|
|
| version 1.42, 2010/03/08 15:02:33 | version 1.43, 2010/03/19 11:42:40 |
|---|---|
| Line 12 from Ft.Xml import EMPTY_NAMESPACE, Pars | Line 12 from Ft.Xml import EMPTY_NAMESPACE, Pars |
| import Ft.Xml.XPath | import Ft.Xml.XPath |
| import cStringIO | |
| import xmlrpclib | import xmlrpclib |
| import os.path | import os.path |
| import sys | import sys |
| Line 22 import math | Line 23 import math |
| import urlparse | import urlparse |
| from types import * | from types import * |
| def logger(txt,method,txt2): | def logger(txt,method,txt2): |
| """logging""" | """logging""" |
| logging.info(txt+ txt2) | logging.info(txt+ txt2) |
| Line 45 def getTextFromNode(nodename): | Line 47 def getTextFromNode(nodename): |
| rc = rc + node.data | rc = rc + node.data |
| return rc | return rc |
| 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 | |
| def getParentDir(path): | def getParentDir(path): |
| """returns pathname shortened by one""" | """returns pathname shortened by one""" |
| Line 78 class documentViewer(Folder): | Line 88 class documentViewer(Folder): |
| # templates and forms | # templates and forms |
| viewer_main = PageTemplateFile('zpt/viewer_main', globals()) | viewer_main = PageTemplateFile('zpt/viewer_main', globals()) |
| thumbs_main = PageTemplateFile('zpt/thumbs_main', globals()) | thumbs_main = PageTemplateFile('zpt/thumbs_main', globals()) |
| image_main = PageTemplateFile('zpt/image_main', globals()) | image_main = PageTemplateFile('zpt/image_main', globals()) # obsolete! |
| page_main_images = PageTemplateFile('zpt/page_main_images', globals()) | |
| page_main_text = PageTemplateFile('zpt/page_main_text', globals()) | |
| head_main = PageTemplateFile('zpt/head_main', globals()) | head_main = PageTemplateFile('zpt/head_main', globals()) |
| docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) |
| info_xml = PageTemplateFile('zpt/info_xml', globals()) | info_xml = PageTemplateFile('zpt/info_xml', globals()) |
| Line 88 class documentViewer(Folder): | Line 100 class documentViewer(Folder): |
| changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) |
| def __init__(self,id,imageViewerUrl,textViewerUrl=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): | def __init__(self,id,imageScalerUrl=None,textServerName=None,title="",digilibBaseUrl=None,thumbcols=2,thumbrows=10,authgroups="mpiwg"): |
| """init document viewer""" | """init document viewer""" |
| self.id=id | self.id=id |
| self.title=title | self.title=title |
| self.imageViewerUrl=imageViewerUrl | |
| self.textViewerUrl=textViewerUrl | |
| if not digilibBaseUrl: | |
| self.digilibBaseUrl = self.findDigilibUrl() | |
| else: | |
| self.digilibBaseUrl = digilibBaseUrl | |
| self.thumbcols = thumbcols | self.thumbcols = thumbcols |
| self.thumbrows = thumbrows | self.thumbrows = thumbrows |
| # authgroups is list of authorized groups (delimited by ,) | # authgroups is list of authorized groups (delimited by ,) |
| self.authgroups = [s.strip().lower() for s in authgroups.split(',')] | self.authgroups = [s.strip().lower() for s in authgroups.split(',')] |
| # add template folder so we can always use template.something | # create template folder so we can always use template.something |
| self.manage_addFolder('template') | |
| templateFolder = Folder('template') | |
| #self['template'] = templateFolder # Zope-2.12 style | |
| self._setObject('template',templateFolder) # old style | |
| try: | |
| from Products.XMLRpcTools.XMLRpcTools import XMLRpcServerProxy | |
| xmlRpcClient = XMLRpcServerProxy(id='fulltextclient', serverUrl=textServerName, use_xmlrpc=False) | |
| #templateFolder['fulltextclient'] = xmlRpcClient | |
| templateFolder._setObject('fulltextclient',xmlRpcClient) | |
| except Exception, e: | |
| logging.error("Unable to create XMLRpcTools 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)) | |
