--- documentViewer/documentViewer.py 2010/08/24 12:34:32 1.94 +++ documentViewer/documentViewer.py 2010/10/08 13:49:44 1.112 @@ -16,6 +16,7 @@ import logging import math import urlparse import cStringIO +import re def logger(txt,method,txt2): """logging""" @@ -68,7 +69,7 @@ def getHttpData(url, data=None, num_trie errmsg = None for cnt in range(num_tries): try: - #logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) + logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) if sys.version_info < (2, 6): # set timeout on socket -- ugly :-( import socket @@ -79,12 +80,12 @@ def getHttpData(url, data=None, num_trie # check result? break except urllib2.HTTPError, e: - #logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) + logging.error("getHttpData: HTTP error(%s): %s"%(e.code,e)) errmsg = str(e) # stop trying break except urllib2.URLError, e: - #logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) + logging.error("getHttpData: URLLIB error(%s): %s"%(e.reason,e)) errmsg = str(e) # stop trying #break @@ -176,7 +177,11 @@ class documentViewer(Folder): def getNumPages(self, docinfo): """get numpages""" return self.template.fulltextclient.getNumPages(docinfo) - + + def getNumTextPages(self, docinfo): + """get numpages text""" + return self.template.fulltextclient.getNumTextPages(docinfo) + def getTranslate(self, **args): """get translate""" return self.template.fulltextclient.getTranslate(**args) @@ -203,8 +208,8 @@ class documentViewer(Folder): @param viewMode: if images display images, if text display text, default is images (text,images or auto) ''' - #logging.debug("HHHHHHHHHHHHHH:load the rss") - #logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) + logging.debug("HHHHHHHHHHHHHH:load the rss") + logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) if not hasattr(self, 'template'): # create template folder if it doesn't exist @@ -226,7 +231,7 @@ class documentViewer(Folder): return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) security.declareProtected('View','index_html') - def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None): + def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=None, characterNormalization=""): ''' view it @param mode: defines how to access the document behind url @@ -237,7 +242,7 @@ class documentViewer(Folder): @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma) ''' - #logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) + logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) if not hasattr(self, 'template'): # this won't work @@ -323,7 +328,7 @@ class documentViewer(Folder): params[param] = str(val) # quote values and assemble into query string - #logging.debug("XYXXXXX: %s"%repr(params.items())) + logging.debug("XYXXXXX: %s"%repr(params.items())) ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) url=self.REQUEST['URL1']+"?"+ps return url @@ -342,21 +347,21 @@ class documentViewer(Folder): def isAccessible(self, docinfo): """returns if access to the resource is granted""" access = docinfo.get('accessType', None) - #logging.debug("documentViewer (accessOK) access type %s"%access) + logging.debug("documentViewer (accessOK) access type %s"%access) if access is not None and access == 'free': - #logging.debug("documentViewer (accessOK) access is free") + logging.debug("documentViewer (accessOK) access is free") return True elif access is None or access in self.authgroups: # only local access -- only logged in users user = getSecurityManager().getUser() - #logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) + logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) if user is not None: #print "user: ", user return (user.getUserName() != "Anonymous User") else: return False - #logging.error("documentViewer (accessOK) unknown access type %s"%access) + logging.error("documentViewer (accessOK) unknown access type %s"%access) return False @@ -371,7 +376,7 @@ class documentViewer(Folder): infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path - #logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) + logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) txt = getHttpData(infoUrl) if txt is None: @@ -379,7 +384,7 @@ class documentViewer(Folder): dom = Parse(txt) sizes=dom.xpath("//dir/size") - #logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) + logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) if sizes: docinfo['numPages'] = int(getTextFromNode(sizes[0])) @@ -390,10 +395,20 @@ class documentViewer(Folder): return docinfo - - def getIndexMeta(self, url): - """returns dom of index.meta document at url""" - dom = None + def getIndexMetaPath(self,url): + """gib nur den Pfad zurueck""" + regexp = re.compile(r".*(experimental|permanent)/(.*)") + regpath = regexp.match(url) + if (regpath==None): + return "" + logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2)) + return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2)) + + + + def getIndexMetaUrl(self,url): + """returns utr of index.meta document at url""" + metaUrl = None if url.startswith("http://"): # real URL @@ -404,8 +419,15 @@ class documentViewer(Folder): metaUrl=server+url.replace("/mpiwg/online","") if not metaUrl.endswith("index.meta"): metaUrl += "/index.meta" + + return metaUrl + + def getDomFromIndexMeta(self, url): + """get dom from index meta""" + dom = None + metaUrl = self.getIndexMetaUrl(url) - #logging.debug("(getIndexMeta): METAURL: %s"%metaUrl) + logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl) txt=getHttpData(metaUrl) if txt is None: raise IOError("Unable to read index meta from %s"%(url)) @@ -435,7 +457,7 @@ class documentViewer(Folder): def getAuthinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): """gets authorization info from the index.meta file at path or given by dom""" - #logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) + logging.debug("documentViewer (getauthinfofromindexmeta) path: %s"%(path)) access = None @@ -445,7 +467,7 @@ class documentViewer(Folder): if dom is None: for x in range(cut): path=getParentDir(path) - dom = self.getIndexMeta(path) + dom = self.getDomFromIndexMeta(path) acctype = dom.xpath("//access-conditions/access/@type") if acctype and (len(acctype)>0): @@ -459,7 +481,7 @@ class documentViewer(Folder): def getBibinfoFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): """gets bibliographical info from the index.meta file at path or given by dom""" - #logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) + logging.debug("documentViewer (getbibinfofromindexmeta) path: %s"%(path)) if