--- documentViewer/documentViewer.py	2010/08/12 11:45:59	1.80
+++ documentViewer/documentViewer.py	2010/10/05 12:55:29	1.102
@@ -16,6 +16,7 @@ import logging
 import math
 import urlparse 
 import cStringIO
+import re
 
 def logger(txt,method,txt2):
     """logging"""
@@ -176,7 +177,11 @@ class documentViewer(Folder):
     def getNumPages(self, docinfo):
         """get numpages"""
         return self.template.fulltextclient.getNumPages(docinfo)
-
+   
+    def getNumTextPages(self, docinfo):
+        """get numpages text"""
+        return self.template.fulltextclient.getNumTextPages(docinfo)
+   
     def getTranslate(self, **args):
         """get translate"""
         return self.template.fulltextclient.getTranslate(**args)
@@ -226,7 +231,7 @@ class documentViewer(Folder):
         return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
   
     security.declareProtected('View','index_html')
-    def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=None):
+    def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
         '''
         view it
         @param mode: defines how to access the document behind url 
@@ -390,10 +395,18 @@ class documentViewer(Folder):
                         
         return docinfo
     
-            
-    def getIndexMeta(self, url):
-        """returns dom of index.meta document at url"""
-        dom = None
+    def getIndexMetaPath(self,url):
+        """gib nur den Pfad zurueck"""
+        regexp = re.compile(r".*(experimental|permanent)/(.*)")
+        regpath = regexp.match(url)
+        if (regpath==None):
+            return ""
+                     
+        return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
+     
+    def getIndexMetaUrl(self,url):
+        """returns utr  of index.meta document at url"""
+      
         metaUrl = None
         if url.startswith("http://"):
             # real URL
@@ -404,8 +417,15 @@ class documentViewer(Folder):
             metaUrl=server+url.replace("/mpiwg/online","")
             if not metaUrl.endswith("index.meta"):
                 metaUrl += "/index.meta"
+        
+        return metaUrl
+    
+    def getDomFromIndexMeta(self, url):
+        """get dom from index meta"""
+        dom = None
+        metaUrl = self.getIndexMetaUrl(url)
                 
-        logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)
+        logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
         txt=getHttpData(metaUrl)
         if txt is None:
             raise IOError("Unable to read index meta from %s"%(url))
@@ -445,7 +465,7 @@ class documentViewer(Folder):
         if dom is None:
             for x in range(cut):
                 path=getParentDir(path)
-            dom = self.getIndexMeta(path)
+            dom = self.getDomFromIndexMeta(path)
        
         acctype = dom.xpath("//access-conditions/access/@type")
         if acctype and (len(acctype)>0):
@@ -467,7 +487,9 @@ class documentViewer(Folder):
         if dom is None:
             for x in range(cut):
                 path=getParentDir(path)
-            dom = self.getIndexMeta(path)
+            dom = self.getDomFromIndexMeta(path)
+        
+        docinfo['indexMetaPath']=self.getIndexMetaPath(path);
         
         logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
         # put in all raw bib fields as dict "bib"
@@ -489,6 +511,8 @@ class documentViewer(Folder):
         bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
         docinfo['bib_type'] = bibtype
         bibmap=metaData.generateMappingForType(bibtype)
+        logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
+        logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
         # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
         if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
             try:
@@ -517,7 +541,7 @@ class documentViewer(Folder):
         if docinfo.get('lang', None) is None:
             docinfo['lang'] = '' # default keine Sprache gesetzt
         if dom is None:
-            dom = self.getIndexMeta(url)
+            dom = self.getDomFromIndexMeta(url)
         
         archivePath = None
         archiveName = None
@@ -678,7 +702,7 @@ class documentViewer(Folder):
         self.REQUEST.SESSION['docinfo'] = docinfo
         return docinfo
                
-    def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
+    def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
         """returns pageinfo with the given parameters"""
         pageinfo = {}
         current = getInt(current)
@@ -701,7 +725,8 @@ class documentViewer(Folder):
                 pageinfo['numgroups'] += 1        
         pageinfo['viewMode'] = viewMode
         pageinfo['tocMode'] = tocMode
-        pageinfo['characterNormalization'] = self.REQUEST.get ('characterNormalization', 'norm')
+        #pageinfo['characterNormalization'] =characterNormalization
+        pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
         pageinfo['query'] = self.REQUEST.get('query',' ')
         pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
         pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')