--- documentViewer/documentViewer.py 2010/04/30 14:36:00 1.48 +++ documentViewer/documentViewer.py 2010/05/19 16:19:45 1.52 @@ -2,6 +2,7 @@ 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 @@ -174,7 +175,7 @@ class documentViewer(Folder): @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 querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph) + @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)) @@ -545,7 +546,10 @@ class documentViewer(Folder): textUrls = dom.xpath("//texttool/text-url-path") if textUrls and (len(textUrls) > 0): textUrl = getTextFromNode(textUrls[0]) - docinfo['textURLPath'] = textUrl + 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 presentationUrls = dom.xpath("//texttool/presentation") docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag @@ -558,7 +562,7 @@ class documentViewer(Folder): presentationUrl = url.replace('index.meta', presentationPath) else: presentationUrl = url + "/" + presentationPath - docinfo = self.getNumPages(docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht + docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info @@ -689,6 +693,9 @@ class documentViewer(Folder): def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None): """get search list""" docpath = docinfo['textURLPath'] + url = docinfo['url'] + logging.debug("documentViewer (gettoc) docpath: %s"%(docpath)) + logging.debug("documentViewer (gettoc) url: %s"%(url)) pagesize = pageinfo['queryPageSize'] pn = pageinfo['searchPN'] sn = pageinfo['sn'] @@ -697,18 +704,49 @@ class documentViewer(Folder): viewMode= pageinfo['viewMode'] tocMode = pageinfo['tocMode'] tocPN = pageinfo['tocPN'] - - page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn) ,outputUnicode=False) - pagexm = page.replace('?document=/echo/la/Benedetti_1585.xml','?url=/mpiwg/online/permanent/library/163127KK') - pagexml=pagexm.replace('mode=text','mode=texttool') + selfurl = self.absolute_url() + logging.debug("documentViewer (gettoc) /mpdl/interface/doc-query.xql?document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode)) + page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode) ,outputUnicode=False) + pagexml = page.replace('?document=%s'%str(docpath),'?url=%s'%url) pagedom = Parse(pagexml) - - if (queryType=="fulltext")or(queryType=="fulltextMorph")or(queryType=="xpath")or(queryType=="xquery"): + if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"): pagedivs = pagedom.xpath("//div[@class='queryResultPage']") - selfurl = self.absolute_url() - page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s&query=%s&queryType=%s'%(selfurl, viewMode, tocMode, tocPN, query, queryType)) - text =page.replace('mode=text','mode=texttool') - return text + if len(pagedivs)>0: + pagenode=pagedivs[0] + links=pagenode.xpath("//a") + for l in links: + hrefNode = l.getAttributeNodeNS(None, u"href") + if hrefNode: + href = hrefNode.nodeValue + if href.startswith('page-fragment.xql'): + selfurl = self.absolute_url() + #l.setAttributeNS(None, "span class = 'hit highlight'", "background-color: #77DD77;") + pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN)) + hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) + l.setAttributeNS(None, "onClick", "id='highlighting'") + return serializeNode(pagenode) + + if (queryType=="fulltextMorph"): + pagedivs = pagedom.xpath("//div[@class='queryResult']") + + if len(pagedivs)>0: + pagenode=pagedivs[0] + links=pagenode.xpath("//a") + for l in links: + hrefNode = l.getAttributeNodeNS(None, u"href") + if hrefNode: + href = hrefNode.nodeValue + if href.startswith('page-fragment.xql'): + selfurl = self.absolute_url() + pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN)) + hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl) + if href.startswith('../lt/lemma.xql'): + selfurl = self.absolute_url() + hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl) + l.setAttributeNS(None, 'target', '_blank') + l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") + l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') + return serializeNode(pagenode) if (queryType=="ftIndex")or(queryType=="ftIndexMorph"): pagedivs= pagedom.xpath("//div[@class='queryResultPage']") @@ -719,23 +757,21 @@ class documentViewer(Folder): hrefNode = l.getAttributeNodeNS(None, u"href") if hrefNode: href = hrefNode.nodeValue + hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn)) + if href.startswith('../lt/lex.xql'): - selfurl = self.absolute_url() - hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl) - - - + # selfurl = self.absolute_url() + hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl) l.setAttributeNS(None, 'target', '_blank') - l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=200, scrollbars=1'); return false;") + l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') if href.startswith('../lt/lemma.xql'): - selfurl = self.absolute_url() - hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl) + #selfurl = self.absolute_url() + hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl) l.setAttributeNS(None, 'target', '_blank') - l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=200, scrollbars=1'); return false;") + l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;") l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') - return serializeNode(pagenode) - + return serializeNode(pagenode) return "no text here" def getNumPages(self,docinfo=None): @@ -768,7 +804,16 @@ class documentViewer(Folder): pagedivs = pagedom.xpath("/div") #queryResultPage if len(pagedivs) > 0: + pagenode = pagedivs[0] + links = pagenode.xpath("//a") + for l in links: + hrefNode = l.getAttributeNodeNS(None, u"href") + if hrefNode: + href= hrefNode.nodeValue + if href.startswith('#note-0006-01'): + selfurl = self.absolute_url() + hrefNode.nodeValue = href.replace("href='#note-'",'xaxa/%s/'%selfurl) return serializeNode(pagenode) if mode == "xml": # first div contains text @@ -811,12 +856,13 @@ class documentViewer(Folder): def getTranslate(self, query=None, language=None): """translate into another languages""" - pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","query=%s&language=%s"%(query,language),outputUnicode=False) + pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query))) return pagexml def getLemma(self, lemma=None, language=None): """simular words lemma """ - pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False) + pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma))) + #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","lemma=%s&language=%s"%(lemma,language),outputUnicode=False) return pagexml def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1): @@ -879,16 +925,18 @@ class documentViewer(Folder): else: queryType = mode docpath = docinfo['textURLPath'] + path = docinfo['textURLPath'] + #logging.debug("documentViewer (gettoc) pathNomer: %s"%(pathNomer)) pagesize = pageinfo['tocPageSize'] pn = pageinfo['tocPN'] - + url = docinfo['url'] selfurl = self.absolute_url() viewMode= pageinfo['viewMode'] tocMode = pageinfo['tocMode'] tocPN = pageinfo['tocPN'] pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn), outputUnicode=False) - page = pagexml.replace('page-fragment.xql?document=/echo/la/Benedetti_1585.xml','%s?url=/mpiwg/online/permanent/library/163127KK&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl, viewMode, tocMode, tocPN)) + page = pagexml.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN)) text = page.replace('mode=image','mode=texttool') return text # post-processing downloaded xml