docinfo is None: docinfo = {} @@ -467,9 +489,11 @@ class documentViewer(Folder): if dom is None: for x in range(cut): path=getParentDir(path) - dom = self.getIndexMeta(path) + dom = self.getDomFromIndexMeta(path) + + docinfo['indexMetaPath']=self.getIndexMetaPath(path); - #logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) + logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) # put in all raw bib fields as dict "bib" bib = dom.xpath("//bib/*") if bib and len(bib)>0: @@ -489,6 +513,8 @@ class documentViewer(Folder): bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) docinfo['bib_type'] = bibtype bibmap=metaData.generateMappingForType(bibtype) + logging.debug("documentViewer (getbibinfofromindexmeta) bibmap:"+repr(bibmap)) + logging.debug("documentViewer (getbibinfofromindexmeta) bibtype:"+repr(bibtype)) # if there is no mapping bibmap is empty (mapping sometimes has empty fields) if len(bibmap) > 0 and len(bibmap['author'][0]) > 0: try: @@ -500,24 +526,51 @@ class documentViewer(Folder): try: docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) except: pass - #logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) + logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) try: docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) except: docinfo['lang']='' - + try: + docinfo['name']=getTextFromNode(dom.xpath("//%s"%bibmap['name'][0])[0]) + except: pass + return docinfo + + def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): + """gets name info from the index.meta file at path or given by dom""" + if docinfo is None: + docinfo = {} + + if dom is None: + for x in range(cut): + path=getParentDir(path) + dom = self.getDomFromIndexMeta(path) + + #docinfo['indexMetaPath']=self.getIndexMetaPath(path); + + #result= dom.xpath("//result/resultPage") + #docinfo['numPages']=int(getTextFromNode(result[0])) + + if len(name) > 0: + try: + result =dom.xpath("//name") + docinfo['name']=getTextFromNode(result[0]) + logging.debug("documentViewer docinfo[name] %s"%docinfo[name]) + except: pass + #logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) + return docinfo def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): """parse texttool tag in index meta""" - #logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) + logging.debug("documentViewer (getdocinfofromtexttool) url: %s" % (url)) if docinfo is None: docinfo = {} if docinfo.get('lang', None) is None: docinfo['lang'] = '' # default keine Sprache gesetzt if dom is None: - dom = self.getIndexMeta(url) + dom = self.getDomFromIndexMeta(url) archivePath = None archiveName = None @@ -538,7 +591,7 @@ class documentViewer(Folder): archivePath += "/" + archiveName else: # try to get archive-path from url - #logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url)) + logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url)) if (not url.startswith('http')): archivePath = url.replace('index.meta', '') @@ -591,10 +644,11 @@ class documentViewer(Folder): docinfo['textURLPath'] = textUrl if not docinfo['imagePath']: # text-only, no page images - docinfo = self.getNumPages(docinfo) + docinfo = self.getNumTextPages(docinfo) presentationUrls = dom.xpath("//texttool/presentation") docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag + #docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) if presentationUrls and (len(presentationUrls) > 0): # ueberschreibe diese durch presentation informationen # presentation url ergiebt sich ersetzen von index.meta in der url der fuer die Metadaten @@ -628,11 +682,15 @@ class documentViewer(Folder): docinfo['year']=getTextFromNode(dom.xpath("//date")[0]) except: pass + try: + docinfo['name']=getTextFromNode(dom.xpath("//name")[0]) + except: + pass return docinfo def getDocinfoFromImagePath(self,path,docinfo=None,cut=0): """path ist the path to the images it assumes that the index.meta file is one level higher.""" - #logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) + logging.debug("documentViewer (getdocinfofromimagepath) path: %s"%(path)) if docinfo is None: docinfo = {} path=path.replace("/mpiwg/online","") @@ -642,7 +700,7 @@ class documentViewer(Folder): pathorig=path for x in range(cut): path=getParentDir(path) - #logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) + logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path docinfo['imageURL'] = imageUrl @@ -654,13 +712,13 @@ class documentViewer(Folder): def getDocinfo(self, mode, url): """returns docinfo depending on mode""" - #logging.debug("documentViewer (getdocinfo) mode: %s, url: %s"%(mode,url)) + logging.debug("documentViewer (getdocinfo) 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: - #logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) + logging.debug("documentViewer (getdocinfo) docinfo in session: %s"%docinfo) return docinfo # new docinfo docinfo = {'mode': mode, 'url': url} @@ -671,14 +729,14 @@ class documentViewer(Folder): elif mode=="filepath": docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) else: - #logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) + logging.error("documentViewer (getdocinfo) unknown mode: %s!"%mode) raise ValueError("Unknown mode %s! Has to be one of 'texttool','imagepath','filepath'."%(mode)) - #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) + logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) self.REQUEST.SESSION['docinfo'] = docinfo return docinfo - def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None): + def getPageinfo(self, current, start=None, rows=None, cols=None, docinfo=None, viewMode=None, tocMode=None,characterNormalization=""): """returns pageinfo with the given parameters""" pageinfo = {} current = getInt(current) @@ -701,7 +759,8 @@ class documentViewer(Folder): pageinfo['numgroups'] += 1 pageinfo['viewMode'] = viewMode pageinfo['tocMode'] = tocMode - pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','') + #pageinfo['characterNormalization'] =characterNormalization + pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization',' ') pageinfo['query'] = self.REQUEST.get('query',' ') pageinfo['queryType'] = self.REQUEST.get('queryType',' ') pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') @@ -767,7 +826,7 @@ def manage_addDocumentViewerTemplate(sel self._setObject(id, DocumentViewerTemplate(id)) ob = getattr(self, id) txt=file(os.path.join(package_home(globals()),'zpt/viewer_main.zpt'),'r').read() - #logging.info("txt %s:"%txt) + logging.info("txt %s:"%txt) ob.pt_edit(txt,"text/html") if title: ob.pt_setTitle(title)