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

Diff for /documentViewer/documentViewer.py between versions 1.10 and 1.21

version 1.10, 2006/04/12 18:53:00 version 1.21, 2007/01/11 20:27:17
Line 1 Line 1
   
   
 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
Line 7  from Globals import package_home Line 9  from Globals import package_home
   
 from Ft.Xml.Domlette import NonvalidatingReader  from Ft.Xml.Domlette import NonvalidatingReader
 from Ft.Xml.Domlette import PrettyPrint, Print  from Ft.Xml.Domlette import PrettyPrint, Print
 from Ft.Xml import EMPTY_NAMESPACE  from Ft.Xml import EMPTY_NAMESPACE, Parse
   
 import Ft.Xml.XPath  import Ft.Xml.XPath
   
Line 15  import os.path Line 17  import os.path
 import sys  import sys
 import cgi  import cgi
 import urllib  import urllib
   import logging
 import zLOG  import zLOG
   import urlparse 
   
 def getInt(number, default=0):  def getInt(number, default=0):
     """returns always an int (0 in case of problems)"""      """returns always an int (0 in case of problems)"""
Line 25  def getInt(number, default=0): Line 29  def getInt(number, default=0):
         return default          return default
   
 def getTextFromNode(nodename):  def getTextFromNode(nodename):
       """get the cdata content of a node"""
     if nodename is None:      if nodename is None:
         return ""          return ""
     nodelist=nodename.childNodes      nodelist=nodename.childNodes
Line 55  def urlopen(url,timeout=2): Line 60  def urlopen(url,timeout=2):
 ##  ##
 class documentViewer(Folder):  class documentViewer(Folder):
     """document viewer"""      """document viewer"""
       #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?"
   
     meta_type="Document viewer"      meta_type="Document viewer"
           
Line 74  class documentViewer(Folder): Line 80  class documentViewer(Folder):
     changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())      changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
   
           
     def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):      def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):
         """init document viewer"""          """init document viewer"""
         self.id=id          self.id=id
         self.title=title          self.title=title
         self.imageViewerUrl=imageViewerUrl          self.imageViewerUrl=imageViewerUrl
           self.textViewerUrl=textViewerUrl
           
         if not digilibBaseUrl:          if not digilibBaseUrl:
             self.digilibBaseUrl = self.findDigilibUrl()              self.digilibBaseUrl = self.findDigilibUrl()
         else:          else:
Line 92  class documentViewer(Folder): Line 100  class documentViewer(Folder):
   
   
     security.declareProtected('View','index_html')      security.declareProtected('View','index_html')
     def index_html(self,mode,url,start=None,pn=1):      def index_html(self,mode,url,viewMode="auto",start=None,pn=1):
         '''          '''
         view it          view it
         @param mode: defines which type of document is behind url          @param mode: defines which type of document is behind url (text,images or auto)
         @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
           
         '''          '''
                   
         zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))          zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
Line 111  class documentViewer(Folder): Line 121  class documentViewer(Folder):
         docinfo = self.getDocinfo(mode=mode,url=url)          docinfo = self.getDocinfo(mode=mode,url=url)
         pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)          pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
         pt = getattr(self.template, 'viewer_main')          pt = getattr(self.template, 'viewer_main')
         return pt(docinfo=docinfo,pageinfo=pageinfo)          
           if viewMode=="auto": # automodus gewaehlt
               if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert
                   viewMode="text"
               else:
                   viewMode="images"
                   
           return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
       
       
     def getLink(self,param=None,val=None):      def getLink(self,param=None,val=None):
Line 142  class documentViewer(Folder): Line 159  class documentViewer(Folder):
     def isAccessible(self, docinfo):      def isAccessible(self, docinfo):
         """returns if access to the resource is granted"""          """returns if access to the resource is granted"""
         access = docinfo.get('accessType', None)          access = docinfo.get('accessType', None)
         if access is None:          zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "access type %s"%access)
             # no information - no access           if access is not None and access == 'free':
             #TODO: check              zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "access is free")
             return True  
         elif access == 'free':  
             return True              return True
         elif access in self.authgroups:          elif access is None or access in self.authgroups:
             # only local access -- only logged in users              # only local access -- only logged in users
             user = getSecurityManager().getUser()              user = getSecurityManager().getUser()
             if user is not None:              if user is not None:
Line 163  class documentViewer(Folder): Line 178  class documentViewer(Folder):
                                   
     def getDirinfoFromDigilib(self,path,docinfo=None):      def getDirinfoFromDigilib(self,path,docinfo=None):
         """gibt param von dlInfo aus"""          """gibt param von dlInfo aus"""
           num_retries = 3
         if docinfo is None:          if docinfo is None:
             docinfo = {}              docinfo = {}
                           
         imageUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path          infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
           
         zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(imageUrl))          zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(infoUrl))
                   
         for cnt in (1,2,3):          for cnt in range(num_retries):
             try:              try:
                 dom = NonvalidatingReader.parseUri(imageUrl)                  # dom = NonvalidatingReader.parseUri(imageUrl)
                   txt=urllib.urlopen(infoUrl).read()
                   dom = Parse(txt)
                 break                  break
             except:              except:
                 zLOG.LOG("documentViewer (getdirinfofromdigilib)", zLOG.ERROR, "error reading %s (try %d)"%(imageUrl,cnt))                  zLOG.LOG("documentViewer (getdirinfofromdigilib)", zLOG.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))
         else:          else:
             raise IOError("Unable to get dir-info from %s"%(imageUrl))              raise IOError("Unable to get dir-info from %s"%(infoUrl))
                   
         sizes=dom.xpath("//dir/size")          sizes=dom.xpath("//dir/size")
         zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%sizes)          zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%sizes)
Line 192  class documentViewer(Folder): Line 210  class documentViewer(Folder):
                           
     def getIndexMeta(self, url):      def getIndexMeta(self, url):
         """returns dom of index.meta document at url"""          """returns dom of index.meta document at url"""
           num_retries = 3
         dom = None          dom = None
           metaUrl = None
         if url.startswith("http://"):          if url.startswith("http://"):
             # real URL              # real URL
             try:              metaUrl = url
                 dom = NonvalidatingReader.parseUri(url)  
             except:  
                 zLOG.LOG("documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])  
                 raise IOError("Unable to read index.meta from %s"%(url))  
         else:          else:
             # online path              # online path
             server=self.digilibBaseUrl+"/servlet/Texter?fn="              server=self.digilibBaseUrl+"/servlet/Texter?fn="
             metaUrl=server+url              metaUrl=server+url.replace("/mpiwg/online","")
             if not metaUrl.endswith("index.meta"):              if not metaUrl.endswith("index.meta"):
                 metaUrl += "/index.meta"                  metaUrl += "/index.meta"
           print metaUrl
           for cnt in range(num_retries):
             try:              try:
                 dom = NonvalidatingReader.parseUri(metaUrl)                  # patch dirk encoding fehler treten dann nicht mehr auf
                   # dom = NonvalidatingReader.parseUri(metaUrl)
                   txt=urllib.urlopen(metaUrl).read()
                   dom = Parse(txt)
                   break
             except:              except:
                 zLOG.LOG("documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])                  zLOG.LOG("ERROR documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])
                   
           if dom is None:
                 raise IOError("Unable to read index meta from %s"%(url))                  raise IOError("Unable to read index meta from %s"%(url))
                                     
         return dom          return dom
                                                   
       def getPresentationInfoXML(self, url):
           """returns dom of info.xml document at url"""
           num_retries = 3
           dom = None
           metaUrl = None
           if url.startswith("http://"):
               # real URL
               metaUrl = url
           else:
               # online path
               server=self.digilibBaseUrl+"/servlet/Texter?fn="
               metaUrl=server+url.replace("/mpiwg/online","")
              
           
           for cnt in range(num_retries):
               try:
                   # patch dirk encoding fehler treten dann nicht mehr auf
                   # dom = NonvalidatingReader.parseUri(metaUrl)
                   txt=urllib.urlopen(metaUrl).read()
                   dom = Parse(txt)
                   break
               except:
                   zLOG.LOG("ERROR documentViewer (getPresentationInfoXML)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])
                   
           if dom is None:
               raise IOError("Unable to read infoXMLfrom %s"%(url))
                    
           return dom
                           
                   
     def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None):      def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None):
         """gets authorization info from the index.meta file at path or given by dom"""          """gets authorization info from the index.meta file at path or given by dom"""
Line 274  class documentViewer(Folder): Line 327  class documentViewer(Folder):
        if dom is None:         if dom is None:
            dom = self.getIndexMeta(url)             dom = self.getIndexMeta(url)
                 
          archivePath = None
          archiveName = None
   
        archiveNames=dom.xpath("//resource/name")         archiveNames=dom.xpath("//resource/name")
        if archiveNames and (len(archiveNames)>0):         if archiveNames and (len(archiveNames)>0):
            archiveName=getTextFromNode(archiveNames[0])             archiveName=getTextFromNode(archiveNames[0])
          else:
              zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.WARNING,"resource/name missing in: %s"%(url))
                 
