File:  [Repository] / documentViewer / documentViewer.py
Revision 1.9: download - view: text, annotated - select for diffs - revision graph
Wed Apr 12 17:47:53 2006 UTC (18 years, 2 months ago) by casties
Branches: MAIN
CVS tags: HEAD
version 0.2.4
* minor improvements
* tries more than one time to read info from digilib

    1: from OFS.Folder import Folder
    2: from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate
    3: from Products.PageTemplates.PageTemplateFile import PageTemplateFile
    4: from AccessControl import ClassSecurityInfo
    5: from AccessControl import getSecurityManager
    6: from Globals import package_home
    7: 
    8: from Ft.Xml.Domlette import NonvalidatingReader
    9: from Ft.Xml.Domlette import PrettyPrint, Print
   10: from Ft.Xml import EMPTY_NAMESPACE
   11: 
   12: import Ft.Xml.XPath
   13: 
   14: import os.path
   15: import sys
   16: import cgi
   17: import urllib
   18: import zLOG
   19: 
   20: def getInt(number, default=0):
   21:     """returns always an int (0 in case of problems)"""
   22:     try:
   23:         return int(number)
   24:     except:
   25:         return default
   26: 
   27: def getTextFromNode(nodename):
   28:     if nodename is None:
   29:         return ""
   30:     nodelist=nodename.childNodes
   31:     rc = ""
   32:     for node in nodelist:
   33:         if node.nodeType == node.TEXT_NODE:
   34:            rc = rc + node.data
   35:     return rc
   36: 
   37:         
   38: def getParentDir(path):
   39:     """returns pathname shortened by one"""
   40:     return '/'.join(path.split('/')[0:-1])
   41:         
   42: 
   43: import socket
   44: 
   45: def urlopen(url,timeout=2):
   46:         """urlopen mit timeout"""
   47:         socket.setdefaulttimeout(timeout)
   48:         ret=urllib.urlopen(url)
   49:         socket.setdefaulttimeout(5)
   50:         return ret
   51: 
   52: 
   53: ##
   54: ## documentViewer class
   55: ##
   56: class documentViewer(Folder):
   57:     """document viewer"""
   58: 
   59:     meta_type="Document viewer"
   60:     
   61:     security=ClassSecurityInfo()
   62:     manage_options=Folder.manage_options+(
   63:         {'label':'main config','action':'changeDocumentViewerForm'},
   64:         )
   65: 
   66:     # templates and forms
   67:     viewer_main = PageTemplateFile('zpt/viewer_main', globals())
   68:     thumbs_main = PageTemplateFile('zpt/thumbs_main', globals())
   69:     image_main = PageTemplateFile('zpt/image_main', globals())
   70:     head_main = PageTemplateFile('zpt/head_main', globals())
   71:     docuviewer_css = PageTemplateFile('css/docuviewer.css', globals())
   72: 
   73:     security.declareProtected('View management screens','changeDocumentViewerForm')    
   74:     changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals())
   75: 
   76:     
   77:     def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"):
   78:         """init document viewer"""
   79:         self.id=id
   80:         self.title=title
   81:         self.imageViewerUrl=imageViewerUrl
   82:         if not digilibBaseUrl:
   83:             self.digilibBaseUrl = self.findDigilibUrl()
   84:         else:
   85:             self.digilibBaseUrl = digilibBaseUrl
   86:         self.thumbcols = thumbcols
   87:         self.thumbrows = thumbrows
   88:         # authgroups is list of authorized groups (delimited by ,)
   89:         self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
   90:         # add template folder so we can always use template.something
   91:         self.manage_addFolder('template')
   92: 
   93: 
   94:     security.declareProtected('View','index_html')
   95:     def index_html(self,mode,url,start=None,pn=1):
   96:         '''
   97:         view it
   98:         @param mode: defines which type of document is behind url
   99:         @param url: url which contains display information
  100:         '''
  101:         
  102:         zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn))
  103:         
  104:         if not hasattr(self, 'template'):
  105:             # create template folder if it doesn't exist
  106:             self.manage_addFolder('template')
  107:             
  108:         if not self.digilibBaseUrl:
  109:             self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary"
  110:             
  111:         docinfo = self.getDocinfo(mode=mode,url=url)
  112:         pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo)
  113:         pt = getattr(self.template, 'viewer_main')
  114:         return pt(docinfo=docinfo,pageinfo=pageinfo)
  115:   
  116:   
  117:     def getLink(self,param=None,val=None):
  118:         """link to documentviewer with parameter param set to val"""
  119:         params=self.REQUEST.form.copy()
  120:         if param is not None:
  121:             if val is None:
  122:                 if params.has_key(param):
  123:                     del params[param]
  124:             else:
  125:                 params[param] = str(val)
  126:                 
  127:         # quote values and assemble into query string
  128:         ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()])
  129:         url=self.REQUEST['URL1']+"?"+ps
  130:         return url
  131: 
  132:     
  133:     def getStyle(self, idx, selected, style=""):
  134:         """returns a string with the given style and append 'sel' if path == selected."""
  135:         #zLOG.LOG("documentViewer (getstyle)", zLOG.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style))
  136:         if idx == selected:
  137:             return style + 'sel'
  138:         else:
  139:             return style
  140:         
  141:         
  142:     def isAccessible(self, docinfo):
  143:         """returns if access to the resource is granted"""
  144:         access = docinfo.get('accessType', None)
  145:         if access is None:
  146:             # no information - no access 
  147:             #TODO: check
  148:             return True
  149:         elif access == 'free':
  150:             return True
  151:         elif access in self.authgroups:
  152:             # only local access -- only logged in users
  153:             user = getSecurityManager().getUser()
  154:             if user is not None:
  155:                 #print "user: ", user
  156:                 return (user.getUserName() != "Anonymous User")
  157:             else:
  158:                 return False
  159:         
  160:         zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "unknown access type %s"%access)
  161:         return False
  162:     
  163:                 
  164:     def getDirinfoFromDigilib(self,path,docinfo=None):
  165:         """gibt param von dlInfo aus"""
  166:         if docinfo is None:
  167:             docinfo = {}
  168:             
  169:         imageUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path
  170:     
  171:         zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(imageUrl))
  172:         
  173:         for cnt in (1,2,3):
  174:             try:
  175:                 dom = NonvalidatingReader.parseUri(imageUrl)
  176:                 break
  177:             except:
  178:                 zLOG.LOG("documentViewer (getdirinfofromdigilib)", zLOG.ERROR, "error reading %s (try %d)"%(imageUrl,cnt))
  179:         else:
  180:             raise IOError("Unable to get dirinfo from %s"%(imageUrl))
  181:         
  182:         params=dom.xpath("//dir/size")
  183:         zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%params)
  184:         
  185:         if params:
  186:             docinfo['numPages'] = int(getTextFromNode(params[0]))
  187:         else:
  188:             docinfo['numPages'] = 0
  189:                         
  190:         return docinfo
  191:     
  192:             
  193:     def getIndexMeta(self, url):
  194:         """returns dom of index.meta document at url"""
  195:         dom = None
  196:         if url.startswith("http://"):
  197:             # real URL
  198:             try:
  199:                 dom = NonvalidatingReader.parseUri(url)
  200:             except:
  201:                 zLOG.LOG("documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])
  202:                 raise IOError("Unable to get info from %s"%(url))
  203:         else:
  204:             # online path
  205:             server=self.digilibBaseUrl+"/servlet/Texter?fn="
  206:             metaUrl=server+url
  207:             if not metaUrl.endswith("index.meta"):
  208:                 metaUrl += "/index.meta"
  209:             try:
  210:                 dom = NonvalidatingReader.parseUri(metaUrl)
  211:             except:
  212:                 zLOG.LOG("documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2])
  213:                 raise IOError("Unable to get info from %s"%(url))
  214:                  
  215:         return dom
  216:                         
  217:         
  218:     def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None):
  219:         """gets authorization info from the index.meta file at path or given by dom"""
  220:         zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))
  221:         
  222:         access = None
  223:         
  224:         if docinfo is None:
  225:             docinfo = {}
  226:             
  227:         if dom is None:
  228:             dom = self.getIndexMeta(getParentDir(path))
  229:             
  230:         acctype = dom.xpath("//access-conditions/access/@type")
  231:         if acctype and (len(acctype)>0):
  232:             access=acctype[0].value
  233:             if access in ['group', 'institution']:
  234:                 access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower()
  235:             
  236:         docinfo['accessType'] = access
  237:         return docinfo
  238:     
  239:         
  240:     def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None):
  241:         """gets bibliographical info from the index.meta file at path or given by dom"""
  242:         zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path))
  243:         
  244:         if docinfo is None:
  245:             docinfo = {}
  246:             
  247:         if dom is None:
  248:             dom = self.getIndexMeta(getParentDir(path))
  249:             
  250:         metaData=self.metadata.main.meta.bib
  251:         bibtype=dom.xpath("//bib/@type")
  252:         if bibtype and (len(bibtype)>0):
  253:             bibtype=bibtype[0].value
  254:         else:
  255:             bibtype="generic"
  256:         bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC)
  257:         bibmap=metaData.generateMappingForType(bibtype)
  258:         #print "bibmap: ", bibmap, " for: ", bibtype
  259:         # if there is no mapping bibmap is empty (mapping sometimes has empty fields)
  260:         if len(bibmap) > 0 and len(bibmap['author'][0]) > 0:
  261:             docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0])
  262:             docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0])
  263:             docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0])
  264:         
  265:         return docinfo
  266: 
  267:         
  268:     def getDocinfoFromTextTool(self,url,dom=None,docinfo=None):
  269:        """parse texttool tag in index meta"""
  270:        zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url))
  271:        if docinfo is None:
  272:            docinfo = {}
  273:            
  274:        if dom is None:
  275:            dom = self.getIndexMeta(url)
  276:        
  277:        archiveNames=dom.xpath("//resource/name")
  278:        if archiveNames and (len(archiveNames)>0):
  279:            archiveName=getTextFromNode(archiveNames[0])
  280:        
  281:        archivePaths=dom.xpath("//resource/archive-path")
  282:        if archivePaths and (len(archivePaths)>0):
  283:            archivePath=getTextFromNode(archivePaths[0])
  284:            # clean up archive path
  285:            if archivePath[0] != '/':
  286:                archivePath = '/' + archivePath
  287:            if not archivePath.endswith(archiveName):
  288:                archivePath += "/" + archiveName
  289:        else:
  290:            archivePath=None
  291:        
  292:        imageDirs=dom.xpath("//texttool/image")
  293:        if imageDirs and (len(imageDirs)>0):
  294:            imageDir=getTextFromNode(imageDirs[0])
  295:        else:
  296:            imageDir=None
  297:            
  298:        if imageDir and archivePath:
  299:            #print "image: ", imageDir, " archivepath: ", archivePath
  300:            imageDir=os.path.join(archivePath,imageDir)
  301:            imageDir=imageDir.replace("/mpiwg/online",'')
  302:            docinfo=self.getDirinfoFromDigilib(imageDir,docinfo=docinfo)
  303:            docinfo['imagePath'] = imageDir
  304:            docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+imageDir
  305:            
  306:        viewerUrls=dom.xpath("//texttool/digiliburlprefix")
  307:        if viewerUrls and (len(viewerUrls)>0):
  308:            viewerUrl=getTextFromNode(viewerUrls[0])
  309:            docinfo['viewerURL'] = viewerUrl
  310:                   
  311:        textUrls=dom.xpath("//texttool/text")
  312:        if textUrls and (len(textUrls)>0):
  313:            textUrl=getTextFromNode(textUrls[0])
  314:            docinfo['textURL'] = textUrl
  315:                      
  316:        docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
  317:        docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom)
  318:        return docinfo
  319:    
  320: 
  321:     def getDocinfoFromImagePath(self,path,docinfo=None):
  322:         """path ist the path to the images it assumes that the index.meta file is one level higher."""
  323:         zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path))
  324:         if docinfo is None:
  325:             docinfo = {}
  326:         path=path.replace("/mpiwg/online","")
  327:         docinfo['imagePath'] = path
  328:         docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo)
  329:         imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path
  330:         docinfo['imageURL'] = imageUrl
  331:         
  332:         docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo)
  333:         docinfo = self.getAuthinfoFromIndexMeta(path,docinfo=docinfo)
  334:         return docinfo
  335:     
  336:     
  337:     def getDocinfo(self, mode, url):
  338:         """returns docinfo depending on mode"""
  339:         zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"mode: %s, url: %s"%(mode,url))
  340:         # look for cached docinfo in session
  341:         if self.REQUEST.SESSION.has_key('docinfo'):
  342:             docinfo = self.REQUEST.SESSION['docinfo']
  343:             # check if its still current
  344:             if docinfo is not None and docinfo.get('mode') == mode and docinfo.get('url') == url:
  345:                 zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo in session: %s"%docinfo)
  346:                 return docinfo
  347:         # new docinfo
  348:         docinfo = {'mode': mode, 'url': url}
  349:         if mode=="texttool": #index.meta with texttool information
  350:             docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo)
  351:         elif mode=="imagepath":
  352:             docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo)
  353:         else:
  354:             zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!")
