DEV Community

Cover image for Code Complete 2: Fundamental Data Types (Part 3)
Iyvonne Bett
Iyvonne Bett

Posted on • Edited on

Code Complete 2: Fundamental Data Types (Part 3)

In this blog post, I'll discuss the fundamental Data types in Steve McConnell's book Code Complete.

Chapter 12: Fundamental Data Types

Numbers in General
By replacing magic numbers with constants, changes are reliable, changes can be made easily, and your code is more readable.
Alt Text

Floating-Point Numbers

  • To increase accuracy when adding numbers with differing magnitudes, add them starting with the smallest values.
  • Avoid equality operations and anticipate rounding errors; cope by switching to greater precision, BCD, or integer variables.

Characters and Strings
To avoid endless strings in C, initialize strings to null, and use strncpy() instead of strcpy().

Enumerated Types

  • Use enumerated types for more type-checking, and as a richer alternative to boolean variables.
  • Explicitly assign their values to specify first and last values for iteration, and an invalid or "null" type.

Arrays
In C, use or define an ARRAY_LENGTH() macro as #define ARRAY_LENGTH(x) (sizeof(x) / sizeof(x[0])).

Creating Your Own Types
Don't name a type created using typedef after the underlying data type, and don't refer to predefined types.

Chapter 13: Unusual Data Types

Structures
By passing only one or two fields from a structure into a method, you promote information hiding from the method.

Pointers

  • Symptoms of pointer errors tend to be unrelated to causes of pointer errors.
  • By isolating pointer operations to methods, you minimize the possibility of propagating careless mistakes through your program.
  • Allocating dog tags allow you to check for freeing memory twice or overwriting memory beyond the last byte.
  • Free pointers at the same scoping level as they were allocated, such as in the same method, or a constructor/destructor pair.
  • Set a pointer to NULL after deallocation; writing to it produces an error, and deallocating twice is more easily caught.
  • In C++, a reference cannot point to NULL and the object it refers to cannot be changed.
  • In C, you can use char or void pointers for any type of variable.

Global Data

  • Passing a global variable to a method, and then referring to both the parameter and global variable is especially tricky.
  • Initialization order among different "translation units," or files, is not defined in languages like C++.
  • Try to contain a global variable as a class variable, and provide an accessor for any other code that needs it.
  • Replace global data with access methods to centralize control over it and protect yourself against changes.
  • Build access methods at the level of the problem domain rather than at the level of the implementation details.

My Key takeaways in these two chapters are;

  • Working with specific data types means remembering many individual rules for each type.
  • Creating your own types makes your programs easier to modify and more self-documenting, if your language supports that capability.
  • When you create a simple type using typedef or its equivalent, consider whether you should be creating a new class instead.
  • Structures can help make programs less complicated, easier to understand, and easier to maintain.
  • Whenever you consider using a structure, consider whether a class would work better.
  • Pointers are error-prone. Protect yourself by using access routines or classes and defensive-programming practices.
  • Avoid global variables, not just because they’re dangerous, but because you can replace them with something better.
  • If you can’t avoid global variables, work with them through access routines.
  • Access routines give you everything that global variables give you, and more.

Top comments (0)