|
|
| version 1.1, 2005/12/18 12:35:02 | version 1.175.2.9, 2011/07/27 19:09:44 |
|---|---|
| Line 1 | Line 1 |
| genericDigilib="http://nausikaa2.rz-berlin.mpg.de/digitallibrary/" | |
| from OFS.Folder import Folder | from OFS.Folder import Folder |
| from Products.PageTemplates.ZopePageTemplate import ZopePageTemplate | 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 ClassSecurityInfo |
| from AccessControl import getSecurityManager | |
| from Globals import package_home | 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 | #import Ft.Xml.Domlette |
| from Ft.Xml import EMPTY_NAMESPACE | |
| import Ft.Xml.XPath | import xml.etree.ElementTree as ET |
| import os.path | import os.path |
| import cgi | import sys |
| import urllib | import urllib |
| import logging | |
| import math | |
| import urlparse | |
| import re | |
| import string | |
| from SrvTxtUtils import getInt, getText, getHttpData | |
| def logger(txt,method,txt2): | |
| """logging""" | |
| logging.info(txt+ txt2) | |
| def serializeNode(node, encoding="utf-8"): | |
| """returns a string containing node as XML""" | |
| s = ET.tostring(node) | |
| # 4Suite: | |
| # stream = cStringIO.StringIO() | |
| # Ft.Xml.Domlette.Print(node, stream=stream, encoding=encoding) | |
| # s = stream.getvalue() | |
| # stream.close() | |
| return s | |
| def browserCheck(self): | |
| """check the browsers request to find out the browser type""" | |
| bt = {} | |
| ua = self.REQUEST.get_header("HTTP_USER_AGENT") | |
| bt['ua'] = ua | |
| bt['isIE'] = False | |
| bt['isN4'] = False | |
| bt['versFirefox']="" | |
| bt['versIE']="" | |
| bt['versSafariChrome']="" | |
| bt['versOpera']="" | |
| def getTextFromNode(nodename): | if string.find(ua, 'MSIE') > -1: |
| nodelist=nodename.childNodes | bt['isIE'] = True |
| rc = "" | else: |
| for node in nodelist: | bt['isN4'] = (string.find(ua, 'Mozilla/4.') > -1) |
| if node.nodeType == node.TEXT_NODE: | # Safari oder Chrome identification |
| 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 | |
| try: | try: |
| dom = NonvalidatingReader.parseUri(imageUrl) | nav = ua[string.find(ua, '('):] |
| except: | nav1=ua[string.find(ua,')'):] |
| return None | nav2=nav1[string.find(nav1,'('):] |
| nav3=nav2[string.find(nav2,')'):] | |
| ie = string.split(nav, "; ")[1] | |
| params=dom.xpath("//document-parameters/parameter[@name='%s']/@value"%param) | ie1 =string.split(nav1, " ")[2] |
| ie2 =string.split(nav3, " ")[1] | |
| ie3 =string.split(nav3, " ")[2] | |
| if string.find(ie3, "Safari") >-1: | |
| bt['versSafariChrome']=string.split(ie2, "/")[1] | |
| except: pass | |
| # IE identification | |
| try: | |
| nav = ua[string.find(ua, '('):] | |
| ie = string.split(nav, "; ")[1] | |
| if string.find(ie, "MSIE") > -1: | |
| bt['versIE'] = string.split(ie, " ")[1] | |
| except:pass | |
| # Firefox identification | |
| try: | |
| nav = ua[string.find(ua, '('):] | |
| nav1=ua[string.find(ua,')'):] | |
| if string.find(ie1, "Firefox") >-1: | |
| nav5= string.split(ie1, "/")[1] | |
| logging.debug("FIREFOX: %s"%(nav5)) | |
| bt['versFirefox']=nav5[0:3] | |
| except:pass | |
| #Opera identification | |
| try: | |
| if string.find(ua,"Opera") >-1: | |
| nav = ua[string.find(ua, '('):] | |
| nav1=nav[string.find(nav,')'):] | |
| bt['versOpera']=string.split(nav1,"/")[2] | |
| except:pass | |
| bt['isMac'] = string.find(ua, 'Macintosh') > -1 | |
| bt['isWin'] = string.find(ua, 'Windows') > -1 | |
| bt['isIEWin'] = bt['isIE'] and bt['isWin'] | |
| bt['isIEMac'] = bt['isIE'] and bt['isMac'] | |
| bt['staticHTML'] = False | |
