import re

patterns = [ 'this', 'that' ]
text = 'Does this text match the pattern?'

for pattern in patterns:
    print 'Looking for "%s" in "%s" ->' % (pattern, text),

    if re.search(pattern,  text):
        print 'found a match!'
    else:
        print 'no match'

import re

pattern = 'this'
text = 'Does this text match the pattern?'

match = re.search(pattern, text)

s = match.start()
e = match.end()

print 'Found "%s" in "%s" from %d to %d ("%s")' % \
    (match.re.pattern, match.string, s, e, text[s:e])

import re

# Pre-compile the patterns
regexes = [ re.compile(p) for p in [ 'this',
                                     'that',
                                     ]
            ]
text = 'Does this text match the pattern?'

for regex in regexes:
    print 'Looking for "%s" in "%s" ->' % (regex.pattern, text),

    if regex.search(text):
        print 'found a match!'
    else:
        print 'no match'

import re

text = 'abbaaabbbbaaaaa'

pattern = 'ab'

for match in re.findall(pattern, text):
    print 'Found "%s"' % match

import re

text = 'abbaaabbbbaaaaa'

pattern = 'ab'

for match in re.finditer(pattern, text):
    s = match.start()
    e = match.end()
    print 'Found "%s" at %d:%d' % (text[s:e], s, e)

import re

def test_patterns(text, patterns=[]):
    """Given source text and a list of patterns, look for
    matches for each pattern within the text and print
    them to stdout.
    """
    # Show the character positions and input text
    print
    print ''.join(str(i/10 or ' ') for i in range(len(text)))
    print ''.join(str(i%10) for i in range(len(text)))
    print text

    # Look for each pattern in the text and print the results
    for pattern in patterns:
        print
        print 'Matching "%s"' % pattern
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            print '  %2d : %2d = "%s"' % \
                (s, e-1, text[s:e])
    return

if __name__ == '__main__':
    test_patterns('abbaaabbbbaaaaa', ['ab'])

import re

text = 'This is some text -- with punctuation.'
pattern = 'is'

print 'Text   :', text
print 'Pattern:', pattern

m = re.match(pattern, text)
print 'Match  :', m
s = re.search(pattern, text)
print 'Search :', s

import re

text = 'This is some text -- with punctuation.'
pattern = re.compile(r'\b\w*is\w*\b')

print 'Text:', text
print

pos = 0
while True:
    match = pattern.search(text, pos)
    if not match:
        break
    s = match.start()
    e = match.end()
    print '  %2d : %2d = "%s"' % \
        (s, e-1, text[s:e])
    # Move forward in text for the next search
    pos = e
    

from re_test_patterns import test_patterns

test_patterns('abbaaabbbbaaaaa',
              [ 'a(ab)',    # 'a' followed by literal 'ab'
                'a(a*b*)',  # 'a' followed by 0-n 'a' and 0-n 'b'
                'a(ab)*',   # 'a' followed by 0-n 'ab'
                'a(ab)+',   # 'a' followed by 1-n 'ab'
                ])

import re

text = 'This is some text -- with punctuation.'

print text
print

for pattern in [ r'^(\w+)',           # word at start of string
                 r'(\w+)\S*$',        # word at end of string, with optional punctuation
                 r'(\bt\w+)\W+(\w+)', # word starting with 't' then another word
                 r'(\w+t)\b',         # word ending with 't'
                 ]:
    regex = re.compile(pattern)
    match = regex.search(text)
    print 'Matching "%s"' % pattern
    print '  ', match.groups()
    print

import re

text = 'This is some text -- with punctuation.'

print 'Input text            :', text

# word starting with 't' then another word
regex = re.compile(r'(\bt\w+)\W+(\w+)')
print 'Pattern               :', regex.pattern

match = regex.search(text)
print 'Entire match          :', match.group(0)
print 'Word starting with "t":', match.group(1)
print 'Word after "t" word   :', match.group(2)

import re

text = 'This is some text -- with punctuation.'

print text
print

for pattern in [ r'^(?P<first_word>\w+)',
                 r'(?P<last_word>\w+)\S*$',
                 r'(?P<t_word>\bt\w+)\W+(?P<other_word>\w+)',
                 r'(?P<ends_with_t>\w+t)\b',
                 ]:
    regex = re.compile(pattern)
    match = regex.search(text)
    print 'Matching "%s"' % pattern
    print '  ', match.groups()
    print '  ', match.groupdict()
    print

import re

def test_patterns(text, patterns=[]):
    """Given source text and a list of patterns, look for
    matches for each pattern within the text and print
    them to stdout.
    """
    # Show the character positions and input text
    print
    print ''.join(str(i/10 or ' ') for i in range(len(text)))
    print ''.join(str(i%10) for i in range(len(text)))
    print text

