--- documentViewer/documentViewer.py 2010/05/05 15:42:56 1.49 +++ documentViewer/documentViewer.py 2010/06/14 10:49:48 1.69.2.1 @@ -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 @@ -12,6 +13,7 @@ from Ft.Xml import EMPTY_NAMESPACE, Pars from xml.dom.minidom import parse, parseString +from extraFunction import * import Ft.Xml.XPath @@ -77,7 +79,7 @@ def urlopen(url,timeout=2): ## ## documentViewer class ## -class documentViewer(Folder): +class documentViewer(Folder, extraFunction): """document viewer""" #textViewerUrl="http://127.0.0.1:8080/HFQP/testXSLT/getPage?" @@ -100,7 +102,8 @@ class documentViewer(Folder): head_main = PageTemplateFile('zpt/head_main', globals()) docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) info_xml = PageTemplateFile('zpt/info_xml', globals()) - + + thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) security.declareProtected('View management screens','changeDocumentViewerForm') changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) @@ -194,14 +197,14 @@ class documentViewer(Folder): # get table of contents docinfo = self.getToc(mode=tocMode, docinfo=docinfo) - pageinfo = self.getPageinfo(start=start,current=pn,docinfo=docinfo,viewMode=viewMode,tocMode=tocMode) - if viewMode=="auto": # automodus gewaehlt if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert - viewMode="text" + viewMode="text_dict" else: viewMode="images" + 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)) @@ -220,6 +223,10 @@ class documentViewer(Folder): """try to get the digilib URL from zogilib""" url = self.template.zogilib.getDLBaseUrl() return url + + def getDocumentViewerURL(self): + """returns the URL of this instance""" + return self.absolute_url() def getStyle(self, idx, selected, style=""): """returns a string with the given style and append 'sel' if path == selected.""" @@ -545,7 +552,10 @@ 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 +568,7 @@ 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 @@ -631,8 +641,7 @@ class documentViewer(Folder): logger("documentViewer (getdocinfo)", logging.INFO,"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): """returns pageinfo with the given parameters""" pageinfo = {} @@ -653,19 +662,16 @@ class documentViewer(Folder): pageinfo['end'] = min(pageinfo['end'], np) pageinfo['numgroups'] = int(np / grpsize) if np % grpsize > 0: - pageinfo['numgroups'] += 1 - - + pageinfo['numgroups'] += 1 pageinfo['viewMode'] = viewMode pageinfo['tocMode'] = tocMode 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','') pageinfo['tocPageSize'] = self.REQUEST.get('tocPageSize', '30') - pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '20') + pageinfo['queryPageSize'] =self.REQUEST.get('queryPageSize', '10') pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') toc = int (pageinfo['tocPN']) pageinfo['textPages'] =int (toc) @@ -673,266 +679,17 @@ class documentViewer(Folder): if 'tocSize_%s'%tocMode in docinfo: tocSize = int(docinfo['tocSize_%s'%tocMode]) tocPageSize = int(pageinfo['tocPageSize']) - # cached toc - + # cached toc if tocSize%tocPageSize>0: tocPages=tocSize/tocPageSize+1 else: tocPages=tocSize/tocPageSize - pageinfo['tocPN'] = min (tocPages,toc) - + pageinfo['tocPN'] = min (tocPages,toc) pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') - pageinfo['sn'] =self.REQUEST.get('sn','1') - + pageinfo['sn'] =self.REQUEST.get('sn','') return pageinfo - - def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None): - """get search list""" - docpath = docinfo['textURLPath'] - pagesize = pageinfo['queryPageSize'] - pn = pageinfo['searchPN'] - sn = pageinfo['sn'] - query =pageinfo['query'] - queryType =pageinfo['queryType'] - viewMode= pageinfo['viewMode'] - tocMode = pageinfo['tocMode'] - tocPN = pageinfo['tocPN'] - selfurl = self.absolute_url() - 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=/echo/la/Benedetti_1585.xml','?url=/mpiwg/online/permanent/library/163127KK') - #hrefNode.nodeValue =pagexml.replace('mode=text','%s&mode=texttool'%selfurl) - pagedom = Parse(pagexml) - #logging.debug("documentViewer (gettoc) pagedom: %s"%(pagedom)) - if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"): - pagedivs = pagedom.xpath("//div[@class='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('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, "span class = 'hit'", "background-color: #77DD77;") - 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']") - 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 - 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) - 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();') - 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) - return "xexe" - - def getNumPages(self,docinfo=None): - """get list of pages from fulltext and put in docinfo""" - xquery = '//pb' - text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) - # TODO: better processing of the page list. do we need the info somewhere else also? - docinfo['numPages'] = text.count(" 0: - pagenode = pagedivs[0] - return serializeNode(pagenode) - if mode == "xml": - # first div contains text - pagedivs = pagedom.xpath("/div") - if len(pagedivs) > 0: - pagenode = pagedivs[0] - return serializeNode(pagenode) - # text-with-links mode - if mode == "text_dict": - # first div contains text - pagedivs = pagedom.xpath("/div") - if len(pagedivs) > 0: - pagenode = pagedivs[0] - # check all a-tags - links = pagenode.xpath("//a") - for l in links: - hrefNode = l.getAttributeNodeNS(None, u"href") - if hrefNode: - # is link with href - href = hrefNode.nodeValue - if href.startswith('lt/lex.xql'): - # is pollux link - selfurl = self.absolute_url() - # change href - hrefNode.nodeValue = href.replace('lt/lex.xql','%s/template/head_main_voc'%selfurl) - # add target - l.setAttributeNS(None, 'target', '_blank') - l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, 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) - l.setAttributeNS(None, 'target', '_blank') - l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;") - l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();') - return serializeNode(pagenode) - - return "no text here" - - 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) - 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) - return pagexml - - def getQuery (self, docinfo=None, pageinfo=None, query=None, queryType=None, pn=1): - """number of""" - docpath = docinfo['textURLPath'] - pagesize = pageinfo['queryPageSize'] - pn = pageinfo['searchPN'] - query =pageinfo['query'] - queryType =pageinfo['queryType'] - - tocSearch = 0 - tocDiv = None - pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False) - - pagedom = Parse(pagexml) - numdivs = pagedom.xpath("//div[@class='queryResultHits']") - tocSearch = int(getTextFromNode(numdivs[0])) - tc=int((tocSearch/20)+1) - logging.debug("documentViewer (gettoc) tc: %s"%(tc)) - return tc - - def getToc(self, mode="text", docinfo=None): - """loads table of contents and stores in docinfo""" - logging.debug("documentViewer (gettoc) mode: %s"%(mode)) - if 'tocSize_%s'%mode in docinfo: - # cached toc - return docinfo - docpath = docinfo['textURLPath'] - # we need to set a result set size - pagesize = 1000 - pn = 1 - if mode == "text": - queryType = "toc" - else: - queryType = mode - # number of entries in toc - tocSize = 0 - tocDiv = None - pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False) - # post-processing downloaded xml - pagedom = Parse(pagexml) - # get number of entries - numdivs = pagedom.xpath("//div[@class='queryResultHits']") - if len(numdivs) > 0: - tocSize = int(getTextFromNode(numdivs[0])) - # div contains text - #pagedivs = pagedom.xpath("//div[@class='queryResultPage']") - #if len(pagedivs) > 0: - # tocDiv = pagedivs[0] - - docinfo['tocSize_%s'%mode] = tocSize - #docinfo['tocDiv_%s'%mode] = tocDiv - return docinfo - def getTocPage(self, mode="text", pn=1, pageinfo=None, docinfo=None): - """returns single page from the table of contents""" - # TODO: this should use the cached TOC - if mode == "text": - queryType = "toc" - else: - queryType = mode - docpath = docinfo['textURLPath'] - pagesize = pageinfo['tocPageSize'] - pn = pageinfo['tocPN'] - - 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)) - text = page.replace('mode=image','mode=texttool') - return text - # post-processing downloaded xml - #pagedom = Parse(text) - # div contains text - #pagedivs = pagedom.xpath("//div[@class='queryResultPage']") - #if len(pagedivs) > 0: - # pagenode = pagedivs[0] - # return serializeNode(pagenode) - #else: - # return "No TOC!" - - - def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): +def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): """init document viewer""" self.title=title self.digilibBaseUrl = digilibBaseUrl @@ -941,8 +698,6 @@ class documentViewer(Folder): self.authgroups = [s.strip().lower() for s in authgroups.split(',')] if RESPONSE is not None: RESPONSE.redirect('manage_main') - - def manage_AddDocumentViewerForm(self): """add the viewer form""" @@ -957,10 +712,7 @@ def manage_AddDocumentViewer(self,id,ima if RESPONSE is not None: RESPONSE.redirect('manage_main') - -## ## DocumentViewerTemplate class -## class DocumentViewerTemplate(ZopePageTemplate): """Template for document viewer""" meta_type="DocumentViewer Template"