--- documentViewer/documentViewer.py 2010/06/16 18:32:20 1.69.2.4 +++ documentViewer/documentViewer.py 2010/11/09 11:38:25 1.156 @@ -2,26 +2,23 @@ from OFS.Folder import Folder from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate from Products.PageTemplates.PageTemplateFile import PageTemplateFile -from Products.PythonScripts.standard import url_quote from AccessControl import ClassSecurityInfo from AccessControl import getSecurityManager from Globals import package_home +from Products.zogiLib.zogiLib import browserCheck -from Ft.Xml.Domlette import NonvalidatingReader -from Ft.Xml.Domlette import PrettyPrint, Print from Ft.Xml import EMPTY_NAMESPACE, Parse -import Ft.Xml.XPath -import cStringIO -import xmlrpclib +import Ft.Xml.Domlette import os.path import sys -import cgi import urllib +import urllib2 import logging import math - import urlparse -from types import * +import cStringIO +import re +import string def logger(txt,method,txt2): """logging""" @@ -49,12 +46,39 @@ def getTextFromNode(nodename): def serializeNode(node, encoding='utf-8'): """returns a string containing node as XML""" buf = cStringIO.StringIO() - Print(node, stream=buf, encoding=encoding) + Ft.Xml.Domlette.Print(node, stream=buf, encoding=encoding) s = buf.getvalue() buf.close() return s +def browserCheck(self): + """check the browsers request to find out the browser type""" + bt = {} + ua = self.REQUEST.get_header("HTTP_USER_AGENT") + bt['ua'] = ua + bt['isIE'] = False + bt['isN4'] = False + if string.find(ua, 'MSIE') > -1: + bt['isIE'] = True + else: + bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) + try: + nav = ua[string.find(ua, '('):] + ie = string.split(nav, "; ")[1] + if string.find(ie, "MSIE") > -1: + bt['versIE'] = string.split(ie, " ")[1] + except: pass + + bt['isMac'] = string.find(ua, 'Macintosh') > -1 + bt['isWin'] = string.find(ua, 'Windows') > -1 + bt['isIEWin'] = bt['isIE'] and bt['isWin'] + bt['isIEMac'] = bt['isIE'] and bt['isMac'] + bt['staticHTML'] = False + + return bt + + def getParentDir(path): """returns pathname shortened by one""" return '/'.join(path.split('/')[0:-1]) @@ -78,7 +102,7 @@ def getHttpData(url, data=None, num_trie if sys.version_info < (2, 6): # set timeout on socket -- ugly :-( import socket - socket.setdefaulttimeout(timeout) + socket.setdefaulttimeout(float(timeout)) response = urllib2.urlopen(url) else: response = urllib2.urlopen(url,timeout=float(timeout)) @@ -125,6 +149,7 @@ class documentViewer(Folder): page_main_images = PageTemplateFile('zpt/page_main_images', globals()) page_main_text = PageTemplateFile('zpt/page_main_text', globals()) page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) + page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals()) page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) head_main = PageTemplateFile('zpt/head_main', globals()) docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) @@ -151,7 +176,7 @@ class documentViewer(Folder): self._setObject('template',templateFolder) # old style try: import MpdlXmlTextServer - textServer = MpdlXmlTextServer(id='fulltextclient') + textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) #templateFolder['fulltextclient'] = xmlRpcClient templateFolder._setObject('fulltextclient',textServer) except Exception, e: @@ -173,15 +198,47 @@ class documentViewer(Folder): def getQuery(self, **args): """get query""" return self.template.fulltextclient.getQuery(**args) + + def getQueryResultHits(self, **args): + """get query""" + return self.template.fulltextclient.getQueryResultHits(**args) + + def getQueryResultHitsText(self, **args): + """get query""" + return self.template.fulltextclient.getQueryResultHitsText(**args) + + def getQueryResultHitsFigures(self, **args): + """get query""" + return self.template.fulltextclient.getQueryResultHitsFigures(**args) + + def getPDF(self, **args): + """get query""" + return self.template.fulltextclient.getPDF(**args) def getSearch(self, **args): """get search""" return self.template.fulltextclient.getSearch(**args) - - def getNumPages(self, **args): + + def getGisPlaces(self, **args): + """get gis places""" + return self.template.fulltextclient.getGisPlaces(**args) + + def getAllGisPlaces(self, **args): + """get all gis places """ + return self.template.fulltextclient.getAllGisPlaces(**args) + + def getOrigPages(self, **args): + """get original page number """ + return self.template.fulltextclient.getOrigPages(**args) + + def getNumPages(self, docinfo): """get numpages""" - return self.template.fulltextclient.getNumPages(**args) - + 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) @@ -219,11 +276,13 @@ class documentViewer(Folder): self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" docinfo = self.getDocinfo(mode=mode,url=url) - pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) + #pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo) + pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) + ''' ZDES ''' pt = getattr(self.template, 'thumbs_main_rss') if viewMode=="auto": # automodus gewaehlt - if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert + if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert viewMode="text" else: viewMode="images" @@ -231,13 +290,14 @@ 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="", optionToggle=None): ''' view it @param mode: defines how to access the document behind url @param url: url which contains display information @param viewMode: if images display images, if text display text, default is auto (text,images or auto) @param tocMode: type of 'table of contents' for navigation (thumbs, text, figures, none) + @param characterNormalization type of text display (reg, norm, none) @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma) ''' @@ -249,22 +309,21 @@ class documentViewer(Folder): return "ERROR: template folder missing!" if not getattr(self, 'digilibBaseUrl', None): - self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" + self.digilibBaseUrl = self.findDigilibUrl() or "http://digilib.mpiwg-berlin.mpg.de/digitallibrary" docinfo = self.getDocinfo(mode=mode,url=url) - if tocMode != "thumbs": # get table of contents docinfo = self.getToc(mode=tocMode, docinfo=docinfo) if viewMode=="auto": # automodus gewaehlt - if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert + if docinfo.has_key('textURL') or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert viewMode="text_dict" else: viewMode="images" - pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) + pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) pt = getattr(self.template, 'viewer_main') return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) @@ -273,13 +332,20 @@ class documentViewer(Folder): ret="" if mk is None: return "" - if type(mk) is not ListType: - mk=[mk] + if not isinstance(mk, list): + mk=[mk] for m in mk: ret+="mk=%s"%m return ret - - + + + def getBrowser(self): + """getBrowser the version of browser """ + names="" + names = browserCheck(self) + #logging.debug("XXXXXXXXXXXXXXXX: %s"%names) + return names + def findDigilibUrl(self): """try to get the digilib URL from zogilib""" url = self.template.zogilib.getDLBaseUrl() @@ -312,7 +378,8 @@ class documentViewer(Folder): params["url"] = getParentDir(params["url"]) # quote values and assemble into query string - ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) + #ps = "&".join(["%s=%s"%(k,urllib.quote(v)) for (k, v) in params.items()]) + ps = urllib.urlencode(params) url=self.REQUEST['URL1']+"?"+ps return url @@ -342,6 +409,20 @@ class documentViewer(Folder): pt = getattr(self.template, 'info_xml') return pt(docinfo=docinfo) + def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True): + """returns new option state""" + if not self.REQUEST.SESSION.has_key(optionName): + # not in session -- initial + opt = {'lastState': newState, 'state': initialState} + else: + opt = self.REQUEST.SESSION.get(optionName) + if opt['lastState'] != newState: + # state in session has changed -- toggle + opt['state'] = not opt['state'] + opt['lastState'] = newState + + self.REQUEST.SESSION[optionName] = opt + return opt['state'] def isAccessible(self, docinfo): """returns if access to the resource is granted""" @@ -353,13 +434,14 @@ class documentViewer(Folder): 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())) if user is not None: #print "user: ", user return (user.getUserName() != "Anonymous User") else: return False - logging.debug("documentViewer (accessOK) unknown access type %s"%access) + logging.error("documentViewer (accessOK) unknown access type %s"%access) return False @@ -393,10 +475,20 @@ 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 @@ -407,8 +499,15 @@ 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)) @@ -448,7 +547,7 @@ 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): @@ -470,7 +569,9 @@ 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)) # put in all raw bib fields as dict "bib" @@ -492,6 +593,8 @@ 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: @@ -511,6 +614,20 @@ class documentViewer(Folder): 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['name']=getTextFromNode(dom.xpath("/resource/name")[0]) + logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) + return docinfo def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): """parse texttool tag in index meta""" @@ -520,7 +637,7 @@ class documentViewer(Folder): 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 @@ -574,7 +691,8 @@ class documentViewer(Folder): if viewerUrls and (len(viewerUrls) > 0): viewerUrl = getTextFromNode(viewerUrls[0]) docinfo['viewerURL'] = viewerUrl - + + # old style text URL textUrls = dom.xpath("//texttool/text") if textUrls and (len(textUrls) > 0): textUrl = getTextFromNode(textUrls[0]) @@ -586,16 +704,19 @@ class documentViewer(Folder): docinfo['textURL'] = textUrl + # new style text-url-path textUrls = dom.xpath("//texttool/text-url-path") if textUrls and (len(textUrls) > 0): textUrl = getTextFromNode(textUrls[0]) docinfo['textURLPath'] = textUrl if not docinfo['imagePath']: # text-only, no page images - docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht + 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 @@ -676,13 +797,15 @@ class documentViewer(Folder): 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"%) 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) + pageinfo['current'] = current rows = int(rows or self.thumbrows) pageinfo['rows'] = rows @@ -702,8 +825,10 @@ class documentViewer(Folder): pageinfo['numgroups'] += 1 pageinfo['viewMode'] = viewMode pageinfo['tocMode'] = tocMode - pageinfo['query'] = self.REQUEST.get('query',' ') - pageinfo['queryType'] = self.REQUEST.get('queryType',' ') + pageinfo['characterNormalization'] = self.REQUEST.get('characterNormalization','') + pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','') + pageinfo['query'] = self.REQUEST.get('query','') + pageinfo['queryType'] = self.REQUEST.get('queryType','') pageinfo['querySearch'] =self.REQUEST.get('querySearch', 'fulltext') pageinfo['textPN'] = self.REQUEST.get('textPN','1') pageinfo['highlightQuery'] = self.REQUEST.get('highlightQuery','') @@ -713,6 +838,8 @@ class documentViewer(Folder): toc = int (pageinfo['tocPN']) pageinfo['textPages'] =int (toc) + + if 'tocSize_%s'%tocMode in docinfo: tocSize = int(docinfo['tocSize_%s'%tocMode]) tocPageSize = int(pageinfo['tocPageSize'])