Mercurial > hg > documentViewer
changeset 495:ede0c93de798 metalify-1
update branch to latest version of HEAD (with modularisierung branch)
| author | casties |
|---|---|
| date | Thu, 17 Jun 2010 19:35:24 +0200 |
| parents | 312446f900da |
| children | f83ffab77502 |
| files | MpdlXmlTextServer.py __init__.py documentViewer.py version.txt zpt/manage_addMpdlXmlTextServer.zpt zpt/manage_changeMpdlXmlTextServer.zpt zpt/page_main_pureXml.zpt zpt/page_main_text.zpt zpt/page_main_text_dict.zpt zpt/viewer_main.zpt |
| diffstat | 10 files changed, 1156 insertions(+), 225 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/MpdlXmlTextServer.py Thu Jun 17 19:35:24 2010 +0200 @@ -0,0 +1,331 @@ + +from OFS.SimpleItem import SimpleItem +from Products.PageTemplates.PageTemplateFile import PageTemplateFile + +from Ft.Xml import EMPTY_NAMESPACE, Parse + +import sys +import logging +import documentViewer +from documentViewer import getTextFromNode, serializeNode + + +class MpdlXmlTextServer(SimpleItem): + """TextServer implementation for MPDL-XML eXist server""" + meta_type="MPDL-XML TextServer" + + manage_options=( + {'label':'Config','action':'manage_changeMpdlXmlTextServerForm'}, + )+SimpleItem.manage_options + + manage_changeMpdlXmlTextServerForm = PageTemplateFile("zpt/manage_changeMpdlXmlTextServer", globals()) + + def __init__(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40): + """constructor""" + self.id=id + self.title=title + self.timeout = timeout + if serverName is None: + self.serverUrl = serverUrl + else: + self.serverUrl = "http://%s/mpdl/interface/"%serverName + + + def getHttpData(self, url, data=None): + """returns result from url+data HTTP request""" + return documentViewer.getHttpData(url,data,timeout=self.timeout) + + + def getServerData(self, method, data=None): + """returns result from text server for method+data""" + url = self.serverUrl+method + return documentViewer.getHttpData(url,data,timeout=self.timeout) + + + def getSearch(self, pn=1, pageinfo=None, docinfo=None, query=None, queryType=None, lemma=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'] + highlightQuery = pageinfo['highlightQuery'] + query =pageinfo['query'] + queryType =pageinfo['queryType'] + viewMode= pageinfo['viewMode'] + tocMode = pageinfo['tocMode'] + tocPN = pageinfo['tocPN'] + selfurl = self.absolute_url() + + data = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery)) + #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&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery) ,outputUnicode=False) + + pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url) + pagedom = Parse(pagexml) + 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() + 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) + 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'): + hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(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();') + pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']") + 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'): + 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'): + 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 "no text here" + + def getNumPages(self,docinfo=None): + """get list of pages from fulltext and put in docinfo""" + if 'numPages' in docinfo: + # already there + return docinfo + + xquery = '//pb' + text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) + #text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery)) + docinfo['numPages'] = text.count("<pb ") + return docinfo + + def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None): + """returns single page from fulltext""" + docpath = docinfo['textURLPath'] + path = docinfo['textURLPath'] + url = docinfo['url'] + viewMode= pageinfo['viewMode'] + tocMode = pageinfo['tocMode'] + tocPN = pageinfo['tocPN'] + selfurl = self.absolute_url() + if mode == "text_dict": + textmode = "textPollux" + else: + textmode = mode + + textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn) + if highlightQuery is not None: + textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn) + + pagexml = self.getServerData("page-fragment.xql",textParam) + #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False) + + pagedom = Parse(pagexml) + # plain text mode + if mode == "text": + # first div contains text + pagedivs = pagedom.xpath("/div") + 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-'): + hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) + return serializeNode(pagenode) + if mode == "xml": + # first div contains text + pagedivs = pagedom.xpath("/div") + if len(pagedivs) > 0: + pagenode = pagedivs[0] + return serializeNode(pagenode) + if mode == "pureXml": + # 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();') + if href.startswith('#note-'): + hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn)) + return