🐛 Normalization: Fix sync from HubSpot to MySQL fails with "Row size too large" on create table (#10485)

* Update mysql normalization to cast string as text.
Bump docker version.
Update basic-normalization.md docs.

* Update docs PR reference

* Update mysql normalization to cast string as for is_timestamp_with_time_zone type

Author: htrueman

airbyte-integrations/bases/base-normalization/Dockerfile

@@ -28,5 +28,5 @@ WORKDIR /airbyte
 ENV AIRBYTE_ENTRYPOINT "/airbyte/entrypoint.sh"
 ENTRYPOINT ["/airbyte/entrypoint.sh"]
 
-LABEL io.airbyte.version=0.1.67
+LABEL io.airbyte.version=0.1.68
 LABEL io.airbyte.name=airbyte/normalization

airbyte-integrations/bases/base-normalization/normalization/transform_catalog/stream_processor.py

@@ -516,6 +516,8 @@ def cast_property_type(self, property_name: str, column_name: str, jinja_column:
                 return f"parseDateTime64BestEffortOrNull(trim(BOTH '\"' from {replace_operation})) as {column_name}"
             # in all other cases
             sql_type = jinja_call("type_timestamp_with_timezone()")
+            if self.destination_type == DestinationType.MYSQL:
+                sql_type = f"{sql_type}(1024)"
             return f"cast({replace_operation} as {sql_type}) as {column_name}"
         elif is_date(definition):
             if self.destination_type.value == DestinationType.MYSQL.value:
@@ -538,6 +540,9 @@ def cast_property_type(self, property_name: str, column_name: str, jinja_column:
                 trimmed_column_name = f"trim(BOTH '\"' from {column_name})"
                 sql_type = f"'{sql_type}'"
                 return f"nullif(accurateCastOrNull({trimmed_column_name}, {sql_type}), 'null') as {column_name}"
+            elif self.destination_type == DestinationType.MYSQL:
+                # Cast to `text` datatype. See https://github.com/airbytehq/airbyte/issues/7994
+                sql_type = f"{sql_type}(1024)"
         else:
             print(f"WARN: Unknown type {definition['type']} for column {property_name} at {self.current_json_path()}")
             return column_name

airbyte-workers/src/main/java/io/airbyte/workers/normalization/NormalizationRunnerFactory.java

@@ -14,7 +14,7 @@
 public class NormalizationRunnerFactory {
 
   public static final String BASE_NORMALIZATION_IMAGE_NAME = "airbyte/normalization";
-  public static final String NORMALIZATION_VERSION = "0.1.67";
+  public static final String NORMALIZATION_VERSION = "0.1.68";
 
   static final Map<String, ImmutablePair<String, DefaultNormalizationRunner.DestinationType>> NORMALIZATION_MAPPING =
       ImmutableMap.<String, ImmutablePair<String, DefaultNormalizationRunner.DestinationType>>builder()

docs/understanding-airbyte/basic-normalization.md

@@ -350,6 +350,7 @@ Therefore, in order to "upgrade" to the desired normalization version, you need
 
 | Airbyte Version | Normalization Version | Date | Pull Request | Subject |
 |:----------------| :--- | :--- | :--- | :--- |
+| 0.35.32-alpha   | 0.1.68 | 2022-02-20 | [\#10485](https://github.com/airbytehq/airbyte/pull/10485) | Fix row size too large for table with numerous `string` fields |
 |                 | 0.1.66 | 2022-02-04 | [\#9341](https://github.com/airbytehq/airbyte/pull/9341) | Fix normalization for bigquery datasetId and tables |
 | 0.35.13-alpha   | 0.1.65 | 2021-01-28 | [\#9846](https://github.com/airbytehq/airbyte/pull/9846) | Tweak dbt multi-thread parameter down |
 | 0.35.12-alpha   | 0.1.64 | 2021-01-28 | [\#9793](https://github.com/airbytehq/airbyte/pull/9793) | Support PEM format for ssh-tunnel keys |