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

Diff for /documentViewer/documentViewer.py between versions 1.175.2.7 and 1.175.2.27

version 1.175.2.7, 2011/07/20 19:36:57 version 1.175.2.27, 2011/08/16 16:27:08
Line 1 Line 1
 from OFS.Folder import Folder  from OFS.Folder import Folder
   from OFS.Image import File
 from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate  from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
 from Products.PageTemplates.PageTemplateFile import PageTemplateFile   from Products.PageTemplates.PageTemplateFile import PageTemplateFile 
 from AccessControl import ClassSecurityInfo  from AccessControl import ClassSecurityInfo
Line 98  def browserCheck(self): Line 99  def browserCheck(self):
   
     return bt      return bt
   
 def getParentDir(path):  def getParentPath(path, cnt=1):
     """returns pathname shortened by one"""      """returns pathname shortened by cnt"""
     return '/'.join(path.split('/')[0:-1])      # make sure path doesn't end with /
               path = path.rstrip('/')
 def normalizeBibtype(bt):      # split by /, shorten, and reassemble
     """returns normalised bib type for looking up mappings"""      return '/'.join(path.split('/')[0:-cnt])
     bt = bt.strip().replace(' ', '-').lower()  
     return bt  
   
 def getBibdataFromDom(dom):  
     """returns dict with all elements from bib-tag"""  
     bibinfo = {}  
     bib = dom.find(".//meta/bib")  
     if bib is not None:  
         # put type in @type  
         type = bib.get('type')  
         bibinfo['@type'] = normalizeBibtype(type)  
         # put all subelements in dict  
         for e in bib:  
             bibinfo[e.tag] = getText(e)  
                           
     return bibinfo  
   
 ##  ##
 ## documentViewer class  ## documentViewer class
Line 133  class documentViewer(Folder): Line 119  class documentViewer(Folder):
         {'label':'main config','action':'changeDocumentViewerForm'},          {'label':'main config','action':'changeDocumentViewerForm'},
         )          )
   
       metadataService = None
       """MetaDataFolder instance"""
   
     # templates and forms      # templates and forms
       viewer_text = PageTemplateFile('zpt/viewer_text', globals())
     viewer_main = PageTemplateFile('zpt/viewer_main', globals())      viewer_main = PageTemplateFile('zpt/viewer_main', globals())
     toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())      toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals())
     toc_text = PageTemplateFile('zpt/toc_text', globals())      toc_text = PageTemplateFile('zpt/toc_text', globals())
Line 146  class documentViewer(Folder): Line 136  class documentViewer(Folder):
     page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())      page_main_xml = PageTemplateFile('zpt/page_main_xml', globals())
     page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())      page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals())
     head_main = PageTemplateFile('zpt/head_main', globals())      head_main = PageTemplateFile('zpt/head_main', globals())
     docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())  
     info_xml = PageTemplateFile('zpt/info_xml', globals())      info_xml = PageTemplateFile('zpt/info_xml', globals())
       # TODO: can this be nicer?
       docuviewer_css = File('docuviewer_css','',open(os.path.join(package_home(globals()),'css/docuviewer.css')), content_type='text/css')
           
           
     thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())      thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals())
     security.declareProtected('View management screens','changeDocumentViewerForm')      
     changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())  
   
           
     def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):      def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"):
Line 175  class documentViewer(Folder): Line 164  class documentViewer(Folder):
             templateFolder._setObject('fulltextclient',textServer)              templateFolder._setObject('fulltextclient',textServer)
         except Exception, e:          except Exception, e:
             logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))              logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e))
               
         try:          try:
             from Products.zogiLib.zogiLib import zogiLib              from Products.zogiLib.zogiLib import zogiLib
             zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")              zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book")
Line 183  class documentViewer(Folder): Line 173  class documentViewer(Folder):
         except Exception, e:          except Exception, e:
             logging.error("Unable to create zogiLib for zogilib: "+str(e))              logging.error("Unable to create zogiLib for zogilib: "+str(e))
                   
           try:
               # assume MetaDataFolder instance is called metadata 
               self.metadataService = getattr(self, 'metadata')
           except Exception, e:
               logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
               
           if digilibBaseUrl is not None:
               self.digilibBaseUrl = digilibBaseUrl
               
