--- ECHO_content/ECHO_collection.py 2004/06/05 10:04:33 1.97 +++ ECHO_content/ECHO_collection.py 2004/08/17 15:24:38 1.164 @@ -14,6 +14,7 @@ import re import os import OFS.Image from types import * +from OFS.Cache import Cacheable from OFS.Image import Image from Globals import DTMLFile from OFS.Folder import Folder @@ -29,7 +30,8 @@ from Products.PageTemplates.ZopePageTemp from Globals import Persistent, package_home from Acquisition import Implicit from ECHO_helpers import displayTypes - +import urllib +import time try: from psycopg import libpq @@ -46,9 +48,165 @@ import xml.dom.minidom from ECHO_graphicalOverview import javaHandler,javaScriptMain import ECHO_helpers +def donatus(txt2): + import xmlrpclib + + server = xmlrpclib.ServerProxy("http://archimedes.fas.harvard.edu/cgi-bin/donatus-rpc") + + txt=txt2.encode('utf-8') + bin=xmlrpclib.Binary(txt) + + + + ret=server.donatus.analyze(bin) + + + return ret['morphData'].data + + +def donatusVariant2Lemma(morphData): + """creates hash variant -> morphdata""" + ret={} + dom=xml.dom.minidom.parseString(morphData) + lemmas=dom.getElementsByTagName('lemma') + for lemma in lemmas: + variants=lemma.getElementsByTagName('variant') + for variant in variants: + atr=variant.getAttribute('form') + if ret.has_key(atr): + ret[atr].append=lemma.getAttribute('form') + else: + ret[atr]=[lemma.getAttribute('form')] + + return ret + +#regexp for extracting elements from xml +patternTXT=r"<\s*txt.*?>(.*?)" +regexpTXT = re.compile(patternTXT, re.IGNORECASE + re.DOTALL) +patternPage=r"<\s*page.*?>(.*?)" +regexpPage = re.compile(patternPage, re.IGNORECASE + re.DOTALL) + + +def ECHO_rerenderLinksMD(self,obj=None,types=['title','label']): + """Rerender all Links""" + ret="" + + if not obj: + obj = self + + entries=obj.ZopeFind(obj,obj_metatypes=['ECHO_resource'],search_sub=1) + + for entry in entries: + if entry[1].meta_type == 'ECHO_resource': + try: + entry[1].ECHO_getResourceMD(template="no") + if "title" in types: + entry[1].generate_title() + if "label" in types: + entry[1].generate_label() + ret+="OK:"+entry[0]+"-- "+entry[1].getTitle().decode('utf-8')+"-- "+entry[1].getTitle().decode('utf-8')+"
" + except: + ret+="Error:"+entry[0]+"
" + + + + + return ""+ret+"Rerenderd all links to resources in: "+self.title+"" + +def reloadMetaDataFromStorage(self,RESPONSE=None): + """copy metadata from the storage to ECHO""" + ret="" + resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource'],search_sub=1) + + for resource in resources: + x=str(resource[1].copyIndex_meta2echo_resource())+"
" + ret+=x + #print x + + + if RESPONSE is not None: + #RESPONSE.redirect('./manage_main') + return ""+ret+"" + + return ret + +def getRDFDescription(self,linkURL,urn=None,nameDef=None,typeName=None): + """rdf""" + + ret="" + about="""""" + name="""%s""" + link="""%s""" + clickable="""%s""" + #link="""""" + type="""%s""" + #xlink="""""" + if not urn: + #urn="urn:"+re.sub('/',':',self.absolute_url()) + urn=self.absolute_url() + about2=about%urn + if not nameDef: + if hasattr(self,'label') and not (self.label==""): + name2=name%self.label + elif not self.title=="": + name2=name%self.title + else: + name2=name%self.getId() + + name2=re.sub('&','&',name2) + else: + name2=name%nameDef + + linkURL=re.sub('http:','',linkURL) + linkURL2=re.sub('&','&',linkURL) + link2=link%(("http:"+linkURL2),("http:"+urllib.quote(linkURL))) + clickable2=clickable%"true" + + if not typeName: + type2=type%self.meta_type + else: + type2=type%typeName + + #ret=about2+"\n"+name2+"\n"+link2+"\n"+type2+"\n"+clickable2+"\n" + ret=about2+"\n"+name2+"\n"+type2+"\n"+clickable2+"\n" + return ret + +def getCopyrightsFromForm(self,argv): + medias={} + partners={} + copyrights={} + + copyrightsFinal=[] + for arg in argv.keys(): + + if arg[0:5]=='media': + nm=int(arg[5:]) + medias[nm]=argv[arg] + elif arg[0:5]=='partn': + nm=int(arg[5:]) + partners[nm]=argv[arg] + elif arg[0:5]=='copyr': + nm=int(arg[5:]) + copyrights[nm]=argv[arg] + + + + copyrightsList=[(medias[nm],partners[nm],copyrights[nm]) for nm in medias.keys()] + for copyright in copyrightsList: + + if copyright[2]=='institution0000': + copyrightsFinal.append((copyright[0],copyright[1],self.getPartnerCopyright(copyright[1],''))) + else: + if not copyright[0]=='': + copyrightsFinal.append(copyright) + + + return copyrightsFinal + #List of different types for the graphical linking viewer viewClassificationListMaster=['view point','area'] + def checkDiffs(self,metadict): """check differences""" @@ -151,22 +309,52 @@ class BrowserCheck: self.isIEMac = self.isIE and self.isMac -def writeMetadata(url,metadict): + + +def writeMetadata(url,metadict,project=None,startpage=None,xslt=None,thumbtemplate=None,topbar=None,digiLibTemplate=None,xmlfrag=None,digiliburlprefix=None): """Einlesen der Metadaten und und erstellen des geaenderten XML file""" - try: - geturl="" - for line in urllib.urlopen(url).readlines(): - geturl=geturl+line - - - except: - return (None,"Cannot open: "+url) + def updateTextToolNode(tag,value): + #print dom,tag,value + metanode=dom.getElementsByTagName('texttool')[0] + try: + nodeOld=metanode.getElementsByTagName(tag) + except: + nodeOld=None + + if nodeOld: + metanode.removeChild(nodeOld[0]).unlink() - try: + node=dom.createElement(tag) + nodetext=dom.createTextNode(value) + node.appendChild(nodetext) + metanode.appendChild(node) + + if xmlfrag: + geturl=""" + + + + + + """ dom=xml.dom.minidom.parseString(geturl) - except: - return (None,"Cannot parse: "+url+"
