fix: unnest range_partitioning.range

Author: kitagry

README.md

@@ -112,10 +112,9 @@ Following options are same as [bq command-line tools](https://cloud.google.com/b
 |  time_partitioning.field          | string   | optional  | nil     | `DATE` or `TIMESTAMP` column used for partitioning |
 |  range_partitioning               | hash     | optional  | nil     | See [Range Partitioning](#range-partitioning) |
 |  range_partitioning.field         | string   | required  | nil     | `INT64` column used for partitioning |
-|  range-partitioning.range         | hash     | required  | nil     | Defines the ranges for range paritioning |
-|  range-partitioning.range.start   | string   | required  | nil     | The start of range partitioning, inclusive. This field is an INT64 value represented as a string. |
-|  range-partitioning.range.end     | string   | required  | nil     | The end of range partitioning, exclusive. This field is an INT64 value represented as a string. |
-|  range-partitioning.range.interval| string   | required  | nil     | The width of each interval. This field is an INT64 value represented as a string. |
+|  range_partitioning.start         | string   | required  | nil     | The start of range partitioning, inclusive. This field is an INT64 value represented as a string. |
+|  range_partitioning.end           | string   | required  | nil     | The end of range partitioning, exclusive. This field is an INT64 value represented as a string. |
+|  range_partitioning.interval      | string   | required  | nil     | The width of each interval. This field is an INT64 value represented as a string. |
 |  clustering                       | hash     | optional  | nil     | Currently, clustering is supported for partitioned tables, so must be used with `time_partitioning` option. See [clustered tables](https://cloud.google.com/bigquery/docs/clustered-tables) |
 |  clustering.fields                | array    | required  | nil     | One or more fields on which data should be clustered. The order of the specified columns determines the sort order of the data. |
 |  schema_update_options            | array    | optional  | nil     | (Experimental) List of `ALLOW_FIELD_ADDITION` or `ALLOW_FIELD_RELAXATION` or both. See [jobs#configuration.load.schemaUpdateOptions](https://cloud.google.com/bigquery/docs/reference/v2/jobs#configuration.load.schemaUpdateOptions). NOTE for the current status: `schema_update_options` does not work for `copy` job, that is, is not effective for most of modes such as `append`, `replace` and `replace_backup`. `delete_in_advance` deletes origin table so does not need to update schema. Only `append_direct` can utilize schema update. |
@@ -466,10 +465,9 @@ out:
   table: table_name$1
   range_partitioning:
     field: customer_id
-    range:
-      start: '1'
-      end: '99999'
-      range: '1'
+    start: '1'
+    end: '99999'
+    range: '1'
 ```
 
 ## Development

example/config_replace_field_range_partitioned_table.yml

@@ -30,7 +30,6 @@ out:
   schema_file: example/schema.json
   range_partitioning:
     field: 'long'
-    range:
-      start: '90'
-      end: '100'
-      interval: '1'
+    start: '90'
+    end: '100'
+    interval: '1'

lib/embulk/output/bigquery.rb

@@ -241,18 +241,14 @@ def self.configure(config, schema, task_count)
           unless task['range_partitioning']['field']
             raise ConfigError.new "`range_partitioning` must have `field` key"
           end
-          unless task['range_partitioning']['range']
-            raise ConfigError.new "`range_partitioning` must have `range` key"
+          unless task['range_partitioning']['start']
+            raise ConfigError.new "`range_partitioning` must have `start` key"
           end
-
-          unless task['range_partitioning']['range']['start']
-            raise ConfigError.new "`range_partitioning` must have `range.start` key"
-          end
-          unless task['range_partitioning']['range']['end']
-            raise ConfigError.new "`range_partitioning` must have `range.end` key"
+          unless task['range_partitioning']['end']
+            raise ConfigError.new "`range_partitioning` must have `end` key"
           end
-          unless task['range_partitioning']['range']['interval']
-            raise ConfigError.new "`range_partitioning` must have `range.interval` key"
+          unless task['range_partitioning']['interval']
+            raise ConfigError.new "`range_partitioning` must have `interval` key"
           end
         end
 

lib/embulk/output/bigquery/bigquery_client.rb

@@ -440,9 +440,9 @@ def create_table_if_not_exists(table, dataset: nil, options: nil)
               body[:range_partitioning] = {
                 field: options['range_partitioning']['field'],
                 range: {
-                  start: options['range_partitioning']['range']['start'],
-                  end: options['range_partitioning']['range']['end'],
-                  interval: options['range_partitioning']['range']['interval'],
+                  start: options['range_partitioning']['start'],
+                  end: options['range_partitioning']['end'],
+                  interval: options['range_partitioning']['interval'],
                 },
               }
             end

test/test_configure.rb

@@ -271,28 +271,23 @@ def test_time_partitioning
       end
 
       def test_range_partitioning
-        config = least_config.merge('range_partitioning' => {'field' => 'foo', 'range' => { 'start' => '1', 'end' => '2', 'interval' => '1' }})
+        config = least_config.merge('range_partitioning' => {'field' => 'foo', 'start' => '1', 'end' => '2', 'interval' => '1'})
         assert_nothing_raised { Bigquery.configure(config, schema, processor_count) }
 
         # field is required
-        config = least_config.merge('range_partitioning' => {'range' => { 'start' => '1', 'end' => '2', 'interval' => '1' }})
+        config = least_config.merge('range_partitioning' => {'start' => '1', 'end' => '2', 'interval' => '1'})
         assert_raise { Bigquery.configure(config, schema, processor_count) }
 
-
-        # range is required
-        config = least_config.merge('range_partitioning' => {'field' => 'foo'})
-        assert_raise { Bigquery.configure(config, schema, processor_count) }
-
-        # range.start is required
-        config = least_config.merge('range_partitioning' => {'field' => 'foo', 'range' => { 'end' => '2', 'interval' => '1' }})
+        # start is required
+        config = least_config.merge('range_partitioning' => {'field' => 'foo', 'end' => '2', 'interval' => '1'})
         assert_raise { Bigquery.configure(config, schema, processor_count) }
 
-        # range.end is required
-        config = least_config.merge('range_partitioning' => {'field' => 'foo', 'range' => { 'start' => '1', 'interval' => '1' }})
+        # end is required
+        config = least_config.merge('range_partitioning' => {'field' => 'foo', 'start' => '1', 'interval' => '1'})
         assert_raise { Bigquery.configure(config, schema, processor_count) }
 
-        # range.interval is required
-        config = least_config.merge('range_partitioning' => {'field' => 'foo', 'range' => { 'start' => '1', 'end' => '2' }})
+        # interval is required
+        config = least_config.merge('range_partitioning' => {'field' => 'foo', 'start' => '1', 'end' => '2'})
         assert_raise { Bigquery.configure(config, schema, processor_count) }
       end