| security.declareProtected('View','thumbs_rss') | security.declareProtected('View','thumbs_rss') |
| Line 116 class documentViewer(Folder): | Line 138 class documentViewer(Folder): |
| @param viewMode: if images display images, if text display text, default is images (text,images or auto) | @param viewMode: if images display images, if text display text, default is images (text,images or auto) |
| ''' | ''' |
| logging.info("HHHHHHHHHHHHHH:load the rss") | logging.debug("HHHHHHHHHHHHHH:load the rss") |
| logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) | logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
| if not hasattr(self, 'template'): | if not hasattr(self, 'template'): |
| Line 139 class documentViewer(Folder): | Line 161 class documentViewer(Folder): |
| return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
| security.declareProtected('View','index_html') | security.declareProtected('View','index_html') |
| def index_html(self,mode,url,viewMode="auto",start=None,pn=1,mk=None): | def index_html(self,url,mode="texttool",viewMode="auto",start=None,pn=1,mk=None): |
| ''' | ''' |
| view it | view it |
| @param mode: defines how to access the document behind url | @param mode: defines how to access the document behind url |
| Line 148 class documentViewer(Folder): | Line 170 class documentViewer(Folder): |
| ''' | ''' |
| logger("documentViewer (index)", logging.INFO, "mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) | logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
| if not hasattr(self, 'template'): | if not hasattr(self, 'template'): |
| # create template folder if it doesn't exist | # this won't work |
| self.manage_addFolder('template') | logging.error("template folder missing!") |
| return "ERROR: template folder missing!" | |
| if not self.digilibBaseUrl: | if not getattr(self, 'digilibBaseUrl', None): |
| self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" | self.digilibBaseUrl = self.findDigilibUrl() or "http://nausikaa.mpiwg-berlin.mpg.de/digitallibrary" |
| docinfo = self.getDocinfo(mode=mode,url=url) | docinfo = self.getDocinfo(mode=mode,url=url) |
| Line 162 class documentViewer(Folder): | Line 185 class documentViewer(Folder): |
| pt = getattr(self.template, 'viewer_main') | pt = getattr(self.template, 'viewer_main') |
| if viewMode=="auto": # automodus gewaehlt | if viewMode=="auto": # automodus gewaehlt |
| if docinfo.get("textURL",'') and self.textViewerUrl: #texturl gesetzt und textViewer konfiguriert | if docinfo.get("textURL",''): #texturl gesetzt und textViewer konfiguriert |
| viewMode="text" | viewMode="text" |
| else: | else: |
| viewMode="images" | viewMode="images" |
| Line 180 class documentViewer(Folder): | Line 203 class documentViewer(Folder): |
| ret+="mk=%s"%m | ret+="mk=%s"%m |
| return ret | return ret |
| def findDigilibUrl(self): | |
| """try to get the digilib URL from zogilib""" | |
| url = self.template.zogilib.getDLBaseUrl() | |
| return 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): | def getLink(self,param=None,val=None): |
| """link to documentviewer with parameter param set to val""" | """link to documentviewer with parameter param set to val""" |
| params=self.REQUEST.form.copy() | params=self.REQUEST.form.copy() |
| Line 189 class documentViewer(Folder): | Line 225 class documentViewer(Folder): |
| del params[param] | del params[param] |
| else: | else: |
| params[param] = str(val) | params[param] = str(val) |
| if params["mode"] == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath | |
| if params.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath | |
| params["mode"] = "imagepath" | params["mode"] = "imagepath" |
| params["url"] = getParentDir(params["url"]) | params["url"] = getParentDir(params["url"]) |
| Line 225 class documentViewer(Folder): | Line 262 class documentViewer(Folder): |
