[BACK]Return to documentViewer.py CVS log [TXT] [DIR] Up to [Repository] / documentViewer

Diff for /documentViewer/documentViewer.py between versions 1.44 and 1.69.2.1

version 1.44, 2010/04/08 11:04:51 version 1.69.2.1, 2010/06/14 10:49:48
Line 2 Line 2
 from OFS.Folder import Folder  from OFS.Folder import Folder
 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate  from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
 from Products.PageTemplates.PageTemplateFile import PageTemplateFile   from Products.PageTemplates.PageTemplateFile import PageTemplateFile 
   from Products.PythonScripts.standard import url_quote
 from AccessControl import ClassSecurityInfo  from AccessControl import ClassSecurityInfo
 from AccessControl import getSecurityManager  from AccessControl import getSecurityManager
 from Globals import package_home  from Globals import package_home
Line 10  from Ft.Xml.Domlette import Nonvalidatin Line 11  from Ft.Xml.Domlette import Nonvalidatin
 from Ft.Xml.Domlette import PrettyPrint, Print  from Ft.Xml.Domlette import PrettyPrint, Print
 from Ft.Xml import EMPTY_NAMESPACE, Parse  from Ft.Xml import EMPTY_NAMESPACE, Parse
   
   from xml.dom.minidom import parse, parseString
   
   from extraFunction import *
   
   
 import Ft.Xml.XPath  import Ft.Xml.XPath
 import cStringIO  import cStringIO
Line 74  def urlopen(url,timeout=2): Line 79  def urlopen(url,timeout=2):
 ##  ##
 ## documentViewer class  ## documentViewer class
 ##  ##
 class documentViewer(Folder):  class documentViewer(Folder, extraFunction):
     """document viewer"""      """document viewer"""
     #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"      #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
           
Line 93  class documentViewer(Folder): Line 98  class documentViewer(Folder):
     page_main_images = PageTemplateFile('zpt/page_main_images', globals())      page_main_images = PageTemplateFile('zpt/page_main_images', globals())
     page_main_text = PageTemplateFile('zpt/page_main_text', globals())      page_main_text = PageTemplateFile('zpt/page_main_text', globals())
     page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())      page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals())
       page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
     head_main = PageTemplateFile('zpt/head_main', globals())      head_main = PageTemplateFile('zpt/head_main', globals())
     docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())      docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
     info_xml = PageTemplateFile('zpt/info_xml', globals())      info_xml = PageTemplateFile('zpt/info_xml', globals())
   
       
     thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())      thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
     security.declareProtected('View management screens','changeDocumentViewerForm')          security.declareProtected('View management screens','changeDocumentViewerForm')    
     changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())      changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
   
           
     def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):      def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
         """init document viewer"""          """init document viewer"""
         self.id=id          self.id=id
         self.title=title          self.title=title
Line 163  class documentViewer(Folder): Line 170  class documentViewer(Folder):
         return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)          return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
       
     security.declareProtected('View','index_html')      security.declareProtected('View','index_html')
     def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):      def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
         '''          '''
         view it          view it
         @param mode: defines how to access the document behind url           @param mode: defines how to access the document behind url 
         @param url: url which contains display information          @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 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)          @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
           @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
         '''          '''
                   
         logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))          logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
Line 183  class documentViewer(Folder): Line 191  class documentViewer(Folder):
             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"              self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
                           
         docinfo = self.getDocinfo(mode=mode,url=url)          docinfo = self.getDocinfo(mode=mode,url=url)
         pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)          
           
         if tocMode != "thumbs":          if tocMode != "thumbs":
             # get table of contents              # get table of contents
             docinfo = self.getToc(mode=tocMode, docinfo=docinfo)              docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
   
         if viewMode=="auto": # automodus gewaehlt          if viewMode=="auto": # automodus gewaehlt
             if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert              if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
                 viewMode="text"                  viewMode="text_dict"
             else:              else:
                 viewMode="images"                  viewMode="images"
                                   
           pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
           
         pt = getattr(self.template, 'viewer_main')                         pt = getattr(self.template, 'viewer_main')               
         return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))          return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
       
