Diff for /documentViewer/documentViewer.py between versions 1.175.2.29 and 1.178

version 1.175.2.29, 2011/08/22 15:00:28 version 1.178, 2012/01/04 07:38:17
Line 1 Line 1
   
 from OFS.Folder import Folder  from OFS.Folder import Folder
 from OFS.Image import File  
 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.ZSimpleFile import ZSimpleFile  
 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 import EMPTY_NAMESPACE, Parse   from Ft.Xml import EMPTY_NAMESPACE, Parse 
 #import Ft.Xml.Domlette  import Ft.Xml.Domlette
   
 import xml.etree.ElementTree as ET  
   
 import os.path  import os.path
 import sys  import sys
 import urllib  import urllib
   import urllib2
 import logging  import logging
 import math  import math
 import urlparse   import urlparse 
   import cStringIO
 import re  import re
 import string  import string
   
 from SrvTxtUtils import getInt, getText, getHttpData  
   
 def logger(txt,method,txt2):  def logger(txt,method,txt2):
     """logging"""      """logging"""
     logging.info(txt+ txt2)      logging.info(txt+ txt2)
           
           
   def getInt(number, default=0):
       """returns always an int (0 in case of problems)"""
       try:
           return int(number)
       except:
           return int(default)
   
   def getTextFromNode(nodename):
       """get the cdata content of a node"""
       if nodename is None:
           return ""
       nodelist=nodename.childNodes
       rc = ""
       for node in nodelist:
           if node.nodeType == node.TEXT_NODE:
              rc = rc + node.data
       return rc
   
 def serializeNode(node, encoding="utf-8"):  def serializeNode(node, encoding="utf-8"):
     """returns a string containing node as XML"""      """returns a string containing node as XML"""
     s = ET.tostring(node)      stream = cStringIO.StringIO()
           #logging.debug("BUF: %s"%(stream))
     # 4Suite:      Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
     #    stream = cStringIO.StringIO()      s = stream.getvalue()
     #    Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)      #logging.debug("BUF: %s"%(s))
     #    s = stream.getvalue()      stream.close()
     #    stream.close()  
     return s      return s
   
 def browserCheck(self):  def browserCheck(self):
Line 100  def browserCheck(self): Line 114  def browserCheck(self):
   
     return bt      return bt
   
 def getParentPath(path, cnt=1):  
     """returns pathname shortened by cnt"""  
     # make sure path doesn't end with /  
     path = path.rstrip('/')  
     # split by /, shorten, and reassemble  
     return '/'.join(path.split('/')[0:-cnt])  
   
   def getParentDir(path):
       """returns pathname shortened by one"""
       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
                   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
       
       raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg))
       #return None
   
 ##  ##
 ## documentViewer class  ## documentViewer class
Line 120  class documentViewer(Folder): Line 175  class documentViewer(Folder):
         {'label':'main config','action':'changeDocumentViewerForm'},          {'label':'main config','action':'changeDocumentViewerForm'},
         )          )
           
     metadataService = None  
     """MetaDataFolder instance"""  
   
     # templates and forms      # templates and forms
     viewer_text = PageTemplateFile('zpt/viewer_text', globals())  
     viewer_images = PageTemplateFile('zpt/viewer_images', globals())  
     viewer_main = PageTemplateFile('zpt/viewer_main', globals())      viewer_main = PageTemplateFile('zpt/viewer_main', globals())
     toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())      toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
     toc_text = PageTemplateFile('zpt/toc_text', globals())      toc_text = PageTemplateFile('zpt/toc_text', globals())
Line 138  class documentViewer(Folder): Line 188  class documentViewer(Folder):
     page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())      page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
     page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', 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())
     info_xml = PageTemplateFile('zpt/info_xml', globals())      info_xml = PageTemplateFile('zpt/info_xml', globals())
     # TODO: can this be nicer?  
     docuviewer_css = ZSimpleFile(content_type='text/css',filename='css/docuviewer.css', id='docuviewer_css',_prefix=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')    
       changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
   
           
     def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):      def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
Line 166  class documentViewer(Folder): Line 217  class documentViewer(Folder):
             templateFolder._setObject('fulltextclient',textServer)              templateFolder._setObject('fulltextclient',textServer)
         except Exception, e:          except Exception, e:
             logging.error("Unable to create MpdlXmlTextServer 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 175  class documentViewer(Folder): Line 225  class documentViewer(Folder):
         except Exception, e:          except Exception, e:
             logging.error("Unable to create zogiLib for zogilib: "+str(e))              logging.error("Unable to create zogiLib for zogilib: "+str(e))
                           
         try:  
             # assume MetaDataFolder instance is called metadata   
             self.metadataService = getattr(self, 'metadata')  
         except Exception, e:  
             logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))  
               
         if digilibBaseUrl is not None:  
             self.digilibBaseUrl = digilibBaseUrl  
               
                   
     # proxy text server methods to fulltextclient      # proxy text server methods to fulltextclient
     def getTextPage(self, **args):      def getTextPage(self, **args):
Line 214  class documentViewer(Folder): Line 255  class documentViewer(Folder):
         """get all gis places """          """get all gis places """
         return self.template.fulltextclient.getAllGisPlaces(**args)          return self.template.fulltextclient.getAllGisPlaces(**args)
                 
     def getWordInfo(self, **args):      def getTranslate(self, **args):
         """get translate"""          """get translate"""
         return self.template.fulltextclient.getWordInfo(**args)          return self.template.fulltextclient.getTranslate(**args)
   
     def getLemma(self, **args):      def getLemma(self, **args):
         """get lemma"""          """get lemma"""
Line 249  class documentViewer(Folder): Line 290  class documentViewer(Folder):
                   
         '''          '''
         logging.debug("HHHHHHHHHHHHHH:load the rss")          logging.debug("HHHHHHHHHHHHHH:load the rss")
         logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))          logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
                   
         if not hasattr(self, 'template'):          if not hasattr(self, 'template'):
             # create template folder if it doesn't exist              # create template folder if it doesn't exist
Line 272  class documentViewer(Folder): Line 313  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",viewType=None,tocMode="thumbs",start=1,pn=1):      def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
         """          '''
         view page          view it
         @param url: url which contains display information  
         @param mode: defines how to access the document behind url           @param mode: defines how to access the document behind url 
         @param viewMode: 'images': display images, 'text': display text, default is 'auto'          @param url: url which contains display information
         @param viewType: sub-type of viewMode, e.g. 'dict' for viewMode='text'          @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 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_html) mode=%s url=%s viewMode=%s viewType=%s start=%s pn=%s"%(mode,url,viewMode,viewType,start,pn))          logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
                   
         if not hasattr(self, 'template'):          if not hasattr(self, 'template'):
             # this won't work              # this won't work
Line 300  class documentViewer(Folder): Line 341  class documentViewer(Folder):
             # get table of contents              # get table of contents
             docinfo = self.getToc(mode=tocMode, docinfo=docinfo)              docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
   
         # auto viewMode: text if there is a text else images          if viewMode=="auto": # automodus gewaehlt
         if viewMode=="auto":               if docinfo.has_key('textURL') or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
             if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):                   viewMode="text_dict"
                 viewMode = "text"  
                 viewType = "dict"  
             else:              else:
                 viewMode = "images"                  viewMode = "images"
                                   
         elif viewMode == "text_dict":          pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
             # legacy fix  
             viewMode = "text"  
             viewType = "dict"  
               
         # stringify viewType  
         if isinstance(viewType, list):  
             logging.debug("index_html: viewType is list:%s"%viewType)  
             viewType = ','.join([t for t in viewType if t])  
                           
         pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode)  
                       
         # get template /template/viewer_$viewMode  
         pt = getattr(self.template, 'viewer_%s'%viewMode, None)  
         if pt is None:  
             logging.error("No template for viewMode=%s!"%viewMode)  
             # TODO: error page?  
             return "No template for viewMode=%s!"%viewMode  
                   
         # and execute with parameters          if (docinfo.get('textURLPath',None)):
         return pt(docinfo=docinfo, pageinfo=pageinfo)              page = self.getTextPage(docinfo=docinfo, pageinfo=pageinfo)
               pageinfo['textPage'] = page
           tt = getattr(self, 'template')   
           pt = getattr(tt, 'viewer_main')               
           return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk))
       
     def generateMarks(self,mk):      def generateMarks(self,mk):
         ret=""          ret=""
Line 352  class documentViewer(Folder): Line 378  class documentViewer(Folder):
         url = self.template.zogilib.getDLBaseUrl()          url = self.template.zogilib.getDLBaseUrl()
         return url          return url
           
     def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None):  
         """returns URL to digilib Scaler with params"""  
         url = None  
         if docinfo is not None:  
             url = docinfo.get('imageURL', None)  
               
         if url is None:  
             url = "%s/servlet/Scaler?"%self.digilibBaseUrl  
             if fn is None and docinfo is not None:  
                 fn = docinfo.get('imagePath','')  
               
             url += "fn=%s"%fn  
               
         if pn:  
             url += "&pn=%s"%pn  
               
         url += "&dw=%s&dh=%s"%(dw,dh)  
         return url  
   
     def getDocumentViewerURL(self):      def getDocumentViewerURL(self):
         """returns the URL of this instance"""          """returns the URL of this instance"""
         return self.absolute_url()          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 idx == 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))
         if idx == selected:          if idx == selected:
             return style + 'sel'              return style + 'sel'
         else:          else:
             return style              return style
           
     def getParams(self, param=None, val=None, params=None, duplicates=None):      def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
         """returns dict with URL parameters.          """returns URL to documentviewer with parameter param set to val or from dict params"""
           
         Takes URL parameters and additionally param=val or dict params.  
         Deletes key if value is None."""  
         # copy existing request params          # copy existing request params
         newParams=self.REQUEST.form.copy()          urlParams=self.REQUEST.form.copy()
         # change single param          # change single param
         if param is not None:          if param is not None:
             if val is None:              if val is None:
                 if newParams.has_key(param):                  if urlParams.has_key(param):
                     del newParams[param]                      del urlParams[param]
             else:              else:
                 newParams[param] = str(val)                  urlParams[param] = str(val)
                                   
         # change more params          # change more params
         if params is not None:          if params is not None:
             for (k, v) in params.items():              for k in params.keys():
                   v = params[k]
                 if v is None:                  if v is None:
                     # val=None removes param                      # val=None removes param
                     if newParams.has_key(k):                      if urlParams.has_key(k):
                         del newParams[k]                          del urlParams[k]
                                                   
                 else:                  else:
                     newParams[k] = v                      urlParams[k] = v
   
         if duplicates:  
             # eliminate lists (coming from duplicate keys)  
             for (k,v) in newParams.items():  
                 if isinstance(v, list):  
                     if duplicates == 'comma':  
                         # make comma-separated list of non-empty entries  
                         newParams[k] = ','.join([t for t in v if t])  
                     elif duplicates == 'first':  
                         # take first non-empty entry  
                         newParams[k] = [t for t in v if t][0]  
                   
         return newParams          # 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"])
           
     def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'):  
         """returns URL to documentviewer with parameter param set to val or from dict params"""  
         urlParams = self.getParams(param=param, val=val, params=params, duplicates=duplicates)  
         # quote values and assemble into query string (not escaping '/')          # quote values and assemble into query string (not escaping '/')
         ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(unicode(v),'/')) for (k, v) in urlParams.items()])          ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])
           #ps = urllib.urlencode(urlParams)
         if baseUrl is None:          if baseUrl is None:
             baseUrl = self.getDocumentViewerURL()              baseUrl = self.REQUEST['URL1']
                           
         url = "%s?%s"%(baseUrl, ps)          url = "%s?%s"%(baseUrl, ps)
         return url          return url
   
     def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'):  
         """link to documentviewer with parameter param set to val"""  
         return self.getLink(param=param, val=val, params=params, baseUrl=baseUrl, paramSep='&amp;', duplicates=duplicates)  
           
       def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):
           """link to documentviewer with parameter param set to val"""
           return self.getLink(param, val, params, baseUrl, '&amp;')
           
     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"""
   
         if not self.digilibBaseUrl:          if not self.digilibBaseUrl:
             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"              self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
                   
Line 447  class documentViewer(Folder): Line 443  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)
         logging.debug("documentViewer (accessOK) access type %s"%access)          logging.debug("documentViewer (accessOK) access type %s"%access)
         if access == 'free':          if access is not None and access == 'free':
             logging.debug("documentViewer (accessOK) 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()
Line 469  class documentViewer(Folder): Line 479  class documentViewer(Folder):
         return False          return False
           
   
       def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
           """gibt param von dlInfo aus"""
           if docinfo is None:
               docinfo = {}
           
           for x in range(cut):
                  
                   path=getParentDir(path)
          
           infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
       
           logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
           
           txt = getHttpData(infoUrl)
           if txt is None:
               raise IOError("Unable to get dir-info from %s"%(infoUrl))
   
           dom = Parse(txt)
           sizes=dom.xpath("//dir/size")
           logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes)
           
           if sizes:
               docinfo['numPages'] = int(getTextFromNode(sizes[0]))
           else:
               docinfo['numPages'] = 0
               
           # TODO: produce and keep list of image names and numbers
   
     def getDocinfo(self, mode, url):  
         """returns docinfo depending on mode"""  
         logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))  
         # look for cached docinfo in session  
         if self.REQUEST.SESSION.has_key('docinfo'):  
             docinfo = self.REQUEST.SESSION['docinfo']  
             # check if its still current  
             if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:  
                 logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())  
                 return docinfo                  return docinfo
                           
         # new docinfo      def getIndexMetaPath(self,url):
         docinfo = {'mode': mode, 'url': url}          """gib nur den Pfad zurueck"""
         # add self url          regexp = re.compile(r".*(experimental|permanent)/(.*)")
         docinfo['viewerUrl'] = self.getDocumentViewerURL()          regpath = regexp.match(url)
         docinfo['digilibBaseUrl'] = self.digilibBaseUrl          if (regpath==None):
         # get index.meta DOM              return ""
         docUrl = None          logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))            
         metaDom = None          return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
         if mode=="texttool":   
             # url points to document dir or index.meta  
             metaDom = self.metadataService.getDomFromPathOrUrl(url)  
             docUrl = url.replace('/index.meta', '')  
             if metaDom is None:  
                 raise IOError("Unable to find index.meta for mode=texttool!")  
   
         elif mode=="imagepath":  
             # url points to folder with images, index.meta optional  
             # asssume index.meta in parent dir  
             docUrl = getParentPath(url)  
             metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)  
   
         elif mode=="filepath":  
             # url points to image file, index.meta optional  
             # asssume index.meta is two path segments up  
             docUrl = getParentPath(url, 2)  
             metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)  
   
       def getIndexMetaUrl(self,url):
           """returns utr  of index.meta document at url"""
         
           metaUrl = None
           if url.startswith("http://"):
               # real URL
               metaUrl = url
         else:          else:
             logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)              # online path
             raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))              server=self.digilibBaseUrl+"/servlet/Texter?fn="
               metaUrl=server+url.replace("/mpiwg/online","")
               if not metaUrl.endswith("index.meta"):
                   metaUrl += "/index.meta"
                   
         docinfo['documentUrl'] = docUrl          return metaUrl
         # process index.meta contents      
         if metaDom is not None and metaDom.tag == 'resource':      def getDomFromIndexMeta(self, url):
             # document directory name and path          """get dom from index meta"""
             resource = self.metadataService.getResourceData(dom=metaDom)          dom = None
             if resource:          metaUrl = self.getIndexMetaUrl(url)
                 docinfo = self.getDocinfoFromResource(docinfo, resource)                  
           logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
             # texttool info          txt=getHttpData(metaUrl)
             texttool = self.metadataService.getTexttoolData(dom=metaDom)          if txt is None:
             if texttool:              raise IOError("Unable to read index meta from %s"%(url))
                 docinfo = self.getDocinfoFromTexttool(docinfo, texttool)          
                       dom = Parse(txt)
             # bib info          return dom
             bib = self.metadataService.getBibData(dom=metaDom)      
             if bib:      def getPresentationInfoXML(self, url):
                 docinfo = self.getDocinfoFromBib(docinfo, bib)          """returns dom of info.xml document at url"""
             else:          dom = None
                 # no bib - try info.xml          metaUrl = None
                 docinfo = self.getDocinfoFromPresentationInfoXml(docinfo)          if url.startswith("http://"):
                               # real URL
             # auth info              metaUrl = url
             access = self.metadataService.getAccessData(dom=metaDom)          else:
             if access:              # online path
                 docinfo = self.getDocinfoFromAccess(docinfo, access)              server=self.digilibBaseUrl+"/servlet/Texter?fn="
               metaUrl=server+url.replace("/mpiwg/online","")
             # attribution info          
             attribution = self.metadataService.getAttributionData(dom=metaDom)          txt=getHttpData(metaUrl)
             if attribution:          if txt is None:
                 logging.debug("getDocinfo: attribution=%s"%repr(attribution))              raise IOError("Unable to read infoXMLfrom %s"%(url))
                 docinfo['attribution'] = attribution              
                 #docinfo = self.getDocinfoFromAccess(docinfo, access)          dom = Parse(txt)
           return dom
             # copyright info                          
             copyright = self.metadataService.getCopyrightData(dom=metaDom)          
             if copyright:      def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
                 logging.debug("getDocinfo: copyright=%s"%repr(copyright))          """gets authorization info from the index.meta file at path or given by dom"""
                 docinfo['copyright'] = copyright          logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
                 #docinfo = self.getDocinfoFromAccess(docinfo, access)          
           access = None
         # image path          
         if mode != 'texttool':          if docinfo is None:
             # override image path from texttool with url              docinfo = {}
             docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1)              
           if dom is None:
         # number of images from digilib              for x in range(cut):
         if docinfo.get('imagePath', None):                  path=getParentDir(path)
             docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']              dom = self.getDomFromIndexMeta(path)
             docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])         
           acctype = dom.xpath("//access-conditions/access/@type")
         logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())          if acctype and (len(acctype)>0):
         #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)              access=acctype[0].value
         # store in session              if access in ['group', 'institution']:
         self.REQUEST.SESSION['docinfo'] = docinfo                  access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
               
           docinfo['accessType'] = access
         return docinfo          return docinfo
   
     def getDocinfoFromResource(self, docinfo, resource):  
         """reads contents of resource element into docinfo"""  
         docName = resource.get('name', None)  
         docinfo['documentName'] = docName  
         docPath = resource.get('archive-path', None)  
         if docPath:  
             # clean up document path  
             if docPath[0] != '/':  
                 docPath = '/' + docPath  
                   
             if docName and (not docPath.endswith(docName)):  
                 docPath += "/" + docName  
               
         else:  
             # use docUrl as docPath  
             docUrl = docinfo['documentURL']  
             if not docUrl.startswith('http:'):  
                 docPath = docUrl  
         if docPath:  
             # fix URLs starting with /mpiwg/online  
             docPath = docPath.replace('/mpiwg/online', '', 1)  
   
         docinfo['documentPath'] = docPath      def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
           """gets bibliographical info from the index.meta file at path or given by dom"""
           #logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
           
           if docinfo is None:
               docinfo = {}
           
           if dom is None:
               for x in range(cut):
                   path=getParentDir(path)
               dom = self.getDomFromIndexMeta(path)
           
           docinfo['indexMetaPath']=self.getIndexMetaPath(path);
           
           #logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
           # put in all raw bib fields as dict "bib"
           bib = dom.xpath("//bib/*")
           if bib and len(bib)>0:
               bibinfo = {}
               for e in bib:
                   bibinfo[e.localName] = getTextFromNode(e)
               docinfo['bib'] = bibinfo
           
           # extract some fields (author, title, year) according to their mapping
           metaData=self.metadata.main.meta.bib
           bibtype=dom.xpath("//bib/@type")
           if bibtype and (len(bibtype)>0):
               bibtype=bibtype[0].value
           else:
               bibtype="generic"
               
           bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
           docinfo['bib_type'] = 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 len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
               try:
                   docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
               except: pass
               try:
                   docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
               except: pass
               try:
                   docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
               except: pass
               #logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
               try:
                   docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
               except:
                   docinfo['lang']=''
               try:
                   docinfo['city']=getTextFromNode(dom.xpath("//bib/city")[0])
               except:
                   docinfo['city']=''
               try:
                   docinfo['number_of_pages']=getTextFromNode(dom.xpath("//bib/number_of_pages")[0])
               except:
                   docinfo['number_of_pages']=''
               try:
                   docinfo['series_volume']=getTextFromNode(dom.xpath("//bib/series_volume")[0])
               except:
                   docinfo['series_volume']=''
               try:
                   docinfo['number_of_volumes']=getTextFromNode(dom.xpath("//bib/number_of_volumes")[0])
               except:
                   docinfo['number_of_volumes']=''
               try:
                   docinfo['translator']=getTextFromNode(dom.xpath("//bib/translator")[0])
               except:
                   docinfo['translator']=''
               try:
                   docinfo['edition']=getTextFromNode(dom.xpath("//bib/edition")[0])
               except:
                   docinfo['edition']=''
               try:
                   docinfo['series_author']=getTextFromNode(dom.xpath("//bib/series_author")[0])
               except:
                   docinfo['series_author']=''
               try:
                   docinfo['publisher']=getTextFromNode(dom.xpath("//bib/publisher")[0])
               except:
                   docinfo['publisher']=''
               try:
                   docinfo['series_title']=getTextFromNode(dom.xpath("//bib/series_title")[0])
               except:
                   docinfo['series_title']=''
               try:
                   docinfo['isbn_issn']=getTextFromNode(dom.xpath("//bib/isbn_issn")[0])
               except:
                   docinfo['isbn_issn']=''           
           #logging.debug("I NEED BIBTEX %s"%docinfo)
         return docinfo          return docinfo
   
     def getDocinfoFromTexttool(self, docinfo, texttool):      
         """reads contents of texttool element into docinfo"""      def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
         # image dir          """gets name info from the index.meta file at path or given by dom"""
         imageDir = texttool.get('image', None)          if docinfo is None:
         docPath = docinfo.get('documentPath', None)              docinfo = {}
         if imageDir and docPath:          
           if dom is None:
               for x in range(cut):
                   path=getParentDir(path)
               dom = self.getDomFromIndexMeta(path)
   
           docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
           logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
           return docinfo
       
       def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):
           """parse texttool tag in index meta"""
           logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
           if docinfo is None:
              docinfo = {}
           if docinfo.get('lang', None) is None:
               docinfo['lang'] = '' # default keine Sprache gesetzt
           if dom is None:
               dom = self.getDomFromIndexMeta(url)
           
           archivePath = None
           archiveName = None
       
           archiveNames = dom.xpath("//resource/name")
           if archiveNames and (len(archiveNames) > 0):
               archiveName = getTextFromNode(archiveNames[0])
           else:
               logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
           
           archivePaths = dom.xpath("//resource/archive-path")
           if archivePaths and (len(archivePaths) > 0):
               archivePath = getTextFromNode(archivePaths[0])
               # clean up archive path
               if archivePath[0] != '/':
                   archivePath = '/' + archivePath
               if archiveName and (not archivePath.endswith(archiveName)):
                   archivePath += "/" + archiveName
           else:
               # try to get archive-path from url
               logging.warning("documentViewer (getdocinfofromtexttool) 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")
           if imageDirs and (len(imageDirs) > 0):
               imageDir = getTextFromNode(imageDirs[0])
               
           else:
               # we balk with no image tag / not necessary anymore because textmode is now standard
               #raise IOError("No text-tool info in %s"%(url))
               imageDir = ""
               #xquery="//pb"  
               docinfo['imagePath'] = "" # keine Bilder
               docinfo['imageURL'] = ""
               
           if imageDir and archivePath:
             #print "image: ", imageDir, " archivepath: ", archivePath              #print "image: ", imageDir, " archivepath: ", archivePath
             imageDir = os.path.join(docPath, imageDir)              imageDir = os.path.join(archivePath, imageDir)
             imageDir = imageDir.replace('/mpiwg/online', '', 1)              imageDir = imageDir.replace("/mpiwg/online", '')
               docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
             docinfo['imagePath'] = imageDir              docinfo['imagePath'] = imageDir
                   
               docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
               
           viewerUrls = dom.xpath("//texttool/digiliburlprefix")
           if viewerUrls and (len(viewerUrls) > 0):
               viewerUrl = getTextFromNode(viewerUrls[0])
               docinfo['viewerURL'] = viewerUrl
           
         # old style text URL          # old style text URL
         textUrl = texttool.get('text', None)          textUrls = dom.xpath("//texttool/text")
         if textUrl and docPath:          if textUrls and (len(textUrls) > 0):
               textUrl = getTextFromNode(textUrls[0])
             if urlparse.urlparse(textUrl)[0] == "": #keine url              if urlparse.urlparse(textUrl)[0] == "": #keine url
                 textUrl = os.path.join(docPath, textUrl)                   textUrl = os.path.join(archivePath, textUrl) 
               # fix URLs starting with /mpiwg/online
               if textUrl.startswith("/mpiwg/online"):
                   textUrl = textUrl.replace("/mpiwg/online", '', 1)
                           
             docinfo['textURL'] = textUrl              docinfo['textURL'] = textUrl
           
   
               #TODO: hack-DW for annalen
               if (textUrl is not None) and (textUrl.startswith("/permanent/einstein/annalen")):
                   textUrl=textUrl.replace("/permanent/einstein/annalen/","/diverse/de/") 
                   splitted=textUrl.split("/fulltext")
                   textUrl=splitted[0]+".xml"
                   textUrlkurz = string.split(textUrl, ".")[0]
                   docinfo['textURLPathkurz'] = textUrlkurz
                   docinfo['textURLPath'] = textUrl
                   logging.debug("hack")
                   logging.debug(textUrl)
               
               
         # new style text-url-path          # new style text-url-path
         textUrl = texttool.get('text-url-path', None)          textUrls = dom.xpath("//texttool/text-url-path")
         if textUrl:          if textUrls and (len(textUrls) > 0):
               textUrl = getTextFromNode(textUrls[0])
             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)
                           
         # page flow  
         docinfo['pageFlow'] = texttool.get('page-flow', 'ltr')  
                           
         # odd pages are left          presentationUrls = dom.xpath("//texttool/presentation")
         docinfo['oddPage'] = texttool.get('odd-scan-position', 'left')          docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get info von bib tag
           #docinfo = self.getDownloadfromDocinfoToBibtex(url, docinfo=docinfo, dom=dom)
           docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
                           
         # number of title page (0: not defined)  
         docinfo['titlePage'] = texttool.get('title-scan-no', 0)  
                           
         # old presentation stuff          if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen 
         presentation = texttool.get('presentation', None)               # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
         if presentation and docPath:               # durch den relativen Pfad auf die presentation infos
             if presentation.startswith('http:'):              presentationPath = getTextFromNode(presentationUrls[0])
                 docinfo['presentationUrl'] = presentation              if url.endswith("index.meta"): 
                   presentationUrl = url.replace('index.meta', presentationPath)
             else:              else:
                 docinfo['presentationUrl'] = os.path.join(docPath, presentation)                  presentationUrl = url + "/" + presentationPath
                           
               docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
                   
         return docinfo          docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get access info
   
     def getDocinfoFromBib(self, docinfo, bib):  
         """reads contents of bib element into docinfo"""  
         logging.debug("getDocinfoFromBib bib=%s"%repr(bib))  
         # put all raw bib fields in dict "bib"  
         docinfo['bib'] = bib  
         bibtype = bib.get('@type', None)  
         docinfo['bibType'] = bibtype  
         # also store DC metadata for convenience  
         dc = self.metadataService.getDCMappedData(bib)  
         docinfo['creator'] = dc.get('creator',None)  
         docinfo['title'] = dc.get('title',None)  
         docinfo['date'] = dc.get('date',None)  
         return docinfo          return docinfo
                           
     def getDocinfoFromAccess(self, docinfo, acc):  
         """reads contents of access element into docinfo"""  
         #TODO: also read resource type  
         logging.debug("getDocinfoFromAccess acc=%s"%repr(acc))  
         try:  
             acctype = acc['@attr']['type']  
             if acctype:  
                 access=acctype  
                 if access in ['group', 'institution']:  
                     access = acc['name'].lower()  
                   
                 docinfo['accessType'] = access  
   
       def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):
           """gets the bibliographical information from the preseantion entry in texttools
           """
           dom=self.getPresentationInfoXML(url)
           try:
               docinfo['author']=getTextFromNode(dom.xpath("//author")[0])
           except:
               pass
           try:
               docinfo['title']=getTextFromNode(dom.xpath("//title")[0])
           except:
               pass
           try:
               docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
         except:          except:
             pass              pass
           
         return docinfo  
   
     def getDocinfoFromDigilib(self, docinfo, path):  
         infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path  
         # fetch data  
         txt = getHttpData(infoUrl)  
         if not txt:  
             logging.error("Unable to get dir-info from %s"%(infoUrl))  
             return docinfo              return docinfo
   
         dom = ET.fromstring(txt)      def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
         size = getText(dom.find("size"))          """path ist the path to the images it assumes that the index.meta file is one level higher."""
         logging.debug("getDocinfoFromDigilib: size=%s"%size)          logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
         if size:          if docinfo is None:
             docinfo['numPages'] = int(size)              docinfo = {}
         else:          path=path.replace("/mpiwg/online","")
             docinfo['numPages'] = 0          docinfo['imagePath'] = path
                       docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
         # TODO: produce and keep list of image names and numbers          
           pathorig=path
           for x in range(cut):       
                   path=getParentDir(path)
           logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
           imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
           docinfo['imageURL'] = imageUrl
           
           #path ist the path to the images it assumes that the index.meta file is one level higher.
           docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
           #docinfo = self.getDownloadfromDocinfoToBibtex(pathorig,docinfo=docinfo,cut=cut+1)
           docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
         return docinfo          return docinfo
                           
                           
     def getDocinfoFromPresentationInfoXml(self,docinfo):      def getDocinfo(self, mode, url):
         """gets DC-like bibliographical information from the presentation entry in texttools"""          """returns docinfo depending on mode"""
         url = docinfo.get('presentationUrl', None)          logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
         if not url:          # look for cached docinfo in session
             logging.error("getDocinfoFromPresentation: no URL!")          if self.REQUEST.SESSION.has_key('docinfo'):
               docinfo = self.REQUEST.SESSION['docinfo']
               # check if its still current
               if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
                   logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
             return docinfo              return docinfo
                   # new docinfo
         dom = None          docinfo = {'mode': mode, 'url': url}
         metaUrl = None          if mode=="texttool": #index.meta with texttool information
         if url.startswith("http://"):              docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
             # real URL          elif mode=="imagepath":
             metaUrl = url              docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
           elif mode=="filepath":
               docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
         else:          else:
             # online path              logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
               raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
                           
             server=self.digilibBaseUrl+"/servlet/Texter?fn="          # FIXME: fake texturlpath 
             metaUrl=server+url          if not docinfo.has_key('textURLPath'):
               docinfo['textURLPath'] = None
                   
         txt=getHttpData(metaUrl)          logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
         if txt is None:          #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
             logging.error("Unable to read info.xml from %s"%(url))          self.REQUEST.SESSION['docinfo'] = docinfo
             return docinfo  
               
         dom = ET.fromstring(txt)  
         docinfo['creator']=getText(dom.find(".//author"))  
         docinfo['title']=getText(dom.find(".//title"))  
         docinfo['date']=getText(dom.find(".//date"))  
         return docinfo          return docinfo
           
       def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
     def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None):  
         """returns pageinfo with the given parameters"""          """returns pageinfo with the given parameters"""
         logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewType=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewType,tocMode))  
         pageinfo = {}          pageinfo = {}
         pageinfo['viewMode'] = viewMode  
         pageinfo['viewType'] = viewType  
         pageinfo['tocMode'] = tocMode  
   
         current = getInt(current)          current = getInt(current)
       
         pageinfo['current'] = current          pageinfo['current'] = current
         pageinfo['pn'] = current  
         rows = int(rows or self.thumbrows)          rows = int(rows or self.thumbrows)
         pageinfo['rows'] = rows          pageinfo['rows'] = rows
         cols = int(cols or self.thumbcols)          cols = int(cols or self.thumbcols)
         pageinfo['cols'] = cols          pageinfo['cols'] = cols
         grpsize = cols * rows          grpsize = cols * rows
         pageinfo['groupsize'] = grpsize          pageinfo['groupsize'] = grpsize
         # is start is empty use one around current  
         start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))          start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
         # int(current / grpsize) * grpsize +1))          # int(current / grpsize) * grpsize +1))
         pageinfo['start'] = start          pageinfo['start'] = start
                   pageinfo['end'] = start + grpsize
         np = int(docinfo.get('numPages', 0))          if (docinfo is not None) and ('numPages' in docinfo):
         if np == 0:              np = int(docinfo['numPages'])
             # numPages unknown - maybe we can get it from text page              pageinfo['end'] = min(pageinfo['end'], np)
             if docinfo.get('textURLPath', None):  
                 # cache text page as well  
                 pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=current, docinfo=docinfo, pageinfo=pageinfo)  
                 np = int(docinfo.get('numPages', 0))  
                   
         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
         pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl'          pageinfo['tocMode'] = tocMode
         oddScanLeft = docinfo.get('oddPage', 'left') != 'right'  
         # add zeroth page for two columns  
         pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft))  
         pageinfo['pageZero'] = pageZero  
         pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np)  
                   
         # TODO: do we need this here?  
         pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')          pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
           #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
         pageinfo['query'] = self.REQUEST.get('query','')           pageinfo['query'] = self.REQUEST.get('query','') 
         pageinfo['queryType'] = self.REQUEST.get('queryType','')          pageinfo['queryType'] = self.REQUEST.get('queryType','')
         pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')          pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
           pageinfo['textPN'] = self.REQUEST.get('textPN','1')
         pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')          pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
         pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30))  
         pageinfo['queryPageSize'] = getInt(self.REQUEST.get('queryPageSize', 10))  
         pageinfo['tocPN'] = getInt(self.REQUEST.get('tocPN', '1'))  
         pageinfo['searchPN'] = getInt(self.REQUEST.get('searchPN','1'))  
                   
         # limit tocPN          pageinfo ['highlightElementPos'] = self.REQUEST.get('highlightElementPos','')
           pageinfo ['highlightElement'] = self.REQUEST.get('highlightElement','')
           
           pageinfo ['xpointer'] = self.REQUEST.get('xpointer','')
           
           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:          if 'tocSize_%s'%tocMode in docinfo:
             tocSize = docinfo['tocSize_%s'%tocMode]              tocSize = int(docinfo['tocSize_%s'%tocMode])
             tocPageSize = pageinfo['tocPageSize']              tocPageSize = int(pageinfo['tocPageSize'])
             # cached toc                         # cached toc           
             if tocSize%tocPageSize>0:              if tocSize%tocPageSize>0:
                 tocPages=tocSize/tocPageSize+1                  tocPages=tocSize/tocPageSize+1
             else:              else:
                 tocPages=tocSize/tocPageSize                  tocPages=tocSize/tocPageSize
                               pageinfo['tocPN'] = min (tocPages,toc)                    
             pageinfo['tocPN'] = min(tocPages,pageinfo['tocPN'])          pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
                       #pageinfo['sn'] =self.REQUEST.get('sn','')
           pageinfo['s'] =self.REQUEST.get('s','')
         return pageinfo          return pageinfo
   
   
     def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0):  
         """returns dict with array of page informations for one screenfull of thumbnails"""  
         batch = {}  
         grpsize = rows * cols  
         if maxIdx == 0:  
             maxIdx = start + grpsize  
   
         nb = int(math.ceil(maxIdx / float(grpsize)))  
         # list of all batch start and end points  
         batches = []  
         if pageZero:  
             ofs = 0  
         else:  
             ofs = 1  
               
         for i in range(nb):  
             s = i * grpsize + ofs  
             e = min((i + 1) * grpsize + ofs - 1, maxIdx)  
             batches.append({'start':s, 'end':e})  
               
         batch['batches'] = batches  
   
         pages = []  
         if pageZero and start == 1:  
             # correct beginning  
             idx = 0  
         else:  
             idx = start  
               
         for r in range(rows):  
             row = []  
             for c in range(cols):  
                 if idx < minIdx or idx > maxIdx:  
                     page = {'idx':None}  
                 else:  
                     page = {'idx':idx}  
                       
                 idx += 1  
                 if pageFlowLtr:  
                     row.append(page)  
                 else:  
                     row.insert(0, page)   
                   
             pages.append(row)  
               
         if start > 1:  
             batch['prevStart'] = max(start - grpsize, 1)  
         else:  
             batch['prevStart'] = None  
               
         if start + grpsize < maxIdx:  
             batch['nextStart'] = start + grpsize  
         else:  
             batch['nextStart'] = None  
   
         batch['pages'] = pages  
         return batch  
           
     def getBatch(self, start=1, size=10, end=0, data=None, fullData=True):  
         """returns dict with information for one screenfull of data."""  
         batch = {}  
         if end == 0:  
             end = start + size                      
               
         nb = int(math.ceil(end / float(size)))  
         # list of all batch start and end points  
         batches = []  
         for i in range(nb):  
             s = i * size + 1  
             e = min((i + 1) * size, end)  
             batches.append({'start':s, 'end':e})  
               
         batch['batches'] = batches  
         # list of elements in this batch  
         this = []  
         j = 0  
         for i in range(start, min(start+size, end)):  
             if data:  
                 if fullData:  
                     d = data[i]  
                 else:  
                     d = data[j]  
                     j += 1  
               
             else:  
                 d = i+1  
                   
             this.append(d)  
               
         batch['this'] = this  
         if start > 1:  
             batch['prevStart'] = max(start - size, 1)  
         else:  
             batch['prevStart'] = None  
               
         if start + size < end:  
             batch['nextStart'] = start + size  
         else:  
             batch['nextStart'] = None  
           
         return batch  
           
   
     security.declareProtected('View management screens','changeDocumentViewerForm')      
     changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())  
       
     def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):      def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
         """init document viewer"""          """init document viewer"""
         self.title=title          self.title=title
Line 899  class documentViewer(Folder): Line 961  class documentViewer(Folder):
         self.thumbrows = thumbrows          self.thumbrows = thumbrows
         self.thumbcols = thumbcols          self.thumbcols = thumbcols
         self.authgroups = [s.strip().lower() for s in authgroups.split(',')]          self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
         try:  
             # assume MetaDataFolder instance is called metadata   
             self.metadataService = getattr(self, 'metadata')  
         except Exception, e:  
             logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))  
   
         if RESPONSE is not None:          if RESPONSE is not None:
             RESPONSE.redirect('manage_main')              RESPONSE.redirect('manage_main')
                   
Line 920  def manage_AddDocumentViewer(self,id,ima Line 976  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
   class DocumentViewerTemplate(ZopePageTemplate):
       """Template for document viewer"""
       meta_type="DocumentViewer Template"
   
   
   def manage_addDocumentViewerTemplateForm(self):
       """Form for adding"""
       pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
       return pt()
   
   def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
                              REQUEST=None, submit=None):
       "Add a Page Template with optional file content."
   
       self._setObject(id, DocumentViewerTemplate(id))
       ob = getattr(self, id)
       txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read()
       logging.info("txt %s:"%txt)
       ob.pt_edit(txt,"text/html")
       if title:
           ob.pt_setTitle(title)
       try:
           u = self.DestinationURL()
       except AttributeError:
           u = REQUEST['URL1']
           
       u = "%s/%s" % (u, urllib.quote(id))
       REQUEST.RESPONSE.redirect(u+'/manage_main')
       return ''
   
   
       

Removed from v.1.175.2.29  
changed lines
  Added in v.1.178


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