"+geturl) + else: + try: + geturl="" + for line in ECHO_helpers.urlopen(url).readlines(): + geturl=geturl+line + + + except: + return (None,"Cannot open: "+url) + + try: + dom=xml.dom.minidom.parseString(geturl) + except: + return (None,"Cannot parse: "+url+"
"+geturl) + + metanodes=dom.getElementsByTagName('bib') @@ -202,6 +390,28 @@ def writeMetadata(url,metadict): metanodeneu.appendChild(metanodetext) metanode.appendChild(metanodeneu) + + + + + if project: + updateTextToolNode('project',project) + + if startpage: + updateTextToolNode('startpage',startpage) + + if topbar: + updateTextToolNode('toptemplate',topbar) + + if thumbtemplate: + updateTextToolNode('thumbtemplate',thumbtemplate) + + if xslt: + updateTextToolNode('xslt',xslt) + + + if digiliburlprefix: + updateTextToolNode('digiliburlprefix',digiliburlprefix) return dom.toxml().encode('utf-8') @@ -214,7 +424,7 @@ def readMetadata(url): metadict={} try: geturl="" - for line in urllib.urlopen(url).readlines(): + for line in ECHO_helpers.urlopen(url).readlines(): geturl=geturl+line @@ -283,52 +493,61 @@ def setECHO_collectionInformation(self,t self.coords=coords[0:] +class ECHO_copyright(Folder): + """Copyright informationen""" + meta_type="ECHO_copyright" + + + + def __init__(self,id,title,copyrights): + """init""" + self.title=title + self.id=id + self.copyrights=copyrights[0:] -class scientificClassification(SimpleItem,Persistent,Implicit): - """outdated will be deleeted in the next versions: subclass""" - security=ClassSecurityInfo() - - def __init__(self,context,science,practice): - self.context=context - self.science=science - self.practice=practice - self.id="scientific_Classification" - - security.declarePublic('get_context') - def get_context(self): - return self.context - - security.declarePublic('get_science') - def get_science(self): - return self.science - - security.declarePublic('get_practice') - def get_practice(self): - return self.practice - - -class scientificInformation(Folder,Persistent,Implicit): - """outdated will be deleted in the next versions: subclass scientificInformation""" - security=ClassSecurityInfo() - - - - def __init__(self,source_type,period): + def getCopyrights(self): + """return coyprights""" + return self.copyrights + + manage_options = Folder.manage_options+( + {'label':'Main Config','action':'ECHO_copyright_configForm'}, + ) - self.id="scientific_Information" - self.source_type=source_type - self.period=period - + def ECHO_copyright_configForm(self): + """change form""" + pt=PageTemplateFile('Products/ECHO_content/zpt/ChangeECHO_copyright').__of__(self) + pt.content_type="text/html" + return pt() + def ECHO_copyright_config(self,title,RESPONSE=None): + """change""" + self.title=title + self.copyrights=[] + self.copyrights=getCopyrightsFromForm(self,self.REQUEST.form)[0:] - security.declarePublic('get_source_type') - def get_source_type(self): - return self.source_type - - security.declarePublic('get_period') - def get_period(self): - return self.period + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + + +def manage_addECHO_copyrightForm(self): + """Form for adding""" + pt=PageTemplateFile('Products/ECHO_content/zpt/AddECHO_copyright.zpt').__of__(self) + return pt() +def manage_addECHO_copyright(self, id,title,RESPONSE=None): + """add the copyright""" + + meta_type="ECHO_copyright" + + #first generate copyrights as list of tripels (mediaType,partner,copyrightType) + + + + self._setObject(id, ECHO_copyright(id, title,getCopyrightsFromForm(self,self.REQUEST.form))) + + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + class ECHO_layoutTemplate(ZopePageTemplate): """Create a layout Template for different purposes""" @@ -397,21 +616,499 @@ def manage_addECHO_layoutTemplate(self, REQUEST.RESPONSE.redirect(u+'/manage_main') return '' +class ECHO_fullText(ZopePageTemplate): + """echo fulltext in xml""" + + meta_type="ECHO_fullText" + + def donatusVariant2Lemma(self,nr='1'): + """analyze by donatus""" + return donatusVariant2Lemma(donatus(self.lemmatize(nr))) + + def tagLex(self,nr="1"): + """generate Links""" + global retLex + global toggle + + toggle=0 + retLex="" + + lemmatized=self.lemmatize(nr)[0:] + #print "ho",repr(lemmatized) + variants=donatusVariant2Lemma(donatus(lemmatized)) + + def createTag(name,attrs): + global toggle + + if name=="w": + toggle=1 + return "" + else: + tag="<" + tag+=name + for attr in attrs.keys(): + tag+=""" %s="%s" """%(attr,attrs[attr]) + tag+=">" + return tag + + def createData(data): + global toggle + astring="""%s """ + if toggle: # tag war ein w + toggle=0 + if variants.has_key(data): + return astring%(variants[data][0],data) + else: + return astring%(data,data) + + + + # 3 handler functions + def start_element(name, attrs): + global retLex + print name + retLex+=createTag(name,attrs) + def end_element(name): + global retLex + if not name=="w": + retLex+=""%(name.encode('utf-8')) + + + def char_data(data): + global retLex + if data: + try: + retLex+=createData(data) + except: + """no""" + + p = xml.parsers.expat.ParserCreate() + + p.StartElementHandler = start_element + p.EndElementHandler = end_element + p.CharacterDataHandler = char_data + + p.Parse(lemmatized.encode('utf-8'),1) + print