Line 213  class documentViewer(Folder): Line 224  class documentViewer(Folder):
         url = self.template.zogilib.getDLBaseUrl()          url = self.template.zogilib.getDLBaseUrl()
         return url          return url
           
       def getDocumentViewerURL(self):
           """returns the URL of this instance"""
           return self.absolute_url()
       
     def getStyle(self, idx, selected, style=""):      def getStyle(self, idx, selected, style=""):
         """returns a string with the given style and append 'sel' if path == selected."""          """returns a string with the given style and append 'sel' if path == selected."""
         #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))          #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
Line 538  class documentViewer(Folder): Line 553  class documentViewer(Folder):
         if textUrls and (len(textUrls) > 0):          if textUrls and (len(textUrls) > 0):
             textUrl = getTextFromNode(textUrls[0])              textUrl = getTextFromNode(textUrls[0])
             docinfo['textURLPath'] = textUrl                 docinfo['textURLPath'] = textUrl   
               if not docinfo['imagePath']:
                   # text-only, no page images
                   docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht    
                     
         presentationUrls = dom.xpath("//texttool/presentation")          presentationUrls = dom.xpath("//texttool/presentation")
         docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get info von bib tag          docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get info von bib tag
Line 550  class documentViewer(Folder): Line 568  class documentViewer(Folder):
                 presentationUrl = url.replace('index.meta', presentationPath)                  presentationUrl = url.replace('index.meta', presentationPath)
             else:              else:
                 presentationUrl = url + "/" + presentationPath                  presentationUrl = url + "/" + presentationPath
             docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht                      
             docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)              docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
           
         docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get access info          docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get access info
Line 624  class documentViewer(Folder): Line 642  class documentViewer(Folder):
         self.REQUEST.SESSION['docinfo'] = docinfo          self.REQUEST.SESSION['docinfo'] = docinfo
         return 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):
         """returns pageinfo with the given parameters"""          """returns pageinfo with the given parameters"""
         pageinfo = {}          pageinfo = {}
Line 646  class documentViewer(Folder): Line 663  class documentViewer(Folder):
             pageinfo['numgroups'] = int(np / grpsize)              pageinfo['numgroups'] = int(np / grpsize)
             if np % grpsize > 0:              if np % grpsize > 0:
                 pageinfo['numgroups'] += 1                  pageinfo['numgroups'] += 1
                   
         pageinfo['viewMode'] = viewMode          pageinfo['viewMode'] = viewMode
         pageinfo['tocMode'] = tocMode          pageinfo['tocMode'] = tocMode
         pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '10')          pageinfo['query'] = self.REQUEST.get('query',' ')
           pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
           pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
           pageinfo['textPN'] = self.REQUEST.get('textPN','1')
           pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
           pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
           pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
         pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')          pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
           toc = int (pageinfo['tocPN'])
           pageinfo['textPages'] =int (toc)
   
         return pageinfo          if 'tocSize_%s'%tocMode in docinfo:
                               tocSize = int(docinfo['tocSize_%s'%tocMode])
               tocPageSize = int(pageinfo['tocPageSize'])
   
     def getNumPages(self,docinfo=None):  
         """get list of pages from fulltext and put in docinfo"""  
         xquery = '//pb'  
         text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))  
         # TODO: better processing of the page list. do we need the info somewhere else also?  
         docinfo['numPages'] = text.count("<pb ")  
         return docinfo  
          
     def getTextPage(self, mode="text", pn=1, docinfo=None):  
         """returns single page from fulltext"""  
         docpath = docinfo['textURLPath']  
         if mode == "text_dict":  
             textmode = "textPollux"  
         else:  
             textmode = mode  
               
         pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False)  
         # post-processing downloaded xml  
         pagedom = Parse(pagexml)  
         # plain text mode  
         if mode == "text":  
             # first div contains text  
             pagedivs = pagedom.xpath("/div")  
             if len(pagedivs) > 0:  
                 pagenode = pagedivs[0]  
                 return serializeNode(pagenode)  
   