                   
     # proxy text server methods to fulltextclient      # proxy text server methods to fulltextclient
     def getTextPage(self, **args):      def getTextPage(self, **args):
Line 213  class documentViewer(Folder): Line 212  class documentViewer(Folder):
         """get all gis places """          """get all gis places """
         return self.template.fulltextclient.getAllGisPlaces(**args)          return self.template.fulltextclient.getAllGisPlaces(**args)
                 
     def getTranslate(self, **args):      def getWordInfo(self, **args):
         """get translate"""          """get translate"""
         return self.template.fulltextclient.getTranslate(**args)          return self.template.fulltextclient.getWordInfo(**args)
   
     def getLemma(self, **args):      def getLemma(self, **args):
         """get lemma"""          """get lemma"""
Line 271  class documentViewer(Folder): Line 270  class documentViewer(Folder):
                                 
         return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)          return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode)
       
     
     security.declareProtected('View','index_html')      security.declareProtected('View','index_html')
     def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None):      def index_html(self,url,mode="texttool",viewMode="auto",viewType=None,tocMode="thumbs",start=1,pn=1):
         '''          """
         view it          view page
         @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 auto (text,images or auto)          @param mode: defines how to access the document behind url 
           @param viewMode: 'images': display images, 'text': display text, default is 'auto'
           @param viewType: sub-type of viewMode, e.g. 'dict' for viewMode='text'
         @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)          @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none)
         @param characterNormalization type of text display (reg, norm, none)          """
         @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma)  
         '''  
                   
         logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))          logging.debug("documentViewer(index_html) mode=%s url=%s viewMode=%s viewType=%s start=%s pn=%s"%(mode,url,viewMode,viewType,start,pn))
                   
         if not hasattr(self, 'template'):          if not hasattr(self, 'template'):
             # this won't work              # this won't work
Line 299  class documentViewer(Folder): Line 298  class documentViewer(Folder):
             # get table of contents              # get table of contents
             docinfo = self.getToc(mode=tocMode, docinfo=docinfo)              docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
   
         # auto viewMode: text_dict if text else images          # auto viewMode: text if there is a text else images
         if viewMode=="auto":           if viewMode=="auto": 
             if docinfo.get('textURL', None) or docinfo.get('textURLPath', None):               if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): 
                 #texturl gesetzt und textViewer konfiguriert                  viewMode = "text"
                 viewMode="text_dict"                  viewType = "dict"
             else:              else:
                 viewMode="images"                  viewMode="images"
                                   
         pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode)          elif viewMode == "text_dict":
               # legacy fix
               viewMode = "text"
               viewType = "dict"
                   
         if viewMode != 'images' and docinfo.get('textURLPath', None):          # stringify viewType
             # get full text page          if isinstance(viewType, list):
             page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo)              logging.debug("index_html: viewType is list:%s"%viewType)
             pageinfo['textPage'] = page              viewType = ','.join([t for t in viewType if t])
                           
           pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, viewType=viewType, tocMode=tocMode)
                       
           # get template /template/viewer_$viewMode
           pt = getattr(self.template, 'viewer_%s'%viewMode, None)
           if pt is None:
               logging.error("No template for viewMode=%s!"%viewMode)
               # TODO: error page?
               return "No template for viewMode=%s!"%viewMode
                           
         # get template /template/viewer_main  
         pt = getattr(self.template, 'viewer_main')  
         # and execute with parameters          # and execute with parameters
         return pt(docinfo=docinfo, pageinfo=pageinfo, viewMode=viewMode, mk=self.generateMarks(mk))          return pt(docinfo=docinfo, pageinfo=pageinfo)
       
     def generateMarks(self,mk):      def generateMarks(self,mk):
         ret=""          ret=""
Line 341  class documentViewer(Folder): Line 350  class documentViewer(Folder):
         url = self.template.zogilib.getDLBaseUrl()          url = self.template.zogilib.getDLBaseUrl()
         return url          return url
   
       def getScalerUrl(self, fn=None, pn=None, dw=100, dh=100, docinfo=None):
           """returns URL to digilib Scaler with params"""
           url = None
           if docinfo is not None:
               url = docinfo.get('imageURL', None)
               
           if url is None:
               url = "%s/servlet/Scaler?"%self.digilibBaseUrl
               if fn is None and docinfo is not None:
                   fn = docinfo.get('imagePath','')
               
               url += "fn=%s"%fn
               
           if pn:
               url += "&pn=%s"%pn
               
           url += "&dw=%s&dh=%s"%(dw,dh)
           return url
   
     def getDocumentViewerURL(self):      def getDocumentViewerURL(self):
         """returns the URL of this instance"""          """returns the URL of this instance"""
         return self.absolute_url()          return self.absolute_url()
           
     def getStyle(self, idx, selected, style=""):      def getStyle(self, idx, selected, style=""):
         """returns a string with the given style and append 'sel' if path == selected."""          """returns a string with the given style and append 'sel' if idx == selected."""
         #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))          #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
         if idx == selected:          if idx == selected:
             return style + 'sel'              return style + 'sel'
         else:          else:
             return style              return style
           
     def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'):      def getParams(self, param=None, val=None, params=None, duplicates=None):
         """returns URL to documentviewer with parameter param set to val or from dict params"""          """returns dict with URL parameters.
           
