 @@ "WithColumnsRenamed.to_proto": "e27bb34d5f13b97a", "WithRelations": null, "WithRelations.INDENT": "4072aed12b3287d8", - "WithRelations.__init__": null, + "WithRelations.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "WithRelations.command": null, "WithRelations.observations": null, "WithRelations.plan": null, @@ -2068,7 +3668,9 @@ "WithRelations.to_proto": "e27bb34d5f13b97a", "WithWatermark": "1c37d23e157d2c54", "WithWatermark.INDENT": "4072aed12b3287d8", - "WithWatermark.__init__": null, + "WithWatermark.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "WithWatermark.command": null, "WithWatermark.observations": null, "WithWatermark.plan": null, @@ -2076,15 +3678,21 @@ "WithWatermark.to_proto": "e27bb34d5f13b97a", "WriteOperation": null, "WriteOperation.INDENT": "4072aed12b3287d8", - "WriteOperation.__init__": null, + "WriteOperation.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "WriteOperation.command": null, "WriteOperation.observations": null, "WriteOperation.plan": null, - "WriteOperation.print": null, + "WriteOperation.print": { + "getdoc": "2bb2945c88af8787" + }, "WriteOperation.to_proto": "e27bb34d5f13b97a", "WriteOperationV2": null, "WriteOperationV2.INDENT": "4072aed12b3287d8", - "WriteOperationV2.__init__": null, + "WriteOperationV2.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "WriteOperationV2.command": null, "WriteOperationV2.observations": null, "WriteOperationV2.plan": null, @@ -2092,7 +3700,9 @@ "WriteOperationV2.to_proto": "e27bb34d5f13b97a", "WriteStreamOperation": null, "WriteStreamOperation.INDENT": "4072aed12b3287d8", - "WriteStreamOperation.__init__": null, + "WriteStreamOperation.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "WriteStreamOperation.command": null, "WriteStreamOperation.observations": null, "WriteStreamOperation.plan": null, @@ -2100,17 +3710,23 @@ "WriteStreamOperation.to_proto": "e27bb34d5f13b97a", "Zip": null, "Zip.INDENT": "4072aed12b3287d8", - "Zip.__init__": null, + "Zip.__init__": { + "getdoc": "755d6d94baf2ff93" + }, "Zip.command": null, "Zip.observations": null, "Zip.plan": null, - "Zip.print": null, + "Zip.print": { + "getdoc": "2bb2945c88af8787" + }, "Zip.to_proto": "e27bb34d5f13b97a" }, "pyspark.sql.connect.profiler": { "": null, "ConnectProfilerCollector": "2bc6744d83c82812", - "ConnectProfilerCollector.__init__": null, + "ConnectProfilerCollector.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ConnectProfilerCollector.clear_memory_profiles": "9c9dc0babb64d319", "ConnectProfilerCollector.clear_perf_profiles": "0c0145635753da7c", "ConnectProfilerCollector.dump_memory_profiles": "0aad6b887b0d69ec", @@ -2129,7 +3745,9 @@ "pyspark.sql.connect.readwriter": { "": null, "DataFrameReader": "3fcc6a33ef8a99b6", - "DataFrameReader.__init__": null, + "DataFrameReader.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataFrameReader.changes": "018645536b248ad0", "DataFrameReader.csv": "f3f4a6920a9d27ab", "DataFrameReader.format": "268088a6c22883f0", @@ -2145,7 +3763,9 @@ "DataFrameReader.text": "be1070ad241e6116", "DataFrameReader.xml": "fa923ba979fd560d", "DataFrameWriter": null, - "DataFrameWriter.__init__": null, + "DataFrameWriter.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataFrameWriter.bucketBy": "eda1d32adb3a9643", "DataFrameWriter.clusterBy": "7d1b983101afb96c", "DataFrameWriter.csv": "2957ba8775208c67", @@ -2165,7 +3785,9 @@ "DataFrameWriter.text": "fbd3a021c2c9467c", "DataFrameWriter.xml": "49f2f99a9acc1331", "DataFrameWriterV2": null, - "DataFrameWriterV2.__init__": null, + "DataFrameWriterV2.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataFrameWriterV2.append": "2022cb8f34fadb54", "DataFrameWriterV2.clusterBy": "1ac7a0a5e00b5238", "DataFrameWriterV2.create": "8cf164efea9057dd", @@ -2187,7 +3809,9 @@ "pyspark.sql.connect.resource.profile": { "": null, "ResourceProfile": "3b1e3ea33b86a616", - "ResourceProfile.__init__": null, + "ResourceProfile.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ResourceProfile.id": null }, "pyspark.sql.connect.shell": { @@ -2203,17 +3827,23 @@ "Progress.finish": "407dd1e60f346a46", "Progress.output": "402088f5efdc64e7", "Progress.update_ticks": "5eb688e99aa0bf1f", - "ProgressHandler": null, + "ProgressHandler": { + "getdoc": "6d2e78bc68039f22" + }, "ProgressHandler.__init__": "15432c8b93cc48ea", "StageInfo": "60af9adf19d0b106", - "StageInfo.__init__": null, + "StageInfo.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "from_proto": null, "get_terminal_size": null }, "pyspark.sql.connect.sql_formatter": { "": null, "SQLStringFormatter": "a486622ff1f81cc5", - "SQLStringFormatter.__init__": null, + "SQLStringFormatter.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SQLStringFormatter.check_unused_args": null, "SQLStringFormatter.clear": null, "SQLStringFormatter.convert_field": null, @@ -2230,7 +3860,9 @@ "pyspark.sql.connect.streaming.query": { "": null, "StreamingQuery": null, - "StreamingQuery.__init__": null, + "StreamingQuery.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingQuery.awaitTermination": "a11b1ec83ec6546d", "StreamingQuery.exception": "ed08fa116b08fdbb", "StreamingQuery.explain": "a79d33e434816e0a", @@ -2244,14 +3876,18 @@ "StreamingQuery.status": "850fd0240933ff8d", "StreamingQuery.stop": "30e0cc8af42a0b36", "StreamingQueryListenerBus": "30a293b6e4e8aa54", - "StreamingQueryListenerBus.__init__": null, + "StreamingQueryListenerBus.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingQueryListenerBus.append": "f81948a078b8b74e", "StreamingQueryListenerBus.close": null, "StreamingQueryListenerBus.deserialize": null, "StreamingQueryListenerBus.post_to_all": "644a7b25024c6bf1", "StreamingQueryListenerBus.remove": "7aee285d0d9cc123", "StreamingQueryManager": null, - "StreamingQueryManager.__init__": null, + "StreamingQueryManager.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingQueryManager.active": "a6849b63629a0d80", "StreamingQueryManager.addListener": "8e4c69400932d658", "StreamingQueryManager.awaitAnyTermination": "dcea09afc5822538", @@ -2263,7 +3899,9 @@ "pyspark.sql.connect.streaming.readwriter": { "": null, "DataStreamReader": "03cc2ed3ce25d8d9", - "DataStreamReader.__init__": null, + "DataStreamReader.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataStreamReader.changes": "541e90706561845c", "DataStreamReader.csv": "b37308d6a4d853ba", "DataStreamReader.format": "b6b3ce7bea080e3b", @@ -2279,7 +3917,9 @@ "DataStreamReader.text": "7b67935235097f9e", "DataStreamReader.xml": "2192865746d1cb2e", "DataStreamWriter": null, - "DataStreamWriter.__init__": null, + "DataStreamWriter.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataStreamWriter.clusterBy": "386ebb81c3394bb8", "DataStreamWriter.foreach": "c915e74a276fe0cf", "DataStreamWriter.foreachBatch": "08db99d591da039b", @@ -2304,10 +3944,31 @@ "": "956d1ee86227af4c", "main": null }, + "pyspark.sql.connect.table_arg": { + "": null, + "TableArg": { + "getdoc": "6f4aee43780d9527" + }, + "TableArg.__init__": { + "getdoc": "15432c8b93cc48ea" + }, + "TableArg.orderBy": { + "getdoc": "e913b6877d6ef502" + }, + "TableArg.partitionBy": { + "getdoc": "cc0c976722a66fd5" + }, + "TableArg.to_plan": null, + "TableArg.withSinglePartition": { + "getdoc": "4855fa4e699e0606" + } + }, "pyspark.sql.connect.tvf": { "": null, "TableValuedFunction": "10c531ad999a6d74", - "TableValuedFunction.__init__": null, + "TableValuedFunction.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "TableValuedFunction.collations": "0ae43ac350cf5062", "TableValuedFunction.explode": "fa99d79beb5f0d3d", "TableValuedFunction.explode_outer": "19c7d0ae4c10a24c", @@ -2326,14 +3987,22 @@ "pyspark.sql.connect.types": { "": null, "UnparsedDataType": "660897af01cd4e18", - "UnparsedDataType.__init__": null, + "UnparsedDataType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UnparsedDataType.fromDDL": "07c5680ac03d8aa8", - "UnparsedDataType.fromInternal": null, + "UnparsedDataType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "UnparsedDataType.json": null, "UnparsedDataType.jsonValue": null, - "UnparsedDataType.needConversion": null, + "UnparsedDataType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "UnparsedDataType.simpleString": null, - "UnparsedDataType.toInternal": null, + "UnparsedDataType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "UnparsedDataType.typeName": null, "parse_attr_name": null, "proto_schema_to_pyspark_data_type": null, @@ -2344,22 +4013,30 @@ "pyspark.sql.connect.udf": { "": "42cd96762c7d007a", "UDFRegistration": "ef817458ec83e4ca", - "UDFRegistration.__init__": null, + "UDFRegistration.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UDFRegistration.register": "73b810ad4db560ca", "UDFRegistration.registerJavaFunction": "a31204b3a38ac937", "UDFRegistration.registerJavaUDAF": "f8cc4e87478e462a", "UserDefinedFunction": "db0d8d809d51a7b9", - "UserDefinedFunction.__init__": null, + "UserDefinedFunction.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UserDefinedFunction.asNondeterministic": "1429109a48df821f", "UserDefinedFunction.returnType": null }, "pyspark.sql.connect.udtf": { "": "a7813e95841dd9b7", "UDTFRegistration": "ced915d0b7ec9b93", - "UDTFRegistration.__init__": null, + "UDTFRegistration.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UDTFRegistration.register": "7e318b93503b0e4a", "UserDefinedTableFunction": "ec6ca068aab074f8", - "UserDefinedTableFunction.__init__": null, + "UserDefinedTableFunction.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UserDefinedTableFunction.asDeterministic": null }, "pyspark.sql.connect.utils": { @@ -2371,10 +4048,56 @@ "require_minimum_grpcio_status_version": "6b7a492af404e682", "require_minimum_zstandard_version": "18d2027f4af27e5b" }, + "pyspark.sql.connect.window": { + "": null, + "Window": { + "getdoc": "74355ae9c5d1e1d6" + }, + "Window.