serializeNode(pagenode) + return "no text here" + + def getTranslate(self, query=None, language=None): + """translate into another languages""" + data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query))) + #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lex.xql","document=&language="+str(language)+"&query="+url_quote(str(query))) + return data + + def getLemma(self, lemma=None, language=None): + """simular words lemma """ + data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma))) + #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(lemma))) + return data + + def getLemmaNew(self, query=None, language=None): + """simular words lemma """ + data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query))) + #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query))) + return data + + 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.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn)) + #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/10)+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 mode == "none": + return docinfo + 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.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn)) + #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])) + docinfo['tocSize_%s'%mode] = tocSize + 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'] + path = docinfo['textURLPath'] + pagesize = pageinfo['tocPageSize'] + pn = pageinfo['tocPN'] + url = docinfo['url'] + selfurl = self.absolute_url() + viewMode= pageinfo['viewMode'] + tocMode = pageinfo['tocMode'] + tocPN = pageinfo['tocPN'] + + data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn)) + + page = data.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 + + def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None): + """change settings""" + self.title=title + self.timeout = timeout + self.serverUrl = serverUrl + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + +# management methods +def manage_addMpdlXmlTextServerForm(self): + """Form for adding""" + pt = PageTemplateFile("zpt/manage_addMpdlXmlTextServer", globals()).__of__(self) + return pt() + +def manage_addMpdlXmlTextServer(self,id,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None): + """add zogiimage""" + newObj = MpdlXmlTextServer(id,title,serverUrl,timeout) + self.Destination()._setObject(id, newObj) + if RESPONSE is not None: + RESPONSE.redirect('manage_main') + + + \ No newline at end of file
--- a/__init__.py Sun Dec 18 13:35:02 2005 +0100 +++ b/__init__.py Thu Jun 17 19:35:24 2010 +0200 @@ -1,5 +1,5 @@ import documentViewer - +import MpdlXmlTextServer def initialize(context): """initialize ImageCollection""" @@ -10,3 +10,20 @@ documentViewer.manage_AddDocumentViewer ) ) + + context.registerClass( + documentViewer.DocumentViewerTemplate, + constructors = ( + documentViewer.manage_addDocumentViewerTemplateForm, + documentViewer.manage_addDocumentViewerTemplate + ) + ) + + context.registerClass( + MpdlXmlTextServer.MpdlXmlTextServer, + constructors = ( + MpdlXmlTextServer.manage_addMpdlXmlTextServerForm, + MpdlXmlTextServer.manage_addMpdlXmlTextServer + ) + ) + \ No newline at end of file
--- a/documentViewer.py Sun Dec 18 13:35:02 2005 +0100 +++ b/documentViewer.py Thu Jun 17 19:35:24 2010 +0200 @@ -1,23 +1,38 @@ - -genericDigilib="http://nausikaa2.rz-berlin.mpg.de/digitallibrary/" from OFS.Folder import Folder from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate -from Products.PageTemplates.PageTemplateFile import PageTemplateFile +from Products.PageTemplates.PageTemplateFile import PageTemplateFile from AccessControl import ClassSecurityInfo +from AccessControl import getSecurityManager from Globals import package_home -from Ft.Xml.Domlette import NonvalidatingReader +from Ft.Xml import EMPTY_NAMESPACE, Parse from Ft.Xml.Domlette import PrettyPrint, Print -from Ft.Xml import EMPTY_NAMESPACE +import os.path +import sys +import urllib +import urllib2 +import logging +import math +import urlparse +import cStringIO -import Ft.Xml.XPath - -import os.path -import cgi -import urllib +def logger(txt,method,txt2): + """logging""" + logging.info(txt+ txt2) + + +def getInt(number, default=0): + """returns always an int (0 in case of problems)""" + try: + return int(number) + except: + return int(default) def getTextFromNode(nodename): + """get the cdata content of a node""" + if nodename is None: + return "" nodelist=nodename.childNodes rc = "" for node in nodelist: @@ -25,269 +40,740 @@ rc = rc + node.data return rc -import socket - -def urlopen(url): - """urlopen mit timeout""" - socket.setdefaulttimeout(2) - ret=urllib.urlopen(url) - socket.setdefaulttimeout(5) - return ret - -def getParamFromDigilib(path,param): - """gibt param von dlInfo aus""" - imageUrl=genericDigilib+"/dlInfo-xml.jsp?fn="+path +def serializeNode(node, encoding='utf-8'): + """returns a string containing