| return pt(docinfo=docinfo) | return pt(docinfo=docinfo) |
| 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 getTextLanguage(self,url,docinfo): | |
| docinfo['lang']=getTextFromNode(dom.xpath("//bib/lang")[0]) | |
| lang = urlencode({'':docinfo['lang']}) | |
| return lang | |
| def isAccessible(self, docinfo): | def isAccessible(self, docinfo): |
| """returns if access to the resource is granted""" | """returns if access to the resource is granted""" |
| access = docinfo.get('accessType', None) | access = docinfo.get('accessType', None) |
| Line 292 class documentViewer(Folder): | Line 315 class documentViewer(Folder): |
| else: | else: |
| docinfo['numPages'] = 0 | docinfo['numPages'] = 0 |
| # TODO: produce and keep list of image names and numbers | |
| return docinfo | return docinfo |
| Line 431 class documentViewer(Folder): | Line 456 class documentViewer(Folder): |
| return docinfo | return docinfo |
| def getNumPages(self, xquery, docinfo=None): #New Method 24.02.2010 | |
| text=self.viewerTemplates.query.eval("/mpdl/interface/xquery.xql","document="+ docinfo['textURLPath'] +"&xquery="+str(xquery)) | |
| docinfo['numPages'] = text.count("<pb ") | |
| return docinfo | |
| def getDocinfoFromTextTool(self,url,dom=None,docinfo=None): | def getDocinfoFromTextTool(self,url,dom=None,docinfo=None): |
| """parse texttool tag in index meta""" | """parse texttool tag in index meta""" |
| logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url)) | logger("documentViewer (getdocinfofromtexttool)", logging.INFO,"url: %s"%(url)) |
| Line 528 class documentViewer(Folder): | Line 547 class documentViewer(Folder): |
| presentationUrl=url.replace('index.meta',presentationPath) | presentationUrl=url.replace('index.meta',presentationPath) |
| else: | else: |
| presentationUrl=url + "/" + presentationPath | presentationUrl=url + "/" + presentationPath |
| docinfo=self.getNumPages('//pb', docinfo) #im moment einfach auf eins setzen, navigation ueber die thumbs geht natuerlich nicht | 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.getBibinfoFromTextToolPresentation(presentationUrl,docinfo=docinfo,dom=dom) |
| docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info | docinfo = self.getAuthinfoFromIndexMeta(url,docinfo=docinfo,dom=dom) # get access info |
| Line 536 class documentViewer(Folder): | Line 555 class documentViewer(Folder): |
| return docinfo | return docinfo |
| def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): | def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
| """gets the bibliographical information from the preseantion entry in texttools | """gets the bibliographical information from the preseantion entry in texttools |
| """ | """ |
| Line 619 class documentViewer(Folder): | Line 641 class documentViewer(Folder): |
| pageinfo['start'] = start | pageinfo['start'] = start |
| pageinfo['end'] = start + grpsize | pageinfo['end'] = start + grpsize |
| if docinfo is not None: | if docinfo is not None: |
| np = int(docinfo['numPages']) | np = int(docinfo['numPages']) |
| pageinfo['end'] = min(pageinfo['end'], np) | pageinfo['end'] = min(pageinfo['end'], np) |
| pageinfo['numgroups'] = int(np / grpsize) | pageinfo['numgroups'] = int(np / grpsize) |
| Line 628 class documentViewer(Folder): | Line 649 class documentViewer(Folder): |
| return pageinfo | return pageinfo |
| def text(self,mode,url,pn): | |
| """give text""" | |
| if mode=="texttool": #index.meta with texttool information | |
| (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) | |
| #print textpath | |
| try: | |
| dom = NonvalidatingReader.parseUri(textpath) | |
| except: | |
| return None | |
| list=[] | |
| nodes=dom.xpath("//pb") | |
| node=nodes[int(pn)-1] | |
| p=node | |
| while p.tagName!="p": | |
| p=p.parentNode | |
| 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("<pb ") | |
| return docinfo | |