           Takes URL parameters and additionally param=val or dict params.
           Deletes key if value is None."""
         # copy existing request params          # copy existing request params
         urlParams=self.REQUEST.form.copy()          newParams=self.REQUEST.form.copy()
         # change single param          # change single param
         if param is not None:          if param is not None:
             if val is None:              if val is None:
                 if urlParams.has_key(param):                  if newParams.has_key(param):
                     del urlParams[param]                      del newParams[param]
             else:              else:
                 urlParams[param] = str(val)                  newParams[param] = str(val)
                                   
         # change more params          # change more params
         if params is not None:          if params is not None:
             for k in params.keys():              for (k, v) in params.items():
                 v = params[k]  
                 if v is None:                  if v is None:
                     # val=None removes param                      # val=None removes param
                     if urlParams.has_key(k):                      if newParams.has_key(k):
                         del urlParams[k]                          del newParams[k]
                                                   
                 else:                  else:
                     urlParams[k] = v                      newParams[k] = v
   
         # FIXME: does this belong here?          if duplicates:
         if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath              # eliminate lists (coming from duplicate keys)
                 urlParams["mode"] = "imagepath"              for (k,v) in newParams.items():
                 urlParams["url"] = getParentDir(urlParams["url"])                  if isinstance(v, list):
                       if duplicates == 'comma':
                           # make comma-separated list of non-empty entries
                           newParams[k] = ','.join([t for t in v if t])
                       elif duplicates == 'first':
                           # take first non-empty entry
                           newParams[k] = [t for t in v if t][0]
                                   
           return newParams
       
       def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&', duplicates='comma'):
           """returns URL to documentviewer with parameter param set to val or from dict params"""
           urlParams = self.getParams(param=param, val=val, params=params, duplicates=duplicates)
         # quote values and assemble into query string (not escaping '/')          # quote values and assemble into query string (not escaping '/')
         ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()])          ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(unicode(v),'/')) for (k, v) in urlParams.items()])
         #ps = urllib.urlencode(urlParams)  
         if baseUrl is None:          if baseUrl is None:
             baseUrl = self.REQUEST['URL1']              baseUrl = self.getDocumentViewerURL()
                           
         url = "%s?%s"%(baseUrl, ps)          url = "%s?%s"%(baseUrl, ps)
         return url          return url
   
       def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None, duplicates='comma'):
     def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None):  
         """link to documentviewer with parameter param set to val"""          """link to documentviewer with parameter param set to val"""
         return self.getLink(param, val, params, baseUrl, '&')          return self.getLink(param=param, val=val, params=params, baseUrl=baseUrl, paramSep='&', duplicates=duplicates)
       
           
     def getInfo_xml(self,url,mode):      def getInfo_xml(self,url,mode):
         """returns info about the document as XML"""          """returns info about the document as XML"""
   
         if not self.digilibBaseUrl:          if not self.digilibBaseUrl:
             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"              self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
                   
Line 406  class documentViewer(Folder): Line 445  class documentViewer(Folder):
         pt = getattr(self.template, 'info_xml')          pt = getattr(self.template, 'info_xml')
         return pt(docinfo=docinfo)          return pt(docinfo=docinfo)
   
     def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True):  
         """returns new option state"""  
         if not self.REQUEST.SESSION.has_key(optionName):  
             # not in session -- initial  
             opt = {'lastState': newState, 'state': initialState}  
         else:  
             opt = self.REQUEST.SESSION.get(optionName)  
             if opt['lastState'] != newState:  
                 # state in session has changed -- toggle  
                 opt['state'] = not opt['state']  
                 opt['lastState'] = newState  
           
         self.REQUEST.SESSION[optionName] = opt  
         return opt['state']  
       
     def isAccessible(self, docinfo):      def isAccessible(self, docinfo):
         """returns if access to the resource is granted"""          """returns if access to the resource is granted"""
         access = docinfo.get('accessType', None)          access = docinfo.get('accessType', None)
         logging.debug("documentViewer (accessOK) access type %s"%access)          logging.debug("documentViewer (accessOK) access type %s"%access)
         if access is not None and access == 'free':          if access == 'free':
             logging.debug("documentViewer (accessOK) access is free")              logging.debug("documentViewer (accessOK) access is free")
             return True              return True
           
         elif access is None or access in self.authgroups:          elif access is None or access in self.authgroups:
             # only local access -- only logged in users              # only local access -- only logged in users
             user = getSecurityManager().getUser()              user = getSecurityManager().getUser()
Line 442  class documentViewer(Folder): Line 467  class documentViewer(Folder):
         return False          return False
           
