feat: dataframe string formatter (#1170)

* Add string formatter

* Rename html_formatter to dataframe_formatter

* Add deprecation warning

* Small adjustments based on user feedback

Author: timsaucer

python/datafusion/__init__.py

@@ -46,11 +46,11 @@
     SQLOptions,
 )
 from .dataframe import DataFrame, ParquetColumnOptions, ParquetWriterOptions
+from .dataframe_formatter import configure_formatter
 from .expr import (
     Expr,
     WindowFrame,
 )
-from .html_formatter import configure_formatter
 from .io import read_avro, read_csv, read_json, read_parquet
 from .plan import ExecutionPlan, LogicalPlan
 from .record_batch import RecordBatch, RecordBatchStream

python/datafusion/dataframe.py

@@ -52,7 +52,6 @@
     import polars as pl
     import pyarrow as pa
 
-    from datafusion._internal import DataFrame as DataFrameInternal
     from datafusion._internal import expr as expr_internal
 
 from enum import Enum
@@ -327,6 +326,20 @@ def __repr__(self) -> str:
     def _repr_html_(self) -> str:
         return self.df._repr_html_()
 
+    @staticmethod
+    def default_str_repr(
+        batches: list[pa.RecordBatch],
+        schema: pa.Schema,
+        has_more: bool,
+        table_uuid: str | None = None,
+    ) -> str:
+        """Return the default string representation of a DataFrame.
+
+        This method is used by the default formatter and implemented in Rust for
+        performance reasons.
+        """
+        return DataFrameInternal.default_str_repr(batches, schema, has_more, table_uuid)
+
     def describe(self) -> DataFrame:
         """Return the statistics for this DataFrame.