#
# -- Useful Reference Syntax --------------
#
# Some special characters are:
#
# abc  Letters
# 123    Digits
# \d      Any Digit
# \D      Any Non-digit character
# .       Any Character
# \.      Period
# [abc]   Only a, b, or c
# [^abc]  Not a, b, nor c
# [a-z]   Characters a to z
# [0-9]   Numbers 0 to 9
# \w      Any Alphanumeric character
# \W      Any Non-alphanumeric character
# {m}     m Repetitions
# {m,n}   m to n Repetitions
# *       Zero or more repetitions
# +       One or more repetitions
# ?       Optional character
# \s      Any Whitespace
# \S      Any Non-whitespace character
# ^...$     Starts and ends
# (...)     Capture Group
# (a(bc)) Capture Sub-group
# (.*)    Capture all
# (abc|def)   Matches abc or def

import re   # Python Module For Regular Expression

example_string="""\
suraj singh bisht\
SURAJ SINGH BISHT\
surajsinghbisht054@gmail.com\
www.bitforestinfo.com\
yashwantsinghbisht054@gmail.com\
0124-100-125-2563\
124-586-9875\
This is an example text\
"""
# Meta Characters

# / Backslash
# ^ Caret
# $ Dollar Sign
# . Dot
# ? Question Mark
# * Asterisk
# | Pipe
# + Plus Sign
# ( Opening Parenthesis
# ) Closing Parenthesis
# [ Opening Square Bracket
# { The Opening Curly Brace

# Hmm, Now, You are wondering what are the usages of meta character.
# if i guess right then please try to rewind you memory and then you will find that
# many character from this list. we have already used in previous examples.
# For More Info Check my previous tutorials about regular expressions
#
# so, let's start this tutorial
#

# Unicode Flag Example
#
# Example 1.
#
string=u'सुरज सिनगह बिसहत'

pattern_unicode = ur'.+'

pattern = re.compile(pattern_unicode, re.UNICODE) # Using re.UNICODE Flag

result=pattern.search(string)
print result.group()

सुरज सिनगह बिसहत

# re.VERBOSE Flag Example
# Example 2.
#
pattern_string="""\d+  # the integral part
\W+           # Capture Whitespace
\d+           # Capture Digit
                   """
pattern=re.compile(pattern_string,re.VERBOSE)

result=pattern.search(example_string)


if result:
    print result.group(0)

0124-100

# Looking Behind and AHead
# (?=pattern) match ahead
# (?<=abc) Match Behind
# Example 3.
# match behind

pattern=re.compile('(?<=abc).{4}')

pattern.findall('abc-efg-hij-klm')

['-efg']

# match ahead
# (?=pattern) 
# Example 4.
#
pattern=re.compile('.{10}(?=klm)')

pattern.findall('abc-efg-hij-klm')

['c-efg-hij-']

# re.sub Works like a replace function but
# with power of regular expressions
# Example 5.
#
# re.sub(pattern, repl, string, count=0, flags=0)
#
pattern=re.compile('abc')

pattern.sub('xyz','abc-efg-hij-klm')

'xyz-efg-hij-klm'

#
# Example 6.
# 
pattern=re.compile('(\w\wc)')

pattern.sub('xyz','abc-efg-hij-klm')

'xyz-efg-hij-klm'

#
# Example 7.
#
string=u'सुरज 1 सिनगह 2 बिसहत'

pattern_unicode = ur'\d'

pattern = re.compile(pattern_unicode, re.UNICODE) # Using re.UNICODE Flag

print "Spliting  : ", pattern.split(string)
print "Replacing : ", pattern.sub('detected',string)

Spliting  :  [u'\u0938\u0941\u0930\u091c ', u' \u0938\u093f\u0928\u0917\u0939 ', u' \u092c\u093f\u0938\u0939\u0924']
Replacing :  सुरज detected सिनगह detected बिसहत

#
# Example 8.
#
example_string="""
suraj singh bisht
SURAJ SINGH BISHT
surajsinghbisht054@gmail.com
www.bitforestinfo.com
yashwantsinghbisht054@gmail.com
0124-100-125-2563
124-586-9875
This is an example text
"""
patterns="""
(?P<email>([a-zA-Z0-9]+@[a-z]+.[a-z]+)) # For Email
(\W.*\W.*\W)                            # For Whitespace
(?P<phone>\d{3}-\d{3}-\d{4})            # For Phone
"""

print re.search(patterns, example_string, re.VERBOSE|re.MULTILINE).group()

yashwantsinghbisht054@gmail.com
0124-100-125-2563
124-586-9875

#
# Done
#
# So, Our This Tutorial Series is now completed.
#