root/trunk/vertical/rest/preprocessors.py

# Copyright 2006, Meir Kriheli <meir@mksoft.co.il>
#
# This file is part of Lahak
#
# Lahak is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# any later version.
#
# Lahak is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Lahak; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
#
# vim: set ts=4 sw=4 et:

from lahak.vertical.core.protocols import supported_protocols, get_protocol_display
from lahak.vertical.uploads.models import Image, Audio
from lahak.vertical.core.templatetags.lahak_general import resize
from django.db.models.base import ObjectDoesNotExist
import urllib, re
from django.utils.translation import ugettext as _

class ProtocolsPreProcessor(object):
    "Converts lahak supported protocols in the content to links"

    def __call__(self, content):
        
        autolinks = supported_protocols.get_regexp().findall(content)

        for match in autolinks:
            the_model = supported_protocols.get_protocols()[match[1]]
            try:
                # we're looking for a 'lookup' key in the model's
                # LahakMeta.protocol, if not, fallback to id
                lookup = { the_model.LahakMeta.protocol.get('lookup','id'): match[2] }

                data = the_model.objects.get(**lookup)
                label = get_protocol_display(data)

                content = content.replace( match[0], r"`%s <%s>`_" % (label, data.get_absolute_url() ) )
            except ObjectDoesNotExist:
                # hmm, object not found, let's try to deal with it.
                # Does the manager has 'protocol_new_path' property ?
                # If so, use it. Otherwise fail silently, and keep
                # the text as is
                new_path = the_model.LahakMeta.protocol.get('new_path', None)
                if new_path:
                    content = content.replace(match[0], r"`%s <%s%s>`_" % ( match[2], new_path, urllib.quote_plus( match[2].encode('utf-8') )) )
                else:
                    # we don't want to get stuck with the vertical bars, as
                    # they defint reST references, so we'll replace them
                    content = content.replace(match[0], r"`%s </error_404>`_" % match[2])

        return content
        
class UploadedImagePreProcessor(object):
    """Converts lahak image directive pointing to an image id to proper reST
    directives.
    
    If width or height is smaller than original image, creates thumbnails
    on the fly"""

    regexp = re.compile( '\.\. (%s|image):: (\d+)((\s+:.+:\s+.*?\s*\n)*)' % _('image'), re.MULTILINE )
    width_regexp = re.compile(r'([ |\t]*):(%s|width):\s+(\d+)' % _('width'))
    height_regexp= re.compile(r'([ |\t]*):(%s|height):\s+(\d+)' % _('height'))

    def _replace_image_url( self, matchobj ):
        
        params = matchobj.group(3)
        url = '.. %s:: %s%s'
        try:
            img = Image.objects.get(pk=int(matchobj.group(2)))

            width_match = self.width_regexp.findall(params)
            height_match = self.height_regexp.findall(params)

            # width is specified, to we need to generate the thumbnail
            if width_match:
                width = int(width_match[0][2])
                image_url = resize(img.get_image_url() ,'width=%d' % width)
                params = "\n%s:target: %s%s" % (width_match[0][0], img.get_image_url(), params)
            elif height_match:
                height = int(height_match[0][2])
                image_url = resize(img.get_image_url() ,'height=%d' % height)
                params = "\n%s:target: %s%s" % (height_match[0][0], img.get_image_url(), params)
            else:
                image_url = img.get_image_url()
                
            return url % ( matchobj.group(1), image_url , params ) 
        except ObjectDoesNotExist:
            return url % ( matchobj.group(1), matchobj.group(2) )

    def __call__(self, content):
        content = self.regexp.sub(self._replace_image_url, content)
        return content


class ParameterTranslationPreProcessor(object):
    """Replaces translated reST paramaters to original ones
    (reST doesn't support param translations)"""

    translations = (
        ( _('width'), 'width' ),
        ( _('height'), 'height' ),
        ( _('alt'), 'alt' ),
    )

    def __call__(self, content):
        # since image params are not translatable by reST, will subst them here

        for tr in self.translations:
            content = content.replace( ':%s:' % tr[0], ':%s:' % tr[1])
        return content


class AdmonitionsPreProcessor(object):
    """Translate block admonitions to general admonition.
    
