From b16b5db3f7e88056c161cdd0fb1d97bba6afdf61 Mon Sep 17 00:00:00 2001
From: lila <beiweitemderbeste@protonmail.com>
Date: Sun, 5 Apr 2026 01:21:32 +0200
Subject: [PATCH] updating data models

---
 packages/db/src/db/schema.ts     | 69 +++++++++++++++++++-------------
 packages/shared/src/constants.ts |  4 +-
 2 files changed, 45 insertions(+), 28 deletions(-)

diff --git a/packages/db/src/db/schema.ts b/packages/db/src/db/schema.ts
index d78e20a..cbc2e34 100644
--- a/packages/db/src/db/schema.ts
+++ b/packages/db/src/db/schema.ts
@@ -13,14 +13,20 @@ import {
 
 import { sql } from "drizzle-orm";
 
-import { SUPPORTED_POS, SUPPORTED_LANGUAGE_CODES } from "@glossa/shared";
+import {
+  SUPPORTED_POS,
+  SUPPORTED_LANGUAGE_CODES,
+  CEFR_LEVELS,
+} from "@glossa/shared";
 
 export const terms = pgTable(
   "terms",
   {
     id: uuid().primaryKey().defaultRandom(),
-    synset_id: text().unique().notNull(),
+    source: varchar({ length: 50 }), // 'omw', 'wiktionary', null for manual
+    source_id: text(), // synset_id value for omw, wiktionary QID, etc.
     pos: varchar({ length: 20 }).notNull(),
+    cefr_level: varchar({ length: 2 }),
     created_at: timestamp({ withTimezone: true }).defaultNow().notNull(),
   },
   (table) => [
@@ -28,31 +34,12 @@ export const terms = pgTable(
       "pos_check",
       sql`${table.pos} IN (${sql.raw(SUPPORTED_POS.map((p) => `'${p}'`).join(", "))})`,
     ),
-    index("idx_terms_pos").on(table.pos),
-  ],
-);
-// sql.raw() is safe here: SUPPORTED_POS is a compile-time constant from @glossa/shared,
-// not user input. If you're refactoring this, make sure the values still come from that
-// constant and never from a runtime/user-controlled source.
-
-export const translations = pgTable(
-  "translations",
-  {
-    id: uuid().primaryKey().defaultRandom(),
-    term_id: uuid()
-      .notNull()
-      .references(() => terms.id, { onDelete: "cascade" }),
-    language_code: varchar({ length: 10 }).notNull(),
-    text: text().notNull(),
-    created_at: timestamp({ withTimezone: true }).defaultNow().notNull(),
-  },
-  (table) => [
-    unique("unique_translations").on(
-      table.term_id,
-      table.language_code,
-      table.text,
+    check(
+      "cefr_check",
+      sql`${table.cefr_level} IN (${sql.raw(CEFR_LEVELS.map((p) => `'${p}'`).join(", "))})`,
     ),
-    index("idx_translations_lang").on(table.language_code, table.term_id),
+    unique("unique_source_id").on(table.source, table.source_id),
+    index("idx_terms_source_pos").on(table.source, table.pos),
   ],
 );
 
@@ -73,7 +60,35 @@ export const term_glosses = pgTable(
       table.language_code,
       table.text,
     ),
-    index("idx_term_glosses_term").on(table.term_id),
+    check(
+      "language_code_check",
+      sql`${table.language_code} IN (${sql.raw(SUPPORTED_LANGUAGE_CODES.map((l) => `'${l}'`).join(", "))})`,
+    ),
+  ],
+);
+
+export const translations = pgTable(
+  "translations",
+  {
+    id: uuid().primaryKey().defaultRandom(),
+    term_id: uuid()
+      .notNull()
+      .references(() => terms.id, { onDelete: "cascade" }),
+    language_code: varchar({ length: 10 }).notNull(),
+    text: text().notNull(),
+    created_at: timestamp({ withTimezone: true }).defaultNow().notNull(),
+  },
+  (table) => [
+    unique("unique_translations").on(
+      table.term_id,
+      table.language_code,
+      table.text,
+    ),
+    check(
+      "language_code_check",
+      sql`${table.language_code} IN (${sql.raw(SUPPORTED_LANGUAGE_CODES.map((l) => `'${l}'`).join(", "))})`,
+    ),
+    index("idx_translations_lang").on(table.language_code, table.term_id),
   ],
 );
 
diff --git a/packages/shared/src/constants.ts b/packages/shared/src/constants.ts
index 26b5467..416aff4 100644
--- a/packages/shared/src/constants.ts
+++ b/packages/shared/src/constants.ts
@@ -1,5 +1,7 @@
 export const SUPPORTED_LANGUAGE_CODES = ["en", "it"] as const;
 
-export const SUPPORTED_POS = ["noun"] as const;
+export const SUPPORTED_POS = ["noun", "verb"] as const;
 
 export const GAME_ROUNDS = ["3", "10"] as const;
+
+export const CEFR_LEVELS = ["A1", "A2", "B1", "B2", "C1", "C2"] as const;