  355:         zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo)
  356:         self.REQUEST.SESSION['docinfo'] = docinfo
  357:         return docinfo
  358:         
  359:         
  360:     def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None):
  361:         """returns pageinfo with the given parameters"""
  362:         pageinfo = {}
  363:         current = getInt(current)
  364:         pageinfo['current'] = current
  365:         rows = int(rows or self.thumbrows)
  366:         pageinfo['rows'] = rows
  367:         cols = int(cols or self.thumbcols)
  368:         pageinfo['cols'] = cols
  369:         grpsize = cols * rows
  370:         pageinfo['groupsize'] = grpsize
  371:         start = getInt(start, default=(int(current / grpsize) * grpsize +1))
  372:         pageinfo['start'] = start
  373:         pageinfo['end'] = start + grpsize
  374:         if docinfo is not None:
  375:             np = int(docinfo['numPages'])
  376:             pageinfo['end'] = min(pageinfo['end'], np)
  377:             pageinfo['numgroups'] = int(np / grpsize)
  378:             if np % grpsize > 0:
  379:                 pageinfo['numgroups'] += 1
  380:                 
  381:         return pageinfo
  382:                 
  383:     def text(self,mode,url,pn):
  384:         """give text"""
  385:         if mode=="texttool": #index.meta with texttool information
  386:             (viewerUrl,imagepath,textpath)=parseUrlTextTool(url)
  387:         
  388:         #print textpath
  389:         try:
  390:             dom = NonvalidatingReader.parseUri(textpath)
  391:         except:
  392:             return None
  393:     
  394:         list=[]
  395:         nodes=dom.xpath("//pb")
  396: 
  397:         node=nodes[int(pn)-1]
  398:         
  399:         p=node
  400:         
  401:         while p.tagName!="p":
  402:             p=p.parentNode
  403:         
  404:         
  405:         endNode=nodes[int(pn)]
  406:         
  407:         
  408:         e=endNode
  409:         
  410:         while e.tagName!="p":
  411:             e=e.parentNode
  412:         
  413:         
  414:         next=node.parentNode
  415:         
  416:         #sammle s
  417:         while next and (next!=endNode.parentNode):
  418:             list.append(next)    
  419:             next=next.nextSibling    
  420:         list.append(endNode.parentNode)
  421:         
  422:         if p==e:# beide im selben paragraphen
  423:             pass
  424: #    else:
  425: #            next=p
  426: #            while next!=e:
  427: #                print next,e
  428: #                list.append(next)
  429: #                next=next.nextSibling
  430: #            
  431: #        for x in list:
  432: #            PrettyPrint(x)
  433: #
  434: #        return list
  435: #
  436: 
  437:     def findDigilibUrl(self):
  438:         """try to get the digilib URL from zogilib"""
  439:         url = self.imageViewerUrl[:-1] + "/getScalerUrl"
  440:         try:
  441:             scaler = urlopen(url).read()
  442:             return scaler.replace("/servlet/Scaler?", "")
  443:         except:
  444:             return None
  445:     
  446:     def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None):
  447:         """init document viewer"""
  448:         self.title=title
  449:         self.imageViewerUrl=imageViewerUrl
  450:         self.digilibBaseUrl = digilibBaseUrl
  451:         self.thumbrows = thumbrows
  452:         self.thumbcols = thumbcols
  453:         self.authgroups = [s.strip().lower() for s in authgroups.split(',')]
  454:         if RESPONSE is not None:
  455:             RESPONSE.redirect('manage_main')
  456:     
  457:     
  458:         
  459:         
  460: #    security.declareProtected('View management screens','renameImageForm')
  461: 
  462: def manage_AddDocumentViewerForm(self):
  463:     """add the viewer form"""
  464:     pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self)
  465:     return pt()
  466:   
  467: def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None):
  468:     """add the viewer"""
  469:     newObj=documentViewer(id,imageViewerUrl,title)
  470:     self._setObject(id,newObj)
  471:     
  472:     if RESPONSE is not None:
  473:         RESPONSE.redirect('manage_main')
  474: 
  475: 
  476: ##
  477: ## DocumentViewerTemplate class
  478: ##
  479: class DocumentViewerTemplate(ZopePageTemplate):
  480:     """Template for document viewer"""
  481:     meta_type="DocumentViewer Template"
  482: 
  483: 
  484: def manage_addDocumentViewerTemplateForm(self):
  485:     """Form for adding"""
  486:     pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self)
  487:     return pt()
  488: 
  489: def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None,
  490:                            REQUEST=None, submit=None):
  491:     "Add a Page Template with optional file content."
  492: 
  493:     self._setObject(id, DocumentViewerTemplate(id))
  494:     ob = getattr(self, id)
  495:     ob.pt_edit(open(os.path.join(package_home(globals()),'zpt/viewer_main.zpt')).read(),None)
  496:     if title:
  497:         ob.pt_setTitle(title)
  498:     try:
  499:         u = self.DestinationURL()
  500:     except AttributeError:
  501:         u = REQUEST['URL1']
  502:         
  503:     u = "%s/%s" % (u, urllib.quote(id))
  504:     REQUEST.RESPONSE.redirect(u+'/manage_main')
  505:     return ''
  506: 
  507: 
  508:     

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