--- a/documentViewer.py	Wed Jul 23 17:20:34 2014 +0200
+++ b/documentViewer.py	Wed Jul 23 17:36:04 2014 +0200
@@ -21,9 +21,21 @@
 
 def getMDText(node):
     """returns the @text content from the MetaDataProvider metadata node"""
+
+    
+
     if isinstance(node, dict):
         return node.get('@text', None)
     
+    if isinstance(node,list): #more than one text file if there is an attribute don't choose it
+        for nodeInList in node:
+            attr = nodeInList.get("@attr",None)
+            if attr is None:
+                return node.get('@text',None)
+        return None
+
+
+
     return node
 
 def getParentPath(path, cnt=1):
@@ -82,6 +94,7 @@
     #
     # viewMode templates
     viewer_text = PageTemplateFile('zpt/viewer/viewer_text', globals())
+    viewer_hocr = PageTemplateFile('zpt/viewer/viewer_hocr', globals())
     viewer_xml = PageTemplateFile('zpt/viewer/viewer_xml', globals())
     viewer_image = PageTemplateFile('zpt/viewer/viewer_image', globals())
     viewer_index = PageTemplateFile('zpt/viewer/viewer_index', globals())
@@ -164,7 +177,11 @@
     # proxy text server methods to fulltextclient
     def getTextPage(self, **args):
         """returns full text content of page"""
+       
         return self.template.fulltextclient.getTextPage(**args)
+    
+   
+   
 
     def getSearchResults(self, **args):
         """loads list of search results and stores XML in docinfo"""
@@ -239,7 +256,7 @@
         show page
         @param url: url which contains display information
         @param mode: defines how to access the document behind url 
-        @param viewMode: 'image': display images, 'text': display text, 'xml': display xml, default is 'auto'
+        @param viewMode: 'image': display images, 'text': display text, 'xml': display xml, default is 'auto', 'hocr' : hocr format
         @param viewLayer: sub-type of viewMode, e.g. layer 'dict' for viewMode='text'
         @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
         """
@@ -250,7 +267,9 @@
             # this won't work
             logging.error("template folder missing!")
             return "ERROR: template folder missing!"
-            
+        
+        
+
         if not getattr(self, 'digilibBaseUrl', None):
             self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
             
@@ -287,6 +306,9 @@
             # legacy fix
             viewMode = 'image'
             self.REQUEST['viewMode'] = 'image'
+            
+        
+            
 
         # safe viewLayer in userinfo
         userinfo['viewLayer'] = viewLayer
@@ -532,6 +554,23 @@
             docUrl = getParentPath(url)
             metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
             docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1)
+            
+        elif mode=="hocr":
+            # url points to folder with images, index.meta optional
+            # asssume index.meta in parent dir
+            docUrl = getParentPath(url)
+            metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
+            docinfo['imagePath'] = url.replace('/mpiwg/online', '', 1)
+            docinfo['textURLPath'] = url.replace('/mpiwg/online', '', 1)
+            if docinfo.get("creator", None) is None:
+                docinfo['creator'] = "" 
+            
+            if docinfo.get("title", None) is None:
+                docinfo['title'] = "" 
+
+            if docinfo.get("documentPath", None) is None:
+                docinfo['documentPath'] = url.replace('/mpiwg/online', '', 1)
+                docinfo['documentPath'] = url.replace('/pages', '', 1)
 
         elif mode=="filepath":
             # url points to image file, index.meta optional
@@ -725,6 +764,10 @@
         
         # old style text URL
         textUrl = getMDText(texttool.get('text', None))
+
+        
+
+
         if textUrl and docPath:
             if urlparse.urlparse(textUrl)[0] == "": #keine url
                 textUrl = os.path.join(docPath, textUrl)