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

Diff for /documentViewer/documentViewer.py between versions 1.43 and 1.175.2.3

version 1.43, 2010/03/19 11:42:40 version 1.175.2.3, 2011/07/15 19:34:41
Line 5  from Products.PageTemplates.PageTemplate Line 5  from Products.PageTemplates.PageTemplate
 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
   from Products.zogiLib.zogiLib import browserCheck
   
 from Ft.Xml.Domlette import NonvalidatingReader  #from Ft.Xml import EMPTY_NAMESPACE, Parse 
 from Ft.Xml.Domlette import PrettyPrint, Print  #import Ft.Xml.Domlette
 from Ft.Xml import EMPTY_NAMESPACE, Parse  
   
   import xml.etree.ElementTree as ET
   
 import Ft.Xml.XPath  
 import cStringIO  
 import xmlrpclib  
 import os.path  import os.path
 import sys  import sys
 import cgi  
 import urllib  import urllib
   import urllib2
 import logging  import logging
 import math  import math
   
 import urlparse   import urlparse 
 from types import *  import re
   import string
   
 def logger(txt,method,txt2):  def logger(txt,method,txt2):
     """logging"""      """logging"""
Line 36  def getInt(number, default=0): Line 34  def getInt(number, default=0):
     except:      except:
         return int(default)          return int(default)
   
 def getTextFromNode(nodename):  def getText(node):
     """get the cdata content of a node"""      """get the cdata content of a node"""
     if nodename is None:      if node is None:
         return ""          return ""
     nodelist=nodename.childNodes      # ET:
     rc = ""      text = node.text or ""
     for node in nodelist:      for e in node:
         if node.nodeType == node.TEXT_NODE:          text += gettext(e)
            rc = rc + node.data          if e.tail:
     return rc              text += e.tail
   
       # 4Suite:
       #nodelist=node.childNodes
       #text = ""
       #for n in nodelist:
       #    if n.nodeType == node.TEXT_NODE:
       #       text = text + n.data
       
       return text
   
 def serializeNode(node, encoding='utf-8'):  getTextFromNode = getText
   
   def serializeNode(node, encoding="utf-8"):
     """returns a string containing node as XML"""      """returns a string containing node as XML"""
     buf = cStringIO.StringIO()      s = ET.tostring(node)
     Print(node, stream=buf, encoding=encoding)      
     s = buf.getvalue()      # 4Suite:
     buf.close()      #    stream = cStringIO.StringIO()
       #    Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
       #    s = stream.getvalue()
       #    stream.close()
     return s      return s
   
   def browserCheck(self):
       """check the browsers request to find out the browser type"""
       bt = {}
       ua = self.REQUEST.get_header("HTTP_USER_AGENT")
       bt['ua'] = ua
       bt['isIE'] = False
       bt['isN4'] = False
       bt['versFirefox']=""
       bt['versIE']=""
       bt['versSafariChrome']=""
       bt['versOpera']=""
       
       if string.find(ua, 'MSIE') > -1:
           bt['isIE'] = True
       else:
           bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
       # Safari oder Chrome identification    
       try:
           nav = ua[string.find(ua, '('):]
           nav1=ua[string.find(ua,')'):]
           nav2=nav1[string.find(nav1,'('):]
           nav3=nav2[string.find(nav2,')'):]
           ie = string.split(nav, "; ")[1]
           ie1 =string.split(nav1, " ")[2]
           ie2 =string.split(nav3, " ")[1]
           ie3 =string.split(nav3, " ")[2]
           if string.find(ie3, "Safari") >-1:
               bt['versSafariChrome']=string.split(ie2, "/")[1]
       except: pass
       # IE identification
       try:
           nav = ua[string.find(ua, '('):]
           ie = string.split(nav, "; ")[1]
           if string.find(ie, "MSIE") > -1:
               bt['versIE'] = string.split(ie, " ")[1]
       except:pass
       # Firefox identification
       try:
           nav = ua[string.find(ua, '('):]
           nav1=ua[string.find(ua,')'):]
           if string.find(ie1, "Firefox") >-1:
               nav5= string.split(ie1, "/")[1]
               logging.debug("FIREFOX: %s"%(nav5))
               bt['versFirefox']=nav5[0:3]                   
       except:pass
       #Opera identification
       try:
           if string.find(ua,"Opera") >-1:
               nav = ua[string.find(ua, '('):]
               nav1=nav[string.find(nav,')'):]
               bt['versOpera']=string.split(nav1,"/")[2]
       except:pass
       
