fix: Rebuilt SExI after Tim's mince pie incident — tables, queries & tests included

calculate_largest_expensors.sql

@@ -0,0 +1,35 @@
+-- =============================================================================
+-- Task 5: Calculate the largest expensors (> 1000 threshold)
+-- =============================================================================
+-- Reports employees whose total expensed amount exceeds 1000, along with
+-- their manager's details. Ordered by total_expensed_amount descending.
+--
+-- Expense totals in the current dataset:
+--   Alex Jacobson (3):   6.50*14 + 11.00*20 + 22.00*18 + 13.00*75 = 1682.00
+--   Darren Poynton (4):  40.00 * 9  = 360.00
+--   Andrea Ghibaudi (9): 300.00 * 1 = 300.00
+--   Umberto Torrielli (2): 17.50 * 4 = 70.00
+--
+-- Only Alex Jacobson exceeds the 1000 threshold.
+-- =============================================================================
+
+USE memory.default;
+
+SELECT
+    emp.employee_id,
+    CONCAT(emp.first_name, ' ', emp.last_name)  AS employee_name,
+    emp.manager_id,
+    CONCAT(mgr.first_name, ' ', mgr.last_name)  AS manager_name,
+    expense_totals.total_expensed_amount
+FROM (
+    -- Aggregate each employee's expenses: unit_price * quantity per line item
+    SELECT
+        ex.employee_id,
+        SUM(ex.unit_price * ex.quantity)         AS total_expensed_amount
+    FROM EXPENSE ex
+    GROUP BY ex.employee_id
+    HAVING SUM(ex.unit_price * ex.quantity) > 1000
+) expense_totals
+JOIN EMPLOYEE emp ON expense_totals.employee_id = emp.employee_id
+JOIN EMPLOYEE mgr ON emp.manager_id = mgr.employee_id
+ORDER BY expense_totals.total_expensed_amount DESC;

create_employees.sql

@@ -0,0 +1,33 @@
+-- =============================================================================
+-- Task 1: Create the EMPLOYEE table
+-- =============================================================================
+-- Loads employee data from hr/employee_index.csv into the SExI database.
+-- employee_id and manager_id are typed as TINYINT per the specification.
+-- All other columns retain their natural VARCHAR type.
+--
+-- DROP TABLE IF EXISTS ensures this script is idempotent and can be re-run
+-- without needing to restart the Trino container.
+-- =============================================================================
+
+USE memory.default;
+
+DROP TABLE IF EXISTS EMPLOYEE;
+
+CREATE TABLE EMPLOYEE (
+    employee_id TINYINT,
+    first_name  VARCHAR,
+    last_name   VARCHAR,
+    job_title   VARCHAR,
+    manager_id  TINYINT
+);
+
+INSERT INTO EMPLOYEE VALUES
+    (CAST(1 AS TINYINT), 'Ian',      'James',     'CEO',           CAST(4 AS TINYINT)),
+    (CAST(2 AS TINYINT), 'Umberto',  'Torrielli', 'CSO',           CAST(1 AS TINYINT)),
+    (CAST(3 AS TINYINT), 'Alex',     'Jacobson',  'MD EMEA',       CAST(2 AS TINYINT)),
+    (CAST(4 AS TINYINT), 'Darren',   'Poynton',   'CFO',           CAST(2 AS TINYINT)),
+    (CAST(5 AS TINYINT), 'Tim',      'Beard',     'MD APAC',       CAST(2 AS TINYINT)),
+    (CAST(6 AS TINYINT), 'Gemma',    'Dodd',      'COS',           CAST(1 AS TINYINT)),
+    (CAST(7 AS TINYINT), 'Lisa',     'Platten',   'CHR',           CAST(6 AS TINYINT)),
+    (CAST(8 AS TINYINT), 'Stefano',  'Camisaca',  'GM Activation', CAST(2 AS TINYINT)),
+    (CAST(9 AS TINYINT), 'Andrea',   'Ghibaudi',  'MD NAM',        CAST(2 AS TINYINT));

