--- documentViewer/documentViewer.py 2006/06/13 14:57:46 1.10.2.1 +++ documentViewer/documentViewer.py 2006/09/11 14:43:09 1.19 @@ -1,3 +1,5 @@ + + from OFS.Folder import Folder from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate from Products.PageTemplates.PageTemplateFile import PageTemplateFile @@ -7,7 +9,7 @@ from Globals import package_home from Ft.Xml.Domlette import NonvalidatingReader from Ft.Xml.Domlette import PrettyPrint, Print -from Ft.Xml import EMPTY_NAMESPACE +from Ft.Xml import EMPTY_NAMESPACE, Parse import Ft.Xml.XPath @@ -16,6 +18,7 @@ import sys import cgi import urllib import zLOG +import urlparse def getInt(number, default=0): """returns always an int (0 in case of problems)""" @@ -25,6 +28,7 @@ def getInt(number, default=0): return default def getTextFromNode(nodename): + """get the cdata content of a node""" if nodename is None: return "" nodelist=nodename.childNodes @@ -55,7 +59,8 @@ def urlopen(url,timeout=2): ## class documentViewer(Folder): """document viewer""" - + textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" + meta_type="Document viewer" security=ClassSecurityInfo() @@ -74,11 +79,13 @@ class documentViewer(Folder): changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) - def __init__(self,id,imageViewerUrl,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): + def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): """init document viewer""" self.id=id self.title=title self.imageViewerUrl=imageViewerUrl + self.textViewerUrl=textViewerUrl + if not digilibBaseUrl: self.digilibBaseUrl = self.findDigilibUrl() else: @@ -92,11 +99,13 @@ class documentViewer(Folder): security.declareProtected('View','index_html') - def index_html(self,mode,url,start=None,pn=1): + def index_html(self,mode,url,viewMode="images",start=None,pn=1): ''' view it @param mode: defines which type of document is behind url @param url: url which contains display information + @param viewMode: if images display images, if text display text, default is images + ''' zLOG.LOG("documentViewer (index)", zLOG.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) @@ -111,7 +120,7 @@ class documentViewer(Folder): docinfo = self.getDocinfo(mode=mode,url=url) pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) pt = getattr(self.template, 'viewer_main') - return pt(docinfo=docinfo,pageinfo=pageinfo) + return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) def getLink(self,param=None,val=None): @@ -142,13 +151,11 @@ class documentViewer(Folder): def isAccessible(self, docinfo): """returns if access to the resource is granted""" access = docinfo.get('accessType', None) - if access is None: - # no information - no access - #TODO: check - return True - elif access == 'free': + zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "access type %s"%access) + if access is not None and access == 'free': + zLOG.LOG("documentViewer (accessOK)", zLOG.INFO, "access is free") return True - elif access in self.authgroups: + elif access is None or access in self.authgroups: # only local access -- only logged in users user = getSecurityManager().getUser() if user is not None: @@ -163,21 +170,24 @@ class documentViewer(Folder): def getDirinfoFromDigilib(self,path,docinfo=None): """gibt param von dlInfo aus""" + num_retries = 3 if docinfo is None: docinfo = {} - imageUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path + infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path - zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(imageUrl)) + zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(infoUrl)) - for cnt in (1,2,3): + for cnt in range(num_retries): try: - dom = NonvalidatingReader.parseUri(imageUrl) + # dom = NonvalidatingReader.parseUri(imageUrl) + txt=urllib.urlopen(infoUrl).read() + dom = Parse(txt) break except: - zLOG.LOG("documentViewer (getdirinfofromdigilib)", zLOG.ERROR, "error reading %s (try %d)"%(imageUrl,cnt)) + zLOG.LOG("documentViewer (getdirinfofromdigilib)", zLOG.ERROR, "error reading %s (try %d)"%(infoUrl,cnt)) else: - raise IOError("Unable to get dir-info from %s"%(imageUrl)) + raise IOError("Unable to get dir-info from %s"%(infoUrl)) sizes=dom.xpath("//dir/size") zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%sizes) @@ -198,22 +208,19 @@ class documentViewer(Folder): if url.startswith("http://"): # real URL metaUrl = url - try: - dom = NonvalidatingReader.parseUri(url) - except: - zLOG.LOG("documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) - raise IOError("Unable to read index.meta from %s"%(url)) else: # online path server=self.digilibBaseUrl+"/servlet/Texter?fn=" - metaUrl=server+url + metaUrl=server+url.replace("/mpiwg/online","") if not metaUrl.endswith("index.meta"): metaUrl += "/index.meta" - - for n in range(num_retries): + print metaUrl + for cnt in range(num_retries): try: - dom = NonvalidatingReader.parseUri(metaUrl) - zLOG.LOG("documentViewer (getIndexMata)", zLOG.INFO,metaUrl) + # patch dirk encoding fehler treten dann nicht mehr auf + # dom = NonvalidatingReader.parseUri(metaUrl) + txt=urllib.urlopen(metaUrl).read() + dom = Parse(txt) break except: zLOG.LOG("ERROR documentViewer (getIndexMata)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) @@ -235,7 +242,7 @@ class documentViewer(Folder): if dom is None: dom = self.getIndexMeta(getParentDir(path)) - + acctype = dom.xpath("//access-conditions/access/@type") if acctype and (len(acctype)>0): access=acctype[0].value @@ -283,9 +290,14 @@ class documentViewer(Folder): if dom is None: dom = self.getIndexMeta(url) + archivePath = None + archiveName = None + archiveNames=dom.xpath("//resource/name") if archiveNames and (len(archiveNames)>0): archiveName=getTextFromNode(archiveNames[0]) + else: + zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.WARNING,"resource/name missing in: %s"%(url)) archivePaths=dom.xpath("//resource/archive-path") if archivePaths and (len(archivePaths)>0): @@ -293,10 +305,17 @@ class documentViewer(Folder): # clean up archive path if archivePath[0] != '/': archivePath = '/' + archivePath - if not archivePath.endswith(archiveName): + if archiveName and (not archivePath.endswith(archiveName)): archivePath += "/" + archiveName else: - archivePath=None + # try to get archive-path from url + zLOG.LOG("documentViewer (getdocinfofromtexttool)", zLOG.WARNING,"resource/archive-path missing in: %s"%(url)) + if (not url.startswith('http')): + archivePath = url.replace('index.meta', '') + + if archivePath is None: + # we balk without archive-path + raise IOError("Missing archive-path (for text-tool) in %s"%(url)) imageDirs=dom.xpath("//texttool/image") if imageDirs and (len(imageDirs)>0): @@ -321,6 +340,9 @@ class documentViewer(Folder): textUrls=dom.xpath("//texttool/text") if textUrls and (len(textUrls)>0): textUrl=getTextFromNode(textUrls[0]) + if urlparse.urlparse(textUrl)[0]=="": #keine url + textUrl=os.path.join(archivePath,textUrl) + docinfo['textURL'] = textUrl docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) @@ -449,16 +471,22 @@ class documentViewer(Folder): def findDigilibUrl(self): """try to get the digilib URL from zogilib""" url = self.imageViewerUrl[:-1] + "/getScalerUrl" + print urlparse.urlparse(url)[0] + print urlparse.urljoin(self.absolute_url(),url) try: + if urlparse.urlparse(url)[0]=='': #relative path + url=urlparse.urljoin(self.absolute_url()+"/",url) + scaler = urlopen(url).read() return scaler.replace("/servlet/Scaler?", "") except: return None - def changeDocumentViewer(self,imageViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): + def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): """init document viewer""" self.title=title self.imageViewerUrl=imageViewerUrl + self.textViewerUrl=textViewerUrl self.digilibBaseUrl = digilibBaseUrl self.thumbrows = thumbrows self.thumbcols = thumbcols @@ -476,9 +504,9 @@ def manage_AddDocumentViewerForm(self): pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) return pt() -def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None): +def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None): """add the viewer""" - newObj=documentViewer(id,imageViewerUrl,title) + newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl) self._setObject(id,newObj) if RESPONSE is not None: @@ -517,4 +545,4 @@ def manage_addDocumentViewerTemplate(sel return '' - \ No newline at end of file +