Changeset 378 for collective.imstransport/trunk/collective/imstransport/utilities/bb/bbreader.py

Timestamp:

07/13/09 14:26:21 (4 years ago)

Author:

jon

Message:

Changing blackboard import to accomodate tufts blackboard packages

File:

• collective.imstransport/trunk/collective/imstransport/utilities/bb/bbreader.py (modified) (5 diffs)

collective.imstransport/trunk/collective/imstransport/utilities/bb/bbreader.py

@@ -1 +1 @@
 from xml.dom import minidom
+from urlparse import urlparse
 from collective.imstransport.IMS_exceptions import ManifestError
-from configbb import LOM_BB_namespace, XML_namespace
+from configbb import LOM_BB_namespace, XML_namespace, EMBEDDED_STRING
+from Products.PageTemplates.PageTemplateFile import PageTemplateFile
+from collective.imstransport.utilities.interfaces import IIMSTransportUtility
 
 class BBReader(object):
@@ -53 +56 @@
                 resource.getAttributeNS(XML_namespace, 'base'))
 
-    def readFiles(self, resource):
+    def readFiles(self, resource, bbase):
         files = []
         flns = resource.getElementsByTagName('file')
@@ -59 +62 @@
             for fln in flns:
                 file = fln.getAttribute('href')
-                files.append(file)
+                if bbase:
+                    files.append('%s/%s' %(bbase, file))
+                else:
+                    files.append(file)
         return files
 
@@ -93 +99 @@
                     value = isfolder_nodes[0].getAttribute('value')
                     if value ==  'true':
-                        md['type'] = 'Folder'
+                        md['bbtype'] = 'Folder'
+            handler_nodes = content_node.getElementsByTagName('CONTENTHANDLER')
+            if handler_nodes:
+                value = handler_nodes[0].getAttribute('value')
+                if value == 'resource/x-bb-externallink':
+                    url_nodes = content_node.getElementsByTagName('URL')
+                    if url_nodes:
+                        url = url_nodes[0].getAttribute('value') 
+                        if url:
+                            md['bbtype'] = 'Link'
+                            md['remoteUrl'] = url        
 
     def readTocItem(self, manifest, resid):
@@ -107 +123 @@
                     idref = item.getAttribute('identifierref')
                     if idref == resid:
-                        childitems = item.getElementsByTagName('item')
+                        childitems = item.childNodes
                         for x in childitems:
-                            itemid = x.getAttribute('identifierref')
-                            tocitems.append(itemid)
+                            if x.nodeName == 'item':
+                                itemid = x.getAttribute('identifierref')
+                                tocitems.append(itemid)
         return tocitems
+
+    def readEmbeddedTags(self, soup):
+        """ Read embedded tags from a text file """
+        prevlink = None
+        links = self.getDocumentHrefLinks(soup)
+        for link in links:
+            if 'embedded' in link['href']:
+                if prevlink and prevlink != link['href']:
+                    return None
+                prevlink = link['href']
+        links = self.getDocumentSrcLinks(soup)
+        for link in links:
+            if 'embedded' in link['src']:
+                if prevlink  and prevlink != link['src']:
+                    return None
+        return prevlink
+
+    def createTocPage(self, entries):
+        """ Create a table of links """
+        text = '<table>'
+        for z in entries:
+            text += "<tr><td><a href='%s'>%s</a></td></tr>" %(z[0], z[1])
+        text += '</table>'
+        return text
+
+    def runDocumentFilters(self, utils, soup, vars, base):
+        """ Run a filter over the links """
+        links = []
+        links = self.getDocumentHrefLinks(soup)
+        for link in links:
+            orig = link['href']
+            link['href'] = self.filterDocumentLink(link['href'], utils, vars, base)
+        links = []
+        links = self.getDocumentSrcLinks(soup)
+        for link in links:
+            orig = link['src']
+            link['src'] = self.filterDocumentLink(link['src'], utils, vars, base)
+        return soup.prettify()
+
+    def getDocumentHrefLinks(self, soup):
+        links = []
+        tags = soup.findAll(href=True)
+        from urlparse import urlparse
+        for tag in tags:
+            if tag.has_key('href'):
+                url = urlparse('href')
+                if not url[1] or 'localhost' in url[1]:
+                    links.append(tag)
+        return links
+
+    def getDocumentSrcLinks(self, soup):
+        links = []
+        tags = soup.findAll(src=True)
+        from urlparse import urlparse
+        for tag in tags:
+            if tag.has_key('src'):
+                url = urlparse('src')
+                if not url[1] or 'localhost' in url[1]:
+                    links.append(tag)
+        return links
+
+    def _convertBBVariables(self, link, vars, base):
+        """ Convert BB variables to their counterparts """
+        lnk = link
+        for var in vars:
+            if base:
+                replace = '%s/%s/' %(base, var[1])
+            else:
+                replace = var[1]
+            lnk = link.replace(var[0], replace)
+        return lnk
+
+    def _convertURLEntities(self, link):
+        """ Convert BB variables to their counterparts """
+        lnk = link
+        import urllib
+        lnk = urllib.unquote(lnk)
+        return lnk
+
+    def _convertToNormalizedLink(self, link, utils):
+        """ Normalize the link so it can be imported without errors """
+        lnk = link
+        url = urlparse(lnk)
+        urlfile = url[2].split('/')
+        urlfile[-1] = utils.normalizeString(urlfile[-1])
+        lnk = '/'.join(urlfile)
+        return lnk
+        
+    def filterDocumentLink(self, link, utils, vars, base):
+        lnk = link
+        from urlparse import urlparse
+        url = urlparse(lnk)
+        if url[2] and not url[0]:
+            lnk = self._convertBBVariables(lnk, vars, base)
+            lnk = self._convertURLEntities(lnk)
+            lnk = self._convertToNormalizedLink(lnk, utils)
+        return lnk
+
+    def runFilters(self, text, filters, **kw):
+        rettext = text
+        for filter in filters:
+            if 'embed' == filter:
+                rettext = self.replaceEmbedVariables(rettext, kw['base'])
+            elif 'reflinks' == filter:
+                rettext = self.rewriteReferenceLinks(rettext)
+        return rettext
+
+    def replaceEmbedVariables(self, text, base):
+        """ Remove the proprietary embed variables and replace with proper path """
+        if base:
+            rpath = '%s/embed/' %base
+        return text.replace(EMBEDDED_STRING, rpath)
+
+    def rewriteReferenceLinks(self, text):
+        """ Rewrite all reference links """
+
+    def removeUrlEntities(self, href):
+        """ Remove the URL entities from the string """
+        
+        
+
+
+
+        
+
+
+
+
+        
+