# -*- coding: utf-8 -*-
# vi:si:et:sw=2:sts=2:ts=2
# GPL written 2008 by j@pad.ma
import re
import string


# Configuration for urlize() function
LEADING_PUNCTUATION  = ['(', '<', '&lt;']
TRAILING_PUNCTUATION = ['.', ',', ')', '>', '\n', '&gt;', "'", '"']

# list of possible strings used for bullets in bulleted lists
DOTS = ['&middot;', '*', '\xe2\x80\xa2', '&#149;', '&bull;', '&#8226;']

unencoded_ampersands_re = re.compile(r'&(?!(\w+|#\d+);)')
word_split_re = re.compile(r'(\s+)')
punctuation_re = re.compile('^(?P<lead>(?:%s)*)(?P<middle>.*?)(?P<trail>(?:%s)*)$' % \
    ('|'.join([re.escape(x) for x in LEADING_PUNCTUATION]),
    '|'.join([re.escape(x) for x in TRAILING_PUNCTUATION])))
simple_email_re = re.compile(r'^\S+@[a-zA-Z0-9._-]+\.[a-zA-Z0-9._-]+$')
link_target_attribute_re = re.compile(r'(<a [^>]*?)target=[^\s>]+')
html_gunk_re = re.compile(r'(?:<br clear="all">|<i><\/i>|<b><\/b>|<em><\/em>|<strong><\/strong>|<\/?smallcaps>|<\/?uppercase>)', re.IGNORECASE)
hard_coded_bullets_re = re.compile(r'((?:<p>(?:%s).*?[a-zA-Z].*?</p>\s*)+)' % '|'.join([re.escape(x) for x in DOTS]), re.DOTALL)
trailing_empty_content_re = re.compile(r'(?:<p>(?:&nbsp;|\s|<br \/>)*?</p>\s*)+\Z')
del x # Temporary variable

def escape(html):
  "Returns the given HTML with ampersands, quotes and carets encoded"
  if not isinstance(html, basestring):
      html = str(html)
  return html.replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;').replace('"', '&quot;').replace("'", '&#39;')

def linebreaks(value):
  "Converts newlines into <p> and <br />s"
  value = re.sub(r'\r\n|\r|\n', '\n', value) # normalize newlines
  paras = re.split('\n{2,}', value)
  paras = ['<p>%s</p>' % p.strip().replace('\n', '<br />') for p in paras]
  return '\n\n'.join(paras)

def stripTags(value):
  "Returns the given HTML with all tags stripped"
  return re.sub(r'<[^>]*?>', '', value)
    
def stripSpacesBetweenTags(value):
  "Returns the given HTML with spaces between tags normalized to a single space"
  return re.sub(r'>\s+<', '> <', value)

def stripEntities(value):
  "Returns the given HTML with all entities (&something;) stripped"
  return re.sub(r'&(?:\w+|#\d);', '', value)

def fixAmpersands(value):
  "Returns the given HTML with all unencoded ampersands encoded correctly"
  return unencoded_ampersands_re.sub('&amp;', value)

def urlize(text, trim_url_limit=None, nofollow=False):
  """
  Converts any URLs in text into clickable links. Works on http://, https:// and
  www. links. Links can have trailing punctuation (periods, commas, close-parens)
  and leading punctuation (opening parens) and it'll still do the right thing.

  If trim_url_limit is not None, the URLs in link text will be limited to
  trim_url_limit characters.

  If nofollow is True, the URLs in link text will get a rel="nofollow" attribute.
  """
  trim_url = lambda x, limit=trim_url_limit: limit is not None and (x[:limit] + (len(x) >=limit and '...' or ''))  or x
  words = word_split_re.split(text)
  nofollow_attr = nofollow and ' rel="nofollow"' or ''
  for i, word in enumerate(words):
    match = punctuation_re.match(word)
    if match:
      lead, middle, trail = match.groups()
      if middle.startswith('www.') or ('@' not in middle and not middle.startswith('http://') and \
              len(middle) > 0 and middle[0] in string.letters + string.digits and \
              (middle.endswith('.org') or middle.endswith('.net') or middle.endswith('.com'))):
        middle = '<a href="http://%s"%s>%s</a>' % (middle, nofollow_attr, trim_url(middle))
      if middle.startswith('http://') or middle.startswith('https://'):
        middle = '<a href="%s"%s>%s</a>' % (middle, nofollow_attr, trim_url(middle))
      if '@' in middle and not middle.startswith('www.') and not ':' in middle \
        and simple_email_re.match(middle):
        middle = '<a href="mailto:%s">%s</a>' % (middle, middle)
      if lead + middle + trail != word:
        words[i] = lead + middle + trail
  return ''.join(words)

def cleanHtml(text):
  """
  Cleans the given HTML. Specifically, it does the following:
      * Converts <b> and <i> to <strong> and <em>.
      * Encodes all ampersands correctly.
      * Removes all "target" attributes from <a> tags.
      * Removes extraneous HTML, such as presentational tags that open and
        immediately close and <br clear="all">.
      * Converts hard-coded bullets into HTML unordered lists.
      * Removes stuff like "<p>&nbsp;&nbsp;</p>", but only if it's at the
        bottom of the text.
  """
  from text import normalizeNewlines
  text = normalizeNewlines(text)
  text = re.sub(r'<(/?)\s*b\s*>', '<\\1strong>', text)
  text = re.sub(r'<(/?)\s*i\s*>', '<\\1em>', text)
  text = fix_ampersands(text)
  # Remove all target="" attributes from <a> tags.
  text = link_target_attribute_re.sub('\\1', text)
  # Trim stupid HTML such as <br clear="all">.
  text = html_gunk_re.sub('', text)
  # Convert hard-coded bullets into HTML unordered lists.
  def replace_p_tags(match):
    s = match.group().replace('</p>', '</li>')
    for d in DOTS:
      s = s.replace('<p>%s' % d, '<li>')
    return '<ul>\n%s\n</ul>' % s
  text = hard_coded_bullets_re.sub(replace_p_tags, text)
  # Remove stuff like "<p>&nbsp;&nbsp;</p>", but only if it's at the bottom of the text.
  text = trailing_empty_content_re.sub('', text)
  return text

def highlight(text, query, hlClass="hl"):
  if query:
    text = text.replace('<br />', '|')
    query = re.escape(query).replace('\ ', '.')
    m = re.compile("(%s)" % query, re.IGNORECASE).findall(text)
    for i in m:
      text = re.sub("(%s)" % re.escape(i).replace('\ ', '.'), '<span class="%s">\\1</span>' % hlClass, text)
    text = text.replace('|', '<br />')
  return text