| return bt | |
| def getParentDir(path): | |
| """returns pathname shortened by one""" | |
| return '/'.join(path.split('/')[0:-1]) | |
| def normalizeBibField(bt, underscore=True): | |
| """returns normalised bib type for looking up mappings""" | |
| bt = bt.strip().replace(' ', '-').lower() | |
| if underscore: | |
| bt = bt.replace('_', '-') | |
| return bt | |
| def getBibdataFromDom(dom): | |
| """returns dict with all elements from bib-tag""" | |
| bibinfo = {} | |
| bib = dom.find(".//meta/bib") | |
| if bib is not None: | |
| # put type in @type | |
| type = bib.get('type') | |
| bibinfo['@type'] = normalizeBibField(type) | |
| # put all subelements in dict | |
| for e in bib: | |
| bibinfo[normalizeBibField(e.tag)] = getText(e) | |
| return bibinfo | |
| ## | |
| ## documentViewer class | |
| ## | |
| class documentViewer(Folder): | |
| """document viewer""" | |
| meta_type="Document viewer" | |
| if params: | security=ClassSecurityInfo() |
| return params[0].value | manage_options=Folder.manage_options+( |
| {'label':'main config','action':'changeDocumentViewerForm'}, | |
| ) | |
| def parseUrlTextTool(url): | # templates and forms |
| """parse index meta""" | 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_double = PageTemplateFile('zpt/page_main_double', globals()) | |
| page_main_text = PageTemplateFile('zpt/page_main_text', globals()) | |
| page_main_text_dict = PageTemplateFile('zpt/page_main_text_dict', globals()) | |
| page_main_gis =PageTemplateFile ('zpt/page_main_gis', globals()) | |
| page_main_xml = PageTemplateFile('zpt/page_main_xml', globals()) | |
| page_main_pureXml = PageTemplateFile('zpt/page_main_pureXml', globals()) | |
| head_main = PageTemplateFile('zpt/head_main', globals()) | |
| docuviewer_css = PageTemplateFile('css/docuviewer.css', globals()) | |
| info_xml = PageTemplateFile('zpt/info_xml', globals()) | |
| 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") | thumbs_main_rss = PageTemplateFile('zpt/thumbs_main_rss', globals()) |
| security.declareProtected('View management screens','changeDocumentViewerForm') | |
| changeDocumentViewerForm = PageTemplateFile('zpt/changeDocumentViewer', globals()) | |
| if archivePaths and (len(archivePaths)>0): | |
| archivePath=getTextFromNode(archivePaths[0]) | |
| else: | |
| archivePath=None | |
| 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.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 | |
| 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)) | |
| # proxy text server methods to fulltextclient | |
| def getTextPage(self, **args): | |
| """get page""" | |
| return self.template.fulltextclient.getTextPage(**args) | |
| def getOrigPages(self, **args): | |
| """get page""" | |
| return self.template.fulltextclient.getOrigPages(**args) | |
| def getOrigPagesNorm(self, **args): | |
| """get page""" | |
| return self.template.fulltextclient.getOrigPagesNorm(**args) | |
| def getQuery(self, **args): | |
| """get query in search""" | |
| return self.template.fulltextclient.getQuery(**args) | |
| def getSearch(self, **args): | |
| """get search""" | |
| return self.template.fulltextclient.getSearch(**args) | |
| def getGisPlaces(self, **args): | |
| """get gis places""" | |
| return self.template.fulltextclient.getGisPlaces(**args) | |
| def getAllGisPlaces(self, **args): | |
| """get all gis places """ | |
| return self.template.fulltextclient.getAllGisPlaces(**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 getLemmaQuery(self, **args): | |
| """get query""" | |
| return self.template.fulltextclient.getLemmaQuery(**args) | |
| def getLex(self, **args): | |
| """get lex""" | |
| return self.template.fulltextclient.getLex(**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) | |
| images=dom.xpath("//texttool/image") | |
| if images and (len(images)>0): | security.declareProtected('View','thumbs_rss') |
| image=getTextFromNode(images[0]) | def thumbs_rss(self,mode,url,viewMode="auto",start=None,pn=1): |
| else: | ''' |
| image=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 images (text,images or auto) | |
| if image and archivePath: | ''' |
| image=os.path.join(archivePath,image) | logging.debug("HHHHHHHHHHHHHH:load the rss") |
| image=image.replace("/mpiwg/online",'') | logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
| pt=getParamFromDigilib(image,'pt') | |
| 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) | |
| pageinfo = self.getPageinfo(start=start,current=pn, docinfo=docinfo) | |
| ''' ZDES ''' | |
| pt = getattr(self.template, 'thumbs_main_rss') | |
| if viewMode=="auto": # automodus gewaehlt | |
| if docinfo.has_key("textURL") or docinfo.get('textURLPath',None): #texturl gesetzt und textViewer konfiguriert | |
| viewMode="text" | |
| else: | else: |
| image=None | viewMode="images" |
| viewerUrls=dom.xpath("//texttool/digiliburlprefix") | return pt(docinfo=docinfo,pageinfo=pageinfo,viewMode=viewMode) |
| if viewerUrls and (len(viewerUrls)>0): | |
| viewerUrl=getTextFromNode(viewerUrls[0]) | |
| else: | |
| viewerUrl=None | |
| security.declareProtected('View','index_html') | |
| def index_html(self,url,mode="texttool",viewMode="auto",tocMode="thumbs",start=None,pn=1,mk=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 characterNormalization type of text display (reg, norm, none) | |
| @param querySearch: type of different search modes (fulltext, fulltextMorph, xpath, xquery, ftIndex, ftIndexMorph, fulltextMorphLemma) | |
| ''' | |
| textUrls=dom.xpath("//texttool/text") | logging.debug("documentViewer (index) mode: %s url:%s start:%s pn:%s"%(mode,url,start,pn)) |
| if textUrls and (len(textUrls)>0): | if not hasattr(self, 'template'): |
| textUrl=getTextFromNode(textUrls[0]) | # 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) | |
| # auto viewMode: text_dict if text else images | |
| if viewMode=="auto": | |
| if docinfo.get('textURL', None) or docinfo.get('textURLPath', None): | |
| #texturl gesetzt und textViewer konfiguriert | |
| viewMode="text_dict" | |
| else: | else: |
| textUrl=None | viewMode="images" |
| return viewerUrl,(image,pt),textUrl | |
| class documentViewer(ZopePageTemplate): | |
| """document viewer""" | |
| meta_type="Document viewer" | |
| security=ClassSecurityInfo() | pageinfo = self.getPageinfo(start=start, current=pn, docinfo=docinfo, viewMode=viewMode, tocMode=tocMode) |
| manage_options=ZopePageTemplate.manage_options+( | |
| {'label':'main config','action':'changeDocumentViewerForm'}, | |
| ) | |
| _default_content_fn = os.path.join(package_home(globals()),'zpt','documentViewer_template.zpt') | if viewMode != 'images' and docinfo.get('textURLPath', None): |
| # get full text page | |
| page = self.getTextPage(mode=viewMode, pn=pn, docinfo=docinfo, pageinfo=pageinfo) | |
| pageinfo['textPage'] = page | |
| def __init__(self,id,imageViewerUrl,title=""): | # get template /template/viewer_main |
| """init document viewer""" | pt = getattr(self.template, 'viewer_main') |
| self.id=id | # and execute with parameters |
| self.title=title | return pt(docinfo=docinfo, pageinfo=pageinfo, viewMode=viewMode, mk=self.generateMarks(mk)) |
