def smart_urlquote_wrapper(matched_url):
    """
    Simple wrapper for smart_urlquote. ValueError("Invalid IPv6 URL") can
    be raised here, see issue #1386
    """
    try:
        return smart_urlquote(matched_url)
    except ValueError:
        return None
def smart_urlquote_wrapper(matched_url):
    """
    Simple wrapper for smart_urlquote. ValueError("Invalid IPv6 URL") can
    be raised here, see issue #1386
    """
    try:
        return smart_urlquote(matched_url)
    except ValueError:
        return None
def urlize_quoted_links(text, trim_url_limit=None, nofollow=True, autoescape=True):
    """
    Converts any URLs in text into clickable links.

    Works on http://, https://, www. links, and also on links ending in one of
    the original seven gTLDs (.com, .edu, .gov, .int, .mil, .net, and .org).
    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 longer than this limit
    will truncated to trim_url_limit-3 characters and appended with an elipsis.

    If nofollow is True, the URLs in link text will get a rel="nofollow"
    attribute.

    If autoescape is True, the link text and URLs will get autoescaped.
    """
    trim_url = lambda x, limit=trim_url_limit: limit is not None and (len(x) > limit and ('%s...' % x[:max(0, limit - 3)])) or x
    safe_input = isinstance(text, SafeData)
    words = word_split_re.split(force_text(text))
    for i, word in enumerate(words):
        match = None
        if '.' in word or '@' in word or ':' in word:
            # Deal with punctuation.
            lead, middle, trail = '', word, ''
            for punctuation in TRAILING_PUNCTUATION:
                if middle.endswith(punctuation):
                    middle = middle[:-len(punctuation)]
                    trail = punctuation + trail
            for opening, closing in WRAPPING_PUNCTUATION:
                if middle.startswith(opening):
                    middle = middle[len(opening):]
                    lead = lead + opening
                # Keep parentheses at the end only if they're balanced.
                if (middle.endswith(closing)
                    and middle.count(closing) == middle.count(opening) + 1):
                    middle = middle[:-len(closing)]
                    trail = closing + trail

            # Make URL we want to point to.
            url = None
            nofollow_attr = ' rel="nofollow"' if nofollow else ''
            if simple_url_re.match(middle):
                url = smart_urlquote(middle)
            elif simple_url_2_re.match(middle):
                url = smart_urlquote('http://%s' % middle)
            elif not ':' in middle and simple_email_re.match(middle):
                local, domain = middle.rsplit('@', 1)
                try:
                    domain = domain.encode('idna').decode('ascii')
                except UnicodeError:
                    continue
                url = 'mailto:%s@%s' % (local, domain)
                nofollow_attr = ''

            # Make link.
            if url:
                trimmed = trim_url(middle)
                if autoescape and not safe_input:
                    lead, trail = escape(lead), escape(trail)
                    url, trimmed = escape(url), escape(trimmed)
                middle = '<a href="%s"%s>%s</a>' % (url, nofollow_attr, trimmed)
                words[i] = mark_safe('%s%s%s' % (lead, middle, trail))
            else:
                if safe_input:
                    words[i] = mark_safe(word)
                elif autoescape:
                    words[i] = escape(word)
        elif safe_input:
            words[i] = mark_safe(word)
        elif autoescape:
            words[i] = escape(word)
    return ''.join(words)
示例#4
0
def urlize_quoted_links(text,
                        trim_url_limit=None,
                        nofollow=True,
                        autoescape=True):
    """
    Converts any URLs in text into clickable links.

    Works on http://, https://, www. links, and also on links ending in one of
    the original seven gTLDs (.com, .edu, .gov, .int, .mil, .net, and .org).
    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 longer than this limit
    will truncated to trim_url_limit-3 characters and appended with an elipsis.

    If nofollow is True, the URLs in link text will get a rel="nofollow"
    attribute.

    If autoescape is True, the link text and URLs will get autoescaped.
    """
    trim_url = lambda x, limit=trim_url_limit: limit is not None and (len(
        x) > limit and ('%s...' % x[:max(0, limit - 3)])) or x
    safe_input = isinstance(text, SafeData)
    words = word_split_re.split(force_text(text))
    for i, word in enumerate(words):
        match = None
        if '.' in word or '@' in word or ':' in word:
            # Deal with punctuation.
            lead, middle, trail = '', word, ''
            for punctuation in TRAILING_PUNCTUATION:
                if middle.endswith(punctuation):
                    middle = middle[:-len(punctuation)]
                    trail = punctuation + trail
            for opening, closing in WRAPPING_PUNCTUATION:
                if middle.startswith(opening):
                    middle = middle[len(opening):]
                    lead = lead + opening
                # Keep parentheses at the end only if they're balanced.
                if (middle.endswith(closing) and middle.count(closing)
                        == middle.count(opening) + 1):
                    middle = middle[:-len(closing)]
                    trail = closing + trail

            # Make URL we want to point to.
            url = None
            nofollow_attr = ' rel="nofollow"' if nofollow else ''
            if simple_url_re.match(middle):
                url = smart_urlquote(middle)
            elif simple_url_2_re.match(middle):
                url = smart_urlquote('http://%s' % middle)
            elif not ':' in middle and simple_email_re.match(middle):
                local, domain = middle.rsplit('@', 1)
                try:
                    domain = domain.encode('idna').decode('ascii')
                except UnicodeError:
                    continue
                url = 'mailto:%s@%s' % (local, domain)
                nofollow_attr = ''

            # Make link.
            if url:
                trimmed = trim_url(middle)
                if autoescape and not safe_input:
                    lead, trail = escape(lead), escape(trail)
                    url, trimmed = escape(url), escape(trimmed)
                middle = '<a href="%s"%s>%s</a>' % (url, nofollow_attr,
                                                    trimmed)
                words[i] = mark_safe('%s%s%s' % (lead, middle, trail))
            else:
                if safe_input:
                    words[i] = mark_safe(word)
                elif autoescape:
                    words[i] = escape(word)
        elif safe_input:
            words[i] = mark_safe(word)
        elif autoescape:
            words[i] = escape(word)
    return ''.join(words)