       bt['isMac'] = string.find(ua, 'Macintosh') > -1
       bt['isWin'] = string.find(ua, 'Windows') > -1
       bt['isIEWin'] = bt['isIE'] and bt['isWin']
       bt['isIEMac'] = bt['isIE'] and bt['isMac']
       bt['staticHTML'] = False
   
       return bt
   
                   
 def getParentDir(path):  def getParentDir(path):
     """returns pathname shortened by one"""      """returns pathname shortened by one"""
     return '/'.join(path.split('/')[0:-1])      return '/'.join(path.split('/')[0:-1])
                   
   
   def getHttpData(url, data=None, num_tries=3, timeout=10):
       """returns result from url+data HTTP request"""
       # we do GET (by appending data to url)
       if isinstance(data, str) or isinstance(data, unicode):
           # if data is string then append
           url = "%s?%s"%(url,data)
       elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple):
           # urlencode
           url = "%s?%s"%(url,urllib.urlencode(data))
       
       response = None
       errmsg = None
       for cnt in range(num_tries):
           try:
               logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url))
               if sys.version_info < (2, 6):
                   # set timeout on socket -- ugly :-(
 import socket  import socket
                   socket.setdefaulttimeout(float(timeout))
                   response = urllib2.urlopen(url)
               else:
                   response = urllib2.urlopen(url,timeout=float(timeout))
               # check result?
               break
           except urllib2.HTTPError, e:
               logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e))
               errmsg = str(e)
               # stop trying
               break
           except urllib2.URLError, e:
               logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e))
               errmsg = str(e)
               # stop trying
               #break
   
       if response is not None:
           data = response.read()
           response.close()
           return data
   
 def urlopen(url,timeout=2):      raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
         """urlopen mit timeout"""      #return None
         socket.setdefaulttimeout(timeout)  
         ret=urllib.urlopen(url)  
         socket.setdefaulttimeout(5)  
         return ret  
   
   
 ##  ##
 ## documentViewer class  ## documentViewer class
 ##  ##
 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"
           
     security=ClassSecurityInfo()      security=ClassSecurityInfo()
Line 87  class documentViewer(Folder): Line 191  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_double = PageTemplateFile('zpt/page_main_double', 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_gis =PageTemplateFile ('zpt/page_main_gis', globals())
       page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
       page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', 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 114  class documentViewer(Folder): Line 225  class documentViewer(Folder):
         #self['template'] = templateFolder # Zope-2.12 style          #self['template'] = templateFolder # Zope-2.12 style
         self._setObject('template',templateFolder) # old style          self._setObject('template',templateFolder) # old style
         try:          try:
             from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy              import MpdlXmlTextServer
             xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False)              textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
             #templateFolder['fulltextclient'] = xmlRpcClient              #templateFolder['fulltextclient'] = xmlRpcClient
             templateFolder._setObject('fulltextclient',xmlRpcClient)              templateFolder._setObject('fulltextclient',textServer)
         except Exception, e:          except Exception, e:
             logging.error("Unable to create XMLRpcTools for fulltextclient: "+str(e))              logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
         try:          try:
             from Products.zogiLib.zogiLib import zogiLib              from Products.zogiLib.zogiLib import zogiLib
             zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")              zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
Line 129  class documentViewer(Folder): Line 240  class documentViewer(Folder):
             logging.error("Unable to create zogiLib for zogilib: "+str(e))              logging.error("Unable to create zogiLib for zogilib: "+str(e))
                   
   
       # proxy text server methods to fulltextclient
       def getTextPage(self, **args):
           """get page"""
           return self.template.fulltextclient.getTextPage(**args)
   
       def getOrigPages(self, **args):
           """get page"""
           return self.template.fulltextclient.getOrigPages(**args)
       
       def getOrigPagesNorm(self, **args):
           """get page"""
           return self.template.fulltextclient.getOrigPagesNorm(**args)
   
       def getQuery(self, **args):
           """get query in search"""
           return self.template.fulltextclient.getQuery(**args)
        
       def getSearch(self, **args):
           """get search"""
           return self.template.fulltextclient.getSearch(**args)
       
       def getGisPlaces(self, **args):
           """get gis places"""
           return self.template.fulltextclient.getGisPlaces(**args)
    
       def getAllGisPlaces(self, **args):
           """get all gis places """
           return self.template.fulltextclient.getAllGisPlaces(**args)
          
       def getTranslate(self, **args):
           """get translate"""
           return self.template.fulltextclient.getTranslate(**args)
   
       def getLemma(self, **args):
           """get lemma"""
           return self.template.fulltextclient.getLemma(**args)
   
       def getLemmaQuery(self, **args):
           """get query"""
           return self.template.fulltextclient.getLemmaQuery(**args)
   
       def getLex(self, **args):
           """get lex"""
           return self.template.fulltextclient.getLex(**args)
   
       def getToc(self, **args):
           """get toc"""
           return self.template.fulltextclient.getToc(**args)
   
       def getTocPage(self, **args):
           """get tocpage"""
           return self.template.fulltextclient.getTocPage(**args)
   
       
     security.declareProtected('View','thumbs_rss')      security.declareProtected('View','thumbs_rss')
     def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):      def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
         '''          '''
Line 149  class documentViewer(Folder): Line 314  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)
         pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)          pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
           ''' ZDES '''
         pt = getattr(self.template, 'thumbs_main_rss')          pt = getattr(self.template, 'thumbs_main_rss')
                   
         if viewMode=="auto": # automodus gewaehlt          if viewMode=="auto": # automodus gewaehlt
             if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert              if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
                 viewMode="text"                  viewMode="text"
             else:              else:
                 viewMode="images"                  viewMode="images"
Line 161  class documentViewer(Folder): Line 328  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):
         '''          '''
         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 characterNormalization type of text display (reg, norm, 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 178  class documentViewer(Folder): Line 347  class documentViewer(Folder):
             return "ERROR: template folder missing!"              return "ERROR: template folder missing!"
                           
         if not getattr(self, 'digilibBaseUrl', None):          if not getattr(self, 'digilibBaseUrl', None):
             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"              self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.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 viewMode=="auto": # automodus gewaehlt          if tocMode != "thumbs":
             if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert              # get table of contents
                 viewMode="text"              docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
   
           # auto viewMode: text_dict if text else images
           if viewMode=="auto": 
               if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): 
                   #texturl gesetzt und textViewer konfiguriert
                   viewMode="text_dict"
             else:              else:
                 viewMode="images"                  viewMode="images"
                                 
           pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode)
           
           if viewMode != 'images' and docinfo.get('textURLPath', None):
               # get full text page
               page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo)
               pageinfo['textPage'] = page
               
           # get template /template/viewer_main
           pt = getattr(self.template, 'viewer_main')
           # and execute with parameters
         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 not isinstance(mk, list):
     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 getBrowser(self):
           """getBrowser the version of browser """
           bt = browserCheck(self)
           logging.debug("BROWSER VERSION: %s"%(bt))
           return bt
           
     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 216  class documentViewer(Folder): Line 409  class documentViewer(Folder):
         else:          else:
             return style              return style
           
     def getLink(self,param=None,val=None):      def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
         """link to documentviewer with parameter param set to val"""          """returns URL to documentviewer with parameter param set to val or from dict params"""
         params=self.REQUEST.form.copy()          # copy existing request params
           urlParams=self.REQUEST.form.copy()
           # change single param
         if param is not None:          if param is not None:
             if val is None:              if val is None:
                 if params.has_key(param):                  if urlParams.has_key(param):
                     del params[param]                      del urlParams[param]
             else:              else:
                 params[param] = str(val)                  urlParams[param] = str(val)
                   
           # change more params
           if params is not None:
               for k in params.keys():
                   v = params[k]
                   if v is None:
                       # val=None removes param
                       if urlParams.has_key(k):
                           del urlParams[k]
                           
                   else:
                       urlParams[k] = v
   
           # FIXME: does this belong here?
           if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
                   urlParams["mode"] = "imagepath"
                   urlParams["url"] = getParentDir(urlParams["url"])
                   
           # quote values and assemble into query string (not escaping '/')
           ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
           #ps = urllib.urlencode(urlParams)
           if baseUrl is None:
               baseUrl = self.REQUEST['URL1']
                                   
         if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath          url = "%s?%s"%(baseUrl, ps)
                 params["mode"] = "imagepath"  
                 params["url"] = getParentDir(params["url"])  
                   
         # quote values and assemble into query string  
         ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])  
         url=self.REQUEST['URL1']+"?"+ps  
         return url          return url
   
     def getLinkAmp(self,param=None,val=None):  
         """link to documentviewer with parameter param set to val"""  
         params=self.REQUEST.form.copy()  
         if param is not None:  
             if val is None:  
                 if params.has_key(param):  
                     del params[param]  
             else:  
                 params[param] = str(val)  
                                   
         # quote values and assemble into query string      def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
         logging.info("XYXXXXX: %s"%repr(params.items()))          """link to documentviewer with parameter param set to val"""
         ps = "&amp;".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])          return self.getLink(param, val, params, baseUrl, '&amp;')
         url=self.REQUEST['URL1']+"?"+ps  
         return url  
           
     def getInfo_xml(self,url,mode):      def getInfo_xml(self,url,mode):
         """returns info about the document as XML"""          """returns info about the document as XML"""
Line 261  class documentViewer(Folder): Line 462  class documentViewer(Folder):
         pt = getattr(self.template, 'info_xml')          pt = getattr(self.template, 'info_xml')
         return pt(docinfo=docinfo)          return pt(docinfo=docinfo)
   
       def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):
           """returns new option state"""
           if not self.REQUEST.SESSION.has_key(optionName):
               # not in session -- initial
               opt = {'lastState': newState, 'state': initialState}
           else:
               opt = self.REQUEST.SESSION.get(optionName)
               if opt['lastState'] != newState:
                   # state in session has changed -- toggle
                   opt['state'] = not opt['state']
                   opt['lastState'] = newState
           
           self.REQUEST.SESSION[optionName] = opt
           return opt['state']
           
     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)
         logger("documentViewer (accessOK)", logging.INFO, "access type %s"%access)          logging.debug("documentViewer (accessOK) access type %s"%access)
         if access is not None and access == 'free':          if access is not None and access == 'free':
             logger("documentViewer (accessOK)", logging.INFO, "access is free")              logging.debug("documentViewer (accessOK) access is free")
             return True              return True
         elif access is None or 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()
               logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
             if user is not None:              if user is not None:
                 #print "user: ", user                  #print "user: ", user
                 return (user.getUserName() != "Anonymous User")                  return (user.getUserName() != "Anonymous User")
             else:              else:
                 return False                  return False
                   
         logger("documentViewer (accessOK)", logging.INFO, "unknown access type %s"%access)          logging.error("documentViewer (accessOK) unknown access type %s"%access)
         return False          return False
           
                                   
     def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):      def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
         """gibt param von dlInfo aus"""          """gibt param von dlInfo aus"""
         num_retries = 3  
         if docinfo is None:          if docinfo is None:
             docinfo = {}              docinfo = {}
                   
         for x in range(cut):          for x in range(cut):
                  
                 path=getParentDir(path)                  path=getParentDir(path)
                 
         infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path          infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
           
         logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo from %s"%(infoUrl))          logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
                   
         for cnt in range(num_retries):          txt = getHttpData(infoUrl)
             try:          if txt is None:
                 # dom = NonvalidatingReader.parseUri(imageUrl)  
                 txt=urllib.urlopen(infoUrl).read()  
                 dom = Parse(txt)  
                 break  
             except:  
                 logger("documentViewer (getdirinfofromdigilib)", logging.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))  
         else:  
             raise IOError("Unable to get dir-info from %s"%(infoUrl))              raise IOError("Unable to get dir-info from %s"%(infoUrl))
                   
         sizes=dom.xpath("//dir/size")          dom = ET.fromstring(txt)
         logger("documentViewer (getparamfromdigilib)", logging.INFO, "dirInfo:size"%sizes)          #dom = Parse(txt)
           size=getText(dom.find("size"))
           #sizes=dom.xpath("//dir/size")
           logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size)
                   
         if sizes:          if size:
             docinfo['numPages'] = int(getTextFromNode(sizes[0]))              docinfo['numPages'] = int(size)
         else:          else:
             docinfo['numPages'] = 0              docinfo['numPages'] = 0
                           
Line 319  class documentViewer(Folder): Line 529  class documentViewer(Folder):
                                                   
         return docinfo          return docinfo
           
       def getIndexMetaPath(self,url):
           """gib nur den Pfad zurueck"""
           regexp = re.compile(r".*(experimental|permanent)/(.*)")
           regpath = regexp.match(url)
           if (regpath==None):
               return ""
           logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))            
           return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
        
       
       
       def getIndexMetaUrl(self,url):
           """returns utr  of index.meta document at url"""
                           
     def getIndexMeta(self, url):  
         """returns dom of index.meta document at url"""  
         num_retries = 3  
         dom = None  
         metaUrl = None          metaUrl = None
         if url.startswith("http://"):          if url.startswith("http://"):
             # real URL              # real URL
Line 334  class documentViewer(Folder): Line 553  class documentViewer(Folder):
             metaUrl=server+url.replace("/mpiwg/online","")              metaUrl=server+url.replace("/mpiwg/online","")
             if not metaUrl.endswith("index.meta"):              if not metaUrl.endswith("index.meta"):
                 metaUrl += "/index.meta"                  metaUrl += "/index.meta"
         logging.debug("METAURL: %s"%metaUrl)  
         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:  
                 logger("ERROR documentViewer (getIndexMata)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])  
                                   
         if dom is None:          return metaUrl
       
       def getDomFromIndexMeta(self, url):
           """get dom from index meta"""
           dom = None
           metaUrl = self.getIndexMetaUrl(url)
                   
           logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
           txt=getHttpData(metaUrl)
           if txt is None:
             raise IOError("Unable to read index meta from %s"%(url))              raise IOError("Unable to read index meta from %s"%(url))
                                     
           dom = ET.fromstring(txt)
           #dom = Parse(txt)
         return dom          return dom
           
     def getPresentationInfoXML(self, url):      def getPresentationInfoXML(self, url):
         """returns dom of info.xml document at url"""          """returns dom of info.xml document at url"""
         num_retries = 3  
         dom = None          dom = None
         metaUrl = None          metaUrl = None
         if url.startswith("http://"):          if url.startswith("http://"):
Line 363  class documentViewer(Folder): Line 582  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","")
                         
                   txt=getHttpData(metaUrl)
         for cnt in range(num_retries):          if txt is None:
             try:  
                 # patch dirk encoding fehler treten dann nicht mehr auf  
                 # dom = NonvalidatingReader.parseUri(metaUrl)  
                 txt=urllib.urlopen(metaUrl).read()  
                 dom = Parse(txt)  
                 break  
             except:  
                 logger("ERROR documentViewer (getPresentationInfoXML)", logging.INFO,"%s (%s)"%sys.exc_info()[0:2])  
                   
         if dom is None:  
             raise IOError("Unable to read infoXMLfrom %s"%(url))              raise IOError("Unable to read infoXMLfrom %s"%(url))
                                     
           dom = ET.fromstring(txt)
           #dom = Parse(txt)
         return dom          return dom
                                                   
                   
     def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):      def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
         """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"""
         logger("documentViewer (getauthinfofromindexmeta)", logging.INFO,"path: %s"%(path))          logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
                   
         access = None          access = None
                   
Line 392  class documentViewer(Folder): Line 603  class documentViewer(Folder):
         if dom is None:          if dom is None:
             for x in range(cut):              for x in range(cut):
                 path=getParentDir(path)                  path=getParentDir(path)
             dom = self.getIndexMeta(path)              dom = self.getDomFromIndexMeta(path)
                 
         acctype = dom.xpath("//access-conditions/access/@type")          acc = dom.find(".//access-conditions/access")
         if acctype and (len(acctype)>0):          if acc is not None:
             access=acctype[0].value              acctype = acc.get('type')
               #acctype = dom.xpath("//access-conditions/access/@type")
               if acctype:
                   access=acctype
             if access in ['group', 'institution']:              if access in ['group', 'institution']:
                 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()                      access = dom.find(".//access-conditions/access/name").text.lower()
                           
         docinfo['accessType'] = access          docinfo['accessType'] = access
         return docinfo          return docinfo
Line 414  class documentViewer(Folder): Line 628  class documentViewer(Folder):
         if dom is None:          if dom is None:
             for x in range(cut):              for x in range(cut):
                 path=getParentDir(path)                  path=getParentDir(path)
             dom = self.getIndexMeta(path)              dom = self.getDomFromIndexMeta(path)
           
           docinfo['indexMetaPath']=self.getIndexMetaPath(path);
                   
         logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))          logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
         # put in all raw bib fields as dict "bib"          # put in all raw bib fields as dict "bib"
         bib = dom.xpath("//bib/*")          bib = dom.find(".//bib")
         if bib and len(bib)>0:          #bib = dom.xpath("//bib/*")
           if bib is not None:
             bibinfo = {}              bibinfo = {}
             for e in bib:              for e in bib:
                 bibinfo[e.localName] = getTextFromNode(e)                  bibinfo[e.tag] = getText(e)
                   
             docinfo['bib'] = bibinfo              docinfo['bib'] = bibinfo
                   
         # extract some fields (author, title, year) according to their mapping          # extract some fields (author, title, year) according to their mapping
         metaData=self.metadata.main.meta.bib          metaData=self.metadata.main.meta.bib
         bibtype=dom.xpath("//bib/@type")          bibtype=bib.get("type")
         if bibtype and (len(bibtype)>0):          #bibtype=dom.xpath("//bib/@type")
             bibtype=bibtype[0].value          if not bibtype:
         else:  
             bibtype="generic"              bibtype="generic"
                           
         bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)          bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
         docinfo['bib_type'] = bibtype          docinfo['bib_type'] = bibtype
         bibmap=metaData.generateMappingForType(bibtype)          bibmap=metaData.generateMappingForType(bibtype)
           logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
           logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
         # if there is no mapping bibmap is empty (mapping sometimes has empty fields)          # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
         if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:          if len(bibmap) > 0 and len(bibmap['author'][0]) > 0 or len(bibmap['title'][0]) > 0:
             try:              try:
                 docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])                  docinfo['author']=getText(bib.find(bibmap['author'][0]))
             except: pass              except: pass
             try:              try:
                 docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])                  docinfo['title']=getText(bib.find(bibmap['title'][0]))
             except: pass              except: pass
             try:              try:
                 docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])                  docinfo['year']=getText(bib.find(bibmap['year'][0]))
             except: pass              except: pass
             logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)  
             try:  
                 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])  
             except:  
                 docinfo['lang']=''  
   
               # ROC: why is this here?
               #            logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
               #            try:
               #                docinfo['lang']=getTextFromNode(dom.find(".//bib/lang")[0])
               #            except:
               #                docinfo['lang']=''
               #            try:
               #                docinfo['city']=getTextFromNode(dom.find(".//bib/city")[0])
               #            except:
               #                docinfo['city']=''
               #            try:
               #                docinfo['number_of_pages']=getTextFromNode(dom.find(".//bib/number_of_pages")[0])
               #            except:
               #                docinfo['number_of_pages']=''
               #            try:
               #                docinfo['series_volume']=getTextFromNode(dom.find(".//bib/series_volume")[0])
               #            except:
               #                docinfo['series_volume']=''
               #            try:
               #                docinfo['number_of_volumes']=getTextFromNode(dom.find(".//bib/number_of_volumes")[0])
               #            except:
               #                docinfo['number_of_volumes']=''
               #            try:
               #                docinfo['translator']=getTextFromNode(dom.find(".//bib/translator")[0])
               #            except:
               #                docinfo['translator']=''
               #            try:
               #                docinfo['edition']=getTextFromNode(dom.find(".//bib/edition")[0])
               #            except:
               #                docinfo['edition']=''
               #            try:
               #                docinfo['series_author']=getTextFromNode(dom.find(".//bib/series_author")[0])
               #            except:
               #                docinfo['series_author']=''
               #            try:
               #                docinfo['publisher']=getTextFromNode(dom.find(".//bib/publisher")[0])
               #            except:
               #                docinfo['publisher']=''
               #            try:
               #                docinfo['series_title']=getTextFromNode(dom.find(".//bib/series_title")[0])
               #            except:
               #                docinfo['series_title']=''
               #            try:
               #                docinfo['isbn_issn']=getTextFromNode(dom.find(".//bib/isbn_issn")[0])
               #            except:
               #                docinfo['isbn_issn']=''           
         return docinfo          return docinfo
           
           
       # TODO: is this needed?
       def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
           """gets name info from the index.meta file at path or given by dom"""
           if docinfo is None:
               docinfo = {}
           
           if dom is None:
               for x in range(cut):
                   path=getParentDir(path)
               dom = self.getDomFromIndexMeta(path)
   
           docinfo['name']=getText(dom.find("name"))
           logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
           return docinfo
       
     def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):      def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
         """parse texttool tag in index meta"""          """parse texttool tag in index meta"""
         logger("documentViewer (getdocinfofromtexttool)", logging.INFO, "url: %s" % (url))          logging.debug("documentViewer (getdocinfofromtexttool) 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:
             dom = self.getIndexMeta(url)              dom = self.getDomFromIndexMeta(url)
                   
         archivePath = None          archivePath = None
         archiveName = None          archiveName = None
           
         archiveNames = dom.xpath("//resource/name")          archiveName = getText(dom.find("name"))
         if archiveNames and (len(archiveNames) > 0):          if not archiveName:
             archiveName = getTextFromNode(archiveNames[0])              logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
         else:          
             logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/name missing in: %s" % (url))          archivePath = getText(dom.find("archive-path"))
                   if archivePath:
         archivePaths = dom.xpath("//resource/archive-path")  
         if archivePaths and (len(archivePaths) > 0):  
             archivePath = getTextFromNode(archivePaths[0])  
             # clean up archive path              # clean up archive path
             if archivePath[0] != '/':              if archivePath[0] != '/':
                 archivePath = '/' + archivePath                  archivePath = '/' + archivePath
Line 486  class documentViewer(Folder): Line 757  class documentViewer(Folder):
                 archivePath += "/" + archiveName                  archivePath += "/" + archiveName
         else:          else:
             # try to get archive-path from url              # try to get archive-path from url
             logger("documentViewer (getdocinfofromtexttool)", logging.WARNING, "resource/archive-path missing in: %s" % (url))              logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))
             if (not url.startswith('http')):              if (not url.startswith('http')):
                 archivePath = url.replace('index.meta', '')                  archivePath = url.replace('index.meta', '')
                                   
Line 494  class documentViewer(Folder): Line 765  class documentViewer(Folder):
             # we balk without archive-path              # we balk without archive-path
             raise IOError("Missing archive-path (for text-tool) in %s" % (url))              raise IOError("Missing archive-path (for text-tool) in %s" % (url))
                   
         imageDirs = dom.xpath("//texttool/image")          imageDir = getText(dom.find(".//texttool/image"))
         if imageDirs and (len(imageDirs) > 0):  
             imageDir = getTextFromNode(imageDirs[0])  
                           
         else:          if not imageDir:
             # we balk with no image tag / not necessary anymore because textmode is now standard              # we balk with no image tag / not necessary anymore because textmode is now standard
             #raise IOError("No text-tool info in %s"%(url))              #raise IOError("No text-tool info in %s"%(url))
             imageDir = ""              imageDir = ""
Line 515  class documentViewer(Folder): Line 784  class documentViewer(Folder):
                           
             docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir              docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
                           
         viewerUrls = dom.xpath("//texttool/digiliburlprefix")          viewerUrl = getText(dom.find(".//texttool/digiliburlprefix"))
         if viewerUrls and (len(viewerUrls) > 0):          if viewerUrl:
             viewerUrl = getTextFromNode(viewerUrls[0])  
             docinfo['viewerURL'] = viewerUrl              docinfo['viewerURL'] = viewerUrl
                                         
         textUrls = dom.xpath("//texttool/text")          # old style text URL
         if textUrls and (len(textUrls) > 0):          textUrl = getText(dom.find(".//texttool/text"))
             textUrl = getTextFromNode(textUrls[0])          if textUrl:
             if urlparse.urlparse(textUrl)[0] == "": #keine url              if urlparse.urlparse(textUrl)[0] == "": #keine url
                 textUrl = os.path.join(archivePath, textUrl)                   textUrl = os.path.join(archivePath, textUrl) 
             # fix URLs starting with /mpiwg/online              # fix URLs starting with /mpiwg/online
Line 531  class documentViewer(Folder): Line 799  class documentViewer(Folder):
                           
             docinfo['textURL'] = textUrl              docinfo['textURL'] = textUrl
           
         textUrls = dom.xpath("//texttool/text-url-path")          # new style text-url-path
         if textUrls and (len(textUrls) > 0):          textUrl = getText(dom.find(".//texttool/text-url-path"))
             textUrl = getTextFromNode(textUrls[0])          if textUrl:
             docinfo['textURLPath'] = textUrl                 docinfo['textURLPath'] = textUrl   
               textUrlkurz = string.split(textUrl, ".")[0]
               docinfo['textURLPathkurz'] = textUrlkurz
               #if not docinfo['imagePath']:
                   # text-only, no page images
                   #docinfo = self.getNumTextPages(docinfo)
                     
                     
         presentationUrls = dom.xpath("//texttool/presentation")          presentationUrl = getText(dom.find(".//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
           # TODO: is this needed here?
           docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
                   
         if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen           
           if presentationUrl: # ueberschreibe diese durch presentation informationen 
              # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten               # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
              # durch den relativen Pfad auf die presentation infos               # durch den relativen Pfad auf die presentation infos
             presentationPath = getTextFromNode(presentationUrls[0])              presentationPath = presentationUrl
             if url.endswith("index.meta"):               if url.endswith("index.meta"): 
                 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 832  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
         """          """
         dom=self.getPresentationInfoXML(url)          dom=self.getPresentationInfoXML(url)
         try:          docinfo['author']=getText(dom.find(".//author"))
             docinfo['author']=getTextFromNode(dom.xpath("//author")[0])          docinfo['title']=getText(dom.find(".//title"))
         except:          docinfo['year']=getText(dom.find(".//date"))
             pass  
         try:  
             docinfo['title']=getTextFromNode(dom.xpath("//title")[0])  
         except:  
             pass  
         try:  
             docinfo['year']=getTextFromNode(dom.xpath("//date")[0])  
         except:  
             pass  
         return docinfo          return docinfo
           
     def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):      def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
         """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."""
         logger("documentViewer (getdocinfofromimagepath)", logging.INFO,"path: %s"%(path))          logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
         if docinfo is None:          if docinfo is None:
             docinfo = {}              docinfo = {}
         path=path.replace("/mpiwg/online","")          path=path.replace("/mpiwg/online","")
Line 588  class documentViewer(Folder): Line 853  class documentViewer(Folder):
         pathorig=path          pathorig=path
         for x in range(cut):                 for x in range(cut):       
                 path=getParentDir(path)                  path=getParentDir(path)
         logging.error("PATH:"+path)          logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
         imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path          imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
         docinfo['imageURL'] = imageUrl          docinfo['imageURL'] = imageUrl
                   
Line 600  class documentViewer(Folder): Line 865  class documentViewer(Folder):
           
     def getDocinfo(self, mode, url):      def getDocinfo(self, mode, url):
         """returns docinfo depending on mode"""          """returns docinfo depending on mode"""
         logger("documentViewer (getdocinfo)", logging.INFO,"mode: %s, url: %s"%(mode,url))          logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
         # look for cached docinfo in session          # look for cached docinfo in session
         if self.REQUEST.SESSION.has_key('docinfo'):          if self.REQUEST.SESSION.has_key('docinfo'):
             docinfo = self.REQUEST.SESSION['docinfo']              docinfo = self.REQUEST.SESSION['docinfo']
             # check if its still current              # check if its still current
             if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:              if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
                 logger("documentViewer (getdocinfo)", logging.INFO,"docinfo in session: %s"%docinfo)                  logging.debug("documentViewer (getdocinfo) docinfo in session. keys=%s"%docinfo.keys())
                 return docinfo                  return docinfo
               
         # new docinfo          # new docinfo
         docinfo = {'mode': mode, 'url': url}          docinfo = {'mode': mode, 'url': url}
         if mode=="texttool": #index.meta with texttool information          # add self url
           docinfo['viewerUrl'] = self.getDocumentViewerURL()
           if mode=="texttool": 
               # index.meta with texttool information
             docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)              docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
         elif mode=="imagepath":          elif mode=="imagepath":
               # folder with images, index.meta optional
             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)              docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
         elif mode=="filepath":          elif mode=="filepath":
               # filename
             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!")              logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
             raise ValueError("Unknown mode %s"%(mode))              raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
                   
           # FIXME: fake texturlpath 
           if not docinfo.has_key('textURLPath'):
               docinfo['textURLPath'] = None
                                                   
         logger("documentViewer (getdocinfo)", logging.INFO,"docinfo: %s"%docinfo)          logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
           #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
         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)
       
         pageinfo['current'] = current          pageinfo['current'] = current
         rows = int(rows or self.thumbrows)          rows = int(rows or self.thumbrows)
         pageinfo['rows'] = rows          pageinfo['rows'] = rows
Line 640  class documentViewer(Folder): Line 916  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['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
           #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
           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 960  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 973  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.1.175.2.3

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