repr(lemmatized.encode('utf-8')) + + return retLex + + + def lemmatize(self,nr='1',lang="de"): + """lemmatize""" + global ret + ret="" + + def createTag(name,attrs): + tag="<" + tag+=name + for attr in attrs.keys(): + tag+=""" %s="%s" """%(attr,attrs[attr]) + tag+=">" + return tag + + def insertW(str): + splitted=str.split() + wordlist=["%s"%split for split in splitted] + return string.join(wordlist,'\n') + + # 3 handler functions + def start_element(name, attrs): + global ret + ret+=createTag(name,attrs) + def end_element(name): + global ret + ret+=""%(name.encode('utf-8')) + + def char_data(data): + global ret + ret+=insertW(data) + + p = xml.parsers.expat.ParserCreate() + + p.StartElementHandler = start_element + p.EndElementHandler = end_element + p.CharacterDataHandler = char_data + + p.Parse(self.getPage(nr), 1) + txt=""" +
%s
+ """ + ret=txt%(lang,ret) + + return ret + + def getPage(self,nr='1'): + """get page n""" + dom=xml.dom.minidom.parseString(self()) + pages=dom.getElementsByTagName('page') + + return pages[int(nr)-1].toxml('utf-8') + +# Product registration and Add support +manage_addECHO_fullTextForm = PageTemplateFile( + 'zpt/AddECHO_fullText.zpt', globals()) + +from urllib import quote + +def manage_addECHO_fullText(self, id, title=None, text=None, + REQUEST=None, submit=None): + "Add a Page Template with optional file content." + + id = str(id) + if REQUEST is None: + self._setObject(id, ECHO_fullText(id, text)) + ob = getattr(self, id) + if title: + ob.pt_setTitle(title) + return ob + else: + file = REQUEST.form.get('file') + headers = getattr(file, 'headers', None) + if headers is None or not file.filename: + zpt = ECHO_fullText(id) + else: + zpt = ECHO_fullText(id, file, headers.get('content_type')) + + self._setObject(id, zpt) + + try: + u = self.DestinationURL() + except AttributeError: + u = REQUEST['URL1'] + + if submit == " Add and Edit ": + u = "%s/%s" % (u, quote(id)) + REQUEST.RESPONSE.redirect(u+'/manage_main') + return '' + class ECHO_resource(Folder,Persistent): """ECHO Ressource""" + security=ClassSecurityInfo() meta_type='ECHO_resource' viewClassificationList=viewClassificationListMaster getSubCols = ECHO_helpers.getSubCols + + security.declareProtected('View','index_html') + + def showRDF(self): + """showrdf""" + self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') + ret="""\n\n""" + ret+=self.getRDF(urn="echo:collectionroot")+"\n" + + ret+="""""" + return ret + + def getRDF(self,urn=None): + """rdf""" + ret=getRDFDescription(self,self.link,urn=urn) + return ret+self.createSubElementRDF(urn=urn) + + + def createSubElementRDF(self,urn=None): + """rdf list""" + if not urn: + urn=self.absolute_url() + ret="" + + rettemp="""\n"""%urn + flag=0 + + li="""\n""" + if not ('' in self.getFullTextXML(noredirect='Yes')): + nurn=self.absolute_url()+'/getFullTextXML' + rettemp+=li%nurn + flag=1 + if not ('' in self.getImageView(noredirect='Yes')): + nurn=self.absolute_url()+'/getImageView' + rettemp+=li%nurn + flag=1 + + + if not ('' in self.showMetaDataXML()): + nurn=self.absolute_url()+'/showMetaDataXML' + rettemp+=li%nurn + flag=1 + + rettemp+="" + + if flag==1: + ret+=rettemp + + if not ('' in self.getFullTextXML(noredirect='Yes')): + nurn=self.absolute_url()+'/getFullTextXML' + ret+=getRDFDescription(self,self.absolute_url()+'/getFullTextXML',urn=nurn,nameDef="Fulltext",typeName="ECHO_fulltext") + + if not ('' in self.getImageView(noredirect='Yes')): + nurn=self.absolute_url()+'/getImageView' + ret+=getRDFDescription(self,self.absolute_url()+'/getImageView',urn=nurn,nameDef="Image View",typeName="ECHO_imageview") + + if not ('' in self.showMetaDataXML()): + nurn=self.absolute_url()+'/showMetaDataXML' + ret+=getRDFDescription(self,self.absolute_url()+'/showMetaDataXML',urn=nurn,nameDef="Metadata",typeName="ECHO_metaData") + + return ret + + def getAccessRightSelectorHTML(self,outlook="select"): + """htmlselector""" + values=['free','mpiwg'] + + if outlook=="select": + ret="""" + + else: + ret="" + for value in values: + + if value==self.getAccessRightMD(): + ret+="""%s"""%(self.getId(),value,value) + else: + ret+="""%s"""%(self.getId(),value,value) + return ret + + + + def getAccessRightMD(self): + """set accessright""" + url=self.metalink + + try: + geturl="" + for line in ECHO_helpers.urlopen(url).readlines(): + geturl=geturl+line + + + except: + return (None,"Cannot open: "+url) + + try: + dom=xml.dom.minidom.parseString(geturl) + root=dom.getElementsByTagName('resource')[0] + except: + return (None,"Cannot parse: "+url+"
"+geturl) + + internal=dom.getElementsByTagName('internal') + if internal: + institution=dom.getElementsByTagName('institution') + return getText(institution[0].childNodes) + + free=dom.getElementsByTagName('free') + if free: + return "free" + + return "free" #default free + + def changeAccessRightMD(self,accessright,RESPONSE=None): + """change the rights""" + + params="accessright=%s"%accessright + + + #print ECHO_helpers.urlopen(self.absolute_url()+'/setAccessRightXML'+'?'+params).read() + + + ECHO_helpers.urlopen('http://xserve02.mpiwg-berlin.mpg.de:18880/echo_nav/storage/downloadExternalXML?index_meta_url=%s&xml_url=%s'%(self.metalink,self.absolute_url()+'/setAccessRightXML'+urllib.quote('?'+params))).read() + + + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + + + def setAccessRightXML(self,accessright): + """set accessright""" + url=self.metalink + + try: + geturl="" + for line in ECHO_helpers.urlopen(url).readlines(): + geturl=geturl+line + + + except: + return (None,"Cannot open: "+url) + + try: + dom=xml.dom.minidom.parseString(geturl) + root=dom.getElementsByTagName('resource')[0] + except: + return (None,"Cannot parse: "+url+"
