--- documentViewer/MpdlXmlTextServer.py	2010/08/24 10:17:06	1.18
+++ documentViewer/MpdlXmlTextServer.py	2010/10/05 12:56:02	1.55
@@ -52,11 +52,11 @@ class MpdlXmlTextServer(SimpleItem):
         queryType =pageinfo['queryType']
         viewMode=  pageinfo['viewMode']
         tocMode = pageinfo['tocMode']
-        #characterNormalization = pageinfo ['characterNormalization']
+        characterNormalization = pageinfo['characterNormalization']
         tocPN = pageinfo['tocPN']
         selfurl = self.absolute_url()
         
-        data = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery))
+        data = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,urllib.quote(highlightQuery)))
         #page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery) ,outputUnicode=False)                
         
         pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
@@ -72,7 +72,7 @@ class MpdlXmlTextServer(SimpleItem):
                         href = hrefNode.nodeValue
                         if href.startswith('page-fragment.xql'):
                             selfurl = self.absolute_url()            
-                            pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN))
+                            pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN))
                             hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)                                           
                 return serializeNode(pagenode)        
         if (queryType=="fulltextMorph"):
@@ -86,7 +86,7 @@ class MpdlXmlTextServer(SimpleItem):
                         href = hrefNode.nodeValue
                         if href.startswith('page-fragment.xql'):
                             selfurl = self.absolute_url()       
-                            pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN))
+                            pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN))
                             hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)  
                         if href.startswith('../lt/lemma.xql'):
                             hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl))        
@@ -122,32 +122,46 @@ class MpdlXmlTextServer(SimpleItem):
         """get list of pages from fulltext and put in docinfo"""
         if 'numPages' in docinfo:
             # already there
-            return docinfo
-        
+            return docinfo        
         xquery = '//pb'
         text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
-        #text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
         docinfo['numPages'] = text.count("<pb ")
         return docinfo
+     
+    def getNumTextPages (self, docinfo):
+        """get list of pages from fulltext (texts without images) and put in docinfo"""
+       # if 'numPages' in docinfo:
+            # allredy there
+        #    return docinfo
+       # xpath ='/count(//pb)'
+       # text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'], xpath))
+       # logging.debug("documentViewer (text) text: %s"%(text))
+        #docinfo['numPages']=text('resultPage')
+       # dom = Parse(text)
+        
+       # result= dom.xpath("//result/resultPage")
+       # docinfo['numPages']=int(getTextFromNode(result[0]))
+        #logging.debug("documentViewer (characterNormalization) docinfo['numPages']: %s"%(docinfo['numPages']))
+        return docinfo
        
-    def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=None):
+    def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=""):
         """returns single page from fulltext"""
         docpath = docinfo['textURLPath']
         path = docinfo['textURLPath']
         url = docinfo['url']
         viewMode= pageinfo['viewMode']
         tocMode = pageinfo['tocMode']
-        characterNormalization = pageinfo ['characterNormalization']
+        characterNormalization=pageinfo['characterNormalization']
         tocPN = pageinfo['tocPN']
         selfurl = self.absolute_url()   
         if mode == "text_dict":
             textmode = "textPollux"
         else:
             textmode = mode
-        logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
-        textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn)
+        #logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
+        textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
         if highlightQuery is not None:
-            textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn)           
+            textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)           
         
         pagexml = self.getServerData("page-fragment.xql",textParam)
         #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
@@ -165,7 +179,7 @@ class MpdlXmlTextServer(SimpleItem):
                     if hrefNode:
                         href= hrefNode.nodeValue
                         if href.startswith('#note-'):
-                            hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&characterNormalization=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,characterNormalization,tocPN,pn))
+                            hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
                 return serializeNode(pagenode)
         if mode == "xml":
               # first div contains text
@@ -178,6 +192,14 @@ class MpdlXmlTextServer(SimpleItem):
               pagedivs = pagedom.xpath("/div")
               if len(pagedivs) > 0:
                   pagenode = pagedivs[0]
+                  links =pagenode.xpath("//a")
+                  for l in links:
+                      hrefNode =l.getAttributeNodeNS(None, u"href")
+                      if hrefNode:
+                          href=hrefNode.nodeValue
+                          if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
+                              hrefNode.nodeValue =href.replace('chinagis_REST','chinagis')
+                              l.setAttributeNS(None, 'target', '_blank')
                   return serializeNode(pagenode)
                     
         if mode == "pureXml":
@@ -215,7 +237,7 @@ class MpdlXmlTextServer(SimpleItem):
                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
                             l.setAttributeNS(None, 'onClick', 'popupWin.focus();')   
                         if href.startswith('#note-'):
-                            hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&characterNormalization=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,characterNormalization,tocPN,pn))    
+                            hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))    
                 return serializeNode(pagenode)
         return "no text here"
 
@@ -236,7 +258,7 @@ class MpdlXmlTextServer(SimpleItem):
         data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
         #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
         return data
-
+    
     def getQuery (self,  docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
          """number of"""
          docpath = docinfo['textURLPath'] 
@@ -247,7 +269,7 @@ class MpdlXmlTextServer(SimpleItem):
          tocSearch = 0
          tocDiv = None
          
-         pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn))
+         pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn))
          #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False)
          pagedom = Parse(pagexml)
          numdivs = pagedom.xpath("//div[@class='queryResultHits']")
@@ -302,16 +324,15 @@ class MpdlXmlTextServer(SimpleItem):
         url = docinfo['url']
         selfurl = self.absolute_url()  
         viewMode=  pageinfo['viewMode']
-        characterNormalization =pageinfo ['characterNormalization']
+        characterNormalization = pageinfo ['characterNormalization']
         tocMode = pageinfo['tocMode']
         tocPN = pageinfo['tocPN']  
         
-        data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))  
-
-        page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&characterNormalization=%s'%(selfurl,url, viewMode, tocMode, tocPN, characterNormalization))
+        data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=%s"%(docpath,queryType, pagesize, pn,characterNormalization))  
+        page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
         text = page.replace('mode=image','mode=texttool')
         logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
-        logging.debug("documentViewer (characterNormalization) text: %s"%(text))
+        #logging.debug("documentViewer (characterNormalization) text: %s"%(text))
         return text
     
     def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):