From 6f46b1be7c85aac4416962deab431b9d85da51ad Mon Sep 17 00:00:00 2001
From: maddiebaka <madeline@cray.lgbt>
Date: Thu, 12 Oct 2023 20:02:10 -0400
Subject: [PATCH] Add parts of speech model and database ingest rake task

---
 .../20231012235050_create_part_of_speeches.rb | 10 +++++++++
 db/schema.rb                                  | 21 +++++++++++++++++++
 lib/tasks/database.rake                       | 21 +++++++++++++++++++
 3 files changed, 52 insertions(+)
 create mode 100644 db/migrate/20231012235050_create_part_of_speeches.rb
 create mode 100644 db/schema.rb
 create mode 100644 lib/tasks/database.rake

diff --git a/db/migrate/20231012235050_create_part_of_speeches.rb b/db/migrate/20231012235050_create_part_of_speeches.rb
new file mode 100644
index 0000000..2001787
--- /dev/null
+++ b/db/migrate/20231012235050_create_part_of_speeches.rb
@@ -0,0 +1,10 @@
+class CreatePartOfSpeeches < ActiveRecord::Migration[7.1]
+  def change
+    create_table :part_of_speeches do |t|
+      t.string :pos
+      t.string :definition
+
+      t.timestamps
+    end
+  end
+end
diff --git a/db/schema.rb b/db/schema.rb
new file mode 100644
index 0000000..c56b2b4
--- /dev/null
+++ b/db/schema.rb
@@ -0,0 +1,21 @@
+# This file is auto-generated from the current state of the database. Instead
+# of editing this file, please use the migrations feature of Active Record to
+# incrementally modify your database, and then regenerate this schema definition.
+#
+# This file is the source Rails uses to define your schema when running `bin/rails
+# db:schema:load`. When creating a new database, `bin/rails db:schema:load` tends to
+# be faster and is potentially less error prone than running all of your
+# migrations from scratch. Old migrations may fail to apply correctly if those
+# migrations use external dependencies or application code.
+#
+# It's strongly recommended that you check this file into your version control system.
+
+ActiveRecord::Schema[7.1].define(version: 2023_10_12_235050) do
+  create_table "part_of_speeches", force: :cascade do |t|
+    t.string "pos"
+    t.string "definition"
+    t.datetime "created_at", null: false
+    t.datetime "updated_at", null: false
+  end
+
+end
diff --git a/lib/tasks/database.rake b/lib/tasks/database.rake
new file mode 100644
index 0000000..0ee2072
--- /dev/null
+++ b/lib/tasks/database.rake
@@ -0,0 +1,21 @@
+namespace :database do
+  desc "TODO"
+  task ingest: :environment do
+    ingest_data
+  end
+
+end
+
+def ingest_data
+  if PartOfSpeech.count > 0
+    puts "Data already exists in table! Aborting."
+    return
+  end
+
+  parts_of_speech = JSON.parse(File.read('db/dataset_en/toki-partsofspeech.json'))
+
+  parts_of_speech.each do |pos|
+    PartOfSpeech.create(pos: pos['pos'], definition: pos['definition'])
+  end
+  puts "Ingest complete."
+end