        archivePaths=dom.xpath("//resource/archive-path")         archivePaths=dom.xpath("//resource/archive-path")
        if archivePaths and (len(archivePaths)>0):         if archivePaths and (len(archivePaths)>0):
Line 284  class documentViewer(Folder): Line 342  class documentViewer(Folder):
            # clean up archive path             # clean up archive path
            if archivePath[0] != '/':             if archivePath[0] != '/':
                archivePath = '/' + archivePath                 archivePath = '/' + archivePath
            if not archivePath.endswith(archiveName):             if archiveName and (not archivePath.endswith(archiveName)):
                archivePath += "/" + archiveName                 archivePath += "/" + archiveName
        else:         else:
            archivePath=None             # try to get archive-path from url
              zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.WARNING,"resource/archive-path missing in: %s"%(url))
              if (not url.startswith('http')):
                  archivePath = url.replace('index.meta', '')
                  
          if archivePath is None:
              # we balk without archive-path
              raise IOError("Missing archive-path (for text-tool) in %s"%(url))
                 
        imageDirs=dom.xpath("//texttool/image")         imageDirs=dom.xpath("//texttool/image")
        if imageDirs and (len(imageDirs)>0):         if imageDirs and (len(imageDirs)>0):
Line 312  class documentViewer(Folder): Line 377  class documentViewer(Folder):
        textUrls=dom.xpath("//texttool/text")         textUrls=dom.xpath("//texttool/text")
        if textUrls and (len(textUrls)>0):         if textUrls and (len(textUrls)>0):
            textUrl=getTextFromNode(textUrls[0])             textUrl=getTextFromNode(textUrls[0])
              if urlparse.urlparse(textUrl)[0]=="": #keine url
                  textUrl=os.path.join(archivePath,textUrl) 
   
            docinfo['textURL'] = textUrl             docinfo['textURL'] = textUrl
                                             
      
          presentationUrls=dom.xpath("//texttool/presentation")
          if presentationUrls and (len(presentationUrls)>0):
               # presentation url ergiebt sich ersetzen von index.meta in der url der fŸr die Metadaten
               # durch den relativen Pfad auf die presentation infos
              presentationUrl=url.replace('index.meta',getTextFromNode(presentationUrls[0]))
              
              docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom)
          else:
        docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)         docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
        docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)         docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
        return docinfo         return docinfo
         
   
       def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
           """gets the bibliographical information from the preseantion entry in texttools
           """
           dom=self.getPresentationInfoXML(url)
           docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
           docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
           docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
           return docinfo
       
     def getDocinfoFromImagePath(self,path,docinfo=None):      def getDocinfoFromImagePath(self,path,docinfo=None):
         """path ist the path to the images it assumes that the index.meta file is one level higher."""          """path ist the path to the images it assumes that the index.meta file is one level higher."""
         zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path))          zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path))
Line 440  class documentViewer(Folder): Line 526  class documentViewer(Folder):
     def findDigilibUrl(self):      def findDigilibUrl(self):
         """try to get the digilib URL from zogilib"""          """try to get the digilib URL from zogilib"""
         url = self.imageViewerUrl[:-1] + "/getScalerUrl"          url = self.imageViewerUrl[:-1] + "/getScalerUrl"
           #print urlparse.urlparse(url)[0]
           #print urlparse.urljoin(self.absolute_url(),url)
           logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0])
           logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url))
           
         try:          try:
               if urlparse.urlparse(url)[0]=='': #relative path
                   url=urlparse.urljoin(self.absolute_url()+"/",url)
                   
             scaler = urlopen(url).read()              scaler = urlopen(url).read()
             return scaler.replace("/servlet/Scaler?", "")              return scaler.replace("/servlet/Scaler?", "")
         except:          except:
             return None              return None
           
     def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):      def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
         """init document viewer"""          """init document viewer"""
         self.title=title          self.title=title
         self.imageViewerUrl=imageViewerUrl          self.imageViewerUrl=imageViewerUrl
           self.textViewerUrl=textViewerUrl
         self.digilibBaseUrl = digilibBaseUrl          self.digilibBaseUrl = digilibBaseUrl
         self.thumbrows = thumbrows          self.thumbrows = thumbrows
         self.thumbcols = thumbcols          self.thumbcols = thumbcols
Line 467  def manage_AddDocumentViewerForm(self): Line 562  def manage_AddDocumentViewerForm(self):
     pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)      pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
     return pt()      return pt()
       
 def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None):  def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None):
     """add the viewer"""      """add the viewer"""
     newObj=documentViewer(id,imageViewerUrl,title)      newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl)
     self._setObject(id,newObj)      self._setObject(id,newObj)
           
     if RESPONSE is not None:      if RESPONSE is not None:
Removed from v.1.10  
changed lines
  Added in v.1.21

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