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

Diff for /documentViewer/documentViewer.py between versions 1.8 and 1.146

version 1.8, 2006/04/11 17:27:57 version 1.146, 2010/10/26 14:44:55
Line 1 Line 1
   
 from OFS.Folder import Folder  from OFS.Folder import Folder
 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate  from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
 from Products.PageTemplates.PageTemplateFile import PageTemplateFile  from Products.PageTemplates.PageTemplateFile import PageTemplateFile
 from AccessControl import ClassSecurityInfo  from AccessControl import ClassSecurityInfo
 from AccessControl import getSecurityManager  from AccessControl import getSecurityManager
 from Globals import package_home  from Globals import package_home
   from Products.zogiLib.zogiLib import browserCheck
   
 from Ft.Xml.Domlette import NonvalidatingReader  from Ft.Xml import EMPTY_NAMESPACE, Parse
 from Ft.Xml.Domlette import PrettyPrint, Print  import Ft.Xml.Domlette
 from Ft.Xml import EMPTY_NAMESPACE  
   
 import Ft.Xml.XPath  
   
 import os.path  import os.path
 import sys  import sys
 import cgi  
 import urllib  import urllib
 import zLOG  import urllib2
   import logging
   import math
   import urlparse 
   import cStringIO
   import re
   
   
   def logger(txt,method,txt2):
       """logging"""
       logging.info(txt+ txt2)
       
   
 def getInt(number, default=0):  def getInt(number, default=0):
     """returns always an int (0 in case of problems)"""      """returns always an int (0 in case of problems)"""
     try:      try:
         return int(number)          return int(number)
     except:      except:
         return default          return int(default)
       
   
 def getTextFromNode(nodename):  def getTextFromNode(nodename):
       """get the cdata content of a node"""
     if nodename is None:      if nodename is None:
         return ""          return ""
     nodelist=nodename.childNodes      nodelist=nodename.childNodes
Line 35  def getTextFromNode(nodename): Line 43  def getTextFromNode(nodename):
            rc = rc + node.data             rc = rc + node.data
     return rc      return rc
   
   def serializeNode(node, encoding='utf-8'):
       """returns a string containing node as XML"""
       buf = cStringIO.StringIO()
       Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding)
       s = buf.getvalue()
       buf.close()
       return s
   
   def getBrowserType(self):
           """get browser type object"""
           if self.REQUEST.SESSION.has_key('browserType'):
               return self.REQUEST.SESSION['browserType']
           else:
               bt = browserCheck(self)
               self.REQUEST.SESSION.set('browserType', bt)    
               logging.debug("documentViewer (BROWSER TYPE) bt %s"%bt)                    
               return bt
   
          
   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  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
   
 def urlopen(url,timeout=2):  
         """urlopen mit timeout"""  
         socket.setdefaulttimeout(timeout)  
         ret=urllib.urlopen(url)  
         socket.setdefaulttimeout(5)  
         return ret  
   
   
 ##  ##
Line 50  def urlopen(url,timeout=2): Line 117  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 60  class documentViewer(Folder): Line 126  class documentViewer(Folder):
   
     # templates and forms      # templates and forms
     viewer_main = PageTemplateFile('zpt/viewer_main', globals())      viewer_main = PageTemplateFile('zpt/viewer_main', globals())
     thumbs_main = PageTemplateFile('zpt/thumbs_main', globals())      toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
     image_main = PageTemplateFile('zpt/image_main', globals())      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_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())
     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())
       
   
       thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
     security.declareProtected('View management screens','changeDocumentViewerForm')          security.declareProtected('View management screens','changeDocumentViewerForm')    
     changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())      changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
   
           
     def __init__(self,id,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))
           try:
               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))
           
           
       # proxy text server methods to fulltextclient
       def getTextPage(self, **args):
           """get page"""
           return self.template.fulltextclient.getTextPage(**args)
   
       def getQuery(self, **args):
           """get query"""
           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 getOrigPages(self, **args):
           """get original page number """
           return self.template.fulltextclient.getOrigPages(**args)
       
       def getNumPages(self, docinfo):
           """get numpages"""
           return self.template.fulltextclient.getNumPages(docinfo)
      
       def getNumTextPages(self, docinfo):
           """get numpages text"""
           return self.template.fulltextclient.getNumTextPages(docinfo)
      
