move helper function to dtypes.py

Author: shuoweil

bigframes/core/blocks.py

@@ -43,7 +43,6 @@
 import warnings
 
 import bigframes_vendored.constants as constants
-import db_dtypes
 import google.cloud.bigquery as bigquery
 import numpy
 import pandas as pd
@@ -135,21 +134,6 @@ class MaterializationOptions:
     ordered: bool = True
 
 
-def _replace_json_arrow_with_string(pa_type: pa.DataType) -> pa.DataType:
-    """Recursively replace JSONArrowType with string type."""
-    if isinstance(pa_type, db_dtypes.JSONArrowType):
-        return pa.string()
-    if isinstance(pa_type, pa.ListType):
-        return pa.list_(_replace_json_arrow_with_string(pa_type.value_type))
-    if isinstance(pa_type, pa.StructType):
-        new_fields = [
-            field.with_type(_replace_json_arrow_with_string(field.type))
-            for field in pa_type
-        ]
-        return pa.struct(new_fields)
-    return pa_type
-
-
 class Block:
     """A immutable 2D data structure."""
 
@@ -746,7 +730,9 @@ def to_pandas_batches(
                 # MyPy doesn't automatically narrow the type of 'dtype' here,
                 # so we add an explicit check.
                 if isinstance(dtype, pd.ArrowDtype):
-                    safe_pa_type = _replace_json_arrow_with_string(dtype.pyarrow_dtype)
+                    safe_pa_type = bigframes.dtypes._replace_json_arrow_with_string(
+                        dtype.pyarrow_dtype
+                    )
                     safe_dtype = pd.ArrowDtype(safe_pa_type)
                     series_map[col] = pd.Series([], dtype=safe_dtype).astype(dtype)
                 else:

bigframes/dtypes.py

@@ -954,6 +954,21 @@ def contains_db_dtypes_json_dtype(dtype):
     return contains_db_dtypes_json_arrow_type(dtype.pyarrow_dtype)
 
 
+def _replace_json_arrow_with_string(pa_type: pa.DataType) -> pa.DataType:
+    """Recursively replace JSONArrowType with string type."""
+    if isinstance(pa_type, db_dtypes.JSONArrowType):
+        return pa.string()
+    if isinstance(pa_type, pa.ListType):
+        return pa.list_(_replace_json_arrow_with_string(pa_type.value_type))
+    if isinstance(pa_type, pa.StructType):
+        new_fields = [
+            field.with_type(_replace_json_arrow_with_string(field.type))
+            for field in pa_type
+        ]
+        return pa.struct(new_fields)
+    return pa_type
+
+
 def warn_on_db_dtypes_json_dtype(dtypes):
     """Warn that the JSON dtype is changing.
 

notebooks/dataframes/anywidget_mode.ipynb

@@ -151,7 +151,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "93dd10072d564a02a0278817d14855a9",
+       "model_id": "47795eaa10f149aeb99574232c0936eb",
        "version_major": 2,
        "version_minor": 1
       },
@@ -214,16 +214,17 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6e2538d446e344ac8505e4706730243e",
+       "model_id": "8354ce0f82d3495a9b630dfc362f73ee",
        "version_major": 2,
        "version_minor": 1
       },
       "text/plain": [
        "TableWidget(page_size=10, row_count=5552452, table_html='<table border=\"1\" class=\"dataframe table table-stripe…"
       ]
      },
+     "execution_count": 7,
      "metadata": {},
-     "output_type": "display_data"
+     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -292,8 +293,27 @@
     {
      "data": {
       "text/html": [
-       "✅ Completed. \n",
-       "    Query processed 171.4 MB in a moment of slot time.\n",
+       "\n",
+       "    Query started with request ID bigframes-dev:US.c45952fb-01b4-409c-9da4-f7c5bfc0d47d.<details><summary>SQL</summary><pre>SELECT\n",
+       "`state` AS `state`,\n",
+       "`gender` AS `gender`,\n",
+       "`year` AS `year`,\n",
+       "`name` AS `name`,\n",
+       "`number` AS `number`\n",
+       "FROM\n",
+       "(SELECT\n",
+       "  *\n",
+       "FROM (\n",
+       "  SELECT\n",
+       "    `state`,\n",
+       "    `gender`,\n",
+       "    `year`,\n",
+       "    `name`,\n",
+       "    `number`\n",
+       "  FROM `bigquery-public-data.usa_names.usa_1910_2013` FOR SYSTEM_TIME AS OF TIMESTAMP(&#x27;2025-10-30T21:48:48.979701+00:00&#x27;)\n",
+       ") AS `t0`)\n",
+       "ORDER BY `name` ASC NULLS LAST ,`year` ASC NULLS LAST ,`state` ASC NULLS LAST\n",
+       "LIMIT 5</pre></details>\n",
        "    "
       ],
       "text/plain": [
@@ -313,16 +333,17 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d6faf367ea5d44ad9d275506d870557a",
+       "model_id": "59461286a17d4a42b6be6d9d9c7bf7e3",
        "version_major": 2,
        "version_minor": 1
       },
       "text/plain": [
        "TableWidget(page_size=10, row_count=5, table_html='<table border=\"1\" class=\"dataframe table table-striped tabl…"
       ]
      },
+     "execution_count": 9,
      "metadata": {},
-     "output_type": "display_data"
+     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -352,7 +373,7 @@
      "data": {
       "text/html": [
        "✅ Completed. \n",
-       "    Query processed 85.9 kB in 24 seconds of slot time.\n",
+       "    Query processed 85.9 kB in 14 seconds of slot time.\n",
        "    "
       ],
       "text/plain": [
@@ -366,20 +387,16 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/usr/local/google/home/shuowei/src/github.com/googleapis/python-bigquery-dataframes/bigframes/dtypes.py:969: JSONDtypeWarning: JSON columns will be represented as pandas.ArrowDtype(pyarrow.json_())\n",
+      "/usr/local/google/home/shuowei/src/python-bigquery-dataframes/bigframes/dtypes.py:969: JSONDtypeWarning: JSON columns will be represented as pandas.ArrowDtype(pyarrow.json_())\n",
       "instead of using `db_dtypes` in the future when available in pandas\n",
       "(https://github.com/pandas-dev/pandas/issues/60958) and pyarrow.\n",
-      "  warnings.warn(msg, bigframes.exceptions.JSONDtypeWarning)\n",
-      "/usr/local/google/home/shuowei/src/github.com/googleapis/python-bigquery-dataframes/bigframes/dataframe.py:867: UserWarning: Converting JSON columns to strings for display. This is temporary and will be removed when the frontend supports JSON types.\n",
-      "  warnings.warn(\n"
+      "  warnings.warn(msg, bigframes.exceptions.JSONDtypeWarning)\n"
      ]
     },
     {
      "data": {
       "text/html": [
-       "✅ Completed. \n",
-       "    Query processed 0 Bytes in a moment of slot time.\n",
-       "    "
+       "✅ Completed. "
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -391,9 +408,9 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "b6d6f3bacc2c43fc9a335e6039db12a5",
+       "model_id": "d1794b42579542a8980bd158e521bd3e",
        "version_major": 2,
-       "version_minor": 0
+       "version_minor": 1
       },
       "text/plain": [
        "TableWidget(page_size=10, row_count=5, table_html='<table border=\"1\" class=\"dataframe table table-striped tabl…"
@@ -430,7 +447,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "3.10.18",
+   "display_name": "venv",
    "language": "python",
    "name": "python3"
   },
@@ -444,7 +461,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.18"
+   "version": "3.10.15"
   }
  },
  "nbformat": 4,