"+geturl) + + metanodes=dom.getElementsByTagName('access-conditions') + + if not metanodes: + nodenew=dom.createElement('access-conditions') + root.appendChild(nodenew) + metanode=nodenew + else: + metanode=metanodes[0] + + accesses=metanode.getElementsByTagName('access') + + if not accesses: + nodenew2=dom.createElement('access') + metanode.appendChild(nodenew2) + metanode2=nodenew2 + else: + metanode2=accesses[0] + + internal=metanode.getElementsByTagName('internal') + + if internal: + metanode2.removeChild(internal[0]).unlink() + + free=metanode.getElementsByTagName('free') + + if free: + metanode2.removeChild(internal[0]).unlink() + + + if accessright=='free': + nodenew3=dom.createElement('free') + metanode2.appendChild(nodenew3) + elif accessright=='mpiwg': + nodenew3=dom.createElement('internal') + nodenew4=dom.createElement('institution') + metanodetext=dom.createTextNode('mpiwg') + nodenew4.appendChild(metanodetext) + nodenew3.appendChild(nodenew4) + metanode2.appendChild(nodenew3) + + return dom.toxml().encode('utf-8') + + def setStartPageForm(self): + """Form for changing the startpage""" + + + pt=PageTemplateFile('Products/ECHO_content/zpt/ChangeECHO_resourceStartPage.zpt').__of__(self) + pt.content_type="text/html" + return pt() + + + def setStartPage(self,startpage=None,RESPONSE=None): + """set start page, if no startpage defined use the generic one of the resource""" + + if (not (type(startpage)==StringType)) and ("__generic" in startpage): # checke ob generic in der liste + startpage=self.absolute_url()+"/startpage_html" + + if (not startpage) or (startpage=="__generic"): + startpage=self.absolute_url()+"/startpage_html" + + + params="startpage=%s"%startpage + + ECHO_helpers.urlopen('http://xserve02.mpiwg-berlin.mpg.de:18880/echo_nav/storage/downloadExternalXML?index_meta_url=%s&xml_url=%s'%(self.metalink,self.absolute_url()+'/newMetaXML'+urllib.quote('?'+params))).read() + + + path=self.metalink + + path=re.sub(self.REQUEST['SERVER_URL'],'',path) + path=re.sub('http://'+self.REQUEST['HTTP_HOST'],'',path) + + path=re.sub('http://foxridge.mpiwg-berlin.mpg.de:8080','',path) # falls foxridge als server + path=re.sub('http://foxridge.mpiwg-berlin.mpg.de','',path) # falls foxridge als server + path=re.sub('http://foxridge.rz-berlin.mpg.de:8080','',path) # falls foxridge als server + path=re.sub('http://content.mpiwg-berlin.mpg.de','',path) # falls content als server + path=re.sub('http://foxridge.rz-berlin.mpg.de','',path) # falls foxridge als server + path=re.sub('http://vision.rz-berlin.mpg.de','',path) # falls vision als server + path=re.sub('/index.meta','',path) + + + ECHO_helpers.urlopen("http://nausikaa2.rz-berlin.mpg.de:86/cgi-bin/toc/admin/reg.cgi?path=%s"%path).readlines() + + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + + def changeViewerTemplateSetForm(self): + """change the viewer template set""" + pt=PageTemplateFile('Products/ECHO_content/zpt/changeResourceViewerTemplateSet').__of__(self) + return pt() + + + def getTextToolsField(self,name,default=''): + """Lese Textoolsfelder aus index.meta im path aus""" + + try: + dom=xml.dom.minidom.parse(self.metalink) + node=dom.getElementsByTagName('texttool')[0] #getNode + subnode=node.getElementsByTagName(name)[0] + + # bei text wird nur der Folder gebraucht + if name=="text": + splitted=getText(subnode.childNodes).split("/") + return splitted[len(splitted)-2] + else: + return getText(subnode.childNodes) + except: + return default + + + def changeViewerTemplateSet(self,project,xslt,thumbtemplate,topbar,digiLibTemplate,digiliburlprefix,RESPONSE=None): + """changeit""" + + paramList=['project','startpage','xslt','thumbtemplate','topbar','digiLibTemplate','digiliburlprefix'] + + + #writeMetadata(self.metalink,self.metaDataHash,project,None,xslt,thumbtemplate,topbar,digiLibTemplate) + + params="project=%s&xslt=%s&thumbtemplate=%s&topbar=%s&digiLibTemplate=%s&digiliburlprefix=%s"%(project,xslt,thumbtemplate,topbar,digiLibTemplate,digiliburlprefix) + + + ECHO_helpers.urlopen('http://echo.mpiwg-berlin.mpg.de/echo_nav/storage/downloadExternalXML?index_meta_url=%s&xml_url=%s'%(self.metalink,self.absolute_url()+'/newMetaXML'+urllib.quote('?'+params))).read() + + #print self.absolute_url()+'/newMetaXML'+urllib.quote'?'