       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 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','index_html')      
     def index_html(self,mode,url,start=None,pn=1):      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")
           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 104  class documentViewer(Folder): Line 243  class documentViewer(Folder):
             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"              self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
                           
         docinfo = self.getDocinfo(mode=mode,url=url)          docinfo = self.getDocinfo(mode=mode,url=url)
           #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
         pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)          pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
           ''' ZDES '''
           pt = getattr(self.template, 'thumbs_main_rss')
           
           if viewMode=="auto": # automodus gewaehlt
               if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
                   viewMode="text"
               else:
                   viewMode="images"
                  
           return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
     
       security.declareProtected('View','index_html')
       def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
           '''
           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)
           @param characterNormalization type of text display (reg, norm, none)
           @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)
           '''
           
           logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
           
           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)
               
           if viewMode=="auto": # automodus gewaehlt
               if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert
                   viewMode="text_dict"
               else:
                   viewMode="images"
                   
           pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
           
         pt = getattr(self.template, 'viewer_main')          pt = getattr(self.template, 'viewer_main')
         return pt(docinfo=docinfo,pageinfo=pageinfo)          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 findDigilibUrl(self):
           """try to get the digilib URL from zogilib"""
           url = self.template.zogilib.getDLBaseUrl()
           return url
   
       def getDocumentViewerURL(self):
           """returns the URL of this instance"""
           return self.absolute_url()
       
       def getStyle(self, idx, selected, style=""):
           """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))
           if idx == selected:
               return style + 'sel'
           else:
               return style
       
     def getLink(self,param=None,val=None):      def getLink(self,param=None,val=None):
         """link to documentviewer with parameter param set to val"""          """link to documentviewer with parameter param set to val"""
         params=cgi.parse_qs(self.REQUEST['QUERY_STRING'])          params=self.REQUEST.form.copy()
         if param is not None:          if param is not None:
             if val is None:              if val is None:
                 if params.has_key(param):                  if params.has_key(param):
                     del params[param]                      del params[param]
             else:              else:
                 params[param] = [str(val)]                  params[param] = str(val)
                                   
         ps = "&".join(["%s=%s"%(k,urllib.quote(v[0])) for (k, v) in params.items()])          if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath
         url=self.REQUEST['URL']+"?"+ps                  params["mode"] = "imagepath"
         #url=self.REQUEST['URL']+"?"+urllib.urlencode(params, doseq=True)                  params["url"] = getParentDir(params["url"])
                   
           # quote values and assemble into query string
           #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
           ps = urllib.urlencode(params)
           url=self.REQUEST['URL1']+"?"+ps
         return url          return url
   
           def getLinkAmp(self,param=None,val=None):
     def getStyle(self, idx, selected, style=""):          """link to documentviewer with parameter param set to val"""
         """returns a string with the given style and append 'sel' if path == selected."""          params=self.REQUEST.form.copy()
         #zLOG.LOG("documentViewer (getstyle)", zLOG.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))          if param is not None:
         if idx == selected:              if val is None:
             return style + 'sel'                  if params.has_key(param):
                       del params[param]
         else:          else:
             return style                      params[param] = str(val)
                   
     def accessOK(self, docinfo):          # quote values and assemble into query string
           logging.debug("XYXXXXX: %s"%repr(params.items()))
           ps = "&amp;".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
           url=self.REQUEST['URL1']+"?"+ps
           return url
       