| 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 generateMarks(self,mk): | |
| ret="" | |
| if mk is None: | |
| return "" | |
| if not isinstance(mk, list): | |
| mk=[mk] | |
| for m in mk: | |
| ret+="mk=%s"%m | |
| return ret | |
| def changeDocumentViewer(self,imageViewerUrl,title="",RESPONSE=None): | |
| """init document viewer""" | |
| self.title=title | |
| self.imageViewerUrl=imageViewerUrl | |
| if RESPONSE is not None: | def getBrowser(self): |
| RESPONSE.redirect('manage_main') | """getBrowser the version of browser """ |
| bt = browserCheck(self) | |
| logging.debug("BROWSER VERSION: %s"%(bt)) | |
| return bt | |
| 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 imageLink(self,nr): | def getLink(self, param=None, val=None, params=None, baseUrl=None, paramSep='&'): |
| """link hinter den images""" | """returns URL to documentviewer with parameter param set to val or from dict params""" |
| paramsTmp=cgi.parse_qs(self.REQUEST['QUERY_STRING']) | # copy existing request params |
| params={} | urlParams=self.REQUEST.form.copy() |
| for x in paramsTmp.iteritems(): | # change single param |
| params[x[0]]=x[1][0] | if param is not None: |
| if val is None: | |
| params['pn']=nr | if urlParams.has_key(param): |
| newUrl=self.REQUEST['URL']+"?"+urllib.urlencode(params) | del urlParams[param] |
| return newUrl | else: |
| urlParams[param] = str(val) | |
| # change more params | |
| if params is not None: | |
| for k in params.keys(): | |
| v = params[k] | |
| if v is None: | |
| # val=None removes param | |
| if urlParams.has_key(k): | |
| del urlParams[k] | |
| def thumbruler(self,cols,rows,start,maximum): | else: |
| """ruler for thumbs""" | urlParams[k] = v |
| ret="" | |
| paramsTmp=cgi.parse_qs(self.REQUEST['QUERY_STRING']) | |
| params={} | |
| for x in paramsTmp.iteritems(): | |
| 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 | |
| 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) | |
| 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 | # FIXME: does this belong here? |
| if urlParams.get("mode", None) == "filepath": #wenn beim erst Aufruf filepath gesetzt wurde aendere das nun zu imagepath | |
| urlParams["mode"] = "imagepath" | |
| urlParams["url"] = getParentDir(urlParams["url"]) | |
| # quote values and assemble into query string (not escaping '/') | |
| ps = paramSep.join(["%s=%s"%(k,urllib.quote_plus(v,'/')) for (k, v) in urlParams.items()]) | |
| #ps = urllib.urlencode(urlParams) | |
| if baseUrl is None: | |
| baseUrl = self.REQUEST['URL1'] | |
| def textToolThumb(self,url,start=0): | url = "%s?%s"%(baseUrl, ps) |
| """understands the texttool format | return url |
| @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) | def getLinkAmp(self, param=None, val=None, params=None, baseUrl=None): |
| return pt(imageUrl=imageUrl,pt=imagepath[1],start=start) | """link to documentviewer with parameter param set to val""" |
| return self.getLink(param, val, params, baseUrl, '&') | |
| 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" | |
| docinfo = self.getDocinfo(mode=mode,url=url) | |
| pt = getattr(self.template, 'info_xml') | |
| return pt(docinfo=docinfo) | |
| def getOptionToggle(self, newState=None, optionName='text_options_open', initialState=True): | |
| """returns new option state""" | |
| if not self.REQUEST.SESSION.has_key(optionName): | |
| # not in session -- initial | |
| opt = {'lastState': newState, 'state': initialState} | |
| else: | |
| opt = self.REQUEST.SESSION.get(optionName) | |
| if opt['lastState'] != newState: | |