node as XML""" + buf = cStringIO.StringIO() + Print(node, stream=buf, encoding=encoding) + s = buf.getvalue() + buf.close() + return s - try: - dom = NonvalidatingReader.parseUri(imageUrl) - except: - return None - - - params=dom.xpath("//document-parameters/parameter[@name='%s']/@value"%param) - - if params: - return params[0].value - -def parseUrlTextTool(url): - """parse index meta""" + +def getParentDir(path): + """returns pathname shortened by one""" + return '/'.join(path.split('/')[0:-1]) + + +def getHttpData(url, data=None, num_tries=3, timeout=10): + """returns result from url+data HTTP request""" + # we do GET (by appending data to url) + if isinstance(data, str) or isinstance(data, unicode): + # if data is string then append + url = "%s?%s"%(url,data) + elif isinstance(data, dict) or isinstance(data, list) or isinstance(data, tuple): + # urlencode + url = "%s?%s"%(url,urllib.urlencode(data)) - try: - dom = NonvalidatingReader.parseUri(url) - except: - zLOG.LOG("documentViewer (parseUrlTexttool)", zLOG.INFO,"%s (%s)"%sys.exc_info()[0:2]) - return (None,None,None) - - archivePaths=dom.xpath("//resource/archive-path") - - if archivePaths and (len(archivePaths)>0): - archivePath=getTextFromNode(archivePaths[0]) - else: - archivePath=None - + response = None + errmsg = None + for cnt in range(num_tries): + try: + logging.debug("getHttpData(#%s %ss) url=%s"%(cnt+1,timeout,url)) + if sys.version_info < (2, 6): + # set timeout on socket -- ugly :-( + import socket + socket.setdefaulttimeout(float(timeout)) + response = urllib2.urlopen(url) + else: + response = urllib2.urlopen(url,timeout=float(timeout)) + # check result? + break + except urllib2.HTTPError, 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)) + errmsg = str(e) + # stop trying + #break + + if response is not None: + data = response.read() + response.close() + return data - images=dom.xpath("//texttool/image") - - if images and (len(images)>0): - image=getTextFromNode(images[0]) - else: - image=None - - if image and archivePath: - image=os.path.join(archivePath,image) - image=image.replace("/mpiwg/online",'') - pt=getParamFromDigilib(image,'pt') - - else: - image=None - - viewerUrls=dom.xpath("//texttool/digiliburlprefix") - - if viewerUrls and (len(viewerUrls)>0): - viewerUrl=getTextFromNode(viewerUrls[0]) - else: - viewerUrl=None - - - textUrls=dom.xpath("//texttool/text") - - if textUrls and (len(textUrls)>0): - textUrl=getTextFromNode(textUrls[0]) - else: - textUrl=None - return viewerUrl,(image,pt),textUrl + raise IOError("ERROR fetching HTTP data from %s: %s"%(url,errmsg)) + #return None -class documentViewer(ZopePageTemplate): + +## +## documentViewer class +## +class documentViewer(Folder): """document viewer""" - meta_type="Document viewer" security=ClassSecurityInfo() - manage_options=ZopePageTemplate.manage_options+( + manage_options=Folder.manage_options+( {'label':'main config','action':'changeDocumentViewerForm'}, ) - _default_content_fn = os.path.join(package_home(globals()),'zpt','documentViewer_template.zpt') + # templates and forms + viewer_main = PageTemplateFile('zpt/viewer_main', globals()) + toc_thumbs = PageTemplateFile('zpt/toc_thumbs', globals()) + toc_text = PageTemplateFile('zpt/toc_text', globals()) + toc_figures = PageTemplateFile('zpt/toc_figures', globals()) + 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()) - def __init__(self,id,imageViewerUrl,title=""): + + 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=5,authgroups="mpiwg"): """init document viewer""" self.id=id self.title=title - self.imageViewerUrl=imageViewerUrl - - security.declareProtected('View management screens','changeDocumentViewerForm') - def changeDocumentViewerForm(self): - """change it""" - pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','changeDocumentViewer.zpt')).__of__(self) - return pt() - - - def changeDocumentViewer(self,imageViewerUrl,title="",RESPONSE=None): - """init document viewer""" - self.title=title - self.imageViewerUrl=imageViewerUrl + self.thumbcols = thumbcols + self.thumbrows = thumbrows + # authgroups is list of authorized groups (delimited by ,) + self.authgroups = [s.strip().lower() for s in authgroups.split(',')] + # create template folder so we can always use template.something - if RESPONSE is not None: - RESPONSE.redirect('manage_main') - - - def imageLink(self,nr): - """link hinter den images""" - paramsTmp=cgi.parse_qs(self.REQUEST['QUERY_STRING']) - params={} - for x in paramsTmp.iteritems(): - params[x[0]]=x[1][0] - - params['pn']=nr - newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params) - return newUrl + templateFolder = Folder('template') + #self['template'] = templateFolder # Zope-2.12 style + self._setObject('template',templateFolder) # old style + try: + import MpdlXmlTextServer + textServer = MpdlXmlTextServer.MpdlXmlTextServer(id='fulltextclient',serverName=textServerName) + #templateFolder['fulltextclient'] = xmlRpcClient + templateFolder._setObject('fulltextclient',textServer) + except Exception, e: + logging.error("Unable to create MpdlXmlTextServer for fulltextclient: "+str(e)) + try: + from Products.zogiLib.zogiLib import zogiLib + zogilib = zogiLib(id="zogilib", title="zogilib for docuviewer", dlServerURL=imageScalerUrl, layout="book") + #templateFolder['zogilib'] = zogilib + templateFolder._setObject('zogilib',zogilib) + except Exception, e: + logging.error("Unable to create zogiLib for zogilib: "+str(e)) - def thumbruler(self,cols,rows,start,maximum): - """ruler for thumbs""" - ret="" - paramsTmp=cgi.parse_qs(self.REQUEST['QUERY_STRING']) - params={} - for x in paramsTmp.iteritems(): + # proxy text server methods to fulltextclient + def getTextPage(self, **args): + """get page""" + return self.template.fulltextclient.getTextPage(**args) + + def getQuery(self, **args): + """get query""" + return self.template.fulltextclient.getQuery(**args) + + def getSearch(self, **args): + """get search""" + return self.template.fulltextclient.getSearch(**args) + + def getNumPages(self, **args): + """get numpages""" + return self.template.fulltextclient.getNumPages(**args) + + def getTranslate(self, **args): + """get translate""" + return self.template.fulltextclient.getTranslate(**args) + + def getLemma(self, **args): + """get lemma""" + return self.template.fulltextclient.getLemma(**args) + + def getToc(self, **args): + """get toc""" + return self.template.fulltextclient.getToc(**args) + + def getTocPage(self, **args): + """get tocpage""" + return self.template.fulltextclient.getTocPage(**args) - if not x[0]=="start": - params[x[0]]=x[1][0] - - newUrlSelect=self.REQUEST['URL']+"?"+urllib.urlencode(params) - if start>0: - newStart=max(start-cols*rows,0) - params['start']=newStart - newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params) - ret+="""<a href="%s">prev</a>"""%newUrl + + security.declareProtected('View','thumbs_rss') + def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): + ''' + 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 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)) + + if not hasattr(self, 'template'): + # create template folder if it doesn't exist + self.manage_addFolder('template') + + if not self.digilibBaseUrl: + 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) + pt = getattr(self.template, 'thumbs_main_rss') + + if viewMode=="auto": # automodus gewaehlt + if docinfo.has_key("textURL") or docinfo.has_key('textURLPath'): #texturl gesetzt und textViewer konfiguriert + viewMode="text" + else: + viewMode="images" + + 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): + ''' + 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 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)) + + if not hasattr(self, 'template'): + # this won't work + logging.error("template folder missing!") + return "ERROR: template folder missing!" + + if not getattr(self, 'digilibBaseUrl', None): + 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.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) + + pt = getattr(self.template, 'viewer_main') + return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode,mk=self.generateMarks(mk)) + + def generateMarks(self,mk): + ret="" + if mk is None: + return "" + if type(mk) is not ListType: + mk=[mk] + for m in mk: + ret+="mk=%s"%m + return ret - ret+="""<select onChange="location.href='%s&start='+this.options[this.selectedIndex].value" """%newUrlSelect - nr,rest=divmod(maximum,cols*rows) - if rest > 0: - nr+=1 - for i in range(nr): - nr=i*cols*rows - - if (start >= nr) and (start < nr+cols*rows): - ret+="""<option value="%s" selected>%s</option>"""%(nr,nr) + def findDigilibUrl(self): + """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.""" + #logger("documentViewer (getstyle)", logging.INFO, "idx: %s selected: %s style: %s"%(idx,selected,style)) + if idx == selected: + return style + 'sel' + else: + return style + + def getLink(self,param=None,val=None): + """link to documentviewer with parameter param set to val""" + params=self.REQUEST.form.copy() + if param is not None: + if val is None: + if params.has_key(param): + del params[param] else: - ret+="""<option value="%s">%s</option>"""%(nr,nr) - ret+="</select>" - - if start<maximum: - newStart=min(start+cols*rows,maximum) - params['start']=newStart - newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params) - ret+="""<a href="%s">next</a>"""%newUrl - - return ret + params[param] = str(val) + + if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath + params["mode"] = "imagepath" + 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()]) + url=self.REQUEST['URL1']+"?"