Das deutsche Python-Forum

Code: Alles auswählen

([a-zA-Z0-9 \t]*)(::)\s*\n\s*\n(.*)(\n)

Code: Alles auswählen

source = """test
    foobar ::
    
    test
    test2

    """
    
TAGS_RE = re.compile(r'([a-zA-Z0-9 \t]*)(::)\s*\n\s*\n(.*)(\n)')
tokens = [x for x in TAGS_RE.split(source) if x != '' and x != None]
print tokens

# ['test\n', '    foobar ', '::', '    test', '\n', '    test2\n    \n    ']

Code: Alles auswählen

['test\n', '    foobar ', '::', '    test\n', '    test2\n    ', '\n', '    ']

Code: Alles auswählen

source = """test
    foobar ::
    test
    test2
    """
# Greift nicht, also i.O. -> ['test\n    foobar ::\n    test\n    test2\n    \n    ']


source = """test
    ::
    
    test
    test2
    """
# Greift also i.O. -> ['test\n', '    ', '::', '    test', '\n', '    test2\n    ']

source = """test
    foobar ::
    
    test
    test2

    """
# Greift also i.O. -> ['test\n', '    foobar ', '::', '    test', '\n', '    test2\n    \n    ']

Code: Alles auswählen

source = source = """test #link[test] **__test__**
foobar
"""
blex = BasisLexer(source)
# So würde das Ergebnis mit Split aussehen: 
# ['test ', '#link', '[', 'test', ']', ' ', '**', '__', 'test', '__', '**', '\n', 'foobar', '\n']
print blex.source

#Der zusammengesetzte RegExp:
# (\*\*)|(//)|(__)|({{{)|(}}})|(#link)([ \t]*)(\[{1})([^\[\].]+)(\]{1})|(#image)([ \t]*)(\[{1})([^\[\].]+)(\]{1})|(\n)|(\r\n)
print blex.regexp_str

#...

#Der fertige lexer_stream
# [[('Literal', 'test ')], [('MarkupCommand', '#link'), ('TOCMD_OPENBR', '['), ('Literal', 'test'), ('TOCMD_CLOSBR', ']')], [('Literal', ' ')], [('MarkupBold', '**'), ('MarkupUnderline', '__'), ('Literal', 'test'), ('MarkupUnderline', '__'), ('MarkupBold', '**')], [('MarkupLinebreak', '\n')], [('Literal', 'foobar')], [('MarkupLinebreak', '\n')]]

# Darüber iteriert
for line in blex:
    print line

# [('Literal', 'test ')]
#[('MarkupCommand', '#link'), ('TOCMD_OPENBR', '['), ('Literal', 'test'), ('TOCMD_CLOSBR', ']')]
#[('Literal', ' ')]
#[('MarkupBold', '**'), ('MarkupUnderline', '__'), ('Literal', 'test'), ('MarkupUnderline', '__'), ('MarkupBold', '**')]
#[('MarkupLinebreak', '\n')]
#[('Literal', 'foobar')]
#[('MarkupLinebreak', '\n')]

Code: Alles auswählen

# Code blocks
499	            (r'(::)(\n)((?:(?: +.*|)\n)+)',
500	             bygroups(String.Escape, Text, String)),
501	            include('inline'),

Code: Alles auswählen

([\w\s]*)       # alphanumeric character any whitespace
                    # zero or more times; hier braucht nix stehen!! Die (::) können am Anfang der Zeile stehen
(::)                # ::
\s*                # zero or more times whitespace
\n                 # NewLine im String wie 'abc\nxyz'
\s*
\n
(.*)
(\n)

Code: Alles auswählen

>>> source = """This is a typical paragraph.  An indented literal block follows.

::

    for a in [5,4,3,2,1]:   # this is program code, shown as-is
        print a
    print "it's..."
    # a literal block continues until the indentation ends

This text has returned to the indentation of the first paragraph,
is outside of the literal block, and is therefore treated as an
ordinary paragraph."""

>>> pattern = re.compile(r'(?P<indent>^[ \t]*)(::[ \t]*\n+)((?:(?P=indent)[ \t]+.*\n)+)', re.MULTILINE)
>>> pattern.findall(source)
[('', '::\n\n', '    for a in [5,4,3,2,1]:   # this is program code, shown as-is\n        print a\n    print "it\'s..."\n    # a literal block continues until the indentation ends\n')]

Code: Alles auswählen

 for m in pattern.finditer(source):
       print m.groupdict()

Code: Alles auswählen

foobar::
    
    for i in xrange(100):
        print i

Code: Alles auswählen

source = """
    *This* text has returned *to* the indentation of the *first paragraph*,
is outside of the literal block, and is therefore treated as *an*
ordinary* paragraph."""
    
pattern = re.compile(r'(\*)([\w \t]+)(\*)', re.MULTILINE | re.UNICODE | re.VERBOSE)
for m in pattern.finditer(source):
    print m.groups()

Code: Alles auswählen

('*', 'This', '*')
('*', 'to', '*')
('*', 'first paragraph', '*')
('*', 'an', '*')

Code: Alles auswählen

source = """
    *This* text has returned *to* the indentation of the *first paragraph*,
is outside of the literal block, and is therefore treated as *an*
ordinary* paragraph."""
    
pattern = re.compile(r'\*[\w \t]+\*', re.MULTILINE | re.UNICODE | re.VERBOSE)
for m in pattern.finditer(source):
    print m.groups()

Code: Alles auswählen

()
()
()
()

Code: Alles auswählen

>>> p=re.compile(r'^(\w+)\n\s+(\S+)\s*(::)\s*\n\n(?:\s+(\w+)\n)*\n')
>>> m=p.search(source)
>>> m.groups()
('test', 'foobar', '::', 'test2')
>>> m.group(0)
'test\n  foobar ::\n\n   test\n   test2\n\n'