--- documentViewer/documentViewer.py 2010/04/08 11:04:51 1.44 +++ 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 @@ -10,6 +11,10 @@ from Ft.Xml.Domlette import Nonvalidatin from Ft.Xml.Domlette import PrettyPrint, Print from Ft.Xml import EMPTY_NAMESPACE, Parse +from xml.dom.minidom import parse, parseString + +from extraFunction import * + import Ft.Xml.XPath import cStringIO @@ -74,7 +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?" @@ -93,16 +98,18 @@ 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_xml = PageTemplateFile('zpt/page_main_xml', globals()) 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()) - def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): + def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=5,authgroups="mpiwg"): """init document viewer""" self.id=id self.title=title @@ -163,13 +170,14 @@ 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): + def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=None, query=None, querySearch=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) + @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, fulltextMorphLemma) ''' logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) @@ -183,17 +191,20 @@ 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,viewMode=viewMode,tocMode=tocMode) + + 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 - 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)) @@ -212,6 +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.""" @@ -537,7 +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 @@ -550,7 +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 @@ -623,8 +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 = {} @@ -645,125 +662,34 @@ 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['tocPageSize'] = self.REQUEST.get('tocPageSize', '10') + 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', '10') pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') - + toc = int (pageinfo['tocPN']) + pageinfo['textPages'] =int (toc) + + if 'tocSize_%s'%tocMode in docinfo: + tocSize = int(docinfo['tocSize_%s'%tocMode]) + tocPageSize = int(pageinfo['tocPageSize']) + # cached toc + if tocSize%tocPageSize>0: + tocPages=tocSize/tocPageSize+1 + else: + tocPages=tocSize/tocPageSize + pageinfo['tocPN'] = min (tocPages,toc) + pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') + pageinfo['sn'] =self.REQUEST.get('sn','') return pageinfo - - - - 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) - - # 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/head_main_voc'%selfurl) - # add target - l.setAttributeNS(None, 'target', '_blank') - return serializeNode(pagenode) - - return "no text here" - - 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="toc", 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'] - 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) - # 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=10,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 @@ -772,8 +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""" @@ -788,10 +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"