--- documentViewer/documentViewer.py 2006/04/10 10:13:01 1.5 +++ documentViewer/documentViewer.py 2006/04/10 19:51:50 1.7 @@ -14,6 +14,7 @@ from Ft.Xml import EMPTY_NAMESPACE import Ft.Xml.XPath import os.path +import sys import cgi import urllib import zLOG @@ -42,25 +43,6 @@ def urlopen(url): 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]) - - ## @@ -111,11 +93,9 @@ class documentViewer(Folder): ''' 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: @@ -131,12 +111,15 @@ class documentViewer(Folder): """link to documentviewer with parameter param set to val""" params=cgi.parse_qs(self.REQUEST['QUERY_STRING']) if param is not None: - if val is None and params.has_key(param): - del params[param] + if val is None: + if params.has_key(param): + del params[param] else: - params[param] = val - - url=self.REQUEST['URL']+"?"+urllib.urlencode(params, doseq=True) + params[param] = [str(val)] + + ps = "&".join(["%s=%s"%(k,urllib.quote(v[0])) for (k, v) in params.items()]) + url=self.REQUEST['URL']+"?"+ps + #url=self.REQUEST['URL']+"?"+urllib.urlencode(params, doseq=True) return url @@ -149,6 +132,32 @@ class documentViewer(Folder): return style + def getDirinfoFromDigilib(self,path,docinfo=None): + """gibt param von dlInfo aus""" + if docinfo is None: + docinfo = {} + + imageUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path + + zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo from %s"%(imageUrl)) + + try: + dom = NonvalidatingReader.parseUri(imageUrl) + except: + zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.ERROR, "error reading %s"%(imageUrl)) + raise IOError("Unable to get dirinfo from %s"%(imageUrl)) + + params=dom.xpath("//dir/size") + zLOG.LOG("documentViewer (getparamfromdigilib)", zLOG.INFO, "dirInfo:size"%params) + + if params: + docinfo['numPages'] = getTextFromNode(params[0]) + else: + docinfo['numPages'] = 0 + + return docinfo + + 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)) @@ -157,7 +166,7 @@ class documentViewer(Folder): docinfo = {} if dom is None: - server="http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary/servlet/Texter?fn=" + server=self.digilibBaseUrl+"/servlet/Texter?fn=" path="/".join(path.split("/")[0:-1]) metaUrl=server+path+"/index.meta" try: @@ -173,7 +182,8 @@ class documentViewer(Folder): bibtype="generic" bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) bibmap=metaData.generateMappingForType(bibtype) - if len(bibmap) > 0: + print "bibmap: ", bibmap, " for: ", bibtype + if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) @@ -191,17 +201,15 @@ class documentViewer(Folder): dom = NonvalidatingReader.parseUri(url) except: zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) - return docinfo + raise IOError("Unable to get texttool info from %s"%(url)) 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: @@ -210,21 +218,19 @@ class documentViewer(Folder): if image and archivePath: image=os.path.join(archivePath,image) image=image.replace("/mpiwg/online",'') - pt=getParamFromDigilib(image,'size') + docinfo=self.getDirinfoFromDigilib(image,docinfo=docinfo) docinfo['imagePath'] = image - docinfo['numPages'] = pt + docinfo['imageURL'] = self.digilibBaseUrl+"/servlet/Scaler?fn="+image viewerUrls=dom.xpath("//texttool/digiliburlprefix") - if viewerUrls and (len(viewerUrls)>0): viewerUrl=getTextFromNode(viewerUrls[0]) - docinfo['imageURL'] = viewerURL + docinfo['viewerURL'] = viewerUrl textUrls=dom.xpath("//texttool/text") - if textUrls and (len(textUrls)>0): textUrl=getTextFromNode(textUrls[0]) - docinfo['textURL'] = textURL + docinfo['textURL'] = textUrl docinfo = self.getBibinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) return docinfo @@ -235,11 +241,10 @@ class documentViewer(Folder): 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['numPages'] = pt - imageUrl=genericDigilib+"/servlet/Scaler?fn=%s"%path + docinfo['imagePath'] = path + docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo) + imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path docinfo['imageURL'] = imageUrl docinfo = self.getBibinfoFromIndexMeta(path,docinfo=docinfo) @@ -281,7 +286,6 @@ class documentViewer(Folder): grpsize = cols * rows pageinfo['groupsize'] = grpsize start = getInt(start, default=(int(current / grpsize) * grpsize +1)) - print "start3:", start pageinfo['start'] = start pageinfo['end'] = start + grpsize if docinfo is not None: