Updating repo structure

.gitignore

@@ -0,0 +1 @@
+.DS_Store

Northwind_populate_data.py

@@ -1,94 +0,0 @@
-from datetime import timedelta, datetime
-from random import randint
-from random import choice as rc
-import sqlite3
-
-
-# This function will return a random datetime between two datetime objects.
-def random_date(start, end):
-  return start + timedelta(seconds=randint(0, int((end - start).total_seconds())))
-
-# Connect to the DB
-conn = sqlite3.connect('Northwind.sqlite')
-c = conn.cursor()
-
-# ShipName, ShipAddress, ShipCity, ShipRegion, ShipPostalCode
-c.execute("select distinct ShipName, ShipAddress, ShipCity, ShipRegion, ShipPostalCode, ShipCountry from [Order]")
-locations = [(row[0], row[1], row[2], row[3], row[4], row[5]) for row in c.fetchall()]
-
-# Customer.Id
-c.execute("select distinct id from [Employee]")
-employees = [row[0] for row in c.fetchall()]
-
-# Shipper.Id
-c.execute("select distinct id from [Shipper]")
-shippers = [row[0] for row in c.fetchall()]
-
-# Customer.Id
-c.execute("select distinct id from [Customer]")
-customers = [row[0] for row in c.fetchall()]
-
-# Create a bunch of new orders
-for i in range(randint(15000,16000)):
-  sql = 'INSERT INTO [Order] (CustomerId, EmployeeId, OrderDate, RequiredDate, ShippedDate, ShipVia, Freight, ShipName, ShipAddress, ShipCity, ShipRegion, ShipPostalCode, ShipCountry) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)'
-  location = rc(locations)
-  order_date = random_date(datetime.strptime('2012-07-10', '%Y-%m-%d'), datetime.today())
-  required_date = random_date(order_date, order_date+timedelta(days=randint(14,60)))
-  shipped_date = random_date(order_date, order_date+timedelta(days=randint(1,30)))
-  params = (
-    rc(customers),  # CustomerId
-    rc(employees),  # EmployeeId
-    order_date,     # OrderDate
-    required_date,  # RequiredDate
-    shipped_date,   # ShippedDate
-    rc(shippers),   # ShipVia
-    0.00,           # Freight
-    location[0],    # ShipName
-    location[1],    # ShipAddress
-    location[2],    # ShipCity
-    location[3],    # ShipRegion
-    location[4],    # ShipPostalCode
-    location[5],    # ShipCountry
-  )
-  c.execute(sql,params)
-
-
-# Product.Id
-c.execute("select distinct id, UnitPrice from [Product]")
-products = [(row[0], row[1]) for row in c.fetchall()]
-
-# Order.Id
-c.execute("select distinct id from [Order] where Freight = 0.00")
-orders = [row[0] for row in c.fetchall()]
-
-# Fill the order with items
-for order in orders:
-  used = []
-  for x in range(randint(1,len(products))):
-    sql = 'INSERT INTO [OrderDetail] (Id, OrderId, ProductId, UnitPrice, Quantity, Discount) VALUES (?, ?, ?, ?, ?, ?)'
-    control = 1
-    while control:
-      product = rc(products)
-      if product not in used:
-        used.append(product)
-        control = 0
-    params = (
-      "%s/%s" % (order, product[0]),
-      order,          # OrderId
-      product[0],     # ProductId
-      product[1],     # UnitPrice
-      randint(1,50),  # Quantity
-      0,              # Discount
-    )
-    c.execute(sql,params)
-
-# Cleanup
-# c.execute('update [Order] set OrderDate = date(OrderDate), RequiredDate = date(RequiredDate), ShippedDate = date(ShippedDate)')
-c.execute("select sum(Quantity)*0.25+10, OrderId from [OrderDetail] group by OrderId")
-orders = [(row[0],row[1]) for row in c.fetchall()]
-for order in orders:
-  c.execute("update [Order] set Freight=? where Id=?", (order[0], order[1]))
-
-
-conn.commit()
-conn.close()

README.md

@@ -1,9 +1,39 @@
-# northwind-SQLite3
+# Northwind-SQLite3
 
 This is a version of the Microsoft Access 2000 Northwind sample database, re-engineered for SQLite3.
 
 The Northwind sample database was provided with Microsoft Access as a tutorial schema for managing small business customers, orders, inventory, purchasing, suppliers, shipping, and employees. Northwind is an excellent tutorial schema for a small-business ERP, with customers, orders, inventory, purchasing, suppliers, shipping, employees, and single-entry accounting.
 
-All the TABLES and VIEWS from the MSSQL-2000 version have been converted to Sqlite3 and included here. Also included are two versions prepopulated with data - a small verison and a large version. Should you decide to, you can use the included python script to pump the database full of more data.
+All the TABLES and VIEWS from the MSSQL-2000 version have been converted to Sqlite3 and included here. Included is a single version prepopulated with data. Should you decide to, you can use the included python script to pump the database full of more data.
 
-![alt tag](https://raw.githubusercontent.com/jpwhite3/northwind-SQLite3/master/Northwind_ERD.png)
+[Download here](https://raw.githubusercontent.com/jpwhite3/northwind-SQLite3/master/dist/northwind.db)
+
+# Structure
+
+![alt tag](https://raw.githubusercontent.com/jpwhite3/northwind-SQLite3/master/images/Northwind_ERD.png)
+
+# Build Instructions
+
+## Prerequisites
+
+- You are running in a unix-like environment (Linux, MacOS)
+- Python 3.6 or higher (`python3 --version`)
+- SQLite3 installed `sqlite3 -help`
+
+## Build
+
+```bash
+make build  # Creates database at ./dist/northwind.db
+```
+
+## Populate with more data
+
+```bash
+make populate
+```
+
+## Print report of row counts
+
+```bash
+make report
+```

makefile

@@ -0,0 +1,23 @@
+.PHONY: clean build run
+.DEFAULT_GOAL := build
+
+
+bootstrap:
+	brew install sqlite
+	brew install graphviz
+
+clean:
+	rm -rf ./dist
+	mkdir ./dist
+
+build: clean
+	sqlite3 dist/northwind.db < src/create.sql > /dev/null
+	sqlite3 dist/northwind.db < src/update.sql > /dev/null
+	sqlite3 dist/northwind.db < src/report.sql
+
+populate:
+	python3 ./src/populate.py
+	sqlite3 dist/northwind.db < src/report.sql
+
+report:
+	sqlite3 dist/northwind.db < src/report.sql

src/create.sql

@@ -1,6 +1,3 @@
--- Valon Hoti @ 2010-07-04 [YYYY-MM-DD]
--- Prishtine,10000
--- KOSOVE
 -- DATABASE : Northwind 
 -- ORIGIN   : MS SQL 
 -- SOURCE   : SQLITE 3
@@ -8,8 +5,6 @@
 -- Converted TABLES and VIEWS from MS SQL 2000  to Sqlite 3 
 -- 
 
--- Modified by Len Boyette @ 2013-02-08
--- Added foreign keys
 PRAGMA foreign_keys=off;
 