       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):
         """returns if access to the resource is granted"""          """returns if access to the resource is granted"""
         access = docinfo.get('accessType', None)          access = docinfo.get('accessType', None)
         if access is None:          logging.debug("documentViewer (accessOK) access type %s"%access)
             # no information - no access (not yet)          if access is not None and access == 'free':
             return True              logging.debug("documentViewer (accessOK) access is free")
         elif access == 'free':  
             return True              return True
           elif access is None or access in self.authgroups:
               # only local access -- only logged in users
               user = getSecurityManager().getUser()
               logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr()))
               if user is not None:
                   #print "user: ", user
                   return (user.getUserName() != "Anonymous User")
               else:
                   return False
                   
         print "access: ", access, " authgroups: ", self.authgroups          logging.error("documentViewer (accessOK) unknown access type %s"%access)
         if access in self.authgroups:  
             # local access OK  
             user = getSecurityManager().getUser().getUserName()  
             print "user: ", user  
             return (user != "Anonymous User")  
           
         zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "unknown access group %s"%access)  
         return False          return False
                                   
                   
     def getDirinfoFromDigilib(self,path,docinfo=None):      def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):
         """gibt param von dlInfo aus"""          """gibt param von dlInfo aus"""
         if docinfo is None:          if docinfo is None:
             docinfo = {}              docinfo = {}
                           
         imageUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path          for x in range(cut):
           
         zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(imageUrl))                  path=getParentDir(path)
                   
         try:          infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
             dom = NonvalidatingReader.parseUri(imageUrl)  
         except:  
             zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.ERROR, "error reading %s"%(imageUrl))  
             raise IOError("Unable to get dirinfo from %s"%(imageUrl))  
                   
         params=dom.xpath("//dir/size")          logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))
         zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%params)  
                   
         if params:          txt = getHttpData(infoUrl)
             docinfo['numPages'] = int(getTextFromNode(params[0]))          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:          else:
             docinfo['numPages'] = 0              docinfo['numPages'] = 0
                                                   
           # TODO: produce and keep list of image names and numbers
                           
         return docinfo          return docinfo
           
       def getIndexMetaPath(self,url):
           """gib nur den Pfad zurueck"""
           regexp = re.compile(r".*(experimental|permanent)/(.*)")
           regpath = regexp.match(url)
           if (regpath==None):
               return ""
           logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))            
           return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
        
       
       
       def getIndexMetaUrl(self,url):
           """returns utr  of index.meta document at url"""
         
           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"
           
           return metaUrl
       
       def getDomFromIndexMeta(self, url):
           """get dom from index meta"""
           dom = None
           metaUrl = self.getIndexMetaUrl(url)
                   
           logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)
           txt=getHttpData(metaUrl)
           if txt is None:
               raise IOError("Unable to read index meta from %s"%(url))
           
           dom = Parse(txt)
           return dom
       
       def getPresentationInfoXML(self, url):
           """returns dom of info.xml document at url"""
           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","")
           
           txt=getHttpData(metaUrl)
           if txt is None:
               raise IOError("Unable to read infoXMLfrom %s"%(url))
               
           dom = Parse(txt)
           return dom
                           
     def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None):          
         """gets authorization info from the index.meta file at url or given by dom"""      def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
         zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))          """gets authorization info from the index.meta file at path or given by dom"""
           logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))
                   
         access = None          access = None
                   
Line 189  class documentViewer(Folder): Line 491  class documentViewer(Folder):
             docinfo = {}              docinfo = {}
                           
         if dom is None:          if dom is None:
             server=self.digilibBaseUrl+"/servlet/Texter?fn="              for x in range(cut):
             path="/".join(path.split("/")[0:-1])                  path=getParentDir(path)
             metaUrl=server+path+"/index.meta"              dom = self.getDomFromIndexMeta(path)
             try:  
                 dom = NonvalidatingReader.parseUri(metaUrl)  
             except:  
                 return docinfo  
                           
         acctype = dom.xpath("//access-conditions/access/@type")          acctype = dom.xpath("//access-conditions/access/@type")
         if acctype and (len(acctype)>0):          if acctype and (len(acctype)>0):
             access=acctype[0].value              access=acctype[0].value
             if access == 'group':              if access in ['group', 'institution']:
                 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()                  access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
                           
         docinfo['accessType'] = access          docinfo['accessType'] = access
         return docinfo          return docinfo
           
