django1/django/utils/html.py

"Useful HTML utilities suitable for global use by World Online projects."

import re, 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)*)$' % \
    ('|'.join([re.escape(p) for p in LEADING_PUNCTUATION]),
    '|'.join([re.escape(p) for p in TRAILING_PUNCTUATION])))
SIMPLE_EMAIL_RE = re.compile(r'^\S+@[a-zA-Z0-9._-]+\.[a-zA-Z0-9._-]+$')
LINK_TARGET_ATTRIBUTE = re.compile(r'(<a [^>]*?)target=[^\s>]+')
HTML_GUNK = re.compile(r'(?:<br clear="all">|<i><\/i>|<b><\/b>|<em><\/em>|<strong><\/strong>|<\/?smallcaps>|<\/?uppercase>)', re.IGNORECASE)
HARD_CODED_BULLETS = re.compile(r'((?:<p>(?:%s).*?[a-zA-Z].*?</p>\s*)+)' % '|'.join([re.escape(d) for d in DOTS]), re.DOTALL)
TRAILING_EMPTY_CONTENT = re.compile(r'(?:<p>(?:&nbsp;|\s|<br \/>)*?</p>\s*)+\Z')

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;')

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 strip_tags(value):
    "Returns the given HTML with all tags stripped"
    return re.sub(r'<[^>]*?>', '', value)

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

def fix_ampersands(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 clean_html(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 django.utils.text import normalize_newlines
    text = normalize_newlines(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.sub('\\1', text)
    # Trim stupid HTML such as <br clear="all">.
    text = HTML_GUNK.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.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.sub('', text)
    return text