Mercurial > hg > documentViewer

changeset 141:39c7d6164da8

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
characterNormalization (reg,norm, none)
author abukhman
date Thu, 12 Aug 2010 12:08:24 +0200
parents 6345583d809a
children 83e35adb92d3
files MpdlXmlTextServer.py documentViewer.py
diffstat 2 files changed, 14 insertions(+), 9 deletions(-) [+]
line wrap: on
line diff
--- a/MpdlXmlTextServer.py	Wed Aug 11 12:17:46 2010 +0200
+++ b/MpdlXmlTextServer.py	Thu Aug 12 12:08:24 2010 +0200
@@ -57,6 +57,7 @@
         queryType =pageinfo['queryType']
         viewMode=  pageinfo['viewMode']
         tocMode = pageinfo['tocMode']
+        characterNormalization = pageinfo ['characterNormalization']
         tocPN = pageinfo['tocPN']
         selfurl = self.absolute_url()
         
@@ -76,7 +77,7 @@
                         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&characterNormalization=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN,characterNormalization))
                             hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)                                           
                 return serializeNode(pagenode)        
         if (queryType=="fulltextMorph"):
@@ -90,7 +91,7 @@
                         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&characterNormalization=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN,characterNormalization))
                             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))        
@@ -108,7 +109,7 @@
                     hrefNode = l.getAttributeNodeNS(None, u"href")
                     if hrefNode:
                         href = hrefNode.nodeValue
-                        hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))             
+                        hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&characterNormalization=%s'%(viewMode,tocMode,tocPN,pn,characterNormalization))             
                         if href.startswith('../lt/lex.xql'):
                             hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)         
                             l.setAttributeNS(None, 'target', '_blank')
@@ -134,13 +135,14 @@
         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 getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None, characterNormalization=None):
         """returns single page from fulltext"""
         docpath = docinfo['textURLPath']
         path = docinfo['textURLPath']
         url = docinfo['url']
         viewMode= pageinfo['viewMode']
         tocMode = pageinfo['tocMode']
+        characterNormalization = pageinfo ['characterNormalization']
         tocPN = pageinfo['tocPN']
         selfurl = self.absolute_url()   
         if mode == "text_dict":
@@ -168,7 +170,7 @@
                     if hrefNode:
                         href= hrefNode.nodeValue
                         if href.startswith('#note-'):
-                            hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))
+                            hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&characterNormalization=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,characterNormalization,tocPN,pn))
                 return serializeNode(pagenode)
         if mode == "xml":
               # first div contains text
@@ -218,7 +220,7 @@
                             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&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))    
+                            hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&characterNormalization=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,characterNormalization,tocPN,pn))    
                 return serializeNode(pagenode)
         return "no text here"
 
@@ -305,12 +307,13 @@
         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))  
 
-        page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
+        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))
         text = page.replace('mode=image','mode=texttool')
         return text
     
--- a/documentViewer.py	Wed Aug 11 12:17:46 2010 +0200
+++ b/documentViewer.py	Thu Aug 12 12:08:24 2010 +0200
@@ -226,13 +226,14 @@
         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):
+    def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=None):
         '''
         view it
         @param mode: defines how to access the document behind url 
         @param url: url which contains display information
         @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
         @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
+        @param characterNormalization type of text display (reg, norm, none)
         @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
         '''
         
@@ -677,7 +678,7 @@
         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=None):
         """returns pageinfo with the given parameters"""
         pageinfo = {}
         current = getInt(current)
@@ -700,6 +701,7 @@
                 pageinfo['numgroups'] += 1        
         pageinfo['viewMode'] = viewMode
         pageinfo['tocMode'] = tocMode
+        pageinfo['characterNormalization'] =characterNormalization
         pageinfo['query'] = self.REQUEST.get('query',' ')
         pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
         pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')