Merge branch 'main' into fill-null

Author: kosiew

.asf.yaml

@@ -29,6 +29,10 @@ github:
     rebase: false
   features:
     issues: true
+  protected_branches:
+    main:
+      required_pull_request_reviews:
+        required_approving_review_count: 1
 
 staging:
   whoami: asf-staging

docs/source/user-guide/dataframe.rst

@@ -75,13 +75,17 @@ You can customize how DataFrames are rendered in HTML by configuring the formatt
     
     # Change the default styling
     configure_formatter(
-        max_rows=50,           # Maximum number of rows to display
-        max_width=None,        # Maximum width in pixels (None for auto)
-        theme="light",         # Theme: "light" or "dark" 
-        precision=2,           # Floating point precision
-        thousands_separator=",", # Separator for thousands
-        date_format="%Y-%m-%d", # Date format
-        truncate_width=20      # Max width for string columns before truncating
+        max_cell_length=25,        # Maximum characters in a cell before truncation
+        max_width=1000,            # Maximum width in pixels
+        max_height=300,            # Maximum height in pixels
+        max_memory_bytes=2097152,  # Maximum memory for rendering (2MB)
+        min_rows_display=20,       # Minimum number of rows to display
+        repr_rows=10,              # Number of rows to display in __repr__
+        enable_cell_expansion=True,# Allow expanding truncated cells
+        custom_css=None,           # Additional custom CSS
+        show_truncation_message=True, # Show message when data is truncated
+        style_provider=None,       # Custom styling provider
+        use_shared_styles=True     # Share styles across tables
     )
 
 The formatter settings affect all DataFrames displayed after configuration.
@@ -113,6 +117,25 @@ For advanced styling needs, you can create a custom style provider:
     # Apply the custom style provider
     configure_formatter(style_provider=MyStyleProvider())
 
+Performance Optimization with Shared Styles
+-------------------------------------------
+The ``use_shared_styles`` parameter (enabled by default) optimizes performance when displaying 
+multiple DataFrames in notebook environments:
+
+ .. code-block:: python
+    from datafusion.html_formatter import StyleProvider, configure_formatter
+    # Default: Use shared styles (recommended for notebooks)
+    configure_formatter(use_shared_styles=True)
+
+    # Disable shared styles (each DataFrame includes its own styles)
+    configure_formatter(use_shared_styles=False)
+
+When ``use_shared_styles=True``:
+- CSS styles and JavaScript are included only once per notebook session
+- This reduces HTML output size and prevents style duplication
+- Improves rendering performance with many DataFrames
+- Applies consistent styling across all DataFrames
+
 Creating a Custom Formatter
 ---------------------------
 
@@ -177,3 +200,18 @@ You can also use a context manager to temporarily change formatting settings:
     
     # Back to default formatting
     df.show()
+
+Memory and Display Controls
+---------------------------
+
+You can control how much data is displayed and how much memory is used for rendering:
+
+ .. code-block:: python
+ 
+    configure_formatter(
+        max_memory_bytes=4 * 1024 * 1024,  # 4MB maximum memory for display
+        min_rows_display=50,               # Always show at least 50 rows
+        repr_rows=20                       # Show 20 rows in __repr__ output
+    )
+
+These parameters help balance comprehensive data display against performance considerations.

python/datafusion/common.py

@@ -33,8 +33,12 @@
 SqlTable = common_internal.SqlTable
 SqlType = common_internal.SqlType
 SqlView = common_internal.SqlView
+TableType = common_internal.TableType
+TableSource = common_internal.TableSource
+Constraints = common_internal.Constraints
 
 __all__ = [
+    "Constraints",
     "DFSchema",
     "DataType",
     "DataTypeMap",
@@ -47,6 +51,8 @@
     "SqlTable",
     "SqlType",
     "SqlView",
+    "TableSource",
+    "TableType",
 ]
 
