Commit b7fea940 authored by Adrian Holovaty's avatar Adrian Holovaty
Browse files

Fixed #7542 -- Fixed bug in urlize where it was appending 'http://' to the... 

Fixed #7542 -- Fixed bug in urlize where it was appending 'http://' to the link text. Thanks for the patch and tests, devin

git-svn-id: http://code.djangoproject.com/svn/django/trunk@7755 bcc190cf-cafb-0310-a4f2-bffc1f526a37
parent 74f0408f

django/utils/html.py

+26 −26
Original line number Diff line number Diff line
@@ -76,19 +76,19 @@ def urlize(text, trim_url_limit=None, nofollow=False, autoescape=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.

    Works on http://, https://, www. links and links ending in .org, .net or

    .com. 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.

    """

    if autoescape:

        trim_url = lambda x, limit=trim_url_limit: conditional_escape(limit is not None and (len(x) > limit and ('%s...' % x[:max(0, limit - 3)])) or x)

    else:

    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_unicode(text))
@@ -97,29 +97,29 @@ def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False): 
        match = punctuation_re.match(word)

        if match:

            lead, middle, trail = match.groups()

            if safe_input:

                middle = mark_safe(middle)

            if middle.startswith('www.') or ('@' not in middle and not (middle.startswith('http://') or middle.startswith('https://')) and \

                    len(middle) > 0 and middle[0] in string.ascii_letters + string.digits and \

                    (middle.endswith('.org') or middle.endswith('.net') or middle.endswith('.com'))):

                middle = 'http://%s' % middle

            # Make URL we want to point to.

            url = None

            if middle.startswith('http://') or middle.startswith('https://'):

                url = urlquote(middle, safe='/&=:;#?+*')

                if autoescape and not safe_input:

                    url = escape(url)

                trimmed_url = trim_url(middle)

                middle = '<a href="%s"%s>%s</a>' % (url, nofollow_attr,

                        trimmed_url)

            elif '@' in middle and not middle.startswith('www.') and \

                      not ':' in middle and simple_email_re.match(middle):

                if autoescape:

                    middle = conditional_escape(middle)

                middle = '<a href="mailto:%s">%s</a>' % (middle, middle)

            if lead + middle + trail != word:

            elif middle.startswith('www.') or ('@' not in middle and \

                    len(middle) > 0 and middle[0] in string.ascii_letters + string.digits and \

                    (middle.endswith('.org') or middle.endswith('.net') or middle.endswith('.com'))):

                url = urlquote('http://%s' % middle, safe='/&=:;#?+*')

            elif '@' in middle and not ':' in middle and simple_email_re.match(middle):

                url = 'mailto:%s' % middle

                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))

            elif autoescape and not safe_input:

            else:

                if safe_input:

                    words[i] = mark_safe(word)

                elif autoescape:

                    words[i] = escape(word)

        elif safe_input:

            words[i] = mark_safe(word)

tests/regressiontests/defaultfilters/tests.py

+3 −3
Original line number Diff line number Diff line
@@ -150,7 +150,7 @@ u'fran%C3%A7ois%20%26%20jill' 
u'<a href="http://short.com/" rel="nofollow">http://short.com/</a>'



>>> urlizetrunc(u'http://www.google.co.uk/search?hl=en&q=some+long+url&btnG=Search&meta=', 20)

u'<a href="http://www.google.co.uk/search?hl=en&q=some+long+url&btnG=Search&meta=" rel="nofollow">http://www.google....</a>'

u'<a href="http://www.google.co.uk/search?hl=en&q=some+long+url&btnG=Search&meta=" rel="nofollow">http://www.google...</a>'



>>> urlizetrunc('http://www.google.co.uk/search?hl=en&q=some+long+url&btnG=Search&meta=', 20)

u'<a href="http://www.google.co.uk/search?hl=en&q=some+long+url&btnG=Search&meta=" rel="nofollow">http://www.google...</a>'
@@ -174,10 +174,10 @@ u'<a href="http://google.com" rel="nofollow">http://google.com</a>' 
u'<a href="http://google.com/" rel="nofollow">http://google.com/</a>'



>>> urlize('www.google.com') 

u'<a href="http://www.google.com" rel="nofollow">http://www.google.com</a>'

u'<a href="http://www.google.com" rel="nofollow">www.google.com</a>'



>>> urlize('djangoproject.org') 

u'<a href="http://djangoproject.org" rel="nofollow">http://djangoproject.org</a>'

u'<a href="http://djangoproject.org" rel="nofollow">djangoproject.org</a>'



>>> urlize('info@djangoproject.org') 

u'<a href="mailto:info@djangoproject.org">info@djangoproject.org</a>'