+ps + return url + + def getLinkAmp(self,param=None,val=None): + """link to documentviewer with parameter param set to val""" + params=self.REQUEST.form.copy() + if param is not None: + if val is None: + if params.has_key(param): + del params[param] + else: + params[param] = str(val) + + # quote values and assemble into query string + 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 + + def getInfo_xml(self,url,mode): + """returns info about the document as XML""" + + if not self.digilibBaseUrl: + self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" - def textToolThumb(self,url,start=0): - """understands the texttool format - @param url: url to index.meta with texttool tag - """ - (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) - - imageUrl=genericDigilib+"/servlet/Scaler?fn=%s"%imagepath[0] - - pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','thumbs.zpt')).__of__(self) - return pt(imageUrl=imageUrl,pt=imagepath[1],start=start) + docinfo = self.getDocinfo(mode=mode,url=url) + pt = getattr(self.template, 'info_xml') + return pt(docinfo=docinfo) + - def text(self,mode,url,pn): - """give text""" - if mode=="texttool": #index.meta with texttool information - (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) + 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) + if access is not None and access == '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() + if user is not None: + #print "user: ", user + return (user.getUserName() != "Anonymous User") + else: + return False - print textpath - try: - dom = NonvalidatingReader.parseUri(textpath) - except: - return None + logging.debug("documentViewer (accessOK) unknown access type %s"%access) + return False - list=[] - nodes=dom.xpath("//pb") + + def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): + """gibt param von dlInfo aus""" + if docinfo is None: + docinfo = {} + + for x in range(cut): + + path=getParentDir(path) + + infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path + + logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) + + txt = getHttpData(infoUrl) + if txt is None: + raise IOError("Unable to get dir-info from %s"%(infoUrl)) - node=nodes[int(pn)-1] - - p=node + dom = Parse(txt) + sizes=dom.xpath("//dir/size") + logging.debug("documentViewer (getparamfromdigilib) dirInfo:size"%sizes) - while p.tagName!="p": - p=p.parentNode - - - endNode=nodes[int(pn)] - - - e=endNode + if sizes: + docinfo['numPages'] = int(getTextFromNode(sizes[0])) + else: + docinfo['numPages'] = 0 + + # TODO: produce and keep list of image names and numbers + + return docinfo + + + def getIndexMeta(self, url): + """returns dom of index.meta document at url""" + dom = None + metaUrl = None + if url.startswith("http://"): + # real URL + metaUrl = url + else: + # online path + server=self.digilibBaseUrl+"/servlet/Texter?fn=" + metaUrl=server+url.replace("/mpiwg/online","") + if not metaUrl.endswith("index.meta"): + metaUrl += "/index.meta" + + logging.debug("(getIndexMeta): METAURL: %s"%metaUrl) + txt=getHttpData(metaUrl) + if txt is None: + raise IOError("Unable to read index meta from %s"%(url)) - while e.tagName!="p": - e=e.parentNode - - - next=node.parentNode + dom = Parse(txt) + return dom + + def getPresentationInfoXML(self, url): + """returns dom of info.xml document at url""" + dom = None + metaUrl = None + if url.startswith("http://"): + # real URL + metaUrl = url + else: + # online path + server=self.digilibBaseUrl+"/servlet/Texter?fn=" + metaUrl=server+url.replace("/mpiwg/online","") - #sammle s - while next and (next!=endNode.parentNode): - list.append(next) - next=next.nextSibling - list.append(endNode.parentNode) + txt=getHttpData(metaUrl) + if txt is None: + raise IOError("Unable to read infoXMLfrom %s"%(url)) + + dom = Parse(txt) + return dom + - if p==e:# beide im selben paragraphen + 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)) + + access = None - else: - next=p - while next!=e: - print next,e - list.append(next) - next=next.nextSibling + if docinfo is None: + docinfo = {} - for x in list: - PrettyPrint(x) - - return list + if dom is None: + for x in range(cut): + path=getParentDir(path) + dom = self.getIndexMeta(path) + + acctype = dom.xpath("//access-conditions/access/@type") + if acctype and (len(acctype)>0): + access=acctype[0].value + if access in ['group', 'institution']: + access = getTextFromNode(dom.xpath("//access-conditions/access/name")[0]).lower() + + docinfo['accessType'] = access + return docinfo - def image(self,mode,url,pn): - """give image out""" - if mode=="texttool": #index.meta with texttool information - (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) - url=viewerUrl+"pn=%s&fn=%s"%(pn,imagepath[0]) - ret="""<iframe height="100%%" width="100%%" src="%s"/>"""%url - return url + + 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)) + + if docinfo is None: + docinfo = {} + + if dom is None: + for x in range(cut): + path=getParentDir(path) + dom = self.getIndexMeta(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: + bibinfo = {} + for e in bib: + bibinfo[e.localName] = getTextFromNode(e) + docinfo['bib'] = bibinfo - def thumbs(self,mode,url,start): - """give thumbs out""" - if mode=="texttool": #index.meta with texttool information - return self.textToolThumb(url,int(start)) - - security.declareProtected('View','index_html') + # extract some fields (author, title, year) according to their mapping + metaData=self.metadata.main.meta.bib + bibtype=dom.xpath("//bib/@type") + if bibtype and (len(bibtype)>0): + bibtype=bibtype[0].value + else: + bibtype="generic" + + bibtype=bibtype.replace("-"," ") # wrong typesiin index meta "-" instead of " " (not wrong! ROC) + docinfo['bib_type'] = bibtype + bibmap=metaData.generateMappingForType(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: + docinfo['author']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['author'][0])[0]) + except: pass + try: + docinfo['title']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['title'][0])[0]) + except: pass + try: + docinfo['year']=getTextFromNode(dom.xpath("//bib/%s"%bibmap['year'][0])[0]) + except: pass + logging.debug("documentViewer (getbibinfofromindexmeta) using mapping for %s"%bibtype) + try: + docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) + except: + docinfo['lang']='' + + return docinfo - def index_html(self,mode,url,start=0,pn=0): - ''' - view it - @param mode: defines which type of document is behind url - @param url: url which contains display information - ''' + def getDocinfoFromTextTool(self, url, dom=None, docinfo=None): + """parse texttool tag in index meta""" + 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) + + archivePath = None + archiveName = None + + archiveNames = dom.xpath("//resource/name") + if archiveNames and (len(archiveNames) > 0): + archiveName = getTextFromNode(archiveNames[0]) + else: + logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) + + archivePaths = dom.xpath("//resource/archive-path") + if archivePaths and (len(archivePaths) > 0): + archivePath = getTextFromNode(archivePaths[0]) + # clean up archive path + if archivePath[0] != '/': + archivePath = '/' + archivePath + if archiveName and (not archivePath.endswith(archiveName)): + archivePath += "/" + archiveName + else: + # try to get archive-path from url + logging.warning("documentViewer (getdocinfofromtexttool) resource/archive-path missing in: %s" % (url)) + if (not url.startswith('http')): + archivePath = url.replace('index.meta', '') + + if archivePath is None: + # we balk without archive-path + raise IOError("Missing archive-path (for text-tool) in %s" % (url)) + imageDirs = dom.xpath("//texttool/image") + if imageDirs and (len(imageDirs) > 0): + imageDir = getTextFromNode(imageDirs[0]) + + else: + # we balk with no image tag / not necessary anymore because textmode is now standard + #raise IOError("No text-tool info in %s"%(url)) + imageDir = "" + #xquery="//pb" + docinfo['imagePath'] = "" # keine Bilder + docinfo['imageURL'] = "" + + if imageDir and archivePath: + #print "image: ", imageDir, " archivepath: ", archivePath + imageDir = os.path.join(archivePath, imageDir) + imageDir = imageDir.replace("/mpiwg/online", '') + docinfo = self.getDirinfoFromDigilib(imageDir, docinfo=docinfo) + docinfo['imagePath'] = imageDir + + docinfo['imageURL'] = self.digilibBaseUrl + "/servlet/Scaler?fn=" + imageDir + + viewerUrls = dom.xpath("//texttool/digiliburlprefix") + 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]) + if urlparse.urlparse(textUrl)[0] == "": #keine url + textUrl = os.path.join(archivePath, textUrl) + # fix URLs starting with /mpiwg/online + if textUrl.startswith("/mpiwg/online"): + textUrl = textUrl.replace("/mpiwg/online", '', 1) + + 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 + + presentationUrls = dom.xpath("//texttool/presentation") + docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag + + 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 + # durch den relativen Pfad auf die presentation infos + presentationPath = getTextFromNode(presentationUrls[0]) + if url.endswith("index.meta"): + presentationUrl = url.replace('index.meta', presentationPath) + else: + presentationUrl = url + "/" + presentationPath + + docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) - pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','documentViewer_template.zpt')).