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

Timestamp:

07/13/09 14:26:21 (3 years ago)

Author:

jon

Message:

Changing blackboard import to accomodate tufts blackboard packages

Files:

• collective.imstransport/trunk/collective/imstransport/utilities/bb/imsbbreader.py (modified) (3 diffs)

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

@@ -6 +6 @@
 from xml.parsers.expat import ExpatError
 from collective.imstransport.IMS_exceptions import ManifestError
+from BeautifulSoup import BeautifulSoup
+from Products.CMFCore.interfaces import ISiteRoot
+import htmlentitydefs
+from configbb import EMBEDDED_STRING
 import re
 
@@ -30 +34 @@
         for x in resources:
             resid, restype, bbfile, bbtitle, bbase = bbreader.readResourceAttributes(x)
+            doctext = filetoc = restoc = ''
+            metadata = {}
             if restype == 'resource/x-bb-document':
                 metadata = {}
@@ -37 +43 @@
                     resnode = bbreader.parseDataFile(dataxml)
                     metadata = bbreader.readMetadata(resnode)
-                files = bbreader.readFiles(x)
-                # If the resource is a file
-                if files:
-                    hash = resid
-                    objDict[hash] = metadata
-                    excludeFromNav = True
-                    file = '%s/%s' %(bbase, files[0])
-                    type = self.determineType(objDict[hash], files[0])
-                    id = self.createIdFromFile(files[0])
-                    path = '%s' %bbase
-                    if orgs.has_key(resid):
-                        title = orgs[resid]
+                if metadata.has_key('text') and metadata['text']:
+                    mtext = metadata['text']                    
+                    if type(mtext) == type(u''):
+                        mtext = mtext.encode('utf-8')
+                    ptext = unquotehtml(mtext)
+                    utils = getUtility(ISiteRoot).plone_utils
+                    soup = BeautifulSoup(ptext)
+                    doctext = bbreader.runDocumentFilters(utils, soup, [(EMBEDDED_STRING, 'embedded'),], bbase)
+                # Handle Files
+                files = bbreader.readFiles(x, bbase)
+                entries = []
+                for y in files:
+                    dhash = resid + y
+                    objDict[dhash] = {}
+                    dexcludeFromNav = True
+                    dfile = y
+                    dfileparts = y.split('/')
+                    # File is embedded
+                    if 'embedded' in y:
+                        # Link is encrypted
+                        if len(dfileparts) > 0 and dfileparts[-1][0] == '!' and doctext:
+                            soup = BeautifulSoup(doctext)
+                            embeddedpath = bbreader.readEmbeddedTags(soup)
+                            if embeddedpath:
+                                dfile = embeddedpath
+                    dfilepath = self.createPathFromFile(dfile)
+                    did = self.createIdFromFile(dfile)
+                    dtype = self.determineType(objDict[dhash], dfile)
+                    portal = getUtility(ISiteRoot)
+                    utils = portal.plone_utils
+                    did = utils.normalizeString(did)
+                    dtitle = did
+                    if dfilepath:
+                        linkpath = '%s/%s' %(dfilepath, did)
                     else:
-                        title = id
-                    self.applyCoreMetadata(objDict, hash, id, path, excludeFromNav, type, title, file=file)
-                # If the resource is a document
-                else:
-                    hash = resid 
-                    objDict[hash] = metadata
-                    excludeFromNav = True
-                    type = 'Document'
-                    id = resid
-                    path = ''
-                    if orgs.has_key(resid):
-                        title = orgs[resid]
-                    else:
-                        title = id
-                    self.applyCoreMetadata(objDict, hash, id, path, excludeFromNav, type, title)
-            # The resource is a table of contents page.
-            elif restype == 'course/x-bb-coursetoc':
+                        linkpath = did
+                    binfile = y
+                    folder_files = source.getFolderFiles(dfilepath)
+                    if len(folder_files) == 1:
+                        binfile = folder_files[0]
+                    entries.append((linkpath, dtitle))
+                    self.applyCoreMetadata(objDict[dhash], did, dfilepath, dexcludeFromNav, dtype, dtitle, file=binfile)
+                if entries:
+                    filetoc = bbreader.createTocPage(entries)
+            # Handle links
+            if metadata.has_key('bbtype') and metadata['bbtype'] == 'Link':
                 hash = resid
-                objDict[hash] = {}
-                excludeFromNav = False
-                tocpages.append(resid)
-                type = 'Document'
-                path = ''
-                id = resid
+                objDict[hash] = metadata
+                filepath = ''
+                id = resid + '.link'
+                excludeFromNav = True
+                ptype = metadata['bbtype']
                 if orgs.has_key(resid):
-                    title = re.sub('(((?<=[a-z])[A-Z])|([A-Z](?![A-Z]|$)))', ' \\1', orgs[resid].split('.')[1])
+                    title = orgs[resid]
                 else:
                     title = id
-                self.applyCoreMetadata(objDict, hash, id, path, excludeFromNav, type, title)
-
-            # Build table of contents pages
+                self.applyCoreMetadata(objDict[hash], id, filepath, excludeFromNav, ptype, title)
+            elif restype in ['resource/x-bb-document', 'course/x-bb-coursetoc']:
+                # Handle normal bb-documents
+                hash = resid
+                objDict[hash] = metadata
+                filepath = ''
+                excludeFromNav = True
+                ptype = 'Document'
+                id = resid + '.html'
+                if orgs.has_key(resid):
+                    title = orgs[resid]
+                else:
+                    title = id
+                # It's a folder object:
+                isFolder = metadata.has_key('bbtype') and metadata['bbtype'] == 'Folder'
+                if isFolder or restype == 'course/x-bb-coursetoc':
+                    tocpages.append(resid)
+                # It's a table of contents object
+                if restype == 'course/x-bb-coursetoc':
+                    if orgs.has_key(resid):
+                        excludeFromNav = False
+                        orgstitle = orgs[resid].split('.')
+                        # Rewrite label tag
+                        if len(orgstitle) > 1 and orgstitle[-1] == 'label':
+                            title = re.sub('(((?<=[a-z])[A-Z])|([A-Z](?![A-Z]|$)))', ' \\1', orgs[resid].split('.')[1])
+                text = doctext
+                if type(filetoc) == type(u''):
+                    text += filetoc.encode('utf-8')
+                self.applyCoreMetadata(objDict[hash], id, filepath, excludeFromNav, ptype, title, text=text)
+        # Build table of contents pages
         for z in tocpages:
-            text = '<table>'
             tocitems = bbreader.readTocItem(doc, z)
+            entries = []
             for titem in tocitems:
-                met = objDict[titem]
-                path = met['path']
-                if path:
-                    linkpath = '%s/%s' %(path, objDict[titem]['id'])
+                if objDict.has_key(titem):
+                    met = objDict[titem]
+                    path = met['path']
+                    if path:
+                        linkpath = '%s/%s' %(path, objDict[titem]['id'])
+                    else:
+                        linkpath = objDict[titem]['id']
+                    entries.append((linkpath, met['title']))
+            if entries:
+                if objDict[z].has_key('text') and objDict[z]['text']:
+                    gtext = objDict[z]['text']
+                    if type(gtext) == type(u''):
+                        gtext = gtext.encode('utf-8')
+                    objDict[z]['text'] = bbreader.createTocPage(entries).encode('utf-8') + gtext
                 else:
-                    linkpath = objDict[titem]['id']
-                text += "<tr><td><a href='%s/view'>%s</a></td></tr>" %(linkpath, objDict[titem]['title'])
-            text += '</table>'
-            objDict[z]['text'] = text
-                
+                    objDict[z]['text'] = bbreader.createTocPage(entries).encode('utf-8')
+            else:
+                objDict[z]['excludeFromNav'] = True
         objcreator = getUtility(IIMSObjectCreator)
         objcreator.createObjects(objDict, context, source)
 