create_expenses.sql

@@ -0,0 +1,41 @@
+-- =============================================================================
+-- Task 2: Create the EXPENSE table
+-- =============================================================================
+-- Loads expense receipts from finance/receipts_from_last_night/ into SExI.
+-- Employee names are resolved to their employee_id from the EMPLOYEE table.
+--
+-- Source receipts and their mappings:
+--   drinkies.txt            -> Alex Jacobson   (employee_id = 3)  6.50  x 14
+--   drinks.txt              -> Alex Jacobson   (employee_id = 3)  11.00 x 20
+--   drinkss.txt             -> Alex Jacobson   (employee_id = 3)  22.00 x 18
+--   duh_i_think_i_got_..    -> Alex Jacobson   (employee_id = 3)  13.00 x 75
+--   i_got_lost_on_the_..    -> Andrea Ghibaudi (employee_id = 9)  300.00 x 1
+--   ubers.txt               -> Darren Poynton  (employee_id = 4)  40.00 x 9
+--   we_stopped_for_a_..     -> Umberto Torrielli (employee_id = 2) 17.50 x 4
+-- =============================================================================
+
+USE memory.default;
+
+DROP TABLE IF EXISTS EXPENSE;
+
+CREATE TABLE EXPENSE (
+    employee_id TINYINT,
+    unit_price  DECIMAL(8, 2),
+    quantity    TINYINT
+);
+
+INSERT INTO EXPENSE VALUES
+    -- drinkies.txt: Alex Jacobson - "Drinks, lots of drinks"
+    (CAST(3 AS TINYINT), CAST(6.50  AS DECIMAL(8,2)), CAST(14 AS TINYINT)),
+    -- drinks.txt: Alex Jacobson - "More Drinks"
+    (CAST(3 AS TINYINT), CAST(11.00 AS DECIMAL(8,2)), CAST(20 AS TINYINT)),
+    -- drinkss.txt: Alex Jacobson - "So Many Drinks!"
+    (CAST(3 AS TINYINT), CAST(22.00 AS DECIMAL(8,2)), CAST(18 AS TINYINT)),
+    -- duh_i_think_i_got_too_many.txt: Alex Jacobson - "I bought everyone in the bar a drink!"
+    (CAST(3 AS TINYINT), CAST(13.00 AS DECIMAL(8,2)), CAST(75 AS TINYINT)),
+    -- i_got_lost_on_the_way_home_and_now_im_in_mexico.txt: Andrea Ghibaudi
+    (CAST(9 AS TINYINT), CAST(300.00 AS DECIMAL(8,2)), CAST(1  AS TINYINT)),
+    -- ubers.txt: Darren Poynton - "Ubers to get us all home"
+    (CAST(4 AS TINYINT), CAST(40.00 AS DECIMAL(8,2)), CAST(9  AS TINYINT)),
+    -- we_stopped_for_a_kebabs.txt: Umberto Torrielli
+    (CAST(2 AS TINYINT), CAST(17.50 AS DECIMAL(8,2)), CAST(4  AS TINYINT));

create_invoices.sql

@@ -0,0 +1,65 @@
+-- =============================================================================
+-- Task 3: Create the SUPPLIER and INVOICE tables
+-- =============================================================================
+-- Loads supplier invoices from finance/invoices_due/ into SExI.
+--
+-- SUPPLIER table: supplier_id assigned alphabetically by company name:
+--   1 = Catering Plus
+--   2 = Dave's Discos
+--   3 = Entertainment tonight
+--   4 = Ice Ice Baby
+--   5 = Party Animals
+--
+-- INVOICE table: due_date is set to the last day of the month, calculated
+-- relative to the current date using the "N months from now" specification
+-- from each invoice file.
+--
+-- Note: The column name "invoice_ammount" preserves the spelling from the
+-- task specification (intentional typo retained for compatibility).
+-- =============================================================================
+
+USE memory.default;
+
+-- Drop in dependency order (INVOICE references SUPPLIER)
+DROP TABLE IF EXISTS INVOICE;
+DROP TABLE IF EXISTS SUPPLIER;
+
+-- Create the SUPPLIER reference table (IDs assigned alphabetically)
+CREATE TABLE SUPPLIER (
+    supplier_id TINYINT,
+    name        VARCHAR
+);
+
+INSERT INTO SUPPLIER VALUES
+    (CAST(1 AS TINYINT), 'Catering Plus'),
+    (CAST(2 AS TINYINT), 'Dave''s Discos'),
+    (CAST(3 AS TINYINT), 'Entertainment tonight'),
+    (CAST(4 AS TINYINT), 'Ice Ice Baby'),
+    (CAST(5 AS TINYINT), 'Party Animals');
+
+-- Create the INVOICE table with due dates as last day of the target month
+CREATE TABLE INVOICE (
+    supplier_id     TINYINT,
+    invoice_ammount DECIMAL(8, 2),
+    due_date        DATE
+);
+
+INSERT INTO INVOICE VALUES
+    -- brilliant_bottles.txt: Catering Plus - Champagne, Whiskey, Vodka, etc. (2 months)
+    (CAST(1 AS TINYINT), CAST(2000.00 AS DECIMAL(8,2)),
+        last_day_of_month(date_add('month', 2, current_date))),
+    -- crazy_catering.txt: Catering Plus - Pizzas, Burgers, Hotdogs, etc. (3 months)
+    (CAST(1 AS TINYINT), CAST(1500.00 AS DECIMAL(8,2)),
+        last_day_of_month(date_add('month', 3, current_date))),
+    -- disco_dj.txt: Dave's Discos - Dave, Dave Equipment (1 month)
+    (CAST(2 AS TINYINT), CAST(500.00  AS DECIMAL(8,2)),
+        last_day_of_month(date_add('month', 1, current_date))),
+    -- excellent_entertainment.txt: Entertainment tonight (3 months)
+    (CAST(3 AS TINYINT), CAST(6000.00 AS DECIMAL(8,2)),
+        last_day_of_month(date_add('month', 3, current_date))),
+    -- fantastic_ice_sculptures.txt: Ice Ice Baby - Ice Luge, sculpture (6 months)
+    (CAST(4 AS TINYINT), CAST(4000.00 AS DECIMAL(8,2)),
+        last_day_of_month(date_add('month', 6, current_date))),
+    -- awesome_animals.txt: Party Animals - Zebra, Lion, Giraffe, Hippo (3 months)
+    (CAST(5 AS TINYINT), CAST(6000.00 AS DECIMAL(8,2)),
+        last_day_of_month(date_add('month', 3, current_date)));