                   
     def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None):      def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
         """gets bibliographical info from the index.meta file at url or given by dom"""          """gets bibliographical info from the index.meta file at path or given by dom"""
         zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))          logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))
                   
         if docinfo is None:          if docinfo is None:
             docinfo = {}              docinfo = {}
                           
         if dom is None:          if dom is None:
             server=self.digilibBaseUrl+"/servlet/Texter?fn="              for x in range(cut):
             path="/".join(path.split("/")[0:-1])                  path=getParentDir(path)
             metaUrl=server+path+"/index.meta"              dom = self.getDomFromIndexMeta(path)
             try:          
                 dom = NonvalidatingReader.parseUri(metaUrl)          docinfo['indexMetaPath']=self.getIndexMetaPath(path);
             except:          
                 return docinfo          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          metaData=self.metadata.main.meta.bib
         bibtype=dom.xpath("//bib/@type")          bibtype=dom.xpath("//bib/@type")
         if bibtype and (len(bibtype)>0):          if bibtype and (len(bibtype)>0):
             bibtype=bibtype[0].value              bibtype=bibtype[0].value
         else:          else:
             bibtype="generic"              bibtype="generic"
               
         bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)          bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
           docinfo['bib_type'] = bibtype
         bibmap=metaData.generateMappingForType(bibtype)          bibmap=metaData.generateMappingForType(bibtype)
         print "bibmap: ", bibmap, " for: ", bibtype          logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
           logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
         # if there is no mapping bibmap is empty (mapping sometimes has empty fields)          # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
         if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:          if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
               try:
             docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])              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])              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])              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']=''
                   
         return docinfo          return docinfo
   
                   
       def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):
           """gets name info from the index.meta file at path or given by dom"""
           if docinfo is None:
               docinfo = {}
           
           if dom is None:
               for x in range(cut):
                   path=getParentDir(path)
               dom = self.getDomFromIndexMeta(path)
   
           docinfo['name']=getTextFromNode(dom.xpath("/resource/name")[0])
           logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])
           return docinfo
       
     def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):      def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):
        """parse texttool tag in index meta"""         """parse texttool tag in index meta"""
        zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url))          logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
        if docinfo is None:         if docinfo is None:
            docinfo = {}             docinfo = {}
                      if docinfo.get('lang', None) is None:
               docinfo['lang'] = '' # default keine Sprache gesetzt
        if dom is None:         if dom is None:
            try:              dom = self.getDomFromIndexMeta(url)
                dom = NonvalidatingReader.parseUri(url)          
            except:          archivePath = None
                zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])          archiveName = None
                raise IOError("Unable to get texttool info from %s"%(url))  
                 
        archiveNames=dom.xpath("//resource/name")         archiveNames=dom.xpath("//resource/name")
        if archiveNames and (len(archiveNames)>0):         if archiveNames and (len(archiveNames)>0):
            archiveName=getTextFromNode(archiveNames[0])             archiveName=getTextFromNode(archiveNames[0])
           else:
               logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))
                 
        archivePaths=dom.xpath("//resource/archive-path")         archivePaths=dom.xpath("//resource/archive-path")
        if archivePaths and (len(archivePaths)>0):         if archivePaths and (len(archivePaths)>0):
Line 264  class documentViewer(Folder): Line 600  class documentViewer(Folder):
            # clean up archive path             # clean up archive path
            if archivePath[0] != '/':             if archivePath[0] != '/':
                archivePath = '/' + archivePath                 archivePath = '/' + archivePath
            if not archivePath.endswith(archiveName):              if archiveName and (not archivePath.endswith(archiveName)):
                archivePath += "/" + archiveName                 archivePath += "/" + archiveName
        else:         else:
            archivePath=None              # try to get archive-path from url
               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])
                 