    # Look for each pattern in the text and print the results
    for pattern in patterns:
        print
        print 'Matching "%s"' % pattern
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            print '  %2d : %2d = "%s"' % \
                (s, e-1, text[s:e])
            print '    Groups:', match.groups()
            if match.groupdict():
                print '    Named groups:', match.groupdict()
            print
    return

from re_test_patterns_groups import test_patterns

test_patterns('abbaaabbbbaaaaa',
              [r'a((a*)(b*))', # 'a' followed by 0-n 'a' and 0-n 'b'
               ])

from re_test_patterns_groups import test_patterns

test_patterns('abbaaabbbbaaaaa',
              [r'a((a+)|(b+))', # 'a' followed by a sequence of 'a' or sequence of 'b'
               r'a((a|b)+)',    # 'a' followed by a sequence of 'a' or 'b'
               ])

from re_test_patterns_groups import test_patterns

test_patterns('abbaaabbbbaaaaa',
              [r'a((a+)|(b+))',     # capturing form
               r'a((?:a+)|(?:b+))', # non-capturing
               ])

import re

address = re.compile(
    '''
    # A name is made up of letters, and may include "." for title
    # abbreviations and middle initials.
    ((?P<name>
       ([\w.,]+\s+)*[\w.,]+
     )
     \s+
    ) # name is no longer optional

    # LOOKAHEAD
    # Email addresses are wrapped in angle brackets, but we only want
    # the brackets if they are both there, or neither are.
    (?= (<.*>$)       # remainder wrapped in angle brackets
        |
        ([^<].*[^>]$) # remainder *not* wrapped in angle brackets
      )

    <? # optional opening angle bracket

    # The address itself: username@domain.tld
    (?P<email>
      [\w\d.+-]+       # username
      @
      ([\w\d.]+\.)+    # domain name prefix
      (com|org|edu)    # limit the allowed top-level domains
    )

    >? # optional closing angle bracket
    ''',
    re.UNICODE | re.VERBOSE)

candidates = [
    u'First Last <first.last@example.com>',
    u'No Brackets first.last@example.com',
    u'Open Bracket <first.last@example.com',
    u'Close Bracket first.last@example.com>',
    ]

for candidate in candidates:
    print
    print 'Candidate:', candidate
    match = address.search(candidate)
    if match:
        print '  Match name :', match.groupdict()['name']
        print '  Match email:', match.groupdict()['email']
    else:
        print '  No match'

import re

address = re.compile(
    '''
    ^

    # An address: username@domain.tld

    # Ignore noreply addresses
    (?!noreply@.*$)

    [\w\d.+-]+       # username
    @
    ([\w\d.]+\.)+    # domain name prefix
    (com|org|edu)    # limit the allowed top-level domains

    $
    ''',
    re.UNICODE | re.VERBOSE)

candidates = [
    u'first.last@example.com',
    u'noreply@example.com',
    ]

for candidate in candidates:
    print
    print 'Candidate:', candidate
    match = address.search(candidate)
    if match:
        print '  Match:', candidate[match.start():match.end()]
    else:
        print '  No match'

import re

address = re.compile(
    '''
    ^

    # An address: username@domain.tld

    [\w\d.+-]+       # username

    # Ignore noreply addresses
    (?<!noreply)

    @
    ([\w\d.]+\.)+    # domain name prefix
    (com|org|edu)    # limit the allowed top-level domains

    $
    ''',
    re.UNICODE | re.VERBOSE)

candidates = [
    u'first.last@example.com',
    u'noreply@example.com',
    ]

for candidate in candidates:
    print
    print 'Candidate:', candidate
    match = address.search(candidate)
    if match:
        print '  Match:', candidate[match.start():match.end()]
    else:
        print '  No match'

import re

twitter = re.compile(
    '''
    # A twitter handle: @username
    (?<=@)
    ([\w\d_]+)       # username
    ''',
    re.UNICODE | re.VERBOSE)

text = '''This text includes two Twitter handles.
One for @ThePSF, and one for the author, @doughellmann.
'''

print text
for match in twitter.findall(text):
    print 'Handle:', match

import re

address = re.compile(
    r'''

    # The regular name
    (\w+)               # first name
    \s+
    (([\w.]+)\s+)?      # optional middle name or initial
    (\w+)               # last name

    \s+

    <

    # The address: first_name.last_name@domain.tld
    (?P<email>
      \1               # first name
      \.
      \4               # last name
      @
      ([\w\d.]+\.)+    # domain name prefix
      (com|org|edu)    # limit the allowed top-level domains
    )