__init__": "15432c8b93cc48ea", + "Window.currentRow": "4072aed12b3287d8", + "Window.orderBy": { + "getdoc": "8f4779a312798cbc" + }, + "Window.partitionBy": { + "getdoc": "ce0742d33a1f96a8" + }, + "Window.rangeBetween": { + "getdoc": "276c460ba06d8e4e" + }, + "Window.rowsBetween": { + "getdoc": "8bd227f85a705744" + }, + "Window.unboundedFollowing": "4072aed12b3287d8", + "Window.unboundedPreceding": "4072aed12b3287d8", + "WindowFrame": null, + "WindowFrame.__init__": { + "getdoc": "15432c8b93cc48ea" + }, + "WindowSpec": { + "getdoc": "c0a891897df5ee58" + }, + "WindowSpec.__init__": { + "getdoc": "15432c8b93cc48ea" + }, + "WindowSpec.orderBy": { + "getdoc": "98f0bee4d28161bd" + }, + "WindowSpec.partitionBy": { + "getdoc": "86bd065cc36929db" + }, + "WindowSpec.rangeBetween": { + "getdoc": "af4e964bf648743a" + }, + "WindowSpec.rowsBetween": { + "getdoc": "f3b8a883d746bfba" + } + }, "pyspark.sql.context": { "": null, "HiveContext": "d8e487688b3e2aaf", - "HiveContext.__init__": null, + "HiveContext.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "HiveContext.cacheTable": "f42558d42652940f", "HiveContext.clearCache": "5b542eb0ba0412b6", "HiveContext.createDataFrame": "f3713943663bbd31", @@ -2400,7 +4123,9 @@ "HiveContext.udtf": "684671bc4e594d99", "HiveContext.uncacheTable": "3dc0af1b211341a5", "SQLContext": "b4c85c9753a4791a", - "SQLContext.__init__": null, + "SQLContext.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SQLContext.cacheTable": "f42558d42652940f", "SQLContext.clearCache": "5b542eb0ba0412b6", "SQLContext.createDataFrame": "f3713943663bbd31", @@ -2456,10 +4181,22 @@ "PandasToArrowConversion.__init__": "15432c8b93cc48ea", "PandasToArrowConversion.convert": "a98c23c396a1230a" }, + "pyspark.sql.dataframe": { + "DataFrameNaFunctions": "9ed19c477acf2818", + "DataFrameNaFunctions.__init__": { + "getdoc": "15432c8b93cc48ea" + }, + "DataFrameStatFunctions": "9c6ac8ae0989da8a", + "DataFrameStatFunctions.__init__": { + "getdoc": "15432c8b93cc48ea" + } + }, "pyspark.sql.datasource": { "": null, "CaseInsensitiveDict": "278dc290fc9a02a8", - "CaseInsensitiveDict.__init__": null, + "CaseInsensitiveDict.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "CaseInsensitiveDict.clear": "974d35923da3e857", "CaseInsensitiveDict.copy": null, "CaseInsensitiveDict.get": "e40c74f4af00cb16", @@ -2468,7 +4205,9 @@ "CaseInsensitiveDict.pop": "5ff6f0e533c96903", "CaseInsensitiveDict.popitem": "c1a74891d60f9e6f", "CaseInsensitiveDict.setdefault": "cfd9855dfe349b9b", - "CaseInsensitiveDict.update": null, + "CaseInsensitiveDict.update": { + "getdoc": "08dd5721de82c952" + }, "CaseInsensitiveDict.values": "e825cbfa1957c928", "DataSource": "7da1ebde5ea83830", "DataSource.__init__": "1b5d733c8417c251", @@ -2490,7 +4229,9 @@ "DataSourceReader.pushFilters": "306c3a826626b4d9", "DataSourceReader.read": "9e54e1a72d8ac1fc", "DataSourceRegistration": "8d4d032448267623", - "DataSourceRegistration.__init__": null, + "DataSourceRegistration.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataSourceRegistration.register": "a8937a98c811311a", "DataSourceStreamArrowWriter": "a7e165546cc21273", "DataSourceStreamArrowWriter.__init__": "15432c8b93cc48ea", @@ -2518,29 +4259,53 @@ "DataSourceWriter.commit": "66d4f823b04a335e", "DataSourceWriter.write": "e318d7682c0139e7", "EqualNullSafe": "4d3a6eaa6ad46a42", - "EqualNullSafe.__init__": null, + "EqualNullSafe.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "EqualTo": "030df41e1f669a87", - "EqualTo.__init__": null, + "EqualTo.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "Filter": "6ddf4e65760804f9", - "Filter.__init__": null, + "Filter.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "GreaterThan": "4f89bf7b3704045a", - "GreaterThan.__init__": null, + "GreaterThan.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "GreaterThanOrEqual": "7f07e575c92f03bc", - "GreaterThanOrEqual.__init__": null, + "GreaterThanOrEqual.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "In": "2b9e8de4381d54e0", - "In.__init__": null, + "In.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "InputPartition": "36affe706cdc7f0e", - "InputPartition.__init__": null, + "InputPartition.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "IsNotNull": "efe9c9532a48cef5", - "IsNotNull.__init__": null, + "IsNotNull.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "IsNull": "d4f7e8d17e172b5c", - "IsNull.__init__": null, + "IsNull.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "LessThan": "f0f784b5989cac8d", - "LessThan.__init__": null, + "LessThan.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "LessThanOrEqual": "0c3ff834a4c7ed24", - "LessThanOrEqual.__init__": null, + "LessThanOrEqual.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "Not": "eaa07fc8d6014c37", - "Not.__init__": null, + "Not.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SimpleDataSourceStreamReader": "dddec37a6a61e77d", "SimpleDataSourceStreamReader.__init__": "15432c8b93cc48ea", "SimpleDataSourceStreamReader.commit": "faa64ba679f3cc1b", @@ -2548,23 +4313,613 @@ "SimpleDataSourceStreamReader.read": "71ff38aa93383265", "SimpleDataSourceStreamReader.readBetweenOffsets": "f8200005d1731ae2", "StringContains": "f1d9da62264289a7", - "StringContains.__init__": null, + "StringContains.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StringEndsWith": "a73c422e79a7d2dc", - "StringEndsWith.__init__": null, + "StringEndsWith.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StringStartsWith": "f118c777405ae9de", - "StringStartsWith.__init__": null, + "StringStartsWith.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "WriterCommitMessage": "fcb262489e4e9d58", "WriterCommitMessage.__init__": "15432c8b93cc48ea" }, "pyspark.sql.datasource_internal": { "": null, "PrefetchedCacheEntry": null, - "PrefetchedCacheEntry.__init__": null, + "PrefetchedCacheEntry.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ReadLimitRegistry": null, - "ReadLimitRegistry.__init__": null, + "ReadLimitRegistry.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ReadLimitRegistry.get": null, - "SimpleInputPartition": null, - "SimpleInputPartition.__init__": null + "SimpleInputPartition": { + "getdoc": "337a941efcd84b73" + }, + "SimpleInputPartition.__init__": { + "getdoc": "15432c8b93cc48ea" + } + }, + "pyspark.sql.functions": { + "": "e4ef69837d0caa9e" + }, + "pyspark.sql.functions.builtin": { + "": "42e6a9aceaeddd7f", + "abs": "d94169d2dd6fc879", + "acos": "32004d165d37b4a1", + "acosh": "3de06e46b21ed2a3", + "add_months": "cf534577a5b261ef", + "aes_decrypt": "5bc1adfdaa03a135", + "aes_encrypt": "043a835e50af3aa6", + "aggregate": "57e13fbd0367796c", + "any_value": "75c9186701b2a50f", + "approxCountDistinct": "3d6b9a3ed2204dab", + "approx_count_distinct": "dab07eca16a4e7e2", + "approx_percentile": "a5360faac4baa897", + "array": "433062d78cb3eda9", + "array_agg": "2836fa0ba49b7066", + "array_append": "7c36d1a76b99a245", + "array_compact": "054ef088f113e27c", + "array_contains": "100db46b8f0e04f9", + "array_distinct": "7a35e29cdb65a662", + "array_except": "ce40e72fe4cb7f7a", + "array_insert": "4dc32f4ebe00957e", + "array_intersect": "bd2312cc5171d3dc", + "array_join": "82573764fd4a37bc", + "array_max": "031d2b2b4f1f7c56", + "array_min": "097881c9b10a610d", + "array_position": "36ff47fa44885f9a", + "array_prepend": "7f890c7ccf99fa90", + "array_remove": "b9d47c1f5fae7717", + "array_repeat": "1dc8f5e9c96eccd7", + "array_size": "485276937cf15323", + "array_sort": "2ceb9093d4551a39", + "array_union": "cd9e5442ba03e5d3", + "arrays_overlap": "47e77d7d6f171724", + "arrays_zip": "b5e054b6d3e082c2", + "arrow_udtf": "16cbe618746447d8", + "asc": "ac476a415e2682e9", + "asc_nulls_first": "77fb8b72e8089f1f", + "asc_nulls_last": "609125df53172800", + "ascii": "e61ec50d0bea8b2a", + "asin": "74eb1d420f590b97", + "asinh": "6104f37ba0068d61", + "assert_true": "666f998eba70935c", + "atan": "8a37a0be357bca44", + "atan2": "b175bfab6e28fba5", + "atanh": "aa71c4d7039c5f3f", + "avg": "61e8590cf6d2687a", + "base64": "1a58ac15148cbcbf", + "bin": "6062f00c9dfb2143", + "bit_and": "d060566ba9549bab", + "bit_count": "5e89ee234a6b4cb2", + "bit_get": "9bca394ecd31ee25", + "bit_length": "e4fae46036b7fd7d", + "bit_or": "99912ffeabbfe003", + "bit_xor": "4d8953e6f19253cf", + "bitmap_and_agg": "d47b8be51fffc509", + "bitmap_bit_position": "46c7ce0b6b710509", + "bitmap_bucket_number": "5a174121093ff776", + "bitmap_construct_agg": "23c457c53cf9740f", + "bitmap_count": "02054cbca8f04482", + "bitmap_or_agg": "9690e80ed7565c93", + "bitwiseNOT": "e87e7c44363fe15a", + "bitwise_not": "b70e60bfda3c13a9", + "bool_and": "1c17bdb24f085c93", + "bool_or": "94d75f08fd338f99", + "broadcast": "9a7140202718320d", + "bround": "6a31bb4395e5d111", + "btrim": "1827112e6567cdba", + "bucket": "14189cc5686f7e66", + "call_function": "1e98618b1cabd541", + "call_udf": "03a59af6fc8fd020", + "cardinality": "493d28b836c5932b", + "cbrt": "9def3e4e4dc81e35", + "ceil": "4c7931ddaf1658ce", + "ceiling": "7dac5e7cd2de693f", + "char": "a0b270c4172dd4a0", + "char_length": "09f2236c73166e22", + "character_length": "59fce8182074f51e", + "chr": "3895244511d37bd1", + "coalesce": "0688a6e11e5f6dca", + "col": "e852ec474b2dd3ca", + "collate": "627045507a217d4e", + "collation": "16c0f24be06f339e", + "collect_list": "a85f9d7484d56915", + "collect_set": "8430d46915cfb23a", + "collect_union": "74368e7f1e2d5c96", + "column": "e852ec474b2dd3ca", + "concat": "057b29b4b18c130b", + "concat_ws": "9f07de6d30947b7d", + "contains": "664636c704fdd055", + "conv": "87fc93e52d0989d7", + "convert_timezone": "1682aa5bce84afa7", + "corr": "2ed70768c1fda1c3", + "cos": "631b7df34e7b8795", + "cosh": "3a8ee4b535dc9392", + "cot": "a8291889ce0dfba3", + "count": "03989ba1e4e6dbbe", + "countDistinct": "a4e31806e102437b", + "count_distinct": "1cd6bf79762b2add", + "count_if": "fd775fbae65abb36", + "count_min_sketch": "9a18c65bec4dc187", + "counter_diff": "47e2aeb0785e7cc8", + "covar_pop": "8bd5af2bc520eb71", + "covar_samp": "3b9103c58fbead70", + "crc32": "3a0fc4250512de91", + "create_map": "265edc48b7e13798", + "csc": "984c53b0db3e192e", + "cume_dist": "da7394e2fa8d2621", + "curdate": "e1022076edab285e", + "current_catalog": "81e9d1b69b4d3b96", + "current_database": "276a6a3396e2195e", + "current_date": "fadbae5dd9865289", + "current_path": "04265fe16f40af5a", + "current_schema": "3f1b2d67845df45e", + "current_time": "53709557112c2e84", + "current_timestamp": "8599b9b3db5d9db9", + "current_timezone": "2cd203c8736fe23f", + "current_user": "d649c5038593a176", + "date_add": "9f507ce9a3c9d419", + "date_diff": "dddf7e7d146303e7", + "date_format": "882a038205b1c186", + "date_from_unix_date": "1a0e14f983e948eb", + "date_part": "e9341a2be853c192", + "date_sub": "85be38a4c0a8ebeb", + "date_trunc": "b23555b913e49600", + "dateadd": "184afb11cf432a75", + "datediff": "617b10035a4b4faa", + "datepart": "68059d82e0978ab8", + "day": "8f69762d1c8a8498", + "dayname": "6c1bdc1631c7b51c", + "dayofmonth": "c01d615fe363026d", + "dayofweek": "fa0d01239042b584", + "dayofyear": "667f6fc04cb75e51", + "days": "05224fbea3f2735d", + "decode": "84c03d976824e27d", + "degrees": "4af0bfd99e6e8f61", + "dense_rank": "289f218b14b2efd6", + "desc": "36397d042f9e0b76", + "desc_nulls_first": "0d6fdfd6e440a2f1", + "desc_nulls_last": "0eea59eb9a4304a8", + "e": "308005749d2f236c", + "element_at": "eb0f01672c442d9c", + "elt": "38039aed5d14caf2", + "encode": "d546456ecedbc309", + "endswith": "7983de5e6b9272d4", + "equal_null": "156a60f7e35cae6c", + "every": "5055d039f77e02a4", + "exists": "3e16c7a8f6d1bdd2", + "exp": "875e231e1a777b42", + "explode": "ade946e06908c79a", + "explode_outer": "a2826f43cfafe537", + "expm1": "33c99e9771fbb8bd", + "expr": "c067e5d66ded13cd", + "extract": "71ddeda9ddb8dfbc", + "factorial": "a21b0c5bc072b73d", + "filter": "ef34e6c2788df310", + "find_in_set": "9893f21bf05cd1d2", + "first": "61fb0ee856f00850", + "first_value": "b038293197088b4f", + "flatten": "87d3daf6f1496f18", + "floor": "d0df0bb0f3895138", + "forall": "e0fb55480d34cf8c", + "format_number": "4cf87dbf0f6b9c87", + "format_string": "19db07ea55cbb99c", + "from_base32": "37899356d15ba2e3", + "from_csv": "f6832849626d9ccb", + "from_json": "fcbce7c6ed5035a5", + "from_unixtime": "74939340a798bd0a", + "from_utc_timestamp": "287af1ead35b82b4", + "from_xml": "737364f25bc1bc0e", + "get": "b1f7f3e40960663c", + "get_json_object": "8bdaf44aaddf8604", + "getbit": "f1f1d57ebd4d76d9", + "greatest": "12a7f332a577b11e", + "grouping": "cf7ce129ec71d94f", + "grouping_id": "55c81a20223d078c", + "hash": "a4fbd5e917ce3fe4", + "hex": "4d661545d7be93ee", + "histogram_numeric": "b1667fba06d58ea7", + "hll_sketch_agg": "70b7937881aa7f94", + "hll_sketch_estimate": "33575a52dcfaa92d", + "hll_union": "910a3bf0ff877fd7", + "hll_union_agg": "65ee252e9e105089", + "hmac": "1d477007f621ba0d", + "hour": "b089dc804034f37e", + "hours": "627f7cd339d5cef6", + "hypot": "9da63e28204ef87d", + "ifnull": "e6bcd9bb46e05b9c", + "ilike": "4f4e3930db948bb2", + "initcap": "f34adec0d5ea10bf", + "inline": "6d5d2034c1d421e5", + "inline_outer": "91d028fd086ccaf1", + "input_file_block_length": "2d6f5dd460dd4582", + "input_file_block_start": "f9d56b335d646647", + "input_file_name": "630dac746449fd9d", + "instr": "640d8850fd99af8c", + "is_valid_utf8": "127f90b223ba2e0b", + "is_valid_variant": "005fc013df1d5ff4", + "is_variant_null": "312a8bd012e61adc", + "isnan": "eb893e24a348ee96", + "isnotnull": "7ed1dde5479d422a", + "isnull": "82ee67fbb2c90ee5", + "jaro_winkler_similarity": "38da1cc3189c42d4", + "java_method": "0b408a6ab4f04747", + "json_array_length": "bf64522844ac19d6", + "json_object_keys": "0e7c6521e8a14d9f", + "json_tuple": "85b1ea7047dd605c", + "kll_merge_agg_bigint": "5c6271e2cbaacd63", + "kll_merge_agg_double": "49f918f7e8a1a256", + "kll_merge_agg_float": "459622dcdffdd46f", + "kll_sketch_agg_bigint": "829abf4cb11886cc", + "kll_sketch_agg_double": "3b520c39f9c252b3", + "kll_sketch_agg_float": "278f25eb54e144e6", + "kll_sketch_get_n_bigint": "d0d52d7cb33caa55", + "kll_sketch_get_n_double": "8cd6f784bafe347e", + "kll_sketch_get_n_float": "69dba7b50620f972", + "kll_sketch_get_quantile_bigint": "03227993dbe5712c", + "kll_sketch_get_quantile_double": "5448c4f8031029af", + "kll_sketch_get_quantile_float": "066b897feccccd50", + "kll_sketch_get_rank_bigint": "a69677e836587821", + "kll_sketch_get_rank_double": "b4dd02276d00391e", + "kll_sketch_get_rank_float": "a16bbb1174e1589d", + "kll_sketch_merge_bigint": "ec7adfcbdbb44d03", + "kll_sketch_merge_double": "087396b12f6b19b8", + "kll_sketch_merge_float": "72601b74937ba504", + "kll_sketch_to_string_bigint": "fc09aec11dc74f90", + "kll_sketch_to_string_double": "e1c06eea0e7c344f", + "kll_sketch_to_string_float": "7c32920e28490c23", + "kurtosis": "15c8e6a328a47326", + "lag": "2d976cdfcfd98ce1", + "last": "1d9ee3d434e174e9", + "last_day": "fea2b4fb73e1e3ff", + "last_value": "81c14feee3c7db6d", + "lcase": "d4bfff940a00a12d", + "lead": "a40dc991a0b57ee2", + "least": "6515e7579c31d375", + "left": "c34a19a9dab381b7", + "length": "ae65f027a5fbea3b", + "levenshtein": "49b2de8360f91f71", + "like": "0f9e9c0bb6b45721", + "listagg": "6d97096121531ebc", + "listagg_distinct": "5c140551a35d22c0", + "lit": "24e8198c7bfa35a7", + "ln": "4efb6a00e3021309", + "localtimestamp": "3d546583b48882b9", + "locate": "115ba75cdc97818b", + "log": "f9675d05a1f2874e", + "log10": "799360f0d4e0b1f6", + "log1p": "c27dc0e668f2c4c7", + "log2": "702c01a658b8c407", + "lower": "28e67f95d8382e00", + "lpad": "4665c198dc4c16fb", + "ltrim": "233e43ad319276fc", + "make_date": "c97a7c1a00acc35b", + "make_dt_interval": "90c3130b3d59b5a6", + "make_interval": "a6f367b1d24159de", + "make_time": "8e8b15723224f22c", + "make_timestamp": "a5420f0eb90899cd", + "make_timestamp_ltz": "cb6a4e03dd5e755f", + "make_timestamp_ntz": "c9d75c794fd25f93", + "make_valid_utf8": "fd2b068d45200927", + "make_ym_interval": "d4a213be9d15a9aa", + "map_concat": "bea522c675af4eb8", + "map_contains_key": "5540d160c37b27b9", + "map_entries": "55ff32528457180a", + "map_filter": "4be994f16e0d0ac6", + "map_from_arrays": "759b860b18f6f65d", + "map_from_entries": "09ea5f43468b1025", + "map_keys": "c0ec18cfbe8a6e59", + "map_values": "34bd51577d64fa2c", + "map_zip_with": "03dad7ec923f23a8", + "mask": "5c8a2a57fcf839a7", + "max": "1cc6f503b7b99dc9", + "max_by": "1a2fd0c3ef5bfa4f", + "md5": "1cb0bb35ddf64f21", + "mean": "6b9af09d59a9ba17", + "median": "20341cafe254066d", + "min": "93ca096a990d1fad", + "min_by": "313575513ded0448", + "minute": "69653633e2a606b1", + "mode": "f42be8142247c377", + "monotonically_increasing_id": "2ad2b4932aa2affd", + "month": "84fe8a15581bc348", + "monthname": "88097599a00ec5bc", + "months": "da37f206bd7c684b", + "months_between": "832b275e60e62753", + "named_struct": "be7e71f75c9690b6", + "nanvl": "3c11f57381be3386", + "negate": "e897ad4365aa8655", + "negative": "e897ad4365aa8655", + "next_day": "f1e71b4ac75a961e", + "now": "8d16195a89fa7303", + "nth_value": "9c29d6e117db1a70", + "ntile": "cb8f1fda23951750", + "nullif": "72a943de98bc6db3", + "nullifzero": "4799ccecc7733159", + "nvl": "110e101e28d30dce", + "nvl2": "67540b35e6e1ca6b", + "octet_length": "32283b1801a40b3a", + "overlay": "020ca7aaea7edf41", + "parse_json": "ee65def0bc67c9e8", + "parse_url": "dbcc3ffa1d7d5ca2", + "percent_rank": "badbaab1c2c3d630", + "percentile": "2d1f9eded8ffe583", + "percentile_approx": "ce1992621975d2f9", + "pi": "3e5ca062c4eb0c54", + "pmod": "6141363dd01342e0", + "posexplode": "3aed0f0d2d223697", + "posexplode_outer": "273dcf608aca9490", + "position": "d61386e748b26e92", + "positive": "0950d8153d25eee2", + "pow": "0d97805b6b4e3171", + "power": "0d97805b6b4e3171", + "printf": "1eba5b813371a4a2", + "product": "ccadfb38657287d2", + "quarter": "d208044babedda3a", + "quote": "7ad7d99f5997c024", + "radians": "abbed92f5d294723", + "raise_error": "ccca5da1fe8a688a", + "rand": "d79ae250586b5e6d", + "randn": "cff5ac7c294cc12e", + "random": "d79ae250586b5e6d", + "randstr": "b34d85401a693666", + "rank": "fa739f1aab54d30a", + "reduce": "373866c54948b1ad", + "reflect": "db0a4acb8af6d832", + "regexp": "0dffc68f2c7f04a4", + "regexp_count": "948e681154db3e3b", + "regexp_extract": "39d190471655777c", + "regexp_extract_all": "ee7223b2e37733bc", + "regexp_instr": "d28f19ee037c3283", + "regexp_like": "29831bb3b33e46ed", + "regexp_replace": "9c67324e066ce91b", + "regexp_substr": "c149a9b36a9dcec7", + "regr_avgx": "78c89102b5f91b50", + "regr_avgy": "02641c410cc99667", + "regr_count": "979ffb1f52060872", + "regr_intercept": "371e9373bbdcf53b", + "regr_r2": "a8507b986ba076b4", + "regr_slope": "62ecec8e88b7602e", + "regr_sxx": "6b07aa20249c3442", + "regr_sxy": "77422c6c1a35aa38", + "regr_syy": "32aff79154fe6173", + "repeat": "ad4809e744f57c76", + "replace": "c62e7afb3d466a88", + "reverse": "95594ea99c6dd10a", + "right": "45aca6f0830bbe4a", + "rint": "3b8a5d8af9bd8a4f", + "rlike": "af37840f6753f84a", + "round": "6348002189074593", + "row_number": "49380e26032b76b3", + "rpad": "4ce79ecc9b3bb7e7", + "rtrim": "332c0c2ac6d4581a", + "schema_of_csv": "5973cec518ceb317", + "schema_of_json": "95a4106a9bfe50c8", + "schema_of_variant": "c63aa6e732cb6727", + "schema_of_variant_agg": "5915aa42ba4717ff", + "schema_of_xml": "acf2d26857c900d8", + "sec": "8de5a7c5ad8daeab", + "second": "c794a175252cc3ae", + "sentences": "e951e704278d59d5", + "sequence": "a29375880e4cea51", + "session_user": "da762248e37d45f2", + "session_window": "497a5f8bd08f420a", + "sha": "ef799e1f0300cbc2", + "sha1": "ffbe