        images=dom.xpath("//texttool/image")          else:
        if images and (len(images)>0):              # we balk with no image tag / not necessary anymore because textmode is now standard
            image=getTextFromNode(images[0])              #raise IOError("No text-tool info in %s"%(url))
        else:              imageDir = ""
            image=None              #xquery="//pb"  
                          docinfo['imagePath'] = "" # keine Bilder
        if image and archivePath:              docinfo['imageURL'] = ""
            print "image: ", image, " archivepath: ", archivePath              
            image=os.path.join(archivePath,image)          if imageDir and archivePath:
            image=image.replace("/mpiwg/online",'')              #print "image: ", imageDir, " archivepath: ", archivePath
            docinfo=self.getDirinfoFromDigilib(image,docinfo=docinfo)              imageDir = os.path.join(archivePath, imageDir)
            docinfo['imagePath'] = image              imageDir = imageDir.replace("/mpiwg/online", '')
            docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+image              docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo)
               docinfo['imagePath'] = imageDir
               
               docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir
                         
        viewerUrls=dom.xpath("//texttool/digiliburlprefix")         viewerUrls=dom.xpath("//texttool/digiliburlprefix")
        if viewerUrls and (len(viewerUrls)>0):         if viewerUrls and (len(viewerUrls)>0):
            viewerUrl=getTextFromNode(viewerUrls[0])             viewerUrl=getTextFromNode(viewerUrls[0])
            docinfo['viewerURL'] = viewerUrl             docinfo['viewerURL'] = viewerUrl
                                       
           # old style text URL
        textUrls=dom.xpath("//texttool/text")         textUrls=dom.xpath("//texttool/text")
        if textUrls and (len(textUrls)>0):         if textUrls and (len(textUrls)>0):
            textUrl=getTextFromNode(textUrls[0])             textUrl=getTextFromNode(textUrls[0])
               if urlparse.urlparse(textUrl)[0] == "": #keine url
                   textUrl = os.path.join(archivePath, textUrl) 
               # fix URLs starting with /mpiwg/online
               if textUrl.startswith("/mpiwg/online"):
                   textUrl = textUrl.replace("/mpiwg/online", '', 1)
               
            docinfo['textURL'] = textUrl             docinfo['textURL'] = textUrl
                                             
        docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)          # new style text-url-path
        docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)          textUrls = dom.xpath("//texttool/text-url-path")
           if textUrls and (len(textUrls) > 0):
               textUrl = getTextFromNode(textUrls[0])
               docinfo['textURLPath'] = textUrl
               if not docinfo['imagePath']:
                   # text-only, no page images
                   docinfo = self.getNumTextPages(docinfo)
            
           presentationUrls = dom.xpath("//texttool/presentation")
           docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get info von bib tag
           docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
           #docinfo =self.getOrigPages(docinfo=docinfo)
           
           if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen 
                # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
                # durch den relativen Pfad auf die presentation infos
               presentationPath = getTextFromNode(presentationUrls[0])
               if url.endswith("index.meta"): 
                   presentationUrl = url.replace('index.meta', presentationPath)
               else:
                   presentationUrl = url + "/" + presentationPath
                   
               docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)
       
           docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get access info
           
        return docinfo         return docinfo
         
   
     def getDocinfoFromImagePath(self,path,docinfo=None):      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:
               pass
           return docinfo
       
       def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
         """path ist the path to the images it assumes that the index.meta file is one level higher."""          """path ist the path to the images it assumes that the index.meta file is one level higher."""
         zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path))          logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))
         if docinfo is None:          if docinfo is None:
             docinfo = {}              docinfo = {}
         path=path.replace("/mpiwg/online","")          path=path.replace("/mpiwg/online","")
         docinfo['imagePath'] = path          docinfo['imagePath'] = path
         docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo)          docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut)
           
           pathorig=path
           for x in range(cut):       
                   path=getParentDir(path)
           logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path)
         imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path          imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
         docinfo['imageURL'] = imageUrl          docinfo['imageURL'] = imageUrl
                   
         docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo)          #path ist the path to the images it assumes that the index.meta file is one level higher.
         docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo)          docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
           docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)
         return docinfo          return docinfo
           
