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

Diff for /documentViewer/Attic/extraFunction.py between versions 1.1.2.1 and 1.1.2.3

version 1.1.2.1, 2010/06/14 10:50:06 version 1.1.2.3, 2010/06/16 16:38:17
Line 21  import urllib Line 21  import urllib
 import logging  import logging
 import math  import math
 import documentViewer  import documentViewer
   import urllib2
   import urllib
 import urlparse   import urlparse 
 from types import *  from types import *
   
Line 53  class extraFunction(Folder): Line 54  class extraFunction(Folder):
         self.id=id          self.id=id
         self.title=title          self.title=title
           
       def getHttpData(self, url, data=None, num_tries=3, timeout=40):
           """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)
           else:
               # we assume its a dict
               url = "%s?%s"%(url,urllib.urlencode(data))
           
           response = None
           errmsg = None
           for cnt in range(num_tries):
               try:
                   logging.debug("getHttpData(%s) url=%s"%(cnt+1,url))
                   if sys.version_info < (2, 6):
                       # set timeout on socket -- ugly :-(
                       import socket
                       socket.setdefaulttimeout(timeout)
                       response = urllib2.urlopen(url)
                   else:
                       response = urllib2.urlopen(url,timeout=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 getSearch(self, pn=1, pageinfo=None,  docinfo=None, query=None, queryType=None, lemma=None):      def getSearch(self, pn=1, pageinfo=None,  docinfo=None, query=None, queryType=None, lemma=None):
         """get search list"""          """get search list"""
         docpath = docinfo['textURLPath']           docpath = docinfo['textURLPath'] 
Line 69  class extraFunction(Folder): Line 115  class extraFunction(Folder):
         tocMode = pageinfo['tocMode']          tocMode = pageinfo['tocMode']
         tocPN = pageinfo['tocPN']          tocPN = pageinfo['tocPN']
         selfurl = self.absolute_url()          selfurl = self.absolute_url()
         page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery) ,outputUnicode=False)                          
         pagexml = page.replace('?document=%s'%str(docpath),'?url=%s'%url)          data = self.getHttpData("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery))
           #page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery) ,outputUnicode=False)                
           #data = page.read()
           #page.close()
           
           pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
         pagedom = Parse(pagexml)          pagedom = Parse(pagexml)
         if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):             if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):   
             pagedivs = pagedom.xpath("//div[@class='queryResultPage']")              pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
Line 132  class extraFunction(Folder): Line 183  class extraFunction(Folder):
     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'
         text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))          text = self.getHttpData("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
           #text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
         docinfo['numPages'] = text.count("<pb ")          docinfo['numPages'] = text.count("<pb ")
         return docinfo          return docinfo
                 
Line 153  class extraFunction(Folder): Line 205  class extraFunction(Folder):
         textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn)          textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn)
         if highlightQuery is not None:          if highlightQuery is not None:
             textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn)                         textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn)           
         pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)          
           pagexml = self.getHttpData("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/page-fragment.xql",textParam)
           """pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)"""
           
         pagedom = Parse(pagexml)          pagedom = Parse(pagexml)
         # plain text mode          # plain text mode
         if mode == "text":          if mode == "text":
Line 216  class extraFunction(Folder): Line 271  class extraFunction(Folder):
   
     def getTranslate(self, query=None, language=None):      def getTranslate(self, query=None, language=None):
         """translate into another languages"""          """translate into another languages"""
         pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))          data = self.getHttpData("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
         return pagexml          #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query)))
           #data = pagexml.read()
           #pagexml.close()
           return data
           
     def getLemma(self, lemma=None, language=None):      def getLemma(self, lemma=None, language=None):
         """simular words lemma """          """simular words lemma """
         pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))          data = self.getHttpData("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
         return pagexml          #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma)))
           #data = pagexml.read()
           #pagexml.close()
           return data
           
     def getLemmaNew(self, query=None, language=None):      def getLemmaNew(self, query=None, language=None):
         """simular words lemma """          """simular words lemma """
         pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))          data = self.getHttpData("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
         return pagexml          #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
           #data = pagexml.read()
           #pagexml.close()
           return data
   
     def getQuery (self,  docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):      def getQuery (self,  docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
          """number of"""           """number of"""
Line 238  class extraFunction(Folder): Line 302  class extraFunction(Folder):
          queryType =pageinfo['queryType']           queryType =pageinfo['queryType']
          tocSearch = 0           tocSearch = 0
          tocDiv = None           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)           
            pagexml = self.getHttpData("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn))
            #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)           pagedom = Parse(pagexml)
          numdivs = pagedom.xpath("//div[@class='queryResultHits']")           numdivs = pagedom.xpath("//div[@class='queryResultHits']")
          tocSearch = int(getTextFromNode(numdivs[0]))           tocSearch = int(getTextFromNode(numdivs[0]))
Line 266  class extraFunction(Folder): Line 332  class extraFunction(Folder):
         # number of entries in toc          # number of entries in toc
         tocSize = 0          tocSize = 0
         tocDiv = None          tocDiv = None
         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.getHttpData("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
           #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
         # post-processing downloaded xml          # post-processing downloaded xml
         pagedom = Parse(pagexml)          pagedom = Parse(pagexml)
         # get number of entries          # get number of entries
Line 292  class extraFunction(Folder): Line 360  class extraFunction(Folder):
         viewMode=  pageinfo['viewMode']          viewMode=  pageinfo['viewMode']
         tocMode = pageinfo['tocMode']          tocMode = pageinfo['tocMode']
         tocPN = pageinfo['tocPN']              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)          
         page = pagexml.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))          data = self.getHttpData("http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))  
           #data = pagexml.read()
           #pagexml.close()
   
           page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
         text = page.replace('mode=image','mode=texttool')          text = page.replace('mode=image','mode=texttool')
         return text          return text
           
Removed from v.1.1.2.1  
changed lines
  Added in v.1.1.2.3

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