__of__(self) - return pt(mode=mode,url=url,start=start,pn=pn) + docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info + return docinfo + + + def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): + """gets the bibliographical information from the preseantion entry in texttools + """ + dom=self.getPresentationInfoXML(url) + try: + docinfo['author']=getTextFromNode(dom.xpath("//author")[0]) + except: + pass + try: + docinfo['title']=getTextFromNode(dom.xpath("//title")[0]) + except: + pass + try: + docinfo['year']=getTextFromNode(dom.xpath("//date")[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)) + if docinfo is None: + docinfo = {} + path=path.replace("/mpiwg/online","") + docinfo['imagePath'] = path + docinfo=self.getDirinfoFromDigilib(path,docinfo=docinfo,cut=cut) + + pathorig=path + for x in range(cut): + path=getParentDir(path) + logging.debug("documentViewer (getdocinfofromimagepath) PATH:"+path) + imageUrl=self.digilibBaseUrl+"/servlet/Scaler?fn="+path + docinfo['imageURL'] = imageUrl + #path ist the path to the images it assumes that the index.meta file is one level higher. + docinfo = self.getBibinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) + docinfo = self.getAuthinfoFromIndexMeta(pathorig,docinfo=docinfo,cut=cut+1) + return docinfo + + + def getDocinfo(self, mode, url): + """returns docinfo depending on mode""" + 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) + return docinfo + # new docinfo + docinfo = {'mode': mode, 'url': url} + if mode=="texttool": #index.meta with texttool information + docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) + elif mode=="imagepath": + docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) + elif mode=="filepath": + docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo,cut=1) + else: + 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) + 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 = {} + current = getInt(current) + pageinfo['current'] = current + rows = int(rows or self.thumbrows) + pageinfo['rows'] = rows + cols = int(cols or self.thumbcols) + pageinfo['cols'] = cols + grpsize = cols * rows + pageinfo['groupsize'] = grpsize + start = getInt(start, default=(math.ceil(float(current)/float(grpsize))*grpsize-(grpsize-1))) + # int(current / grpsize) * grpsize +1)) + pageinfo['start'] = start + pageinfo['end'] = start + grpsize + if (docinfo is not None) and ('numPages' in docinfo): + np = int(docinfo['numPages']) + pageinfo['end'] = min(pageinfo['end'], np) + pageinfo['numgroups'] = int(np / grpsize) + if np % grpsize > 0: + 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', '10') + pageinfo['tocPN'] = self.REQUEST.get('tocPN', '1') + toc = int (pageinfo['tocPN']) + pageinfo['textPages'] =int (toc) -# security.declareProtected('View management screens','renameImageForm') - + 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 changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=5,authgroups='mpiwg',RESPONSE=None): + """init document viewer""" + self.title=title + self.digilibBaseUrl = digilibBaseUrl + self.thumbrows = thumbrows + self.thumbcols = thumbcols + 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""" - pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','addDocumentViewer.zpt')).__of__(self) + pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) return pt() -def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None): +def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): """add the viewer""" - newObj=documentViewer(id,imageViewerUrl,title) + newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) self._setObject(id,newObj) if RESPONSE is not None: RESPONSE.redirect('manage_main') - \ No newline at end of file + +## DocumentViewerTemplate class +class DocumentViewerTemplate(ZopePageTemplate): + """Template for document viewer""" + meta_type="DocumentViewer Template" + + +def manage_addDocumentViewerTemplateForm(self): + """Form for adding""" + pt=PageTemplateFile('zpt/addDocumentViewerTemplate', globals()).__of__(self) + return pt() + +def manage_addDocumentViewerTemplate(self, id='viewer_main', title=None, text=None, + REQUEST=None, submit=None): + "Add a Page Template with optional file content." + + 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) + ob.pt_edit(txt,"text/html") + if title: + ob.pt_setTitle(title) + try: + u = self.DestinationURL() + except AttributeError: + u = REQUEST['URL1'] + + u = "%s/%s" % (u, urllib.quote(id)) + REQUEST.RESPONSE.redirect(u+'/manage_main') + return '' + + +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/version.txt Thu Jun 17 19:35:24 2010 +0200 @@ -0,0 +1,1 @@ +DocumentViewer 0.5.1 \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/zpt/manage_addMpdlXmlTextServer.zpt Thu Jun 17 19:35:24 2010 +0200 @@ -0,0 +1,11 @@ +<h1 tal:replace="structure here/manage_page_header">Header</h1> + <h2>Add an MPDL-XML TextServer</h2> + <form action="manage_addMpdlXmlTextServer"> + <p class="form-label">Id<input name="id"></p> + <p class="form-optional">Title<input size="80" name="title"></p> + <p class="form-label">Text Server URL<input size="80" name="serverUrl" value="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/"></p> + <p class="form-optional">Timeout (s)<input size="10" name="timeout" value="30"></p> + <p><input type="submit" value="add"></p> + </form> + +<h1 tal:replace="structure here/manage_page_footer">Footer</h1>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/zpt/manage_changeMpdlXmlTextServer.zpt Thu Jun 17 19:35:24 2010 +0200 @@ -0,0 +1,17 @@ +<div tal:replace="structure here/manage_page_header">Header</div> +<!