Das deutsche Python-Forum

Code: Alles auswählen

#!/usr/bin/python
# -*- coding: UTF-8 -*-

"""
Source Code Parser

Based on J�en Hermann's "MoinMoin - Python Source Parser"
http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/52298/
"""

__version__="0.2.0"

__history__="""
v0.2.0
    - Einige Optimierungen
    - Bug mit den speziellen Zeilenumbrüche mit \ am ende (kein Zeilenumbruch) behoben
v0.1.0
    - aus SourceCode.py Plugin entnommen, damit er auch f�tinyTextile genutzt werden kann
"""

import sys, cgi, cStringIO, \
    keyword, token, tokenize

token.KEYWORD = token.NT_OFFSET + 1

class python_source_parser:

    def parse( self, raw_txt ):
        """
        Parse and send the colored source.
        """
        self.special_not_newline = False
        self.raw = raw_txt.expandtabs()

        # store line offsets in self.lines
        self.lines = [0, 0]
        pos = 0
        while 1:
            pos = self.raw.find( '\n', pos ) + 1
            if not pos: break
            self.lines.append( pos )
        self.lines.append( len(self.raw) )

        # parse the source and write it
        self.pos = 0
        text = cStringIO.StringIO( self.raw )

        try:
            tokenize.tokenize(text.readline, self)
        except tokenize.TokenError, ex:
            msg = ex[0]
            line = ex[1][0]
            print "<h3>ERROR: %s</h3>%s\n" % (
                msg, self.raw[self.lines[line]:]
            )

        print "<br />\n"


    def __call__(self, toktype, toktext, (srow,scol), (erow,ecol), line):
        """ Token handler.
        """
        # calculate new positions
        oldpos = self.pos
        newpos = self.lines[srow] + scol
        self.pos = newpos + len(toktext)

        # Patch for special not newline with \
        if line.endswith("\\\n") and toktype!=tokenize.COMMENT:
            self.special_not_newline = True
        elif self.special_not_newline == True:
            self.special_not_newline = False
            print "\\<br />\n"

        # handle newlines
        if toktype in (token.NEWLINE, tokenize.NL):
            sys.stdout.write( '<br />\n' )
            return

        # Spaces
        if newpos > oldpos:
            sys.stdout.write(" " * (newpos-oldpos))

        if toktext=="":
            return

        # map token type to a color group
        if token.LPAR <= toktype and toktype <= token.OP:
            toktype = token.OP
        elif toktype == token.NAME and keyword.iskeyword(toktext):
            toktype = token.KEYWORD

        # Text Escapen
        toktext = cgi.escape( toktext )

        # Non-Breaking-Spaces
        toktext = toktext.replace(" "," ")

        # Zeilenumbrüche umwandeln
        toktext = toktext.replace("\n","<br />\n")

        if toktype==token.NAME:
            sys.stdout.write(toktext)
        else:
            sys.stdout.write('<span class="t%s">%s</span>' % (toktype,toktext))

        #~ print "\n>>>",toktype

if __name__ == '__main__':
    python_source_parser().parse(open(__file__).read())

Code: Alles auswählen

a = "ababa<<teststring1>>cbcbc<<teststring2>>dcdc"
lastfoundindex = 0
s1 = '<<'
s2 = '>>'
found = []

while 1:
  lf1 = a.find(s1, lastfoundindex) + len(s1)
  lf2 = a.find(s2, lastfoundindex)
  if lf1 > -1 and lf2 > -1 and lf1 < lf2:
    found.append (a[lf1:lf2])
    lastfoundindex = lf2 + 1
  else:
    break

print "Strings found:" 
for s in found:
  print s