                                   
     def getDirinfoFromDigilib(self,path,docinfo=None,cut=0):  
         """gibt param von dlInfo aus"""  
         if docinfo is None:  
             docinfo = {}  
                   
         for x in range(cut):      def getDocinfo(self, mode, url):
             path=getParentDir(path)          """returns docinfo depending on mode"""
                  logging.debug("getDocinfo: mode=%s, url=%s"%(mode,url))
         infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path          # look for cached docinfo in session
           if self.REQUEST.SESSION.has_key('docinfo'):
               docinfo = self.REQUEST.SESSION['docinfo']
               # check if its still current
               if docinfo is not None and docinfo.get('mode', None) == mode and docinfo.get('url', None) == url:
                   logging.debug("getDocinfo: docinfo in session. keys=%s"%docinfo.keys())
                   return docinfo
           
         logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl))          # new docinfo
           docinfo = {'mode': mode, 'url': url}
           # add self url
           docinfo['viewerUrl'] = self.getDocumentViewerURL()
           docinfo['digilibBaseUrl'] = self.digilibBaseUrl
           # 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!")
                   
         txt = getHttpData(infoUrl)          elif mode=="imagepath":
         if txt is None:              # url points to folder with images, index.meta optional
             raise IOError("Unable to get dir-info from %s"%(infoUrl))              # asssume index.meta in parent dir
               docUrl = getParentPath(url)
               metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
   
         dom = ET.fromstring(txt)          elif mode=="filepath":
         #dom = Parse(txt)              # url points to image file, index.meta optional
         size=getText(dom.find("size"))              # asssume index.meta is two path segments up
         #sizes=dom.xpath("//dir/size")              docUrl = getParentPath(url, 2)
         logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size)              metaDom = self.metadataService.getDomFromPathOrUrl(docUrl)
                   
         if size:  
             docinfo['numPages'] = int(size)  
         else:          else:
             docinfo['numPages'] = 0              logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)
               raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))
                           
         # TODO: produce and keep list of image names and numbers          docinfo['documentUrl'] = docUrl
           # process index.meta contents
           if metaDom is not None and metaDom.tag == 'resource':
               # document directory name and path
               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 with url
               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 getIndexMetaPath(self,url):      def getDocinfoFromResource(self, docinfo, resource):
         """gib nur den Pfad zurueck"""          """reads contents of resource element into docinfo"""
         regexp = re.compile(r".*(experimental|permanent)/(.*)")          docName = resource.get('name', None)
         regpath = regexp.match(url)          docinfo['documentName'] = docName
         if (regpath==None):          docPath = resource.get('archive-path', None)
             return ""          if docPath:
         logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))                          # clean up document path
         return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))              if docPath[0] != '/':
                   docPath = '/' + docPath
                   
               if docName and (not docPath.endswith(docName)):
                   docPath += "/" + docName
               
           else:
               # use docUrl as docPath
               docUrl = docinfo['documentURL']
               if not docUrl.startswith('http:'):
                   docPath = docUrl
           if docPath:
               # fix URLs starting with /mpiwg/online
               docPath = docPath.replace('/mpiwg/online', '', 1)
             
           docinfo['documentPath'] = docPath
           return docinfo
           
       def getDocinfoFromTexttool(self, docinfo, texttool):
           """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
           
     def getIndexMetaUrl(self,url):          # old style text URL
         """returns utr  of index.meta document at url"""          textUrl = texttool.get('text', None)
           if textUrl and docPath:
               if urlparse.urlparse(textUrl)[0] == "": #keine url
                   textUrl = os.path.join(docPath, textUrl) 
               
         metaUrl = None              docinfo['textURL'] = textUrl
         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          # new style text-url-path
           textUrl = texttool.get('text-url-path', None)
           if textUrl:
               docinfo['textURLPath'] = textUrl
           
     def getDomFromIndexMeta(self, url):          # page flow
         """get dom from index meta"""          docinfo['pageFlow'] = texttool.get('page-flow', 'ltr')
         dom = None  
         metaUrl = self.getIndexMetaUrl(url)  
                                   
         logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl)          # odd pages are left
         txt=getHttpData(metaUrl)          docinfo['oddPage'] = texttool.get('odd-scan-position', 'left')
         if txt is None:  
             raise IOError("Unable to read index meta from %s"%(url))  
                   
         dom = ET.fromstring(txt)          # number of title page (0: not defined)
         #dom = Parse(txt)          docinfo['titlePage'] = texttool.get('title-scan-no', 0)
         return dom  
           
     def getPresentationInfoXML(self, url):          # old presentation stuff
         """returns dom of info.xml document at url"""          presentation = texttool.get('presentation', None)
         dom = None          if presentation and docPath:
         metaUrl = None              if presentation.startswith('http:'):
         if url.startswith("http://"):                  docinfo['presentationUrl'] = presentation
             # real URL  
             metaUrl = url  
         else:          else:
             # online path                  docinfo['presentationUrl'] = os.path.join(docPath, presentation)
             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 = ET.fromstring(txt)  
         #dom = Parse(txt)  
         return dom  
                           
                   
     def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):  
         """gets authorization info from the index.meta file at path or given by dom"""  
         logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path))  
                   
         access = None          return docinfo
           
         if docinfo is None:  
             docinfo = {}  
                           
         if dom is None:      def getDocinfoFromBib(self, docinfo, bib):
             for x in range(cut):          """reads contents of bib element into docinfo"""
                 path=getParentDir(path)          logging.debug("getDocinfoFromBib bib=%s"%repr(bib))
             dom = self.getDomFromIndexMeta(path)          # 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
                 
         acc = dom.find(".//access-conditions/access")      def getDocinfoFromAccess(self, docinfo, acc):
         if acc is not None:          """reads contents of access element into docinfo"""
             acctype = acc.get('type')          #TODO: also read resource type
             #acctype = dom.xpath("//access-conditions/access/@type")          logging.debug("getDocinfoFromAccess acc=%s"%repr(acc))
           try:
               acctype = acc['@attr']['type']
             if acctype:              if acctype:
                 access=acctype                  access=acctype
                 if access in ['group', 'institution']:                  if access in ['group', 'institution']:
                     access = dom.find(".//access-conditions/access/name").text.lower()                      access = acc['name'].lower()
                           
         docinfo['accessType'] = access          docinfo['accessType'] = access
         return docinfo  
       
           
     def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):  
         """gets bibliographical info from the index.meta file at path or given by dom"""  
         logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path))  
           
         if docinfo is None:  
             docinfo = {}  
                   
         if dom is None:  
             for x in range(cut):  
                 path=getParentDir(path)  
             dom = self.getDomFromIndexMeta(path)  
           
         docinfo['indexMetaPath']=self.getIndexMetaPath(path);  
           
         logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))  
         # put all raw bib fields in dict "bib"  
         bib = getBibdataFromDom(dom)  
         docinfo['bib'] = bib  
         bibtype = bib.get('@type', None)  
         docinfo['bib_type'] = bibtype  
         if bibtype:  
             # also store standard mapped metadata for convenience  
             try:  
                 stdbib = self.metadata.getStdMappedHash(bib)  
                 docinfo['std_bib'] = stdbib  
                 docinfo['author'] = stdbib['author']  
                 docinfo['title'] = stdbib['title']  
                 docinfo['year'] = stdbib['year']  
             except:              except:
                 pass                  pass
   
         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
           
     # TODO: is this needed?          dom = ET.fromstring(txt)
     def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0):          size = getText(dom.find("size"))
         """gets name info from the index.meta file at path or given by dom"""          logging.debug("getDocinfoFromDigilib: size=%s"%size)
         if docinfo is None:          if size:
             docinfo = {}              docinfo['numPages'] = int(size)
           
         if dom is None:  
             for x in range(cut):  
                 path=getParentDir(path)  
             dom = self.getDomFromIndexMeta(path)  
   
         docinfo['name']=getText(dom.find("name"))  
         logging.debug("documentViewer docinfo[name] %s"%docinfo['name'])  
         return docinfo  
       
     def getDocinfoFromTextTool(self, url, dom=None, docinfo=None):  
         """parse texttool tag in index meta"""  
         logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))  
         if docinfo is None:  
            docinfo = {}  
         if docinfo.get('lang', None) is None:  
             docinfo['lang'] = '' # default keine Sprache gesetzt  
         if dom is None:  
             dom = self.getDomFromIndexMeta(url)  
           
         archivePath = None  
         archiveName = None  
       
         archiveName = getText(dom.find("name"))  
         if not archiveName:  
             logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url))  
           
