Merge pull request #23 from trocco-io/add_column_type_numeric

[Ruby版][ADD]NUMERIC対応

Author: HokutoMorita

.github/workflows/gem-push.yml

@@ -0,0 +1,25 @@
+name: Ruby Gem
+
+on:
+  workflow_dispatch:
+  push:
+    tags:
+      - 'v*'
+
+jobs:
+  build:
+    name: Build + Publish
+    runs-on: ubuntu-latest
+    permissions:
+      packages: write
+      contents: read
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Ruby 2.7
+        uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: 2.7
+      - name: push gem
+        uses: trocco-io/push-gem-to-gpr-action@v1
+        with:
+          github-token: "${{ secrets.GITHUB_TOKEN }}"

Gemfile

@@ -1,7 +1,7 @@
 source 'https://rubygems.org/'
 
 gemspec
-gem 'embulk'
+gem 'embulk', '< 0.10'
 gem 'liquid', '= 4.0.0' # the version included in embulk.jar
 gem 'embulk-parser-none'
 gem 'embulk-parser-jsonl'

README.md

@@ -307,18 +307,20 @@ Column options are used to aid guessing BigQuery schema, or to define conversion
 
 - **column_options**: advanced: an array of options for columns
   - **name**: column name
-  - **type**: BigQuery type such as `BOOLEAN`, `INTEGER`, `FLOAT`, `STRING`, `TIMESTAMP`, `DATETIME`, `DATE`, and `RECORD`. See belows for supported conversion type.
+  - **type**: BigQuery type such as `BOOLEAN`, `INTEGER`, `FLOAT`, `STRING`, `TIMESTAMP`, `DATETIME`, `DATE`, `RECORD`, and `NUMERIC`. See belows for supported conversion type.
     - boolean:   `BOOLEAN`, `STRING` (default: `BOOLEAN`)
     - long:      `BOOLEAN`, `INTEGER`, `FLOAT`, `STRING`, `TIMESTAMP` (default: `INTEGER`)
     - double:    `INTEGER`, `FLOAT`, `STRING`, `TIMESTAMP` (default: `FLOAT`)
     - string:    `BOOLEAN`, `INTEGER`, `FLOAT`, `STRING`, `TIMESTAMP`, `DATETIME`, `DATE`, `RECORD` (default: `STRING`)
     - timestamp: `INTEGER`, `FLOAT`, `STRING`, `TIMESTAMP`, `DATETIME`, `DATE` (default: `TIMESTAMP`)
     - json:      `STRING`,  `RECORD` (default: `STRING`)
+    - numeric:   `STRING`
   - **mode**: BigQuery mode such as `NULLABLE`, `REQUIRED`, and `REPEATED` (string, default: `NULLABLE`)
   - **fields**: Describes the nested schema fields if the type property is set to RECORD. Please note that this is **required** for `RECORD` column.
   - **timestamp_format**: timestamp format to convert into/from `timestamp` (string, default is `default_timestamp_format`)
   - **timezone**: timezone to convert into/from `timestamp`, `date` (string, default is `default_timezone`).
   - **description**: description for the column.
+  - **scale**: optional, [scale](https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types?hl=ja#decimal_types) for numeric column (long, default is 9).
 - **default_timestamp_format**: default timestamp format for column_options (string, default is "%Y-%m-%d %H:%M:%S.%6N")
 - **default_timezone**: default timezone for column_options (string, default is "UTC")
 

embulk-output-bigquery.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |spec|
   spec.name          = "embulk-output-bigquery"
-  spec.version       = "0.6.13"
+  spec.version       = "0.7.0"
   spec.authors       = ["Satoshi Akama", "Naotoshi Seo"]
   spec.summary       = "Google BigQuery output plugin for Embulk"
   spec.description   = "Embulk plugin that insert records to Google BigQuery."

lib/embulk/output/bigquery/value_converter_factory.rb

@@ -1,6 +1,7 @@
 require 'time'
 require 'time_with_zone'
 require 'json'
+require 'bigdecimal'
 require_relative 'helper'
 
 module Embulk
@@ -14,6 +15,7 @@ class TypeCastError < StandardError; end
 
         DEFAULT_TIMESTAMP_FORMAT = "%Y-%m-%d %H:%M:%S.%6N" # BigQuery timestamp format
         DEFAULT_TIMEZONE         = "UTC"
+        DEFAULT_SCALE            = 9
 
         # @param [Hash] task
         # @option task [String] default_timestamp_format
@@ -29,13 +31,15 @@ def self.create_converters(task, schema)
             column_name   = column[:name]
             embulk_type   = column[:type]
             column_option = column_options_map[column_name] || {}
+            scale         = column_option['scale'] || DEFAULT_SCALE
             self.new(
               embulk_type, column_option['type'],
               timestamp_format: column_option['timestamp_format'],
               timezone: column_option['timezone'],
               strict: column_option['strict'],
               default_timestamp_format: default_timestamp_format,
               default_timezone: default_timezone,
+              scale: scale
             ).create_converter
           end
         end
@@ -46,7 +50,8 @@ def initialize(
           embulk_type, type = nil,
           timestamp_format: nil, timezone: nil, strict: nil,
           default_timestamp_format: DEFAULT_TIMESTAMP_FORMAT,
-          default_timezone: DEFAULT_TIMEZONE
+          default_timezone: DEFAULT_TIMEZONE,
+          scale: DEFAULT_SCALE
         )
           @embulk_type      = embulk_type
           @type             = (type || Helper.bq_type_from_embulk_type(embulk_type)).upcase
@@ -55,6 +60,7 @@ def initialize(
           @timezone         = timezone || default_timezone
           @zone_offset      = TimeWithZone.zone_offset(@timezone)
           @strict           = strict.nil? ? true : strict
+          @scale            = scale
         end
 
         def create_converter
@@ -231,6 +237,13 @@ def string_converter
                 JSON.parse(val)
               end
             }
+          when 'NUMERIC'
+            Proc.new {|val|
+              next nil if val.nil?
+              with_typecast_error(val) do |val|
+                BigDecimal(val).round(@scale, BigDecimal::ROUND_CEILING)
+              end
+            }
           else
             raise NotSupportedType, "cannot take column type #{type} for string column"
           end