    Since we want the special style name generated by admonitions, but can't
    support unicode (hence Hebrew in style names, a post precessor is also
    required"""

    translations = (
        ( _('exercise'), 'exercise' ),
        ( _('quote'), 'quote' ),
    )
    
    def __call__(self, content):
        for tr in self.translations:
            content = content.replace( '.. %s::' % tr[0], '.. admonition:: %s' % tr[1])
        return content

class SanitizePreProcessor(object):
    """Sanitize unwanted javascript (and other) in links"""

    regexp_hyperlink = re.compile(r'(\.\.\s*\_.*?:\s*)(.*script:)(.*)', re.MULTILINE)
    regexp_hyperlink_embedded = re.compile(r'(\`.*?\<)(.*?script:)(.*?\>\`_)', re.MULTILINE)


    def __call__(self, content):
        content = self.regexp_hyperlink.sub(r'\1script_not_allowed\3', content)
        content = self.regexp_hyperlink_embedded.sub(r'\1script_not_allowed\3', content)
        return content

class UploadedAudioPreProcessor(object):

    # replaces all |audio|fileid| to some prevalue, later will be replaced in the
    # post processor to the flash applet

    def __call__(self, content):
        
        def repl_func(match):
            return "lahakaudio__%s__lahakaudio" % match.group(1)

        re_str = u"\|%s\|(\d+)\|" % _("audio")
         
        content = re.sub(re_str, repl_func,content)

        return content

# builtin special protocols dict, key is protocol name, value is a tuple of 2 element:
# regex_find, regex replace

YOUTUBE_STR = r"""
<object width="425" height="355"><param name="movie" value="http://www.youtube.com/v/\1"></param><param name="wmode" value="transparent"></param><embed src="http://www.youtube.com/v/\1" type="application/x-shockwave-flash" wmode="transparent" width="425" height="355"></embed></object>

"""

YOUTUBE_HELP = "youtube.com/watch?v=xxx "+ _("will be") +" xxx"

GOOGLE_VIDEO_STR = r"""
<embed style="width:400px; height:326px;" id="VideoPlayback" type="application/x-shockwave-flash" src="http://video.google.com/googleplayer.swf?docId=\1&amp;hl=en" flashvars=""> </embed>
"""

GOOGLE_VIDEO_HELP = "video.google.com/videoplay?docid=-xyz " + _("will be") + " -xyz"

FLICKR_STR = r"""
<iframe align="center" src="http://www.flickr.com/photos/\1/show/" frameborder="0" width="100%" height="500" scrolling="yes"></iframe>
"""

FLICKR_HELP = "flickr.com/photos/user_name/ "+ _("will be") +"  user_name, flickr.com/photos/user_name/tags/airplane/ " + _("will be") +" usrename/tags/airplane "

VIDEO_STR = r"""<embed height="268" width="320" flashvars='config={"videoFile":"\1","autoPlay":false,"autoBuffering":false}' pluginspage="http://www.adobe.com/go/getflashplayer" type="application/x-shockwave-flash" bgcolor="#ffffff" quality="high" allowscriptaccess="always" allowfullscreen="true" src="/media/swf/FlowPlayerDark.swf"/>"""

VIDEO_HELP = _("Link to any flash supported video")

BUILTIN_PROTOCOLOS={
    _('youtube'): (r'(.*)', YOUTUBE_STR, YOUTUBE_HELP),
    _('google_video'): (r'(.*)', GOOGLE_VIDEO_STR, GOOGLE_VIDEO_HELP),
    _('flickr'): (r'(.*)', FLICKR_STR, FLICKR_HELP),
    _('video'): (r'(.*)', VIDEO_STR, VIDEO_HELP),
}

class SpecialProtocolsPreProcessor(object):
    "Handles special protocols"

    def __init__(self):
        "Build a preprocessing regex"
        re_str = r"\|(%s)\|(.*?)\|" % '|'.join(BUILTIN_PROTOCOLOS.keys())

        self.protocols_re = re.compile(re_str, re.UNICODE)

    def __call__(self, content):

        return self.protocols_re.sub( r'lahakprotocol__\1__\2__lahakprotocol', content )