         archivePath = getText(dom.find("archive-path"))  
         if archivePath:  
             # clean up archive path  
             if archivePath[0] != '/':  
                 archivePath = '/' + archivePath  
             if archiveName and (not archivePath.endswith(archiveName)):  
                 archivePath += "/" + archiveName  
         else:  
             # try to get archive-path from url  
             logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url))  
             if (not url.startswith('http')):  
                 archivePath = url.replace('index.meta', '')  
                   
         if archivePath is None:  
             # we balk without archive-path  
             raise IOError("Missing archive-path (for text-tool) in %s" % (url))  
           
         imageDir = getText(dom.find(".//texttool/image"))  
               
         if not imageDir:  
             # we balk with no image tag / not necessary anymore because textmode is now standard  
             #raise IOError("No text-tool info in %s"%(url))  
             imageDir = ""  
             #xquery="//pb"    
             docinfo['imagePath'] = "" # keine Bilder  
             docinfo['imageURL'] = ""  
               
         if imageDir and archivePath:  
             #print "image: ", imageDir, " archivepath: ", archivePath  
             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  
               
         viewerUrl = getText(dom.find(".//texttool/digiliburlprefix"))  
         if viewerUrl:  
             docinfo['viewerURL'] = viewerUrl  
           
         # old style text URL  
         textUrl = getText(dom.find(".//texttool/text"))  
         if textUrl:  
             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  
       
         # new style text-url-path  
         textUrl = getText(dom.find(".//texttool/text-url-path"))  
         if textUrl:  
             docinfo['textURLPath'] = textUrl  
             textUrlkurz = string.split(textUrl, ".")[0]  
             docinfo['textURLPathkurz'] = textUrlkurz  
             #if not docinfo['imagePath']:  
                 # text-only, no page images  
                 #docinfo = self.getNumTextPages(docinfo)  
                     
            
         presentationUrl = getText(dom.find(".//texttool/presentation"))  
         docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get info von bib tag  
         # TODO: is this needed here?  
         docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)  
           
           
         if presentationUrl: # 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 = presentationUrl  
             if url.endswith("index.meta"):   
                 presentationUrl = url.replace('index.meta', presentationPath)  
             else:              else:
                 presentationUrl = url + "/" + presentationPath              docinfo['numPages'] = 0
                   
             docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom)  
       
         docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get access info  
                   
           # TODO: produce and keep list of image names and numbers
         return docinfo          return docinfo
         
         
     def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None):      def getDocinfoFromPresentationInfoXml(self,docinfo):
         """gets the bibliographical information from the preseantion entry in texttools          """gets DC-like bibliographical information from the presentation entry in texttools"""
         """          url = docinfo.get('presentationUrl', None)
         dom=self.getPresentationInfoXML(url)          if not url:
         docinfo['author']=getText(dom.find(".//author"))              logging.error("getDocinfoFromPresentation: no URL!")
         docinfo['title']=getText(dom.find(".//title"))  
         docinfo['year']=getText(dom.find(".//date"))  
         return docinfo          return docinfo
           
     def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):          dom = None
         """path ist the path to the images it assumes that the index.meta file is one level higher."""          metaUrl = None
         logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path))          if url.startswith("http://"):
         if docinfo is None:              # real URL
             docinfo = {}              metaUrl = url
         path=path.replace("/mpiwg/online","")          else:
         docinfo['imagePath'] = path              # online path
         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  
         docinfo['imageURL'] = imageUrl  
           
         #TODO: use getDocinfoFromIndexMeta  
         #path ist the path to the images it assumes that the index.meta file is one level higher.  
         docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)  
         docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1)  
         return docinfo  
           
               server=self.digilibBaseUrl+"/servlet/Texter?fn="
               metaUrl=server+url
           
     def getDocinfo(self, mode, url):          txt=getHttpData(metaUrl)
         """returns docinfo depending on mode"""          if txt is None:
         logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url))              logging.error("Unable to read info.xml from %s"%(url))
         # look for cached docinfo in session  
         if self.REQUEST.SESSION.has_key('docinfo'):  
             docinfo = self.REQUEST.SESSION['docinfo']  
             # check if its still current  
             if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:  
                 logging.debug("documentViewer (getdocinfo) docinfo in session. keys=%s"%docinfo.keys())  
                 return docinfo                  return docinfo
                           