| # state in session has changed -- toggle | |
| opt['state'] = not opt['state'] | |
| opt['lastState'] = newState | |
| self.REQUEST.SESSION[optionName] = opt | |
| return opt['state'] | |
| 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() | |
| logging.debug("documentViewer (accessOK) user=%s ip=%s"%(user,self.REQUEST.getClientAddr())) | |
| if user is not None: | |
| #print "user: ", user | |
| return (user.getUserName() != "Anonymous User") | |
| else: | |
| return False | |
| def text(self,mode,url,pn): | logging.error("documentViewer (accessOK) unknown access type %s"%access) |
| """give text""" | return False |
| if mode=="texttool": #index.meta with texttool information | |
| (viewerUrl,imagepath,textpath)=parseUrlTextTool(url) | |
| print textpath | |
| try: | |
| dom = NonvalidatingReader.parseUri(textpath) | |
| except: | |
| return None | |
| list=[] | def getDirinfoFromDigilib(self,path,docinfo=None,cut=0): |
| nodes=dom.xpath("//pb") | """gibt param von dlInfo aus""" |
| if docinfo is None: | |
| docinfo = {} | |
| node=nodes[int(pn)-1] | for x in range(cut): |
| path=getParentDir(path) | |
| p=node | infoUrl=self.digilibBaseUrl+"/dirInfo-xml.jsp?mo=dir&fn="+path |
| while p.tagName!="p": | logging.debug("documentViewer (getparamfromdigilib) dirInfo from %s"%(infoUrl)) |
| p=p.parentNode | |
| txt = getHttpData(infoUrl) | |
| if txt is None: | |
| raise IOError("Unable to get dir-info from %s"%(infoUrl)) | |
| endNode=nodes[int(pn)] | dom = ET.fromstring(txt) |
| #dom = Parse(txt) | |
| size=getText(dom.find("size")) | |
| #sizes=dom.xpath("//dir/size") | |
| logging.debug("documentViewer (getparamfromdigilib) dirInfo:size=%s"%size) | |
| if size: | |
| docinfo['numPages'] = int(size) | |
| else: | |
| docinfo['numPages'] = 0 | |
| e=endNode | # TODO: produce and keep list of image names and numbers |
| while e.tagName!="p": | return docinfo |
| e=e.parentNode | |
| def getIndexMetaPath(self,url): | |
| """gib nur den Pfad zurueck""" | |
| regexp = re.compile(r".*(experimental|permanent)/(.*)") | |
| regpath = regexp.match(url) | |
| if (regpath==None): | |
| return "" | |
| logging.debug("(getDomFromIndexMeta): URLXAXA: %s"%regpath.group(2)) | |
| return ("/mpiwg/online/"+regpath.group(1)+"/"+regpath.group(2)) | |
| next=node.parentNode | |
| #sammle s | |
| while next and (next!=endNode.parentNode): | |
| list.append(next) | |
| next=next.nextSibling | |
| list.append(endNode.parentNode) | |
| if p==e:# beide im selben paragraphen | def getIndexMetaUrl(self,url): |
| """returns utr of index.meta document at url""" | |
| 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" | |
| return metaUrl | |
| def getDomFromIndexMeta(self, url): | |
| """get dom from index meta""" | |
| dom = None | |
| metaUrl = self.getIndexMetaUrl(url) | |
| logging.debug("(getDomFromIndexMeta): METAURL: %s"%metaUrl) | |
| txt=getHttpData(metaUrl) | |
| if txt is None: | |
| raise IOError("Unable to read index meta from %s"%(url)) | |
| dom = ET.fromstring(txt) | |
| #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","") | |
| txt=getHttpData(metaUrl) | |
| if txt is None: | |
| raise IOError("Unable to read infoXMLfrom %s"%(url)) | |
| dom = ET.fromstring(txt) | |
| #dom = Parse(txt) | |
| return dom | |
| 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 | |
| if docinfo is None: | |
| docinfo = {} | |
| if dom is None: | |
| for x in range(cut): | |
| path=getParentDir(path) | |
| dom = self.getDomFromIndexMeta(path) | |
| acc = dom.find(".//access-conditions/access") | |
| if acc is not None: | |