-- ZOPE management tabs --> +<h2 tal:define="manage_tabs_message options/manage_tabs_message | nothing" + tal:replace="structure here/manage_tabs">Tabs</h2> +<!-- end of ZOPE management tabs --> + <form action="manage_changeMpdlXmlTextServer"> + + <p class="form-optional">Title</p> + <p class="form-element"><input size="80" tal:attributes="value here/title" name="title"></p> + <p class="form-optional">Text Server URL</p> + <p class="form-element"><input size="80" tal:attributes="value here/serverUrl | default" name="serverUrl"></p> + <p class="form-optional">Timeout (s)</p> + <p class="form-element"><input size="3" tal:attributes="value here/timeout | default" name="timeout"></p> + <p><input type="submit" value="change"></p> + </form> + +<div tal:replace="structure here/manage_page_footer">Footer</div>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/zpt/page_main_pureXml.zpt Thu Jun 17 19:35:24 2010 +0200 @@ -0,0 +1,4 @@ + +<tal:block tal:define="pageinfo python:options.get('pageinfo',None); docinfo python:options.get('docinfo',None) "> + <div tal:content="structure python:here.getTextPage(mode='pureXml',pn=pageinfo['current'],docinfo=docinfo, pageinfo=pageinfo)"></div> +</tal:block> \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/zpt/page_main_text.zpt Thu Jun 17 19:35:24 2010 +0200 @@ -0,0 +1,16 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" + "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> +<html xmlns="http://www.w3.org/1999/xhtml"> +<head> + <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> + <!-- block used for definitions and scripts in head --> + <metal:block metal:define-macro="head"> + </metal:block> +</head> +<body> + <!-- block used for main content area --> + <metal:block metal:define-macro="main" tal:define="pageinfo python:options.get('pageinfo',None); docinfo python:options.get('docinfo',None) ;highlightQuery python:pageinfo.get('highlightQuery','');sn python:pageinfo.get('sn','')"> + <div tal:content="structure python:here.getTextPage(mode='text',pn=pageinfo['current'],docinfo=docinfo, highlightQuery=highlightQuery, sn=sn, pageinfo=pageinfo)"></div> + </metal:block> +</body> +</html>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/zpt/page_main_text_dict.zpt Thu Jun 17 19:35:24 2010 +0200 @@ -0,0 +1,16 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" + "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> +<html xmlns="http://www.w3.org/1999/xhtml"> +<head> + <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> + <!-- block used for definitions and scripts in head --> + <metal:block metal:define-macro="head"> + </metal:block> +</head> +<body> + <!-- block used for main content area --> + <metal:block metal:define-macro="main" tal:define="pageinfo options/pageinfo; docinfo options/docinfo; highlightQuery pageinfo/highlightQuery|nothing; sn pageinfo/sn|nothing"> + <div tal:content="structure python:here.getTextPage(mode='text_dict',pn=pageinfo['current'],docinfo=docinfo,highlightQuery=highlightQuery,sn=sn,pageinfo=pageinfo)"/> + </metal:block> +</body> +</html>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/zpt/viewer_main.zpt Thu Jun 17 19:35:24 2010 +0200 @@ -0,0 +1,32 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" + "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> +<html xmlns="http://www.w3.org/1999/xhtml" + tal:define="docinfo options/docinfo; pageinfo options/pageinfo; global viewMode pageinfo/viewMode; tocMode pageinfo/tocMode; + body_onload nothing"> +<head> + <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> + <link rel="stylesheet" href="template/docuviewer_css" type="text/css"> + <metal:block metal:use-macro="python:path('here/template/page_main_%s/macros/head'%viewMode)"/> +</head> +<body tal:condition="docinfo/numPages" tal:attributes="onload body_onload"> + <metal:block metal:use-macro="here/template/head_main/macros/main"/> + <tal:block tal:condition="python:here.isAccessible(docinfo)"> + <table border="0" width="100%" height="100%"> + <tr> + <td width="300px" valign="top"> + <metal:block metal:use-macro="python:path('here/template/toc_%s/macros/main'%tocMode)"/> + </td> + <td width="100%" valign="top"> + <metal:block metal:use-macro="python:path('here/template/page_main_%s/macros/main'%viewMode)"/> + </td> + </tr> + </table> + </tal:block> + <tal:block tal:condition="not:python:here.isAccessible(docinfo)"> + <div class="errortext">Sorry, access to this document is restricted.</div> + </tal:block> +</body> +<body tal:condition="not:docinfo/numPages"> +<div class="errortext">Sorry, document doesn't exist.</div> +</body> +</html>