--- documentViewer/MpdlXmlTextServer.py	2010/08/24 12:43:24	1.23
+++ documentViewer/MpdlXmlTextServer.py	2010/10/18 10:01:16	1.168
@@ -42,8 +42,6 @@ class MpdlXmlTextServer(SimpleItem):
         """get search list"""
         docpath = docinfo['textURLPath'] 
         url = docinfo['url']
-        logging.debug("documentViewer (gettoc) docpath: %s"%(docpath))
-        logging.debug("documentViewer (gettoc) url: %s"%(url))
         pagesize = pageinfo['queryPageSize']
         pn = pageinfo['searchPN']
         sn = pageinfo['sn']
@@ -52,11 +50,11 @@ 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 +70,7 @@ 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 +84,7 @@ 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))        
@@ -118,23 +116,91 @@ class MpdlXmlTextServer(SimpleItem):
                 return serializeNode(pagenode)      
         return "no text here"   
                        
-    def getNumPages(self, docinfo):
-        """get list of pages from fulltext and put in docinfo"""
+    """def getNumPages(self, docinfo):
+        ""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))
+        dom = Parse(text)
+        result= dom.xpath("//result/resultPage")
+        docinfo['numPages']=int(getTextFromNode(result[0]))
+        return docinfo
+    
+    def getGisPlaces(self, docinfo=None, pageinfo=None):
+        """ Show all Gis Places of whole Page"""
+        xpath='//place'
+        docpath = docinfo['textURLPath'] 
+        url = docinfo['url']
+        selfurl = self.absolute_url()
+        pn = pageinfo['current']
+        hrefList=[]
+        myList= ""
+        text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
+        dom = Parse(text)
+        result = dom.xpath("//result/resultPage/place")
+        for l in result:
+            hrefNode= l.getAttributeNodeNS(None, u"id")
+            href= hrefNode.nodeValue
+            hrefList.append(href)
+            myList = ",".join(hrefList)
+        logging.debug("getGisPlaces :%s"%(myList))                             
+        return myList
+    
+    def getAllGisPlaces (self, docinfo=None, pageinfo=None):
+        """Show all Gis Places of whole Book """
+        xpath ='//echo:place'
+        docpath =docinfo['textURLPath']
+        url = docinfo['url']
+        selfurl =self.absolute_url()
+        pn =pageinfo['current']
+        hrefList=[]
+        myList=""
+        text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
+        dom =Parse(text)
+        result = dom.xpath("//result/resultPage/place")
+        for l in result:
+            hrefNode = l.getAttributeNodeNS(None, u"id")
+            href= hrefNode.nodeValue
+            hrefList.append(href)
+            myList = ",".join(hrefList)
+            logging.debug("getALLGisPlaces :%s"%(myList))
+        return myList
+    
+    def getOrigPages (self, docinfo=None):
+        """Show original page """
+        #docpath = docinfo['textURLPath'] 
+        #url = docinfo['url']
+        selfurl = self.absolute_url()
+        pn =pageinfo['current']
        
-    def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=None):
+        viewMode=  pageinfo['viewMode']
+        text = self.getServerData("page-fragment.xql","document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'], 'text',  pn))
+        dom =Parse(text)
+        pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
+        if len(pagedivs)>0:
+            docinfo['originalPage'] = getTextFromNode(pagedivs[0])
+            #return docinfo['originalPage']
+            #return originalPage
+            return docinfo
+        
+    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']
+        name = docinfo['name']
         viewMode= pageinfo['viewMode']
         tocMode = pageinfo['tocMode']
         characterNormalization=pageinfo['characterNormalization']
@@ -145,9 +211,9 @@ class MpdlXmlTextServer(SimpleItem):
         else:
             textmode = mode
         #logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
-        textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn)
+        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 +231,7 @@ class MpdlXmlTextServer(SimpleItem):
                     if hrefNode:
                         href= hrefNode.nodeValue
                         if href.startswith('#note-'):
-                            hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&characterNormalization=%s#note-"%(url,viewMode,tocMode,tocPN,pn,characterNormalization))
+                            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 +244,14 @@ 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/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)
+                              l.setAttributeNS(None, 'target', '_blank') 
                   return serializeNode(pagenode)
                     
         if mode == "pureXml":
@@ -236,7 +310,7 @@ 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 +321,7 @@ 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']")
@@ -302,7 +376,7 @@ 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']