| acctype = acc.get('type') | |
| #acctype = dom.xpath("//access-conditions/access/@type") | |
| if acctype: | |
| access=acctype | |
| if access in ['group', 'institution']: | |
| access = dom.find(".//access-conditions/access/name").text.lower() | |
| docinfo['accessType'] = access | |
| return docinfo | |
| 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.getDomFromIndexMeta(path) | |
| docinfo['indexMetaPath']=self.getIndexMetaPath(path); | |
| logging.debug("documentViewer (getbibinfofromindexmeta cutted) path: %s"%(path)) | |
| # try to get MetaDataFolder | |
| metadata = getattr(self, 'metadata') | |
| if metadata is not None: | |
| # put all raw bib fields in dict "bib" | |
| bib = metadata.getBibdataFromDom(dom) | |
| docinfo['bib'] = bib | |
| bibtype = bib.get('@type', None) | |
| docinfo['bib_type'] = bibtype | |
| # also store DC metadata for convenience | |
| dc = metadata.getDCMappedData(bib) | |
| docinfo['creator'] = dc.get('creator',None) | |
| docinfo['title'] = dc.get('title',None) | |
| docinfo['date'] = dc.get('date',None) | |
| else: | else: |
| next=p | logging.error("MetaDataFolder 'metadata' not found!") |
| while next!=e: | #TODO: remove |
| print next,e | bib = getBibdataFromDom(dom) |
| list.append(next) | return docinfo |
| next=next.nextSibling | |
| # TODO: is this needed? | |
| def getNameFromIndexMeta(self,path,docinfo=None,dom=None,cut=0): | |
| """gets name info from the index.meta file at path or given by dom""" | |
| if docinfo is None: | |
| docinfo = {} | |
| if dom is None: | |
| for x in range(cut): | |
| path=getParentDir(path) | |
| dom = self.getDomFromIndexMeta(path) | |
| docinfo['name']=getText(dom.find("name")) | |
| logging.debug("documentViewer docinfo[name] %s"%docinfo['name']) | |
| return docinfo | |
| 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.getDomFromIndexMeta(url) | |
| for x in list: | archivePath = None |
| PrettyPrint(x) | archiveName = None |
| return list | archiveName = getText(dom.find("name")) |
| if not archiveName: | |
| logging.warning("documentViewer (getdocinfofromtexttool) resource/name missing in: %s" % (url)) | |
| archivePath = getText(dom.find("archive-path")) | |
| if archivePath: | |
| # 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)) | |
| imageDir = getText(dom.find(".//texttool/image")) | |
| if not imageDir: | |
| # 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 | |
| viewerUrl = getText(dom.find(".//texttool/digiliburlprefix")) | |
| if viewerUrl: | |
| docinfo['viewerURL'] = viewerUrl | |
| # old style text URL | |
| textUrl = getText(dom.find(".//texttool/text")) | |
| if textUrl: | |
| 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 | |
| textUrl = getText(dom.find(".//texttool/text-url-path")) | |
| if textUrl: | |
| docinfo['textURLPath'] = textUrl | |
| textUrlkurz = string.split(textUrl, ".")[0] | |
| docinfo['textURLPathkurz'] = textUrlkurz | |
| #if not docinfo['imagePath']: | |
| # text-only, no page images | |
| #docinfo = self.getNumTextPages(docinfo) | |
| presentationUrl = getText(dom.find(".//texttool/presentation")) | |
| docinfo = self.getBibinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get info von bib tag | |
| # TODO: is this needed here? | |
| docinfo = self.getNameFromIndexMeta(url, docinfo=docinfo, dom=dom) | |
| if presentationUrl: # 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 = presentationUrl | |
| if url.endswith("index.meta"): | |
| presentationUrl = url.replace('index.meta', presentationPath) | |
| else: | |
| presentationUrl = url + "/" + presentationPath | |
