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

Diff for /documentViewer/documentViewer.py between versions 1.44 and 1.47

version 1.44, 2010/04/08 11:04:51 version 1.47, 2010/04/27 12:58:31
Line 10  from Ft.Xml.Domlette import Nonvalidatin Line 10  from Ft.Xml.Domlette import Nonvalidatin
 from Ft.Xml.Domlette import PrettyPrint, Print  from Ft.Xml.Domlette import PrettyPrint, Print
 from Ft.Xml import EMPTY_NAMESPACE, Parse  from Ft.Xml import EMPTY_NAMESPACE, Parse
   
   from xml.dom.minidom import parse, parseString
   
   
   
 import Ft.Xml.XPath  import Ft.Xml.XPath
 import cStringIO  import cStringIO
Line 102  class documentViewer(Folder): Line 105  class documentViewer(Folder):
     changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())      changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
   
           
     def __init__(self,id,imageScalerUrl=None,textServerName=None,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
Line 163  class documentViewer(Folder): Line 166  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",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None):
         '''          '''
         view it          view it
         @param mode: defines how to access the document 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 auto (text,images or auto)          @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)          @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, search)
           @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph)
         '''          '''
                   
         logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))          logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
Line 183  class documentViewer(Folder): Line 187  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,viewMode=viewMode,tocMode=tocMode)          
           
         if tocMode != "thumbs":          if tocMode != "thumbs":
             # get table of contents              # get table of contents
             docinfo = self.getToc(mode=tocMode, docinfo=docinfo)              docinfo = self.getToc(mode=tocMode, docinfo=docinfo)
   
           pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode)
           
         if viewMode=="auto": # automodus gewaehlt          if viewMode=="auto": # automodus gewaehlt
             if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert              if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert
                 viewMode="text"                  viewMode="text"
Line 649  class documentViewer(Folder): Line 656  class documentViewer(Folder):
                                   
         pageinfo['viewMode'] = viewMode          pageinfo['viewMode'] = viewMode
         pageinfo['tocMode'] = tocMode          pageinfo['tocMode'] = tocMode
         pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '10')          pageinfo['query'] = self.REQUEST.get('query',' ')
           pageinfo['queryType'] = self.REQUEST.get('queryType',' ')
           pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext')
           pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30')
           pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '20')
         pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')          pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1')
           #if 'tocSize_%s'%tocMode in docinfo:
               # cached toc
             # pageinfo['tocPN'] = min (int (docinfo['tocSize_%s'%tocMode])/int(pageinfo['tocPageSize']),int(pageinfo['tocPN']))
                  
           pageinfo['searchPN'] =self.REQUEST.get('searchPN','1')
           pageinfo['sn'] =self.REQUEST.get('sn','1')
   
         return pageinfo          return pageinfo
                                   
       def getSearch(self, pn=1, pageinfo=None,  docinfo=None, query=None, queryType=None):
           """get search list"""
           docpath = docinfo['textURLPath'] 
           pagesize = pageinfo['queryPageSize']
           pn = pageinfo['searchPN']
           sn = pageinfo['sn']
           query =pageinfo['query']
           queryType =pageinfo['queryType']
           viewMode=  pageinfo['viewMode']
           tocMode = pageinfo['tocMode']
           tocPN = pageinfo['tocPN']
           pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn) ,outputUnicode=False)           
           pagedom = Parse(pagexml)
           pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
           
           selfurl = self.absolute_url()
           
           page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s&query=%s&queryType=%s'%(selfurl, viewMode, tocMode, tocPN, query, queryType))
           text =page.replace('mode=text','mode=texttool')
           href = text.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
           lemma= href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
           #logging.debug("documentViewer (gettoc) lemma: %s"%(lemma))
           
           return lemma
   
   
           #if len(pagedivs) > 0:
           #    pagenode = pagedom[0]
           #    return serializeNode(pagenode)
           #else:
           #    return "xaxa"
   
     def getNumPages(self,docinfo=None):      def getNumPages(self,docinfo=None):
         """get list of pages from fulltext and put in docinfo"""          """get list of pages from fulltext and put in docinfo"""
         xquery = '//pb'          xquery = '//pb'
Line 664  class documentViewer(Folder): Line 711  class documentViewer(Folder):
         docinfo['numPages'] = text.count("<pb ")          docinfo['numPages'] = text.count("<pb ")
         return docinfo          return docinfo
                 
     def getTextPage(self, mode="text", pn=1, docinfo=None):      def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None,):
         """returns single page from fulltext"""          """returns single page from fulltext"""
         docpath = docinfo['textURLPath']          docpath = docinfo['textURLPath']
         if mode == "text_dict":          if mode == "text_dict":
Line 672  class documentViewer(Folder): Line 719  class documentViewer(Folder):
         else:          else:
             textmode = mode              textmode = mode
                           