3938d6cba771", + "sha2": "bbf51b061ee5b656", + "shiftLeft": "4a777d8e57e9cae7", + "shiftRight": "e7c2631fd55b1481", + "shiftRightUnsigned": "3b363aab1c5e55f0", + "shiftleft": "1d551f422c5eee5a", + "shiftright": "56c98814fbbf2cc1", + "shiftrightunsigned": "156753c22d0a6d84", + "shuffle": "ee927f7c57b92d7b", + "sign": "36cee609caf4052b", + "signum": "791493c89ba6c02d", + "sin": "3af94e9d7cddd076", + "sinh": "e61ccc0150e0d374", + "size": "c2d96b389d67c467", + "skewness": "d9802d472b1756a9", + "slice": "4b8fc4310edc2f52", + "some": "0c02733eb262e677", + "sort_array": "fadf5b527a8b62d6", + "soundex": "14ea077dfc7a0661", + "spark_partition_id": "f9ef158a30b48ed4", + "split": "6068b7b90ac414e8", + "split_part": "f5654f2b3ae527ef", + "sqrt": "14056fe18c284cde", + "st_asbinary": "616e9f552b2aa48c", + "st_geogfromwkb": "75fe2ed08071660d", + "st_geomfromwkb": "2fbc6c459d55decf", + "st_setsrid": "662a2486186eb8b4", + "st_srid": "8f25756dafa35fb7", + "stack": "74fdde41cacdac16", + "startswith": "a380956c4adeaefe", + "std": "2e5c921925d2b1f9", + "stddev": "2ceac986585b86ca", + "stddev_pop": "78ff13b3b92f8c94", + "stddev_samp": "3cffb6b953f9510c", + "str_to_map": "7c91c71ee70f2e78", + "string_agg": "77b4152fad69f041", + "string_agg_distinct": "a8b0c97555197f28", + "struct": "6dd3dcc1e61720b9", + "substr": "298b69b80be42ac7", + "substring": "381984a3689a8a07", + "substring_index": "3624f81481d1ec8d", + "sum": "02c1a3094057652a", + "sumDistinct": "c0b83f51e0f4c136", + "sum_distinct": "aa86f390dfc5ed2a", + "tan": "8dd44c4d4c5c99d1", + "tanh": "c77d45140318544c", + "theta_difference": "a74e0b31b4bfecb6", + "theta_intersection": "ce917848780c5d5c", + "theta_intersection_agg": "3ef41b981c21ef83", + "theta_sketch_agg": "192199ce74ee3402", + "theta_sketch_estimate": "817f99db6600e368", + "theta_union": "f6feb9adbe4c3cd4", + "theta_union_agg": "143e910295999890", + "time_bucket": "f1c47d91c4acc7be", + "time_diff": "ef570ad507ba20d6", + "time_from_micros": "586ac4f84b8584e9", + "time_from_millis": "9b1ee615f32e8606", + "time_from_seconds": "61bb395e41232777", + "time_to_micros": "3e96f32e8e94c2cc", + "time_to_millis": "be945a2eaedf4f8d", + "time_to_seconds": "a78cabbd1235d859", + "time_trunc": "0ef118220d3b2663", + "timestamp_add": "fbd55dcabc8e77e7", + "timestamp_diff": "07d402cfdd7427ba", + "timestamp_micros": "062953c15a462da7", + "timestamp_millis": "949011ac47996715", + "timestamp_nanos": "26497d9d5be6772e", + "timestamp_seconds": "b6fa35adde863fbf", + "toDegrees": "98f6de96b00640b7", + "toRadians": "d67b46ec2a4927b1", + "to_base32": "e21497df25d0be3f", + "to_binary": "60ebd4c1e845f2b4", + "to_char": "21f9d2ec2c35aa8e", + "to_csv": "2b22df5e55212ee3", + "to_date": "4db4bde885ec5ba9", + "to_json": "0690831e11177ba9", + "to_number": "ea810169e01be4bb", + "to_time": "726bd65a7ecbdc48", + "to_timestamp": "66998f4e7050c51f", + "to_timestamp_ltz": "4c176de5f0df0f83", + "to_timestamp_ntz": "d0f9b6f7caa7f3f7", + "to_unix_timestamp": "2fccfd9a66667396", + "to_utc_timestamp": "34bf8f636c6f4e29", + "to_varchar": "05cc858a6ce3f814", + "to_variant_object": "10938e516e34aa11", + "to_xml": "044ac22d0312ecfd", + "transform": "a56fd4fa5e4b37a7", + "transform_keys": "4bf5dd13fa41bb3d", + "transform_values": "860e5de5d42ed64e", + "translate": "fb94d9f5d1f280b0", + "trim": "6f5d5b410065ee92", + "trunc": "faba8f67477b5210", + "try_add": "2227ef78882ad20d", + "try_aes_decrypt": "b4f5350ea1b3ca4a", + "try_avg": "cdf5da478c3c1b39", + "try_divide": "e38cc9bc9adb016f", + "try_element_at": "1483d9ee5f7df026", + "try_make_interval": "2d5a9ec4c0135126", + "try_make_timestamp": "035859ff7468b5b3", + "try_make_timestamp_ltz": "bd94e87613383539", + "try_make_timestamp_ntz": "874b8c33721527f1", + "try_mod": "cf05020bab9a1c5b", + "try_multiply": "d654528ce929e409", + "try_parse_json": "6cee97b7d3068e9d", + "try_parse_url": "f6b7cbf26bccf05d", + "try_reflect": "95dafd7be31a4d78", + "try_subtract": "96a09e77df99e296", + "try_sum": "69c2e29f926b7a9f", + "try_to_binary": "3c3213c0cb3caccb", + "try_to_date": "b1f53484e3f321d0", + "try_to_number": "28e84d8546aa0d1f", + "try_to_time": "9785223e6b35eebd", + "try_to_timestamp": "86f90c156409abbb", + "try_url_decode": "ba56cb6c52ecf535", + "try_validate_utf8": "2de9c35e2e361be7", + "try_variant_array_append": "eb0102f7cdd9d239", + "try_variant_get": "2abc88055c634ead", + "try_variant_insert": "2dd0b393011e045d", + "try_variant_set": "c0a6dd29cbbf4191", + "tuple_difference_double": "a8f3d13f57d7a5ae", + "tuple_difference_integer": "9e54a8d9c045a901", + "tuple_difference_theta_double": "dc868b56b98063ab", + "tuple_difference_theta_integer": "268d1e354f53bfe9", + "tuple_intersection_agg_double": "6fd196f1198530e9", + "tuple_intersection_agg_integer": "2f18e529aac48cce", + "tuple_intersection_double": "9c1050bc9ff4fe99", + "tuple_intersection_integer": "9bd3676ec4ce2536", + "tuple_intersection_theta_double": "38f6a864b8657e5b", + "tuple_intersection_theta_integer": "9b33636a9d969d46", + "tuple_sketch_agg_double": "93ba360c5003abe8", + "tuple_sketch_agg_integer": "8bb0ef1a6e75ad71", + "tuple_sketch_estimate_double": "07319585172773e3", + "tuple_sketch_estimate_integer": "842b96efff301320", + "tuple_sketch_summary_double": "07bc2c80d181fc23", + "tuple_sketch_summary_integer": "09be91a7b0a0e956", + "tuple_sketch_theta_double": "88a6e27e9d5d6534", + "tuple_sketch_theta_integer": "0d960cf99f1e6d55", + "tuple_union_agg_double": "f39245da5ee4aa25", + "tuple_union_agg_integer": "a4a7dc2581abe3df", + "tuple_union_double": "2809762a399460b5", + "tuple_union_integer": "187647f533077701", + "tuple_union_theta_double": "9aca4e11e47fcbd7", + "tuple_union_theta_integer": "8b613251081c248e", + "typeof": "ce3bf7abab867017", + "ucase": "83b806742cada732", + "udf": "b99fed075406b4be", + "udtf": "4121a64f2bb59859", + "unbase64": "22c1530d7093bba3", + "unhex": "ff3a7ff1400801a6", + "uniform": "1b39777cd40d575b", + "unix_date": "20813b5eeebe6f5d", + "unix_micros": "b6c43803febc5be7", + "unix_millis": "b5100c98007a98b5", + "unix_nanos": "b55bdf8341dd3444", + "unix_seconds": "cc091f6f0d55cc62", + "unix_timestamp": "650eb1b4ede9e6d2", + "unwrap_udt": "6f7cdbfbd406d105", + "upper": "ccb592aef856b628", + "url_decode": "89d45cf75285d63d", + "url_encode": "6ce670a651bde97e", + "user": "c6cf8927af611a8e", + "uuid": "f92de7039f8fa879", + "validate_utf8": "c10cc7b18a0f601d", + "var_pop": "fc0be13e0065976f", + "var_samp": "d3feb5667846199d", + "variance": "8fb7e1fb4139e221", + "variant_array_append": "493a95aac3a59d52", + "variant_delete": "7f6380a9947071ea", + "variant_get": "23c4e2d1175ea1b5", + "variant_insert": "4783201bd765f96e", + "variant_set": "50ee06fc4aae2994", + "variant_strip_nulls": "8d3cb659d76606db", + "vector_avg": "d6259ba6aba4e736", + "vector_cosine_similarity": "5e6c91c5b4c9b637", + "vector_inner_product": "a29acbdb76acbeb7", + "vector_l2_distance": "656f01fcf6f06caa", + "vector_norm": "d3e426ae948cfbfa", + "vector_normalize": "5cbe1eca31d2a0ee", + "vector_sum": "d513faea14c5f5cb", + "version": "cd51fb5ab88739e6", + "weekday": "d201eea2f777ca13", + "weekofyear": "e518e42706b87a44", + "when": "1f20e0856d4a38b6", + "width_bucket": "7d4a160c4832366a", + "window": "9f1b34a7cdfd0c80", + "window_time": "efd7b305a3610723", + "xpath": "727f186711c48f1b", + "xpath_boolean": "20b198e976e043ff", + "xpath_double": "13b30f927857a89c", + "xpath_float": "52acd0cc9a5b36f0", + "xpath_int": "3e68e56675bcd1f1", + "xpath_long": "b9507c207f95c91f", + "xpath_number": "4d0e802bfa933e2b", + "xpath_short": "362bae302dadb530", + "xpath_string": "f2aeafa6d980002e", + "xxhash64": "ec809d05fb6386ad", + "year": "a7e590da777b7c9c", + "years": "ca6e1e3d49717724", + "zeroifnull": "eaad5a9432d81b92", + "zip_with": "4d60303577da9444" + }, + "pyspark.sql.functions.partitioning": { + "": "bd20af04bf720a2c", + "bucket": "56707b7d014918a9", + "days": "f967843fd17e3b67", + "hours": "399452773ecfb80a", + "months": "232f02b1378570e9", + "years": "539ba45c0d07504e" }, "pyspark.sql.geo_utils": { "": null, @@ -2577,17 +4932,23 @@ "GeographicSpatialReferenceSystemMapper.get_srid": null, "GeographicSpatialReferenceSystemMapper.get_string_id": null, "SpatialReferenceSystemCache": null, - "SpatialReferenceSystemCache.__init__": null, + "SpatialReferenceSystemCache.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SpatialReferenceSystemCache.get_srs_by_srid": null, "SpatialReferenceSystemCache.get_srs_by_string_id": null, "SpatialReferenceSystemCache.instance": null, "SpatialReferenceSystemInformation": "153cacb4dc4dc9fe", - "SpatialReferenceSystemInformation.__init__": null + "SpatialReferenceSystemInformation.__init__": { + "getdoc": "15432c8b93cc48ea" + } }, "pyspark.sql.group": { "": null, "GroupedData": "4a6a06a1319caa28", - "GroupedData.__init__": null, + "GroupedData.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "GroupedData.agg": "590f40c6fa987591", "GroupedData.apply": "e2f3cebe1ae08945", "GroupedData.applyInArrow": "8fb441e057226613", @@ -2609,7 +4970,9 @@ "pyspark.sql.interchange": { "": null, "SparkArrowCStreamer": "2ff190f41cc2b48c", - "SparkArrowCStreamer.__init__": null + "SparkArrowCStreamer.__init__": { + "getdoc": "15432c8b93cc48ea" + } }, "pyspark.sql.internal": { "": null, @@ -2639,7 +5002,9 @@ "MergeIntoWriter.WhenMatched": "ea003cc72784340c", "MergeIntoWriter.WhenNotMatched": "2cd0d5ee07c3ab4d", "MergeIntoWriter.WhenNotMatchedBySource": "97618580d879b28f", - "MergeIntoWriter.__init__": null, + "MergeIntoWriter.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "MergeIntoWriter.merge": "e23d36247d335212", "MergeIntoWriter.whenMatched": "e763837f75f1c868", "MergeIntoWriter.whenNotMatched": "350347531c324a8d", @@ -2650,29 +5015,39 @@ "": null, "CollectedMetrics": null, "CollectedMetrics.Node": "870585ad466a8e72", - "CollectedMetrics.