"""Strings.  
Material from Chapter 7
http://openbookproject.net/thinkcs/python/english2e/ch07.html
"""

# The bracket operator selects a single character from a string:

fruit = "banana"
letter = fruit[1]
print letter

# The expression fruit[1] selects the character with index 1 from fruit. 
# When we display letter, we get a surprise:
# a
# The letter with index 1 is not the first letter!
# Computer scientists always start counting from zero.
# A nice explanation is given at:
# http://www.cs.utexas.edu/~EWD/ewd08xx/EWD831.PDF
# (the writer is Edsger W. Dijkstra, one of the founding fathers
# of computer science)

# The len function returns the number of characters in a string:

fruit = "banana"
print len(fruit)

# Traversing the letters of a string can be done in two ways:

fruit = "banana"
for i in range(len(fruit)) :
    print fruit[i]

# or

fruit = "banana"
for character in fruit :
    print character

# we can extract a substring of a string using the bracket operator:

s = "python java perl"
print s[0:6]
print s[7:11]
print s[12:len(s)]
# these are called slices

# some shortcuts:
print s[:6]  # print a prefix of the string
print s[12:]  # print a suffix of the string

# what do you think s[:] would give?
print s[:]

def extract_every_2nd(s) :
    result = ''  # the empty string
    for i in range(0, len(s), 2) :
        result += s[i]
    return result

# It is tempting to use the bracket operator in order to modify
# a string.
greeting = "Hello, world!"
#greeting[0] = 'J'  # ERROR!

# strings are immutable, i.e. cannot be changed once created.

# you will have to create a new string with the desired modification:
greeting = "Hello, world!"
new_greeting = 'J' + greeting[1:]
print new_greeting

# The in operator

#The in operator tests if one string is a substring of another:
'p' in 'apple'
'i' in 'apple'
'ap' in 'apple'

# Note that a string is a substring of itself:
'apple' in 'apple'

def remove_vowels(s) :
    """a function that removes the vowels from a string"""
    vowels = "aeiouAEIOU"
    s_without_vowels = ""
    for letter in s:
        if letter not in vowels:
            s_without_vowels += letter
    return s_without_vowels


# the in operator only determines if a string is a substring of
# another one.  here's a function that also provides the index
# of the first occurrence:
# (the book gives a version with a while loop, and it only finds 
# the location of a single character)

def find(s, substr) :
    for index in range(len(s)) :
        if s[index:index+len(substr)] == substr:
            return index
    return -1

# here's a version that searches in s[start:end]
# we use default arguments to provide start and end
# as optional parameters

def find(s, substr, start=0, end=None) :
    if end is None :
        end = len(s)
    for index in range(start, end) :
        if s[index:index+len(substr)] == substr:
            return index
    return -1

# Exercise:  write a function that behaves like the
# range function, except that instead of returning a 
# list it prints the numbers in the range.

# the string module contains useful functions for manipulating strings.
# among other things, it includes our find function!

import string
help(string.find)
print string.find.__doc__

# let's write a function that determines if a character is lower case.

# here are three ways of doing so:

def is_lower(ch):
    return string.find(string.lowercase, ch) != -1

# notice the use of string.lowercase

# using the in operator:

def is_lower(ch):
    return ch in string.lowercase

# using the comparison operator:

def is_lower(ch):
    return 'a' <= ch <= 'z'

def is_lowercase(s) :
    """determine if a string is all lowercase characters"""
    for c in s :
        if not(c in string.lowercase) :
            return False
    return True

# Another constant defined in the string module may surprise you when you print it:

print string.whitespace

# Whitespace characters move the cursor without printing anything.