           #selfurl = self.absolute_url()  
           #viewMode=  pageinfo['viewMode']
           #tocMode = pageinfo['tocMode']
           #tocPN = pageinfo['tocPN']
     
         pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False)          pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn), outputUnicode=False)
           #######
           #page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl, viewMode, tocMode, tocPN))
           #text =page.replace('mode=text','mode=texttool')
           #######
         # post-processing downloaded xml          # post-processing downloaded xml
         pagedom = Parse(pagexml)          pagedom = Parse(pagexml)
         # plain text mode          # plain text mode
         if mode == "text":          if mode == "text":
             # first div contains text              # first div contains text
             pagedivs = pagedom.xpath("/div")              pagedivs = pagedom.xpath("/div")
               #queryResultPage
             if len(pagedivs) > 0:              if len(pagedivs) > 0:
                 pagenode = pagedivs[0]                  pagenode = pagedivs[0]
                 return serializeNode(pagenode)                  return serializeNode(pagenode)
Line 700  class documentViewer(Folder): Line 757  class documentViewer(Folder):
                             # is pollux link                              # is pollux link
                             selfurl = self.absolute_url()                              selfurl = self.absolute_url()
                             # change href                              # change href
                             hrefNode.nodeValue = href.replace('lt/lex.xql','%s/head_main_voc'%selfurl)                              hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl)
                             # add target                              # add target
                             l.setAttributeNS(None, 'target', '_blank')                              l.setAttributeNS(None, 'target', '_blank')
                               
                           if href.startswith('lt/lemma.xql'):    
                               selfurl = self.absolute_url()
                               hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
                               l.setAttributeNS(None, 'target', '_blank')
                 return serializeNode(pagenode)                  return serializeNode(pagenode)
                   
         return "no text here"          return "no text here"
   
       def getTranslate(self, query=None, language=None):
           """translate into another languages"""
           pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","query=%s&language=%s"%(query,language),outputUnicode=False)
           return pagexml
       
       def getLemma(self, lemma=None, language=None):
           """lemma"""
           pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False)
           return pagexml
   
       def getQuery (self,  docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
            """number of"""
            docpath = docinfo['textURLPath'] 
            pagesize = pageinfo['queryPageSize']
            pn = pageinfo['searchPN']
            query =pageinfo['query']
            queryType =pageinfo['queryType']
   
            tocSearch = 0
            tocDiv = None
            pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False)
            
            pagedom = Parse(pagexml)
            numdivs = pagedom.xpath("//div[@class='queryResultHits']")
            tocSearch = int(getTextFromNode(numdivs[0]))
            tc=int((tocSearch/20)+1)
            logging.debug("documentViewer (gettoc) tc: %s"%(tc))
            return tc
   
     def getToc(self, mode="text", docinfo=None):      def getToc(self, mode="text", docinfo=None):
         """loads table of contents and stores in docinfo"""          """loads table of contents and stores in docinfo"""
         logging.debug("documentViewer (gettoc) mode: %s"%(mode))          logging.debug("documentViewer (gettoc) mode: %s"%(mode))
         if 'tocSize_%s'%mode in docinfo:          if 'tocSize_%s'%mode in docinfo:
             # cached toc              # cached toc
             return docinfo              return docinfo
           
         docpath = docinfo['textURLPath']          docpath = docinfo['textURLPath']
         # we need to set a result set size          # we need to set a result set size
         pagesize = 1000          pagesize = 1000
Line 741  class documentViewer(Folder): Line 831  class documentViewer(Folder):
         #docinfo['tocDiv_%s'%mode] = tocDiv          #docinfo['tocDiv_%s'%mode] = tocDiv
         return docinfo          return docinfo
           
     def getTocPage(self, mode="toc", pn=1, pageinfo=None, docinfo=None):      def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None):
         """returns single page from the table of contents"""          """returns single page from the table of contents"""
         # TODO: this should use the cached TOC          # TODO: this should use the cached TOC
         if mode == "text":          if mode == "text":
Line 751  class documentViewer(Folder): Line 841  class documentViewer(Folder):
         docpath = docinfo['textURLPath']          docpath = docinfo['textURLPath']
         pagesize = pageinfo['tocPageSize']          pagesize = pageinfo['tocPageSize']
         pn = pageinfo['tocPN']          pn = pageinfo['tocPN']
           
           selfurl = self.absolute_url()  
           viewMode=  pageinfo['viewMode']
           tocMode = pageinfo['tocMode']
           tocPN = pageinfo['tocPN']
       
         pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)          pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
           page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl, viewMode, tocMode, tocPN))
           text = page.replace('mode=image','mode=texttool')
           return text
         # post-processing downloaded xml          # post-processing downloaded xml
         pagedom = Parse(pagexml)          #pagedom = Parse(text)
         # div contains text          # div contains text
         pagedivs = pagedom.xpath("//div[@class='queryResultPage']")          #pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
         if len(pagedivs) > 0:          #if len(pagedivs) > 0:
             pagenode = pagedivs[0]          #    pagenode = pagedivs[0]
             return serializeNode(pagenode)          #    return serializeNode(pagenode)
         else:          #else:
             return "No TOC!"          #    return "No TOC!"
   
           
     def changeDocumentViewer(self,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.digilibBaseUrl = digilibBaseUrl          self.digilibBaseUrl = digilibBaseUrl
Removed from v.1.44  
changed lines
  Added in v.1.47

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