    >
    ''',
    re.UNICODE | re.VERBOSE | re.IGNORECASE)

candidates = [
    u'First Last <first.last@example.com>',
    u'Different Name <first.last@example.com>',
    u'First Middle Last <first.last@example.com>',
    u'First M. Last <first.last@example.com>',
    ]

for candidate in candidates:
    print
    print 'Candidate:', candidate
    match = address.search(candidate)
    if match:
        print '  Match name :', match.group(1), match.group(4)
        print '  Match email:', match.group(5)
    else:
        print '  No match'

import re

address = re.compile(
    '''

    # The regular name
    (?P<first_name>\w+)
    \s+
    (([\w.]+)\s+)?      # optional middle name or initial
    (?P<last_name>\w+)

    \s+

    <

    # The address: first_name.last_name@domain.tld
    (?P<email>
      (?P=first_name)
      \.
      (?P=last_name)
      @
      ([\w\d.]+\.)+    # domain name prefix
      (com|org|edu)    # limit the allowed top-level domains
    )

    >
    ''',
    re.UNICODE | re.VERBOSE | re.IGNORECASE)

candidates = [
    u'First Last <first.last@example.com>',
    u'Different Name <first.last@example.com>',
    u'First Middle Last <first.last@example.com>',
    u'First M. Last <first.last@example.com>',
    ]

for candidate in candidates:
    print
    print 'Candidate:', candidate
    match = address.search(candidate)
    if match:
        print '  Match name :', match.groupdict()['first_name'], match.groupdict()['last_name']
        print '  Match email:', match.groupdict()['email']
    else:
        print '  No match'

import re

address = re.compile(
    '''
    ^

    # A name is made up of letters, and may include "." for title
    # abbreviations and middle initials.
    (?P<name>
       ([\w.]+\s+)*[\w.]+
     )?
    \s*

    # Email addresses are wrapped in angle brackets, but we only want
    # the brackets if we found a name.
    (?(name)
      # remainder wrapped in angle brackets because we have a name
      (?P<brackets>(?=(<.*>$)))
      |
      # remainder does not include angle brackets without name
      (?=([^<].*[^>]$))
     )

    # Only look for a bracket if our look ahead assertion found both
    # of them.
    (?(brackets)<|\s*)

    # The address itself: username@domain.tld
    (?P<email>
      [\w\d.+-]+       # username
      @
      ([\w\d.]+\.)+    # domain name prefix
      (com|org|edu)    # limit the allowed top-level domains
     )

    # Only look for a bracket if our look ahead assertion found both
    # of them.
    (?(brackets)>|\s*)

    $
    ''',
    re.UNICODE | re.VERBOSE)

candidates = [
    u'First Last <first.last@example.com>',
    u'No Brackets first.last@example.com',
    u'Open Bracket <first.last@example.com',
    u'Close Bracket first.last@example.com>',
    u'no.brackets@example.com',
    ]

for candidate in candidates:
    print
    print 'Candidate:', candidate
    match = address.search(candidate)
    if match:
        print '  Match name :', match.groupdict()['name']
        print '  Match email:', match.groupdict()['email']
    else:
        print '  No match'

import re

bold = re.compile(r'\*{2}(.*?)\*{2}', re.UNICODE)

text = 'Make this **bold**.  This **too**.'

print 'Text:', text
print 'Bold:', bold.sub(r'<b>\1</b>', text)

import re

bold = re.compile(r'\*{2}(?P<bold_text>.*?)\*{2}', re.UNICODE)

text = 'Make this **bold**.  This **too**.'

print 'Text:', text
print 'Bold:', bold.sub(r'<b>\g<bold_text></b>', text)

import re

bold = re.compile(r'\*{2}(.*?)\*{2}', re.UNICODE)

text = 'Make this **bold**.  This **too**.'

print 'Text:', text
print 'Bold:', bold.sub(r'<b>\1</b>', text, count=1)

import re

bold = re.compile(r'\*{2}(.*?)\*{2}', re.UNICODE)

text = 'Make this **bold**.  This **too**.'

print 'Text:', text
print 'Bold:', bold.subn(r'<b>\1</b>', text)

import re

text = 'Paragraph one\non two lines.\n\nParagraph two.\n\n\nParagraph three.'

for num, para in enumerate(re.findall(r'(.+?)\n{2,}', text, flags=re.DOTALL)):
    print num, repr(para)
    print

import re

text = 'Paragraph one\non two lines.\n\nParagraph two.\n\n\nParagraph three.'

print 'With findall:'
for num, para in enumerate(re.findall(r'(.+?)(\n{2,}|$)', text, flags=re.DOTALL)):
    print num, repr(para)
    print

print
print 'With split:'
for num, para in enumerate(re.split(r'\n{2,}', text)):
    print num, repr(para)
    print

import re

text = 'Paragraph one\non two lines.\n\nParagraph two.\n\n\nParagraph three.'

print
print 'With split:'
for num, para in enumerate(re.split(r'(\n{2,})', text)):
    print num, repr(para)
    print