genericDigilib="http://nausikaa2.rz-berlin.mpg.de/digitallibrary/" from OFS.Folder import Folder from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate from Products.PageTemplates.PageTemplateFile import PageTemplateFile from AccessControl import ClassSecurityInfo from Globals import package_home from Ft.Xml.Domlette import NonvalidatingReader from Ft.Xml.Domlette import PrettyPrint, Print from Ft.Xml import EMPTY_NAMESPACE import Ft.Xml.XPath import os.path import cgi import urllib import zLOG def getTextFromNode(nodename): nodelist=nodename.childNodes rc = "" for node in nodelist: if node.nodeType == node.TEXT_NODE: rc = rc + node.data return rc import socket def urlopen(url): """urlopen mit timeout""" socket.setdefaulttimeout(2) ret=urllib.urlopen(url) socket.setdefaulttimeout(5) return ret def getParamFromDigilib(path,param): """gibt param von dlInfo aus""" imageUrl=genericDigilib+"/dirInfo-xml.jsp?mo=dir&fn="+path zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo (%s) from %s"%(param,imageUrl)) try: dom = NonvalidatingReader.parseUri(imageUrl) except: return None params=dom.xpath("//dir/%s"%param) zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:%s"%params) if params: return getTextFromNode(params[0]) ## ## documentViewer class ## class documentViewer(Folder): """document viewer""" meta_type="Document viewer" security=ClassSecurityInfo() manage_options=Folder.manage_options+( {'label':'main config','action':'changeDocumentViewerForm'}, ) # templates and forms viewer_main = PageTemplateFile('zpt/viewer_main', globals()) thumbs_main = PageTemplateFile('zpt/thumbs_main', globals()) image_main = PageTemplateFile('zpt/image_main', globals()) head_main = PageTemplateFile('zpt/head_main', globals()) docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) security.declareProtected('View management screens','changeDocumentViewerForm') changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None): """init document viewer""" self.id=id self.title=title self.imageViewerUrl=imageViewerUrl self.digilibBaseUrl = digilibBaseUrl if not self.digilibBaseUrl: self.digilibBaseUrl = self.findDigilibUrl() # add template folder so we can always use template.something self.manage_addFolder('template') security.declareProtected('View','index_html') def index_html(self,mode,url,start=0,pn=1): ''' view it @param mode: defines which type of document is behind url @param url: url which contains display information ''' zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) print "dlbaseurl:", self.digilibBaseUrl if not hasattr(self, 'template'): # create template folder if it doesn't exist print "no template folder -- creating" self.manage_addFolder('template') if not self.digilibBaseUrl: self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" print "dlbaseurl:", self.digilibBaseUrl docinfo = self.getDocinfo(mode=mode, url=url) pageinfo = self.getPageinfo(start=start,current=pn) pt = getattr(self.template, 'viewer_main') return pt(docinfo=docinfo,pageinfo=pageinfo) def imageLink(self,nr): """link hinter den images""" paramsTmp=cgi.parse_qs(self.REQUEST['QUERY_STRING']) params={} for x in paramsTmp.iteritems(): params[x[0]]=x[1][0] params['pn']=nr newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params) return newUrl def getStyle(self, idx, selected, style=""): """returns a string with the given style + 'sel' if path == selected.""" #zLOG.LOG("documentViewer (getstyle)", zLOG.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) if idx == selected: return style + 'sel' else: return style def thumbruler(self,cols,rows,start,maximum): """ruler for thumbs""" ret="" paramsTmp=cgi.parse_qs(self.REQUEST['QUERY_STRING']) params={} for x in paramsTmp.iteritems(): if not x[0]=="start": params[x[0]]=x[1][0] newUrlSelect=self.REQUEST['URL']+"?"+urllib.urlencode(params) if start>0: newStart=max(start-cols*rows,0) params['start']=newStart newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params) ret+="""prev"""%newUrl ret+="""" if startnext"""%newUrl return ret def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None): """gets bibliographical info from the index.meta file at url or given by dom""" zLOG.LOG("documentViewer (getbibinfofromindexmeta)", zLOG.INFO,"path: %s"%(path)) if docinfo is None: docinfo = {} metaData=self.metadata.main.meta.bib if dom is None: server="http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary/servlet/Texter?fn=" path="/".join(path.split("/")[0:-1]) metaUrl=server+path+"/index.meta" try: dom = NonvalidatingReader.parseUri(metaUrl) except: return docinfo type=dom.xpath("//bib/@type") if type and (len(type)>0): type=type[0].value else: type="generic" type=type.replace("-"," ")# wrong typesiin index meta "-" instead of " " hash=metaData.generateMappingForType(type) docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%hash['author'][0])[0]) docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%hash['title'][0])[0]) docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%hash['year'][0])[0]) return docinfo def getDocinfoFromTextTool(self,url,docinfo=None): """parse texttool tag in index meta""" zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.INFO,"url: %s"%(url)) if docinfo is None: docinfo = {} try: dom = NonvalidatingReader.parseUri(url) except: zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) return docinfo archivePaths=dom.xpath("//resource/archive-path") if archivePaths and (len(archivePaths)>0): archivePath=getTextFromNode(archivePaths[0]) else: archivePath=None images=dom.xpath("//texttool/image") if images and (len(images)>0): image=getTextFromNode(images[0]) else: image=None if image and archivePath: image=os.path.join(archivePath,image) image=image.replace("/mpiwg/online",'') pt=getParamFromDigilib(image,'size') docinfo['imagePath'] = image docinfo['numberOfPages'] = pt viewerUrls=dom.xpath("//texttool/digiliburlprefix") if viewerUrls and (len(viewerUrls)>0): viewerUrl=getTextFromNode(viewerUrls[0]) docinfo['imageURL'] = viewerURL textUrls=dom.xpath("//texttool/text") if textUrls and (len(textUrls)>0): textUrl=getTextFromNode(textUrls[0]) docinfo['textURL'] = textURL docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) return docinfo def getDocinfoFromImagePath(self,path,docinfo=None): """path ist the path to the images it assumes that the index.meta file is one level higher.""" zLOG.LOG("documentViewer (getdocinfofromimagepath)", zLOG.INFO,"path: %s"%(path)) if docinfo is None: docinfo = {} docinfo['imagePath'] = path path=path.replace("/mpiwg/online","") pt=getParamFromDigilib(path,'size') docinfo['numberOfPages'] = pt imageUrl=genericDigilib+"/servlet/Scaler?fn=%s"%path docinfo['imageURL'] = imageUrl docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo) return docinfo def getDocinfo(self, mode, url): """returns docinfo depending on mode""" zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"mode: %s, url: %s"%(mode,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: zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo in session: %s"%docinfo) return docinfo # new docinfo docinfo = {'mode': mode, 'url': url} if mode=="texttool": #index.meta with texttool information docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) elif mode=="imagepath": docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) else: zLOG.LOG("documentViewer (getdocinfo)", zLOG.ERROR,"unknown mode!") zLOG.LOG("documentViewer (getdocinfo)", zLOG.INFO,"docinfo: %s"%docinfo) self.REQUEST.SESSION['docinfo'] = docinfo return docinfo def getPageinfo(self, start, current): """returns pageinfo with the given parameters""" pageinfo = {} pageinfo['start'] = start pageinfo['current'] = current return pageinfo def text(self,mode,url,pn): """give text""" if mode=="texttool": #index.meta with texttool information (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) print textpath try: dom = NonvalidatingReader.parseUri(textpath) except: return None list=[] nodes=dom.xpath("//pb") node=nodes[int(pn)-1] p=node while p.tagName!="p": p=p.parentNode endNode=nodes[int(pn)] e=endNode while e.tagName!="p": e=e.parentNode next=node.parentNode #sammle s while next and (next!=endNode.parentNode): list.append(next) next=next.nextSibling list.append(endNode.parentNode) if p==e:# beide im selben paragraphen pass # else: # next=p # while next!=e: # print next,e # list.append(next) # next=next.nextSibling # # for x in list: # PrettyPrint(x) # # return list # def image(self,mode,url,pn): """give image out""" if mode=="texttool": #index.meta with texttool information (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) if not viewerUrl: viewerUrl=self.imageViewerUrl url=viewerUrl+"pn=%s&fn=%s"%(pn,imagepath[0]) ret="""