PERF: avoid NumPy fallback in ArrowStringArray._from_sequence for integer types

When converting ArrowExtensionArray to string dtype, use PyArrow's native
pc.cast() for integer and string types where the string representation
matches Python's str(). This avoids unnecessary conversion through NumPy.

Float and boolean types still fall back to lib.ensure_string_array because
PyArrow's string representation differs from Python's str():
- Float: 1.0 -> "1" (PyArrow) vs "1.0" (Python)
- Bool: True -> "true" (PyArrow) vs "True" (Python)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <[email protected]>

Author: fangchenli

pandas/core/arrays/string_arrow.py

@@ -210,6 +210,23 @@ def _from_sequence(
             result = scalars._data
             result = lib.ensure_string_array(result, copy=copy, convert_na_value=False)
             pa_arr = pa.array(result, mask=na_values, type=pa.large_string())
+        elif isinstance(scalars, ArrowExtensionArray):
+            pa_type = scalars._pa_array.type
+            # Use PyArrow's native cast for integer and string types where
+            # the string representation matches Python's str().
+            # Float and boolean have different representations in PyArrow
+            # (e.g., 1.0 -> "1" instead of "1.0", True -> "true" instead of "True")
+            if (
+                pa.types.is_integer(pa_type)
+                or pa.types.is_large_string(pa_type)
+                or pa.types.is_string(pa_type)
+            ):
+                pa_arr = pc.cast(scalars._pa_array, pa.large_string())
+            else:
+                # Fall back for types where PyArrow's string representation
+                # differs from Python's str()
+                result = lib.ensure_string_array(scalars, copy=copy)
+                pa_arr = pa.array(result, type=pa.large_string(), from_pandas=True)
         elif isinstance(scalars, (pa.Array, pa.ChunkedArray)):
             pa_arr = pc.cast(scalars, pa.large_string())
         else: