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

Diff for /documentViewer/documentViewer.py between versions 1.15 and 1.175.2.15

version 1.15, 2006/07/14 16:22:36 version 1.175.2.15, 2011/08/02 16:29:15
Line 5  from AccessControl import ClassSecurityI Line 5  from AccessControl import ClassSecurityI
 from AccessControl import getSecurityManager  from AccessControl import getSecurityManager
 from Globals import package_home  from Globals import package_home
   
 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 Ft.Xml.XPath  import xml.etree.ElementTree as ET
   
 import os.path  import os.path
 import sys  import sys
 import cgi  
 import urllib  import urllib
 import zLOG  import logging
   import math
   import urlparse 
   import re
   import string
   
   from SrvTxtUtils import getInt, getText, getHttpData
   
   def logger(txt,method,txt2):
       """logging"""
       logging.info(txt+ txt2)
       
       
   def serializeNode(node, encoding="utf-8"):
       """returns a string containing node as XML"""
       s = ET.tostring(node)
       
       # 4Suite:
       #    stream = cStringIO.StringIO()
       #    Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding)
       #    s = stream.getvalue()
       #    stream.close()
       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']=""
   
 def getInt(number, default=0):      if string.find(ua, 'MSIE') > -1:
     """returns always an int (0 in case of problems)"""          bt['isIE'] = True
       else:
           bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1)
       # Safari oder Chrome identification    
     try:      try:
         return int(number)          nav = ua[string.find(ua, '('):]
     except:          nav1=ua[string.find(ua,')'):]
         return default          nav2=nav1[string.find(nav1,'('):]
           nav3=nav2[string.find(nav2,')'):]
 def getTextFromNode(nodename):          ie = string.split(nav, "; ")[1]
     if nodename is None:          ie1 =string.split(nav1, " ")[2]
         return ""          ie2 =string.split(nav3, " ")[1]
     nodelist=nodename.childNodes          ie3 =string.split(nav3, " ")[2]
     rc = ""          if string.find(ie3, "Safari") >-1:
     for node in nodelist:              bt['versSafariChrome']=string.split(ie2, "/")[1]
         if node.nodeType == node.TEXT_NODE:      except: pass
            rc = rc + node.data      # IE identification
     return rc      try:
           nav = ua[string.find(ua, '('):]
                   ie = string.split(nav, "; ")[1]
 def getParentDir(path):          if string.find(ie, "MSIE") > -1:
     """returns pathname shortened by one"""              bt['versIE'] = string.split(ie, " ")[1]
     return '/'.join(path.split('/')[0:-1])      except:pass
               # Firefox identification
       try:
 import socket          nav = ua[string.find(ua, '('):]
           nav1=ua[string.find(ua,')'):]
 def urlopen(url,timeout=2):          if string.find(ie1, "Firefox") >-1:
         """urlopen mit timeout"""              nav5= string.split(ie1, "/")[1]
         socket.setdefaulttimeout(timeout)              logging.debug("FIREFOX: %s"%(nav5))
         ret=urllib.urlopen(url)              bt['versFirefox']=nav5[0:3]                   
         socket.setdefaulttimeout(5)      except:pass
         return ret      #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 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])
   
   
 ##  ##
Line 55  def urlopen(url,timeout=2): Line 111  def urlopen(url,timeout=2):
 ##  ##
 class documentViewer(Folder):  class documentViewer(Folder):
     """document viewer"""      """document viewer"""
   
     meta_type="Document viewer"      meta_type="Document viewer"
           
     security=ClassSecurityInfo()      security=ClassSecurityInfo()
Line 63  class documentViewer(Folder): Line 118  class documentViewer(Folder):
         {'label':'main config','action':'changeDocumentViewerForm'},          {'label':'main config','action':'changeDocumentViewerForm'},
         )          )
   
       metadataService = None
       """MetaDataFolder instance"""
   
     # 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())      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_double = PageTemplateFile('zpt/page_main_double', 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())
   
     security.declareProtected('View management screens','changeDocumentViewerForm')      
     changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())  
   
       thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
           
     def __init__(self,id,imageViewerUrl,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
         self.imageViewerUrl=imageViewerUrl  
         if not digilibBaseUrl:  
             self.digilibBaseUrl = self.findDigilibUrl()  
         else:  
             self.digilibBaseUrl = digilibBaseUrl  
         self.thumbcols = thumbcols          self.thumbcols = thumbcols
         self.thumbrows = thumbrows          self.thumbrows = thumbrows
         # authgroups is list of authorized groups (delimited by ,)          # authgroups is list of authorized groups (delimited by ,)
         self.authgroups = [s.strip().lower() for s in authgroups.split(',')]          self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
         # add template folder so we can always use template.something          # create template folder so we can always use template.something
         self.manage_addFolder('template')  
   
           templateFolder = Folder('template')
           #self['template'] = templateFolder # Zope-2.12 style
           self._setObject('template',templateFolder) # old style
           try:
               import MpdlXmlTextServer
               textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName)
               #templateFolder['fulltextclient'] = xmlRpcClient
               templateFolder._setObject('fulltextclient',textServer)
           except Exception, e:
               logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
   
     security.declareProtected('View','index_html')          try:
     def index_html(self,mode,url,start=None,pn=1):              from Products.zogiLib.zogiLib import zogiLib
               zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
               #templateFolder['zogilib'] = zogilib
               templateFolder._setObject('zogilib',zogilib)
           except Exception, 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))
               
           
       # 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')
       def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1):
         '''          '''
         view it          view it
         @param mode: defines which type of document is behind url          @param mode: defines 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)
                   
         zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))          '''
           logging.debug("HHHHHHHHHHHHHH:load the rss")
           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'):
             # create template folder if it doesn't exist              # create template folder if it doesn't exist
Line 109  class documentViewer(Folder): Line 251  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)
         pt = getattr(self.template, 'viewer_main')          ''' ZDES '''
         return pt(docinfo=docinfo,pageinfo=pageinfo)          pt = getattr(self.template, 'thumbs_main_rss')
       
           if viewMode=="auto": # automodus gewaehlt
               if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert
                   viewMode="text"
               else:
                   viewMode="images"
       
     def getLink(self,param=None,val=None):          return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
         """link to documentviewer with parameter param set to val"""  
         params=self.REQUEST.form.copy()    
         if param is not None:      security.declareProtected('View','index_html')
             if val is None:      def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):
                 if params.has_key(param):          """
                     del params[param]          view it
           @param mode: defines how to access the document behind url 
           @param url: url which contains display information
           @param viewMode: if images display images, if text display text, default is auto (text,images or auto)
           @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
           """
           
           logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
           
           if not hasattr(self, 'template'):
               # this won't work
               logging.error("template folder missing!")
               return "ERROR: template folder missing!"
               
           if not getattr(self, 'digilibBaseUrl', None):
               self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary"
               
           docinfo = self.getDocinfo(mode=mode,url=url)
           
           if tocMode != "thumbs":
               # get table of contents
               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): 
                   viewMode="text_dict"
             else:              else:
                 params[param] = str(val)                  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))
     
       def generateMarks(self,mk):
           ret=""
           if mk is None:
               return ""
           if not isinstance(mk, list):
               mk=[mk]
           for m in mk:
               ret+="mk=%s"%m
           return ret
       
       
       def getBrowser(self):
           """getBrowser the version of browser """
           bt = browserCheck(self)
           logging.debug("BROWSER VERSION: %s"%(bt))
           return bt
                                   
         # quote values and assemble into query string      def findDigilibUrl(self):
         ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])          """try to get the digilib URL from zogilib"""
         url=self.REQUEST['URL1']+"?"+ps          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."""
         #zLOG.LOG("documentViewer (getstyle)", zLOG.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 getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):
           """returns URL to documentviewer with parameter param set to val or from dict params"""
           # copy existing request params
           urlParams=self.REQUEST.form.copy()
           # change single param
           if param is not None:
               if val is None:
                   if urlParams.has_key(param):
                       del urlParams[param]
               else:
                   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"] = getParentPath(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']
               
           url = "%s?%s"%(baseUrl, ps)
           return url
   
   
       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, '&')
       
       def getInfo_xml(self,url,mode):
           """returns info about the document as XML"""
           if not self.digilibBaseUrl:
               self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
           
           docinfo = self.getDocinfo(mode=mode,url=url)
           pt = getattr(self.template, 'info_xml')
           return pt(docinfo=docinfo)
                   
     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)
         zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "access type %s"%access)          logging.debug("documentViewer (accessOK) access type %s"%access)
         if access is None:          if access == 'free':
             # no information - no access               logging.debug("documentViewer (accessOK) access is free")
             return False  
         elif access == 'free':  
             zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "access is free")  
             return True              return True
         elif access in self.authgroups:          
           elif access is None or access in self.authgroups:
             # only local access -- only logged in users              # only local access -- only logged in users
             user = getSecurityManager().getUser()              user = getSecurityManager().getUser()
               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
                   
         zLOG.LOG("documentViewer (accessOK)", zLOG.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):  
         """gibt param von dlInfo aus"""  
         num_retries = 3  
         if docinfo is None:  
             docinfo = {}  
                           
         infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path      def getDocinfo(self, mode, url):
               """returns docinfo depending on mode"""
         zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(infoUrl))          logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
                   # look for cached docinfo in session
         for cnt in range(num_retries):          if self.REQUEST.SESSION.has_key('docinfo'):
             try:              docinfo = self.REQUEST.SESSION['docinfo']
                 # dom = NonvalidatingReader.parseUri(imageUrl)              # check if its still current
                 txt=urllib.urlopen(infoUrl).read()              if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
                 dom = Parse(txt)                  logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
                 break                  return docinfo
             except:  
                 zLOG.LOG("documentViewer (getdirinfofromdigilib)", zLOG.ERROR, "error reading %s (try %d)"%(infoUrl,cnt))  
         else:  
             raise IOError("Unable to get dir-info from %s"%(infoUrl))  
           
         sizes=dom.xpath("//dir/size")  
         zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%sizes)  
                   
         if sizes:          # new docinfo
             docinfo['numPages'] = int(getTextFromNode(sizes[0]))          docinfo = {'mode': mode, 'url': url}
         else:          # add self url
             docinfo['numPages'] = 0          docinfo['viewerUrl'] = self.getDocumentViewerURL()
           # get index.meta DOM
           docUrl = None
           metaDom = None
           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)
   
           else:
               logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
               raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
           
           docinfo['documentUrl'] = docUrl
           # process index.meta contents
           if metaDom is not None:
               # document directory name and path
               logging.debug("RESOURCE: %s"%repr(self.metadataService.resource.meta.getData(dom=metaDom, all=True, recursive=2)))
               resource = self.metadataService.getResourceData(dom=metaDom)
               if resource:
                   docinfo = self.getDocinfoFromResource(docinfo, resource)
   
               # texttool info
               texttool = self.metadataService.getTexttoolData(dom=metaDom)
               if texttool:
                   docinfo = self.getDocinfoFromTexttool(docinfo, texttool)
               
               # bib info
               bib = self.metadataService.getBibData(dom=metaDom)
               if bib:
                   docinfo = self.getDocinfoFromBib(docinfo, bib)
               else:
                   # no bib - try info.xml
                   docinfo = self.getDocinfoFromPresentationInfoXml(docinfo)
                   
               # auth info
               access = self.metadataService.getAccessData(dom=metaDom)
               if access:
                   docinfo = self.getDocinfoFromAccess(docinfo, access)
   
               # attribution info
               attribution = self.metadataService.getAttributionData(dom=metaDom)
               if attribution:
                   logging.debug("getDocinfo: attribution=%s"%repr(attribution))
                   docinfo['attribution'] = attribution
                   #docinfo = self.getDocinfoFromAccess(docinfo, access)
   
               # copyright info
               copyright = self.metadataService.getCopyrightData(dom=metaDom)
               if copyright:
                   logging.debug("getDocinfo: copyright=%s"%repr(copyright))
                   docinfo['copyright'] = copyright
                   #docinfo = self.getDocinfoFromAccess(docinfo, access)
   
           # image path
           if mode != 'texttool':
               # override image path from texttool
               docinfo['imagePath'] = url.replace('/mpiwg/online/', '', 1)
   
           # number of images from digilib
           if docinfo.get('imagePath', None):
               docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + docinfo['imagePath']
               docinfo = self.getDocinfoFromDigilib(docinfo, docinfo['imagePath'])
   
           logging.debug("documentViewer (getdocinfo) docinfo: keys=%s"%docinfo.keys())
           #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
           # store in session
           self.REQUEST.SESSION['docinfo'] = docinfo
         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)
                           
     def getIndexMeta(self, url):          docinfo['documentPath'] = docPath
         """returns dom of index.meta document at url"""          return docinfo
         num_retries = 3  
         dom = None  
         metaUrl = None  
         if url.startswith("http://"):  
             # real URL  
             metaUrl = url  
         else:  
             # online path  
             server=self.digilibBaseUrl+"/servlet/Texter?fn="  
             metaUrl=server+url.replace("/mpiwg/online","")  
             if not metaUrl.endswith("index.meta"):  
                 metaUrl += "/index.meta"  
           
         for cnt in range(num_retries):  
             try:  
                 # patch dirk encoding fehler treten dann nicht mehr auf  
                 # dom = NonvalidatingReader.parseUri(metaUrl)  
                 txt=urllib.urlopen(metaUrl).read()  
                 dom = Parse(txt)  
                 break  
             except:  
                 zLOG.LOG("ERROR documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])  
                                   
         if dom is None:      def getDocinfoFromTexttool(self, docinfo, texttool):
             raise IOError("Unable to read index meta from %s"%(url))          """reads contents of texttool element into docinfo"""
           # image dir
           imageDir = texttool.get('image', None)
           docPath = docinfo.get('documentPath', None)
           if imageDir and docPath:
               #print "image: ", imageDir, " archivepath: ", archivePath
               imageDir = os.path.join(docPath, imageDir)
               imageDir = imageDir.replace('/mpiwg/online', '', 1)
               docinfo['imagePath'] = imageDir
                                     
         return dom          # old style text URL
           textUrl = texttool.get('text', None)
           if textUrl and docPath:
               if urlparse.urlparse(textUrl)[0] == "": #keine url
                   textUrl = os.path.join(docPath, textUrl) 
                                                   
               docinfo['textURL'] = textUrl
                   
     def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None):          # new style text-url-path
         """gets authorization info from the index.meta file at path or given by dom"""          textUrl = texttool.get('text-url-path', None)
         zLOG.LOG("documentViewer (getauthinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))          if textUrl:
               docinfo['textURLPath'] = textUrl
               
           # page flow
           docinfo['pageFlow'] = texttool.get('page-flow', 'ltr')
               
           # odd pages are left
           docinfo['oddPage'] = texttool.get('odd-scan-orientation', 'left')
               
           # number of title page
           docinfo['titlePage'] = texttool.get('title-scan-no', 0)
               
           # old presentation stuff
           presentation = texttool.get('presentation', None)
           if presentation and docPath:
               if presentation.startswith('http:'):
                   docinfo['presentationUrl'] = presentation
               else:
                   docinfo['presentationUrl'] = os.path.join(docPath, presentation)
                   
         access = None  
                   
         if docinfo is None:          return docinfo
             docinfo = {}  
                           
         if dom is None:      def getDocinfoFromBib(self, docinfo, bib):
             dom = self.getIndexMeta(getParentDir(path))          """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
                           
         acctype = dom.xpath("//access-conditions/access/@type")      def getDocinfoFromAccess(self, docinfo, acc):
         if acctype and (len(acctype)>0):          """reads contents of access element into docinfo"""
             access=acctype[0].value          #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']:              if access in ['group', 'institution']:
                 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()                      access = acc['name'].lower()
                           
         docinfo['accessType'] = access          docinfo['accessType'] = access
         return docinfo  
       
                   
     def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None):          except:
         """gets bibliographical info from the index.meta file at path or given by dom"""              pass
         zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))  
           
         if docinfo is None:  
             docinfo = {}  
               
         if dom is None:  
             dom = self.getIndexMeta(getParentDir(path))  
               