+params) + # hack Pfad auf die Dokumente + path=self.metalink + + + + path=re.sub('/index.meta','',path) + + path=re.sub(self.REQUEST['SERVER_URL'],'',path) + path=re.sub('http://'+self.REQUEST['HTTP_HOST'],'',path) + + path=re.sub('http://foxridge.mpiwg-berlin.mpg.de:8080','',path) # falls foxridge als server + path=re.sub('http://foxridge.mpiwg-berlin.mpg.de:8080','',path) # falls foxridge als server + path=re.sub('http://foxridge.mpiwg-berlin.mpg.de','',path) # falls foxridge als server + + path=re.sub('http://foxridge.rz-berlin.mpg.de:8080','',path) # falls foxridge als server + path=re.sub('http://foxridge.rz-berlin.mpg.de','',path) # falls foxridge als server + path=re.sub('http://content.mpiwg-berlin.mpg.de','',path) # falls content als server + + path=re.sub('http://vision.rz-berlin.mpg.de','',path) # falls vision als server + + return ECHO_helpers.urlopen("http://nausikaa2.rz-berlin.mpg.de:86/cgi-bin/toc/admin/reg.cgi?path=%s"%path).readlines() + + + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + + def getTitle(self): """title""" - return self.title.encode('utf-8') - + try: + return self.title.encode('utf-8','ignore') + except: + self.title=self.title.decode('iso-8859-1','ignore')[0:] #correnct conding error + return self.title.encode('utf-8','ignore') + def getLabel(self): """title""" - return self.label.encode('utf-8') - + try: + return self.label.encode('utf-8','ignore') + except: + self.label=self.label.decode('iso-8859-1','ignore')[0:] #correnct conding error + return self.label.encode('utf-8','ignore') + def content_html(self): """template fuer content""" return content_html(self,'resource') @@ -425,13 +1122,14 @@ class ECHO_resource(Folder,Persistent): def getFullTextXML(self,noredirect=None): """getFullTextXML; gives the FullText as an XML Document, and if somthing goes wrong.""" try: - fh=urllib.urlopen(self.metalink) + fh=ECHO_helpers.urlopen(self.metalink) dom=xml.dom.minidom.parse(fh) texttools=dom.getElementsByTagName('texttool') text=texttools[0].getElementsByTagName('text') texturl=getText(text[0].childNodes) - self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') + if not noredirect: + self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') self.REQUEST.RESPONSE.redirect(texturl) else: return texturl @@ -443,17 +1141,80 @@ class ECHO_resource(Folder,Persistent): else: return "no fulltext available" - def getCopyright(self): - """gib link auf copyright notiz aus""" - if hasattr(self,'copyrightType') and hasattr(self.copyrightTypes,self.copyrightType): - obj=getattr(self.copyrightTypes,self.copyrightType) - else: - obj=getattr(self.copyrightTypes,'generic') - label=obj.label - link="copyrightTypes/"+obj.getId()+'/copyright.html' + def getImageView(self,noredirect=None): + """getImages; give Imageviewr and if somthing goes wrong.""" + try: + fh=ECHO_helpers.urlopen(self.metalink) + dom=xml.dom.minidom.parse(fh) + texttools=dom.getElementsByTagName('texttool') + text=texttools[0].getElementsByTagName('image') + imagetemp=getText(text[0].childNodes) + + text=dom.getElementsByTagName('archive-path') + archivepath=getText(text[0].childNodes) + archivepath=re.sub('/mpiwg/online/','',archivepath) + imageurl="http://echo.mpiwg-berlin.mpg.de/zogilib?fn="+archivepath+"/"+imagetemp + if not noredirect: + self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') + self.REQUEST.RESPONSE.redirect(imageurl) + else: + return imageurl + except: + + if not noredirect: + self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') + self.REQUEST.RESPONSE.write("no fulltext available") + else: + return "no images available" + + + def getCopyrightsHTML(self): + """gib (link auf copyright link, mediatyp, institution, copyrightType, label von copyrightType) aus""" - return """%s"""%(link,label) + if hasattr(self,'copyrightModel'): + obj=self.copyrightModel + + else: + return "ERROR" + ret=[] + + for copyright in obj.getCopyrights(): #copyright - media / partner / copyrightID + + + try: + if hasattr(self.copyrightTypes,copyright[2]): + copyrightTypeObj=getattr(self.copyrightTypes,copyright[2]) + link="copyrightTypes/"+copyright[2]+'/copyright.html' + else: + copyrightTypeObj=getattr(obj,copyright[2]) + link="copyrightModel/"+copyright[2]+'/copyright.html' + + label=copyrightTypeObj.label + url=getattr(copyrightTypeObj, 'url', '') + + if url!='': + ret.append((url,copyright[0],copyright[1],copyright[2],label)) + else: + if hasattr(copyrightTypeObj, 'copyright.html'): + ret.append(("""%s?partner=%s"""%(link,copyright[1]),copyright[0],copyright[1],copyright[2],label)) + else: + ret.append(('empty',copyright[0],copyright[1],copyright[2],label)) + except: + """nothing""" + + return ret + + def getInstitutionsHTML(self): + """gibt Liste der fšrdernden Institutionen aus""" + + if hasattr(self,'support'): + obj=self.support + ret=obj.getSupporter() + return ret + else: + return '' + def getCredits(self): """Ausgabe der credits""" @@ -489,7 +1250,7 @@ class ECHO_resource(Folder,Persistent): def getCoords(self): - """gibt coordinaten als String zurück und löscht zugleich einträge die keine Koordinaten sind, letzteres zur korrektur der Eingabe der alten version""" + """gibt coordinaten als String zurück und löscht zugleich einträge die keine Koordinaten sind, letzteres zur korrektur der Eingabe der alten version""" retList=[] if hasattr(self,'coords'): for x in self.coords: @@ -556,7 +1317,8 @@ class ECHO_resource(Folder,Persistent): self.contentType=self.bib_type for data in self.metadata: data_neu=re.sub('-','_',data) - self.metaDataHash[data_neu]=getattr(self,data) + self.meta + DataHash[data_neu]=getattr(self,data)[0:] pt=PageTemplateFile('Products/ECHO_content/zpt/ChangeECHO_resource_metadata.zpt').