         # new docinfo          dom = ET.fromstring(txt)
         docinfo = {'mode': mode, 'url': url}          docinfo['creator']=getText(dom.find(".//author"))
         # add self url          docinfo['title']=getText(dom.find(".//title"))
         docinfo['viewerUrl'] = self.getDocumentViewerURL()          docinfo['date']=getText(dom.find(".//date"))
         if mode=="texttool":   
             # index.meta with texttool information  
             docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)  
         elif mode=="imagepath":  
             # folder with images, index.meta optional  
             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)  
         elif mode=="filepath":  
             # filename  
             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1)  
         else:  
             logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode)  
             raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode))  
                   
         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 getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None):  
       def getPageinfo(self, current=None, start=None, rows=None, cols=None, docinfo=None, viewMode=None, viewType=None, tocMode=None):
         """returns pageinfo with the given parameters"""          """returns pageinfo with the given parameters"""
           logging.debug("getPageInfo(current=%s, start=%s, rows=%s, cols=%s, viewMode=%s, viewType=%s, tocMode=%s)"%(current,start,rows,cols,viewMode,viewType,tocMode))
         pageinfo = {}          pageinfo = {}
         current = getInt(current)          pageinfo['viewMode'] = viewMode
           pageinfo['viewType'] = viewType
           pageinfo['tocMode'] = tocMode
           
           current = getInt(current)
         pageinfo['current'] = current          pageinfo['current'] = current
           pageinfo['pn'] = current
         rows = int(rows or self.thumbrows)          rows = int(rows or self.thumbrows)
         pageinfo['rows'] = rows          pageinfo['rows'] = rows
         cols = int(cols or self.thumbcols)          cols = int(cols or self.thumbcols)
         pageinfo['cols'] = cols          pageinfo['cols'] = cols
         grpsize = cols * rows          grpsize = cols * rows
         pageinfo['groupsize'] = grpsize          pageinfo['groupsize'] = grpsize
         # what does this do?          # is start is empty use one around current
         start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))          start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1)))
         # int(current / grpsize) * grpsize +1))          # int(current / grpsize) * grpsize +1))
         pageinfo['start'] = start          pageinfo['start'] = start
         pageinfo['end'] = start + grpsize          
         if (docinfo is not None) and ('numPages' in docinfo):          np = int(docinfo.get('numPages', 0))
             np = int(docinfo['numPages'])          if np == 0:
             pageinfo['end'] = min(pageinfo['end'], np)              # numPages unknown - maybe we can get it from text page
               if docinfo.get('textURLPath', None):
                   # cache text page as well
                   pageinfo['textPage'] = self.getTextPage(mode=viewType, pn=current, docinfo=docinfo, pageinfo=pageinfo)
                   np = int(docinfo.get('numPages', 0))
                   
             pageinfo['numgroups'] = int(np / grpsize)              pageinfo['numgroups'] = int(np / grpsize)
             if np % grpsize > 0:              if np % grpsize > 0:
                 pageinfo['numgroups'] += 1                  pageinfo['numgroups'] += 1
                                   
         pageinfo['viewMode'] = viewMode          pageFlowLtr = docinfo.get('pageFlow', 'ltr') != 'rtl'
         pageinfo['tocMode'] = tocMode          oddScanLeft = docinfo.get('oddPage', 'left') != 'right'
           # add zeroth page for two columns
           pageZero = (cols == 2 and (pageFlowLtr != oddScanLeft))
           pageinfo['pageZero'] = pageZero
           pageinfo['pageBatch'] = self.getPageBatch(start=start, rows=rows, cols=cols, pageFlowLtr=pageFlowLtr, pageZero=pageZero, minIdx=1, maxIdx=np)
                   
           # TODO: do we need this here?
         pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')          pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','reg')
         #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1')  
         pageinfo['query'] = self.REQUEST.get('query','')           pageinfo['query'] = self.REQUEST.get('query','') 
         pageinfo['queryType'] = self.REQUEST.get('queryType','')          pageinfo['queryType'] = self.REQUEST.get('queryType','')
         pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')          pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
         pageinfo['textPN'] = self.REQUEST.get('textPN','1')  
         pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')          pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','')
         pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')          pageinfo['tocPageSize'] = getInt(self.REQUEST.get('tocPageSize', 30))
         pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10')          pageinfo['queryPageSize'] = getInt(self.REQUEST.get('queryPageSize', 10))
         pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')          pageinfo['tocPN'] = getInt(self.REQUEST.get('tocPN', '1'))
         # WTF?:          pageinfo['searchPN'] = getInt(self.REQUEST.get('searchPN','1'))
         toc = int(pageinfo['tocPN'])  
         pageinfo['textPages'] =int(toc)  
                   