           
     def getDocinfo(self, mode, url):      def getDocinfo(self, mode, url):
         """returns docinfo depending on mode"""          """returns docinfo depending on mode"""
         zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"mode: %s, url: %s"%(mode,url))          logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))
         # look for cached docinfo in session          # look for cached docinfo in session
         if self.REQUEST.SESSION.has_key('docinfo'):          if self.REQUEST.SESSION.has_key('docinfo'):
             docinfo = self.REQUEST.SESSION['docinfo']              docinfo = self.REQUEST.SESSION['docinfo']
             # check if its still current              # check if its still current
             if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:              if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
                 zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo in session: %s"%docinfo)                  logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo)
                 return docinfo                  return docinfo
         # new docinfo          # new docinfo
         docinfo = {'mode': mode, 'url': url}          docinfo = {'mode': mode, 'url': url}
Line 330  class documentViewer(Folder): Line 736  class documentViewer(Folder):
             docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)              docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
         elif mode=="imagepath":          elif mode=="imagepath":
             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)              docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
           elif mode=="filepath":
               docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)
         else:          else:
             zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!")              logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
         zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo)              raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
                           
           logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo)
           #logging.debug("documentViewer (getdocinfo) docinfo: %s"%)
         self.REQUEST.SESSION['docinfo'] = docinfo          self.REQUEST.SESSION['docinfo'] = docinfo
         return docinfo          return docinfo
                   
               def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
     def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None):  
         """returns pageinfo with the given parameters"""          """returns pageinfo with the given parameters"""
         pageinfo = {}          pageinfo = {}
         current = getInt(current)          current = getInt(current)
       
         pageinfo['current'] = current          pageinfo['current'] = current
         rows = int(rows or self.thumbrows)          rows = int(rows or self.thumbrows)
         pageinfo['rows'] = rows          pageinfo['rows'] = rows
Line 348  class documentViewer(Folder): Line 759  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))          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
           pageinfo['viewMode'] = viewMode
           pageinfo['tocMode'] = tocMode
           #pageinfo ['originalPage'] = self.getOrigPages(docinfo=None, pageinfo=None)
           pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','')
           pageinfo['query'] = self.REQUEST.get('query','')
           pageinfo['queryType'] = self.REQUEST.get('queryType','')
           pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
           pageinfo['textPN'] = self.REQUEST.get('textPN','1')
           pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
           pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
           pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')
           pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
           toc = int (pageinfo['tocPN'])
           pageinfo['textPages'] =int (toc)
                                   
         return pageinfo  
                   
     def text(self,mode,url,pn):  
         """give text"""  
         if mode=="texttool": #index.meta with texttool information  
             (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)  
           
         print textpath  
         try:  
             dom = NonvalidatingReader.parseUri(textpath)  
         except:  
             return None  
       
         list=[]  
         nodes=dom.xpath("//pb")  
   
         node=nodes[int(pn)-1]  
           
         p=node  
           
         while p.tagName!="p":  
             p=p.parentNode  
                   
                   
         endNode=nodes[int(pn)]          if 'tocSize_%s'%tocMode in docinfo:
                       tocSize = int(docinfo['tocSize_%s'%tocMode])
                       tocPageSize = int(pageinfo['tocPageSize'])
         e=endNode              # cached toc           
                       if tocSize%tocPageSize>0:
         while e.tagName!="p":                  tocPages=tocSize/tocPageSize+1
             e=e.parentNode              else:
                           tocPages=tocSize/tocPageSize
                       pageinfo['tocPN'] = min (tocPages,toc)                    
         next=node.parentNode          pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
                   pageinfo['sn'] =self.REQUEST.get('sn','')
         #sammle s          return pageinfo
         while next and (next!=endNode.parentNode):  
             list.append(next)      
             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):  
         """try to get the digilib URL from zogilib"""  
         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
Line 434  class documentViewer(Folder): Line 809  class documentViewer(Folder):
         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 472  def manage_addDocumentViewerTemplate(sel Line 839  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.1.8  
changed lines
  Added in v.1.146

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