-    def applyCoreMetadata(self, objDict, hash, id, path, excludeFromNav, type, title, file=None, text=None):
+    def applyCoreMetadata(self, metadata, id, path, excludeFromNav, type, title, file=None, text=None):
         """ Helper function for applying metadata """
-        objDict[hash]['id'] = id
-        objDict[hash]['path'] = path
-        objDict[hash]['excludeFromNav'] = excludeFromNav
-        if not (objDict[hash].has_key('type') and objDict[hash]['type']):
-            objDict[hash]['type'] = type
-        if not (objDict[hash].has_key('title') and objDict[hash]['title']):
-            objDict[hash]['title'] = title
+        portal = getUtility(ISiteRoot)
+        utils = portal.plone_utils
+        metadata['id'] = utils.normalizeString(id)
+        metadata['path'] = path
+        metadata['excludeFromNav'] = excludeFromNav
+        metadata['type'] = type
+        if not (metadata.has_key('title') and metadata['title']):
+            metadata['title'] = title
         if file:
-            objDict[hash]['file'] =  file
+            metadata['file'] =  file
         if text:
-            objDict[hash]['text'] = text
+            metadata['text'] = text
 
+def convertentity(m):
+    """Convert a HTML entity into normal string (ISO-8859-1)"""
+    if m.group(1)=='#':
+        try:
+            return chr(int(m.group(2)))
+        except ValueError:
+            return '&#%s;' % m.group(2)
+    try:
+        return htmlentitydefs.entitydefs[m.group(2)]
+    except KeyError:
+        return '&%s;' % m.group(2)
+
+def unquotehtml(s):
+    """Convert a HTML quoted string into normal string (ISO-8859-1).
+
+    Works with &#XX; and with &nbsp; &gt; etc."""
+    return re.sub(r'&(#?)(.+?);',convertentity,s)