__init__": null, + "CollectedMetrics.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "CollectedMetrics.extract_graph": "83ece9306f9523ef", "CollectedMetrics.text": "c31c662f5a9b472b", "CollectedMetrics.toDot": "77fd429751acf81c", "CollectedMetrics.toText": "1251075fb7b3b338", "ExecutionInfo": "1f685ed8d78cf3d7", - "ExecutionInfo.__init__": null, + "ExecutionInfo.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ExecutionInfo.flows": null, "ExecutionInfo.metrics": null, "ExecutionInfo.operation_id": "4a7c4a83357b04f4", "MetricValue": "a2715e08eb75fb06", - "MetricValue.__init__": null, + "MetricValue.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "MetricValue.metric_type": null, "MetricValue.name": null, "MetricValue.to_dict": "674c910ca8ed7300", "MetricValue.value": null, - "ObservedMetrics": null, + "ObservedMetrics": { + "getdoc": "6d2e78bc68039f22" + }, "ObservedMetrics.__init__": "15432c8b93cc48ea", "ObservedMetrics.keys": null, "ObservedMetrics.name": null, "ObservedMetrics.pairs": null, "PlanMetrics": "aff2cc0cd8456ff4", - "PlanMetrics.__init__": null, + "PlanMetrics.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PlanMetrics.metrics": null, "PlanMetrics.name": null, "PlanMetrics.parent_plan_id": null, @@ -2721,7 +5096,9 @@ "pyspark.sql.pandas.group_ops": { "": null, "PandasCogroupedOps": "50671c128a962e8d", - "PandasCogroupedOps.__init__": null, + "PandasCogroupedOps.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PandasCogroupedOps.applyInArrow": "75ab8fc23bc05d41", "PandasCogroupedOps.applyInPandas": "bda600b794baaa87", "PandasGroupedOpsMixin": "a4b76af5d37c6853", @@ -2744,22 +5121,30 @@ "pyspark.sql.pandas.serializers": { "": "295b9bce7c2354d9", "ArrowCollectSerializer": "932f5de367932508", - "ArrowCollectSerializer.__init__": null, + "ArrowCollectSerializer.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ArrowCollectSerializer.dump_stream": "4251cfc5775c880e", "ArrowCollectSerializer.dumps": "3635f367dd1f8178", "ArrowCollectSerializer.load_stream": "9a0b9e70d2abc43c", "ArrowStreamCoGroupSerializer": "dcea2ebbfc0c9943", - "ArrowStreamCoGroupSerializer.__init__": null, + "ArrowStreamCoGroupSerializer.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ArrowStreamCoGroupSerializer.dump_stream": "4251cfc5775c880e", "ArrowStreamCoGroupSerializer.dumps": "3635f367dd1f8178", "ArrowStreamCoGroupSerializer.load_stream": "5cf742914f91aecc", "ArrowStreamGroupSerializer": "28c9b1270a4644b2", - "ArrowStreamGroupSerializer.__init__": null, + "ArrowStreamGroupSerializer.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ArrowStreamGroupSerializer.dump_stream": "4251cfc5775c880e", "ArrowStreamGroupSerializer.dumps": "3635f367dd1f8178", "ArrowStreamGroupSerializer.load_stream": "eef964d6e903f7a9", "ArrowStreamSerializer": "987166b432fbbc94", - "ArrowStreamSerializer.__init__": null, + "ArrowStreamSerializer.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ArrowStreamSerializer.dump_stream": "4251cfc5775c880e", "ArrowStreamSerializer.dumps": "3635f367dd1f8178", "ArrowStreamSerializer.load_stream": "0c264184839428ce", @@ -2822,7 +5207,9 @@ "PySparkKdePlotBase.compute_kde_col": null, "PySparkKdePlotBase.get_ind": null, "PySparkPlotAccessor": "46b4f5c86ee26126", - "PySparkPlotAccessor.__init__": null, + "PySparkPlotAccessor.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "PySparkPlotAccessor.area": "e85a5d0856d65fd6", "PySparkPlotAccessor.bar": "bda9c54d4246822f", "PySparkPlotAccessor.barh": "4618346baf2ce78e", @@ -2851,8 +5238,12 @@ }, "pyspark.sql.profiler": { "": null, - "AccumulatorProfilerCollector": null, - "AccumulatorProfilerCollector.__init__": null, + "AccumulatorProfilerCollector": { + "getdoc": "cc059df91d7620bd" + }, + "AccumulatorProfilerCollector.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "AccumulatorProfilerCollector.clear_memory_profiles": "9c9dc0babb64d319", "AccumulatorProfilerCollector.clear_perf_profiles": "0c0145635753da7c", "AccumulatorProfilerCollector.dump_memory_profiles": "0aad6b887b0d69ec", @@ -2860,13 +5251,17 @@ "AccumulatorProfilerCollector.show_memory_profiles": "f44dddaa79123073", "AccumulatorProfilerCollector.show_perf_profiles": "fdbba9b702395c41", "Profile": "0f429b5911d17cf1", - "Profile.__init__": null, + "Profile.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "Profile.clear": "ea935b87d308b573", "Profile.dump": "0c0dcd56b9936c98", "Profile.render": "d7b7284f0475c6ea", "Profile.show": "e106c9d1f75f864e", "ProfilerCollector": "dd24a53fb4a01b6e", - "ProfilerCollector.__init__": null, + "ProfilerCollector.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ProfilerCollector.clear_memory_profiles": "9c9dc0babb64d319", "ProfilerCollector.clear_perf_profiles": "0c0145635753da7c", "ProfilerCollector.dump_memory_profiles": "0aad6b887b0d69ec", @@ -2874,12 +5269,16 @@ "ProfilerCollector.show_memory_profiles": "f44dddaa79123073", "ProfilerCollector.show_perf_profiles": "fdbba9b702395c41", "WorkerMemoryProfiler": "102e5f60dff40ccc", - "WorkerMemoryProfiler.__init__": null, + "WorkerMemoryProfiler.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "WorkerMemoryProfiler.save": null, "WorkerMemoryProfiler.start": null, "WorkerMemoryProfiler.stop": null, "WorkerPerfProfiler": "d65091d62d37aab7", - "WorkerPerfProfiler.__init__": null, + "WorkerPerfProfiler.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "WorkerPerfProfiler.save": null, "WorkerPerfProfiler.start": null, "WorkerPerfProfiler.stop": null @@ -2895,7 +5294,9 @@ "pyspark.sql.readwriter": { "": null, "DataFrameReader": "3fcc6a33ef8a99b6", - "DataFrameReader.__init__": null, + "DataFrameReader.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataFrameReader.changes": "018645536b248ad0", "DataFrameReader.csv": "f3f4a6920a9d27ab", "DataFrameReader.format": "268088a6c22883f0", @@ -2911,7 +5312,9 @@ "DataFrameReader.text": "be1070ad241e6116", "DataFrameReader.xml": "fa923ba979fd560d", "DataFrameWriter": "e45defc353269480", - "DataFrameWriter.__init__": null, + "DataFrameWriter.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataFrameWriter.bucketBy": "eda1d32adb3a9643", "DataFrameWriter.clusterBy": "7d1b983101afb96c", "DataFrameWriter.csv": "2957ba8775208c67", @@ -2931,7 +5334,9 @@ "DataFrameWriter.text": "fbd3a021c2c9467c", "DataFrameWriter.xml": "49f2f99a9acc1331", "DataFrameWriterV2": "3f02f0485415d847", - "DataFrameWriterV2.__init__": null, + "DataFrameWriterV2.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataFrameWriterV2.append": "2022cb8f34fadb54", "DataFrameWriterV2.clusterBy": "1ac7a0a5e00b5238", "DataFrameWriterV2.create": "8cf164efea9057dd", @@ -2951,7 +5356,9 @@ "": null, "SparkSession": "50abd019d6660100", "SparkSession.Builder": "46c0b45bc4793f74", - "SparkSession.__init__": null, + "SparkSession.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SparkSession.active": "6545d6963980acf6", "SparkSession.addArtifact": "5a81d93b27d78a7f", "SparkSession.addArtifacts": "5a81d93b27d78a7f", @@ -2987,12 +5394,16 @@ "SparkSession.udtf": "bf00ab74cabee1d6", "SparkSession.version": "85a9269b929e203d", "classproperty": "bdc115833cf1beb1", - "classproperty.__init__": null + "classproperty.__init__": { + "getdoc": "15432c8b93cc48ea" + } }, "pyspark.sql.sql_formatter": { "": null, "SQLStringFormatter": "a486622ff1f81cc5", - "SQLStringFormatter.__init__": null, + "SQLStringFormatter.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SQLStringFormatter.check_unused_args": null, "SQLStringFormatter.clear": null, "SQLStringFormatter.convert_field": null, @@ -3009,17 +5420,27 @@ "pyspark.sql.streaming.datasource": { "": null, "ReadAllAvailable": "1a4b88938f13d253", - "ReadAllAvailable.__init__": null, + "ReadAllAvailable.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ReadLimit": "bb698daa6429fd81", "ReadLimit.__init__": "15432c8b93cc48ea", "ReadMaxBytes": "c1a4d0cfa8d5153e", - "ReadMaxBytes.__init__": null, + "ReadMaxBytes.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ReadMaxFiles": "97c9a03fe986bf5b", - "ReadMaxFiles.__init__": null, + "ReadMaxFiles.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ReadMaxRows": "0d199ea015c862ec", - "ReadMaxRows.__init__": null, + "ReadMaxRows.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ReadMinRows": "ab7a4f856d7f3205", - "ReadMinRows.__init__": null, + "ReadMinRows.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SupportsTriggerAvailableNow": "b20096e102ee3ace", "SupportsTriggerAvailableNow.__init__": "15432c8b93cc48ea", "SupportsTriggerAvailableNow.prepareForTriggerAvailableNow": "d5f2d20f80c9721d" @@ -3027,7 +5448,9 @@ "pyspark.sql.streaming.list_state_client": { "": null, "ListStateClient": null, - "ListStateClient.__init__": null, + "ListStateClient.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ListStateClient.append_list": null, "ListStateClient.append_value": null, "ListStateClient.clear": null, @@ -3035,31 +5458,41 @@ "ListStateClient.get": null, "ListStateClient.put": null, "ListStateIterator": null, - "ListStateIterator.__init__": null + "ListStateIterator.__init__": { + "getdoc": "15432c8b93cc48ea" + } }, "pyspark.sql.streaming.listener": { "": null, "JStreamingQueryListener": "5417a83d7d89668a", "JStreamingQueryListener.Java": null, - "JStreamingQueryListener.__init__": null, + "JStreamingQueryListener.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "JStreamingQueryListener.onQueryIdle": null, "JStreamingQueryListener.onQueryProgress": null, "JStreamingQueryListener.onQueryStarted": null, "JStreamingQueryListener.onQueryTerminated": null, "QueryIdleEvent": "1672e57502526e38", - "QueryIdleEvent.__init__": null, + "QueryIdleEvent.