 -- Categories

src/populate.py

@@ -0,0 +1,101 @@
+from datetime import timedelta, datetime
+from random import randint
+from random import choice as rc
+import sqlite3
+
+
+# This function will return a random datetime between two datetime objects.
+def random_date(start, end):
+    return start + timedelta(seconds=randint(0, int((end - start).total_seconds())))
+
+
+# Connect to the DB
+conn = sqlite3.connect("./dist/northwind.db")
+c = conn.cursor()
+
+# ShipName, ShipAddress, ShipCity, ShipRegion, ShipPostalCode
+c.execute(
+    "select distinct ShipName, ShipAddress, ShipCity, ShipRegion, ShipPostalCode, ShipCountry from [Orders]"
+)
+locations = [(row[0], row[1], row[2], row[3], row[4], row[5]) for row in c.fetchall()]
+
+# Customer.Id
+c.execute("select distinct EmployeeId from [Employees]")
+employees = [row[0] for row in c.fetchall()]
+
+# Shipper.Id
+c.execute("select distinct ShipperId from [Shippers]")
+shippers = [row[0] for row in c.fetchall()]
+
+# Customer.Id
+c.execute("select distinct CustomerId from [Customers]")
+customers = [row[0] for row in c.fetchall()]
+
+# Create a bunch of new orders
+for i in range(randint(15000, 16000)):
+    sql = "INSERT INTO [Orders] (CustomerId, EmployeeId, OrderDate, RequiredDate, ShippedDate, ShipVia, Freight, ShipName, ShipAddress, ShipCity, ShipRegion, ShipPostalCode, ShipCountry) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)"
+    location = rc(locations)
+    order_date = random_date(
+        datetime.strptime("2012-07-10", "%Y-%m-%d"), datetime.today()
+    )
+    required_date = random_date(
+        order_date, order_date + timedelta(days=randint(14, 60))
+    )
+    shipped_date = random_date(order_date, order_date + timedelta(days=randint(1, 30)))
+    params = (
+        rc(customers),  # CustomerId
+        rc(employees),  # EmployeeId
+        order_date,  # OrderDate
+        required_date,  # RequiredDate
+        shipped_date,  # ShippedDate
+        rc(shippers),  # ShipVia
+        0.00,  # Freight
+        location[0],  # ShipName
+        location[1],  # ShipAddress
+        location[2],  # ShipCity
+        location[3],  # ShipRegion
+        location[4],  # ShipPostalCode
+        location[5],  # ShipCountry
+    )
+    c.execute(sql, params)
+
+
+# Product.Id
+c.execute("select distinct ProductId, UnitPrice from [Products]")
+products = [(row[0], row[1]) for row in c.fetchall()]
+
+# Order.Id
+c.execute("select distinct OrderId from [Orders] where Freight = 0.00")
+orders = [row[0] for row in c.fetchall()]
+
+# Fill the order with items
+for order in orders:
+    used = []
+    for x in range(randint(1, len(products))):
+        sql = "INSERT INTO [Order Details] (OrderId, ProductId, UnitPrice, Quantity, Discount) VALUES (?, ?, ?, ?, ?)"
+        control = 1
+        while control:
+            product = rc(products)
+            if product not in used:
+                used.append(product)
+                control = 0
+        params = (
+            # "%s/%s" % (order, product[0]),
+            order,  # OrderId
+            product[0],  # ProductId
+            product[1],  # UnitPrice
+            randint(1, 50),  # Quantity
+            0,  # Discount
+        )
+        c.execute(sql, params)
+
+# Cleanup
+# c.execute('update [Order] set OrderDate = date(OrderDate), RequiredDate = date(RequiredDate), ShippedDate = date(ShippedDate)')
+c.execute("select sum(Quantity)*0.25+10, OrderId from [Order Details] group by OrderId")
+orders = [(row[0], row[1]) for row in c.fetchall()]
+for order in orders:
+    c.execute("update [Orders] set Freight=? where OrderId=?", (order[0], order[1]))
+
+
+conn.commit()
+conn.close()

src/report.sql

@@ -0,0 +1,13 @@
+select "Categories", count(*) from [Categories];
+select "CustomerCustomerDemo", count(*) from [CustomerCustomerDemo];
+select "CustomerDemographics", count(*) from [CustomerDemographics];
+select "Customers", count(*) from [Customers];
+select "EmployeeTerritories", count(*) from [EmployeeTerritories];
+select "Employees", count(*) from [Employees];
+select "Details", count(*) from [Order Details];
+select "Orders", count(*) from [Orders];
+select "Products", count(*) from [Products];
+select "Regions", count(*) from [Regions];
+select "Shippers", count(*) from [Shippers];
+select "Suppliers", count(*) from [Suppliers];
+select "Territories", count(*) from [Territories];

src/update.sql

@@ -22,8 +22,8 @@ update [Customers] set Region='Scandinavia' where Country='Finland';
 
 update [Employees] set Region='British Isles' where Country='UK';
 update [Employees] set Region='North America' where Country='USA';
-update [Employees] set BirthDate = date(BirthDate,'+16 year');
-update [Employees] set HireDate = date(HireDate,'+16 year');
+update [Employees] set BirthDate = date(BirthDate,'+20 year');
+update [Employees] set HireDate = date(HireDate,'+20 year');
 
 update [Orders] set ShipRegion='British Isles' where ShipCountry='UK';
 update [Orders] set ShipRegion='British Isles' where ShipCountry='Ireland';
@@ -47,9 +47,9 @@ update [Orders] set ShipRegion='Western Europe' where ShipCountry='Austria';
 update [Orders] set ShipRegion='Scandinavia' where ShipCountry='Norway';
 update [Orders] set ShipRegion='Scandinavia' where ShipCountry='Finland';
 
-update [Orders] set OrderDate = date(OrderDate,'+16 year');
-update [Orders] set RequiredDate = date(RequiredDate,'+16 year');
-update [Orders] set ShippedDate = date(ShippedDate,'+16 year');
+update [Orders] set OrderDate = date(OrderDate,'+20 year');
+update [Orders] set RequiredDate = date(RequiredDate,'+20 year');
+update [Orders] set ShippedDate = date(ShippedDate,'+20 year');
 
 update [Suppliers] set Region='British Isles' where Country='UK';
 update [Suppliers] set Region='British Isles' where Country='Ireland';