__of__(self) @@ -566,7 +1328,7 @@ class ECHO_resource(Folder,Persistent): def changeECHO_resource_main(self,metalink,link,title,label,description,contentType,renderingType,weight,resourceID,RESPONSE=None): - """Änderung der Properties""" + """Änderung der Properties""" self.resourceID=resourceID self.title=title self.label=label @@ -584,7 +1346,7 @@ class ECHO_resource(Folder,Persistent): def changeECHO_resource_coords(self,coords,viewClassification,RESPONSE=None): - """Änderung der Properties - coords""" + """Änderung der Properties - coords""" if type(coords)==StringType: coords=[coords] @@ -601,7 +1363,7 @@ class ECHO_resource(Folder,Persistent): RESPONSE.redirect('manage_main') def changeECHO_resource_credits(self,credits,responsible,copyrightType,RESPONSE=None): - """Änderung der Properties""" + """Änderung der Properties""" self.credits=credits self.responsible=responsible self.copyrightType=copyrightType @@ -614,7 +1376,7 @@ class ECHO_resource(Folder,Persistent): """change metadata""" tags=self.findTagsFromMapping(self.contentType) for field in tags[1]: - self.metaDataHash[self.getFieldTag(tags,field)]=self.REQUEST.form[self.getFieldTag(tags,field)] + self.metaDataHash[self.getFieldTag(tags,field)]=self.REQUEST.form[self.getFieldTag(tags,field)][0:] @@ -632,8 +1394,9 @@ class ECHO_resource(Folder,Persistent): except: """nothing""" - return urllib.urlopen('http://xserve02.mpiwg-berlin.mpg.de:18880/echo_nav/storage/downloadExternalXML?index_meta_url=%s&xml_url=%s'%(self.metalink,self.absolute_url()+'/newMetaXML')).read() - + ECHO_helpers.urlopen('http://xserve02.mpiwg-berlin.mpg.de:18880/echo_nav/storage/downloadExternalXML?index_meta_url=%s&xml_url=%s'%(self.metalink,self.absolute_url()+'/newMetaXML')).read() + + if RESPONSE is not None: RESPONSE.redirect('manage_main') @@ -641,19 +1404,34 @@ class ECHO_resource(Folder,Persistent): def getMDValue(self,fieldName): return self.metaDataHash.get(fieldName,'!!NOT USED HERE in Type: %s'%self.contentType) - def newMetaXML(self): + def newMetaXML(self,project=None,startpage=None,xslt=None,thumbtemplate=None,topbar=None,digiLibTemplate=None,digiliburlprefix=None): """new index.meta""" self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') - return writeMetadata(self.metalink,self.OSAS_meta) + if not hasattr(self,'metaDataHash'): + + self.copyIndex_meta2echo_resource() + try: + return writeMetadata(self.metalink,self.OSAS_meta,project,startpage,xslt,thumbtemplate,topbar,digiLibTemplate,digiliburlprefix=digiliburlprefix) + except: + return writeMetadata(self.metalink,self.metaDataHash,project,startpage,xslt,thumbtemplate,topbar,digiLibTemplate,digiliburlprefix=digiliburlprefix) - def getMetaDataXML(self): + def showMetaDataXML(self,project=None,startpage=None,xslt=None,thumbtemplate=None,topbar=None,digiLibTemplate=None): + """schreibe md""" + + try: + + return writeMetadata(self.metalink,self.metaDataHash,project,startpage,xslt,thumbtemplate,topbar,digiLibTemplate,xmlfrag="yes") + except: + return " no metadata stored" + + def getMetaDataXML(self,project=None,startpage=None,xslt=None,thumbtemplate=None,topbar=None,digiLibTemplate=None): """prints out metadata as stored in the echo environment, format is the index.meta format""" self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') return writeMetadata(self.metalink,self.metaDataHash) def changeECHO_resource(self,metalink,link,title,label,description,contentType,responsible,weight,viewClassification="",coords=None,credits=None,RESPONSE=None): - """Änderung der Properties""" + """Änderung der Properties""" try: coordsnew=[ string.split(x,",") for x in coords] @@ -672,11 +1450,13 @@ class ECHO_resource(Folder,Persistent): manage_options = Folder.manage_options+( {'label':'Main Config','action':'ECHO_resource_config_main'}, - {'label':'Change Partners & Copyright','action':'ECHO_resource_config_credits'}, {'label':'Change Metadata','action':'ECHO_resource_config_metadata'}, {'label':'Change Coords','action':'ECHO_resource_config_coords'}, {'label':'Add coords','action':'ECHO_graphicEntry'}, {'label':'Sync Metadata','action':'ECHO_getResourceMD'}, + {'label':'Change TemplateSets and Image Viewer','action':'changeViewerTemplateSetForm'}, + {'label':'set/change startpage','action':'setStartPageForm'}, + {'label':'Copy MD for indexing and search','action':'copySearchFields'}, ) def getOverview(self): @@ -765,6 +1545,12 @@ class ECHO_resource(Folder,Persistent): self.metaDataHash[field]=value[0:] + def copySearchFields(self): + """copys metadatafields to the object""" + fields=['author','title','year'] + for field in fields: + setattr(self,'MD_'+field,self.getFieldValue(field)) + def findLabelsFromMapping(self,referenceType): """gib hash mit label -> generic zurueck""" @@ -819,8 +1605,9 @@ class ECHO_resource(Folder,Persistent): bibdata={} retdata={} fieldlist=self.standardMD.fieldList - + fields=[] for referenceTypeF in temp: + #print referenceType if referenceTypeF[1].title.lower() == referenceType.lower(): try: @@ -836,15 +1623,20 @@ class ECHO_resource(Folder,Persistent): return retdata,fieldlist,temp,fields - + security.declarePublic('copyIndex_meta2echo_resource') # has to be change, presentlyset because of OSAS koordination def copyIndex_meta2echo_resource(self,RESPONSE=None): """copy MD von Index_meta to the echo_resource""" (metadict, error)=readMetadata(self.metalink) + + self.metaDataHash={} if not error=="": #Fehler beim Auslesen des Metafiles - return "ERROR:",error + + return "ERROR:",error,self.absolute_url() + + self.contentType=metadict['bib_type'][0:] fields=self.findTagsFromMapping(self.contentType) #fields=self.findLabelsFromMapping(self.contentType) @@ -859,11 +1651,12 @@ class ECHO_resource(Folder,Persistent): if RESPONSE: return RESPONSE.redirect('manage_main') - def