Analysis of keywords in few popular languages

keyword_stats.py

"""
Analyzing keywords from different programming languages.
"""

def word_stats(words):
    count = len(words)
    len_sum = sum(map(len, words))
    return {
        'count': count,
        'total_chars': len_sum,
        'average_length': len_sum / float(count)
    }


# Python
python_keywords = """
and       del       from      not       while
as        elif      global    or        with
assert    else      if        pass      yield
break     except    import    print
class     exec      in        raise
continue  finally   is        return 
def       for       lambda    try
""".split()

# C++ (http://en.cppreference.com/w/cpp/keyword)
cpp_keywords = [k for k in """
alignas (since C++11)
alignof (since C++11)
and
and_eq
asm
auto(1)
bitand
bitor
bool
break
case
catch
char
char16_t(since C++11)
char32_t(since C++11)
class
compl
const
constexpr(since C++11)
const_cast
continue
decltype(since C++11)
default(1)
delete(1)
do
double
dynamic_cast
else
enum
explicit
export
extern
false
float
for
friend
goto
if
inline
int
long
mutable
namespace
new
noexcept(since C++11)
not
not_eq
nullptr (since C++11)
operator
or
or_eq
private
protected
public
register
reinterpret_cast
return
short
signed
sizeof
static
static_assert(since C++11)
static_cast
struct
switch
template
this
thread_local(since C++11)
throw
true
try
typedef
typeid
typename
union
unsigned
using(1)
virtual
void
volatile
wchar_t
while
xor
xor_eq 
""".splitlines() if len(k.strip()) > 0]
cpp11_keywords = [k[:k.find('(')] if '(' in k else k
                  for k in cpp_keywords]
cpp03_keywords = [k for i, k in enumerate(cpp11_keywords)
                   if '11' not in cpp_keywords[i]]

# Java (http://docs.oracle.com/javase/tutorial/java/nutsandbolts/_keywords.html)
java_keywords = [w.strip('*') for w in """
abstract    continue    for     new     switch
assert***   default     goto*   package     synchronized
boolean     do  if  private     this
break   double  implements  protected   throw
byte    else    import  public  throws
case    enum****    instanceof  return  transient
catch   extends     int     short   try
char    final   interface   static  void
class   finally     long    strictfp**  volatile
const*  float   native  super   while
""".split()]

# C (http://msdn.microsoft.com/en-us/library/befeaky0.aspx)
c_keywords = """
auto
double
int
struct
break
else
long
switch
case
enum
register
typedef
char
extern
return
union
const
float
short
unsigned
continue
for
signed
void
default
goto
sizeof
volatile
do
if
static
while
""".split()

# C# (http://msdn.microsoft.com/en-us/library/x53a06bb%28v=vs.71%29.aspx)
cs_keywords = """
abstract    event   new     struct
as  explicit    null    switch
base    extern  object  this
bool    false   operator    throw
break   finally     out     true
byte    fixed   override    try
case    float   params  typeof
catch   for     private     uint
char    foreach     protected   ulong
checked     goto    public  unchecked
class   if  readonly    unsafe
const   implicit    ref     ushort
continue    in  return  using
decimal     int     sbyte   virtual
default     interface   sealed  volatile
delegate    internal    short   void
do  is  sizeof  while
double  lock    stackalloc   
else    long    static   
enum    namespace   string   
""".split()

# Go (http://golang.org/ref/spec#Keywords)
go_keywords = """
break        default      func         interface    select
case         defer        go           map          struct
chan         else         goto         package      switch
const        fallthrough  if           range        type
continue     for          import       return       var
""".split()


if __name__ == '__main__':
    print "Python 2.7:", word_stats(python_keywords)
    print "C++03:", word_stats(cpp03_keywords)
    print "C++11:", word_stats(cpp11_keywords)
    print "Java 1.7:", word_stats(java_keywords)
    print "C:", word_stats(c_keywords)
    print "C# 4.0:", word_stats(cs_keywords)
    print "Go:", word_stats(go_keywords)