--- MPIWGWeb/xmlhelper.py	2012/01/09 07:33:31	1.6.2.2
+++ MPIWGWeb/xmlhelper.py	2012/02/15 11:51:47	1.6.2.3
@@ -16,6 +16,9 @@ import xml.dom.minidom
 
 #from Ft.Lib import Uri
 
+from xml.etree import ElementTree
+import logging
+
 xml2html={'WEB_normal':('<p>','</p>'),'Normal':('<p>','</p>'),'WEB_picture':('<p class=\"picture\">','</p>'),'WEB_figuretitle':('<p class=\"picturetitle\">','</p>'),'WEB_bibliography':('<p><i>','</i></p>'),'Web_kursiv':('<i>','</i>'),'WEB_kursiv':('<i>','</i>'),'WEB_hyperlink':('',''),'Hyperlink':('','')}
 
 def addToDict(dict,name,value):
@@ -32,23 +35,33 @@ def addToDict(dict,name,value):
 def proj2hash(xmlstring):
     """wandelt xml-files fuer die projekte in ein hash"""
     
-    dom=xml.dom.minidom.parseString(xmlstring)
+    #dom=xml.dom.minidom.parseString(xmlstring)
     
-        
+    tree = ElementTree.fromstring(xmlstring)
+    
+
+    pars = tree.findall(".//part[0]/par")
+
     list={}
 
     #gettitle
-    pars=Evaluate('par',dom.getElementsByTagName('part')[0])
+    #part= dom.getElementsByTagName('part')[0]
+    #pars=part.getElementsByTagName('par')
+    #pars=Evaluate('par',dom.getElementsByTagName('part')[0])
+    logging.debug(pars)
     for par in pars:
-        className=par.getAttribute('class')
-        content=getText(par.childNodes)
+        logging.debug(par)
+        className=par.attrib['class']
+        #.getAttribute('class')
+        content=par.text
         addToDict(list,className,content)
              
-    list.update(parseTable(dom.getElementsByTagName('html:table')[0])) # Parse the Table
+    list.update(parseTable(tree.find('.//{http://www.w3.org/HTML/1998/html4}table'))) # Parse the Table
 
     #evaluate level 1
-
-    sections=Evaluate('section',dom.getElementsByTagName('part')[0])# Parse all Sections
+    sections = tree.findall(".//part[0]/section")
+    #sections=Evaluate('section',dom.getElementsByTagName('part')[0])# Parse all Sections
+    #sections=Evaluate('section',dom.getElementsByTagName('part')[0])# Parse all Sections
     #print sections,dom.getElementsByTagName('part')[0]
     for section in sections:
 
@@ -62,10 +75,11 @@ def proj2hash(xmlstring):
             addToDict(list,sec[0],sec[2])
 
     #evaluate higher level sections
-
-    sections=Evaluate('section/section',dom.getElementsByTagName('part')[0])
+    sections = tree.findall(".//part[0]/section/section")
+    #sections=Evaluate('section/section',dom.getElementsByTagName('part')[0])
 
     for section in sections:
+        logging.debug("sections2:"+repr(section))
         sec=parseSection(section)
         
         if sec[0]=="WEB_project_header": # Sonderfall project
@@ -81,63 +95,80 @@ def proj2hash(xmlstring):
 def parseSection(section):
     type=""
     header=""
-    for heading in section.childNodes:
-        if getattr(heading,'tagName','')=="heading":
-            
-            type=heading.getAttribute('class')
-            header=getText(heading.childNodes)
-
+    #for heading in section.childNodes:
+    
+    heading=section.find(".//heading")
+       # if getattr(heading,'tagName','')=="heading":
+    
+    
+    type=heading.attrib['class']
+    logging.debug("parseSection (class):"+type)
+    header=heading.text
+    logging.debug("parseSection (header):"+header)
+    
     if type=="": # falls heading fehlt, pruefe ob erster par richtig
-        par=section.getElementsByTagName('par')[0]
-        type=par.getAttribute('class')
-        header=getText(par.childNodes)
+        par=section.find(".//par")
+        #par=section.getElementsByTagName('par')[0]
+        type=par.attrib['class']
+        header=par.text
         
     #print section.childNodes
-    pars=Evaluate('par',section)
+    pars=section.findall(".//par")
+    #pars=Evaluate('par',section)
     content=par2html(pars)
     
     return (type,header,content)
 
 def parseTable(table):
     fields={}
-    rows=table.getElementsByTagName('html:tr')
+    rows=table.findall('.//{http://www.w3.org/HTML/1998/html4}tr')
+    #rows=table.getElementsByTagName('html:tr')
     for row in rows:
-        #print "ROW"
-        cols=row.getElementsByTagName('html:td')
+        logging.debug("ROW")
+        cols=row.findall('.//{http://www.w3.org/HTML/1998/html4}td')
+        #cols=row.getElementsByTagName('html:td')
         
         #Name des Datenfeldes einlesen
         try:
-            field=cols[0].getElementsByTagName('par')[0].getAttribute('class')
+            field=cols[0].find('.//par').attrib['class']
+            #field=cols[0].getElementsByTagName('par')[0].getAttribute('class')
             #print "field",field
         except:
-            print "error"
+            logging.debug("error")
             field=""
 
         #Wandeln der Eintrge in HTML
-
-        pars=cols[1].getElementsByTagName('par')
+        
+        pars=cols[1].findall('.//par')
+        #pars=cols[1].getElementsByTagName('par')
 
         
         html=par2html(pars,tags=("",";"))
-        
+        logging.debug("field:"+field)
+        logging.debug("html:"+html)
         addToDict(fields,field,html)
         #print fields
     return fields
 
 def par2html(pars,tags=None):
     #html=""
-
+    logging.debug("part2html:"+repr(pars))
+    if pars is None:
+        return ""
     for par in pars:
-        #print "par",par
+        logging.debug("part2html:"+repr(par))
         if not tags:
             try:
-                tag=xml2html[par.getAttribute('class')]
+                tag=xml2html[par.attrib['class']]
             except:
                 tag=('<p>','</p>')
         else:
             tag=tags
         
-        content=getText(par.childNodes)
+        content=par.text
+        if content is None:
+            content=""
+        logging.debug("part2html:"+content)
         #print "CONTETN",content
         
         #print par.getAttribute('class'),node