From 41f10c18cf4b8be481370b9cc2190b1f8a487bc5 Mon Sep 17 00:00:00 2001
From: Dylan De Faoite <dylanseandefaoite@gmail.com>
Date: Tue, 24 Feb 2026 14:13:41 +0000
Subject: [PATCH] feat: add nlp cols to database schema

---
 db/database.py |  3 +++
 db/schema.sql  | 48 ++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 45 insertions(+), 6 deletions(-)

diff --git a/db/database.py b/db/database.py
index f06dcde..4f2209e 100644
--- a/db/database.py
+++ b/db/database.py
@@ -30,6 +30,7 @@ class PostgresConnector:
             cursor.executemany(query, param_list)
             self.connection.commit()
 
+    ## User Management Methods
     def save_user(self, username, email, password_hash):
         query = """
             INSERT INTO users (username, email, password_hash)
@@ -46,6 +47,8 @@ class PostgresConnector:
         query = "SELECT id, username, email, password_hash FROM users WHERE email = %s"
         result = self.execute(query, (email,), fetch=True)
         return result[0] if result else None
+    
+    # Dataset Management Methods
 
     def close(self):
         if self.connection:
diff --git a/db/schema.sql b/db/schema.sql
index e4551d5..d7c8636 100644
--- a/db/schema.sql
+++ b/db/schema.sql
@@ -6,30 +6,66 @@ CREATE TABLE users (
     created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
 );
 
-CREATE TABLE has_access (
+CREATE TABLE datasets (
     id SERIAL PRIMARY KEY,
     user_id INTEGER NOT NULL,
-    post_id INTEGER NOT NULL,
-    FOREIGN KEY (user_id) REFERENCES users(id) ON DELETE CASCADE,
-    FOREIGN KEY (post_id) REFERENCES posts(id) ON DELETE CASCADE
+    name VARCHAR(255) NOT NULL,
+    description TEXT,
+    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+    nlp_completed BOOLEAN DEFAULT FALSE,
+    FOREIGN KEY (user_id) REFERENCES users(id) ON DELETE CASCADE
 );
 
 CREATE TABLE posts (
     id SERIAL PRIMARY KEY,
+    dataset_id INTEGER NOT NULL,
+
     author VARCHAR(255) NOT NULL,
     title VARCHAR(255) NOT NULL,
     content TEXT NOT NULL,
     created_at TIMESTAMP NOT NULL,
-    source VARCHAR(255) NOT NULL
+    source VARCHAR(255) NOT NULL,
+
+    topic VARCHAR(255),
+    topic_confidence FLOAT,
+
+    ner_entities JSONB,
+
+    emotion_anger FLOAT,
+    emotion_disgust FLOAT,
+    emotion_fear FLOAT,
+    emotion_joy FLOAT,
+    emotion_neutral FLOAT,
+    emotion_sadness FLOAT,
+    emotion_surprise FLOAT,
+
+    FOREIGN KEY (dataset_id) REFERENCES datasets(id) ON DELETE CASCADE
 );
 
 CREATE TABLE comments (
     id SERIAL PRIMARY KEY,
+    dataset_id INTEGER NOT NULL,
+
     post_id INTEGER NOT NULL,
     author VARCHAR(255) NOT NULL,
     content TEXT NOT NULL,
     created_at TIMESTAMP NOT NULL,
     reply_to VARCHAR(255),
     source VARCHAR(255) NOT NULL,
-    FOREIGN KEY (post_id) REFERENCES posts(id) ON DELETE CASCADE
+
+    topic VARCHAR(255),
+    topic_confidence FLOAT,
+
+    ner_entities JSONB,
+
+    emotion_anger FLOAT,
+    emotion_disgust FLOAT,
+    emotion_fear FLOAT,
+    emotion_joy FLOAT,
+    emotion_neutral FLOAT,
+    emotion_sadness FLOAT,
+    emotion_surprise FLOAT,
+
+    FOREIGN KEY (post_id) REFERENCES posts(id) ON DELETE CASCADE,
+    FOREIGN KEY (dataset_id) REFERENCES datasets(id) ON DELETE CASCADE
 );
\ No newline at end of file