ECHO_getResourceMD(self,template="yes"): + def ECHO_getResourceMD(self,template="yes",back=None): """Einlesen der Metadaten und Anlegen dieser Metadaten als Informationen zur Resource""" (metadict, error)=readMetadata(self.metalink) - + if back: + self.REQUEST.SESSION['back']=back if not error=="": #Fehler beim Auslesen des Metafiles return "ERROR:",error @@ -910,7 +1703,7 @@ class ECHO_resource(Folder,Persistent): if sp: return sp[1]() - #prüfen ob irgendwo ein template + #prüfen ob irgendwo ein template if hasattr(self,'startpage_index_template'): return self.startpage_index_template() @@ -928,21 +1721,27 @@ class ECHO_resource(Folder,Persistent): return sp[0][1]() - + security.declarePublic('generate_label') # has to be change, presentlyset because of OSAS koordination + def generate_label(self): """Erzeugt_standard_Label aus Template""" - pt=getattr(self,"label_template_"+self.bib_type) + pt=getattr(self,"label_template_"+self.contentType.lower()) + self.label=pt()[0:] return pt() + security.declarePublic('generate_title') # has to be change, presentlyset because of OSAS koordination + def generate_title(self,RESPONSE=None): """Erzeugt_standard_Label aus Template""" - pt=getattr(self,"label_template_"+self.contentType) + pt=getattr(self,"label_template_"+self.contentType.lower()) - self.title=pt() + self.title=pt()[0:] return pt() +Globals.InitializeClass(ECHO_resource) + def manage_addECHO_resourceForm(self): """Form for adding a ressource""" pt=PageTemplateFile('Products/ECHO_content/zpt/AddECHO_resourceForm.zpt').__of__(self) @@ -968,11 +1767,19 @@ class ECHO_externalLink(Folder): def getTitle(self): """title""" - return self.title.encode('utf-8') - + try: + return self.title.encode('utf-8','ignore') + except: + self.title=self.title.decode('iso-8859-1','ignore')[0:] #correnct conding error + return self.title.encode('utf-8','ignore') + def getLabel(self): """title""" - return self.label.encode('utf-8') + try: + return self.label.encode('utf-8','ignore') + except: + self.label=self.label.decode('iso-8859-1','ignore')[0:] #correnct conding error + return self.label.encode('utf-8','ignore') def content_html(self): """template fuer content""" @@ -1010,7 +1817,7 @@ class ECHO_externalLink(Folder): def changeECHO_externalLink(self,link,title,label,description,contentType,responsible,weight,coords=None,credits=None,RESPONSE=None): - """Änderung der Properties""" + """Änderung der Properties""" try: coordsnew=[ string.split(x,",") for x in coords] except: @@ -1028,12 +1835,6 @@ class ECHO_externalLink(Folder): {'label':'Main Config','action':'ECHO_externalLink_config'}, ) - def getCredits(self): - """Ausgabe der credits""" - if self.credits: - return self.credits - else: - return [] def index_html(self): """standard page""" @@ -1087,7 +1888,7 @@ def manage_addECHO_link(self,id,title,la RESPONSE.redirect('manage_main') -class ECHO_collection(Folder, Persistent, Implicit): +class ECHO_collection(Folder, Persistent, Implicit, Cacheable): """ECHO Collection""" security=ClassSecurityInfo() @@ -1095,6 +1896,306 @@ class ECHO_collection(Folder, Persistent viewClassificationList=viewClassificationListMaster displayTypes=displayTypes + path="/mpiwg/online/permanent/shipbuilding" + + def getRDF(self,urn=None): + """rdf of the collection""" + + contents=self.ZopeFind(self,obj_metatypes=['ECHO_group','ECHO_resource','ECHO_collection']) + + ret=getRDFDescription(self,self.absolute_url(),urn=urn) + + if not urn: + urn=self.absolute_url() + + li="""\n""" + + + for content in contents: + ret+=content[1].getRDF()+"\n" + + ret+="""\n"""%urn + for content in contents: + nurn=content[1].absolute_url() + ret+=li%nurn + return ret+"" + + + def showRDF(self): + """showrdf""" + self.REQUEST.RESPONSE.setHeader('Content-Type','text/xml') + ret="""\n\n""" + ret+=self.getRDF(urn="echo:collectionroot")+"\n" + + ret+="""""" + + return ret + + + + def changeLabels(self): + """change form""" + pt=PageTemplateFile('Products/ECHO_content/zpt/changeLabelsForm').__of__(self) + pt.content_type="text/html" + return pt() + + def changeTitles(self): + """change form""" + pt=PageTemplateFile('Products/ECHO_content/zpt/changeTitleForm').__of__(self) + pt.content_type="text/html" + return pt() + + def changeWeights(self): + """change form""" + pt=PageTemplateFile('Products/ECHO_content/zpt/changeWeightForm').__of__(self) + pt.content_type="text/html" + return pt() + + def changeMetaDataLinks(self): + """change form""" + pt=PageTemplateFile('Products/ECHO_content/zpt/changeMetaDataLinkForm').__of__(self) + pt.content_type="text/html" + return pt() + def changeAccessRightsCollection(self): + """change""" + ret="" + argv=self.REQUEST.form + + resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource']) + for resource in resources: + + try: + ret+=resource[1].getId()+" "+argv[resource[1].getId()]+"
" + resource[1].changeAccessRightMD(argv[resource[1].getId()]) + except: + """not""" + return ret + + def changeMetaDataLinkInCollection(self): + """change all lables of a collection""" + ret="" + argv=self.REQUEST.form + + resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource']) + for resource in resources: + + try: + ret+=resource[1].getId()+" "+argv[resource[1].getId()]+"