         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)  
         bibmap=metaData.generateMappingForType(bibtype)  
         #print "bibmap: ", bibmap, " for: ", bibtype  
         # if there is no mapping bibmap is empty (mapping sometimes has empty fields)  
         if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:  
             docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])  
             docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])  
             docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])  
                   
         return docinfo          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
                   
     def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):          dom = ET.fromstring(txt)
        """parse texttool tag in index meta"""          size = getText(dom.find("size"))
        zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url))          logging.debug("getDocinfoFromDigilib: size=%s"%size)
        if docinfo is None:          if size:
            docinfo = {}              docinfo['numPages'] = int(size)
              
        if dom is None:  
            dom = self.getIndexMeta(url)  
          
        archiveNames=dom.xpath("//resource/name")  
        if archiveNames and (len(archiveNames)>0):  
            archiveName=getTextFromNode(archiveNames[0])  
          
        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 not archivePath.endswith(archiveName):  
                archivePath += "/" + archiveName  
        else:  
            archivePath=None  
          
        imageDirs=dom.xpath("//texttool/image")  
        if imageDirs and (len(imageDirs)>0):  
            imageDir=getTextFromNode(imageDirs[0])  
        else:         else:
            # we balk with no image tag              docinfo['numPages'] = 0
            raise IOError("No text-tool info in %s"%(url))  
              
        if imageDir and archivePath:  
            #print "image: ", imageDir, " archivepath: ", archivePath  
            imageDir=os.path.join(archivePath,imageDir)  
            imageDir=imageDir.replace("/mpiwg/online",'')  
            docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo)  
            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  
                     
        textUrls=dom.xpath("//texttool/text")  
        if textUrls and (len(textUrls)>0):  
            textUrl=getTextFromNode(textUrls[0])  
            docinfo['textURL'] = textUrl  
                                             
        docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)          # TODO: produce and keep list of image names and numbers
        docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)  
        return docinfo         return docinfo
         
   
     def getDocinfoFromImagePath(self,path,docinfo=None):      def getDocinfoFromPresentationInfoXml(self,docinfo):
         """path ist the path to the images it assumes that the index.meta file is one level higher."""          """gets DC-like bibliographical information from the presentation entry in texttools"""
         zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path))          url = docinfo.get('presentationUrl', None)
         if docinfo is None:          if not url:
             docinfo = {}              logging.error("getDocinfoFromPresentation: no URL!")
         path=path.replace("/mpiwg/online","")  
         docinfo['imagePath'] = path  
         docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo)  
         imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path  
         docinfo['imageURL'] = imageUrl  
           
         docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo)  
         docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo)  
         return docinfo          return docinfo
           
           dom = None
           metaUrl = None
           if url.startswith("http://"):
               # real URL
               metaUrl = url
           else:
               # online path
           
     def getDocinfo(self, mode, url):              server=self.digilibBaseUrl+"/servlet/Texter?fn="
         """returns docinfo depending on mode"""              metaUrl=server+url
         zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"mode: %s, url: %s"%(mode,url))          
         # look for cached docinfo in session          txt=getHttpData(metaUrl)
         if self.REQUEST.SESSION.has_key('docinfo'):          if txt is None:
             docinfo = self.REQUEST.SESSION['docinfo']              logging.error("Unable to read info.xml from %s"%(url))
             # check if its still current  
             if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:  
                 zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo in session: %s"%docinfo)  
                 return docinfo                  return docinfo
         # new docinfo  
         docinfo = {'mode': mode, 'url': url}  
         if mode=="texttool": #index.meta with texttool information  
             docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)  
         elif mode=="imagepath":  
             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)  
         else:  
             zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!")  
             raise ValueError("Unknown mode %s"%(mode))  
                                                   
         zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo)          dom = ET.fromstring(txt)
         self.REQUEST.SESSION['docinfo'] = docinfo          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):      def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):
         """returns pageinfo with the given parameters"""          """returns pageinfo with the given parameters"""
         pageinfo = {}          pageinfo = {}
         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 381  class documentViewer(Folder): Line 680  class documentViewer(Folder):
         pageinfo['cols'] = cols          pageinfo['cols'] = cols
         grpsize = cols * rows          grpsize = cols * rows
         pageinfo['groupsize'] = grpsize          pageinfo['groupsize'] = grpsize
         start = getInt(start, default=(int(current / grpsize) * grpsize +1))          # what does this do?
           start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*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
                                   
         return pageinfo          pageinfo['viewMode'] = viewMode
                           pageinfo['tocMode'] = tocMode
     def text(self,mode,url,pn):          pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
         """give text"""          #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')
         if mode=="texttool": #index.meta with texttool information          pageinfo['query'] = self.REQUEST.get('query','') 
             (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)          pageinfo['queryType'] = self.REQUEST.get('queryType','')
                   pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
         #print textpath          pageinfo['textPN'] = self.REQUEST.get('textPN','1')
         try:          pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
             dom = NonvalidatingReader.parseUri(textpath)          pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
         except:          pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
             return None          pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
               # WTF?:
         list=[]          toc = int(pageinfo['tocPN'])
         nodes=dom.xpath("//pb")          pageinfo['textPages'] =int(toc)
           
         node=nodes[int(pn)-1]          # What does this do?
                   if 'tocSize_%s'%tocMode in docinfo:
         p=node              tocSize = int(docinfo['tocSize_%s'%tocMode])
                       tocPageSize = int(pageinfo['tocPageSize'])
         while p.tagName!="p":              # cached toc           
             p=p.parentNode              if tocSize%tocPageSize>0:
                           tocPages=tocSize/tocPageSize+1
                       else:
         endNode=nodes[int(pn)]                  tocPages=tocSize/tocPageSize
           
           
         e=endNode  
           
         while e.tagName!="p":  
             e=e.parentNode  
           
                   
         next=node.parentNode              pageinfo['tocPN'] = min(tocPages,toc)
                   
         #sammle s          pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
         while next and (next!=endNode.parentNode):          pageinfo['sn'] =self.REQUEST.get('sn','')
             list.append(next)              return pageinfo
             next=next.nextSibling      
         list.append(endNode.parentNode)  
                   
         if p==e:# beide im selben paragraphen  
             pass  
 #    else:  
 #            next=p  
 #            while next!=e:  
 #                print next,e  
 #                list.append(next)  
 #                next=next.nextSibling  
 #              
 #        for x in list:  
 #            PrettyPrint(x)  
 #  
 #        return list  
 #  
   
     def findDigilibUrl(self):      security.declareProtected('View management screens','changeDocumentViewerForm')    
         """try to get the digilib URL from zogilib"""      changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
         url = self.imageViewerUrl[:-1] + "/getScalerUrl"  
         try:  
             scaler = urlopen(url).read()  
             return scaler.replace("/servlet/Scaler?", "")  
         except:  
             return None  
           
     def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):      def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
         """init document viewer"""          """init document viewer"""
         self.title=title          self.title=title
         self.imageViewerUrl=imageViewerUrl  
         self.digilibBaseUrl = digilibBaseUrl          self.digilibBaseUrl = digilibBaseUrl
         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')
           
       
           
           
 #    security.declareProtected('View management screens','renameImageForm')  
   
 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)
     return pt()      return pt()
       
 def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None):  def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None):
     """add the viewer"""      """add the viewer"""
     newObj=documentViewer(id,imageViewerUrl,title)      newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName)
     self._setObject(id,newObj)      self._setObject(id,newObj)
           
     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"
Line 505  def manage_addDocumentViewerTemplate(sel Line 774  def manage_addDocumentViewerTemplate(sel
   
     self._setObject(id, DocumentViewerTemplate(id))      self._setObject(id, DocumentViewerTemplate(id))
     ob = getattr(self, id)      ob = getattr(self, id)
     ob.pt_edit(open(os.path.join(package_home(globals()),'zpt/viewer_main.zpt')).read(),None)      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:      if title:
         ob.pt_setTitle(title)          ob.pt_setTitle(title)
     try:      try:
Removed from v.1.15  
changed lines
  Added in v.1.175.2.15

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