| endNode=nodes[int(pn)] | def getTextPage(self, mode="text", pn=1, docinfo=None): |
| """returns single page from fulltext""" | |
| pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", "document=%s&mode=%s&pn=%s"%(docinfo['textURLPath'],mode,pn), outputUnicode=False) | |
| e=endNode | # post-processing downloaded xml |
| pagedom = Parse(pagexml) | |
| while e.tagName!="p": | # plain text mode |
| e=e.parentNode | if mode == "text": |
| # first div contains text | |
| pagedivs = pagedom.xpath("/div") | |
| next=node.parentNode | if len(pagedivs) > 0: |
| pagenode = pagedivs[0] | |
| #sammle s | return serializeNode(pagenode) |
| while next and (next!=endNode.parentNode): | |
| list.append(next) | # text-with-links mode |
| next=next.nextSibling | if mode == "textPollux": |
| list.append(endNode.parentNode) | # first div contains text |
| pagedivs = pagedom.xpath("/div") | |
| if p==e:# beide im selben paragraphen | if len(pagedivs) > 0: |
| pass | pagenode = pagedivs[0] |
| # else: | # check all a-tags |
| # next=p | links = pagenode.xpath("//a") |
| # while next!=e: | for l in links: |
| # print next,e | hrefNode = l.getAttributeNodeNS(None, u"href") |
| # list.append(next) | if hrefNode: |
| # next=next.nextSibling | # is link with href |
| # | href = hrefNode.nodeValue |
| # for x in list: | if href.startswith('lt/lex.xql'): |
| # PrettyPrint(x) | # is pollux link |
| # | selfurl = self.absolute_url() |
| # return list | # change href |
| # | hrefNode.nodeValue = href.replace('lt/lex.xql','%s/head_main_voc'%selfurl) |
| # add target | |
| def findDigilibUrl(self): | l.setAttributeNS(None, 'target', '_blank') |
| """try to get the digilib URL from zogilib""" | return serializeNode(pagenode) |
| url = self.imageViewerUrl[:-1] + "/getScalerUrl" | |
| #print urlparse.urlparse(url)[0] | |
| #print urlparse.urljoin(self.absolute_url(),url) | |
| logging.info("finddigiliburl: %s"%urlparse.urlparse(url)[0]) | |
| logging.info("finddigiliburl: %s"%urlparse.urljoin(self.absolute_url(),url)) | |
| try: | return "no text here" |
| if urlparse.urlparse(url)[0]=='': #relative path | |
| url=urlparse.urljoin(self.absolute_url()+"/",url) | |
| scaler = urlopen(url).read() | |
| return scaler.replace("/servlet/Scaler?", "") | |
| except: | |
| return None | |
| def changeDocumentViewer(self,imageViewerUrl,textViewerUrl,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): | def changeDocumentViewer(self,title="",digilibBaseUrl=None,thumbrows=2,thumbcols=10,authgroups='mpiwg',RESPONSE=None): |
| """init document viewer""" | """init document viewer""" |
| self.title=title | self.title=title |
| self.imageViewerUrl=imageViewerUrl | |
| self.textViewerUrl=textViewerUrl | |
| self.digilibBaseUrl = digilibBaseUrl | self.digilibBaseUrl = digilibBaseUrl |
| self.thumbrows = thumbrows | self.thumbrows = thumbrows |
| self.thumbcols = thumbcols | self.thumbcols = thumbcols |
| Line 713 class documentViewer(Folder): | Line 709 class documentViewer(Folder): |
| # security.declareProtected('View management screens','renameImageForm') | |
| def manage_AddDocumentViewerForm(self): | def manage_AddDocumentViewerForm(self): |
| """add the viewer form""" | """add the viewer form""" |
| pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) | pt=PageTemplateFile('zpt/addDocumentViewer', globals()).__of__(self) |
| return pt() | return pt() |
| def manage_AddDocumentViewer(self,id,imageViewerUrl="",textViewerUrl="",title="",RESPONSE=None): | def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
| """add the viewer""" | """add the viewer""" |
| newObj=documentViewer(id,imageViewerUrl,title=title,textViewerUrl=textViewerUrl) | newObj=documentViewer(id,imageScalerUrl=imageScalerUrl,title=title,textServerName=textServerName) |
| self._setObject(id,newObj) | self._setObject(id,newObj) |
| if RESPONSE is not None: | if RESPONSE is not None: |