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

Diff for /documentViewer/documentViewer.py between versions 1.43 and 1.69.2.1

version 1.43, 2010/03/19 11:42:40 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 87  class documentViewer(Folder): Line 92  class documentViewer(Folder):
   
     # templates and forms      # templates and forms
     viewer_main = PageTemplateFile('zpt/viewer_main', globals())      viewer_main = PageTemplateFile('zpt/viewer_main', globals())
     thumbs_main = PageTemplateFile('zpt/thumbs_main', globals())      toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
     image_main = PageTemplateFile('zpt/image_main', globals()) # obsolete!      toc_text = PageTemplateFile('zpt/toc_text', globals())
       toc_figures = PageTemplateFile('zpt/toc_figures', globals())
     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_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 161  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",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 images (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, 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 181  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)          
         pt = getattr(self.template, 'viewer_main')          
           if tocMode != "thumbs":
               # get table of contents
               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')               
         return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))          return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
       
     def generateMarks(self,mk):      def generateMarks(self,mk):
         ret=""          ret=""
     if mk is None:      if mk is None:
         return ""          return ""
       
     if type(mk) is not ListType:      if type(mk) is not ListType:
         mk=[mk]          mk=[mk]
         for m in mk:          for m in mk:
             ret+="mk=%s"%m              ret+="mk=%s"%m
         return ret          return ret
   
   
     def findDigilibUrl(self):      def findDigilibUrl(self):
         """try to get the digilib URL from zogilib"""          """try to get the digilib URL from zogilib"""
         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 343  class documentViewer(Folder): Line 363  class documentViewer(Folder):
                 dom = Parse(txt)                  dom = Parse(txt)
                 break                  break
             except:              except:
                 logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])                  logger("ERROR documentViewer (getIndexMeta)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])
                                   
         if dom is None:          if dom is None:
             raise IOError("Unable to read index meta from %s"%(url))              raise IOError("Unable to read index meta from %s"%(url))
Line 363  class documentViewer(Folder): Line 383  class documentViewer(Folder):
             server=self.digilibBaseUrl+"/servlet/Texter?fn="              server=self.digilibBaseUrl+"/servlet/Texter?fn="
             metaUrl=server+url.replace("/mpiwg/online","")              metaUrl=server+url.replace("/mpiwg/online","")
                         
           
         for cnt in range(num_retries):          for cnt in range(num_retries):
             try:              try:
                 # patch dirk encoding fehler treten dann nicht mehr auf                  # patch dirk encoding fehler treten dann nicht mehr auf
Line 461  class documentViewer(Folder): Line 480  class documentViewer(Folder):
         logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))          logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))
         if docinfo is None:          if docinfo is None:
            docinfo = {}             docinfo = {}
               
         if docinfo.get('lang', None) is None:          if docinfo.get('lang', None) is None:
             docinfo['lang'] = '' # default keine Sprache gesetzt              docinfo['lang'] = '' # default keine Sprache gesetzt
         if dom is None:          if dom is None:
Line 535  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 547  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 555  class documentViewer(Folder): Line 576  class documentViewer(Folder):
         return docinfo          return docinfo
   
   
   
      
      
     def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):      def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
         """gets the bibliographical information from the preseantion entry in texttools          """gets the bibliographical information from the preseantion entry in texttools
         """          """
Line 618  class documentViewer(Folder): Line 636  class documentViewer(Folder):
             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)              docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
         else:          else:
             logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")              logger("documentViewer (getdocinfo)", logging.ERROR,"unknown mode!")
             raise ValueError("Unknown mode %s"%(mode))              raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
                                                   
         logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)          logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)
         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):  
         """returns pageinfo with the given parameters"""          """returns pageinfo with the given parameters"""
         pageinfo = {}          pageinfo = {}
         current = getInt(current)          current = getInt(current)
Line 640  class documentViewer(Folder): Line 657  class documentViewer(Folder):
         # int(current / grpsize) * grpsize +1))          # int(current / grpsize) * grpsize +1))
         pageinfo['start'] = start          pageinfo['start'] = start
         pageinfo['end'] = start + grpsize          pageinfo['end'] = start + grpsize
         if docinfo is not None:          if (docinfo is not None) and ('numPages' in docinfo):
             np = int(docinfo['numPages'])              np = int(docinfo['numPages'])
             pageinfo['end'] = min(pageinfo['end'], np)              pageinfo['end'] = min(pageinfo['end'], np)
             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['tocMode'] = tocMode
           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')
           toc = int (pageinfo['tocPN'])
           pageinfo['textPages'] =int (toc)
           
           if 'tocSize_%s'%tocMode in docinfo:
               tocSize = int(docinfo['tocSize_%s'%tocMode])
               tocPageSize = int(pageinfo['tocPageSize'])
               # cached toc           
               if tocSize%tocPageSize>0:
                   tocPages=tocSize/tocPageSize+1
               else:
                   tocPages=tocSize/tocPageSize
               pageinfo['tocPN'] = min (tocPages,toc)                    
           pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
           pageinfo['sn'] =self.REQUEST.get('sn','')
         return pageinfo          return pageinfo
                                   
   def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
   
     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"""  
         pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'],mode,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 == "textPollux":  
             # 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 changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):  
         """init document viewer"""          """init document viewer"""
         self.title=title          self.title=title
         self.digilibBaseUrl = digilibBaseUrl          self.digilibBaseUrl = digilibBaseUrl
Line 707  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 722  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.1.43  
changed lines
  Added in v.1.69.2.1

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