feat: add blob.exif function support (#1703)

Author: GarrettWu

bigframes/blob/_functions.py

@@ -108,6 +108,38 @@ def udf(self):
         return self._session.read_gbq_function(udf_name)
 
 
+def exif_func(src_obj_ref_rt: str) -> str:
+    import io
+    import json
+
+    from PIL import ExifTags, Image
+    import requests
+    from requests import adapters
+
+    session = requests.Session()
+    session.mount("https://", adapters.HTTPAdapter(max_retries=3))
+
+    src_obj_ref_rt_json = json.loads(src_obj_ref_rt)
+
+    src_url = src_obj_ref_rt_json["access_urls"]["read_url"]
+
+    response = session.get(src_url, timeout=30)
+    bts = response.content
+
+    image = Image.open(io.BytesIO(bts))
+    exif_data = image.getexif()
+    exif_dict = {}
+    if exif_data:
+        for tag, value in exif_data.items():
+            tag_name = ExifTags.TAGS.get(tag, tag)
+            exif_dict[tag_name] = value
+
+    return json.dumps(exif_dict)
+
+
+exif_func_def = FunctionDef(exif_func, ["pillow", "requests"])
+
+
 # Blur images. Takes ObjectRefRuntime as JSON string. Outputs ObjectRefRuntime JSON string.
 def image_blur_func(
     src_obj_ref_rt: str, dst_obj_ref_rt: str, ksize_x: int, ksize_y: int, ext: str

bigframes/operations/blob.py

@@ -300,6 +300,46 @@ def get_runtime_json_str(
         runtime = self._get_runtime(mode=mode, with_metadata=with_metadata)
         return runtime._apply_unary_op(ops.ToJSONString())
 
+    def exif(
+        self,
+        *,
+        connection: Optional[str] = None,
+        max_batching_rows: int = 8192,
+        container_cpu: Union[float, int] = 0.33,
+        container_memory: str = "512Mi",
+    ) -> bigframes.series.Series:
+        """Extract EXIF data. Now only support image types.
+
+        Args:
+            connection (str or None, default None): BQ connection used for function internet transactions, and the output blob if "dst" is str. If None, uses default connection of the session.
+            max_batching_rows (int, default 8,192): Max number of rows per batch send to cloud run to execute the function.
+            container_cpu (int or float, default 0.33): number of container CPUs. Possible values are [0.33, 8]. Floats larger than 1 are cast to intergers.
+            container_memory (str, default "512Mi"): container memory size. String of the format <number><unit>. Possible values are from 512Mi to 32Gi.
+
+        Returns:
+            bigframes.series.Series: JSON series of key-value pairs.
+        """
+
+        import bigframes.bigquery as bbq
+        import bigframes.blob._functions as blob_func
+
+        connection = self._resolve_connection(connection)
+        df = self.get_runtime_json_str(mode="R").to_frame()
+
+        exif_udf = blob_func.TransformFunction(
+            blob_func.exif_func_def,
+            session=self._block.session,
+            connection=connection,
+            max_batching_rows=max_batching_rows,
+            container_cpu=container_cpu,
+            container_memory=container_memory,
+        ).udf()
+
+        res = self._df_apply_udf(df, exif_udf)
+        res = bbq.parse_json(res)
+
+        return res
+
     def image_blur(
         self,
         ksize: tuple[int, int],

notebooks/experimental/multimodal_dataframe.ipynb

@@ -106,7 +106,7 @@
       },
       "source": [
         "### 1. Create Multimodal DataFrame\n",
-        "There are several ways to create Multimodal DataFrame. The easiest way is from the wiledcard paths."
+        "There are several ways to create Multimodal DataFrame. The easiest way is from the wildcard paths."
       ]
     },
     {

tests/system/large/blob/test_function.py

@@ -51,6 +51,30 @@ def images_output_uris(images_output_folder: str) -> list[str]:
     ]
 
 
+def test_blob_exif(
+    bq_connection: str,
+    test_session: bigframes.Session,
+):
+    exif_image_df = test_session.from_glob_path(
+        "gs://bigframes_blob_test/images_exif/*",
+        name="blob_col",
+        connection=bq_connection,
+    )
+
+    actual = exif_image_df["blob_col"].blob.exif(connection=bq_connection)
+    expected = bpd.Series(
+        ['{"ExifOffset": 47, "Make": "MyCamera"}'],
+        session=test_session,
+        dtype=dtypes.JSON_DTYPE,
+    )
+    pd.testing.assert_series_equal(
+        actual.to_pandas(),
+        expected.to_pandas(),
+        check_dtype=False,
+        check_index_type=False,
+    )
+
+
 def test_blob_image_blur_to_series(
     images_mm_df: bpd.DataFrame,
     bq_connection: str,