         # What does this do?          # limit tocPN
         if 'tocSize_%s'%tocMode in docinfo:          if 'tocSize_%s'%tocMode in docinfo:
             tocSize = int(docinfo['tocSize_%s'%tocMode])              tocSize = docinfo['tocSize_%s'%tocMode]
             tocPageSize = int(pageinfo['tocPageSize'])              tocPageSize = pageinfo['tocPageSize']
             # cached toc                         # cached toc           
             if tocSize%tocPageSize>0:              if tocSize%tocPageSize>0:
                 tocPages=tocSize/tocPageSize+1                  tocPages=tocSize/tocPageSize+1
             else:              else:
                 tocPages=tocSize/tocPageSize                  tocPages=tocSize/tocPageSize
                                   
             pageinfo['tocPN'] = min(tocPages,toc)              pageinfo['tocPN'] = min(tocPages,pageinfo['tocPN'])
                           
         pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')  
         pageinfo['sn'] =self.REQUEST.get('sn','')  
         return pageinfo          return pageinfo
   
           
       def getPageBatch(self, start=1, rows=10, cols=2, pageFlowLtr=True, pageZero=False, minIdx=1, maxIdx=0):
           """returns dict with array of page informations for one screenfull of thumbnails"""
           batch = {}
           grpsize = rows * cols
           if maxIdx == 0:
               maxIdx = start + grpsize
   
           nb = int(math.ceil(maxIdx / float(grpsize)))
           # list of all batch start and end points
           batches = []
           if pageZero:
               ofs = 0
           else:
               ofs = 1
               
           for i in range(nb):
               s = i * grpsize + ofs
               e = min((i + 1) * grpsize + ofs - 1, maxIdx)
               batches.append({'start':s, 'end':e})
               
           batch['batches'] = batches
   
           pages = []
           if pageZero and start == 1:
               # correct beginning
               idx = 0
           else:
               idx = start
               
           for r in range(rows):
               row = []
               for c in range(cols):
                   if idx < minIdx or idx > maxIdx:
                       page = {'idx':None}
                   else:
                       page = {'idx':idx}
                       
                   idx += 1
                   if pageFlowLtr:
                       row.append(page)
                   else:
                       row.insert(0, page) 
                   
               pages.append(row)
               
           if start > 1:
               batch['prevStart'] = max(start - grpsize, 1)
           else:
               batch['prevStart'] = None
               
           if start + grpsize < maxIdx:
               batch['nextStart'] = start + grpsize
           else:
               batch['nextStart'] = None
   
           batch['pages'] = pages
           return batch
           
       def getBatch(self, start=1, size=10, end=0, data=None, fullData=True):
           """returns dict with information for one screenfull of data."""
           batch = {}
           if end == 0:
               end = start + size                    
               
           nb = int(math.ceil(end / float(size)))
           # list of all batch start and end points
           batches = []
           for i in range(nb):
               s = i * size + 1
               e = min((i + 1) * size, end)
               batches.append({'start':s, 'end':e})
               
           batch['batches'] = batches
           # list of elements in this batch
           this = []
           j = 0
           for i in range(start, min(start+size, end)):
               if data:
                   if fullData:
                       d = data[i]
                   else:
                       d = data[j]
                       j += 1
               
               else:
                   d = i+1
                   
               this.append(d)
               
           batch['this'] = this
           if start > 1:
               batch['prevStart'] = max(start - size, 1)
           else:
               batch['prevStart'] = None
               
           if start + size < end:
               batch['nextStart'] = start + size
           else:
               batch['nextStart'] = None
           
           return batch
           
   
       security.declareProtected('View management screens','changeDocumentViewerForm')    
       changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
       
     def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):      def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None):
         """init document viewer"""          """init document viewer"""
         self.title=title          self.title=title
Line 842  class documentViewer(Folder): Line 897  class documentViewer(Folder):
         self.thumbrows = thumbrows          self.thumbrows = thumbrows
         self.thumbcols = thumbcols          self.thumbcols = thumbcols
         self.authgroups = [s.strip().lower() for s in authgroups.split(',')]          self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
           try:
               # assume MetaDataFolder instance is called metadata 
               self.metadataService = getattr(self, 'metadata')
           except Exception, e:
               logging.error("Unable to find MetaDataFolder 'metadata': "+str(e))
   
         if RESPONSE is not None:          if RESPONSE is not None:
             RESPONSE.redirect('manage_main')              RESPONSE.redirect('manage_main')
                   
Removed from v.1.175.2.7  
changed lines
  Added in v.1.175.2.27

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