Diff for /documentViewer/documentViewer.py between versions 1.78 and 1.112

version 1.78, 2010/08/12 10:08:24 version 1.112, 2010/10/08 13:49:44
Line 16  import logging Line 16  import logging
 import math  import math
 import urlparse   import urlparse 
 import cStringIO  import cStringIO
   import re
   
 def logger(txt,method,txt2):  def logger(txt,method,txt2):
     """logging"""      """logging"""
Line 177  class documentViewer(Folder): Line 178  class documentViewer(Folder):
         """get numpages"""          """get numpages"""
         return self.template.fulltextclient.getNumPages(docinfo)          return self.template.fulltextclient.getNumPages(docinfo)
   
       def getNumTextPages(self, docinfo):
           """get numpages text"""
           return self.template.fulltextclient.getNumTextPages(docinfo)
      
     def getTranslate(self, **args):      def getTranslate(self, **args):
         """get translate"""          """get translate"""
         return self.template.fulltextclient.getTranslate(**args)          return self.template.fulltextclient.getTranslate(**args)
Line 226  class documentViewer(Folder): Line 231  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, query=None, querySearch=None, characterNormalization=None):      def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""):
         '''          '''
         view it          view it
         @param mode: defines how to access the document behind url           @param mode: defines how to access the document behind url 
Line 390  class documentViewer(Folder): Line 395  class documentViewer(Folder):
                                                   
         return docinfo          return docinfo
           
       def getIndexMetaPath(self,url):
           """gib nur den Pfad zurueck"""
           regexp = re.compile(r".*(experimental|permanent)/(.*)")
           regpath = regexp.match(url)
           if (regpath==None):
               return ""
           logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2))            
           return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2))
        
       
       
       def getIndexMetaUrl(self,url):
           """returns utr  of index.meta document at url"""
                           
     def getIndexMeta(self, url):  
         """returns dom of index.meta document at url"""  
         dom = None  
         metaUrl = None          metaUrl = None
         if url.startswith("http://"):          if url.startswith("http://"):
             # real URL              # real URL
Line 405  class documentViewer(Folder): Line 420  class documentViewer(Folder):
             if not metaUrl.endswith("index.meta"):              if not metaUrl.endswith("index.meta"):
                 metaUrl += "/index.meta"                  metaUrl += "/index.meta"
                                   
         logging.debug("(getIndexMeta): METAURL: %s"%metaUrl)          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)          txt=getHttpData(metaUrl)
         if txt is None:          if txt is None:
             raise IOError("Unable to read index meta from %s"%(url))              raise IOError("Unable to read index meta from %s"%(url))
Line 445  class documentViewer(Folder): Line 467  class documentViewer(Folder):
         if dom is None:          if dom is None:
             for x in range(cut):              for x in range(cut):
                 path=getParentDir(path)                  path=getParentDir(path)
             dom = self.getIndexMeta(path)              dom = self.getDomFromIndexMeta(path)
                 
         acctype = dom.xpath("//access-conditions/access/@type")          acctype = dom.xpath("//access-conditions/access/@type")
         if acctype and (len(acctype)>0):          if acctype and (len(acctype)>0):
Line 467  class documentViewer(Folder): Line 489  class documentViewer(Folder):
         if dom is None:          if dom is None:
             for x in range(cut):              for x in range(cut):
                 path=getParentDir(path)                  path=getParentDir(path)
             dom = self.getIndexMeta(path)              dom = self.getDomFromIndexMeta(path)
           
           docinfo['indexMetaPath']=self.getIndexMetaPath(path);
                   
         logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))          logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path))
         # put in all raw bib fields as dict "bib"          # put in all raw bib fields as dict "bib"
Line 489  class documentViewer(Folder): Line 513  class documentViewer(Folder):
         bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)          bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
         docinfo['bib_type'] = bibtype          docinfo['bib_type'] = bibtype
         bibmap=metaData.generateMappingForType(bibtype)          bibmap=metaData.generateMappingForType(bibtype)
           logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap))
           logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype))
         # if there is no mapping bibmap is empty (mapping sometimes has empty fields)          # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
         if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:          if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
             try:              try:
Line 505  class documentViewer(Folder): Line 531  class documentViewer(Folder):
                 docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])                  docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0])
             except:              except:
                 docinfo['lang']=''                  docinfo['lang']=''
               try:
                   docinfo['name']=getTextFromNode(dom.xpath("//%s"%bibmap['name'][0])[0])
               except: pass
   
         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['indexMetaPath']=self.getIndexMetaPath(path);
           
           #result= dom.xpath("//result/resultPage")
           #docinfo['numPages']=int(getTextFromNode(result[0]))
           
           if len(name) > 0:
               try:
                   result =dom.xpath("//name")
                   docinfo['name']=getTextFromNode(result[0])
                   logging.debug("documentViewer docinfo[name] %s"%docinfo[name])
               except: pass  
                   #logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype)
           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"""
         logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))          logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url))
Line 517  class documentViewer(Folder): Line 570  class documentViewer(Folder):
         if docinfo.get('lang', None) is None:          if docinfo.get('lang', None) is None:
             docinfo['lang'] = '' # default keine Sprache gesetzt              docinfo['lang'] = '' # default keine Sprache gesetzt
         if dom is None:          if dom is None:
             dom = self.getIndexMeta(url)              dom = self.getDomFromIndexMeta(url)
                   
         archivePath = None          archivePath = None
         archiveName = None          archiveName = None
Line 591  class documentViewer(Folder): Line 644  class documentViewer(Folder):
             docinfo['textURLPath'] = textUrl              docinfo['textURLPath'] = textUrl
             if not docinfo['imagePath']:              if not docinfo['imagePath']:
                 # text-only, no page images                  # text-only, no page images
                 docinfo = self.getNumPages(docinfo)                  docinfo = self.getNumTextPages(docinfo)
                     
         presentationUrls = dom.xpath("//texttool/presentation")          presentationUrls = dom.xpath("//texttool/presentation")
         docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get info von bib tag          docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom)   # get info von bib tag
           #docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom)
                   
         if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen           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               # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten
Line 628  class documentViewer(Folder): Line 682  class documentViewer(Folder):
             docinfo['year']=getTextFromNode(dom.xpath("//date")[0])              docinfo['year']=getTextFromNode(dom.xpath("//date")[0])
         except:          except:
             pass              pass
           try:
               docinfo['name']=getTextFromNode(dom.xpath("//name")[0])
           except:
               pass
         return docinfo          return docinfo
           
     def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):      def getDocinfoFromImagePath(self,path,docinfo=None,cut=0):
Line 678  class documentViewer(Folder): Line 736  class documentViewer(Folder):
         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=None):      def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""):
         """returns pageinfo with the given parameters"""          """returns pageinfo with the given parameters"""
         pageinfo = {}          pageinfo = {}
         current = getInt(current)          current = getInt(current)
Line 701  class documentViewer(Folder): Line 759  class documentViewer(Folder):
                 pageinfo['numgroups'] += 1                          pageinfo['numgroups'] += 1        
         pageinfo['viewMode'] = viewMode          pageinfo['viewMode'] = viewMode
         pageinfo['tocMode'] = tocMode          pageinfo['tocMode'] = tocMode
         pageinfo['characterNormalization'] =characterNormalization          #pageinfo['characterNormalization'] =characterNormalization
           pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ')
         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')

Removed from v.1.78  
changed lines
  Added in v.1.112


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