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "QueryIdleEvent.fromJObject": null, "QueryIdleEvent.fromJson": null, "QueryIdleEvent.id": "e8d328e575a1b363", "QueryIdleEvent.runId": "3b5315e3cc1d95a2", "QueryIdleEvent.timestamp": "2e7e91510c441d8a", "QueryProgressEvent": "8825cbe6f30e212f", - "QueryProgressEvent.__init__": null, + "QueryProgressEvent.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "QueryProgressEvent.fromJObject": null, "QueryProgressEvent.fromJson": null, "QueryProgressEvent.progress": "da543cae2ab5fc63", "QueryStartedEvent": "41bc17923ab6b677", - "QueryStartedEvent.__init__": null, + "QueryStartedEvent.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "QueryStartedEvent.fromJObject": null, "QueryStartedEvent.fromJson": null, "QueryStartedEvent.id": "e8d328e575a1b363", @@ -3068,7 +5501,9 @@ "QueryStartedEvent.runId": "3b5315e3cc1d95a2", "QueryStartedEvent.timestamp": "a7c5c95999df6bbb", "QueryTerminatedEvent": "9795140913b92355", - "QueryTerminatedEvent.__init__": null, + "QueryTerminatedEvent.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "QueryTerminatedEvent.errorClassOnException": "6dbf09391af688d6", "QueryTerminatedEvent.exception": "0f1d10dd3817305b", "QueryTerminatedEvent.fromJObject": null, @@ -3076,7 +5511,9 @@ "QueryTerminatedEvent.id": "e8d328e575a1b363", "QueryTerminatedEvent.runId": "3b5315e3cc1d95a2", "SinkProgress": "59831f67996a2613", - "SinkProgress.__init__": null, + "SinkProgress.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SinkProgress.description": "77a6d17a1cd4b89a", "SinkProgress.fromJObject": null, "SinkProgress.fromJson": null, @@ -3085,7 +5522,9 @@ "SinkProgress.numOutputRows": "7919716d7fc8b7ee", "SinkProgress.prettyJson": "2eded33a72ddaeda", "SourceProgress": "59831f67996a2613", - "SourceProgress.__init__": null, + "SourceProgress.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SourceProgress.description": "77a6d17a1cd4b89a", "SourceProgress.endOffset": "eb3861ed162d6375", "SourceProgress.fromJObject": null, @@ -3099,7 +5538,9 @@ "SourceProgress.processedRowsPerSecond": "47b2ee9951820dc9", "SourceProgress.startOffset": "90ff589f4f598454", "StateOperatorProgress": "59831f67996a2613", - "StateOperatorProgress.__init__": null, + "StateOperatorProgress.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StateOperatorProgress.allRemovalsTimeMs": null, "StateOperatorProgress.allUpdatesTimeMs": null, "StateOperatorProgress.commitTimeMs": null, @@ -3124,7 +5565,9 @@ "StreamingQueryListener.onQueryTerminated": "14fb9d4174f7aa21", "StreamingQueryListener.spark": null, "StreamingQueryProgress": "59831f67996a2613", - "StreamingQueryProgress.__init__": null, + "StreamingQueryProgress.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingQueryProgress.batchDuration": "beaf6d729f965cbe", "StreamingQueryProgress.batchId": "89e5cb585e0050e1", "StreamingQueryProgress.durationMs": "c5c02452bc99dd79", @@ -3148,7 +5591,9 @@ "pyspark.sql.streaming.map_state_client": { "": null, "MapStateClient": null, - "MapStateClient.__init__": null, + "MapStateClient.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "MapStateClient.clear": null, "MapStateClient.contains_key": null, "MapStateClient.exists": null, @@ -3158,9 +5603,13 @@ "MapStateClient.remove_key": null, "MapStateClient.update_value": null, "MapStateIterator": null, - "MapStateIterator.__init__": null, + "MapStateIterator.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "MapStateKeyValuePairIterator": null, - "MapStateKeyValuePairIterator.__init__": null + "MapStateKeyValuePairIterator.__init__": { + "getdoc": "15432c8b93cc48ea" + } }, "pyspark.sql.streaming.python_streaming_source_runner": { "": null, @@ -3179,10 +5628,14 @@ "pyspark.sql.streaming.query": { "": null, "StreamingCheckpointManager": "dbf4a7be50589bfb", - "StreamingCheckpointManager.__init__": null, + "StreamingCheckpointManager.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingCheckpointManager.repartition": "64457f4185c5a615", "StreamingQuery": "3d2a8c73ac5b63b9", - "StreamingQuery.__init__": null, + "StreamingQuery.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingQuery.awaitTermination": "a11b1ec83ec6546d", "StreamingQuery.exception": "ed08fa116b08fdbb", "StreamingQuery.explain": "a79d33e434816e0a", @@ -3196,7 +5649,9 @@ "StreamingQuery.status": "850fd0240933ff8d", "StreamingQuery.stop": "30e0cc8af42a0b36", "StreamingQueryManager": "b05c80407cfc30a0", - "StreamingQueryManager.__init__": null, + "StreamingQueryManager.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StreamingQueryManager.active": "a6849b63629a0d80", "StreamingQueryManager.addListener": "8e4c69400932d658", "StreamingQueryManager.awaitAnyTermination": "dcea09afc5822538", @@ -3207,7 +5662,9 @@ "pyspark.sql.streaming.readwriter": { "": null, "DataStreamReader": "03cc2ed3ce25d8d9", - "DataStreamReader.__init__": null, + "DataStreamReader.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataStreamReader.changes": "541e90706561845c", "DataStreamReader.csv": "b37308d6a4d853ba", "DataStreamReader.format": "b6b3ce7bea080e3b", @@ -3223,7 +5680,9 @@ "DataStreamReader.text": "7b67935235097f9e", "DataStreamReader.xml": "2192865746d1cb2e", "DataStreamWriter": "656cceac232502e0", - "DataStreamWriter.__init__": null, + "DataStreamWriter.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DataStreamWriter.clusterBy": "386ebb81c3394bb8", "DataStreamWriter.foreach": "c915e74a276fe0cf", "DataStreamWriter.foreachBatch": "08db99d591da039b", @@ -3241,7 +5700,9 @@ "": null, "GroupState": "81685dc76206fd19", "GroupState.NO_TIMESTAMP": "4072aed12b3287d8", - "GroupState.__init__": null, + "GroupState.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "GroupState.exists": "e98dcf053a995cbe", "GroupState.get": "2c5ef61dab7e76ca", "GroupState.getCurrentProcessingTimeMs": "048045748fd7d6dc", @@ -3263,10 +5724,14 @@ "pyspark.sql.streaming.stateful_processor": { "": null, "ExpiredTimerInfo": "84d3509426ecaaee", - "ExpiredTimerInfo.__init__": null, + "ExpiredTimerInfo.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ExpiredTimerInfo.getExpiryTimeInMs": "61c70d07f872237f", "ListState": "6159265fcd5d7211", - "ListState.__init__": null, + "ListState.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ListState.appendList": "b89727b2506f5eaa", "ListState.appendValue": "2b11b3776caf08a4", "ListState.clear": "8144e97b263e4dbe", @@ -3274,7 +5739,9 @@ "ListState.get": "a5f50adce3b31478", "ListState.put": "77051ee0760b7dbb", "MapState": "d3d261a981c23c2d", - "MapState.__init__": null, + "MapState.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "MapState.clear": "8144e97b263e4dbe", "MapState.containsKey": "c0bd4a0113c1e18a", "MapState.exists": "e98dcf053a995cbe", @@ -3292,7 +5759,9 @@ "StatefulProcessor.handleInputRows": "72cc70dda8c66dfc", "StatefulProcessor.init": "283d6dcbd992962e", "StatefulProcessorHandle": "0c71bb9f4b2323ba", - "StatefulProcessorHandle.__init__": null, + "StatefulProcessorHandle.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StatefulProcessorHandle.deleteIfExists": "267fe4d8c1d465df", "StatefulProcessorHandle.deleteTimer": "3516fb2e1e160eaf", "StatefulProcessorHandle.getListState": "ca68339833d9c016", @@ -3301,11 +5770,15 @@ "StatefulProcessorHandle.listTimers": "2e7020de042abdd7", "StatefulProcessorHandle.registerTimer": "ba6a109dac9ce614", "TimerValues": "3ee68340a344cfeb", - "TimerValues.__init__": null, + "TimerValues.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "TimerValues.getCurrentProcessingTimeInMs": "8ce75897de54b17d", "TimerValues.getCurrentWatermarkInMs": "25a310ca59489e5e", "ValueState": "73abd84e82e0a69b", - "ValueState.__init__": null, + "ValueState.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ValueState.clear": "8144e97b263e4dbe", "ValueState.exists": "e98dcf053a995cbe", "ValueState.get": "fb12cc8e84aca0eb", @@ -3314,11 +5787,17 @@ "pyspark.sql.streaming.stateful_processor_api_client": { "": null, "ExpiredTimerIterator": null, - "ExpiredTimerIterator.__init__": null, + "ExpiredTimerIterator.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ListTimerIterator": null, - "ListTimerIterator.__init__": null, + "ListTimerIterator.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StatefulProcessorApiClient": null, - "StatefulProcessorApiClient.__init__": null, + "StatefulProcessorApiClient.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StatefulProcessorApiClient.delete_if_exists": null, "StatefulProcessorApiClient.delete_timer": null, "StatefulProcessorApiClient.get_expiry_timers_iterator": null, @@ -3331,7 +5810,9 @@ "StatefulProcessorApiClient.remove_implicit_key": null, "StatefulProcessorApiClient.set_handle_state": null, "StatefulProcessorApiClient.set_implicit_key": null, - "StatefulProcessorHandleState": null, + "StatefulProcessorHandleState": { + "getdoc": "996efef2cf143fdc" + }, "StatefulProcessorHandleState.CLOSED": null, "StatefulProcessorHandleState.CREATED": null, "StatefulProcessorHandleState.DATA_PROCESSED": null, @@ -3347,7 +5828,9 @@ "TransformWithStateInPandasFuncMode.PROCESS_DATA": "ecc4c011305ba0e0", "TransformWithStateInPandasFuncMode.PROCESS_TIMER": "ecc4c011305ba0e0", "TransformWithStateInPandasUdfUtils": "d881240bc6f706a9", - "TransformWithStateInPandasUdfUtils.__init__": null, + "TransformWithStateInPandasUdfUtils.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "TransformWithStateInPandasUdfUtils.transformWithStateUDF": null, "TransformWithStateInPandasUdfUtils.transformWithStateWithInitStateUDF": "3ccf79985f4d1a8d" }, @@ -3358,7 +5841,9 @@ "pyspark.sql.streaming.tws_tester": { "": null, "TwsTester": "e270a817cb5d77f1", - "TwsTester.__init__": null, + "TwsTester.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "TwsTester.deleteState": "3202b53436dcd537", "TwsTester.peekListState": "d257e68246b45a61", "TwsTester.peekMapState": "0852e1f0e5c375c7", @@ -3374,12 +5859,22 @@ "pyspark.sql.streaming.value_state_client": { "": null, "ValueStateClient": null, - "ValueStateClient.