" + resource[1].metalink=argv[resource[1].getId()][0:] + except: + """not""" + return ret + + def changeMetaDataLinkInCollection(self): + """change all lables of a collection""" + ret="" + argv=self.REQUEST.form + + resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource']) + for resource in resources: + + try: + ret+=resource[1].getId()+" "+argv[resource[1].getId()]+"
" + resource[1].metalink=argv[resource[1].getId()][0:] + except: + """not""" + return ret + + def changeWeightsInCollection(self): + """change all lables of a collection""" + ret="" + argv=self.REQUEST.form + + resources=self.ZopeFind(self,obj_metatypes=['ECHO_pageTemplate','ECHO_resource','ECHO_collection','ECHO_link','ECHO_externalLink']) + for resource in resources: + + try: + ret+=resource[1].getId()+" "+argv[resource[1].getId()]+"
" + resource[1].weight=argv[resource[1].getId()][0:] + except: + """not""" + return ret + + def changeTitlesInCollection(self): + """change all lables of a collection""" + ret="" + argv=self.REQUEST.form + + resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource']) + for resource in resources: + + try: + ret+=resource[1].getId()+" "+argv[resource[1].getId()]+"
" + resource[1].title=argv[resource[1].getId()][0:] + except: + """not""" + return ret + + def updateCollection(self,RESPONSE=None): + """liest verzeichnisse aus dem pfad und legt sie dann als objekte in den ordner""" + files=os.listdir(self.path) + ret="" + for fileName in files: + + if fileName: + + tempPath=re.sub("/mpiwg/online","",self.path) + link="http://echo.mpiwg-berlin.mpg.de/zogilib_book?fn="+tempPath+"/"+fileName+"/pageimg" + + metalink=self.path+"/"+fileName+"/index.meta" + try: + + #link="http://nausikaa2.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.x.cgi?dir="+fileName+"&step=thumb" + + newObj=ECHO_resource(fileName,link,metalink,fileName,fileName,fileName,'generated','book','','','','','','') + self._setObject(fileName,newObj) + + genObj=getattr(self,fileName) + #genObj.createIndexFile() + ret+="OK:"+fileName+"
" + except: + print "ERROR" + ret+="ERROR:"+fileName+"
" + + return ret + + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + + def updateCollectionMD(self,RESPONSE=None): + """updateMD""" + files=os.listdir(self.path) + for fileName in files: + if fileName: + genObj=getattr(self,fileName) + genObj.copyIndex_meta2echo_resource() + genObj.generate_title() + + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + + + + def changeViewerTemplateSetsForm(self): + """change the viewer template set""" + pt=PageTemplateFile('Products/ECHO_content/zpt/changeViewerTemplateSet').__of__(self) + return pt() + + def getViewerTemplateSets(self,obj_ids=None): + """Get the ViewerTemplateSet title for configuration""" + ret=[] + + try: + viewerTemplateSets=self.ZopeFind(self.viewerTemplateSets,obj_metatypes=['OSAS_viewerTemplateSet'],obj_ids=obj_ids)#assumes viewerTemplateSets folder somewhere in the hierarchie. + + for viewerTemplateSet in viewerTemplateSets: + ret.append((viewerTemplateSet[1].title,viewerTemplateSet[0],viewerTemplateSet[1])) + + return ret + + except: + return [('no ViewerTemplateSetfolders','')] + + def getTextToolsField(self,name,default=''): + """Lese viewerTemplateSet der Collection not implemented yet!""" + + return default + + + def isSelectedViewerTemplateSet(self,obj,id): + """is ausgewählt""" + + if self.REQUEST['viewerTemplateSet']==id: + return 1 + else: + return None + + def changeViewerTemplateSets(self,project,xslt,thumbtemplate,topbar,digiLibTemplate,digiliburlprefix,RESPONSE=None): + """change the templates""" + + resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource'],search_sub=1) + + for resource in resources: + + resource[1].changeViewerTemplateSet(project,xslt,thumbtemplate,topbar,digiLibTemplate,digiliburlprefix) + + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + + + def setStartpageFolderForm(self): + """Form for changing the startpage""" + + + pt=PageTemplateFile('Products/ECHO_content/zpt/ChangeECHO_resourceStartPageFolder.zpt').__of__(self) + pt.content_type="text/html" + return pt() + + def setStartpageFolder(self,startpage=None,RESPONSE=None): + """change the templates""" + + resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource'],search_sub=1) + + for resource in resources: + + resource[1].setStartPage(startpage) + + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + + + + def copySearchFields(self,RESPONSE=None): + """copys import metadatafields to the object""" + resources=self.ZopeFind(self,obj_metatypes=['ECHO_resource']) + + for resource in resources: + + resource[1].copySearchFields() + + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + + def reloadMetaDataFromStorageWarning(self,RESPONSE=None): + """warning""" + pt=PageTemplateFile('Products/ECHO_content/zpt/reloadMetaDataFromStorageWarning.zpt').__of__(self) + pt.content_type="text/html" + return pt() + + def reloadMetaDataFromStorage(self,RESPONSE=None): + """copy metadata from the storage to ECHO""" + + return reloadMetaDataFromStorage(self,RESPONSE=None) + + + def getPartnerCopyright(self,name,sonst="generic"): + """gibt generisches copyright eines partners aus, sonst behalte jetzige einsteillung""" + #print "hi",name,sonst + #print getattr(self.partners,name).copyrightType + try: + partner=getattr(self.partners,name) + return partner.copyrightType + except: + print "error" + return sonst + + def partnerSelector_HTML(self,selected=None): + """give type selector""" + if not selected: + retStr="