ARROW-35 Improve error message when schema contains an unsupported type (#45)

Author: blink1073

bindings/python/docs/source/changelog.rst

@@ -4,6 +4,7 @@ Changelog
 Changes in Version 0.3.0
 ------------------------
 - Support for `ObjectId` `bson` type.
+- Improve error message when schema contains an unsupported type.
 
 Changes in Version 0.2.0
 ------------------------

bindings/python/docs/source/supported_types.rst

@@ -36,3 +36,7 @@ respectively, and '_id' that is an `ObjectId`, your schema can be defined as::
     'f1': pyarrow.int32(),
     'f2': pyarrow.timestamp('ms')
 })
+
+Unsupported data types in a schema cause a ``ValueError`` identifying the
+field and its data type.
+

bindings/python/pymongoarrow/types.py

@@ -80,5 +80,8 @@ def _get_internal_typemap(typemap):
                     internal_typemap[fname] = internal_id
             except AttributeError:
                 pass
-    assert len(internal_typemap) == len(typemap)
+        if fname not in internal_typemap:
+            raise ValueError('Unsupported data type in schema for ' +
+                f'field "{fname}" of type "{ftype}"')
+
     return internal_typemap

bindings/python/test/test_bson.py

@@ -15,6 +15,7 @@
 
 from bson import encode, InvalidBSON
 
+import pyarrow
 from pymongoarrow.context import PyMongoArrowContext
 from pymongoarrow.lib import process_bson_stream
 from pymongoarrow.schema import Schema
@@ -94,3 +95,16 @@ def test_simple(self):
         with self.assertRaisesRegex(
                 InvalidBSON, "Could not read BSON document stream"):
             self._run_test(docs, as_dict)
+
+
+class TestUnsupportedDataType(TestBsonToArrowConversionBase):
+
+    def test_simple(self):
+
+        schema = Schema({'_id': ObjectId,
+                         'data': int64(),
+                         'title': pyarrow.string() })
+        msg =  ("Unsupported data type in schema for field " +
+                '"title" of type "string"')
+        with self.assertRaisesRegex(ValueError, msg):
+            PyMongoArrowContext.from_schema(schema)