import re #the regex module in the python standard library

#strings to be searched for matching regex patterns
str1 = "Aardvarks belong to the Captain"
str2 = "Albert's famous equation, E = mc^2."
str3 = "Located at 455 Serra Mall."
str4 = "Beware of the shape-shifters!"
test_strings = [str1, str2, str3, str4] #created a list of strings

for test_string in test_strings:
    print 'The test string is "' + test_string + '"'
    match = re.search(r'[A-Z]', test_string)
    if match:
        print 'The first possible match is: ' + match.group()
    else:
        print 'no match.'

for string in test_strings:
    print re.findall(r'[A-Z]', string)

patterns = [re.compile(r'[ABC]'),
re.compile(r'[^ABC]'),
re.compile(r'[ABC^]'),
re.compile(r'[0123456789]'),
re.compile(r'[0-9]'),
re.compile(r'[0-4]'),
re.compile(r'[A-Z]'),
re.compile(r'[A-Za-z]'),
re.compile(r'[A-Za-z0-9]'),
re.compile(r'[-a-z]'),
re.compile(r'[- a-z]')]

def find_match(pattern, string):
    match = re.search(pattern, string)
    if match:
        return match.group()
    else:
        return 'no match.'
    
for test_string in test_strings:
    matches = [find_match(pattern, test_string) for pattern in patterns]
  
    for pattern in patterns:
        print 'The first potential match for "' + pattern.pattern + '" in "' + test_string + '" is: ' + matches[patterns.index(pattern)]

print patterns.index(re.compile(r'[^ABC]'))

patterns2 = [re.compile(r'.'),
re.compile(r'\w'),
re.compile(r'\W'),
re.compile(r'\d'),
re.compile(r'\D'),
re.compile(r'\n'),
re.compile(r'\r'),
re.compile(r'\t'),
re.compile(r'\f'),
re.compile(r'\s')]

test_strings.append('Aardvarks belong to the Captain, capt_hook')

for test_string in test_strings:
    matches = [find_match(pattern, test_string) for pattern in patterns2]

    for pattern in patterns2:
        print 'The first potential match for "' + pattern.pattern + '" in "' + test_string + '" is: ' + matches[patterns2.index(pattern)]

test_strings2 = ["The Aardvarks belong to the Captain.",
                 "Bitter butter won't make the batter better.",
                 "Hark, the pitter patter of little feet!"]

patterns3 = [re.compile(r'Aa'),
re.compile(r'[Aa][Aa]'),
re.compile(r'[aeiou][aeiou]'),
re.compile(r'[AaEeIiOoUu][aeiou]'),
re.compile(r'[Tt]he'),
re.compile(r'^[Tt]he'),
re.compile(r'n.'),
re.compile(r'n.$'),
re.compile(r'\W\w'),
re.compile(r'\w[aeiou]tter'),
re.compile(r'\w[aeiou]tter'),
re.compile(r'..tt..')]

for test_string in test_strings2:
    matches = [find_match(pattern, test_string) for pattern in patterns3]

    for pattern in patterns3:
        print 'The first potential match for "' + pattern.pattern + '" in "' + test_string + '" is: ' + matches[patterns3.index(pattern)]

def find_all_matches(pattern, string):
    matches = re.findall(pattern, string)
    if matches:
        return matches
    else:
        return None

for test_string in test_strings2:
    matches = [find_all_matches(pattern, test_string) for pattern in patterns3]
    
    for pattern in patterns3:
        if matches[patterns3.index(pattern)]:
            print 'All potential matches for "' + pattern.pattern + '" in "' + test_string + '" is/are: ' + ', '.join(matches[patterns3.index(pattern)])
        else:
            print 'There were no matches for "' + pattern.pattern + '" in "' + test_string + '".'


test_strings3 = ['Now Mr. N said, "Nooooooo!"',
                 'Then she told him he had to be quiet.']

patterns4 = [re.compile(r'No*'),
re.compile(r'No+'),
re.compile(r'No?'),
re.compile(r'No{7}'),
re.compile(r's?he'),
re.compile(r'(she|he)')]

for test_string in test_strings3:
    matches = [find_all_matches(pattern, test_string) for pattern in patterns4]
    
    for pattern in patterns4:
        if matches[patterns4.index(pattern)]:
            print 'All potential matches for "' + pattern.pattern + '" in "' + test_string + '" is/are: ' + ', '.join(matches[patterns4.index(pattern)])
        else:
            print 'There were no matches for "' + pattern.pattern + '" in "' + test_string + '".'

test_strings4 = ['The benefit is being held for Mr. Kite and Mr. Henderson.',
                 'Tickets cost $5.00 for adults, $3.50 for children.',
                 'Over 9000 attendees are expected, up from 900 attendees last year.',
                 'Over 9,000 attendees are expected, up from 900 attendees last year.']

patterns5 = [re.compile(r'Mr\. (\w+)'),
re.compile(r'\$(\d+\.\d\d)'),
re.compile(r'(\d+) attendees'),
re.compile(r'((\d+,)*\d+) attendees')]

# simple example

matches = re.search(patterns5[3], test_strings4[3])
print 'Group 0: ' + matches.group(0)
print 'Group 1: ' + matches.group(1)
print 'Group 2: ' + matches.group(2)
#print 'Group 3: ' + matches.group(3) # what happens if you uncomment this?

for test_string in test_strings4:
    for pattern in patterns5:
        for result in re.finditer(pattern, test_string):
            for i in range(pattern.groups+1):
                
                print 'In "' + test_string + '", '  + 'given pattern "' + pattern.pattern + '", the group ' +str(i)+ ' match is ' + str(result.group(i))

matches = re.findall(patterns5[3], test_strings4[3])
matches

matches[0][0]

phone_strings = ['Call Empire Carpets at 588-2300',
'Does Jenny live at 867 5309?',
'You can reach Mr. Plow at 636-555-3226']