| def image(self,mode,url,pn): | docinfo = self.getBibinfoFromTextToolPresentation(presentationUrl, docinfo=docinfo, dom=dom) |
| """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 thumbs(self,mode,url,start): | docinfo = self.getAuthinfoFromIndexMeta(url, docinfo=docinfo, dom=dom) # get access info |
| """give thumbs out""" | |
| if mode=="texttool": #index.meta with texttool information | |
| return self.textToolThumb(url,int(start)) | |
| security.declareProtected('View','index_html') | return docinfo |
| def index_html(self,mode,url,start=0,pn=0): | def getBibinfoFromTextToolPresentation(self,url,docinfo=None,dom=None): |
| ''' | """gets the bibliographical information from the preseantion entry in texttools |
| view it | """ |
| @param mode: defines which type of document is behind url | dom=self.getPresentationInfoXML(url) |
| @param url: url which contains display information | docinfo['author']=getText(dom.find(".//author")) |
| ''' | docinfo['title']=getText(dom.find(".//title")) |
| docinfo['year']=getText(dom.find(".//date")) | |
| 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 | |
| #TODO: use getDocinfoFromIndexMeta | |
| #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. keys=%s"%docinfo.keys()) | |
| return docinfo | |
| # new docinfo | |
| docinfo = {'mode': mode, 'url': url} | |
| # add self url | |
| docinfo['viewerUrl'] = self.getDocumentViewerURL() | |
| if mode=="texttool": | |
| # index.meta with texttool information | |
| docinfo = self.getDocinfoFromTextTool(url, docinfo=docinfo) | |
| elif mode=="imagepath": | |
| # folder with images, index.meta optional | |
| docinfo = self.getDocinfoFromImagePath(url, docinfo=docinfo) | |
| elif mode=="filepath": | |
| # filename | |
| 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: keys=%s"%docinfo.keys()) | |
| #logging.debug("documentViewer (getdocinfo) docinfo: %s"%docinfo) | |
| # store in session | |
| 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 | |
| # what does this do? | |
| 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['characterNormalization'] = self.REQUEST.get('characterNormalization','reg') | |
| #pageinfo['optionToggle'] = self.REQUEST.get('optionToggle','1') | |
| 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') | |
| # WTF?: | |
| toc = int(pageinfo['tocPN']) | |
| pageinfo['textPages'] =int(toc) | |
| # What does this do? | |
| 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 | |
| pt=PageTemplateFile(os.path.join(package_home(globals()),'zpt','documentViewer_template.zpt')).__of__(self) | pageinfo['tocPN'] = min(tocPages,toc) |
| return pt(mode=mode,url=url,start=start,pn=pn) | |
| pageinfo['searchPN'] =self.REQUEST.get('searchPN','1') | |
| pageinfo['sn'] =self.REQUEST.get('sn','') | |
| return pageinfo | |
| # security.declareProtected('View management screens','renameImageForm') | 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): | def manage_AddDocumentViewerForm(self): |
| """add the viewer form""" | """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() | return pt() |
| def manage_AddDocumentViewer(self,id,imageViewerUrl="",title="",RESPONSE=None): | def manage_AddDocumentViewer(self,id,imageScalerUrl="",textServerName="",title="",RESPONSE=None): |
| """add the viewer""" | """add the viewer""" |
| newObj=documentViewer(id,imageViewerUrl,title) | 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: |
| RESPONSE.redirect('manage_main') | RESPONSE.redirect('manage_main') |
| ## 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 '' | |