--- documentViewer/MpdlXmlTextServer.py	2010/07/15 13:16:52	1.6
+++ documentViewer/MpdlXmlTextServer.py	2010/10/15 10:30:52	1.145
@@ -1,7 +1,6 @@
 
 from OFS.SimpleItem import SimpleItem
 from Products.PageTemplates.PageTemplateFile import PageTemplateFile 
-
 from Ft.Xml import EMPTY_NAMESPACE, Parse
 
 import sys
@@ -10,7 +9,6 @@ import urllib
 import documentViewer
 from documentViewer import getTextFromNode, serializeNode
 
-
 class MpdlXmlTextServer(SimpleItem):
     """TextServer implementation for MPDL-XML eXist server"""
     meta_type="MPDL-XML TextServer"
@@ -30,19 +28,16 @@ class MpdlXmlTextServer(SimpleItem):
             self.serverUrl = serverUrl
         else:
             self.serverUrl = "http://%s/mpdl/interface/"%serverName
-
         
     def getHttpData(self, url, data=None):
         """returns result from url+data HTTP request"""
         return documentViewer.getHttpData(url,data,timeout=self.timeout)
-
     
     def getServerData(self, method, data=None):
         """returns result from text server for method+data"""
         url = self.serverUrl+method
         return documentViewer.getHttpData(url,data,timeout=self.timeout)
 
-
     def getSearch(self, pn=1, pageinfo=None,  docinfo=None, query=None, queryType=None, lemma=None):
         """get search list"""
         docpath = docinfo['textURLPath'] 
@@ -57,10 +52,11 @@ class MpdlXmlTextServer(SimpleItem):
         queryType =pageinfo['queryType']
         viewMode=  pageinfo['viewMode']
         tocMode = pageinfo['tocMode']
+        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)
@@ -76,7 +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"):
@@ -90,7 +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))        
@@ -122,35 +118,88 @@ 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 getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None):
+     """
+    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 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']
         tocPN = pageinfo['tocPN']
         selfurl = self.absolute_url()   
         if mode == "text_dict":
             textmode = "textPollux"
         else:
             textmode = mode
-        
-        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)
@@ -176,6 +225,21 @@ class MpdlXmlTextServer(SimpleItem):
               if len(pagedivs) > 0:
                   pagenode = pagedivs[0]
                   return serializeNode(pagenode)
+        if mode == "gis":
+              # first div contains text
+              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":
               # first div contains text
               pagedivs = pagedom.xpath("/div")
@@ -232,7 +296,7 @@ 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'] 
@@ -243,7 +307,7 @@ 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']")
@@ -298,13 +362,15 @@ class MpdlXmlTextServer(SimpleItem):
         url = docinfo['url']
         selfurl = self.absolute_url()  
         viewMode=  pageinfo['viewMode']
+        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))  
-
+        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))
         return text
     
     def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):