lxneng · August 14, 2012 04:45
diff --git a/gistfile1.html b/gistfile1.html
 <!DOCTYPE html>
 <html>
 <head>
  <meta charset="utf-8">
  <title>Sanitise a (unicode) string so it is suitable as a URL path
    component.</title>  
 </head>
 <body>
 <xmp  theme="United">

 ```py
 # coding=utf-8
 import re
 import unicodedata


 def cropText(text, length):
    """Crop a text at a given length. If the text is shorter than the
    given length it is returned unchanged.

    :param unicode text: text to crop
    :param int length: maximum length of returned string
    """
    if not text:
        return text
    if len(text) <= length:
        return text

    return text[:length] + u'…'


 def NormalizeTitleToPath(title):
    """Sanitise a (unicode) string so it is suitable as a URL path
    component."""
    path = title.strip().lower()

    # Normalize the unicode form
    def norm(c):
        category = unicodedata.category(c)
        # Return normalized version of all letter and number forms
        if category in ['Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nd', 'Nl', 'No']:
            return unicodedata.normalize("NFKD", c)
        # Reduce all separators to a simple space
        if category in ['Zs', 'Zl', 'Zp']:
            return u' '
        # List of allowed non-letter characters
        if c in '+-':
            return c
        # Everything else is ignored
        return u''

    path = u''.join([norm(part) for part in path])
    path = re.sub(r' +', u'-', path)
    return path
 ```
 </xmp>
 <script src="http://strapdownjs.com/v/0.1/strapdown.js"></script>
 </body>
	<!DOCTYPE html>
	<html>
	<head>
	<meta charset="utf-8">
	<title>Sanitise a (unicode) string so it is suitable as a URL path
	component.</title>
	</head>
	<body>
	<xmp theme="United">

	```py
	# coding=utf-8
	import re
	import unicodedata


	def cropText(text, length):
	"""Crop a text at a given length. If the text is shorter than the
	given length it is returned unchanged.

	:param unicode text: text to crop
	:param int length: maximum length of returned string
	"""
	if not text:
	return text
	if len(text) <= length:
	return text

	return text[:length] + u'…'


	def NormalizeTitleToPath(title):
	"""Sanitise a (unicode) string so it is suitable as a URL path
	component."""
	path = title.strip().lower()

	# Normalize the unicode form
	def norm(c):
	category = unicodedata.category(c)
	# Return normalized version of all letter and number forms
	if category in ['Lu', 'Ll', 'Lt', 'Lm', 'Lo', 'Nd', 'Nl', 'No']:
	return unicodedata.normalize("NFKD", c)
	# Reduce all separators to a simple space
	if category in ['Zs', 'Zl', 'Zp']:
	return u' '
	# List of allowed non-letter characters
	if c in '+-':
	return c
	# Everything else is ignored
	return u''

	path = u''.join([norm(part) for part in path])
	path = re.sub(r' +', u'-', path)
	return path
	```
	</xmp>
	<script src="http://strapdownjs.com/v/0.1/strapdown.js"></script>
	</body>