__init__": null, + "ValueStateClient.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ValueStateClient.clear": null, "ValueStateClient.exists": null, "ValueStateClient.get": null, "ValueStateClient.update": null }, + "pyspark.sql.table_arg": { + "": null, + "TableArg": "a6c0854a7a59db3a", + "TableArg.__init__": "15432c8b93cc48ea", + "TableArg.orderBy": "a4f8f955b2d3c855", + "TableArg.partitionBy": "6d9411c14fd293f5", + "TableArg.withSinglePartition": "8b8abdf6e78ea42a" + }, "pyspark.sql.transpile": { "": "a78def915627df87", "AbstractTranspiler": "763062fd0f677410", @@ -3388,7 +5883,9 @@ "AbstractTranspiler.varieties": "6e3fb2af1d74c393", "AbstractTranspiler.variety": "fdf09be211280cf3", "CatalystTranspiler": "dacb6a7fb09f6ad5", - "CatalystTranspiler.__init__": null, + "CatalystTranspiler.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "CatalystTranspiler.register": null, "CatalystTranspiler.varieties": "6e3fb2af1d74c393", "CatalystTranspiler.variety": "fdf09be211280cf3" @@ -3396,7 +5893,9 @@ "pyspark.sql.tvf": { "": null, "TableValuedFunction": "10c531ad999a6d74", - "TableValuedFunction.__init__": null, + "TableValuedFunction.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "TableValuedFunction.collations": "0ae43ac350cf5062", "TableValuedFunction.explode": "fa99d79beb5f0d3d", "TableValuedFunction.explode_outer": "19c7d0ae4c10a24c", @@ -3440,15 +5939,23 @@ "AnyTimeType.toInternal": "dc31cc961abb5d2a", "AnyTimeType.typeName": null, "ArrayType": "630aab7ebf44a605", - "ArrayType.__init__": null, + "ArrayType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ArrayType.fromDDL": "07c5680ac03d8aa8", - "ArrayType.fromInternal": null, + "ArrayType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "ArrayType.fromJson": null, "ArrayType.json": null, "ArrayType.jsonValue": null, - "ArrayType.needConversion": null, + "ArrayType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "ArrayType.simpleString": null, - "ArrayType.toInternal": null, + "ArrayType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "ArrayType.toNullable": "83d7cead31026744", "ArrayType.typeName": null, "AtomicType": "64c7efef59a417fa", @@ -3494,15 +6001,23 @@ "CalendarIntervalType": "5a6709a93125a2f1", "CalendarIntervalType.__init__": "15432c8b93cc48ea", "CalendarIntervalType.fromDDL": "07c5680ac03d8aa8", - "CalendarIntervalType.fromInternal": null, + "CalendarIntervalType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "CalendarIntervalType.json": null, "CalendarIntervalType.jsonValue": null, - "CalendarIntervalType.needConversion": null, + "CalendarIntervalType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "CalendarIntervalType.simpleString": null, - "CalendarIntervalType.toInternal": null, + "CalendarIntervalType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "CalendarIntervalType.typeName": null, "CharType": "eb28e4ac40eff68c", - "CharType.__init__": null, + "CharType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "CharType.fromDDL": "07c5680ac03d8aa8", "CharType.fromInternal": "05c5a31cc99d2fd7", "CharType.json": null, @@ -3531,12 +6046,18 @@ "DateType.EPOCH_ORDINAL": "4072aed12b3287d8", "DateType.__init__": "15432c8b93cc48ea", "DateType.fromDDL": "07c5680ac03d8aa8", - "DateType.fromInternal": null, + "DateType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "DateType.json": null, "DateType.jsonValue": null, - "DateType.needConversion": null, + "DateType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "DateType.simpleString": null, - "DateType.toInternal": null, + "DateType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "DateType.typeName": null, "DatetimeConverter": null, "DatetimeConverter.__init__": "15432c8b93cc48ea", @@ -3561,21 +6082,31 @@ "DayTimeIntervalType.HOUR": "4072aed12b3287d8", "DayTimeIntervalType.MINUTE": "4072aed12b3287d8", "DayTimeIntervalType.SECOND": "4072aed12b3287d8", - "DayTimeIntervalType.__init__": null, + "DayTimeIntervalType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DayTimeIntervalType.fromDDL": "07c5680ac03d8aa8", - "DayTimeIntervalType.fromInternal": null, + "DayTimeIntervalType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "DayTimeIntervalType.json": null, "DayTimeIntervalType.jsonValue": null, - "DayTimeIntervalType.needConversion": null, + "DayTimeIntervalType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "DayTimeIntervalType.simpleString": null, - "DayTimeIntervalType.toInternal": null, + "DayTimeIntervalType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "DayTimeIntervalType.typeName": null, "DayTimeIntervalTypeConverter": null, "DayTimeIntervalTypeConverter.__init__": "15432c8b93cc48ea", "DayTimeIntervalTypeConverter.can_convert": null, "DayTimeIntervalTypeConverter.convert": null, "DecimalType": "e9fb195c186f6134", - "DecimalType.__init__": null, + "DecimalType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "DecimalType.fromDDL": "07c5680ac03d8aa8", "DecimalType.fromInternal": "05c5a31cc99d2fd7", "DecimalType.json": null, @@ -3615,7 +6146,9 @@ "FractionalType.toInternal": "dc31cc961abb5d2a", "FractionalType.typeName": null, "Geography": "4fcddd1cc0991472", - "Geography.__init__": null, + "Geography.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "Geography.fromWKB": "d1946544cda53a94", "Geography.getBytes": "12687d75d73c4630", "Geography.getSrid": "adcac79a906cedb2", @@ -3625,17 +6158,27 @@ "GeographyType.DEFAULT_SRID": "4072aed12b3287d8", "GeographyType.MIXED_CRS": "fdf09be211280cf3", "GeographyType.MIXED_SRID": "4072aed12b3287d8", - "GeographyType.__init__": null, + "GeographyType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "GeographyType.fromDDL": "07c5680ac03d8aa8", - "GeographyType.fromInternal": null, + "GeographyType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "GeographyType.json": null, "GeographyType.jsonValue": null, - "GeographyType.needConversion": null, + "GeographyType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "GeographyType.simpleString": null, - "GeographyType.toInternal": null, + "GeographyType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "GeographyType.typeName": null, "Geometry": "c314fdabe44a6354", - "Geometry.__init__": null, + "Geometry.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "Geometry.fromWKB": "1e9815e3b6d3c252", "Geometry.getBytes": "0973196f1e0f88ac", "Geometry.getSrid": "4483690c41d9e8c7", @@ -3644,14 +6187,22 @@ "GeometryType.DEFAULT_SRID": "4072aed12b3287d8", "GeometryType.MIXED_CRS": "fdf09be211280cf3", "GeometryType.MIXED_SRID": "4072aed12b3287d8", - "GeometryType.__init__": null, + "GeometryType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "GeometryType.fromDDL": "07c5680ac03d8aa8", - "GeometryType.fromInternal": null, + "GeometryType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "GeometryType.json": null, "GeometryType.jsonValue": null, - "GeometryType.needConversion": null, + "GeometryType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "GeometryType.simpleString": null, - "GeometryType.toInternal": null, + "GeometryType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "GeometryType.typeName": null, "IntegerType": "34bd02baa68f2751", "IntegerType.__init__": "15432c8b93cc48ea", @@ -3684,15 +6235,23 @@ "LongType.toInternal": "dc31cc961abb5d2a", "LongType.typeName": null, "MapType": "fb478b42f3b42432", - "MapType.__init__": null, + "MapType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "MapType.fromDDL": "07c5680ac03d8aa8", - "MapType.fromInternal": null, + "MapType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "MapType.fromJson": null, "MapType.json": null, "MapType.jsonValue": null, - "MapType.needConversion": null, + "MapType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "MapType.simpleString": null, - "MapType.toInternal": null, + "MapType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "MapType.toNullable": "4535a3f632b1f875", "MapType.typeName": null, "NullType": "f45c066ca20cb7d7", @@ -3749,7 +6308,9 @@ "SpatialType.toInternal": "dc31cc961abb5d2a", "SpatialType.typeName": null, "StringType": "68bbc0eecaf5ee40", - "StringType.__init__": null, + "StringType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StringType.collationProvider": null, "StringType.fromDDL": "07c5680ac03d8aa8", "StringType.fromInternal": "05c5a31cc99d2fd7", @@ -3764,32 +6325,48 @@ "StringType.toInternal": "dc31cc961abb5d2a", "StringType.typeName": null, "StructField": "0dc25016971da3a1", - "StructField.__init__": null, + "StructField.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StructField.fromDDL": "07c5680ac03d8aa8", - "StructField.fromInternal": null, + "StructField.fromInternal": { + "getdoc": "badf139c068433ac" + }, "StructField.fromJson": null, "StructField.getCollationMetadata": null, "StructField.getCollationsMap": null, "StructField.json": null, "StructField.jsonValue": null, - "StructField.needConversion": null, + "StructField.needConversion": { + "getdoc": "2a369a983858c79a" + }, "StructField.schemaCollationValue": null, "StructField.simpleString": null, - "StructField.toInternal": null, + "StructField.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "StructField.typeName": null, "StructType": "563aafbbf157a0d2", - "StructType.