         # text-with-links mode  
         if mode == "text_dict":  
             # first div contains text  
             pagedivs = pagedom.xpath("/div")  
             if len(pagedivs) > 0:  
                 pagenode = pagedivs[0]  
                 # check all a-tags  
                 links = pagenode.xpath("//a")  
                 for l in links:  
                     hrefNode = l.getAttributeNodeNS(None, u"href")  
                     if hrefNode:  
                         # is link with href  
                         href = hrefNode.nodeValue  
                         if href.startswith('lt/lex.xql'):  
                             # is pollux link  
                             selfurl = self.absolute_url()  
                             # change href  
                             hrefNode.nodeValue = href.replace('lt/lex.xql','%s/head_main_voc'%selfurl)  
                             # add target  
                             l.setAttributeNS(None, 'target', '_blank')  
                 return serializeNode(pagenode)  
           
         return "no text here"  
   
     def getToc(self, mode="text", docinfo=None):  
         """loads table of contents and stores in docinfo"""  
         logging.debug("documentViewer (gettoc) mode: %s"%(mode))  
         if 'tocSize_%s'%mode in docinfo:  
             # cached toc              # cached toc
             return docinfo              if tocSize%tocPageSize>0:
                           tocPages=tocSize/tocPageSize+1
         docpath = docinfo['textURLPath']  
         # we need to set a result set size  
         pagesize = 1000  
         pn = 1  
         if mode == "text":  
             queryType = "toc"  
         else:  
             queryType = mode  
         # number of entries in toc  
         tocSize = 0  
         tocDiv = None  
         pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)  
         # post-processing downloaded xml  
         pagedom = Parse(pagexml)  
         # get number of entries  
         numdivs = pagedom.xpath("//div[@class='queryResultHits']")  
         if len(numdivs) > 0:  
             tocSize = int(getTextFromNode(numdivs[0]))  
             # div contains text  
             #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")  
             #if len(pagedivs) > 0:  
             #    tocDiv = pagedivs[0]  
   
         docinfo['tocSize_%s'%mode] = tocSize  
         #docinfo['tocDiv_%s'%mode] = tocDiv  
         return docinfo  
       
     def getTocPage(self, mode="toc", pn=1, pageinfo=None, docinfo=None):  
         """returns single page from the table of contents"""  
         # TODO: this should use the cached TOC  
         if mode == "text":  
             queryType = "toc"  
         else:  
             queryType = mode  
         docpath = docinfo['textURLPath']  
         pagesize = pageinfo['tocPageSize']  
         pn = pageinfo['tocPN']  
         pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)  
         # post-processing downloaded xml  
         pagedom = Parse(pagexml)  
         # div contains text  
         pagedivs = pagedom.xpath("//div[@class='queryResultPage']")  
         if len(pagedivs) > 0:  
             pagenode = pagedivs[0]  
             return serializeNode(pagenode)  
         else:          else:
             return "No TOC!"                  tocPages=tocSize/tocPageSize
               pageinfo['tocPN'] = min (tocPages,toc)                    
           pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
           pageinfo['sn'] =self.REQUEST.get('sn','')
           return pageinfo
           
     def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):  def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
         """init document viewer"""          """init document viewer"""
         self.title=title          self.title=title
         self.digilibBaseUrl = digilibBaseUrl          self.digilibBaseUrl = digilibBaseUrl
Line 773  class documentViewer(Folder): Line 699  class documentViewer(Folder):
         if RESPONSE is not None:          if RESPONSE is not None:
             RESPONSE.redirect('manage_main')              RESPONSE.redirect('manage_main')
           
       
           
 def manage_AddDocumentViewerForm(self):  def manage_AddDocumentViewerForm(self):
     """add the viewer form"""      """add the viewer form"""
     pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)      pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
Line 788  def manage_AddDocumentViewer(self,id,ima Line 712  def manage_AddDocumentViewer(self,id,ima
     if RESPONSE is not None:      if RESPONSE is not None:
         RESPONSE.redirect('manage_main')          RESPONSE.redirect('manage_main')
   
   
 ##  
 ## DocumentViewerTemplate class  ## DocumentViewerTemplate class
 ##  
 class DocumentViewerTemplate(ZopePageTemplate):  class DocumentViewerTemplate(ZopePageTemplate):
     """Template for document viewer"""      """Template for document viewer"""
     meta_type="DocumentViewer Template"      meta_type="DocumentViewer Template"
Removed from v.1.44  
changed lines
  Added in v.1.69.2.1

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>