 

python/datafusion/expr.py

@@ -54,14 +54,29 @@
 Case = expr_internal.Case
 Cast = expr_internal.Cast
 Column = expr_internal.Column
+CopyTo = expr_internal.CopyTo
+CreateCatalog = expr_internal.CreateCatalog
+CreateCatalogSchema = expr_internal.CreateCatalogSchema
+CreateExternalTable = expr_internal.CreateExternalTable
+CreateFunction = expr_internal.CreateFunction
+CreateFunctionBody = expr_internal.CreateFunctionBody
+CreateIndex = expr_internal.CreateIndex
 CreateMemoryTable = expr_internal.CreateMemoryTable
 CreateView = expr_internal.CreateView
+Deallocate = expr_internal.Deallocate
+DescribeTable = expr_internal.DescribeTable
 Distinct = expr_internal.Distinct
+DmlStatement = expr_internal.DmlStatement
+DropCatalogSchema = expr_internal.DropCatalogSchema
+DropFunction = expr_internal.DropFunction
 DropTable = expr_internal.DropTable
+DropView = expr_internal.DropView
 EmptyRelation = expr_internal.EmptyRelation
+Execute = expr_internal.Execute
 Exists = expr_internal.Exists
 Explain = expr_internal.Explain
 Extension = expr_internal.Extension
+FileType = expr_internal.FileType
 Filter = expr_internal.Filter
 GroupingSet = expr_internal.GroupingSet
 Join = expr_internal.Join
@@ -83,21 +98,31 @@
 Literal = expr_internal.Literal
 Negative = expr_internal.Negative
 Not = expr_internal.Not
+OperateFunctionArg = expr_internal.OperateFunctionArg
 Partitioning = expr_internal.Partitioning
 Placeholder = expr_internal.Placeholder
+Prepare = expr_internal.Prepare
 Projection = expr_internal.Projection
+RecursiveQuery = expr_internal.RecursiveQuery
 Repartition = expr_internal.Repartition
 ScalarSubquery = expr_internal.ScalarSubquery
 ScalarVariable = expr_internal.ScalarVariable
+SetVariable = expr_internal.SetVariable
 SimilarTo = expr_internal.SimilarTo
 Sort = expr_internal.Sort
 Subquery = expr_internal.Subquery
 SubqueryAlias = expr_internal.SubqueryAlias
 TableScan = expr_internal.TableScan
+TransactionAccessMode = expr_internal.TransactionAccessMode
+TransactionConclusion = expr_internal.TransactionConclusion
+TransactionEnd = expr_internal.TransactionEnd
+TransactionIsolationLevel = expr_internal.TransactionIsolationLevel
+TransactionStart = expr_internal.TransactionStart
 TryCast = expr_internal.TryCast
 Union = expr_internal.Union
 Unnest = expr_internal.Unnest
 UnnestExpr = expr_internal.UnnestExpr
+Values = expr_internal.Values
 WindowExpr = expr_internal.WindowExpr
 
 __all__ = [
@@ -111,15 +136,30 @@
     "CaseBuilder",
     "Cast",
     "Column",
+    "CopyTo",
+    "CreateCatalog",
+    "CreateCatalogSchema",
+    "CreateExternalTable",
+    "CreateFunction",
+    "CreateFunctionBody",
+    "CreateIndex",
     "CreateMemoryTable",
     "CreateView",
+    "Deallocate",
+    "DescribeTable",
     "Distinct",
+    "DmlStatement",
+    "DropCatalogSchema",
+    "DropFunction",
     "DropTable",
+    "DropView",
     "EmptyRelation",
+    "Execute",
     "Exists",
     "Explain",
     "Expr",
     "Extension",
+    "FileType",
     "Filter",
     "GroupingSet",
     "ILike",
@@ -142,22 +182,32 @@
     "Literal",
     "Negative",
     "Not",
+    "OperateFunctionArg",
     "Partitioning",
     "Placeholder",
+    "Prepare",
     "Projection",
+    "RecursiveQuery",
     "Repartition",
     "ScalarSubquery",
     "ScalarVariable",
+    "SetVariable",
     "SimilarTo",
     "Sort",
     "SortExpr",
     "Subquery",
     "SubqueryAlias",
     "TableScan",
+    "TransactionAccessMode",
+    "TransactionConclusion",
+    "TransactionEnd",
+    "TransactionIsolationLevel",
+    "TransactionStart",
     "TryCast",
     "Union",
     "Unnest",
     "UnnestExpr",
+    "Values",
     "Window",
     "WindowExpr",
     "WindowFrame",
@@ -686,8 +736,8 @@ def log10(self) -> Expr:
     def initcap(self) -> Expr:
         """Set the initial letter of each word to capital.
 
-        Converts the first letter of each word in ``string``
-        to uppercase and the remaining characters to lowercase.
+        Converts the first letter of each word in ``string`` to uppercase and the
+        remaining characters to lowercase.
         """
         from . import functions as F