__init__": null, + "StructType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StructType.add": "34e5370e7e2ec5f5", "StructType.fieldNames": "404fa0e8e57a15d8", "StructType.fromDDL": "07c5680ac03d8aa8", - "StructType.fromInternal": null, + "StructType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "StructType.fromJson": "1bfc9b9dcd758379", "StructType.json": null, "StructType.jsonValue": null, - "StructType.needConversion": null, + "StructType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "StructType.simpleString": null, "StructType.toDDL": null, - "StructType.toInternal": null, + "StructType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "StructType.toNullable": "1ae989c966c44396", "StructType.treeString": null, "StructType.typeName": null, @@ -3798,53 +6375,81 @@ "TimeConverter.can_convert": null, "TimeConverter.convert": null, "TimeType": "415eace46fe9b58d", - "TimeType.__init__": null, + "TimeType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "TimeType.fromDDL": "07c5680ac03d8aa8", - "TimeType.fromInternal": null, + "TimeType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "TimeType.json": null, "TimeType.jsonValue": null, - "TimeType.needConversion": null, + "TimeType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "TimeType.simpleString": null, - "TimeType.toInternal": null, + "TimeType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "TimeType.typeName": null, "TimestampNTZType": "20083c6311d1df6d", "TimestampNTZType.__init__": "15432c8b93cc48ea", "TimestampNTZType.fromDDL": "07c5680ac03d8aa8", - "TimestampNTZType.fromInternal": null, + "TimestampNTZType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "TimestampNTZType.json": null, "TimestampNTZType.jsonValue": null, - "TimestampNTZType.needConversion": null, + "TimestampNTZType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "TimestampNTZType.simpleString": null, - "TimestampNTZType.toInternal": null, + "TimestampNTZType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "TimestampNTZType.typeName": null, "TimestampType": "cdcdda36b0013fe5", "TimestampType.__init__": "15432c8b93cc48ea", "TimestampType.fromDDL": "07c5680ac03d8aa8", - "TimestampType.fromInternal": null, + "TimestampType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "TimestampType.json": null, "TimestampType.jsonValue": null, - "TimestampType.needConversion": null, + "TimestampType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "TimestampType.simpleString": null, - "TimestampType.toInternal": null, + "TimestampType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "TimestampType.typeName": null, "UserDefinedType": "81cad2f4f8bcda3b", "UserDefinedType.__init__": "15432c8b93cc48ea", "UserDefinedType.deserialize": "988178e4abc6a3f3", "UserDefinedType.fromDDL": "07c5680ac03d8aa8", - "UserDefinedType.fromInternal": null, + "UserDefinedType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "UserDefinedType.fromJson": null, "UserDefinedType.json": null, "UserDefinedType.jsonValue": null, "UserDefinedType.module": "7f2655fa1fec9e7a", - "UserDefinedType.needConversion": null, + "UserDefinedType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "UserDefinedType.scalaUDT": "e6ca69a04363d4bb", "UserDefinedType.serialize": "f6905507d453fc00", "UserDefinedType.simpleString": null, "UserDefinedType.sqlType": "973e4f7ccf604dd6", - "UserDefinedType.toInternal": null, + "UserDefinedType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "UserDefinedType.typeName": null, "VarcharType": "9d612c2423b567f7", - "VarcharType.__init__": null, + "VarcharType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "VarcharType.fromDDL": "07c5680ac03d8aa8", "VarcharType.fromInternal": "05c5a31cc99d2fd7", "VarcharType.json": null, @@ -3856,66 +6461,100 @@ "VariantType": "f3d1b0723e2f6533", "VariantType.__init__": "15432c8b93cc48ea", "VariantType.fromDDL": "07c5680ac03d8aa8", - "VariantType.fromInternal": null, + "VariantType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "VariantType.json": null, "VariantType.jsonValue": null, - "VariantType.needConversion": null, + "VariantType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "VariantType.simpleString": null, - "VariantType.toInternal": null, + "VariantType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "VariantType.typeName": null, "VariantVal": "fa42eee8cbdacc7c", - "VariantVal.__init__": null, + "VariantVal.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "VariantVal.parseJson": "4f6e61f1c96d8cbc", "VariantVal.toJson": "e5ac03714db27b28", "VariantVal.toPython": "1b0fd060c4d35213", "YearMonthIntervalType": "21c291b990403c12", "YearMonthIntervalType.MONTH": "4072aed12b3287d8", "YearMonthIntervalType.YEAR": "4072aed12b3287d8", - "YearMonthIntervalType.__init__": null, + "YearMonthIntervalType.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "YearMonthIntervalType.fromDDL": "07c5680ac03d8aa8", - "YearMonthIntervalType.fromInternal": null, + "YearMonthIntervalType.fromInternal": { + "getdoc": "badf139c068433ac" + }, "YearMonthIntervalType.json": null, "YearMonthIntervalType.jsonValue": null, - "YearMonthIntervalType.needConversion": null, + "YearMonthIntervalType.needConversion": { + "getdoc": "2a369a983858c79a" + }, "YearMonthIntervalType.simpleString": null, - "YearMonthIntervalType.toInternal": null, + "YearMonthIntervalType.toInternal": { + "getdoc": "4a093690cb28f84a" + }, "YearMonthIntervalType.typeName": null }, "pyspark.sql.udf": { "": "42cd96762c7d007a", "UDFRegistration": "c4d35c0ca1455708", - "UDFRegistration.__init__": null, + "UDFRegistration.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UDFRegistration.register": "73b810ad4db560ca", "UDFRegistration.registerJavaFunction": "a31204b3a38ac937", "UDFRegistration.registerJavaUDAF": "f8cc4e87478e462a", "UserDefinedFunction": "a76e51ff5987ee07", - "UserDefinedFunction.__init__": null, + "UserDefinedFunction.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UserDefinedFunction.asNondeterministic": "957f8595f679a691", "UserDefinedFunction.returnType": null }, "pyspark.sql.udtf": { "": "a7813e95841dd9b7", "AnalyzeArgument": "6f7ce68204570b71", - "AnalyzeArgument.__init__": null, + "AnalyzeArgument.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "AnalyzeResult": "2ae97bf58f6504a9", - "AnalyzeResult.__init__": null, + "AnalyzeResult.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "AnalyzeResult.withSinglePartition": "89d61a0f6c4b7b36", "OrderingColumn": "459b96a0fecb2dba", - "OrderingColumn.__init__": null, + "OrderingColumn.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "OrderingColumn.ascending": "89d61a0f6c4b7b36", "OrderingColumn.overrideNullsFirst": null, "PartitioningColumn": "b048a606885b4b1f", - "PartitioningColumn.__init__": null, + "PartitioningColumn.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SelectedColumn": "63abc590b7def2b6", - "SelectedColumn.__init__": null, + "SelectedColumn.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "SelectedColumn.alias": "fdf09be211280cf3", "SkipRestOfInputTableException": "9d4b73313160b6ea", "SkipRestOfInputTableException.__init__": "15432c8b93cc48ea", "UDTFRegistration": "84441756739752eb", - "UDTFRegistration.__init__": null, + "UDTFRegistration.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UDTFRegistration.register": "7e318b93503b0e4a", "UserDefinedTableFunction": "bf6705fd3b211f24", - "UserDefinedTableFunction.__init__": null, + "UserDefinedTableFunction.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "UserDefinedTableFunction.asDeterministic": "897bbcc8e3ff742b", "UserDefinedTableFunction.returnType": null }, @@ -3923,13 +6562,17 @@ "": null, "ForeachBatchFunction": "e1eeab26dc430fce", "ForeachBatchFunction.Java": null, - "ForeachBatchFunction.__init__": null, + "ForeachBatchFunction.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "ForeachBatchFunction.call": null, "NumpyHelper": null, "NumpyHelper.__init__": "15432c8b93cc48ea", "NumpyHelper.linspace": null, "StringConcat": null, - "StringConcat.__init__": null, + "StringConcat.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "StringConcat.append": null, "StringConcat.atLimit": null, "StringConcat.toString": null, @@ -3965,7 +6608,9 @@ "FieldEntry.offset": "4f66f8b98c6e244c", "VariantBuilder": "6a4f2f34e3cc80f7", "VariantBuilder.DEFAULT_SIZE_LIMIT": "4072aed12b3287d8", - "VariantBuilder.__init__": null, + "VariantBuilder.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "VariantBuilder.build": null, "VariantUtils": "6c7d061776c9fd60", "VariantUtils.ARRAY": "4072aed12b3287d8", @@ -4021,12 +6666,32 @@ "VariantUtils.to_json": "0237dd9d87361b23", "VariantUtils.to_python": "dd916509a98e2acc" }, + "pyspark.sql.window": { + "": null, + "Window": "929073b8f8d08d22", + "Window.__init__": "15432c8b93cc48ea", + "Window.currentRow": "4072aed12b3287d8", + "Window.orderBy": "91479d60cfb4c460", + "Window.partitionBy": "c278fd2e638ec4e6", + "Window.rangeBetween": "7bd4e3e8435fb599", + "Window.rowsBetween": "c2bdda1450f2bdcb", + "Window.unboundedFollowing": "4072aed12b3287d8", + "Window.unboundedPreceding": "4072aed12b3287d8", + "WindowSpec": "f00688d7505aa255", + "WindowSpec.__init__": "15432c8b93cc48ea", + "WindowSpec.orderBy": "379f395fea5c8dc8", + "WindowSpec.partitionBy": "a0fa4fd5474337d4", + "WindowSpec.rangeBetween": "12faf25adf07d36b", + "WindowSpec.rowsBetween": "9be7a8de3e382f0f" + }, "pyspark.sql.worker": { "": null }, "pyspark.sql.worker.analyze_udtf": { "": null, - "UDTFHandler": null, + "UDTFHandler": { + "getdoc": "5b08ecf2d7e4e8a1" + }, "UDTFHandler.__init__": null, "UDTFHandler.analyze": null, "main": null, @@ -4044,7 +6709,9 @@ "pyspark.sql.worker.data_source_pushdown_filters": { "": null, "FilterRef": "05620f0422e6e683", - "FilterRef.__init__": null, + "FilterRef.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "deserializeFilter": null, "deserializeVariant": null, "main": null @@ -4066,7 +6733,9 @@ "pyspark.sql.worker.utils": { "": null, "RunnerConf": null, - "RunnerConf.__init__": null, + "RunnerConf.__init__": { + "getdoc": "15432c8b93cc48ea" + }, "RunnerConf.get": null, "RunnerConf.load": null, "RunnerConf.profiler": null,